Compare commits

..
Author SHA1 Message Date
github-actions b54e1255ce [version] update
Created by: pukkandan

:ci skip all
2022-01-21 11:57:11 +00:00
pukkandan f20d607b0e Release 2021.01.21 2022-01-21 17:05:45 +05:30
186 changed files with 2851 additions and 7856 deletions
+4 -4
View File
@@ -1,4 +1,4 @@
name: Broken site
name: Broken site support
description: Report broken or misfunctioning site
labels: [triage, site-bug]
body:
@@ -11,7 +11,7 @@ body:
options:
- label: I'm reporting a broken site
required: true
- label: I've verified that I'm running yt-dlp version **2022.03.08**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
- label: I've verified that I'm running yt-dlp version **2022.01.21**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
required: true
- label: I've checked that all provided URLs are alive and playable in a browser
required: true
@@ -51,12 +51,12 @@ body:
[debug] Portable config file: yt-dlp.conf
[debug] Portable config: ['-i']
[debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
[debug] yt-dlp version 2022.03.08 (exe)
[debug] yt-dlp version 2022.01.21 (exe)
[debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
[debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
[debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
[debug] Proxy map: {}
yt-dlp is up to date (2022.03.08)
yt-dlp is up to date (2022.01.21)
<more lines>
render: shell
validations:
@@ -11,7 +11,7 @@ body:
options:
- label: I'm reporting a new site support request
required: true
- label: I've verified that I'm running yt-dlp version **2022.03.08**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
- label: I've verified that I'm running yt-dlp version **2022.01.21**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
required: true
- label: I've checked that all provided URLs are alive and playable in a browser
required: true
@@ -62,12 +62,12 @@ body:
[debug] Portable config file: yt-dlp.conf
[debug] Portable config: ['-i']
[debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
[debug] yt-dlp version 2022.03.08 (exe)
[debug] yt-dlp version 2022.01.21 (exe)
[debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
[debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
[debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
[debug] Proxy map: {}
yt-dlp is up to date (2022.03.08)
yt-dlp is up to date (2022.01.21)
<more lines>
render: shell
validations:
@@ -11,7 +11,7 @@ body:
options:
- label: I'm reporting a site feature request
required: true
- label: I've verified that I'm running yt-dlp version **2022.03.08**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
- label: I've verified that I'm running yt-dlp version **2022.01.21**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
required: true
- label: I've checked that all provided URLs are alive and playable in a browser
required: true
@@ -60,12 +60,12 @@ body:
[debug] Portable config file: yt-dlp.conf
[debug] Portable config: ['-i']
[debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
[debug] yt-dlp version 2022.03.08 (exe)
[debug] yt-dlp version 2022.01.21 (exe)
[debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
[debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
[debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
[debug] Proxy map: {}
yt-dlp is up to date (2022.03.08)
yt-dlp is up to date (2022.01.21)
<more lines>
render: shell
validations:
+3 -3
View File
@@ -11,7 +11,7 @@ body:
options:
- label: I'm reporting a bug unrelated to a specific site
required: true
- label: I've verified that I'm running yt-dlp version **2022.03.08**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
- label: I've verified that I'm running yt-dlp version **2022.01.21**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
required: true
- label: I've checked that all provided URLs are alive and playable in a browser
required: true
@@ -45,12 +45,12 @@ body:
[debug] Portable config file: yt-dlp.conf
[debug] Portable config: ['-i']
[debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
[debug] yt-dlp version 2022.03.08 (exe)
[debug] yt-dlp version 2022.01.21 (exe)
[debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
[debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
[debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
[debug] Proxy map: {}
yt-dlp is up to date (2022.03.08)
yt-dlp is up to date (2022.01.21)
<more lines>
render: shell
validations:
+1 -3
View File
@@ -11,9 +11,7 @@ body:
options:
- label: I'm reporting a feature request
required: true
- label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
required: true
- label: I've verified that I'm running yt-dlp version **2022.03.08**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
- label: I've verified that I'm running yt-dlp version **2022.01.21**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
required: true
- label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
required: true
+1 -2
View File
@@ -25,8 +25,7 @@ body:
Ask your question in an arbitrary form.
Please make sure it's worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
Provide any additional information and as much context and examples as possible.
If your question contains "isn't working" or "can you add", this is most likely the wrong template.
If you are in doubt if this is the right template, use another template!
If your question contains "isn't working" or "can you add", this is most likely the wrong template
placeholder: WRITE QUESTION HERE
validations:
required: true
-3
View File
@@ -3,6 +3,3 @@ contact_links:
- name: Get help from the community on Discord
url: https://discord.gg/H5MNcFW63r
about: Join the yt-dlp Discord for community-powered support!
- name: Matrix Bridge to the Discord server
url: https://matrix.to/#/#yt-dlp:matrix.org
about: For those who do not want to use Discord
@@ -1,4 +1,4 @@
name: Broken site
name: Broken site support
description: Report broken or misfunctioning site
labels: [triage, site-bug]
body:
@@ -11,8 +11,6 @@ body:
options:
- label: I'm reporting a feature request
required: true
- label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
required: true
- label: I've verified that I'm running yt-dlp version **%(version)s**. ([update instructions](https://github.com/yt-dlp/yt-dlp#update))
required: true
- label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+1 -2
View File
@@ -25,8 +25,7 @@ body:
Ask your question in an arbitrary form.
Please make sure it's worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
Provide any additional information and as much context and examples as possible.
If your question contains "isn't working" or "can you add", this is most likely the wrong template.
If you are in doubt if this is the right template, use another template!
If your question contains "isn't working" or "can you add", this is most likely the wrong template
placeholder: WRITE QUESTION HERE
validations:
required: true
+4 -3
View File
@@ -161,10 +161,11 @@ jobs:
steps:
- uses: actions/checkout@v2
# In order to create a universal2 application, the version of python3 in /usr/bin has to be used
# Pyinstaller is pinned to 4.5.1 because the builds are failing in 4.6, 4.7
- name: Install Requirements
run: |
brew install coreutils
/usr/bin/python3 -m pip install -U --user pip Pyinstaller==4.10 -r requirements.txt
/usr/bin/python3 -m pip install -U --user pip Pyinstaller==4.5.1 -r requirements.txt
- name: Bump version
id: bump_version
run: /usr/bin/python3 devscripts/update-version.py
@@ -233,7 +234,7 @@ jobs:
# Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
run: |
python -m pip install --upgrade pip setuptools wheel py2exe
pip install "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-4.10-py3-none-any.whl" -r requirements.txt
pip install "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-4.5.1-py3-none-any.whl" -r requirements.txt
- name: Bump version
id: bump_version
env:
@@ -320,7 +321,7 @@ jobs:
- name: Install Requirements
run: |
python -m pip install --upgrade pip setuptools wheel
pip install "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-4.10-py3-none-any.whl" -r requirements.txt
pip install "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-4.5.1-py3-none-any.whl" -r requirements.txt
- name: Bump version
id: bump_version
env:
+1 -3
View File
@@ -24,7 +24,6 @@ cookies
*.3gp
*.ape
*.ass
*.avi
*.desktop
*.flac
@@ -93,7 +92,7 @@ README.txt
*.tar.gz
*.zsh
*.spec
test/testdata/sigs/player-*.js
test/testdata/player-*.js
# Binary
/youtube-dl
@@ -107,7 +106,6 @@ yt-dlp.zip
*.iml
.vscode
*.sublime-*
*.code-workspace
# Lazy extractors
*/extractor/lazy_extractors.py
+3 -17
View File
@@ -11,7 +11,6 @@
- [Is anyone going to need the feature?](#is-anyone-going-to-need-the-feature)
- [Is your question about yt-dlp?](#is-your-question-about-yt-dlp)
- [Are you willing to share account details if needed?](#are-you-willing-to-share-account-details-if-needed)
- [Is the website primarily used for piracy](#is-the-website-primarily-used-for-piracy)
- [DEVELOPER INSTRUCTIONS](#developer-instructions)
- [Adding new feature or making overarching changes](#adding-new-feature-or-making-overarching-changes)
- [Adding support for a new site](#adding-support-for-a-new-site)
@@ -25,7 +24,6 @@
- [Collapse fallbacks](#collapse-fallbacks)
- [Trailing parentheses](#trailing-parentheses)
- [Use convenience conversion and parsing functions](#use-convenience-conversion-and-parsing-functions)
- [My pull request is labeled pending-fixes](#my-pull-request-is-labeled-pending-fixes)
- [EMBEDDING YT-DLP](README.md#embedding-yt-dlp)
@@ -115,7 +113,7 @@ If the issue is with `youtube-dl` (the upstream fork of yt-dlp) and not with yt-
### Are you willing to share account details if needed?
The maintainers and potential contributors of the project often do not have an account for the website you are asking support for. So any developer interested in solving your issue may ask you for account details. It is your personal discretion whether you are willing to share the account in order for the developer to try and solve your issue. However, if you are unwilling or unable to provide details, they obviously cannot work on the issue and it cannot be solved unless some developer who both has an account and is willing/able to contribute decides to solve it.
The maintainers and potential contributors of the project often do not have an account for the website you are asking support for. So any developer interested in solving your issue may ask you for account details. It is your personal discression whether you are willing to share the account in order for the developer to try and solve your issue. However, if you are unwilling or unable to provide details, they obviously cannot work on the issue and it cannot be solved unless some developer who both has an account and is willing/able to contribute decides to solve it.
By sharing an account with anyone, you agree to bear all risks associated with it. The maintainers and yt-dlp can't be held responsible for any misuse of the credentials.
@@ -125,10 +123,6 @@ While these steps won't necessarily ensure that no misuse of the account takes p
- Change the password before sharing the account to something random (use [this](https://passwordsgenerator.net/) if you don't have a random password generator).
- Change the password after receiving the account back.
### Is the website primarily used for piracy?
We follow [youtube-dl's policy](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free) to not support services that is primarily used for infringing copyright. Additionally, it has been decided to not to support porn sites that specialize in deep fake. We also cannot support any service that serves only [DRM protected content](https://en.wikipedia.org/wiki/Digital_rights_management).
@@ -216,7 +210,7 @@ After you have ensured this site is distributing its content legally, you can fo
}
```
1. Add an import in [`yt_dlp/extractor/extractors.py`](yt_dlp/extractor/extractors.py).
1. Run `python test/test_download.py TestDownload.test_YourExtractor` (note that `YourExtractor` doesn't end with `IE`). This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, the tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. You can also run all the tests in one go with `TestDownload.test_YourExtractor_all`
1. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, the tests will then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. Note that tests with `only_matching` key in test's dict are not counted in. You can also run all the tests in one go with `TestDownload.test_YourExtractor_all`
1. Make sure you have atleast one test for your extractor. Even if all videos covered by the extractor are expected to be inaccessible for automated testing, tests should still be added with a `skip` parameter indicating why the particular test is disabled from running.
1. Have a look at [`yt_dlp/extractor/common.py`](yt_dlp/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should and may return](yt_dlp/extractor/common.py#L91-L426). Add tests and code for as many as you want.
1. Make sure your code follows [yt-dlp coding conventions](#yt-dlp-coding-conventions) and check the code with [flake8](https://flake8.pycqa.org/en/latest/index.html#quickstart):
@@ -258,11 +252,7 @@ For extraction to work yt-dlp relies on metadata your extractor extracts and pro
- `title` (media title)
- `url` (media download URL) or `formats`
The aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken. While all extractors must return a `title`, they must also allow it's extraction to be non-fatal.
For pornographic sites, appropriate `age_limit` must also be returned.
The extractor is allowed to return the info dict without url or formats in some special cases if it allows the user to extract usefull information with `--ignore-no-formats-error` - Eg: when the video is a live stream that has not started yet.
The aforementioned metafields are the critical data that the extraction does not make any sense without and if any of them fail to be extracted then the extractor is considered completely broken. While, in fact, only `id` is technically mandatory, due to compatibility reasons, yt-dlp also treats `title` as mandatory. The extractor is allowed to return the info dict without url or formats in some special cases if it allows the user to extract usefull information with `--ignore-no-formats-error` - Eg: when the video is a live stream that has not started yet.
[Any field](yt_dlp/extractor/common.py#219-L426) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
@@ -664,10 +654,6 @@ duration = float_or_none(video.get('durationMs'), scale=1000)
view_count = int_or_none(video.get('views'))
```
# My pull request is labeled pending-fixes
The `pending-fixes` label is added when there are changes requested to a PR. When the necessary changes are made, the label should be removed. However, despite our best efforts, it may sometimes happen that the maintainer did not see the changes or forgot to remove the label. If your PR is still marked as `pending-fixes` a few days after all requested changes have been made, feel free to ping the maintainer who labeled your issue and ask them to re-review and remove the label.
+2 -26
View File
@@ -146,7 +146,7 @@ chio0hai
cntrl-s
Deer-Spangle
DEvmIb
Grabien/MaximVol
Grabien
j54vc1bk
mpeter50
mrpapersonic
@@ -160,7 +160,7 @@ PilzAdam
zmousm
iw0nderhow
unit193
TwoThousandHedgehogs/KathrynElrod
TwoThousandHedgehogs
Jertzukka
cypheron
Hyeeji
@@ -190,27 +190,3 @@ CreaValix
sian1468
arkamar
hyano
KiberInfinity
tejing1
Bricio
lazypete365
Aniruddh-J
blackgear
CplPwnies
cyberfox1691
FestplattenSchnitzel
hatienl0i261299
iphoting
jakeogh
lukasfink1
lyz-code
marieell
mdpauley
Mipsters
mxmehl
ofkz
P-reducible
pycabbage
regarten
Ronnnny
schn0sch
+1 -194
View File
@@ -11,200 +11,7 @@
-->
### 2022.03.08
* Merge youtube-dl: Upto [commit/6508688](https://github.com/ytdl-org/youtube-dl/commit/6508688e88c83bb811653083db9351702cd39a6a) (except NDR)
* Add regex operator and quoting to format filters by [lukasfink1](https://github.com/lukasfink1)
* Add brotli content-encoding support by [coletdjnz](https://github.com/coletdjnz)
* Add pre-processor stage `after_filter`
* Better error message when no `--live-from-start` format
* Create necessary directories for `--print-to-file`
* Fill more fields for playlists by [Lesmiscore](https://github.com/Lesmiscore)
* Fix `-all` for `--sub-langs`
* Fix doubling of `video_id` in `ExtractorError`
* Fix for when stdout/stderr encoding is `None`
* Handle negative duration from extractor
* Implement `--add-header` without modifying `std_headers`
* Obey `--abort-on-error` for "ffmpeg not installed"
* Set `webpage_url_...` from `webpage_url` and not input URL
* Tolerate failure to `--write-link` due to unknown URL
* [aria2c] Add `--http-accept-gzip=true`
* [build] Update pyinstaller to 4.10 by [shirt-dev](https://github.com/shirt-dev)
* [cookies] Update MacOS12 `Cookies.binarycookies` location by [mdpauley](https://github.com/mdpauley)
* [devscripts] Improve `prepare_manpage`
* [downloader] Do not use aria2c for non-native `m3u8`
* [downloader] Obey `--file-access-retries` when deleting/renaming by [ehoogeveen-medweb](https://github.com/ehoogeveen-medweb)
* [extractor] Allow `http_headers` to be specified for `thumbnails`
* [extractor] Extract subtitles from manifests for vimeo, globo, kaltura, svt by [fstirlitz](https://github.com/fstirlitz)
* [extractor] Fix for manifests without period duration by [dirkf,](https://github.com/dirkf,) [pukkandan](https://github.com/pukkandan)
* [extractor] Support `--mark-watched` without `_NETRC_MACHINE` by [coletdjnz](https://github.com/coletdjnz)
* [FFmpegConcat] Abort on `--simulate`
* [FormatSort] Consider `acodec`=`ogg` as `vorbis`
* [fragment] Fix bugs around resuming with Range by [Lesmiscore](https://github.com/Lesmiscore)
* [fragment] Improve `--live-from-start` for YouTube livestreams by [Lesmiscore](https://github.com/Lesmiscore)
* [generic] Pass referer to extracted formats
* [generic] Set rss `guid` as video id by [Bricio](https://github.com/Bricio)
* [options] Better ambiguous option resolution
* [options] Rename `--clean-infojson` to `--clean-info-json`
* [SponsorBlock] Fixes for highlight and "full video labels" by [nihil-admirari](https://github.com/nihil-admirari)
* [Sponsorblock] minor fixes by [nihil-admirari](https://github.com/nihil-admirari)
* [utils] Better traceback for `ExtractorError`
* [utils] Fix file locking for AOSP by [jakeogh](https://github.com/jakeogh)
* [utils] Improve file locking
* [utils] OnDemandPagedList: Do not download pages after error
* [utils] render_table: Fix character calculation for removing extra gap by [Lesmiscore](https://github.com/Lesmiscore)
* [utils] Use `locked_file` for `sanitize_open` by [jakeogh](https://github.com/jakeogh)
* [utils] Validate `DateRange` input
* [utils] WebSockets wrapper for non-async functions by [Lesmiscore](https://github.com/Lesmiscore)
* [cleanup] Don't pass protocol to `_extract_m3u8_formats` for live videos
* [cleanup] Remove extractors for some dead websites by [marieell](https://github.com/marieell)
* [cleanup, docs] Misc cleanup
* [AbemaTV] Add extractors by [Lesmiscore](https://github.com/Lesmiscore)
* [adobepass] Add Suddenlink MSO by [CplPwnies](https://github.com/CplPwnies)
* [ant1newsgr] Add extractor by [zmousm](https://github.com/zmousm)
* [bigo] Add extractor by [Lesmiscore](https://github.com/Lesmiscore)
* [Caltrans] Add extractor by [Bricio](https://github.com/Bricio)
* [daystar] Add extractor by [hatienl0i261299](https://github.com/hatienl0i261299)
* [fc2:live] Add extractor by [Lesmiscore](https://github.com/Lesmiscore)
* [fptplay] Add extractor by [hatienl0i261299](https://github.com/hatienl0i261299)
* [murrtube] Add extractor by [cyberfox1691](https://github.com/cyberfox1691)
* [nfb] Add extractor by [ofkz](https://github.com/ofkz)
* [niconico] Add playlist extractors and refactor by [Lesmiscore](https://github.com/Lesmiscore)
* [peekvids] Add extractor by [schn0sch](https://github.com/schn0sch)
* [piapro] Add extractor by [pycabbage,](https://github.com/pycabbage,) [Lesmiscore](https://github.com/Lesmiscore)
* [rokfin] Add extractor by [P-reducible,](https://github.com/P-reducible,) [pukkandan](https://github.com/pukkandan)
* [rokfin] Add stack and channel extractors by [P-reducible,](https://github.com/P-reducible,) [pukkandan](https://github.com/pukkandan)
* [ruv.is] Add extractor by [iw0nderhow](https://github.com/iw0nderhow)
* [telegram] Add extractor by [hatienl0i261299](https://github.com/hatienl0i261299)
* [VideocampusSachsen] Add extractors by [FestplattenSchnitzel](https://github.com/FestplattenSchnitzel)
* [xinpianchang] Add extractor by [hatienl0i261299](https://github.com/hatienl0i261299)
* [abc] Support 1080p by [Ronnnny](https://github.com/Ronnnny)
* [afreecatv] Support password-protected livestreams by [wlritchi](https://github.com/wlritchi)
* [ard] Fix valid URL
* [ATVAt] Detect geo-restriction by [marieell](https://github.com/marieell)
* [bandcamp] Detect acodec
* [bandcamp] Fix user URLs by [lyz-code](https://github.com/lyz-code)
* [bbc] Fix extraction of news articles by [ajj8](https://github.com/ajj8)
* [beeg] Fix extractor by [Bricio](https://github.com/Bricio)
* [bigo] Fix extractor to not to use `form_params`
* [Bilibili] Pass referer for all formats by [blackgear](https://github.com/blackgear)
* [Biqle] Fix extractor by [Bricio](https://github.com/Bricio)
* [ccma] Fix timestamp parsing by [nyuszika7h](https://github.com/nyuszika7h)
* [crunchyroll] Better error reporting on login failure by [tejing1](https://github.com/tejing1)
* [cspan] Support of C-Span congress videos by [Grabien](https://github.com/Grabien)
* [dropbox] fix regex by [zenerdi0de](https://github.com/zenerdi0de)
* [fc2] Fix extraction by [Lesmiscore](https://github.com/Lesmiscore)
* [fujitv] Extract resolution for free sources by [YuenSzeHong](https://github.com/YuenSzeHong)
* [Gettr] Add `GettrStreamingIE` by [i6t](https://github.com/i6t)
* [Gettr] Fix formats order by [i6t](https://github.com/i6t)
* [Gettr] Improve extractor by [i6t](https://github.com/i6t)
* [globo] Expand valid URL by [Bricio](https://github.com/Bricio)
* [lbry] Fix `--ignore-no-formats-error`
* [manyvids] Extract `uploader` by [regarten](https://github.com/regarten)
* [mildom] Fix linter
* [mildom] Rework extractors by [Lesmiscore](https://github.com/Lesmiscore)
* [mirrativ] Cleanup extractor code by [Lesmiscore](https://github.com/Lesmiscore)
* [nhk] Add support for NHK for School by [Lesmiscore](https://github.com/Lesmiscore)
* [niconico:tag] Add support for searching tags
* [nrk] Add fallback API
* [peekvids] Use JSON-LD by [schn0sch](https://github.com/schn0sch)
* [peertube] Add media.fsfe.org by [mxmehl](https://github.com/mxmehl)
* [rtvs] Fix extractor by [Bricio](https://github.com/Bricio)
* [spiegel] Fix `_VALID_URL`
* [ThumbnailsConvertor] Support `webp`
* [tiktok] Fix `vm.tiktok`/`vt.tiktok` URLs
* [tubitv] Fix/improve TV series extraction by [bbepis](https://github.com/bbepis)
* [tumblr] Fix extractor by [foghawk](https://github.com/foghawk)
* [twitcasting] Add fallback for finding running live by [Lesmiscore](https://github.com/Lesmiscore)
* [TwitCasting] Check for password protection by [Lesmiscore](https://github.com/Lesmiscore)
* [twitcasting] Fix extraction by [Lesmiscore](https://github.com/Lesmiscore)
* [twitch] Fix field name of `view_count`
* [twitter] Fix for private videos by [iphoting](https://github.com/iphoting)
* [washingtonpost] Fix extractor by [Bricio](https://github.com/Bricio)
* [youtube:tab] Add `approximate_date` extractor-arg
* [youtube:tab] Follow redirect to regional channel by [coletdjnz](https://github.com/coletdjnz)
* [youtube:tab] Reject webpage data if redirected to home page
* [youtube] De-prioritize potentially damaged formats
* [youtube] Differentiate descriptive audio by language code
* [youtube] Ensure subtitle urls are absolute by [coletdjnz](https://github.com/coletdjnz)
* [youtube] Escape possible `$` in `_extract_n_function_name` regex by [Lesmiscore](https://github.com/Lesmiscore)
* [youtube] Fix automatic captions
* [youtube] Fix n-sig extraction for phone player JS by [MinePlayersPE](https://github.com/MinePlayersPE)
* [youtube] Further de-prioritize 3gp format
* [youtube] Label original auto-subs
* [youtube] Prefer UTC upload date for videos by [coletdjnz](https://github.com/coletdjnz)
* [zaq1] Remove dead extractor by [marieell](https://github.com/marieell)
* [zee5] Support web-series by [Aniruddh-J](https://github.com/Aniruddh-J)
* [zingmp3] Fix extractor by [hatienl0i261299](https://github.com/hatienl0i261299)
* [zoom] Add support for screen cast by [Mipsters](https://github.com/Mipsters)
### 2022.02.04
* [youtube:search] Fix extractor by [coletdjnz](https://github.com/coletdjnz)
* [youtube:search] Add tests
* [twitcasting] Enforce UTF-8 for POST payload by [Lesmiscore](https://github.com/Lesmiscore)
* [mediaset] Fix extractor by [nixxo](https://github.com/nixxo)
* [websocket] Make syntax error in `websockets` module non-fatal
### 2022.02.03
* Merge youtube-dl: Upto [commit/78ce962](https://github.com/ytdl-org/youtube-dl/commit/78ce962f4fe020994c216dd2671546fbe58a5c67)
* Add option `--print-to-file`
* Make nested --config-locations relative to parent file
* Ensure `_type` is present in `info.json`
* Fix `--compat-options list-formats`
* Fix/improve `InAdvancePagedList`
* [downloader/ffmpeg] Handle unknown formats better
* [outtmpl] Handle `-o ""` better
* [outtmpl] Handle hard-coded file extension better
* [extractor] Add convinience function `_yes_playlist`
* [extractor] Allow non-fatal `title` extraction
* [extractor] Extract video inside `Article` json_ld
* [generic] Allow further processing of json_ld URL
* [cookies] Fix keyring selection for unsupported desktops
* [utils] Strip double spaces in `clean_html` by [dirkf](https://github.com/dirkf)
* [aes] Add `unpad_pkcs7`
* [test] Fix `test_youtube_playlist_noplaylist`
* [docs,cleanup] Misc cleanup
* [dplay] Add extractors for site changes by [Sipherdrakon](https://github.com/Sipherdrakon)
* [ertgr] Add extractors by [zmousm](https://github.com/zmousm), [dirkf](https://github.com/dirkf)
* [Musicdex] Add extractors by [Ashish0804](https://github.com/Ashish0804)
* [YandexVideoPreview] Add extractor by [KiberInfinity](https://github.com/KiberInfinity)
* [youtube] Add extractor `YoutubeMusicSearchURLIE`
* [archive.org] Ignore unnecessary files
* [Bilibili] Add 8k support by [u-spec-png](https://github.com/u-spec-png)
* [bilibili] Fix extractor, make anthology title non-fatal
* [CAM4] Add thumbnail extraction by [alerikaisattera](https://github.com/alerikaisattera)
* [cctv] De-prioritize sample format
* [crunchyroll:beta] Add cookies support by [tejing1](https://github.com/tejing1)
* [crunchyroll] Fix login by [tejing1](https://github.com/tejing1)
* [doodstream] Fix extractor
* [fc2] Fix extraction by [Lesmiscore](https://github.com/Lesmiscore)
* [FFmpegConcat] Abort on --skip-download and download errors
* [Fujitv] Extract metadata and support premium by [YuenSzeHong](https://github.com/YuenSzeHong)
* [globo] Fix extractor by [Bricio](https://github.com/Bricio)
* [glomex] Simplify embed detection
* [GoogleSearch] Fix extractor
* [Instagram] Fix extraction when logged in by [MinePlayersPE](https://github.com/MinePlayersPE)
* [iq.com] Add VIP support by [MinePlayersPE](https://github.com/MinePlayersPE)
* [mildom] Fix extractor by [lazypete365](https://github.com/lazypete365)
* [MySpass] Fix video url processing by [trassshhub](https://github.com/trassshhub)
* [Odnoklassniki] Improve embedded players extraction by [KiberInfinity](https://github.com/KiberInfinity)
* [orf:tvthek] Lazy playlist extraction and obey --no-playlist
* [Pladform] Fix redirection to external player by [KiberInfinity](https://github.com/KiberInfinity)
* [ThisOldHouse] Improve Premium URL check by [Ashish0804](https://github.com/Ashish0804)
* [TikTok] Iterate through app versions by [MinePlayersPE](https://github.com/MinePlayersPE)
* [tumblr] Fix 403 errors and handle vimeo embeds by [foghawk](https://github.com/foghawk)
* [viki] Fix "Bad request" for manifest by [nyuszika7h](https://github.com/nyuszika7h)
* [Vimm] add recording extractor by [alerikaisattera](https://github.com/alerikaisattera)
* [web.archive:youtube] Add `ytarchive:` prefix and misc cleanup
* [youtube:api] Do not use seek when reading HTTPError response by [coletdjnz](https://github.com/coletdjnz)
* [youtube] Fix n-sig for player e06dea74
* [youtube, cleanup] Misc fixes and cleanup
### 2022.01.21
### 2021.01.21
* Add option `--concat-playlist` to **concat videos in a playlist**
* Allow **multiple and nested configuration files**
+2 -2
View File
@@ -14,9 +14,9 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites com
.PHONY: all clean install test tar pypi-files completions ot offlinetest codetest supportedsites
clean-test:
rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
rm -rf test/testdata/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
*.3gp *.ape *.ass *.avi *.desktop *.flac *.flv *.jpeg *.jpg *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 \
*.3gp *.ape *.avi *.desktop *.flac *.flv *.jpeg *.jpg *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 \
*.mp4 *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
clean-dist:
rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
+53 -83
View File
@@ -71,7 +71,7 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
# NEW FEATURES
* Based on **youtube-dl 2021.12.17 [commit/5add3f4](https://github.com/ytdl-org/youtube-dl/commit/5add3f4373287e6346ca3551239edab549284db3)** and **youtube-dlc 2020.11.11-3 [commit/f9401f2](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee)**: You get all the features and patches of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) in addition to the latest [youtube-dl](https://github.com/ytdl-org/youtube-dl)
* Based on **youtube-dl 2021.12.17 [commit/5014bd6](https://github.com/ytdl-org/youtube-dl/commit/5014bd67c22b421207b2650d4dc874b95b36dda1)** and **youtube-dlc 2020.11.11-3 [commit/f9401f2](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee)**: You get all the features and patches of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) in addition to the latest [youtube-dl](https://github.com/ytdl-org/youtube-dl)
* **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in youtube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
@@ -112,7 +112,7 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
* **Other new options**: Many new options have been added such as `--concat-playlist`, `--print`, `--wait-for-video`, `--sleep-requests`, `--convert-thumbnails`, `--write-link`, `--force-download-archive`, `--force-overwrites`, `--break-on-reject` etc
* **Improvements**: Regex and other operators in `--format`/`--match-filter`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc
* **Improvements**: Regex and other operators in `--match-filter`, multiple `--postprocessor-args` and `--downloader-args`, faster archive checking, more [format selection options](#format-selection), merge multi-video/audio, multiple `--config-locations`, `--exec` at different stages, etc
* **Plugins**: Extractors and PostProcessors can be loaded from an external file. See [plugins](#plugins) for details
@@ -130,7 +130,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
* The default [format sorting](#sorting-formats) is different from youtube-dl and prefers higher resolution and better codecs rather than higher bitrates. You can use the `--format-sort` option to change this to any order you prefer, or use `--compat-options format-sort` to use youtube-dl's sorting order
* The default format selector is `bv*+ba/b`. This means that if a combined video + audio format that is better than the best video-only format is found, the former will be preferred. Use `-f bv+ba/b` or `--compat-options format-spec` to revert this
* Unlike youtube-dlc, yt-dlp does not allow merging multiple audio/video streams into one file by default (since this conflicts with the use of `-f bv*+ba`). If needed, this feature must be enabled using `--audio-multistreams` and `--video-multistreams`. You can also use `--compat-options multistreams` to enable both
* `--no-abort-on-error` is enabled by default. Use `--abort-on-error` or `--compat-options abort-on-error` to abort on errors instead
* `--ignore-errors` is enabled by default. Use `--abort-on-error` or `--compat-options abort-on-error` to abort on errors instead
* When writing metadata files such as thumbnails, description or infojson, the same information (if available) is also written for playlists. Use `--no-write-playlist-metafiles` or `--compat-options no-playlist-metafiles` to not write these files
* `--add-metadata` attaches the `infojson` to `mkv` files in addition to writing the metadata when used with `--write-info-json`. Use `--no-embed-info-json` or `--compat-options no-attach-info-json` to revert this
* Some metadata are embedded into different fields when using `--add-metadata` as compared to youtube-dl. Most notably, `comment` field contains the `webpage_url` and `synopsis` contains the `description`. You can [use `--parse-metadata`](#modifying-metadata) to modify this to your liking or use `--compat-options embed-metadata` to revert this
@@ -267,8 +267,7 @@ While all the other dependencies are optional, `ffmpeg` and `ffprobe` are highly
* [**pycryptodomex**](https://github.com/Legrandin/pycryptodome) - For decrypting AES-128 HLS streams and various other data. Licensed under [BSD2](https://github.com/Legrandin/pycryptodome/blob/master/LICENSE.rst)
* [**websockets**](https://github.com/aaugustin/websockets) - For downloading over websocket. Licensed under [BSD3](https://github.com/aaugustin/websockets/blob/main/LICENSE)
* [**secretstorage**](https://github.com/mitya57/secretstorage) - For accessing the Gnome keyring while decrypting cookies of Chromium-based browsers on Linux. Licensed under [BSD](https://github.com/mitya57/secretstorage/blob/master/LICENSE)
* [**AtomicParsley**](https://github.com/wez/atomicparsley) - For embedding thumbnail in mp4/m4a if mutagen/ffmpeg cannot. Licensed under [GPLv2+](https://github.com/wez/atomicparsley/blob/master/COPYING)
* [**brotli**](https://github.com/google/brotli) or [**brotlicffi**](https://github.com/python-hyper/brotlicffi) - [Brotli](https://en.wikipedia.org/wiki/Brotli) content encoding support. Both licensed under MIT <sup>[1](https://github.com/google/brotli/blob/master/LICENSE) [2](https://github.com/python-hyper/brotlicffi/blob/master/LICENSE) </sup>
* [**AtomicParsley**](https://github.com/wez/atomicparsley) - For embedding thumbnail in mp4/m4a if mutagen is not present. Licensed under [GPLv2+](https://github.com/wez/atomicparsley/blob/master/COPYING)
* [**rtmpdump**](http://rtmpdump.mplayerhq.hu) - For downloading `rtmp` streams. ffmpeg will be used as a fallback. Licensed under [GPLv2+](http://rtmpdump.mplayerhq.hu)
* [**mplayer**](http://mplayerhq.hu/design7/info.html) or [**mpv**](https://mpv.io) - For downloading `rstp` streams. ffmpeg will be used as a fallback. Licensed under [GPLv2+](https://github.com/mpv-player/mpv/blob/master/Copyright)
* [**phantomjs**](https://github.com/ariya/phantomjs) - Used in extractors where javascript needs to be run. Licensed under [BSD3](https://github.com/ariya/phantomjs/blob/master/LICENSE.BSD)
@@ -279,14 +278,13 @@ To use or redistribute the dependencies, you must agree to their respective lice
The Windows and MacOS standalone release binaries are already built with the python interpreter, mutagen, pycryptodomex and websockets included.
<!-- TODO: ffmpeg has merged this patch. Remove this note once there is new release -->
**Note**: There are some regressions in newer ffmpeg versions that causes various issues when used alongside yt-dlp. Since ffmpeg is such an important dependency, we provide [custom builds](https://github.com/yt-dlp/FFmpeg-Builds#ffmpeg-static-auto-builds) with patches for these issues at [yt-dlp/FFmpeg-Builds](https://github.com/yt-dlp/FFmpeg-Builds). See [the readme](https://github.com/yt-dlp/FFmpeg-Builds#patches-applied) for details on the specific issues solved by these builds
## COMPILE
**For Windows**:
To build the Windows executable, you must have pyinstaller (and any of yt-dlp's optional dependencies if needed). Once you have all the necessary dependencies installed, (optionally) build lazy extractors using `devscripts/make_lazy_extractors.py`, and then just run `pyinst.py`. The executable will be built for the same architecture (32/64 bit) as the python used to build it.
To build the Windows executable, you must have pyinstaller (and optionally mutagen, pycryptodomex, websockets). Once you have all the necessary dependencies installed, (optionally) build lazy extractors using `devscripts/make_lazy_extractors.py`, and then just run `pyinst.py`. The executable will be built for the same architecture (32/64 bit) as the python used to build it.
py -m pip install -U pyinstaller -r requirements.txt
py devscripts/make_lazy_extractors.py
@@ -381,9 +379,8 @@ You can also fork the project on github and run your fork's [build workflow](.gi
--proxy URL Use the specified HTTP/HTTPS/SOCKS proxy.
To enable SOCKS proxy, specify a proper
scheme. For example
socks5://user:pass@127.0.0.1:1080/. Pass in
an empty string (--proxy "") for direct
connection
socks5://127.0.0.1:1080/. Pass in an empty
string (--proxy "") for direct connection
--socket-timeout SECONDS Time to wait before giving up, in seconds
--source-address IP Client-side IP address to bind to
-4, --force-ipv4 Make all connections via IPv4
@@ -396,7 +393,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
option is not present) is used for the
actual downloading
--geo-bypass Bypass geographic restriction via faking
X-Forwarded-For HTTP header (default)
X-Forwarded-For HTTP header
--no-geo-bypass Do not bypass geographic restriction via
faking X-Forwarded-For HTTP header
--geo-bypass-country CODE Force bypass geographic restriction with
@@ -607,11 +604,11 @@ You can also fork the project on github and run your fork's [build workflow](.gi
--write-description etc. (default)
--no-write-playlist-metafiles Do not write playlist metadata when using
--write-info-json, --write-description etc.
--clean-info-json Remove some private fields such as
--clean-infojson Remove some private fields such as
filenames from the infojson. Note that it
could still contain some personal
information (default)
--no-clean-info-json Write all fields to the infojson
--no-clean-infojson Write all fields to the infojson
--write-comments Retrieve video comments to be placed in the
infojson. The comments are fetched even
without this option if the extraction is
@@ -689,12 +686,6 @@ You can also fork the project on github and run your fork's [build workflow](.gi
Implies --quiet and --simulate (unless
--no-simulate is used). This option can be
used multiple times
--print-to-file [WHEN:]TEMPLATE FILE
Append given template to the file. The
values of WHEN and TEMPLATE are same as
that of --print. FILE uses the same syntax
as the output template. This option can be
used multiple times
-j, --dump-json Quiet, but print JSON information for each
video. Simulate unless --no-simulate is
used. See "OUTPUT TEMPLATE" for a
@@ -739,6 +730,9 @@ You can also fork the project on github and run your fork's [build workflow](.gi
--prefer-insecure Use an unencrypted connection to retrieve
information about the video (Currently
supported only for YouTube)
--user-agent UA Specify a custom user agent
--referer URL Specify a custom referer, use if the video
access is restricted to one domain
--add-header FIELD:VALUE Specify a custom HTTP header and its value,
separated by a colon ":". You can use this
option multiple times
@@ -950,7 +944,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
(currently supported: srt|vtt|ass|lrc)
(Alias: --convert-subtitles)
--convert-thumbnails FORMAT Convert the thumbnails to another format
(currently supported: jpg|png|webp)
(currently supported: jpg|png)
--split-chapters Split video into multiple files based on
internal chapters. The "chapter:" prefix
can be used with "--paths" and "--output"
@@ -981,17 +975,15 @@ You can also fork the project on github and run your fork's [build workflow](.gi
semicolon ";" delimited list of NAME=VALUE.
The "when" argument determines when the
postprocessor is invoked. It can be one of
"pre_process" (after video extraction),
"after_filter" (after video passes filter),
"before_dl" (before each video download),
"post_process" (after each video download;
default), "after_move" (after moving video
file to it's final locations),
"after_video" (after downloading and
processing all formats of a video), or
"playlist" (at end of playlist). This
option can be used multiple times to add
different postprocessors
"pre_process" (after extraction),
"before_dl" (before video download),
"post_process" (after video download;
default), "after_move" (after moving file
to their final locations), "after_video"
(after downloading and processing all
formats of a video), or "playlist" (end of
playlist). This option can be used multiple
times to add different postprocessors
## SponsorBlock Options:
Make chapter entries for, or remove various segments (sponsor,
@@ -1051,7 +1043,7 @@ You can configure yt-dlp by placing any supported command line option to a confi
1. **Main Configuration**: The file given by `--config-location`
1. **Portable Configuration**: `yt-dlp.conf` in the same directory as the bundled binary. If you are running from source-code (`<root dir>/yt_dlp/__main__.py`), the root directory is used instead.
1. **Home Configuration**: `yt-dlp.conf` in the home path given by `-P`, or in the current directory if no such path is given
1. **Home Configuration**: `yt-dlp.conf` in the home path given by `-P "home:<path>"`, or in the current directory if no such path is given
1. **User Configuration**:
* `%XDG_CONFIG_HOME%/yt-dlp/config` (recommended on Linux/macOS)
* `%XDG_CONFIG_HOME%/yt-dlp.conf`
@@ -1138,13 +1130,12 @@ To summarize, the general syntax for a field is:
%(name[.keys][addition][>strf][,alternate][&replacement][|default])[flags][width][.precision][length]type
```
Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon `:`. The different file types supported are `subtitle`, `thumbnail`, `description`, `annotation` (deprecated), `infojson`, `link`, `pl_thumbnail`, `pl_description`, `pl_infojson`, `chapter`, `pl_video`. For example, `-o "%(title)s.%(ext)s" -o "thumbnail:%(title)s\%(title)s.%(ext)s"` will put the thumbnails in a folder with the same name as the video. If any of the templates is empty, that type of file will not be written. Eg: `--write-thumbnail -o "thumbnail:"` will write thumbnails only for playlists and not for video.
Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon `:`. The different file types supported are `subtitle`, `thumbnail`, `description`, `annotation` (deprecated), `infojson`, `link`, `pl_thumbnail`, `pl_description`, `pl_infojson`, `chapter`, `pl_video`. For example, `-o "%(title)s.%(ext)s" -o "thumbnail:%(title)s\%(title)s.%(ext)s"` will put the thumbnails in a folder with the same name as the video. If any of the templates (except default) is empty, that type of file will not be written. Eg: `--write-thumbnail -o "thumbnail:"` will write thumbnails only for playlists and not for video.
The available fields are:
- `id` (string): Video identifier
- `title` (string): Video title
- `fulltitle` (string): Video title ignoring live timestamp and generic title
- `url` (string): Video URL
- `ext` (string): Video filename extension
- `alt_title` (string): A secondary title of the video
@@ -1200,16 +1191,16 @@ The available fields are:
- `protocol` (string): The protocol that will be used for the actual download
- `extractor` (string): Name of the extractor
- `extractor_key` (string): Key name of the extractor
- `epoch` (numeric): Unix epoch of when the information extraction was completed
- `epoch` (numeric): Unix epoch when creating the file
- `autonumber` (numeric): Number that will be increased with each download, starting at `--autonumber-start`
- `video_autonumber` (numeric): Number that will be increased with each video
- `n_entries` (numeric): Total number of extracted items in the playlist
- `playlist_id` (string): Identifier of the playlist that contains the video
- `playlist_title` (string): Name of the playlist that contains the video
- `playlist` (string): `playlist_id` or `playlist_title`
- `playlist` (string): Name or id of the playlist that contains the video
- `playlist_count` (numeric): Total number of items in the playlist. May not be known if entire playlist is not extracted
- `playlist_index` (numeric): Index of the video in the playlist padded with leading zeros according the final index
- `playlist_autonumber` (numeric): Position of the video in the playlist download queue padded with leading zeros according to the total length of the playlist
- `playlist_id` (string): Playlist identifier
- `playlist_title` (string): Playlist title
- `playlist_uploader` (string): Full name of the playlist uploader
- `playlist_uploader_id` (string): Nickname or id of the playlist uploader
- `webpage_url` (string): A URL to the video webpage which if given to yt-dlp should allow to get the same result again
@@ -1400,7 +1391,7 @@ The following numeric meta fields can be used with comparisons `<`, `<=`, `>`, `
- `asr`: Audio sampling rate in Hertz
- `fps`: Frame rate
Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains), `~=` (matches regex) and following string meta fields:
Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends with), `*=` (contains) and following string meta fields:
- `ext`: File extension
- `acodec`: Name of the audio codec in use
@@ -1410,7 +1401,7 @@ Also filtering work for comparisons `=` (equals), `^=` (starts with), `$=` (ends
- `format_id`: A short description of the format
- `language`: Language code
Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). The comparand of a string comparison needs to be quoted with either double or single quotes if it contains spaces or special characters other than `._-`.
Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain).
Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering.
@@ -1553,9 +1544,8 @@ $ yt-dlp -S "proto"
# Download the best video with either h264 or h265 codec,
# or the best video if there is no such video
$ yt-dlp -f "(bv*[vcodec~='^((he|a)vc|h26[45])']+ba) / (bv*+ba/b)"
# Download the best video with h264 codec, or the best video if there is no such video
$ yt-dlp -f "(bv*+ba/b)[vcodec^=avc1] / (bv*+ba/b)"
# Download the best video with best codec no better than h264,
# or the best video with worst codec if there is no such video
@@ -1600,28 +1590,25 @@ This option also has a few special uses:
* You can download an additional URL based on the metadata of the currently downloaded video. To do this, set the field `additional_urls` to the URL that you want to download. Eg: `--parse-metadata "description:(?P<additional_urls>https?://www\.vimeo\.com/\d+)` will download the first vimeo video found in the description
* You can use this to change the metadata that is embedded in the media file. To do this, set the value of the corresponding field with a `meta_` prefix. For example, any value you set to `meta_description` field will be added to the `description` field in the file. For example, you can use this to set a different "description" and "synopsis". To modify the metadata of individual streams, use the `meta<n>_` prefix (Eg: `meta1_language`). Any value set to the `meta_` field will overwrite all default values.
**Note**: Metadata modification happens before format selection, post-extraction and other post-processing operations. Some fields may be added or changed during these steps, overriding your changes.
For reference, these are the fields yt-dlp adds by default to the file metadata:
Metadata fields | From
:--------------------------|:------------------------------------------------
`title` | `track` or `title`
`date` | `upload_date`
`description`, `synopsis` | `description`
`purl`, `comment` | `webpage_url`
`track` | `track_number`
`artist` | `artist`, `creator`, `uploader` or `uploader_id`
`genre` | `genre`
`album` | `album`
`album_artist` | `album_artist`
`disc` | `disc_number`
`show` | `series`
`season_number` | `season_number`
`episode_id` | `episode` or `episode_id`
`episode_sort` | `episode_number`
`language` of each stream | the format's `language`
Metadata fields|From
:---|:---
`title`|`track` or `title`
`date`|`upload_date`
`description`, `synopsis`|`description`
`purl`, `comment`|`webpage_url`
`track`|`track_number`
`artist`|`artist`, `creator`, `uploader` or `uploader_id`
`genre`|`genre`
`album`|`album`
`album_artist`|`album_artist`
`disc`|`disc_number`
`show`|`series`
`season_number`|`season_number`
`episode_id`|`episode` or `episode_id`
`episode_sort`|`episode_number`
`language` of each stream|From the format's `language`
**Note**: The file format may not support some of these fields
@@ -1667,7 +1654,6 @@ The following extractors use this feature:
#### youtubetab (YouTube playlists, channels, feeds, etc.)
* `skip`: One or more of `webpage` (skip initial webpage download), `authcheck` (allow the download of playlists requiring authentication when no initial webpage is downloaded. This may cause unwanted behavior, see [#1122](https://github.com/yt-dlp/yt-dlp/pull/1122) for more details)
* `approximate_date`: Extract approximate `upload_date` in flat-playlist. This may cause date-based filters to be slightly off
#### funimation
* `language`: Languages to extract. Eg: `funimation:language=english,japanese`
@@ -1677,11 +1663,6 @@ The following extractors use this feature:
* `language`: Languages to extract. Eg: `crunchyroll:language=jaJp`
* `hardsub`: Which hard-sub versions to extract. Eg: `crunchyroll:hardsub=None,enUS`
#### crunchyroll:beta
* `format`: Which stream type(s) to extract. Default is `adaptive_hls` Eg: `crunchyrollbeta:format=vo_adaptive_hls`
* Potentially useful values include `adaptive_hls`, `adaptive_dash`, `vo_adaptive_hls`, `vo_adaptive_dash`, `download_hls`, `trailer_hls`, `trailer_dash`
* `hardsub`: Preference order for which hardsub versions to extract. Default is `None` (no hardsubs). Eg: `crunchyrollbeta:hardsub=en-US,None`
#### vikichannel
* `video_types`: Types of videos to download - one or more of `episodes`, `movies`, `clips`, `trailers`
@@ -1696,14 +1677,6 @@ The following extractors use this feature:
* `vcodec`: vcodec to ignore - one or more of `h264`, `h265`, `dvh265`
* `dr`: dynamic range to ignore - one or more of `sdr`, `hdr10`, `dv`
#### tiktok
* `app_version`: App version to call mobile APIs with - should be set along with `manifest_app_version`. (e.g. `20.2.1`)
* `manifest_app_version`: Numeric app version to call mobile APIs with. (e.g. `221`)
#### rokfinchannel
* `tab`: Which tab to download. One of `new`, `top`, `videos`, `podcasts`, `streams`, `stacks`. (E.g. `rokfinchannel:tab=streams`)
NOTE: These options may be changed/removed in the future without concern for backward compatibility
<!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->
@@ -1820,11 +1793,12 @@ ydl_opts = {
}],
'logger': MyLogger(),
'progress_hooks': [my_hook],
# Add custom headers
'http_headers': {'Referer': 'https://www.google.com'}
}
# Add custom headers
yt_dlp.utils.std_headers.update({'Referer': 'https://www.google.com'})
# ️ See the public functions in yt_dlp.YoutubeDL for for other available functions.
# Eg: "ydl.download", "ydl.download_with_info_file"
with yt_dlp.YoutubeDL(ydl_opts) as ydl:
@@ -1867,8 +1841,6 @@ While these options are redundant, they are still expected to be used due to the
--reject-title REGEX --match-filter "title !~= (?i)REGEX"
--min-views COUNT --match-filter "view_count >=? COUNT"
--max-views COUNT --match-filter "view_count <=? COUNT"
--user-agent UA --add-header "User-Agent:UA"
--referer URL --add-header "Referer:URL"
#### Not recommended
@@ -1906,13 +1878,11 @@ These options are not intended to be used by the end-user
These are aliases that are no longer documented for various reasons
--avconv-location --ffmpeg-location
--clean-infojson --clean-info-json
--cn-verification-proxy URL --geo-verification-proxy URL
--dump-headers --print-traffic
--dump-intermediate-pages --dump-pages
--force-write-download-archive --force-write-archive
--load-info --load-info-json
--no-clean-infojson --no-clean-info-json
--no-split-tracks --no-split-chapters
--no-write-srt --no-write-subs
--prefer-unsecure --prefer-insecure
+14 -14
View File
@@ -75,21 +75,21 @@ def filter_options(readme):
section = re.search(r'(?sm)^# USAGE AND OPTIONS\n.+?(?=^# )', readme).group(0)
options = '# OPTIONS\n'
for line in section.split('\n')[1:]:
mobj = re.fullmatch(r'''(?x)
\s{4}(?P<opt>-(?:,\s|[^\s])+)
(?:\s(?P<meta>(?:[^\s]|\s(?!\s))+))?
(\s{2,}(?P<desc>.+))?
''', line)
if not mobj:
options += f'{line.lstrip()}\n'
continue
option, metavar, description = mobj.group('opt', 'meta', 'desc')
if line.lstrip().startswith('-'):
split = re.split(r'\s{2,}', line.lstrip())
# Description string may start with `-` as well. If there is
# only one piece then it's a description bit not an option.
if len(split) > 1:
option, description = split
split_option = option.split(' ')
# Pandoc's definition_lists. See http://pandoc.org/README.html
option = f'{option} *{metavar}*' if metavar else option
description = f'{description}\n' if description else ''
options += f'\n{option}\n: {description}'
continue
if not split_option[-1].startswith('-'): # metavar
option = ' '.join(split_option[:-1] + [f'*{split_option[-1]}*'])
# Pandoc's definition_lists. See http://pandoc.org/README.html
options += f'\n{option}\n: {description}\n'
continue
options += line.lstrip() + '\n'
return readme.replace(section, options, 1)
+1 -1
View File
@@ -74,7 +74,7 @@ def version_to_list(version):
def dependency_options():
dependencies = [pycryptodome_module(), 'mutagen', 'brotli'] + collect_submodules('websockets')
dependencies = [pycryptodome_module(), 'mutagen'] + collect_submodules('websockets')
excluded_modules = ['test', 'ytdlp_plugins', 'youtube-dl', 'youtube-dlc']
yield from (f'--hidden-import={module}' for module in dependencies)
-2
View File
@@ -1,5 +1,3 @@
mutagen
pycryptodomex
websockets
brotli; platform_python_implementation=='CPython'
brotlicffi; platform_python_implementation!='CPython'
+2 -2
View File
@@ -21,9 +21,9 @@ DESCRIPTION = 'A youtube-dl fork with additional features and patches'
LONG_DESCRIPTION = '\n\n'.join((
'Official repository: <https://github.com/yt-dlp/yt-dlp>',
'**PS**: Some links in this document will not work since this is a copy of the README.md from Github',
open('README.md').read()))
open('README.md', 'r', encoding='utf-8').read()))
REQUIREMENTS = open('requirements.txt').read().splitlines()
REQUIREMENTS = ['mutagen', 'pycryptodomex', 'websockets']
if sys.argv[1:2] == ['py2exe']:
+20 -67
View File
@@ -3,6 +3,7 @@
- **17live:clip**
- **1tv**: Первый канал
- **20min**
- **220.ro**
- **23video**
- **247sports**
- **24video**
@@ -10,6 +11,7 @@
- **3sat**
- **4tube**
- **56.com**
- **5min**
- **6play**
- **7plus**
- **8tracks**
@@ -24,8 +26,6 @@
- **abcnews:video**
- **abcotvs**: ABC Owned Television Stations
- **abcotvs:clips**
- **AbemaTV**
- **AbemaTVTitle**
- **AcademicEarth:Course**
- **acast**
- **acast:channel**
@@ -47,8 +47,6 @@
- **AlJazeera**
- **Allocine**
- **AlphaPorno**
- **Alsace20TV**
- **Alsace20TVEmbed**
- **Alura**
- **AluraCourse**
- **Amara**
@@ -56,15 +54,11 @@
- **AMCNetworks**
- **AmericasTestKitchen**
- **AmericasTestKitchenSeason**
- **AmHistoryChannel**
- **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
- **AnimalPlanet**
- **AnimeLab**
- **AnimeLabShows**
- **AnimeOnDemand**
- **ant1newsgr:article**: ant1news.gr articles
- **ant1newsgr:embed**: ant1news.gr embedded videos
- **ant1newsgr:watch**: ant1news.gr videos
- **Anvato**
- **aol.com**: Yahoo screen and movies
- **APA**
@@ -82,7 +76,6 @@
- **Arkena**
- **arte.sky.it**
- **ArteTV**
- **ArteTVCategory**
- **ArteTVEmbed**
- **ArteTVPlaylist**
- **AsianCrush**
@@ -107,8 +100,8 @@
- **bandaichannel**
- **Bandcamp**
- **Bandcamp:album**
- **Bandcamp:user**
- **Bandcamp:weekly**
- **BandcampMusic**
- **bangumi.bilibili.com**: BiliBili番剧
- **BannedVideo**
- **bbc**: BBC
@@ -130,7 +123,6 @@
- **bfmtv:live**
- **BibelTV**
- **Bigflix**
- **Bigo**
- **Bild**: Bild.de
- **BiliBili**
- **Bilibili category extractor**
@@ -172,7 +164,6 @@
- **BYUtv**
- **CableAV**
- **Callin**
- **Caltrans**
- **CAM4**
- **Camdemy**
- **CamdemyFolder**
@@ -236,13 +227,10 @@
- **ComedyCentralTV**
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
- **CONtv**
- **CookingChannel**
- **Corus**
- **Coub**
- **CozyTV**
- **cp24**
- **cpac**
- **cpac:playlist**
- **Cracked**
- **Crackle**
- **CrooksAndLiars**
@@ -253,7 +241,6 @@
- **crunchyroll:playlist**
- **crunchyroll:playlist:beta**
- **CSpan**: C-SPAN
- **CSpanCongress**
- **CtsNews**: 華視新聞
- **CTV**
- **CTVNews**
@@ -275,27 +262,27 @@
- **daum.net:clip**
- **daum.net:playlist**
- **daum.net:user**
- **daystar:clip**
- **DBTV**
- **DctpTv**
- **DeezerAlbum**
- **DeezerPlaylist**
- **defense.gouv.fr**
- **democracynow**
- **DestinationAmerica**
- **DHM**: Filmarchiv - Deutsches Historisches Museum
- **Digg**
- **DigitalConcertHall**: DigitalConcertHall extractor
- **DigitallySpeaking**
- **Digiteka**
- **Discovery**
- **DiscoveryLife**
- **DiscoveryGo**
- **DiscoveryGoPlaylist**
- **DiscoveryNetworksDe**
- **DiscoveryPlus**
- **DiscoveryPlusIndia**
- **DiscoveryPlusIndiaShow**
- **DiscoveryPlusItaly**
- **DiscoveryPlusItalyShow**
- **DiscoveryVR**
- **Disney**
- **DIYNetwork**
- **dlive:stream**
@@ -344,9 +331,6 @@
- **Eporner**
- **EroProfile**
- **EroProfile:album**
- **ertflix**: ERTFLIX videos
- **ertflix:codename**: ERTFLIX videos by codename
- **ertwebtv:embed**: ert.gr webtv embedded videos
- **Escapist**
- **ESPN**
- **ESPNArticle**
@@ -367,7 +351,6 @@
- **faz.net**
- **fc2**
- **fc2:embed**
- **fc2:live**
- **Fczenit**
- **Filmmodu**
- **filmon**
@@ -377,7 +360,6 @@
- **FiveTV**
- **Flickr**
- **Folketinget**: Folketinget (ft.dk; Danish parliament)
- **FoodNetwork**
- **FootyRoom**
- **Formula1**
- **FOX**
@@ -387,7 +369,6 @@
- **foxnews**: Fox News and Fox Business Video
- **foxnews:article**
- **FoxSports**
- **fptplay**: fptplay.vn
- **FranceCulture**
- **FranceInter**
- **FranceTV**
@@ -395,6 +376,7 @@
- **FranceTVSite**
- **Freesound**
- **freespeech.org**
- **FreshLive**
- **FrontendMasters**
- **FrontendMastersCourse**
- **FrontendMastersLesson**
@@ -426,7 +408,6 @@
- **gem.cbc.ca:playlist**
- **generic**: Generic downloader that works on some sites
- **Gettr**
- **GettrStreaming**
- **Gfycat**
- **GiantBomb**
- **Giga**
@@ -437,7 +418,6 @@
- **glomex**: Glomex videos
- **glomex:embed**: Glomex embedded videos
- **Go**
- **GoDiscovery**
- **GodTube**
- **Gofile**
- **Golem**
@@ -459,7 +439,6 @@
- **hetklokhuis**
- **hgtv.com:show**
- **HGTVDe**
- **HGTVUsa**
- **HiDive**
- **HistoricFilms**
- **history:player**
@@ -468,6 +447,7 @@
- **hitbox:live**
- **HitRecord**
- **hketv**: 香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau
- **HornBunny**
- **HotNewHipHop**
- **hotstar**
- **hotstar:playlist**
@@ -506,12 +486,12 @@
- **InstagramIOS**: IOS instagram:// URL
- **Internazionale**
- **InternetVideoArchive**
- **InvestigationDiscovery**
- **IPrima**
- **IPrimaCNN**
- **iq.com**: International version of iQiyi
- **iq.com:album**
- **iqiyi**: 爱奇艺
- **Ir90Tv**
- **ITTF**
- **ITV**
- **ITVBTCC**
@@ -528,6 +508,7 @@
- **JWPlatform**
- **Kakao**
- **Kaltura**
- **Kankan**
- **Karaoketv**
- **KarriereVideos**
- **Katsomo**
@@ -639,9 +620,8 @@
- **MiaoPai**
- **microsoftstream**: Microsoft Stream
- **mildom**: Record ongoing live by specific user in Mildom
- **mildom:clip**: Clip in Mildom
- **mildom:user:vod**: Download all VODs from specific user in Mildom
- **mildom:vod**: VOD in Mildom
- **mildom:vod**: Download a VOD in Mildom
- **minds**
- **minds:channel**
- **minds:group**
@@ -684,13 +664,7 @@
- **mtvservices:embedded**
- **MTVUutisetArticle**
- **MuenchenTV**: münchen.tv
- **Murrtube**
- **MurrtubeUser**: Murrtube user profile
- **MuseScore**
- **MusicdexAlbum**
- **MusicdexArtist**
- **MusicdexPlaylist**
- **MusicdexSong**
- **mva**: Microsoft Virtual Academy videos
- **mva:course**: Microsoft Virtual Academy courses
- **Mwave**
@@ -754,13 +728,9 @@
- **NextTV**: 壹電視
- **Nexx**
- **NexxEmbed**
- **NFB**
- **NFHSNetwork**
- **nfl.com** (Currently broken)
- **nfl.com:article** (Currently broken)
- **NhkForSchoolBangumi**
- **NhkForSchoolProgramList**
- **NhkForSchoolSubject**: Portal page for each school subjects, like Japanese (kokugo, 国語) or math (sansuu/suugaku or 算数・数学)
- **NhkVod**
- **NhkVodProgram**
- **nhl.com**
@@ -770,10 +740,7 @@
- **nickelodeonru**
- **nicknight**
- **niconico**: ニコニコ動画
- **niconico:history**: NicoNico user history. Requires cookies.
- **niconico:playlist**
- **niconico:series**
- **niconico:tag**: NicoNico video tag URLs
- **NiconicoPlaylist**
- **NiconicoUser**
- **nicovideo:search**: Nico video search; "nicosearch:" prefix
- **nicovideo:search:date**: Nico video search, newest first; "nicosearchdate:" prefix
@@ -872,7 +839,6 @@
- **PatreonUser**
- **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
- **PearVideo**
- **PeekVids**
- **peer.tv**
- **PeerTube**
- **PeerTube:Playlist**
@@ -885,7 +851,6 @@
- **PhilharmonieDeParis**: Philharmonie de Paris
- **phoenix.de**
- **Photobucket**
- **Piapro**
- **Picarto**
- **PicartoVod**
- **Piksel**
@@ -905,7 +870,6 @@
- **PlaysTV**
- **Playtvak**: Playtvak.cz, iDNES.cz and Lidovky.cz
- **Playvid**
- **PlayVids**
- **Playwire**
- **pluralsight**
- **pluralsight:course**
@@ -1010,12 +974,10 @@
- **RICE**
- **RMCDecouverte**
- **RockstarGames**
- **Rokfin**
- **rokfin:channel**
- **rokfin:stack**
- **RoosterTeeth**
- **RoosterTeethSeries**
- **RottenTomatoes**
- **Roxwel**
- **Rozhlas**
- **RTBF**
- **RTDocumentry**
@@ -1052,7 +1014,6 @@
- **RUTV**: RUTV.RU
- **Ruutu**
- **Ruv**
- **ruv.is:spila**
- **safari**: safaribooksonline.com online video
- **safari:api**
- **safari:course**: safaribooksonline.com online courses
@@ -1192,7 +1153,6 @@
- **TeleBruxelles**
- **Telecinco**: telecinco.es, cuatro.com and mediaset.es
- **Telegraaf**
- **telegram:embed**
- **TeleMB**
- **Telemundo**
- **TeleQuebec**
@@ -1209,6 +1169,7 @@
- **TheIntercept**
- **ThePlatform**
- **ThePlatformFeed**
- **TheScene**
- **TheStar**
- **TheSun**
- **ThetaStream**
@@ -1225,7 +1186,6 @@
- **tiktok:tag**
- **tiktok:user**
- **tinypic**: tinypic.com videos
- **TLC**
- **TMZ**
- **TNAFlix**
- **TNAFlixNetworkEmbed**
@@ -1238,7 +1198,6 @@
- **Toypics**: Toypics video
- **ToypicsUser**: Toypics user profile
- **TrailerAddict** (Currently broken)
- **TravelChannel**
- **Trilulilu**
- **Trovo**
- **TrovoChannelClip**: All Clips of a trovo.live channel; "trovoclip:" prefix
@@ -1351,11 +1310,9 @@
- **Viddler**
- **Videa**
- **video.arnes.si**: Arnes Video
- **video.google:search**: Google Video search; "gvsearch:" prefix
- **video.google:search**: Google Video search; "gvsearch:" prefix (Currently broken)
- **video.sky.it**
- **video.sky.it:live**
- **VideocampusSachsen**
- **VideocampusSachsenEmbed**
- **VideoDetective**
- **videofy.me**
- **videomore**
@@ -1382,8 +1339,7 @@
- **vimeo:review**: Review pages on vimeo
- **vimeo:user**
- **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
- **Vimm:recording**
- **Vimm:stream**
- **Vimm**
- **Vimple**: Vimple - one-click video hosting
- **Vine**
- **vine:user**
@@ -1398,7 +1354,6 @@
- **vlive**
- **vlive:channel**
- **vlive:post**
- **vm.tiktok**
- **Vodlocker**
- **VODPl**
- **VODPlatform**
@@ -1418,6 +1373,7 @@
- **VShare**
- **VTM**
- **VTXTV**
- **vube**: Vube.com
- **VuClip**
- **Vupload**
- **VVVVID**
@@ -1433,10 +1389,10 @@
- **WatchBox**
- **WatchIndianPorn**: Watch Indian Porn
- **WDR**
- **wdr:mobile** (Currently broken)
- **wdr:mobile**
- **WDRElefant**
- **WDRPage**
- **web.archive:youtube**: web.archive.org saved youtube videos, "ytarchive:" prefix
- **web.archive:youtube**: web.archive.org saved youtube videos
- **Webcaster**
- **WebcasterFeed**
- **WebOfStories**
@@ -1468,7 +1424,6 @@
- **xiami:song**: 虾米音乐
- **ximalaya**: 喜马拉雅FM
- **ximalaya:album**: 喜马拉雅FM 专辑
- **xinpianchang**: xinpianchang.com
- **XMinus**
- **XNXX**
- **Xstream**
@@ -1488,7 +1443,6 @@
- **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
- **yandexmusic:track**: Яндекс.Музыка - Трек
- **YandexVideo**
- **YandexVideoPreview**
- **YapFiles**
- **YesJapan**
- **yinyuetai:video**: 音悦Tai
@@ -1505,7 +1459,6 @@
- **youtube**: YouTube
- **youtube:favorites**: YouTube liked videos; ":ytfav" keyword (requires cookies)
- **youtube:history**: Youtube watch history; ":ythis" keyword (requires cookies)
- **youtube:music:search_url**: YouTube music search URLs with selectable sections (Eg: #songs)
- **youtube:playlist**: YouTube playlists
- **youtube:recommended**: YouTube recommended videos; ":ytrec" keyword
- **youtube:search**: YouTube search; "ytsearch:" prefix
@@ -1527,7 +1480,7 @@
- **ZenYandex**
- **ZenYandexChannel**
- **Zhihu**
- **zingmp3**: zingmp3.vn
- **zingmp3**: mp3.zing.vn
- **zingmp3:album**
- **zoom**
- **Zype**
+1 -1
View File
@@ -220,7 +220,7 @@ def sanitize_got_info_dict(got_dict):
IGNORED_PREFIXES = ('', 'playlist', 'requested', 'webpage')
def sanitize(key, value):
if isinstance(value, str) and len(value) > 100 and key != 'thumbnail':
if isinstance(value, str) and len(value) > 100:
return f'md5:{md5(value)}'
elif isinstance(value, list) and len(value) > 10:
return f'count:{len(value)}'
+18 -2
View File
@@ -30,7 +30,9 @@ class YDL(FakeYDL):
self.msgs = []
def process_info(self, info_dict):
self.downloaded_info_dicts.append(info_dict.copy())
info_dict = info_dict.copy()
info_dict.pop('__original_infodict', None)
self.downloaded_info_dicts.append(info_dict)
def to_screen(self, msg):
self.msgs.append(msg)
@@ -896,6 +898,20 @@ class TestYoutubeDL(unittest.TestCase):
os.unlink(filename)
def test_match_filter(self):
class FilterYDL(YDL):
def __init__(self, *args, **kwargs):
super(FilterYDL, self).__init__(*args, **kwargs)
self.params['simulate'] = True
def process_info(self, info_dict):
super(YDL, self).process_info(info_dict)
def _match_entry(self, info_dict, incomplete=False):
res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
if res is None:
self.downloaded_info_dicts.append(info_dict.copy())
return res
first = {
'id': '1',
'url': TEST_URL,
@@ -923,7 +939,7 @@ class TestYoutubeDL(unittest.TestCase):
videos = [first, second]
def get_videos(filter_=None):
ydl = YDL({'match_filter': filter_, 'simulate': True})
ydl = FilterYDL({'match_filter': filter_})
for v in videos:
ydl.process_ie_result(v, download=True)
return [v['id'] for v in ydl.downloaded_info_dicts]
+1 -1
View File
@@ -1133,7 +1133,7 @@ class TestUtil(unittest.TestCase):
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
self.assertEqual(clean_html('a<br>\xa0b'), 'a\nb')
def test_intlist_to_bytes(self):
+26 -4
View File
@@ -9,9 +9,11 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import FakeYDL, is_download_test
from yt_dlp.extractor import (
YoutubeIE,
YoutubePlaylistIE,
YoutubeTabIE,
YoutubeIE,
)
@@ -25,10 +27,21 @@ class TestYoutubeLists(unittest.TestCase):
dl = FakeYDL()
dl.params['noplaylist'] = True
ie = YoutubeTabIE(dl)
result = ie.extract('https://www.youtube.com/watch?v=OmJ-4B-mS-Y&list=PLydZ2Hrp_gPRJViZjLFKaBMgCQOYEEkyp&index=2')
result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertEqual(result['_type'], 'url')
self.assertEqual(result['ie_key'], YoutubeIE.ie_key())
self.assertEqual(YoutubeIE.extract_id(result['url']), 'OmJ-4B-mS-Y')
self.assertEqual(YoutubeIE.extract_id(result['url']), 'FXxLjLQi3Fg')
def test_youtube_course(self):
print('Skipping: Course URLs no longer exists')
return
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
# TODO find a > 100 (paginating?) videos course
result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
entries = list(result['entries'])
self.assertEqual(YoutubeIE.extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE.extract_id(entries[-1]['url']), 'rYefUsYuEp0')
def test_youtube_mix(self):
dl = FakeYDL()
@@ -39,6 +52,15 @@ class TestYoutubeLists(unittest.TestCase):
original_video = entries[0]
self.assertEqual(original_video['id'], 'tyITL_exICo')
def test_youtube_toptracks(self):
print('Skipping: The playlist page gives error 500')
return
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
entries = result['entries']
self.assertEqual(len(entries), 100)
def test_youtube_flat_playlist_extraction(self):
dl = FakeYDL()
dl.params['extract_flat'] = True
+1 -16
View File
@@ -86,14 +86,6 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/8040e515/player_ias.vflset/en_US/base.js',
'wvOFaY-yjgDuIEg5', 'HkfBFDHmgw4rsw',
),
(
'https://www.youtube.com/s/player/e06dea74/player_ias.vflset/en_US/base.js',
'AiuodmaDDYw8d3y4bf', 'ankd8eza2T6Qmw',
),
(
'https://www.youtube.com/s/player/5dd88d1d/player-plasma-ias-phone-en_US.vflset/base.js',
'kSxKFLeqzv_ZyHSAt', 'n8gS8oRlHOxPFA',
),
]
@@ -124,17 +116,10 @@ class TestPlayerInfo(unittest.TestCase):
class TestSignature(unittest.TestCase):
def setUp(self):
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
self.TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata/sigs')
self.TESTDATA_DIR = os.path.join(TEST_DIR, 'testdata')
if not os.path.exists(self.TESTDATA_DIR):
os.mkdir(self.TESTDATA_DIR)
def tearDown(self):
try:
for f in os.listdir(self.TESTDATA_DIR):
os.remove(f)
except OSError:
pass
def t_factory(name, sig_func, url_pattern):
def make_tfunc(url, sig_input, expected_sig):
+137 -203
View File
@@ -32,7 +32,6 @@ from string import ascii_letters
from .compat import (
compat_basestring,
compat_brotli,
compat_get_terminal_size,
compat_kwargs,
compat_numeric_types,
@@ -73,7 +72,6 @@ from .utils import (
GeoRestrictedError,
get_domain,
HEADRequest,
InAdvancePagedList,
int_or_none,
iri_to_uri,
ISO3166Utils,
@@ -84,7 +82,6 @@ from .utils import (
make_dir,
make_HTTPS_handler,
MaxDownloadsReached,
merge_headers,
network_exceptions,
number_of_digits,
orderedSet,
@@ -203,12 +200,9 @@ class YoutubeDL(object):
verbose: Print additional info to stdout.
quiet: Do not print messages to stdout.
no_warnings: Do not print out anything for warnings.
forceprint: A dict with keys WHEN mapped to a list of templates to
print to stdout. The allowed keys are video or any of the
items in utils.POSTPROCESS_WHEN.
forceprint: A dict with keys video/playlist mapped to
a list of templates to force print to stdout
For compatibility, a single list is also accepted
print_to_file: A dict with keys WHEN (same as forceprint) mapped to
a list of tuples with (template, filename)
forceurl: Force printing final URL. (Deprecated)
forcetitle: Force printing title. (Deprecated)
forceid: Force printing ID. (Deprecated)
@@ -235,8 +229,6 @@ class YoutubeDL(object):
See "Sorting Formats" for more details.
format_sort_force: Force the given format_sort. see "Sorting Formats"
for more details.
prefer_free_formats: Whether to prefer video formats with free containers
over non-free ones of same quality.
allow_multiple_video_streams: Allow multiple video streams to be merged
into a single file
allow_multiple_audio_streams: Allow multiple audio streams to be merged
@@ -336,7 +328,6 @@ class YoutubeDL(object):
nocheckcertificate: Do not verify SSL certificates
prefer_insecure: Use HTTP instead of HTTPS to retrieve information.
At the moment, this is only supported by YouTube.
http_headers: A dictionary of custom headers to be used for all requests
proxy: URL of the proxy server to use
geo_verification_proxy: URL of the proxy to use for IP address verification
on geo-restricted sites.
@@ -357,8 +348,8 @@ class YoutubeDL(object):
postprocessors: A list of dictionaries, each with an entry
* key: The name of the postprocessor. See
yt_dlp/postprocessor/__init__.py for a list.
* when: When to run the postprocessor. Allowed values are
the entries of utils.POSTPROCESS_WHEN
* when: When to run the postprocessor. Can be one of
pre_process|before_dl|post_process|after_move.
Assumed to be 'post_process' if not given
post_hooks: Deprecated - Register a custom postprocessor instead
A list of functions that get called as the final step
@@ -489,7 +480,6 @@ class YoutubeDL(object):
extractor_args: A dictionary of arguments to be passed to the extractors.
See "EXTRACTOR ARGUMENTS" for details.
Eg: {'youtube': {'skip': ['dash', 'hls']}}
mark_watched: Mark videos watched (even with --simulate). Only for YouTube
youtube_include_dash_manifest: Deprecated - Use extractor_args instead.
If True (default), DASH manifests and related
data will be downloaded and processed by extractor.
@@ -601,14 +591,12 @@ class YoutubeDL(object):
else:
self.params['nooverwrites'] = not self.params['overwrites']
self.params.setdefault('forceprint', {})
self.params.setdefault('print_to_file', {})
# Compatibility with older syntax
params.setdefault('forceprint', {})
if not isinstance(params['forceprint'], dict):
self.params['forceprint'] = {'video': params['forceprint']}
params['forceprint'] = {'video': params['forceprint']}
if self.params.get('bidi_workaround', False):
if params.get('bidi_workaround', False):
try:
import pty
master, slave = pty.openpty()
@@ -636,7 +624,7 @@ class YoutubeDL(object):
if (sys.platform != 'win32'
and sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968']
and not self.params.get('restrictfilenames', False)):
and not params.get('restrictfilenames', False)):
# Unicode filesystem API will throw errors (#1474, #13027)
self.report_warning(
'Assuming --restrict-filenames since file system encoding '
@@ -652,9 +640,6 @@ class YoutubeDL(object):
else self.params['format'] if callable(self.params['format'])
else self.build_format_selector(self.params['format']))
# Set http_headers defaults according to std_headers
self.params['http_headers'] = merge_headers(std_headers, self.params.get('http_headers', {}))
self._setup_opener()
if auto_init:
@@ -896,8 +881,7 @@ class YoutubeDL(object):
def _format_text(self, handle, allow_colors, text, f, fallback=None, *, test_encoding=False):
if test_encoding:
original_text = text
# handle.encoding can be None. See https://github.com/yt-dlp/yt-dlp/issues/2711
encoding = self.params.get('encoding') or getattr(handle, 'encoding', None) or 'ascii'
encoding = self.params.get('encoding') or getattr(handle, 'encoding', 'ascii')
text = text.encode(encoding, 'ignore').decode(encoding)
if fallback is not None and text != original_text:
text = fallback
@@ -962,13 +946,13 @@ class YoutubeDL(object):
except UnicodeEncodeError:
self.to_screen('Deleting existing file')
def raise_no_formats(self, info, forced=False, *, msg=None):
def raise_no_formats(self, info, forced=False):
has_drm = info.get('__has_drm')
ignored, expected = self.params.get('ignore_no_formats_error'), bool(msg)
msg = msg or has_drm and 'This video is DRM protected' or 'No video formats found!'
if forced or not ignored:
msg = 'This video is DRM protected' if has_drm else 'No video formats found!'
expected = self.params.get('ignore_no_formats_error')
if forced or not expected:
raise ExtractorError(msg, video_id=info['id'], ie=info['extractor'],
expected=has_drm or ignored or expected)
expected=has_drm or expected)
else:
self.report_warning(msg)
@@ -1045,7 +1029,8 @@ class YoutubeDL(object):
@staticmethod
def _copy_infodict(info_dict):
info_dict = dict(info_dict)
info_dict.pop('__postprocessors', None)
for key in ('__original_infodict', '__postprocessors'):
info_dict.pop(key, None)
return info_dict
def prepare_outtmpl(self, outtmpl, info_dict, sanitize=False):
@@ -1230,17 +1215,10 @@ class YoutubeDL(object):
try:
outtmpl = self._outtmpl_expandpath(self.outtmpl_dict.get(tmpl_type, self.outtmpl_dict['default']))
filename = self.evaluate_outtmpl(outtmpl, info_dict, True)
if not filename:
return None
if tmpl_type in ('default', 'temp'):
final_ext, ext = self.params.get('final_ext'), info_dict.get('ext')
if final_ext and ext and final_ext != ext and filename.endswith(f'.{final_ext}'):
filename = replace_extension(filename, ext, final_ext)
else:
force_ext = OUTTMPL_TYPES[tmpl_type]
if force_ext:
filename = replace_extension(filename, force_ext, info_dict.get('ext'))
force_ext = OUTTMPL_TYPES.get(tmpl_type)
if filename and force_ext is not None:
filename = replace_extension(filename, force_ext, info_dict.get('ext'))
# https://github.com/blackjack4494/youtube-dlc/issues/85
trim_file_name = self.params.get('trim_file_name', False)
@@ -1479,12 +1457,8 @@ class YoutubeDL(object):
self.add_extra_info(ie_result, {
'webpage_url': url,
'original_url': url,
})
webpage_url = ie_result.get('webpage_url')
if webpage_url:
self.add_extra_info(ie_result, {
'webpage_url_basename': url_basename(webpage_url),
'webpage_url_domain': get_domain(webpage_url),
'webpage_url_basename': url_basename(url),
'webpage_url_domain': get_domain(url),
})
if ie is not None:
self.add_extra_info(ie_result, {
@@ -1592,7 +1566,6 @@ class YoutubeDL(object):
self._playlist_level += 1
self._playlist_urls.add(webpage_url)
self._fill_common_fields(ie_result, False)
self._sanitize_thumbnails(ie_result)
try:
return self.__process_playlist(ie_result, download)
@@ -1689,9 +1662,6 @@ class YoutubeDL(object):
msg = 'Downloading %d videos'
if not isinstance(ie_entries, (PagedList, LazyList)):
ie_entries = LazyList(ie_entries)
elif isinstance(ie_entries, InAdvancePagedList):
if ie_entries._pagesize == 1:
playlist_count = ie_entries._pagecount
def get_entry(i):
return YoutubeDL.__handle_extraction_exceptions(
@@ -1855,21 +1825,15 @@ class YoutubeDL(object):
'^=': lambda attr, value: attr.startswith(value),
'$=': lambda attr, value: attr.endswith(value),
'*=': lambda attr, value: value in attr,
'~=': lambda attr, value: value.search(attr) is not None
}
str_operator_rex = re.compile(r'''(?x)\s*
(?P<key>[a-zA-Z0-9._-]+)\s*
(?P<negation>!\s*)?(?P<op>%s)\s*(?P<none_inclusive>\?\s*)?
(?P<quote>["'])?
(?P<value>(?(quote)(?:(?!(?P=quote))[^\\]|\\.)+|[\w.-]+))
(?(quote)(?P=quote))\s*
(?P<negation>!\s*)?(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
(?P<value>[a-zA-Z0-9._-]+)\s*
''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
m = str_operator_rex.fullmatch(filter_spec)
if m:
if m.group('op') == '~=':
comparison_value = re.compile(m.group('value'))
else:
comparison_value = re.sub(r'''\\([\\"'])''', r'\1', m.group('value'))
comparison_value = m.group('value')
str_op = STR_OPERATORS[m.group('op')]
if m.group('negation'):
op = lambda attr, value: not str_op(attr, value)
@@ -2258,7 +2222,11 @@ class YoutubeDL(object):
return _build_selector_function(parsed_selector)
def _calc_headers(self, info_dict):
res = merge_headers(self.params['http_headers'], info_dict.get('http_headers') or {})
res = std_headers.copy()
add_headers = info_dict.get('http_headers')
if add_headers:
res.update(add_headers)
cookies = self._calc_cookies(info_dict)
if cookies:
@@ -2316,17 +2284,55 @@ class YoutubeDL(object):
else:
info_dict['thumbnails'] = thumbnails
def _fill_common_fields(self, info_dict, is_video=True):
# TODO: move sanitization here
if is_video:
# playlists are allowed to lack "title"
info_dict['fulltitle'] = info_dict.get('title')
if 'title' not in info_dict:
raise ExtractorError('Missing "title" field in extractor result',
video_id=info_dict['id'], ie=info_dict['extractor'])
elif not info_dict.get('title'):
self.report_warning('Extractor failed to obtain "title". Creating a generic title instead')
info_dict['title'] = f'{info_dict["extractor"]} video #{info_dict["id"]}'
def process_video_result(self, info_dict, download=True):
assert info_dict.get('_type', 'video') == 'video'
self._num_videos += 1
if 'id' not in info_dict:
raise ExtractorError('Missing "id" field in extractor result')
if 'title' not in info_dict:
raise ExtractorError('Missing "title" field in extractor result',
video_id=info_dict['id'], ie=info_dict['extractor'])
def report_force_conversion(field, field_not, conversion):
self.report_warning(
'"%s" field is not %s - forcing %s conversion, there is an error in extractor'
% (field, field_not, conversion))
def sanitize_string_field(info, string_field):
field = info.get(string_field)
if field is None or isinstance(field, compat_str):
return
report_force_conversion(string_field, 'a string', 'string')
info[string_field] = compat_str(field)
def sanitize_numeric_fields(info):
for numeric_field in self._NUMERIC_FIELDS:
field = info.get(numeric_field)
if field is None or isinstance(field, compat_numeric_types):
continue
report_force_conversion(numeric_field, 'numeric', 'int')
info[numeric_field] = int_or_none(field)
sanitize_string_field(info_dict, 'id')
sanitize_numeric_fields(info_dict)
if 'playlist' not in info_dict:
# It isn't part of a playlist
info_dict['playlist'] = None
info_dict['playlist_index'] = None
self._sanitize_thumbnails(info_dict)
thumbnail = info_dict.get('thumbnail')
thumbnails = info_dict.get('thumbnails')
if thumbnail:
info_dict['thumbnail'] = sanitize_url(thumbnail)
elif thumbnails:
info_dict['thumbnail'] = thumbnails[-1]['url']
if info_dict.get('display_id') is None and 'id' in info_dict:
info_dict['display_id'] = info_dict['id']
if info_dict.get('duration') is not None:
info_dict['duration_string'] = formatSeconds(info_dict['duration'])
@@ -2368,59 +2374,6 @@ class YoutubeDL(object):
if info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
def process_video_result(self, info_dict, download=True):
assert info_dict.get('_type', 'video') == 'video'
self._num_videos += 1
if 'id' not in info_dict:
raise ExtractorError('Missing "id" field in extractor result', ie=info_dict['extractor'])
elif not info_dict.get('id'):
raise ExtractorError('Extractor failed to obtain "id"', ie=info_dict['extractor'])
def report_force_conversion(field, field_not, conversion):
self.report_warning(
'"%s" field is not %s - forcing %s conversion, there is an error in extractor'
% (field, field_not, conversion))
def sanitize_string_field(info, string_field):
field = info.get(string_field)
if field is None or isinstance(field, compat_str):
return
report_force_conversion(string_field, 'a string', 'string')
info[string_field] = compat_str(field)
def sanitize_numeric_fields(info):
for numeric_field in self._NUMERIC_FIELDS:
field = info.get(numeric_field)
if field is None or isinstance(field, compat_numeric_types):
continue
report_force_conversion(numeric_field, 'numeric', 'int')
info[numeric_field] = int_or_none(field)
sanitize_string_field(info_dict, 'id')
sanitize_numeric_fields(info_dict)
if (info_dict.get('duration') or 0) <= 0 and info_dict.pop('duration', None):
self.report_warning('"duration" field is negative, there is an error in extractor')
if 'playlist' not in info_dict:
# It isn't part of a playlist
info_dict['playlist'] = None
info_dict['playlist_index'] = None
self._sanitize_thumbnails(info_dict)
thumbnail = info_dict.get('thumbnail')
thumbnails = info_dict.get('thumbnails')
if thumbnail:
info_dict['thumbnail'] = sanitize_url(thumbnail)
elif thumbnails:
info_dict['thumbnail'] = thumbnails[-1]['url']
if info_dict.get('display_id') is None and 'id' in info_dict:
info_dict['display_id'] = info_dict['id']
self._fill_common_fields(info_dict)
for cc_kind in ('subtitles', 'automatic_captions'):
cc = info_dict.get(cc_kind)
if cc:
@@ -2447,14 +2400,14 @@ class YoutubeDL(object):
if not self.params.get('allow_unplayable_formats'):
formats = [f for f in formats if not f.get('has_drm')]
get_from_start = not info_dict.get('is_live') or bool(self.params.get('live_from_start'))
if not get_from_start:
info_dict['title'] += ' ' + datetime.datetime.now().strftime('%Y-%m-%d %H:%M')
if info_dict.get('is_live') and formats:
# backward compatibility
info_dict['fulltitle'] = info_dict['title']
if info_dict.get('is_live'):
get_from_start = bool(self.params.get('live_from_start'))
formats = [f for f in formats if bool(f.get('is_from_start')) == get_from_start]
if get_from_start and not formats:
self.raise_no_formats(info_dict, msg='--live-from-start is passed, but there are no formats that can be downloaded from the start. '
'If you want to download from the current time, pass --no-live-from-start')
if not get_from_start:
info_dict['title'] += ' ' + datetime.datetime.now().strftime('%Y-%m-%d %H:%M')
if not formats:
self.raise_no_formats(info_dict)
@@ -2530,6 +2483,8 @@ class YoutubeDL(object):
if '__x_forwarded_for_ip' in info_dict:
del info_dict['__x_forwarded_for_ip']
# TODO Central sorting goes here
if self.params.get('check_formats') is True:
formats = LazyList(self._check_formats(formats[::-1]), reverse=True)
@@ -2542,12 +2497,6 @@ class YoutubeDL(object):
info_dict, _ = self.pre_process(info_dict)
if self._match_entry(info_dict) is not None:
return info_dict
self.post_extract(info_dict)
info_dict, _ = self.pre_process(info_dict, 'after_filter')
# The pre-processors may have modified the formats
formats = info_dict.get('formats', [info_dict])
@@ -2632,12 +2581,15 @@ class YoutubeDL(object):
+ ', '.join([f['format_id'] for f in formats_to_download]))
max_downloads_reached = False
for i, fmt in enumerate(formats_to_download):
formats_to_download[i] = new_info = self._copy_infodict(info_dict)
formats_to_download[i] = new_info = dict(info_dict)
# Save a reference to the original info_dict so that it can be modified in process_info if needed
new_info.update(fmt)
new_info['__original_infodict'] = info_dict
try:
self.process_info(new_info)
except MaxDownloadsReached:
max_downloads_reached = True
new_info.pop('__original_infodict')
# Remove copied info
for key, val in tuple(new_info.items()):
if info_dict.get(key) == val:
@@ -2682,15 +2634,12 @@ class YoutubeDL(object):
# given in subtitleslangs. See https://github.com/yt-dlp/yt-dlp/issues/1041
requested_langs = []
for lang_re in self.params.get('subtitleslangs'):
if lang_re == 'all':
requested_langs.extend(all_sub_langs)
continue
discard = lang_re[0] == '-'
if discard:
lang_re = lang_re[1:]
if lang_re == 'all':
if discard:
requested_langs = []
else:
requested_langs.extend(all_sub_langs)
continue
current_langs = filter(re.compile(lang_re + '$').match, all_sub_langs)
if discard:
for lang in current_langs:
@@ -2730,33 +2679,19 @@ class YoutubeDL(object):
subs[lang] = f
return subs
def _forceprint(self, key, info_dict):
if info_dict is None:
return
info_copy = info_dict.copy()
info_copy['formats_table'] = self.render_formats_table(info_dict)
info_copy['thumbnails_table'] = self.render_thumbnails_table(info_dict)
info_copy['subtitles_table'] = self.render_subtitles_table(info_dict.get('id'), info_dict.get('subtitles'))
info_copy['automatic_captions_table'] = self.render_subtitles_table(info_dict.get('id'), info_dict.get('automatic_captions'))
def _forceprint(self, tmpl, info_dict):
mobj = re.match(r'\w+(=?)$', tmpl)
if mobj and mobj.group(1):
tmpl = f'{tmpl[:-1]} = %({tmpl[:-1]})r'
elif mobj:
tmpl = '%({})s'.format(tmpl)
def format_tmpl(tmpl):
mobj = re.match(r'\w+(=?)$', tmpl)
if mobj and mobj.group(1):
return f'{tmpl[:-1]} = %({tmpl[:-1]})r'
elif mobj:
return f'%({tmpl})s'
return tmpl
for tmpl in self.params['forceprint'].get(key, []):
self.to_stdout(self.evaluate_outtmpl(format_tmpl(tmpl), info_copy))
for tmpl, file_tmpl in self.params['print_to_file'].get(key, []):
filename = self.evaluate_outtmpl(file_tmpl, info_dict)
tmpl = format_tmpl(tmpl)
self.to_screen(f'[info] Writing {tmpl!r} to: {filename}')
if self._ensure_dir_exists(filename):
with io.open(filename, 'a', encoding='utf-8') as f:
f.write(self.evaluate_outtmpl(tmpl, info_copy) + '\n')
info_dict = info_dict.copy()
info_dict['formats_table'] = self.render_formats_table(info_dict)
info_dict['thumbnails_table'] = self.render_thumbnails_table(info_dict)
info_dict['subtitles_table'] = self.render_subtitles_table(info_dict.get('id'), info_dict.get('subtitles'))
info_dict['automatic_captions_table'] = self.render_subtitles_table(info_dict.get('id'), info_dict.get('automatic_captions'))
self.to_stdout(self.evaluate_outtmpl(tmpl, info_dict))
def __forced_printings(self, info_dict, filename, incomplete):
def print_mandatory(field, actual_field=None):
@@ -2780,11 +2715,10 @@ class YoutubeDL(object):
elif 'url' in info_dict:
info_dict['urls'] = info_dict['url'] + info_dict.get('play_path', '')
if (self.params.get('forcejson')
or self.params['forceprint'].get('video')
or self.params['print_to_file'].get('video')):
if self.params['forceprint'].get('video') or self.params.get('forcejson'):
self.post_extract(info_dict)
self._forceprint('video', info_dict)
for tmpl in self.params['forceprint'].get('video', []):
self._forceprint(tmpl, info_dict)
print_mandatory('title')
print_mandatory('id')
@@ -2845,7 +2779,7 @@ class YoutubeDL(object):
return None
def process_info(self, info_dict):
"""Process a single resolved IE result. (Modifies it in-place)"""
"""Process a single resolved IE result. (Modified it in-place)"""
assert info_dict.get('_type', 'video') == 'video'
original_infodict = info_dict
@@ -2853,22 +2787,18 @@ class YoutubeDL(object):
if 'format' not in info_dict and 'ext' in info_dict:
info_dict['format'] = info_dict['ext']
# This is mostly just for backward compatibility of process_info
# As a side-effect, this allows for format-specific filters
if self._match_entry(info_dict) is not None:
info_dict['__write_download_archive'] = 'ignore'
return
# Does nothing under normal operation - for backward compatibility of process_info
self.post_extract(info_dict)
self._num_downloads += 1
# info_dict['_filename'] needs to be set for backward compatibility
info_dict['_filename'] = full_filename = self.prepare_filename(info_dict, warn=True)
temp_filename = self.prepare_filename(info_dict, 'temp')
files_to_move = {}
self._num_downloads += 1
# Forced printings
self.__forced_printings(info_dict, full_filename, incomplete=('format' not in info_dict))
@@ -2931,11 +2861,9 @@ class YoutubeDL(object):
# Write internet shortcut files
def _write_link_file(link_type):
url = try_get(info_dict['webpage_url'], iri_to_uri)
if not url:
self.report_warning(
f'Cannot write internet shortcut file because the actual URL of "{info_dict["webpage_url"]}" is unknown')
return True
if 'webpage_url' not in info_dict:
self.report_error('Cannot write internet shortcut file because the "webpage_url" field is missing in the media information')
return False
linkfn = replace_extension(self.prepare_filename(info_dict, 'link'), link_type, info_dict.get('ext'))
if not self._ensure_dir_exists(encodeFilename(linkfn)):
return False
@@ -2946,7 +2874,7 @@ class YoutubeDL(object):
self.to_screen(f'[info] Writing internet shortcut (.{link_type}) to: {linkfn}')
with io.open(encodeFilename(to_high_limit_path(linkfn)), 'w', encoding='utf-8',
newline='\r\n' if link_type == 'url' else '\n') as linkfile:
template_vars = {'url': url}
template_vars = {'url': iri_to_uri(info_dict['webpage_url'])}
if link_type == 'desktop':
template_vars['filename'] = linkfn[:-(len(link_type) + 1)]
linkfile.write(LINK_TEMPLATES[link_type] % template_vars)
@@ -3081,11 +3009,9 @@ class YoutubeDL(object):
'while also allowing unplayable formats to be downloaded. '
'The formats won\'t be merged to prevent data corruption.')
elif not merger.available:
msg = 'You have requested merging of multiple formats but ffmpeg is not installed'
if not self.params.get('ignoreerrors'):
self.report_error(f'{msg}. Aborting due to --abort-on-error')
return
self.report_warning(f'{msg}. The formats won\'t be merged')
self.report_warning(
'You have requested merging of multiple formats but ffmpeg is not installed. '
'The formats won\'t be merged.')
if temp_filename == '-':
reason = ('using a downloader other than ffmpeg' if FFmpegFD.can_merge_formats(info_dict, self.params)
@@ -3281,15 +3207,17 @@ class YoutubeDL(object):
if info_dict is None:
return info_dict
info_dict.setdefault('epoch', int(time.time()))
info_dict.setdefault('_type', 'video')
remove_keys = {'__original_infodict'} # Always remove this since this may contain a copy of the entire dict
keep_keys = ['_type'] # Always keep this to facilitate load-info-json
if remove_private_keys:
reject = lambda k, v: v is None or (k.startswith('_') and k != '_type') or k in {
remove_keys |= {
'requested_downloads', 'requested_formats', 'requested_subtitles', 'requested_entries',
'entries', 'filepath', 'infojson_filename', 'original_url', 'playlist_autonumber',
}
reject = lambda k, v: k not in keep_keys and (
k.startswith('_') or k in remove_keys or v is None)
else:
reject = lambda k, v: False
reject = lambda k, v: k in remove_keys
def filter_fn(obj):
if isinstance(obj, dict):
@@ -3316,8 +3244,14 @@ class YoutubeDL(object):
actual_post_extract(video_dict or {})
return
post_extractor = info_dict.pop('__post_extractor', None) or (lambda: {})
info_dict.update(post_extractor())
post_extractor = info_dict.get('__post_extractor') or (lambda: {})
extra = post_extractor().items()
info_dict.update(extra)
info_dict.pop('__post_extractor', None)
original_infodict = info_dict.get('__original_infodict') or {}
original_infodict.update(extra)
original_infodict.pop('__post_extractor', None)
actual_post_extract(info_dict or {})
@@ -3351,7 +3285,8 @@ class YoutubeDL(object):
return infodict
def run_all_pps(self, key, info, *, additional_pps=None):
self._forceprint(key, info)
for tmpl in self.params['forceprint'].get(key, []):
self._forceprint(tmpl, info)
for pp in (additional_pps or []) + self._pps[key]:
info = self.run_pp(pp, info)
return info
@@ -3546,7 +3481,7 @@ class YoutubeDL(object):
delim=self._format_screen('\u2500', self.Styles.DELIM, '-', test_encoding=True))
def render_thumbnails_table(self, info_dict):
thumbnails = list(info_dict.get('thumbnails') or [])
thumbnails = list(info_dict.get('thumbnails'))
if not thumbnails:
return None
return render_table(
@@ -3595,7 +3530,7 @@ class YoutubeDL(object):
return
def get_encoding(stream):
ret = str(getattr(stream, 'encoding', 'missing (%s)' % type(stream).__name__))
ret = getattr(stream, 'encoding', 'missing (%s)' % type(stream).__name__)
if not supports_terminal_sequences(stream):
from .compat import WINDOWS_VT_MODE
ret += ' (No VT)' if WINDOWS_VT_MODE is False else ' (No ANSI)'
@@ -3678,7 +3613,6 @@ class YoutubeDL(object):
from .cookies import SQLITE_AVAILABLE, SECRETSTORAGE_AVAILABLE
lib_str = join_nonempty(
compat_brotli and compat_brotli.__name__,
compat_pycrypto_AES and compat_pycrypto_AES.__name__.split('.')[0],
SECRETSTORAGE_AVAILABLE and 'secretstorage',
has_mutagen and 'mutagen',
@@ -3894,7 +3828,7 @@ class YoutubeDL(object):
else:
self.to_screen(f'[info] Downloading {thumb_display_id} ...')
try:
uf = self.urlopen(sanitized_Request(t['url'], headers=t.get('http_headers', {})))
uf = self.urlopen(t['url'])
self.to_screen(f'[info] Writing {thumb_display_id} to: {thumb_filename}')
with open(encodeFilename(thumb_filename), 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf)
+11 -16
View File
@@ -41,7 +41,6 @@ from .utils import (
SameFileError,
setproctitle,
std_headers,
traverse_obj,
write_string,
)
from .update import run_update
@@ -76,15 +75,20 @@ def _real_main(argv=None):
parser, opts, args = parseOpts(argv)
warnings, deprecation_warnings = [], []
# Set user agent
if opts.user_agent is not None:
opts.headers.setdefault('User-Agent', opts.user_agent)
std_headers['User-Agent'] = opts.user_agent
# Set referer
if opts.referer is not None:
opts.headers.setdefault('Referer', opts.referer)
std_headers['Referer'] = opts.referer
# Custom HTTP headers
std_headers.update(opts.headers)
# Dump user agent
if opts.dump_user_agent:
ua = traverse_obj(opts.headers, 'User-Agent', casesense=False, default=std_headers['User-Agent'])
write_string(f'{ua}\n', out=sys.stdout)
write_string(std_headers['User-Agent'] + '\n', out=sys.stdout)
sys.exit(0)
# Batch file verification
@@ -331,9 +335,6 @@ def _real_main(argv=None):
if _video_multistreams_set is False and _audio_multistreams_set is False:
_unused_compat_opt('multistreams')
outtmpl_default = opts.outtmpl.get('default')
if outtmpl_default == '':
outtmpl_default, opts.skip_download = None, True
del opts.outtmpl['default']
if opts.useid:
if outtmpl_default is None:
outtmpl_default = opts.outtmpl['default'] = '%(id)s.%(ext)s'
@@ -355,10 +356,6 @@ def _real_main(argv=None):
for type_, tmpl_list in opts.forceprint.items():
for tmpl in tmpl_list:
validate_outtmpl(tmpl, f'{type_} print template')
for type_, tmpl_list in opts.print_to_file.items():
for tmpl, file in tmpl_list:
validate_outtmpl(tmpl, f'{type_} print-to-file template')
validate_outtmpl(file, f'{type_} print-to-file filename')
validate_outtmpl(opts.sponsorblock_chapter_title, 'SponsorBlock chapter title')
for k, tmpl in opts.progress_template.items():
k = f'{k[:-6]} console title' if '-title' in k else f'{k} progress'
@@ -470,8 +467,8 @@ def _real_main(argv=None):
'key': 'SponsorBlock',
'categories': sponsorblock_query,
'api': opts.sponsorblock_api,
# Run this after filtering videos
'when': 'after_filter'
# Run this immediately after extraction is complete
'when': 'pre_process'
})
if opts.parse_metadata:
postprocessors.append({
@@ -666,7 +663,6 @@ def _real_main(argv=None):
'forcefilename': opts.getfilename,
'forceformat': opts.getformat,
'forceprint': opts.forceprint,
'print_to_file': opts.print_to_file,
'forcejson': opts.dumpjson or opts.print_json,
'dump_single_json': opts.dump_single_json,
'force_write_download_archive': opts.force_write_download_archive,
@@ -763,7 +759,6 @@ def _real_main(argv=None):
'legacyserverconnect': opts.legacy_server_connect,
'nocheckcertificate': opts.no_check_certificate,
'prefer_insecure': opts.prefer_insecure,
'http_headers': opts.headers,
'proxy': opts.proxy,
'socket_timeout': opts.socket_timeout,
'bidi_workaround': opts.bidi_workaround,
+3 -15
View File
@@ -2,15 +2,8 @@ from __future__ import unicode_literals
from math import ceil
from .compat import (
compat_b64decode,
compat_ord,
compat_pycrypto_AES,
)
from .utils import (
bytes_to_intlist,
intlist_to_bytes,
)
from .compat import compat_b64decode, compat_pycrypto_AES
from .utils import bytes_to_intlist, intlist_to_bytes
if compat_pycrypto_AES:
@@ -32,10 +25,6 @@ else:
return intlist_to_bytes(aes_gcm_decrypt_and_verify(*map(bytes_to_intlist, (data, key, tag, nonce))))
def unpad_pkcs7(data):
return data[:-compat_ord(data[-1])]
BLOCK_SIZE_BYTES = 16
@@ -517,6 +506,5 @@ __all__ = [
'aes_encrypt',
'aes_gcm_decrypt_and_verify',
'aes_gcm_decrypt_and_verify_bytes',
'key_expansion',
'unpad_pkcs7',
'key_expansion'
]
-26
View File
@@ -2,7 +2,6 @@
import asyncio
import base64
import collections
import ctypes
import getpass
import html
@@ -134,16 +133,6 @@ except AttributeError:
asyncio.run = compat_asyncio_run
try: # >= 3.7
asyncio.tasks.all_tasks
except AttributeError:
asyncio.tasks.all_tasks = asyncio.tasks.Task.all_tasks
try:
import websockets as compat_websockets
except ImportError:
compat_websockets = None
# Python 3.8+ does not honor %HOME% on windows, but this breaks compatibility with youtube-dl
# See https://github.com/yt-dlp/yt-dlp/issues/792
# https://docs.python.org/3/library/os.path.html#os.path.expanduser
@@ -170,13 +159,6 @@ except ImportError:
except ImportError:
compat_pycrypto_AES = None
try:
import brotlicffi as compat_brotli
except ImportError:
try:
import brotli as compat_brotli
except ImportError:
compat_brotli = None
WINDOWS_VT_MODE = False if compat_os_name == 'nt' else None
@@ -198,17 +180,14 @@ def windows_enable_vt_mode(): # TODO: Do this the proper way https://bugs.pytho
compat_basestring = str
compat_chr = chr
compat_filter = filter
compat_input = input
compat_integer_types = (int, )
compat_kwargs = lambda kwargs: kwargs
compat_map = map
compat_numeric_types = (int, float, complex)
compat_str = str
compat_xpath = lambda xpath: xpath
compat_zip = zip
compat_collections_abc = collections.abc
compat_HTMLParser = html.parser.HTMLParser
compat_HTTPError = urllib.error.HTTPError
compat_Struct = struct.Struct
@@ -265,9 +244,7 @@ __all__ = [
'compat_asyncio_run',
'compat_b64decode',
'compat_basestring',
'compat_brotli',
'compat_chr',
'compat_collections_abc',
'compat_cookiejar',
'compat_cookiejar_Cookie',
'compat_cookies',
@@ -277,7 +254,6 @@ __all__ = [
'compat_etree_fromstring',
'compat_etree_register_namespace',
'compat_expanduser',
'compat_filter',
'compat_get_terminal_size',
'compat_getenv',
'compat_getpass',
@@ -289,7 +265,6 @@ __all__ = [
'compat_integer_types',
'compat_itertools_count',
'compat_kwargs',
'compat_map',
'compat_numeric_types',
'compat_ord',
'compat_os_name',
@@ -321,7 +296,6 @@ __all__ = [
'compat_urllib_response',
'compat_urlparse',
'compat_urlretrieve',
'compat_websockets',
'compat_xml_parse_error',
'compat_xpath',
'compat_zip',
+7 -12
View File
@@ -11,11 +11,7 @@ from datetime import datetime, timedelta, timezone
from enum import Enum, auto
from hashlib import pbkdf2_hmac
from .aes import (
aes_cbc_decrypt_bytes,
aes_gcm_decrypt_and_verify_bytes,
unpad_pkcs7,
)
from .aes import aes_cbc_decrypt_bytes, aes_gcm_decrypt_and_verify_bytes
from .compat import (
compat_b64decode,
compat_cookiejar_Cookie,
@@ -454,10 +450,7 @@ def _extract_safari_cookies(profile, logger):
cookies_path = os.path.expanduser('~/Library/Cookies/Cookies.binarycookies')
if not os.path.isfile(cookies_path):
logger.debug('Trying secondary cookie location')
cookies_path = os.path.expanduser('~/Library/Containers/com.apple.Safari/Data/Library/Cookies/Cookies.binarycookies')
if not os.path.isfile(cookies_path):
raise FileNotFoundError('could not find safari cookies database')
raise FileNotFoundError('could not find safari cookies database')
with open(cookies_path, 'rb') as f:
cookies_data = f.read()
@@ -676,7 +669,8 @@ def _get_linux_desktop_environment(env):
return _LinuxDesktopEnvironment.GNOME
elif 'KDE_FULL_SESSION' in env:
return _LinuxDesktopEnvironment.KDE
return _LinuxDesktopEnvironment.OTHER
else:
return _LinuxDesktopEnvironment.OTHER
def _choose_linux_keyring(logger):
@@ -853,9 +847,10 @@ def pbkdf2_sha1(password, salt, iterations, key_length):
def _decrypt_aes_cbc(ciphertext, key, logger, initialization_vector=b' ' * 16):
plaintext = unpad_pkcs7(aes_cbc_decrypt_bytes(ciphertext, key, initialization_vector))
plaintext = aes_cbc_decrypt_bytes(ciphertext, key, initialization_vector)
padding_length = plaintext[-1]
try:
return plaintext.decode('utf-8')
return plaintext[:-padding_length].decode('utf-8')
except UnicodeDecodeError:
logger.warning('failed to decrypt cookie (AES-CBC) because UTF-8 decoding failed. Possibly the key is wrong?', only_once=True)
return None
+1 -3
View File
@@ -30,7 +30,6 @@ def get_suitable_downloader(info_dict, params={}, default=NO_DEFAULT, protocol=N
from .common import FileDownloader
from .dash import DashSegmentsFD
from .f4m import F4mFD
from .fc2 import FC2LiveFD
from .hls import HlsFD
from .http import HttpFD
from .rtmp import RtmpFD
@@ -59,7 +58,6 @@ PROTOCOL_MAP = {
'ism': IsmFD,
'mhtml': MhtmlFD,
'niconico_dmc': NiconicoDmcFD,
'fc2_live': FC2LiveFD,
'websocket_frag': WebSocketFragmentFD,
'youtube_live_chat': YoutubeLiveChatFD,
'youtube_live_chat_replay': YoutubeLiveChatFD,
@@ -119,7 +117,7 @@ def _get_suitable_downloader(info_dict, protocol, params, default):
return FFmpegFD
elif (external_downloader or '').lower() == 'native':
return HlsFD
elif protocol == 'm3u8_native' and get_suitable_downloader(
elif get_suitable_downloader(
info_dict, params, None, protocol='m3u8_frag_urls', to_stdout=info_dict['to_stdout']):
return HlsFD
elif params.get('hls_prefer_native') is True:
+17 -30
View File
@@ -210,41 +210,28 @@ class FileDownloader(object):
def ytdl_filename(self, filename):
return filename + '.ytdl'
def wrap_file_access(action, *, fatal=False):
def outer(func):
def inner(self, *args, **kwargs):
file_access_retries = self.params.get('file_access_retries', 0)
retry = 0
while True:
try:
return func(self, *args, **kwargs)
except (IOError, OSError) as err:
retry = retry + 1
if retry > file_access_retries or err.errno not in (errno.EACCES, errno.EINVAL):
if not fatal:
self.report_error(f'unable to {action} file: {err}')
return
raise
self.to_screen(
f'[download] Unable to {action} file due to file access error. '
f'Retrying (attempt {retry} of {self.format_retries(file_access_retries)}) ...')
time.sleep(0.01)
return inner
return outer
@wrap_file_access('open', fatal=True)
def sanitize_open(self, filename, open_mode):
return sanitize_open(filename, open_mode)
file_access_retries = self.params.get('file_access_retries', 10)
retry = 0
while True:
try:
return sanitize_open(filename, open_mode)
except (IOError, OSError) as err:
retry = retry + 1
if retry > file_access_retries or err.errno not in (errno.EACCES,):
raise
self.to_screen(
'[download] Got file access error. Retrying (attempt %d of %s) ...'
% (retry, self.format_retries(file_access_retries)))
time.sleep(0.01)
@wrap_file_access('remove')
def try_remove(self, filename):
os.remove(filename)
@wrap_file_access('rename')
def try_rename(self, old_filename, new_filename):
if old_filename == new_filename:
return
os.replace(old_filename, new_filename)
try:
os.replace(old_filename, new_filename)
except (IOError, OSError) as err:
self.report_error(f'unable to rename file: {err}')
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
+3 -14
View File
@@ -17,13 +17,11 @@ from ..utils import (
cli_valueless_option,
cli_bool_option,
_configuration_args,
determine_ext,
encodeFilename,
encodeArgument,
handle_youtubedl_headers,
check_executable,
Popen,
remove_end,
)
@@ -159,9 +157,9 @@ class ExternalFD(FragmentFD):
dest.write(decrypt_fragment(fragment, src.read()))
src.close()
if not self.params.get('keep_fragments', False):
self.try_remove(encodeFilename(fragment_filename))
os.remove(encodeFilename(fragment_filename))
dest.close()
self.try_remove(encodeFilename('%s.frag.urls' % tmpfilename))
os.remove(encodeFilename('%s.frag.urls' % tmpfilename))
return 0
@@ -253,7 +251,7 @@ class Aria2cFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-c',
'--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
'--http-accept-gzip=true', '--file-allocation=none', '-x16', '-j16', '-s16']
'--file-allocation=none', '-x16', '-j16', '-s16']
if 'fragments' in info_dict:
cmd += ['--allow-overwrite=true', '--allow-piece-length-change=true']
else:
@@ -465,15 +463,6 @@ class FFmpegFD(ExternalFD):
args += ['-f', 'flv']
elif ext == 'mp4' and tmpfilename == '-':
args += ['-f', 'mpegts']
elif ext == 'unknown_video':
ext = determine_ext(remove_end(tmpfilename, '.part'))
if ext == 'unknown_video':
self.report_warning(
'The video format is unknown and cannot be downloaded by ffmpeg. '
'Explicitly set the extension in the filename to attempt download in that format')
else:
self.report_warning(f'The video format is unknown. Trying to download as {ext} according to the filename')
args += ['-f', EXT_TO_OUT_FORMATS.get(ext, ext)]
else:
args += ['-f', EXT_TO_OUT_FORMATS.get(ext, ext)]
-41
View File
@@ -1,41 +0,0 @@
from __future__ import division, unicode_literals
import threading
from .common import FileDownloader
from .external import FFmpegFD
class FC2LiveFD(FileDownloader):
"""
Downloads FC2 live without being stopped. <br>
Note, this is not a part of public API, and will be removed without notice.
DO NOT USE
"""
def real_download(self, filename, info_dict):
ws = info_dict['ws']
heartbeat_lock = threading.Lock()
heartbeat_state = [None, 1]
def heartbeat():
try:
heartbeat_state[1] += 1
ws.send('{"name":"heartbeat","arguments":{},"id":%d}' % heartbeat_state[1])
except Exception:
self.to_screen('[fc2:live] Heartbeat failed')
with heartbeat_lock:
heartbeat_state[0] = threading.Timer(30, heartbeat)
heartbeat_state[0]._daemonic = True
heartbeat_state[0].start()
heartbeat()
new_info_dict = info_dict.copy()
new_info_dict.update({
'ws': None,
'protocol': 'live_ffmpeg',
})
return FFmpegFD(self.ydl, self.params or {}).download(filename, new_info_dict)
+17 -40
View File
@@ -14,7 +14,7 @@ except ImportError:
from .common import FileDownloader
from .http import HttpFD
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..aes import aes_cbc_decrypt_bytes
from ..compat import (
compat_os_name,
compat_urllib_error,
@@ -25,7 +25,6 @@ from ..utils import (
error_to_compat_str,
encodeFilename,
sanitized_Request,
traverse_obj,
)
@@ -137,12 +136,7 @@ class FragmentFD(FileDownloader):
if fragment_info_dict.get('filetime'):
ctx['fragment_filetime'] = fragment_info_dict.get('filetime')
ctx['fragment_filename_sanitized'] = fragment_filename
try:
return True, self._read_fragment(ctx)
except FileNotFoundError:
if not info_dict.get('is_live'):
raise
return False, None
return True, self._read_fragment(ctx)
def _read_fragment(self, ctx):
down, frag_sanitized = self.sanitize_open(ctx['fragment_filename_sanitized'], 'rb')
@@ -159,7 +153,7 @@ class FragmentFD(FileDownloader):
if self.__do_ytdl_file(ctx):
self._write_ytdl_file(ctx)
if not self.params.get('keep_fragments', False):
self.try_remove(encodeFilename(ctx['fragment_filename_sanitized']))
os.remove(encodeFilename(ctx['fragment_filename_sanitized']))
del ctx['fragment_filename_sanitized']
def _prepare_frag_download(self, ctx):
@@ -178,7 +172,7 @@ class FragmentFD(FileDownloader):
dl = HttpQuietDownloader(
self.ydl,
{
'continuedl': self.params.get('continuedl', True),
'continuedl': True,
'quiet': self.params.get('quiet'),
'noprogress': True,
'ratelimit': self.params.get('ratelimit'),
@@ -305,7 +299,7 @@ class FragmentFD(FileDownloader):
if self.__do_ytdl_file(ctx):
ytdl_filename = encodeFilename(self.ytdl_filename(ctx['filename']))
if os.path.isfile(ytdl_filename):
self.try_remove(ytdl_filename)
os.remove(ytdl_filename)
elapsed = time.time() - ctx['started']
if ctx['tmpfilename'] == '-':
@@ -372,7 +366,8 @@ class FragmentFD(FileDownloader):
# not what it decrypts to.
if self.params.get('test', False):
return frag_content
return unpad_pkcs7(aes_cbc_decrypt_bytes(frag_content, decrypt_info['KEY'], iv))
decrypted_data = aes_cbc_decrypt_bytes(frag_content, decrypt_info['KEY'], iv)
return decrypted_data[:-decrypted_data[-1]]
return decrypt_fragment
@@ -388,7 +383,6 @@ class FragmentFD(FileDownloader):
max_workers = self.params.get('concurrent_fragment_downloads', 1)
if max_progress > 1:
self._prepare_multiline_status(max_progress)
is_live = any(traverse_obj(args, (..., 2, 'is_live'), default=[]))
def thread_func(idx, ctx, fragments, info_dict, tpe):
ctx['max_progress'] = max_progress
@@ -402,43 +396,25 @@ class FragmentFD(FileDownloader):
def __exit__(self, exc_type, exc_val, exc_tb):
pass
if compat_os_name == 'nt':
def bindoj_result(future):
while True:
try:
return future.result(0.1)
except KeyboardInterrupt:
raise
except concurrent.futures.TimeoutError:
continue
else:
def bindoj_result(future):
return future.result()
def interrupt_trigger_iter(fg):
for f in fg:
if not interrupt_trigger[0]:
break
yield f
spins = []
if compat_os_name == 'nt':
self.report_warning('Ctrl+C does not work on Windows when used with parallel threads. '
'This is a known issue and patches are welcome')
for idx, (ctx, fragments, info_dict) in enumerate(args):
tpe = FTPE(math.ceil(max_workers / max_progress))
job = tpe.submit(thread_func, idx, ctx, interrupt_trigger_iter(fragments), info_dict, tpe)
job = tpe.submit(thread_func, idx, ctx, fragments, info_dict, tpe)
spins.append((tpe, job))
result = True
for tpe, job in spins:
try:
result = result and bindoj_result(job)
result = result and job.result()
except KeyboardInterrupt:
interrupt_trigger[0] = False
finally:
tpe.shutdown(wait=True)
if not interrupt_trigger[0] and not is_live:
if not interrupt_trigger[0]:
raise KeyboardInterrupt()
# we expect the user wants to stop and DO WANT the preceding postprocessors to run;
# so returning a intermediate result here instead of KeyboardInterrupt on live
return result
def download_and_append_fragments(
@@ -456,11 +432,10 @@ class FragmentFD(FileDownloader):
pack_func = lambda frag_content, _: frag_content
def download_fragment(fragment, ctx):
if not interrupt_trigger[0]:
return False, fragment['frag_index']
frag_index = ctx['fragment_index'] = fragment['frag_index']
ctx['last_error'] = None
if not interrupt_trigger[0]:
return False, frag_index
headers = info_dict.get('http_headers', {}).copy()
byte_range = fragment.get('byte_range')
if byte_range:
@@ -526,6 +501,8 @@ class FragmentFD(FileDownloader):
self.report_warning('The download speed shown is only of one thread. This is a known issue and patches are welcome')
with tpe or concurrent.futures.ThreadPoolExecutor(max_workers) as pool:
for fragment, frag_content, frag_index, frag_filename in pool.map(_download_fragment, fragments):
if not interrupt_trigger[0]:
break
ctx['fragment_filename_sanitized'] = frag_filename
ctx['fragment_index'] = frag_index
result = append_fragment(decrypt_fragment(fragment, frag_content), frag_index, ctx)
+18 -30
View File
@@ -5,6 +5,7 @@ import os
import socket
import time
import random
import re
from .common import FileDownloader
from ..compat import (
@@ -15,7 +16,6 @@ from ..utils import (
ContentTooShortError,
encodeFilename,
int_or_none,
parse_http_range,
sanitized_Request,
ThrottledDownload,
write_xattr,
@@ -59,9 +59,6 @@ class HttpFD(FileDownloader):
ctx.chunk_size = None
throttle_start = None
# parse given Range
req_start, req_end, _ = parse_http_range(headers.get('Range'))
if self.params.get('continuedl', True):
# Establish possible resume length
if os.path.isfile(encodeFilename(ctx.tmpfilename)):
@@ -94,9 +91,6 @@ class HttpFD(FileDownloader):
if not is_test and chunk_size else chunk_size)
if ctx.resume_len > 0:
range_start = ctx.resume_len
if req_start is not None:
# offset the beginning of Range to be within request
range_start += req_start
if ctx.is_resume:
self.report_resuming_byte(ctx.resume_len)
ctx.open_mode = 'ab'
@@ -105,17 +99,7 @@ class HttpFD(FileDownloader):
else:
range_start = None
ctx.is_resume = False
if ctx.chunk_size:
chunk_aware_end = range_start + ctx.chunk_size - 1
# we're not allowed to download outside Range
range_end = chunk_aware_end if req_end is None else min(chunk_aware_end, req_end)
elif req_end is not None:
# there's no need for chunked downloads, so download until the end of Range
range_end = req_end
else:
range_end = None
range_end = range_start + ctx.chunk_size - 1 if ctx.chunk_size else None
if range_end and ctx.data_len is not None and range_end >= ctx.data_len:
range_end = ctx.data_len - 1
has_range = range_start is not None
@@ -140,19 +124,23 @@ class HttpFD(FileDownloader):
# https://github.com/ytdl-org/youtube-dl/issues/6057#issuecomment-126129799)
if has_range:
content_range = ctx.data.headers.get('Content-Range')
content_range_start, content_range_end, content_len = parse_http_range(content_range)
if content_range_start is not None and range_start == content_range_start:
if content_range:
content_range_m = re.search(r'bytes (\d+)-(\d+)?(?:/(\d+))?', content_range)
# Content-Range is present and matches requested Range, resume is possible
accept_content_len = (
# Non-chunked download
not ctx.chunk_size
# Chunked download and requested piece or
# its part is promised to be served
or content_range_end == range_end
or content_len < range_end)
if accept_content_len:
ctx.data_len = content_len
return
if content_range_m:
if range_start == int(content_range_m.group(1)):
content_range_end = int_or_none(content_range_m.group(2))
content_len = int_or_none(content_range_m.group(3))
accept_content_len = (
# Non-chunked download
not ctx.chunk_size
# Chunked download and requested piece or
# its part is promised to be served
or content_range_end == range_end
or content_len < range_end)
if accept_content_len:
ctx.data_len = content_len
return
# Content-Range is either not present or invalid. Assuming remote webserver is
# trying to send the whole file, resume is not possible, so wiping the local file
# and performing entire redownload
+2 -5
View File
@@ -5,12 +5,9 @@ import threading
try:
import websockets
except (ImportError, SyntaxError):
# websockets 3.10 on python 3.6 causes SyntaxError
# See https://github.com/yt-dlp/yt-dlp/issues/2633
has_websockets = False
else:
has_websockets = True
except ImportError:
has_websockets = False
from .common import FileDownloader
from .external import FFmpegFD
-3
View File
@@ -22,9 +22,6 @@ class YoutubeLiveChatFD(FragmentFD):
def real_download(self, filename, info_dict):
video_id = info_dict['video_id']
self.to_screen('[%s] Downloading live chat' % self.FD_NAME)
if not self.params.get('skip_download'):
self.report_warning('Live chat download runs until the livestream ends. '
'If you wish to download the video simultaneously, run a separate yt-dlp instance')
fragment_retries = self.params.get('fragment_retries', 0)
test = self.params.get('test', False)
+5 -4
View File
@@ -213,7 +213,7 @@ class ABCIViewIE(InfoExtractor):
'hdnea': token,
})
for sd in ('1080', '720', 'sd', 'sd-low'):
for sd in ('720', 'sd', 'sd-low'):
sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str)
if not sd_url:
@@ -300,10 +300,11 @@ class ABCIViewShowSeriesIE(InfoExtractor):
unescapeHTML(webpage_data).encode('utf-8').decode('unicode_escape'), show_id)
video_data = video_data['route']['pageData']['_embedded']
highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl'])
if not self._yes_playlist(show_id, bool(highlight), video_label='highlight video'):
return self.url_result(highlight, ie=ABCIViewIE.ie_key())
if self.get_param('noplaylist') and 'highlightVideo' in video_data:
self.to_screen('Downloading just the highlight video because of --no-playlist')
return self.url_result(video_data['highlightVideo']['shareUrl'], ie=ABCIViewIE.ie_key())
self.to_screen(f'Downloading playlist {show_id} - add --no-playlist to just download the highlight video')
series = video_data['selectedSeries']
return {
'_type': 'playlist',
-484
View File
@@ -1,484 +0,0 @@
import io
import json
import time
import hashlib
import hmac
import re
import struct
from base64 import urlsafe_b64encode
from binascii import unhexlify
from .common import InfoExtractor
from ..aes import aes_ecb_decrypt
from ..compat import (
compat_urllib_response,
compat_urllib_parse_urlparse,
compat_urllib_request,
)
from ..utils import (
ExtractorError,
decode_base,
int_or_none,
random_uuidv4,
request_to_url,
time_seconds,
update_url_query,
traverse_obj,
intlist_to_bytes,
bytes_to_intlist,
urljoin,
)
# NOTE: network handler related code is temporary thing until network stack overhaul PRs are merged (#2861/#2862)
def add_opener(ydl, handler):
''' Add a handler for opening URLs, like _download_webpage '''
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
assert isinstance(ydl._opener, compat_urllib_request.OpenerDirector)
ydl._opener.add_handler(handler)
def remove_opener(ydl, handler):
'''
Remove handler(s) for opening URLs
@param handler Either handler object itself or handler type.
Specifying handler type will remove all handler which isinstance returns True.
'''
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
opener = ydl._opener
assert isinstance(ydl._opener, compat_urllib_request.OpenerDirector)
if isinstance(handler, (type, tuple)):
find_cp = lambda x: isinstance(x, handler)
else:
find_cp = lambda x: x is handler
removed = []
for meth in dir(handler):
if meth in ["redirect_request", "do_open", "proxy_open"]:
# oops, coincidental match
continue
i = meth.find("_")
protocol = meth[:i]
condition = meth[i + 1:]
if condition.startswith("error"):
j = condition.find("_") + i + 1
kind = meth[j + 1:]
try:
kind = int(kind)
except ValueError:
pass
lookup = opener.handle_error.get(protocol, {})
opener.handle_error[protocol] = lookup
elif condition == "open":
kind = protocol
lookup = opener.handle_open
elif condition == "response":
kind = protocol
lookup = opener.process_response
elif condition == "request":
kind = protocol
lookup = opener.process_request
else:
continue
handlers = lookup.setdefault(kind, [])
if handlers:
handlers[:] = [x for x in handlers if not find_cp(x)]
removed.append(x for x in handlers if find_cp(x))
if removed:
for x in opener.handlers:
if find_cp(x):
x.add_parent(None)
opener.handlers[:] = [x for x in opener.handlers if not find_cp(x)]
class AbemaLicenseHandler(compat_urllib_request.BaseHandler):
handler_order = 499
STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
def __init__(self, ie: 'AbemaTVIE'):
# the protcol that this should really handle is 'abematv-license://'
# abematv_license_open is just a placeholder for development purposes
# ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510
setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open'))
self.ie = ie
def _get_videokey_from_ticket(self, ticket):
to_show = self.ie._downloader.params.get('verbose', False)
media_token = self.ie._get_media_token(to_show=to_show)
license_response = self.ie._download_json(
'https://license.abema.io/abematv-hls', None, note='Requesting playback license' if to_show else False,
query={'t': media_token},
data=json.dumps({
'kv': 'a',
'lt': ticket
}).encode('utf-8'),
headers={
'Content-Type': 'application/json',
})
res = decode_base(license_response['k'], self.STRTABLE)
encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
h = hmac.new(
unhexlify(self.HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode('utf-8'),
digestmod=hashlib.sha256)
enckey = bytes_to_intlist(h.digest())
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url):
url = request_to_url(url)
ticket = compat_urllib_parse_urlparse(url).netloc
response_data = self._get_videokey_from_ticket(ticket)
return compat_urllib_response.addinfourl(io.BytesIO(response_data), headers={
'Content-Length': len(response_data),
}, url=url, code=200)
class AbemaTVBaseIE(InfoExtractor):
def _extract_breadcrumb_list(self, webpage, video_id):
for jld in re.finditer(
r'(?is)</span></li></ul><script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
webpage):
jsonld = self._parse_json(jld.group('json_ld'), video_id, fatal=False)
if jsonld:
if jsonld.get('@type') != 'BreadcrumbList':
continue
trav = traverse_obj(jsonld, ('itemListElement', ..., 'name'))
if trav:
return trav
return []
class AbemaTVIE(AbemaTVBaseIE):
_VALID_URL = r'https?://abema\.tv/(?P<type>now-on-air|video/episode|channels/.+?/slots)/(?P<id>[^?/]+)'
_NETRC_MACHINE = 'abematv'
_TESTS = [{
'url': 'https://abema.tv/video/episode/194-25_s2_p1',
'info_dict': {
'id': '194-25_s2_p1',
'title': '第1話 「チーズケーキ」 「モーニング再び」',
'series': '異世界食堂2',
'series_number': 2,
'episode': '第1話 「チーズケーキ」 「モーニング再び」',
'episode_number': 1,
},
'skip': 'expired',
}, {
'url': 'https://abema.tv/channels/anime-live2/slots/E8tvAnMJ7a9a5d',
'info_dict': {
'id': 'E8tvAnMJ7a9a5d',
'title': 'ゆるキャン△ SEASON2 全話一挙【無料ビデオ72時間】',
'series': 'ゆるキャン△ SEASON',
'episode': 'ゆるキャン△ SEASON2 全話一挙【無料ビデオ72時間】',
'series_number': 2,
'episode_number': 1,
'description': 'md5:9c5a3172ae763278f9303922f0ea5b17',
},
'skip': 'expired',
}, {
'url': 'https://abema.tv/video/episode/87-877_s1282_p31047',
'info_dict': {
'id': 'E8tvAnMJ7a9a5d',
'title': '第5話『光射す』',
'description': 'md5:56d4fc1b4f7769ded5f923c55bb4695d',
'thumbnail': r're:https://hayabusa\.io/.+',
'series': '相棒',
'episode': '第5話『光射す』',
},
'skip': 'expired',
}, {
'url': 'https://abema.tv/now-on-air/abema-anime',
'info_dict': {
'id': 'abema-anime',
# this varies
# 'title': '女子高生の無駄づかい 全話一挙【無料ビデオ72時間】',
'description': 'md5:55f2e61f46a17e9230802d7bcc913d5f',
'is_live': True,
},
'skip': 'Not supported until yt-dlp implements native live downloader OR AbemaTV can start a local HTTP server',
}]
_USERTOKEN = None
_DEVICE_ID = None
_TIMETABLE = None
_MEDIATOKEN = None
_SECRETKEY = b'v+Gjs=25Aw5erR!J8ZuvRrCx*rGswhB&qdHd_SYerEWdU&a?3DzN9BRbp5KwY4hEmcj5#fykMjJ=AuWz5GSMY-d@H7DMEh3M@9n2G552Us$$k9cD=3TxwWe86!x#Zyhe'
def _generate_aks(self, deviceid):
deviceid = deviceid.encode('utf-8')
# add 1 hour and then drop minute and secs
ts_1hour = int((time_seconds(hours=9) // 3600 + 1) * 3600)
time_struct = time.gmtime(ts_1hour)
ts_1hour_str = str(ts_1hour).encode('utf-8')
tmp = None
def mix_once(nonce):
nonlocal tmp
h = hmac.new(self._SECRETKEY, digestmod=hashlib.sha256)
h.update(nonce)
tmp = h.digest()
def mix_tmp(count):
nonlocal tmp
for i in range(count):
mix_once(tmp)
def mix_twist(nonce):
nonlocal tmp
mix_once(urlsafe_b64encode(tmp).rstrip(b'=') + nonce)
mix_once(self._SECRETKEY)
mix_tmp(time_struct.tm_mon)
mix_twist(deviceid)
mix_tmp(time_struct.tm_mday % 5)
mix_twist(ts_1hour_str)
mix_tmp(time_struct.tm_hour % 5)
return urlsafe_b64encode(tmp).rstrip(b'=').decode('utf-8')
def _get_device_token(self):
if self._USERTOKEN:
return self._USERTOKEN
self._DEVICE_ID = random_uuidv4()
aks = self._generate_aks(self._DEVICE_ID)
user_data = self._download_json(
'https://api.abema.io/v1/users', None, note='Authorizing',
data=json.dumps({
'deviceId': self._DEVICE_ID,
'applicationKeySecret': aks,
}).encode('utf-8'),
headers={
'Content-Type': 'application/json',
})
self._USERTOKEN = user_data['token']
# don't allow adding it 2 times or more, though it's guarded
remove_opener(self._downloader, AbemaLicenseHandler)
add_opener(self._downloader, AbemaLicenseHandler(self))
return self._USERTOKEN
def _get_media_token(self, invalidate=False, to_show=True):
if not invalidate and self._MEDIATOKEN:
return self._MEDIATOKEN
self._MEDIATOKEN = self._download_json(
'https://api.abema.io/v1/media/token', None, note='Fetching media token' if to_show else False,
query={
'osName': 'android',
'osVersion': '6.0.1',
'osLang': 'ja_JP',
'osTimezone': 'Asia/Tokyo',
'appId': 'tv.abema',
'appVersion': '3.27.1'
}, headers={
'Authorization': 'bearer ' + self._get_device_token()
})['token']
return self._MEDIATOKEN
def _real_initialize(self):
self._login()
def _login(self):
username, password = self._get_login_info()
# No authentication to be performed
if not username:
return True
if '@' in username: # don't strictly check if it's email address or not
ep, method = 'user/email', 'email'
else:
ep, method = 'oneTimePassword', 'userId'
login_response = self._download_json(
f'https://api.abema.io/v1/auth/{ep}', None, note='Logging in',
data=json.dumps({
method: username,
'password': password
}).encode('utf-8'), headers={
'Authorization': 'bearer ' + self._get_device_token(),
'Origin': 'https://abema.tv',
'Referer': 'https://abema.tv/',
'Content-Type': 'application/json',
})
self._USERTOKEN = login_response['token']
self._get_media_token(True)
def _real_extract(self, url):
# starting download using infojson from this extractor is undefined behavior,
# and never be fixed in the future; you must trigger downloads by directly specifing URL.
# (unless there's a way to hook before downloading by extractor)
video_id, video_type = self._match_valid_url(url).group('id', 'type')
headers = {
'Authorization': 'Bearer ' + self._get_device_token(),
}
video_type = video_type.split('/')[-1]
webpage = self._download_webpage(url, video_id)
canonical_url = self._search_regex(
r'<link\s+rel="canonical"\s*href="(.+?)"', webpage, 'canonical URL',
default=url)
info = self._search_json_ld(webpage, video_id, default={})
title = self._search_regex(
r'<span\s*class=".+?EpisodeTitleBlock__title">(.+?)</span>', webpage, 'title', default=None)
if not title:
jsonld = None
for jld in re.finditer(
r'(?is)<span\s*class="com-m-Thumbnail__image">(?:</span>)?<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
webpage):
jsonld = self._parse_json(jld.group('json_ld'), video_id, fatal=False)
if jsonld:
break
if jsonld:
title = jsonld.get('caption')
if not title and video_type == 'now-on-air':
if not self._TIMETABLE:
# cache the timetable because it goes to 5MiB in size (!!)
self._TIMETABLE = self._download_json(
'https://api.abema.io/v1/timetable/dataSet?debug=false', video_id,
headers=headers)
now = time_seconds(hours=9)
for slot in self._TIMETABLE.get('slots', []):
if slot.get('channelId') != video_id:
continue
if slot['startAt'] <= now and now < slot['endAt']:
title = slot['title']
break
# read breadcrumb on top of page
breadcrumb = self._extract_breadcrumb_list(webpage, video_id)
if breadcrumb:
# breadcrumb list translates to: (example is 1st test for this IE)
# Home > Anime (genre) > Isekai Shokudo 2 (series name) > Episode 1 "Cheese cakes" "Morning again" (episode title)
# hence this works
info['series'] = breadcrumb[-2]
info['episode'] = breadcrumb[-1]
if not title:
title = info['episode']
description = self._html_search_regex(
(r'<p\s+class="com-video-EpisodeDetailsBlock__content"><span\s+class=".+?">(.+?)</span></p><div',
r'<span\s+class=".+?SlotSummary.+?">(.+?)</span></div><div',),
webpage, 'description', default=None, group=1)
if not description:
og_desc = self._html_search_meta(
('description', 'og:description', 'twitter:description'), webpage)
if og_desc:
description = re.sub(r'''(?sx)
^(.+?)(?:
アニメの動画を無料で見るならABEMA| # anime
.+ # applies for most of categories
)?
''', r'\1', og_desc)
# canonical URL may contain series and episode number
mobj = re.search(r's(\d+)_p(\d+)$', canonical_url)
if mobj:
seri = int_or_none(mobj.group(1), default=float('inf'))
epis = int_or_none(mobj.group(2), default=float('inf'))
info['series_number'] = seri if seri < 100 else None
# some anime like Detective Conan (though not available in AbemaTV)
# has more than 1000 episodes (1026 as of 2021/11/15)
info['episode_number'] = epis if epis < 2000 else None
is_live, m3u8_url = False, None
if video_type == 'now-on-air':
is_live = True
channel_url = 'https://api.abema.io/v1/channels'
if video_id == 'news-global':
channel_url = update_url_query(channel_url, {'division': '1'})
onair_channels = self._download_json(channel_url, video_id)
for ch in onair_channels['channels']:
if video_id == ch['id']:
m3u8_url = ch['playback']['hls']
break
else:
raise ExtractorError(f'Cannot find on-air {video_id} channel.', expected=True)
elif video_type == 'episode':
api_response = self._download_json(
f'https://api.abema.io/v1/video/programs/{video_id}', video_id,
note='Checking playability',
headers=headers)
ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType'), default=[])
if 3 not in ondemand_types:
# cannot acquire decryption key for these streams
self.report_warning('This is a premium-only stream')
m3u8_url = f'https://vod-abematv.akamaized.net/program/{video_id}/playlist.m3u8'
elif video_type == 'slots':
api_response = self._download_json(
f'https://api.abema.io/v1/media/slots/{video_id}', video_id,
note='Checking playability',
headers=headers)
if not traverse_obj(api_response, ('slot', 'flags', 'timeshiftFree'), default=False):
self.report_warning('This is a premium-only stream')
m3u8_url = f'https://vod-abematv.akamaized.net/slot/{video_id}/playlist.m3u8'
else:
raise ExtractorError('Unreachable')
if is_live:
self.report_warning("This is a livestream; yt-dlp doesn't support downloading natively, but FFmpeg cannot handle m3u8 manifests from AbemaTV")
self.report_warning('Please consider using Streamlink to download these streams (https://github.com/streamlink/streamlink)')
formats = self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4', live=is_live)
info.update({
'id': video_id,
'title': title,
'description': description,
'formats': formats,
'is_live': is_live,
})
return info
class AbemaTVTitleIE(AbemaTVBaseIE):
_VALID_URL = r'https?://abema\.tv/video/title/(?P<id>[^?/]+)'
_TESTS = [{
'url': 'https://abema.tv/video/title/90-1597',
'info_dict': {
'id': '90-1597',
'title': 'シャッフルアイランド',
},
'playlist_mincount': 2,
}, {
'url': 'https://abema.tv/video/title/193-132',
'info_dict': {
'id': '193-132',
'title': '真心が届く~僕とスターのオフィス・ラブ!?~',
},
'playlist_mincount': 16,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
playlist_title, breadcrumb = None, self._extract_breadcrumb_list(webpage, video_id)
if breadcrumb:
playlist_title = breadcrumb[-1]
playlist = [
self.url_result(urljoin('https://abema.tv/', mobj.group(1)))
for mobj in re.finditer(r'<li\s*class=".+?EpisodeList.+?"><a\s*href="(/[^"]+?)"', webpage)]
return self.playlist_result(playlist, playlist_title=playlist_title, playlist_id=video_id)
+10 -6
View File
@@ -8,10 +8,11 @@ import os
import random
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..aes import aes_cbc_decrypt
from ..compat import (
compat_HTTPError,
compat_b64decode,
compat_ord,
)
from ..utils import (
ass_subtitles_timecode,
@@ -83,11 +84,14 @@ class ADNIE(InfoExtractor):
return None
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = unpad_pkcs7(aes_cbc_decrypt_bytes(
compat_b64decode(enc_subtitles[24:]),
binascii.unhexlify(self._K + 'ab9f52f5baae7c72'),
compat_b64decode(enc_subtitles[:24])))
subtitles_json = self._parse_json(dec_subtitles.decode(), None, fatal=False)
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
bytes_to_intlist(binascii.unhexlify(self._K + 'ab9f52f5baae7c72')),
bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
))
subtitles_json = self._parse_json(
dec_subtitles[:-compat_ord(dec_subtitles[-1])].decode(),
None, fatal=False)
if not subtitles_json:
return None
-51
View File
@@ -1345,11 +1345,6 @@ MSO_INFO = {
'username_field': 'username',
'password_field': 'password',
},
'Suddenlink': {
'name': 'Suddenlink',
'username_field': 'username',
'password_field': 'password',
},
}
@@ -1640,52 +1635,6 @@ class AdobePassIE(InfoExtractor):
urlh.geturl(), video_id, 'Sending final bookend',
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Suddenlink':
# Suddenlink is similar to SlingTV in using a tab history count and a meta refresh,
# but they also do a dynmaic redirect using javascript that has to be followed as well
first_bookend_page, urlh = post_form(
provider_redirect_page_res, 'Pressing Continue...')
hidden_data = self._hidden_inputs(first_bookend_page)
hidden_data['history_val'] = 1
provider_login_redirect_page = self._download_webpage(
urlh.geturl(), video_id, 'Sending First Bookend',
query=hidden_data)
provider_tryauth_url = self._html_search_regex(
r'url:\s*[\'"]([^\'"]+)', provider_login_redirect_page, 'ajaxurl')
provider_tryauth_page = self._download_webpage(
provider_tryauth_url, video_id, 'Submitting TryAuth',
query=hidden_data)
provider_login_page_res = self._download_webpage_handle(
f'https://authorize.suddenlink.net/saml/module.php/authSynacor/login.php?AuthState={provider_tryauth_page}',
video_id, 'Getting Login Page',
query=hidden_data)
provider_association_redirect, urlh = post_form(
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password
})
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.geturl())
last_bookend_page, urlh = self._download_webpage_handle(
provider_refresh_redirect_url, video_id,
'Downloading Auth Association Redirect Page')
hidden_data = self._hidden_inputs(last_bookend_page)
hidden_data['history_val'] = 3
mvpd_confirm_page_res = self._download_webpage_handle(
urlh.geturl(), video_id, 'Sending Final Bookend',
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
else:
# Some providers (e.g. DIRECTV NOW) have another meta refresh
+6 -15
View File
@@ -416,35 +416,26 @@ class AfreecaTVLiveIE(AfreecaTVIE):
def _real_extract(self, url):
broadcaster_id, broadcast_no = self._match_valid_url(url).group('id', 'bno')
password = self.get_param('videopassword')
info = self._download_json(self._LIVE_API_URL, broadcaster_id, fatal=False,
data=urlencode_postdata({'bid': broadcaster_id})) or {}
channel_info = info.get('CHANNEL') or {}
broadcaster_id = channel_info.get('BJID') or broadcaster_id
broadcast_no = channel_info.get('BNO') or broadcast_no
password_protected = channel_info.get('BPWD')
if not broadcast_no:
raise ExtractorError(f'Unable to extract broadcast number ({broadcaster_id} may not be live)', expected=True)
if password_protected == 'Y' and password is None:
raise ExtractorError(
'This livestream is protected by a password, use the --video-password option',
expected=True)
formats = []
quality_key = qualities(self._QUALITIES)
for quality_str in self._QUALITIES:
params = {
'bno': broadcast_no,
'stream_type': 'common',
'type': 'aid',
'quality': quality_str,
}
if password is not None:
params['pwd'] = password
aid_response = self._download_json(
self._LIVE_API_URL, broadcast_no, fatal=False,
data=urlencode_postdata(params),
data=urlencode_postdata({
'bno': broadcast_no,
'stream_type': 'common',
'type': 'aid',
'quality': quality_str,
}),
note=f'Downloading access token for {quality_str} stream',
errnote=f'Unable to download access token for {quality_str} stream')
aid = traverse_obj(aid_response, ('CHANNEL', 'AID'))
+1 -1
View File
@@ -18,7 +18,7 @@ class AliExpressLiveIE(InfoExtractor):
'id': '2800002704436634',
'ext': 'mp4',
'title': 'CASIMA7.22',
'thumbnail': r're:https?://.*\.jpg',
'thumbnail': r're:http://.*\.jpg',
'uploader': 'CASIMA Official Store',
'timestamp': 1500717600,
'upload_date': '20170722',
-87
View File
@@ -1,87 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
dict_get,
get_element_by_class,
int_or_none,
unified_strdate,
url_or_none,
)
class Alsace20TVBaseIE(InfoExtractor):
def _extract_video(self, video_id, url=None):
info = self._download_json(
'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
video_id) or {}
title = info.get('titre')
formats = []
for res, fmt_url in (info.get('files') or {}).items():
formats.extend(
self._extract_smil_formats(fmt_url, video_id, fatal=False)
if '/smil:_' in fmt_url
else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
self._sort_formats(formats)
webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
return {
'id': video_id,
'title': title,
'formats': formats,
'description': clean_html(get_element_by_class('wysiwyg', webpage)),
'upload_date': upload_date,
'thumbnail': thumbnail,
'duration': int_or_none(self._og_search_property('video:duration', webpage) if webpage else None),
'view_count': int_or_none(info.get('nb_vues')),
}
class Alsace20TVIE(Alsace20TVBaseIE):
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/(?:[\w-]+/)+[\w-]+-(?P<id>[\w]+)'
_TESTS = [{
'url': 'https://www.alsace20.tv/VOD/Actu/JT/Votre-JT-jeudi-3-fevrier-lyNHCXpYJh.html',
'info_dict': {
'id': 'lyNHCXpYJh',
'ext': 'mp4',
'description': 'md5:fc0bc4a0692d3d2dba4524053de4c7b7',
'title': 'Votre JT du jeudi 3 février',
'upload_date': '20220203',
'thumbnail': r're:https?://.+\.jpg',
'duration': 1073,
'view_count': int,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video(video_id, url)
class Alsace20TVEmbedIE(Alsace20TVBaseIE):
_VALID_URL = r'https?://(?:www\.)?alsace20\.tv/emb/(?P<id>[\w]+)'
_TESTS = [{
'url': 'https://www.alsace20.tv/emb/lyNHCXpYJh',
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
'info_dict': {
'id': 'lyNHCXpYJh',
'ext': 'mp4',
'title': 'Votre JT du jeudi 3 février',
'upload_date': '20220203',
'thumbnail': r're:https?://.+\.jpg',
'view_count': int,
},
'params': {
'format': 'bestvideo',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
return self._extract_video(video_id)
-143
View File
@@ -1,143 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import urllib.parse
from .common import InfoExtractor
from ..utils import (
HEADRequest,
ExtractorError,
determine_ext,
scale_thumbnails_to_max_format_width,
unescapeHTML,
)
class Ant1NewsGrBaseIE(InfoExtractor):
def _download_and_extract_api_data(self, video_id, netloc, cid=None):
url = f'{self.http_scheme()}//{netloc}{self._API_PATH}'
info = self._download_json(url, video_id, query={'cid': cid or video_id})
try:
source = info['url']
except KeyError:
raise ExtractorError('no source found for %s' % video_id)
formats, subs = (self._extract_m3u8_formats_and_subtitles(source, video_id, 'mp4')
if determine_ext(source) == 'm3u8' else ([{'url': source}], {}))
self._sort_formats(formats)
thumbnails = scale_thumbnails_to_max_format_width(
formats, [{'url': info['thumb']}], r'(?<=/imgHandler/)\d+')
return {
'id': video_id,
'title': info.get('title'),
'thumbnails': thumbnails,
'formats': formats,
'subtitles': subs,
}
class Ant1NewsGrWatchIE(Ant1NewsGrBaseIE):
IE_NAME = 'ant1newsgr:watch'
IE_DESC = 'ant1news.gr videos'
_VALID_URL = r'https?://(?P<netloc>(?:www\.)?ant1news\.gr)/watch/(?P<id>\d+)/'
_API_PATH = '/templates/data/player'
_TESTS = [{
'url': 'https://www.ant1news.gr/watch/1506168/ant1-news-09112021-stis-18-45',
'md5': '95925e6b32106754235f2417e0d2dfab',
'info_dict': {
'id': '1506168',
'ext': 'mp4',
'title': 'md5:0ad00fa66ecf8aa233d26ab0dba7514a',
'description': 'md5:18665af715a6dcfeac1d6153a44f16b0',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/26d46bf6-8158-4f02-b197-7096c714b2de.jpg',
},
}]
def _real_extract(self, url):
video_id, netloc = self._match_valid_url(url).group('id', 'netloc')
webpage = self._download_webpage(url, video_id)
info = self._download_and_extract_api_data(video_id, netloc)
info['description'] = self._og_search_description(webpage)
return info
class Ant1NewsGrArticleIE(Ant1NewsGrBaseIE):
IE_NAME = 'ant1newsgr:article'
IE_DESC = 'ant1news.gr articles'
_VALID_URL = r'https?://(?:www\.)?ant1news\.gr/[^/]+/article/(?P<id>\d+)/'
_TESTS = [{
'url': 'https://www.ant1news.gr/afieromata/article/549468/o-tzeims-mpont-sta-meteora-oi-apeiles-kai-o-xesikomos-ton-kalogeron',
'md5': '294f18331bb516539d72d85a82887dcc',
'info_dict': {
'id': '_xvg/m_cmbatw=',
'ext': 'mp4',
'title': 'md5:a93e8ecf2e4073bfdffcb38f59945411',
'timestamp': 1603092840,
'upload_date': '20201019',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/756206d2-d640-40e2-b201-3555abdfc0db.jpg',
},
}, {
'url': 'https://ant1news.gr/Society/article/620286/symmoria-anilikon-dikigoros-thymaton-ithelan-na-toys-apoteleiosoyn',
'info_dict': {
'id': '620286',
'title': 'md5:91fe569e952e4d146485740ae927662b',
},
'playlist_mincount': 2,
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
info = self._search_json_ld(webpage, video_id, expected_type='NewsArticle')
embed_urls = list(Ant1NewsGrEmbedIE._extract_urls(webpage))
if not embed_urls:
raise ExtractorError('no videos found for %s' % video_id, expected=True)
return self.playlist_from_matches(
embed_urls, video_id, info.get('title'), ie=Ant1NewsGrEmbedIE.ie_key(),
video_kwargs={'url_transparent': True, 'timestamp': info.get('timestamp')})
class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
IE_NAME = 'ant1newsgr:embed'
IE_DESC = 'ant1news.gr embedded videos'
_BASE_PLAYER_URL_RE = r'(?:https?:)?//(?:[a-zA-Z0-9\-]+\.)?(?:antenna|ant1news)\.gr/templates/pages/player'
_VALID_URL = rf'{_BASE_PLAYER_URL_RE}\?([^#]+&)?cid=(?P<id>[^#&]+)'
_API_PATH = '/news/templates/data/jsonPlayer'
_TESTS = [{
'url': 'https://www.antenna.gr/templates/pages/player?cid=3f_li_c_az_jw_y_u=&w=670&h=377',
'md5': 'dfc58c3a11a5a9aad2ba316ed447def3',
'info_dict': {
'id': '3f_li_c_az_jw_y_u=',
'ext': 'mp4',
'title': 'md5:a30c93332455f53e1e84ae0724f0adf7',
'thumbnail': 'https://ant1media.azureedge.net/imgHandler/640/bbe31201-3f09-4a4e-87f5-8ad2159fffe2.jpg',
},
}]
@classmethod
def _extract_urls(cls, webpage):
_EMBED_URL_RE = rf'{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+'
_EMBED_RE = rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_EMBED_URL_RE})(?P=_q1)'
for mobj in re.finditer(_EMBED_RE, webpage):
url = unescapeHTML(mobj.group('url'))
if not cls.suitable(url):
continue
yield url
def _real_extract(self, url):
video_id = self._match_id(url)
canonical_url = self._request_webpage(
HEADRequest(url), video_id,
note='Resolve canonical player URL',
errnote='Could not resolve canonical player URL').geturl()
_, netloc, _, _, query, _ = urllib.parse.urlparse(canonical_url)
cid = urllib.parse.parse_qs(query)['cid'][0]
return self._download_and_extract_api_data(video_id, netloc, cid=cid)
+11 -37
View File
@@ -3,9 +3,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
clean_podcast_url,
get_element_by_class,
int_or_none,
parse_iso8601,
try_get,
@@ -16,17 +14,16 @@ class ApplePodcastsIE(InfoExtractor):
_VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
_TESTS = [{
'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
'md5': '41dc31cd650143e530d9423b6b5a344f',
'md5': 'df02e6acb11c10e844946a39e7222b08',
'info_dict': {
'id': '1000482637777',
'ext': 'mp3',
'title': '207 - Whitney Webb Returns',
'description': 'md5:75ef4316031df7b41ced4e7b987f79c6',
'description': 'md5:13a73bade02d2e43737751e3987e1399',
'upload_date': '20200705',
'timestamp': 1593932400,
'duration': 6454,
'timestamp': 1593921600,
'duration': 6425,
'series': 'The Tim Dillon Show',
'thumbnail': 're:.+[.](png|jpe?g|webp)',
}
}, {
'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
@@ -42,47 +39,24 @@ class ApplePodcastsIE(InfoExtractor):
def _real_extract(self, url):
episode_id = self._match_id(url)
webpage = self._download_webpage(url, episode_id)
episode_data = {}
ember_data = {}
# new page type 2021-11
amp_data = self._parse_json(self._search_regex(
r'(?s)id="shoebox-media-api-cache-amp-podcasts"[^>]*>\s*({.+?})\s*<',
webpage, 'AMP data', default='{}'), episode_id, fatal=False) or {}
amp_data = try_get(amp_data,
lambda a: self._parse_json(
next(a[x] for x in iter(a) if episode_id in x),
episode_id),
dict) or {}
amp_data = amp_data.get('d') or []
episode_data = try_get(
amp_data,
lambda a: next(x for x in a
if x['type'] == 'podcast-episodes' and x['id'] == episode_id),
dict)
if not episode_data:
# try pre 2021-11 page type: TODO: consider deleting if no longer used
ember_data = self._parse_json(self._search_regex(
r'(?s)id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
webpage, 'ember data'), episode_id) or {}
ember_data = ember_data.get(episode_id) or ember_data
episode_data = try_get(ember_data, lambda x: x['data'], dict)
episode = episode_data['attributes']
ember_data = self._parse_json(self._search_regex(
r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
webpage, 'ember data'), episode_id)
ember_data = ember_data.get(episode_id) or ember_data
episode = ember_data['data']['attributes']
description = episode.get('description') or {}
series = None
for inc in (amp_data or ember_data.get('included') or []):
for inc in (ember_data.get('included') or []):
if inc.get('type') == 'media/podcast':
series = try_get(inc, lambda x: x['attributes']['name'])
series = series or clean_html(get_element_by_class('podcast-header__identity', webpage))
return {
'id': episode_id,
'title': episode.get('name'),
'title': episode['name'],
'url': clean_podcast_url(episode['assetUrl']),
'description': description.get('standard') or description.get('short'),
'timestamp': parse_iso8601(episode.get('releaseDateTime')),
'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
'series': series,
'thumbnail': self._og_search_thumbnail(webpage),
'vcodec': 'none',
}
+37 -39
View File
@@ -19,7 +19,6 @@ from ..utils import (
get_element_by_id,
HEADRequest,
int_or_none,
join_nonempty,
KNOWN_EXTENSIONS,
merge_dicts,
mimetype2ext,
@@ -65,7 +64,7 @@ class ArchiveOrgIE(InfoExtractor):
'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
'uploader': 'yorkmba99@hotmail.com',
'timestamp': 1387699629,
'upload_date': '20131222',
'upload_date': "20131222",
},
}, {
'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
@@ -151,7 +150,8 @@ class ArchiveOrgIE(InfoExtractor):
# Archive.org metadata API doesn't clearly demarcate playlist entries
# or subtitle tracks, so we get them from the embeddable player.
embed_page = self._download_webpage(f'https://archive.org/embed/{identifier}', identifier)
embed_page = self._download_webpage(
'https://archive.org/embed/' + identifier, identifier)
playlist = self._playlist_data(embed_page)
entries = {}
@@ -166,17 +166,17 @@ class ArchiveOrgIE(InfoExtractor):
'thumbnails': [],
'artist': p.get('artist'),
'track': p.get('title'),
'subtitles': {},
}
'subtitles': {}}
for track in p.get('tracks', []):
if track['kind'] != 'subtitles':
continue
entries[p['orig']][track['label']] = {
'url': 'https://archive.org/' + track['file'].lstrip('/')
}
metadata = self._download_json('http://archive.org/metadata/' + identifier, identifier)
entries[p['orig']][track['label']] = {
'url': 'https://archive.org/' + track['file'].lstrip('/')}
metadata = self._download_json(
'http://archive.org/metadata/' + identifier, identifier)
m = metadata['metadata']
identifier = m['identifier']
@@ -189,7 +189,7 @@ class ArchiveOrgIE(InfoExtractor):
'license': m.get('licenseurl'),
'release_date': unified_strdate(m.get('date')),
'timestamp': unified_timestamp(dict_get(m, ['publicdate', 'addeddate'])),
'webpage_url': f'https://archive.org/details/{identifier}',
'webpage_url': 'https://archive.org/details/' + identifier,
'location': m.get('venue'),
'release_year': int_or_none(m.get('year'))}
@@ -207,7 +207,7 @@ class ArchiveOrgIE(InfoExtractor):
'discnumber': int_or_none(f.get('disc')),
'release_year': int_or_none(f.get('year'))})
entry = entries[f['name']]
elif traverse_obj(f, 'original', expected_type=str) in entries:
elif f.get('original') in entries:
entry = entries[f['original']]
else:
continue
@@ -230,12 +230,13 @@ class ArchiveOrgIE(InfoExtractor):
'filesize': int_or_none(f.get('size')),
'protocol': 'https'})
# Sort available formats by filesize
for entry in entries.values():
self._sort_formats(entry['formats'])
entry['formats'] = list(sorted(entry['formats'], key=lambda x: x.get('filesize', -1)))
if len(entries) == 1:
# If there's only one item, use it as the main info dict
only_video = next(iter(entries.values()))
only_video = entries[list(entries.keys())[0]]
if entry_id:
info = merge_dicts(only_video, info)
else:
@@ -260,19 +261,19 @@ class ArchiveOrgIE(InfoExtractor):
class YoutubeWebArchiveIE(InfoExtractor):
IE_NAME = 'web.archive:youtube'
IE_DESC = 'web.archive.org saved youtube videos, "ytarchive:" prefix'
_VALID_URL = r'''(?x)(?:(?P<prefix>ytarchive:)|
(?:https?://)?web\.archive\.org/
(?:web/)?(?:(?P<date>[0-9]{14})?[0-9A-Za-z_*]*/)? # /web and the version index is optional
(?:https?(?::|%3[Aa])//)?(?:
(?:\w+\.)?youtube\.com(?::(?:80|443))?/watch(?:\.php)?(?:\?|%3[fF])(?:[^\#]+(?:&|%26))?v(?:=|%3[dD]) # Youtube URL
|(?:wayback-fakeurl\.archive\.org/yt/) # Or the internal fake url
)
)(?P<id>[0-9A-Za-z_-]{11})
(?(prefix)
(?::(?P<date2>[0-9]{14}))?$|
(?:%26|[#&]|$)
)'''
IE_DESC = 'web.archive.org saved youtube videos'
_VALID_URL = r"""(?x)^
(?:https?://)?web\.archive\.org/
(?:web/)?
(?:(?P<date>[0-9]{14})?[0-9A-Za-z_*]*/)? # /web and the version index is optional
(?:https?(?::|%3[Aa])//)?
(?:
(?:\w+\.)?youtube\.com(?::(?:80|443))?/watch(?:\.php)?(?:\?|%3[fF])(?:[^\#]+(?:&|%26))?v(?:=|%3[dD]) # Youtube URL
|(?:wayback-fakeurl\.archive\.org/yt/) # Or the internal fake url
)
(?P<id>[0-9A-Za-z_-]{11})(?:%26|\#|&|$)
"""
_TESTS = [
{
@@ -437,13 +438,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
}, {
'url': 'https://web.archive.org/http://www.youtube.com:80/watch?v=-05VVye-ffg',
'only_matching': True
}, {
'url': 'ytarchive:BaW_jenozKc:20050214000000',
'only_matching': True
}, {
'url': 'ytarchive:BaW_jenozKc',
'only_matching': True
},
}
]
_YT_INITIAL_DATA_RE = r'(?:(?:(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;)|%s)' % YoutubeBaseInfoExtractor._YT_INITIAL_DATA_RE
_YT_INITIAL_PLAYER_RESPONSE_RE = r'(?:(?:(?:window\s*\[\s*["\']ytInitialPlayerResponse["\']\s*\]|ytInitialPlayerResponse)\s*=[(\s]*({.+?})[)\s]*;)|%s)' % YoutubeBaseInfoExtractor._YT_INITIAL_PLAYER_RESPONSE_RE
@@ -489,6 +484,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
page_title, 'title', default='')
def _extract_metadata(self, video_id, webpage):
search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None)) if webpage else (lambda x: None))
player_response = self._extract_yt_initial_variable(
webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE, video_id, 'initial player response') or {}
@@ -600,7 +596,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
# Prefer the new polymer UI captures as we support extracting more metadata from them
# WBM captures seem to all switch to this layout ~July 2020
modern_captures = [x for x in all_captures if x >= 20200701000000]
modern_captures = list(filter(lambda x: x >= 20200701000000, all_captures))
if modern_captures:
capture_dates.append(modern_captures[0])
capture_dates.append(url_date)
@@ -612,11 +608,11 @@ class YoutubeWebArchiveIE(InfoExtractor):
# Fallbacks if any of the above fail
capture_dates.extend([self._OLDEST_CAPTURE_DATE, self._NEWEST_CAPTURE_DATE])
return orderedSet(filter(None, capture_dates))
return orderedSet(capture_dates)
def _real_extract(self, url):
video_id, url_date, url_date_2 = self._match_valid_url(url).group('id', 'date', 'date2')
url_date = url_date or url_date_2
url_date, video_id = self._match_valid_url(url).groups()
urlh = None
try:
@@ -633,9 +629,11 @@ class YoutubeWebArchiveIE(InfoExtractor):
raise
capture_dates = self._get_capture_dates(video_id, int_or_none(url_date))
self.write_debug('Captures to try: ' + join_nonempty(*capture_dates, delim=', '))
self.write_debug('Captures to try: ' + ', '.join(str(i) for i in capture_dates if i is not None))
info = {'id': video_id}
for capture in capture_dates:
if not capture:
continue
webpage = self._download_webpage(
(self._WAYBACK_BASE_URL + 'http://www.youtube.com/watch?v=%s') % (capture, video_id),
video_id=video_id, fatal=False, errnote='unable to download capture webpage (it may not be archived)',
@@ -650,7 +648,7 @@ class YoutubeWebArchiveIE(InfoExtractor):
info['thumbnails'] = self._extract_thumbnails(video_id)
if urlh:
url = compat_urllib_parse_unquote(urlh.geturl())
url = compat_urllib_parse_unquote(urlh.url)
video_file_url_qs = parse_qs(url)
# Attempt to recover any ext & format info from playback url & response headers
format = {'url': url, 'filesize': int_or_none(urlh.headers.get('x-archive-orig-content-length'))}
+2 -1
View File
@@ -124,7 +124,8 @@ class ArcPublishingIE(InfoExtractor):
formats.extend(smil_formats)
elif stream_type in ('ts', 'hls'):
m3u8_formats = self._extract_m3u8_formats(
s_url, uuid, 'mp4', live=is_live, m3u8_id='hls', fatal=False)
s_url, uuid, 'mp4', 'm3u8' if is_live else 'm3u8_native',
m3u8_id='hls', fatal=False)
if all([f.get('acodec') == 'none' for f in m3u8_formats]):
continue
for f in m3u8_formats:
+5 -14
View File
@@ -407,9 +407,8 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
(?:(?:beta|www)\.)?ardmediathek\.de/
(?:(?P<client>[^/]+)/)?
(?:player|live|video|(?P<playlist>sendung|sammlung))/
(?:(?P<display_id>(?(playlist)[^?#]+?|[^?#]+))/)?
(?P<id>(?(playlist)|Y3JpZDovL)[a-zA-Z0-9]+)
(?(playlist)/(?P<season>\d+)?/?(?:[?#]|$))'''
(?:(?P<display_id>[^?#]+)/)?
(?P<id>(?(playlist)|Y3JpZDovL)[a-zA-Z0-9]+)'''
_TESTS = [{
'url': 'https://www.ardmediathek.de/mdr/video/die-robuste-roswita/Y3JpZDovL21kci5kZS9iZWl0cmFnL2Ntcy84MWMxN2MzZC0wMjkxLTRmMzUtODk4ZS0wYzhlOWQxODE2NGI/',
@@ -437,13 +436,6 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
'description': 'md5:39578c7b96c9fe50afdf5674ad985e6b',
'upload_date': '20211108',
},
}, {
'url': 'https://www.ardmediathek.de/sendung/beforeigners/beforeigners/staffel-1/Y3JpZDovL2Rhc2Vyc3RlLmRlL2JlZm9yZWlnbmVycw/1',
'playlist_count': 6,
'info_dict': {
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL2JlZm9yZWlnbmVycw',
'title': 'beforeigners/beforeigners/staffel-1',
},
}, {
'url': 'https://beta.ardmediathek.de/ard/video/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
'only_matching': True,
@@ -569,15 +561,14 @@ class ARDBetaMediathekIE(ARDMediathekBaseIE):
break
pageNumber = pageNumber + 1
return self.playlist_result(entries, playlist_id, playlist_title=display_id)
return self.playlist_result(entries, playlist_title=display_id)
def _real_extract(self, url):
video_id, display_id, playlist_type, client, season_number = self._match_valid_url(url).group(
'id', 'display_id', 'playlist', 'client', 'season')
video_id, display_id, playlist_type, client = self._match_valid_url(url).group(
'id', 'display_id', 'playlist', 'client')
display_id, client = display_id or video_id, client or 'ard'
if playlist_type:
# TODO: Extract only specified season
return self._ARD_extract_playlist(url, video_id, display_id, client, playlist_type)
player_page = self._download_json(
-42
View File
@@ -12,7 +12,6 @@ from ..utils import (
int_or_none,
parse_qs,
qualities,
strip_or_none,
try_get,
unified_strdate,
url_or_none,
@@ -254,44 +253,3 @@ class ArteTVPlaylistIE(ArteTVBaseIE):
title = collection.get('title')
description = collection.get('shortDescription') or collection.get('teaserText')
return self.playlist_result(entries, playlist_id, title, description)
class ArteTVCategoryIE(ArteTVBaseIE):
_VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>[\w-]+(?:/[\w-]+)*)/?\s*$' % ArteTVBaseIE._ARTE_LANGUAGES
_TESTS = [{
'url': 'https://www.arte.tv/en/videos/politics-and-society/',
'info_dict': {
'id': 'politics-and-society',
'title': 'Politics and society',
'description': 'Investigative documentary series, geopolitical analysis, and international commentary',
},
'playlist_mincount': 13,
},
]
@classmethod
def suitable(cls, url):
return (
not any(ie.suitable(url) for ie in (ArteTVIE, ArteTVPlaylistIE, ))
and super(ArteTVCategoryIE, cls).suitable(url))
def _real_extract(self, url):
lang, playlist_id = self._match_valid_url(url).groups()
webpage = self._download_webpage(url, playlist_id)
items = []
for video in re.finditer(
r'<a\b[^>]*?href\s*=\s*(?P<q>"|\'|\b)(?P<url>https?://www\.arte\.tv/%s/videos/[\w/-]+)(?P=q)' % lang,
webpage):
video = video.group('url')
if video == url:
continue
if any(ie.suitable(video) for ie in (ArteTVIE, ArteTVPlaylistIE, )):
items.append(video)
title = (self._og_search_title(webpage, default=None)
or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title>', default=None))
title = strip_or_none(title.rsplit('|', 1)[0]) or self._generic_title(url)
return self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=title,
description=self._og_search_description(webpage, default=None))
-6
View File
@@ -8,7 +8,6 @@ from ..utils import (
float_or_none,
jwt_encode_hs256,
try_get,
ExtractorError,
)
@@ -95,11 +94,6 @@ class ATVAtIE(InfoExtractor):
})
video_id, videos_data = list(videos['data'].items())[0]
error_msg = try_get(videos_data, lambda x: x['error']['title'])
if error_msg == 'Geo check failed':
self.raise_geo_restricted(error_msg)
elif error_msg:
raise ExtractorError(error_msg)
entries = [
self._extract_video_info(url, contentResource[video['id']], video)
for video in videos_data]
-1
View File
@@ -29,7 +29,6 @@ class AudiomackIE(InfoExtractor):
}
},
# audiomack wrapper around soundcloud song
# Needs new test URL.
{
'add_ie': ['Soundcloud'],
'url': 'http://www.audiomack.com/song/hip-hop-daily/black-mamba-freestyle',
+27 -42
View File
@@ -183,7 +183,6 @@ class BandcampIE(InfoExtractor):
'format_note': f.get('description'),
'filesize': parse_filesize(f.get('size_mb')),
'vcodec': 'none',
'acodec': format_id.split('-')[0],
})
self._sort_formats(formats)
@@ -213,7 +212,7 @@ class BandcampIE(InfoExtractor):
class BandcampAlbumIE(BandcampIE):
IE_NAME = 'Bandcamp:album'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com/album/(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:(?P<subdomain>[^.]+)\.)?bandcamp\.com(?!/music)(?:/album/(?P<id>[^/?#&]+))?'
_TESTS = [{
'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1',
@@ -258,6 +257,14 @@ class BandcampAlbumIE(BandcampIE):
'id': 'hierophany-of-the-open-grave',
},
'playlist_mincount': 9,
}, {
'url': 'http://dotscale.bandcamp.com',
'info_dict': {
'title': 'Loom',
'id': 'dotscale',
'uploader_id': 'dotscale',
},
'playlist_mincount': 7,
}, {
# with escaped quote in title
'url': 'https://jstrecords.bandcamp.com/album/entropy-ep',
@@ -384,63 +391,41 @@ class BandcampWeeklyIE(BandcampIE):
}
class BandcampUserIE(InfoExtractor):
IE_NAME = 'Bandcamp:user'
_VALID_URL = r'https?://(?!www\.)(?P<id>[^.]+)\.bandcamp\.com(?:/music)?/?(?:[#?]|$)'
class BandcampMusicIE(InfoExtractor):
_VALID_URL = r'https?://(?P<id>[^/]+)\.bandcamp\.com/music'
_TESTS = [{
# Type 1 Bandcamp user page.
'url': 'https://adrianvonziegler.bandcamp.com',
'info_dict': {
'id': 'adrianvonziegler',
'title': 'Discography of adrianvonziegler',
},
'playlist_mincount': 23,
}, {
# Bandcamp user page with only one album
'url': 'http://dotscale.bandcamp.com',
'info_dict': {
'id': 'dotscale',
'title': 'Discography of dotscale'
},
'playlist_count': 1,
}, {
# Type 2 Bandcamp user page.
'url': 'https://nightcallofficial.bandcamp.com',
'info_dict': {
'id': 'nightcallofficial',
'title': 'Discography of nightcallofficial',
},
'playlist_count': 4,
}, {
'url': 'https://steviasphere.bandcamp.com/music',
'playlist_mincount': 47,
'info_dict': {
'id': 'steviasphere',
'title': 'Discography of steviasphere',
},
}, {
'url': 'https://coldworldofficial.bandcamp.com/music',
'playlist_mincount': 10,
'info_dict': {
'id': 'coldworldofficial',
'title': 'Discography of coldworldofficial',
},
}, {
'url': 'https://nuclearwarnowproductions.bandcamp.com/music',
'playlist_mincount': 399,
'info_dict': {
'id': 'nuclearwarnowproductions',
'title': 'Discography of nuclearwarnowproductions',
},
}]
}
]
_TYPE_IE_DICT = {
'album': BandcampAlbumIE.ie_key(),
'track': BandcampIE.ie_key()
}
def _real_extract(self, url):
uploader = self._match_id(url)
webpage = self._download_webpage(url, uploader)
discography_data = (re.findall(r'<li data-item-id=["\'][^>]+>\s*<a href=["\']([^"\']+)', webpage)
or re.findall(r'<div[^>]+trackTitle["\'][^"\']+["\']([^"\']+)', webpage))
return self.playlist_from_matches(
discography_data, uploader, f'Discography of {uploader}', getter=lambda x: urljoin(url, x))
id = self._match_id(url)
webpage = self._download_webpage(url, id)
items = re.findall(r'href\=\"\/(?P<path>(?P<type>album|track)+/[^\"]+)', webpage)
entries = [
self.url_result(
f'https://{id}.bandcamp.com/{item[0]}',
ie=self._TYPE_IE_DICT[item[1]])
for item in items]
return self.playlist_result(entries, id)
+13 -44
View File
@@ -11,7 +11,6 @@ from ..compat import (
compat_etree_Element,
compat_HTTPError,
compat_str,
compat_urllib_error,
compat_urlparse,
)
from ..utils import (
@@ -39,7 +38,7 @@ from ..utils import (
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_ID_REGEX = r'(?:[pbml][\da-z]{7}|w[\da-z]{7,14})'
_ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?bbc\.co\.uk/
@@ -395,17 +394,9 @@ class BBCCoUkIE(InfoExtractor):
formats.extend(self._extract_mpd_formats(
href, programme_id, mpd_id=format_id, fatal=False))
elif transfer_format == 'hls':
# TODO: let expected_status be passed into _extract_xxx_formats() instead
try:
fmts = self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False)
except ExtractorError as e:
if not (isinstance(e.exc_info[1], compat_urllib_error.HTTPError)
and e.exc_info[1].code in (403, 404)):
raise
fmts = []
formats.extend(fmts)
formats.extend(self._extract_m3u8_formats(
href, programme_id, ext='mp4', entry_protocol='m3u8_native',
m3u8_id=format_id, fatal=False))
elif transfer_format == 'hds':
formats.extend(self._extract_f4m_formats(
href, programme_id, f4m_id=format_id, fatal=False))
@@ -793,33 +784,21 @@ class BBCIE(BBCCoUkIE):
'timestamp': 1437785037,
'upload_date': '20150725',
},
}, {
# video with window.__INITIAL_DATA__ and value as JSON string
'url': 'https://www.bbc.com/news/av/world-europe-59468682',
'info_dict': {
'id': 'p0b71qth',
'ext': 'mp4',
'title': 'Why France is making this woman a national hero',
'description': 'md5:7affdfab80e9c3a1f976230a1ff4d5e4',
'thumbnail': r're:https?://.+/.+\.jpg',
'timestamp': 1638230731,
'upload_date': '20211130',
},
}, {
# single video article embedded with data-media-vpid
'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
'only_matching': True,
}, {
# bbcthreeConfig
'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
'info_dict': {
'id': 'p06556y7',
'ext': 'mp4',
'title': 'Things Not To Say to people that live on council estates',
'description': "From being labelled a 'chav', to the presumption that they're 'scroungers', people who live on council estates encounter all kinds of prejudices and false assumptions about themselves, their families, and their lifestyles. Here, eight people discuss the common statements, misconceptions, and clichés that they're tired of hearing.",
'duration': 360,
'thumbnail': r're:https?://.+/.+\.jpg',
'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?',
'description': 'md5:4b7dfd063d5a789a1512e99662be3ddd',
},
'params': {
'skip_download': True,
}
}, {
# window.__PRELOADED_STATE__
'url': 'https://www.bbc.co.uk/radio/play/b0b9z4yl',
@@ -1192,16 +1171,9 @@ class BBCIE(BBCCoUkIE):
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
initial_data = self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*("{.+?}")\s*;', webpage,
'quoted preload state', default=None)
if initial_data is None:
initial_data = self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*({.+?})\s*;', webpage,
'preload state', default={})
else:
initial_data = self._parse_json(initial_data or '"{}"', playlist_id, fatal=False)
initial_data = self._parse_json(initial_data, playlist_id, fatal=False)
initial_data = self._parse_json(self._search_regex(
r'window\.__INITIAL_DATA__\s*=\s*({.+?});', webpage,
'preload state', default='{}'), playlist_id, fatal=False)
if initial_data:
def parse_media(media):
if not media:
@@ -1242,10 +1214,7 @@ class BBCIE(BBCCoUkIE):
if name == 'media-experience':
parse_media(try_get(resp, lambda x: x['data']['initialItem']['mediaItem'], dict))
elif name == 'article':
for block in (try_get(resp,
(lambda x: x['data']['blocks'],
lambda x: x['data']['content']['model']['blocks'],),
list) or []):
for block in (try_get(resp, lambda x: x['data']['blocks'], list) or []):
if block.get('type') != 'media':
continue
parse_media(block.get('model'))
+73 -50
View File
@@ -1,45 +1,32 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_str,
)
from ..utils import (
int_or_none,
traverse_obj,
try_get,
parse_qs,
unified_timestamp,
)
class BeegIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?beeg\.(?:com(?:/video)?)/-?(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?beeg\.(?:com|porn(?:/video)?)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://beeg.com/-0983946056129650',
'md5': '51d235147c4627cfce884f844293ff88',
# api/v6 v1
'url': 'http://beeg.com/5416503',
'md5': 'a1a1b1a8bc70a89e49ccfd113aed0820',
'info_dict': {
'id': '0983946056129650',
'id': '5416503',
'ext': 'mp4',
'title': 'sucked cock and fucked in a private plane',
'duration': 927,
'title': 'Sultry Striptease',
'description': 'md5:d22219c09da287c14bed3d6c37ce4bc2',
'timestamp': 1391813355,
'upload_date': '20140207',
'duration': 383,
'tags': list,
'age_limit': 18,
'upload_date': '20220131',
'timestamp': 1643656455,
'display_id': 2540839,
}
}, {
'url': 'https://beeg.com/-0599050563103750?t=4-861',
'md5': 'bd8b5ea75134f7f07fad63008db2060e',
'info_dict': {
'id': '0599050563103750',
'ext': 'mp4',
'title': 'Bad Relatives',
'duration': 2060,
'tags': list,
'age_limit': 18,
'description': 'md5:b4fc879a58ae6c604f8f259155b7e3b9',
'timestamp': 1643623200,
'display_id': 2569965,
'upload_date': '20220131',
}
}, {
# api/v6 v2
@@ -49,6 +36,12 @@ class BeegIE(InfoExtractor):
# api/v6 v2 w/o t
'url': 'https://beeg.com/1277207756',
'only_matching': True,
}, {
'url': 'https://beeg.porn/video/5416503',
'only_matching': True,
}, {
'url': 'https://beeg.porn/5416503',
'only_matching': True,
}]
def _real_extract(self, url):
@@ -56,38 +49,68 @@ class BeegIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video = self._download_json(
'https://store.externulls.com/facts/file/%s' % video_id,
video_id, 'Downloading JSON for %s' % video_id)
beeg_version = self._search_regex(
r'beeg_version\s*=\s*([\da-zA-Z_-]+)', webpage, 'beeg version',
default='1546225636701')
fc_facts = video.get('fc_facts')
first_fact = {}
for fact in fc_facts:
if not first_fact or try_get(fact, lambda x: x['id'] < first_fact['id']):
first_fact = fact
if len(video_id) >= 10:
query = {
'v': 2,
}
qs = parse_qs(url)
t = qs.get('t', [''])[0].split('-')
if len(t) > 1:
query.update({
's': t[0],
'e': t[1],
})
else:
query = {'v': 1}
resources = traverse_obj(video, ('file', 'hls_resources')) or first_fact.get('hls_resources')
for api_path in ('', 'api.'):
video = self._download_json(
'https://%sbeeg.com/api/v6/%s/video/%s'
% (api_path, beeg_version, video_id), video_id,
fatal=api_path == 'api.', query=query)
if video:
break
formats = []
for format_id, video_uri in resources.items():
if not video_uri:
for format_id, video_url in video.items():
if not video_url:
continue
height = int_or_none(self._search_regex(r'fl_cdn_(\d+)', format_id, 'height', default=None))
current_formats = self._extract_m3u8_formats(f'https://video.beeg.com/{video_uri}', video_id, ext='mp4', m3u8_id=str(height))
for f in current_formats:
f['height'] = height
formats.extend(current_formats)
height = self._search_regex(
r'^(\d+)[pP]$', format_id, 'height', default=None)
if not height:
continue
formats.append({
'url': self._proto_relative_url(
video_url.replace('{DATA_MARKERS}', 'data=pc_XX__%s_0' % beeg_version), 'https:'),
'format_id': format_id,
'height': int(height),
})
self._sort_formats(formats)
title = video['title']
video_id = compat_str(video.get('id') or video_id)
display_id = video.get('code')
description = video.get('desc')
series = video.get('ps_name')
timestamp = unified_timestamp(video.get('date'))
duration = int_or_none(video.get('duration'))
tags = [tag.strip() for tag in video['tags'].split(',')] if video.get('tags') else None
return {
'id': video_id,
'display_id': first_fact.get('id'),
'title': traverse_obj(video, ('file', 'stuff', 'sf_name')),
'description': traverse_obj(video, ('file', 'stuff', 'sf_story')),
'timestamp': unified_timestamp(first_fact.get('fc_created')),
'duration': int_or_none(traverse_obj(video, ('file', 'fl_duration'))),
'tags': traverse_obj(video, ('tags', ..., 'tg_name')),
'display_id': display_id,
'title': title,
'description': description,
'series': series,
'timestamp': timestamp,
'duration': duration,
'tags': tags,
'formats': formats,
'age_limit': self._rta_search(webpage),
}
-59
View File
@@ -1,59 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import ExtractorError, urlencode_postdata
class BigoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bigo\.tv/(?:[a-z]{2,}/)?(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://www.bigo.tv/ja/221338632',
'info_dict': {
'id': '6576287577575737440',
'title': '土よ〜💁‍♂️ 休憩室/REST room',
'thumbnail': r're:https?://.+',
'uploader': '✨Shin💫',
'uploader_id': '221338632',
'is_live': True,
},
'skip': 'livestream',
}, {
'url': 'https://www.bigo.tv/th/Tarlerm1304',
'only_matching': True,
}, {
'url': 'https://bigo.tv/115976881',
'only_matching': True,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
info_raw = self._download_json(
'https://bigo.tv/studio/getInternalStudioInfo',
user_id, data=urlencode_postdata({'siteId': user_id}))
if not isinstance(info_raw, dict):
raise ExtractorError('Received invalid JSON data')
if info_raw.get('code'):
raise ExtractorError(
'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
info = info_raw.get('data') or {}
if not info.get('alive'):
raise ExtractorError('This user is offline.', expected=True)
return {
'id': info.get('roomId') or user_id,
'title': info.get('roomTopic') or info.get('nick_name') or user_id,
'formats': [{
'url': info.get('hls_src'),
'ext': 'mp4',
'protocol': 'm3u8',
}],
'thumbnail': info.get('snapshot'),
'uploader': info.get('nick_name'),
'uploader_id': user_id,
'is_live': True,
}
+89 -93
View File
@@ -17,9 +17,9 @@ from ..utils import (
ExtractorError,
int_or_none,
float_or_none,
mimetype2ext,
parse_iso8601,
traverse_obj,
try_get,
parse_count,
smuggle_url,
srt_subtitles_timecode,
@@ -52,14 +52,16 @@ class BiliBiliIE(InfoExtractor):
'url': 'http://www.bilibili.com/video/av1074402/',
'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
'info_dict': {
'id': '1074402_part1',
'ext': 'mp4',
'id': '1074402',
'ext': 'flv',
'title': '【金坷垃】金泡沫',
'uploader_id': '156160',
'uploader': '菊子桑',
'upload_date': '20140420',
'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
'duration': 308.067,
'timestamp': 1398012678,
'upload_date': '20140420',
'thumbnail': r're:^https?://.+\.jpg',
'uploader': '菊子桑',
'uploader_id': '156160',
},
}, {
# Tested in BiliBiliBangumiIE
@@ -73,27 +75,49 @@ class BiliBiliIE(InfoExtractor):
'url': 'http://bangumi.bilibili.com/anime/5802/play#100643',
'md5': '3f721ad1e75030cc06faf73587cfec57',
'info_dict': {
'id': '100643_part1',
'id': '100643',
'ext': 'mp4',
'title': 'CHAOS;CHILD',
'description': '如果你是神明,并且能够让妄想成为现实。那你会进行怎么样的妄想?是淫靡的世界?独裁社会?毁灭性的制裁?还是……2015年,涩谷。从6年前发生的大灾害“涩谷地震”之后复兴了的这个街区里新设立的私立高中...',
},
'skip': 'Geo-restricted to China',
}, {
# Title with double quotes
'url': 'http://www.bilibili.com/video/av8903802/',
'info_dict': {
'id': '8903802_part1',
'ext': 'mp4',
'id': '8903802',
'title': '阿滴英文|英文歌分享#6 "Closer',
'upload_date': '20170301',
'description': '滴妹今天唱Closer給你聽! 有史以来,被推最多次也是最久的歌曲,其实歌词跟我原本想像差蛮多的,不过还是好听! 微博@阿滴英文',
'timestamp': 1488382634,
'uploader_id': '65880958',
'uploader': '阿滴英文',
},
'params': {
'skip_download': True,
},
'playlist': [{
'info_dict': {
'id': '8903802_part1',
'ext': 'flv',
'title': '阿滴英文|英文歌分享#6 "Closer',
'description': 'md5:3b1b9e25b78da4ef87e9b548b88ee76a',
'uploader': '阿滴英文',
'uploader_id': '65880958',
'timestamp': 1488382634,
'upload_date': '20170301',
},
'params': {
'skip_download': True,
},
}, {
'info_dict': {
'id': '8903802_part2',
'ext': 'flv',
'title': '阿滴英文|英文歌分享#6 "Closer',
'description': 'md5:3b1b9e25b78da4ef87e9b548b88ee76a',
'uploader': '阿滴英文',
'uploader_id': '65880958',
'timestamp': 1488382634,
'upload_date': '20170301',
},
'params': {
'skip_download': True,
},
}]
}, {
# new BV video id format
'url': 'https://www.bilibili.com/video/BV1JE411F741',
@@ -128,7 +152,6 @@ class BiliBiliIE(InfoExtractor):
av_id, bv_id = self._get_video_id_set(video_id, mobj.group('id_bv') is not None)
video_id = av_id
info = {}
anime_id = mobj.group('anime_id')
page_id = mobj.group('page')
webpage = self._download_webpage(url, video_id)
@@ -180,95 +203,66 @@ class BiliBiliIE(InfoExtractor):
}
headers.update(self.geo_verification_headers())
video_info = self._parse_json(
self._search_regex(r'window.__playinfo__\s*=\s*({.+?})</script>', webpage, 'video info', default=None) or '{}',
video_id, fatal=False)
video_info = video_info.get('data') or {}
durl = traverse_obj(video_info, ('dash', 'video'))
audios = traverse_obj(video_info, ('dash', 'audio')) or []
entries = []
RENDITIONS = ('qn=80&quality=80&type=', 'quality=2&type=mp4')
for num, rendition in enumerate(RENDITIONS, start=1):
payload = 'appkey=%s&cid=%s&otype=json&%s' % (self._APP_KEY, cid, rendition)
sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
if not video_info:
video_info = self._download_json(
'http://interface.bilibili.com/v2/playurl?%s&sign=%s' % (payload, sign),
video_id, note='Downloading video info page',
headers=headers, fatal=num == len(RENDITIONS))
if not video_info:
continue
if not durl and 'durl' not in video_info:
video_info = self._download_json(
'http://interface.bilibili.com/v2/playurl?%s&sign=%s' % (payload, sign),
video_id, note='Downloading video info page',
headers=headers, fatal=num == len(RENDITIONS))
if not video_info:
continue
if 'durl' not in video_info:
if num < len(RENDITIONS):
continue
self._report_error(video_info)
formats = []
for idx, durl in enumerate(durl or video_info['durl']):
formats.append({
'url': durl.get('baseUrl') or durl.get('base_url') or durl.get('url'),
'ext': mimetype2ext(durl.get('mimeType') or durl.get('mime_type')),
'fps': int_or_none(durl.get('frameRate') or durl.get('frame_rate')),
'width': int_or_none(durl.get('width')),
'height': int_or_none(durl.get('height')),
'vcodec': durl.get('codecs'),
'acodec': 'none' if audios else None,
'tbr': float_or_none(durl.get('bandwidth'), scale=1000),
'filesize': int_or_none(durl.get('size')),
})
for backup_url in traverse_obj(durl, 'backup_url', expected_type=list) or []:
formats.append({
'url': backup_url,
'quality': -2 if 'hd.mp4' in backup_url else -3,
})
for audio in audios:
formats.append({
'url': audio.get('baseUrl') or audio.get('base_url') or audio.get('url'),
'ext': mimetype2ext(audio.get('mimeType') or audio.get('mime_type')),
'fps': int_or_none(audio.get('frameRate') or audio.get('frame_rate')),
'width': int_or_none(audio.get('width')),
'height': int_or_none(audio.get('height')),
'acodec': audio.get('codecs'),
'vcodec': 'none',
'tbr': float_or_none(audio.get('bandwidth'), scale=1000),
'filesize': int_or_none(audio.get('size'))
})
for backup_url in traverse_obj(audio, 'backup_url', expected_type=list) or []:
for idx, durl in enumerate(video_info['durl']):
formats = [{
'url': durl['url'],
'filesize': int_or_none(durl['size']),
}]
for backup_url in durl.get('backup_url', []):
formats.append({
'url': backup_url,
# backup URLs have lower priorities
'quality': -3,
'quality': -2 if 'hd.mp4' in backup_url else -3,
})
info.update({
'id': video_id,
'duration': float_or_none(durl.get('length'), 1000),
'formats': formats,
'http_headers': {
'Referer': url,
},
})
for a_format in formats:
a_format.setdefault('http_headers', {}).update({
'Referer': url,
})
self._sort_formats(formats)
entries.append({
'id': '%s_part%s' % (video_id, idx),
'duration': float_or_none(durl.get('length'), 1000),
'formats': formats,
})
break
self._sort_formats(formats)
title = self._html_search_regex((
r'<h1[^>]+title=(["\'])(?P<content>[^"\']+)',
r'(?s)<h1[^>]*>(?P<content>.+?)</h1>',
self._meta_regex('title')
), webpage, 'title', group='content', fatal=False)
title = self._html_search_regex(
(r'<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
r'(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
group='title')
# Get part title for anthologies
if page_id is not None:
# TODO: The json is already downloaded by _extract_anthology_entries. Don't redownload for each video.
part_info = traverse_obj(self._download_json(
f'https://api.bilibili.com/x/player/pagelist?bvid={bv_id}&jsonp=jsonp',
video_id, note='Extracting videos in anthology'), 'data', expected_type=list)
title = title if len(part_info) == 1 else traverse_obj(part_info, (int(page_id) - 1, 'part')) or title
# TODO: The json is already downloaded by _extract_anthology_entries. Don't redownload for each video
part_title = try_get(
self._download_json(
f'https://api.bilibili.com/x/player/pagelist?bvid={bv_id}&jsonp=jsonp',
video_id, note='Extracting videos in anthology'),
lambda x: x['data'][int(page_id) - 1]['part'])
title = part_title or title
description = self._html_search_meta('description', webpage)
timestamp = unified_timestamp(self._html_search_regex(
@@ -278,15 +272,15 @@ class BiliBiliIE(InfoExtractor):
thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
# TODO 'view_count' requires deobfuscating Javascript
info.update({
'id': f'{video_id}_part{page_id or 1}',
info = {
'id': str(video_id) if page_id is None else '%s_part%s' % (video_id, page_id),
'cid': cid,
'title': title,
'description': description,
'timestamp': timestamp,
'thumbnail': thumbnail,
'duration': float_or_none(video_info.get('timelength'), scale=1000),
})
}
uploader_mobj = re.search(
r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]*>\s*(?P<name>[^<]+?)\s*<',
@@ -307,7 +301,7 @@ class BiliBiliIE(InfoExtractor):
video_id, fatal=False, note='Downloading tags'), ('data', ..., 'tag_name')),
}
info['subtitles'] = {
entries[0]['subtitles'] = {
'danmaku': [{
'ext': 'xml',
'url': f'https://comment.bilibili.com/{cid}.xml',
@@ -342,10 +336,12 @@ class BiliBiliIE(InfoExtractor):
entry['id'] = '%s_part%d' % (video_id, (idx + 1))
return {
'_type': 'multi_video',
'id': str(video_id),
'bv_id': bv_id,
'title': title,
'description': description,
'entries': entries,
**info, **top_level_info
}
@@ -486,9 +482,9 @@ class BilibiliChannelIE(InfoExtractor):
data = self._download_json(
self._API_URL % (list_id, page_num), list_id, note=f'Downloading page {page_num}')['data']
max_count = max_count or traverse_obj(data, ('page', 'count'))
max_count = max_count or try_get(data, lambda x: x['page']['count'])
entries = traverse_obj(data, ('list', 'vlist'))
entries = try_get(data, lambda x: x['list']['vlist'])
if not entries:
return
for entry in entries:
@@ -526,7 +522,7 @@ class BilibiliCategoryIE(InfoExtractor):
api_url, query, query={'Search_key': query, 'pn': page_num},
note='Extracting results from page %s of %s' % (page_num, num_pages))
video_list = traverse_obj(parsed_json, ('data', 'archives'), expected_type=list)
video_list = try_get(parsed_json, lambda x: x['data']['archives'], list)
if not video_list:
raise ExtractorError('Failed to retrieve video list for page %d' % page_num)
@@ -556,7 +552,7 @@ class BilibiliCategoryIE(InfoExtractor):
api_url = 'https://api.bilibili.com/x/web-interface/newlist?rid=%d&type=1&ps=20&jsonp=jsonp' % rid_value
page_json = self._download_json(api_url, query, query={'Search_key': query, 'pn': '1'})
page_data = traverse_obj(page_json, ('data', 'page'), expected_type=dict)
page_data = try_get(page_json, lambda x: x['data']['page'], dict)
count, size = int_or_none(page_data.get('count')), int_or_none(page_data.get('size'))
if count is None or not size:
raise ExtractorError('Failed to calculate either page count or size')
+42 -51
View File
@@ -3,28 +3,27 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from .vk import VKIE
from ..compat import compat_b64decode
from ..utils import (
int_or_none,
js_to_json,
traverse_obj,
unified_timestamp,
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote,
)
from ..utils import int_or_none
class BIQLEIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?biqle\.(?:com|org|ru)/watch/(?P<id>-?\d+_\d+)'
_TESTS = [{
'url': 'https://biqle.ru/watch/-2000421746_85421746',
'md5': 'ae6ef4f04d19ac84e4658046d02c151c',
# Youtube embed
'url': 'https://biqle.ru/watch/-115995369_456239081',
'md5': '97af5a06ee4c29bbf9c001bdb1cf5c06',
'info_dict': {
'id': '-2000421746_85421746',
'id': '8v4f-avW-VI',
'ext': 'mp4',
'title': 'Forsaken By Hope Studio Clip',
'description': 'Forsaken By Hope Studio Clip — Смотреть онлайн',
'upload_date': '19700101',
'thumbnail': r're:https://[^/]+/impf/7vN3ACwSTgChP96OdOfzFjUCzFR6ZglDQgWsIw/KPaACiVJJxM\.jpg\?size=800x450&quality=96&keep_aspect_ratio=1&background=000000&sign=b48ea459c4d33dbcba5e26d63574b1cb&type=video_thumb',
'timestamp': 0,
'title': "PASSE-PARTOUT - L'ete c'est fait pour jouer",
'description': 'Passe-Partout',
'uploader_id': 'mrsimpsonstef3',
'uploader': 'Phanolito',
'upload_date': '20120822',
},
}, {
'url': 'http://biqle.org/watch/-44781847_168547604',
@@ -33,62 +32,53 @@ class BIQLEIE(InfoExtractor):
'id': '-44781847_168547604',
'ext': 'mp4',
'title': 'Ребенок в шоке от автоматической мойки',
'description': 'Ребенок в шоке от автоматической мойки — Смотреть онлайн',
'timestamp': 1396633454,
'uploader': 'Dmitry Kotov',
'upload_date': '20140404',
'thumbnail': r're:https://[^/]+/c535507/u190034692/video/l_b84df002\.jpg',
'uploader_id': '47850140',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta('name', webpage, 'Title', fatal=False)
timestamp = unified_timestamp(self._html_search_meta('uploadDate', webpage, 'Upload Date', default=None))
description = self._html_search_meta('description', webpage, 'Description', default=None)
global_embed_url = self._search_regex(
r'<script[^<]+?window.globEmbedUrl\s*=\s*\'((?:https?:)?//(?:daxab\.com|dxb\.to|[^/]+/player)/[^\']+)\'',
webpage, 'global Embed url')
hash = self._search_regex(
r'<script id="data-embed-video[^<]+?hash: "([^"]+)"[^<]*</script>', webpage, 'Hash')
embed_url = global_embed_url + hash
embed_url = self._proto_relative_url(self._search_regex(
r'<iframe.+?src="((?:https?:)?//(?:daxab\.com|dxb\.to|[^/]+/player)/[^"]+)".*?></iframe>',
webpage, 'embed url'))
if VKIE.suitable(embed_url):
return self.url_result(embed_url, VKIE.ie_key(), video_id)
embed_page = self._download_webpage(
embed_url, video_id, 'Downloading embed webpage', headers={'Referer': url})
glob_params = self._parse_json(self._search_regex(
r'<script id="globParams">[^<]*window.globParams = ([^;]+);[^<]+</script>',
embed_page, 'Global Parameters'), video_id, transform_source=js_to_json)
host_name = compat_b64decode(glob_params['server'][::-1]).decode()
embed_url, video_id, headers={'Referer': url})
video_ext = self._get_cookies(embed_url).get('video_ext')
if video_ext:
video_ext = compat_urllib_parse_unquote(video_ext.value)
if not video_ext:
video_ext = compat_b64decode(self._search_regex(
r'video_ext\s*:\s*[\'"]([A-Za-z0-9+/=]+)',
embed_page, 'video_ext')).decode()
video_id, sig, _, access_token = video_ext.split(':')
item = self._download_json(
f'https://{host_name}/method/video.get/{video_id}', video_id,
headers={'Referer': url}, query={
'token': glob_params['video']['access_token'],
'https://api.vk.com/method/video.get', video_id,
headers={'User-Agent': 'okhttp/3.4.1'}, query={
'access_token': access_token,
'sig': sig,
'v': 5.44,
'videos': video_id,
'ckey': glob_params['c_key'],
'credentials': glob_params['video']['credentials'],
})['response']['items'][0]
title = item['title']
formats = []
for f_id, f_url in item.get('files', {}).items():
if f_id == 'external':
return self.url_result(f_url)
ext, height = f_id.split('_')
height_extra_key = traverse_obj(glob_params, ('video', 'partial', 'quality', height))
if height_extra_key:
formats.append({
'format_id': f'{height}p',
'url': f'https://{host_name}/{f_url[8:]}&videos={video_id}&extra_key={height_extra_key}',
'height': int_or_none(height),
'ext': ext,
})
formats.append({
'format_id': height + 'p',
'url': f_url,
'height': int_or_none(height),
'ext': ext,
})
self._sort_formats(formats)
thumbnails = []
@@ -106,9 +96,10 @@ class BIQLEIE(InfoExtractor):
'title': title,
'formats': formats,
'comment_count': int_or_none(item.get('comments')),
'description': description,
'description': item.get('description'),
'duration': int_or_none(item.get('duration')),
'thumbnails': thumbnails,
'timestamp': timestamp,
'timestamp': int_or_none(item.get('date')),
'uploader': item.get('owner_id'),
'view_count': int_or_none(item.get('views')),
}
-41
View File
@@ -1,41 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class CaltransIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?ca\.gov/vm/loc/[^/]+/(?P<id>[a-z0-9_]+)\.htm'
_TEST = {
'url': 'https://cwwp2.dot.ca.gov/vm/loc/d3/hwy50at24th.htm',
'info_dict': {
'id': 'hwy50at24th',
'ext': 'ts',
'title': 'US-50 : Sacramento : Hwy 50 at 24th',
'live_status': 'is_live',
'thumbnail': 'https://cwwp2.dot.ca.gov/data/d3/cctv/image/hwy50at24th/hwy50at24th.jpg',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
global_vars = self._search_regex(
r'<script[^<]+?([^<]+\.m3u8[^<]+)</script>',
webpage, 'Global Vars')
route_place = self._search_regex(r'routePlace\s*=\s*"([^"]+)"', global_vars, 'Route Place', fatal=False)
location_name = self._search_regex(r'locationName\s*=\s*"([^"]+)"', global_vars, 'Location Name', fatal=False)
poster_url = self._search_regex(r'posterURL\s*=\s*"([^"]+)"', global_vars, 'Poster Url', fatal=False)
video_stream = self._search_regex(r'videoStreamURL\s*=\s*"([^"]+)"', global_vars, 'Video Stream URL', fatal=False)
formats = self._extract_m3u8_formats(video_stream, video_id, 'ts', live=True)
self._sort_formats(formats)
return {
'id': video_id,
'title': f'{route_place} : {location_name}',
'is_live': True,
'formats': formats,
'thumbnail': poster_url,
}
-3
View File
@@ -13,8 +13,6 @@ class CAM4IE(InfoExtractor):
'ext': 'mp4',
'title': 're:^foxynesss [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'age_limit': 18,
'live_status': 'is_live',
'thumbnail': 'https://snapshots.xcdnpro.com/thumbnails/foxynesss',
}
}
@@ -31,5 +29,4 @@ class CAM4IE(InfoExtractor):
'is_live': True,
'age_limit': 18,
'formats': formats,
'thumbnail': f'https://snapshots.xcdnpro.com/thumbnails/{channel_id}',
}
+11 -2
View File
@@ -1,14 +1,17 @@
# coding: utf-8
from __future__ import unicode_literals
import calendar
import datetime
from .common import InfoExtractor
from ..utils import (
clean_html,
extract_timezone,
int_or_none,
parse_duration,
parse_resolution,
try_get,
unified_timestamp,
url_or_none,
)
@@ -92,8 +95,14 @@ class CCMAIE(InfoExtractor):
duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
tematica = try_get(informacio, lambda x: x['tematica']['text'])
timestamp = None
data_utc = try_get(informacio, lambda x: x['data_emissio']['utc'])
timestamp = unified_timestamp(data_utc)
try:
timezone, data_utc = extract_timezone(data_utc)
timestamp = calendar.timegm((datetime.datetime.strptime(
data_utc, '%Y-%d-%mT%H:%M:%S') - timezone).timetuple())
except TypeError:
pass
subtitles = {}
subtitols = media.get('subtitols') or []
+1 -2
View File
@@ -162,8 +162,7 @@ class CCTVIE(InfoExtractor):
'url': video_url,
'format_id': 'http',
'quality': quality,
# Sample clip
'preference': -10
'source_preference': -10
})
hls_url = try_get(data, lambda x: x['hls_url'], compat_str)
+37 -71
View File
@@ -75,7 +75,6 @@ from ..utils import (
str_to_int,
strip_or_none,
traverse_obj,
try_get,
unescapeHTML,
UnsupportedError,
unified_strdate,
@@ -226,7 +225,6 @@ class InfoExtractor(object):
The following fields are optional:
direct: True if a direct video file was given (must only be set by GenericIE)
alt_title: A secondary title of the video.
display_id An alternative identifier for the video, not necessarily
unique, but available before title. Typically, id is
@@ -241,7 +239,6 @@ class InfoExtractor(object):
* "resolution" (optional, string "{width}x{height}",
deprecated)
* "filesize" (optional, int)
* "http_headers" (dict) - HTTP headers for the request
thumbnail: Full URL to a video thumbnail image.
description: Full video description.
uploader: Full name of the video uploader.
@@ -275,8 +272,6 @@ class InfoExtractor(object):
* "url": A URL pointing to the subtitles file
It can optionally also have:
* "name": Name or description of the subtitles
* "http_headers": A dictionary of additional HTTP headers
to add to the request.
"ext" will be calculated from URL if missing
automatic_captions: Like 'subtitles'; contains automatically generated
captions instead of normal subtitles
@@ -426,8 +421,8 @@ class InfoExtractor(object):
title, description etc.
Subclasses of this should define a _VALID_URL regexp and, re-define the
_real_extract() and (optionally) _real_initialize() methods.
Subclasses of this one should re-define the _real_initialize() and
_real_extract() methods and define a _VALID_URL regexp.
Probably, they should also be added to the list of extractors.
Subclasses may also override suitable() if necessary, but ensure the function
@@ -640,7 +635,7 @@ class InfoExtractor(object):
}
if hasattr(e, 'countries'):
kwargs['countries'] = e.countries
raise type(e)(e.orig_msg, **kwargs)
raise type(e)(e.msg, **kwargs)
except compat_http_client.IncompleteRead as e:
raise ExtractorError('A network error has occurred.', cause=e, expected=True, video_id=self.get_temp_id(url))
except (KeyError, StopIteration) as e:
@@ -662,7 +657,7 @@ class InfoExtractor(object):
return False
def set_downloader(self, downloader):
"""Sets a YoutubeDL instance as the downloader for this IE."""
"""Sets the downloader for this IE."""
self._downloader = downloader
def _real_initialize(self):
@@ -671,7 +666,7 @@ class InfoExtractor(object):
def _real_extract(self, url):
"""Real extraction process. Redefine in subclasses."""
raise NotImplementedError('This method must be implemented by subclasses')
pass
@classmethod
def ie_key(cls):
@@ -750,7 +745,7 @@ class InfoExtractor(object):
errmsg = '%s: %s' % (errnote, error_to_compat_str(err))
if fatal:
raise ExtractorError(errmsg, cause=err)
raise ExtractorError(errmsg, sys.exc_info()[2], cause=err)
else:
self.report_warning(errmsg)
return False
@@ -1102,7 +1097,6 @@ class InfoExtractor(object):
if metadata_available and (
self.get_param('ignore_no_formats_error') or self.get_param('wait_for_video')):
self.report_warning(msg)
return
if method is not None:
msg = '%s. %s' % (msg, self._LOGIN_HINTS[method])
raise ExtractorError(msg, expected=True)
@@ -1141,8 +1135,8 @@ class InfoExtractor(object):
'url': url,
}
def playlist_from_matches(self, matches, playlist_id=None, playlist_title=None, getter=None, ie=None, video_kwargs=None, **kwargs):
urls = (self.url_result(self._proto_relative_url(m), ie, **(video_kwargs or {}))
def playlist_from_matches(self, matches, playlist_id=None, playlist_title=None, getter=None, ie=None, **kwargs):
urls = (self.url_result(self._proto_relative_url(m), ie)
for m in orderedSet(map(getter, matches) if getter else matches))
return self.playlist_result(urls, playlist_id, playlist_title, **kwargs)
@@ -1297,7 +1291,6 @@ class InfoExtractor(object):
return self._og_search_property('description', html, fatal=False, **kargs)
def _og_search_title(self, html, **kargs):
kargs.setdefault('fatal', False)
return self._og_search_property('title', html, **kargs)
def _og_search_video_url(self, html, name='video url', secure=True, **kargs):
@@ -1309,10 +1302,6 @@ class InfoExtractor(object):
def _og_search_url(self, html, **kargs):
return self._og_search_property('url', html, **kargs)
def _html_extract_title(self, html, name, **kwargs):
return self._html_search_regex(
r'(?s)<title>(.*?)</title>', html, name, **kwargs)
def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs):
name = variadic(name)
if display_name is None:
@@ -1458,7 +1447,7 @@ class InfoExtractor(object):
'title': part.get('name'),
'start_time': part.get('startOffset'),
'end_time': part.get('endOffset'),
} for part in variadic(e.get('hasPart') or []) if part.get('@type') == 'Clip']
} for part in e.get('hasPart', []) if part.get('@type') == 'Clip']
for idx, (last_c, current_c, next_c) in enumerate(zip(
[{'end_time': 0}] + chapters, chapters, chapters[1:])):
current_c['end_time'] = current_c['end_time'] or next_c['start_time']
@@ -1539,8 +1528,6 @@ class InfoExtractor(object):
'title': unescapeHTML(e.get('headline')),
'description': unescapeHTML(e.get('articleBody') or e.get('description')),
})
if traverse_obj(e, ('video', 0, '@type')) == 'VideoObject':
extract_video_object(e['video'][0])
elif item_type == 'VideoObject':
extract_video_object(e)
if expected_type is None:
@@ -1619,7 +1606,7 @@ class InfoExtractor(object):
'vcodec': {'type': 'ordered', 'regex': True,
'order': ['av0?1', 'vp0?9.2', 'vp0?9', '[hx]265|he?vc?', '[hx]264|avc', 'vp0?8', 'mp4v|h263', 'theora', '', None, 'none']},
'acodec': {'type': 'ordered', 'regex': True,
'order': ['[af]lac', 'wav|aiff', 'opus', 'vorbis|ogg', 'aac', 'mp?4a?', 'mp3', 'e-?a?c-?3', 'ac-?3', 'dts', '', None, 'none']},
'order': ['[af]lac', 'wav|aiff', 'opus', 'vorbis', 'aac', 'mp?4a?', 'mp3', 'e-?a?c-?3', 'ac-?3', 'dts', '', None, 'none']},
'hdr': {'type': 'ordered', 'regex': True, 'field': 'dynamic_range',
'order': ['dv', '(hdr)?12', r'(hdr)?10\+', '(hdr)?10', 'hlg', '', 'sdr', None]},
'proto': {'type': 'ordered', 'regex': True, 'field': 'protocol',
@@ -1662,31 +1649,31 @@ class InfoExtractor(object):
'format_id': {'type': 'alias', 'field': 'id'},
'preference': {'type': 'alias', 'field': 'ie_pref'},
'language_preference': {'type': 'alias', 'field': 'lang'},
'source_preference': {'type': 'alias', 'field': 'source'},
'protocol': {'type': 'alias', 'field': 'proto'},
'filesize_approx': {'type': 'alias', 'field': 'fs_approx'},
# Deprecated
'dimension': {'type': 'alias', 'field': 'res', 'deprecated': True},
'resolution': {'type': 'alias', 'field': 'res', 'deprecated': True},
'extension': {'type': 'alias', 'field': 'ext', 'deprecated': True},
'bitrate': {'type': 'alias', 'field': 'br', 'deprecated': True},
'total_bitrate': {'type': 'alias', 'field': 'tbr', 'deprecated': True},
'video_bitrate': {'type': 'alias', 'field': 'vbr', 'deprecated': True},
'audio_bitrate': {'type': 'alias', 'field': 'abr', 'deprecated': True},
'framerate': {'type': 'alias', 'field': 'fps', 'deprecated': True},
'filesize_estimate': {'type': 'alias', 'field': 'size', 'deprecated': True},
'samplerate': {'type': 'alias', 'field': 'asr', 'deprecated': True},
'video_ext': {'type': 'alias', 'field': 'vext', 'deprecated': True},
'audio_ext': {'type': 'alias', 'field': 'aext', 'deprecated': True},
'video_codec': {'type': 'alias', 'field': 'vcodec', 'deprecated': True},
'audio_codec': {'type': 'alias', 'field': 'acodec', 'deprecated': True},
'video': {'type': 'alias', 'field': 'hasvid', 'deprecated': True},
'has_video': {'type': 'alias', 'field': 'hasvid', 'deprecated': True},
'audio': {'type': 'alias', 'field': 'hasaud', 'deprecated': True},
'has_audio': {'type': 'alias', 'field': 'hasaud', 'deprecated': True},
'extractor': {'type': 'alias', 'field': 'ie_pref', 'deprecated': True},
'extractor_preference': {'type': 'alias', 'field': 'ie_pref', 'deprecated': True},
'dimension': {'type': 'alias', 'field': 'res'},
'resolution': {'type': 'alias', 'field': 'res'},
'extension': {'type': 'alias', 'field': 'ext'},
'bitrate': {'type': 'alias', 'field': 'br'},
'total_bitrate': {'type': 'alias', 'field': 'tbr'},
'video_bitrate': {'type': 'alias', 'field': 'vbr'},
'audio_bitrate': {'type': 'alias', 'field': 'abr'},
'framerate': {'type': 'alias', 'field': 'fps'},
'protocol': {'type': 'alias', 'field': 'proto'},
'source_preference': {'type': 'alias', 'field': 'source'},
'filesize_approx': {'type': 'alias', 'field': 'fs_approx'},
'filesize_estimate': {'type': 'alias', 'field': 'size'},
'samplerate': {'type': 'alias', 'field': 'asr'},
'video_ext': {'type': 'alias', 'field': 'vext'},
'audio_ext': {'type': 'alias', 'field': 'aext'},
'video_codec': {'type': 'alias', 'field': 'vcodec'},
'audio_codec': {'type': 'alias', 'field': 'acodec'},
'video': {'type': 'alias', 'field': 'hasvid'},
'has_video': {'type': 'alias', 'field': 'hasvid'},
'audio': {'type': 'alias', 'field': 'hasaud'},
'has_audio': {'type': 'alias', 'field': 'hasaud'},
'extractor': {'type': 'alias', 'field': 'ie_pref'},
'extractor_preference': {'type': 'alias', 'field': 'ie_pref'},
}
def __init__(self, ie, field_preference):
@@ -1786,7 +1773,7 @@ class InfoExtractor(object):
continue
if self._get_field_setting(field, 'type') == 'alias':
alias, field = field, self._get_field_setting(field, 'field')
if self._get_field_setting(alias, 'deprecated'):
if alias not in ('format_id', 'preference', 'language_preference'):
self.ydl.deprecation_warning(
f'Format sorting alias {alias} is deprecated '
f'and may be removed in a future version. Please use {field} instead')
@@ -2885,8 +2872,7 @@ class InfoExtractor(object):
segment_duration = None
if 'total_number' not in representation_ms_info and 'segment_duration' in representation_ms_info:
segment_duration = float_or_none(representation_ms_info['segment_duration'], representation_ms_info['timescale'])
representation_ms_info['total_number'] = int(math.ceil(
float_or_none(period_duration, segment_duration, default=0)))
representation_ms_info['total_number'] = int(math.ceil(float(period_duration) / segment_duration))
representation_ms_info['fragments'] = [{
media_location_key: media_template % {
'Number': segment_number,
@@ -2977,10 +2963,6 @@ class InfoExtractor(object):
f['url'] = initialization_url
f['fragments'].append({location_key(initialization_url): initialization_url})
f['fragments'].extend(representation_ms_info['fragments'])
if not period_duration:
period_duration = try_get(
representation_ms_info,
lambda r: sum(frag['duration'] for frag in r['fragments']), float)
else:
# Assuming direct URL to unfragmented media.
f['url'] = base_url
@@ -3123,7 +3105,7 @@ class InfoExtractor(object):
})
return formats, subtitles
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8_native', mpd_id=None, preference=None, quality=None):
def _parse_html5_media_entries(self, base_url, webpage, video_id, m3u8_id=None, m3u8_entry_protocol='m3u8', mpd_id=None, preference=None, quality=None):
def absolute_url(item_url):
return urljoin(base_url, item_url)
@@ -3680,7 +3662,7 @@ class InfoExtractor(object):
def mark_watched(self, *args, **kwargs):
if not self.get_param('mark_watched', False):
return
if (hasattr(self, '_NETRC_MACHINE') and self._get_login_info()[0] is not None
if (self._get_login_info()[0] is not None
or self.get_param('cookiefile')
or self.get_param('cookiesfrombrowser')):
self._mark_watched(*args, **kwargs)
@@ -3728,22 +3710,6 @@ class InfoExtractor(object):
return [] if default is NO_DEFAULT else default
return list(val) if casesense else [x.lower() for x in val]
def _yes_playlist(self, playlist_id, video_id, smuggled_data=None, *, playlist_label='playlist', video_label='video'):
if not playlist_id or not video_id:
return not video_id
no_playlist = (smuggled_data or {}).get('force_noplaylist')
if no_playlist is not None:
return not no_playlist
video_id = '' if video_id is True else f' {video_id}'
playlist_id = '' if playlist_id is True else f' {playlist_id}'
if self.get_param('noplaylist'):
self.to_screen(f'Downloading just the {video_label}{video_id} because of --no-playlist')
return False
self.to_screen(f'Downloading {playlist_label}{playlist_id} - add --no-playlist to download just the {video_label}{video_id}')
return True
class SearchInfoExtractor(InfoExtractor):
"""
-148
View File
@@ -1,148 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
str_or_none,
try_get,
unified_timestamp,
update_url_query,
urljoin,
)
# compat_range
try:
if callable(xrange):
range = xrange
except (NameError, TypeError):
pass
class CPACIE(InfoExtractor):
IE_NAME = 'cpac'
_VALID_URL = r'https?://(?:www\.)?cpac\.ca/(?P<fr>l-)?episode\?id=(?P<id>[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12})'
_TEST = {
# 'url': 'http://www.cpac.ca/en/programs/primetime-politics/episodes/65490909',
'url': 'https://www.cpac.ca/episode?id=fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
'md5': 'e46ad699caafd7aa6024279f2614e8fa',
'info_dict': {
'id': 'fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
'ext': 'mp4',
'upload_date': '20220215',
'title': 'News Conference to Celebrate National Kindness Week February 15, 2022',
'description': 'md5:466a206abd21f3a6f776cdef290c23fb',
'timestamp': 1644901200,
},
'params': {
'format': 'bestvideo',
'hls_prefer_native': True,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
url_lang = 'fr' if '/l-episode?' in url else 'en'
content = self._download_json(
'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/episode/index.xml&crafterSite=cpacca&id=' + video_id,
video_id)
video_url = try_get(content, lambda x: x['page']['details']['videoUrl'], compat_str)
formats = []
if video_url:
content = content['page']
title = str_or_none(content['details']['title_%s_t' % (url_lang, )])
formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', ext='mp4')
for fmt in formats:
# prefer language to match URL
fmt_lang = fmt.get('language')
if fmt_lang == url_lang:
fmt['language_preference'] = 10
elif not fmt_lang:
fmt['language_preference'] = -1
else:
fmt['language_preference'] = -10
self._sort_formats(formats)
category = str_or_none(content['details']['category_%s_t' % (url_lang, )])
def is_live(v_type):
return (v_type == 'live') if v_type is not None else None
return {
'id': video_id,
'formats': formats,
'title': title,
'description': str_or_none(content['details'].get('description_%s_t' % (url_lang, ))),
'timestamp': unified_timestamp(content['details'].get('liveDateTime')),
'category': [category] if category else None,
'thumbnail': urljoin(url, str_or_none(content['details'].get('image_%s_s' % (url_lang, )))),
'is_live': is_live(content['details'].get('type')),
}
class CPACPlaylistIE(InfoExtractor):
IE_NAME = 'cpac:playlist'
_VALID_URL = r'(?i)https?://(?:www\.)?cpac\.ca/(?:program|search|(?P<fr>emission|rechercher))\?(?:[^&]+&)*?(?P<id>(?:id=\d+|programId=\d+|key=[^&]+))'
_TESTS = [{
'url': 'https://www.cpac.ca/program?id=6',
'info_dict': {
'id': 'id=6',
'title': 'Headline Politics',
'description': 'Watch CPACs signature long-form coverage of the days pressing political events as they unfold.',
},
'playlist_count': 10,
}, {
'url': 'https://www.cpac.ca/search?key=hudson&type=all&order=desc',
'info_dict': {
'id': 'key=hudson',
'title': 'hudson',
},
'playlist_count': 22,
}, {
'url': 'https://www.cpac.ca/search?programId=50',
'info_dict': {
'id': 'programId=50',
'title': '50',
},
'playlist_count': 9,
}, {
'url': 'https://www.cpac.ca/emission?id=6',
'only_matching': True,
}, {
'url': 'https://www.cpac.ca/rechercher?key=hudson&type=all&order=desc',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
url_lang = 'fr' if any(x in url for x in ('/emission?', '/rechercher?')) else 'en'
pl_type, list_type = ('program', 'itemList') if any(x in url for x in ('/program?', '/emission?')) else ('search', 'searchResult')
api_url = (
'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/%s/index.xml&crafterSite=cpacca&%s'
% (pl_type, video_id, ))
content = self._download_json(api_url, video_id)
entries = []
total_pages = int_or_none(try_get(content, lambda x: x['page'][list_type]['totalPages']), default=1)
for page in range(1, total_pages + 1):
if page > 1:
api_url = update_url_query(api_url, {'page': '%d' % (page, ), })
content = self._download_json(
api_url, video_id,
note='Downloading continuation - %d' % (page, ),
fatal=False)
for item in try_get(content, lambda x: x['page'][list_type]['item'], list) or []:
episode_url = urljoin(url, try_get(item, lambda x: x['url_%s_s' % (url_lang, )]))
if episode_url:
entries.append(episode_url)
return self.playlist_result(
(self.url_result(entry) for entry in entries),
playlist_id=video_id,
playlist_title=try_get(content, lambda x: x['page']['program']['title_%s_t' % (url_lang, )]) or video_id.split('=')[-1],
playlist_description=try_get(content, lambda x: x['page']['program']['description_%s_t' % (url_lang, )]),
)
+51 -142
View File
@@ -1,7 +1,6 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import re
import json
import zlib
@@ -24,17 +23,15 @@ from ..utils import (
bytes_to_intlist,
extract_attributes,
float_or_none,
format_field,
intlist_to_bytes,
int_or_none,
join_nonempty,
lowercase_escape,
merge_dicts,
qualities,
remove_end,
sanitized_Request,
traverse_obj,
try_get,
urlencode_postdata,
xpath_text,
)
from ..aes import (
@@ -43,8 +40,8 @@ from ..aes import (
class CrunchyrollBaseIE(InfoExtractor):
_LOGIN_URL = 'https://www.crunchyroll.com/welcome/login'
_API_BASE = 'https://api.crunchyroll.com'
_LOGIN_URL = 'https://www.crunchyroll.com/login'
_LOGIN_FORM = 'login_form'
_NETRC_MACHINE = 'crunchyroll'
def _call_rpc_api(self, method, video_id, note=None, data=None):
@@ -61,33 +58,50 @@ class CrunchyrollBaseIE(InfoExtractor):
username, password = self._get_login_info()
if username is None:
return
if self._get_cookies(self._LOGIN_URL).get('etp_rt'):
login_page = self._download_webpage(
self._LOGIN_URL, None, 'Downloading login page')
def is_logged(webpage):
return 'href="/logout"' in webpage
# Already logged in
if is_logged(login_page):
return
upsell_response = self._download_json(
f'{self._API_BASE}/get_upsell_data.0.json', None, 'Getting session id',
query={
'sess_id': 1,
'device_id': 'whatvalueshouldbeforweb',
'device_type': 'com.crunchyroll.static',
'access_token': 'giKq5eY27ny3cqz',
'referer': self._LOGIN_URL
})
if upsell_response['code'] != 'ok':
raise ExtractorError('Could not get session id')
session_id = upsell_response['data']['session_id']
login_form_str = self._search_regex(
r'(?P<form><form[^>]+?id=(["\'])%s\2[^>]*>)' % self._LOGIN_FORM,
login_page, 'login form', group='form')
login_response = self._download_json(
f'{self._API_BASE}/login.1.json', None, 'Logging in',
data=compat_urllib_parse_urlencode({
'account': username,
'password': password,
'session_id': session_id
}).encode('ascii'))
if login_response['code'] != 'ok':
raise ExtractorError('Login failed. Server message: %s' % login_response['message'], expected=True)
if not self._get_cookies(self._LOGIN_URL).get('etp_rt'):
raise ExtractorError('Login succeeded but did not set etp_rt cookie')
post_url = extract_attributes(login_form_str).get('action')
if not post_url:
post_url = self._LOGIN_URL
elif not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
login_form = self._form_hidden_inputs(self._LOGIN_FORM, login_page)
login_form.update({
'login_form[name]': username,
'login_form[password]': password,
})
response = self._download_webpage(
post_url, None, 'Logging in', 'Wrong login info',
data=urlencode_postdata(login_form),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
# Successful login
if is_logged(response):
return
error = self._html_search_regex(
'(?s)<ul[^>]+class=["\']messages["\'][^>]*>(.+?)</ul>',
response, 'error message', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
def _real_initialize(self):
self._login()
@@ -719,118 +733,13 @@ class CrunchyrollBetaIE(CrunchyrollBaseIE):
def _real_extract(self, url):
lang, internal_id, display_id = self._match_valid_url(url).group('lang', 'internal_id', 'id')
webpage = self._download_webpage(url, display_id)
initial_state = self._parse_json(
self._search_regex(r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'initial state'),
display_id)
episode_data = initial_state['content']['byId'][internal_id]
if not self._get_cookies(url).get('etp_rt'):
video_id = episode_data['external_id'].split('.')[1]
series_id = episode_data['episode_metadata']['series_slug_title']
return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id}/{display_id}-{video_id}',
CrunchyrollIE.ie_key(), video_id)
app_config = self._parse_json(
self._search_regex(r'__APP_CONFIG__\s*=\s*({.+?})\s*;', webpage, 'app config'),
display_id)
client_id = app_config['cxApiParams']['accountAuthClientId']
api_domain = app_config['cxApiParams']['apiDomain']
basic_token = str(base64.b64encode(('%s:' % client_id).encode('ascii')), 'ascii')
auth_response = self._download_json(
f'{api_domain}/auth/v1/token', display_id,
note='Authenticating with cookie',
headers={
'Authorization': 'Basic ' + basic_token
}, data='grant_type=etp_rt_cookie'.encode('ascii'))
policy_response = self._download_json(
f'{api_domain}/index/v2', display_id,
note='Retrieving signed policy',
headers={
'Authorization': auth_response['token_type'] + ' ' + auth_response['access_token']
})
bucket = policy_response['cms']['bucket']
params = {
'Policy': policy_response['cms']['policy'],
'Signature': policy_response['cms']['signature'],
'Key-Pair-Id': policy_response['cms']['key_pair_id']
}
locale = traverse_obj(initial_state, ('localization', 'locale'))
if locale:
params['locale'] = locale
episode_response = self._download_json(
f'{api_domain}/cms/v2{bucket}/episodes/{internal_id}', display_id,
note='Retrieving episode metadata',
query=params)
if episode_response.get('is_premium_only') and not episode_response.get('playback'):
raise ExtractorError('This video is for premium members only.', expected=True)
stream_response = self._download_json(
episode_response['playback'], display_id,
note='Retrieving stream info')
thumbnails = []
for thumbnails_data in traverse_obj(episode_response, ('images', 'thumbnail')):
for thumbnail_data in thumbnails_data:
thumbnails.append({
'url': thumbnail_data.get('source'),
'width': thumbnail_data.get('width'),
'height': thumbnail_data.get('height'),
})
subtitles = {}
for lang, subtitle_data in stream_response.get('subtitles').items():
subtitles[lang] = [{
'url': subtitle_data.get('url'),
'ext': subtitle_data.get('format')
}]
requested_hardsubs = [('' if val == 'none' else val) for val in (self._configuration_arg('hardsub') or ['none'])]
hardsub_preference = qualities(requested_hardsubs[::-1])
requested_formats = self._configuration_arg('format') or ['adaptive_hls']
formats = []
for stream_type, streams in stream_response.get('streams', {}).items():
if stream_type not in requested_formats:
continue
for stream in streams.values():
hardsub_lang = stream.get('hardsub_locale') or ''
if hardsub_lang.lower() not in requested_hardsubs:
continue
format_id = join_nonempty(
stream_type,
format_field(stream, 'hardsub_locale', 'hardsub-%s'))
if not stream.get('url'):
continue
if stream_type.split('_')[-1] == 'hls':
adaptive_formats = self._extract_m3u8_formats(
stream['url'], display_id, 'mp4', m3u8_id=format_id,
note='Downloading %s information' % format_id,
fatal=False)
elif stream_type.split('_')[-1] == 'dash':
adaptive_formats = self._extract_mpd_formats(
stream['url'], display_id, mpd_id=format_id,
note='Downloading %s information' % format_id,
fatal=False)
for f in adaptive_formats:
if f.get('acodec') != 'none':
f['language'] = stream_response.get('audio_locale')
f['quality'] = hardsub_preference(hardsub_lang.lower())
formats.extend(adaptive_formats)
self._sort_formats(formats)
return {
'id': internal_id,
'title': '%s Episode %s %s' % (episode_response.get('season_title'), episode_response.get('episode'), episode_response.get('title')),
'description': episode_response.get('description').replace(r'\r\n', '\n'),
'duration': float_or_none(episode_response.get('duration_ms'), 1000),
'thumbnails': thumbnails,
'series': episode_response.get('series_title'),
'series_id': episode_response.get('series_id'),
'season': episode_response.get('season_title'),
'season_id': episode_response.get('season_id'),
'season_number': episode_response.get('season_number'),
'episode': episode_response.get('title'),
'episode_number': episode_response.get('sequence_number'),
'subtitles': subtitles,
'formats': formats
}
episode_data = self._parse_json(
self._search_regex(r'__INITIAL_STATE__\s*=\s*({.+?})\s*;', webpage, 'episode data'),
display_id)['content']['byId'][internal_id]
video_id = episode_data['external_id'].split('.')[1]
series_id = episode_data['episode_metadata']['series_slug_title']
return self.url_result(f'https://www.crunchyroll.com/{lang}{series_id}/{display_id}-{video_id}',
CrunchyrollIE.ie_key(), video_id)
class CrunchyrollBetaShowIE(CrunchyrollBaseIE):
+2 -48
View File
@@ -3,7 +3,6 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_HTMLParseError
from ..utils import (
determine_ext,
ExtractorError,
@@ -12,11 +11,9 @@ from ..utils import (
get_element_by_attribute,
get_element_by_class,
int_or_none,
join_nonempty,
js_to_json,
merge_dicts,
parse_iso8601,
parse_qs,
smuggle_url,
str_to_int,
unescapeHTML,
@@ -129,12 +126,8 @@ class CSpanIE(InfoExtractor):
ext = 'vtt'
subtitle['ext'] = ext
ld_info = self._search_json_ld(webpage, video_id, default={})
try:
title = get_element_by_class('video-page-title', webpage)
except compat_HTMLParseError:
title = None
if title is None:
title = self._og_search_title(webpage)
title = get_element_by_class('video-page-title', webpage) or \
self._og_search_title(webpage)
description = get_element_by_attribute('itemprop', 'description', webpage) or \
self._html_search_meta(['og:description', 'description'], webpage)
return merge_dicts(info, ld_info, {
@@ -249,42 +242,3 @@ class CSpanIE(InfoExtractor):
'title': title,
'id': 'c' + video_id if video_type == 'clip' else video_id,
}
class CSpanCongressIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?c-span\.org/congress/'
_TESTS = [{
'url': 'https://www.c-span.org/congress/?chamber=house&date=2017-12-13&t=1513208380',
'info_dict': {
'id': 'house_2017-12-13',
'title': 'Congressional Chronicle - Members of Congress, Hearings and More',
'description': 'md5:54c264b7a8f219937987610243305a84',
'thumbnail': r're:https://ximage.c-spanvideo.org/.+',
'ext': 'mp4'
}
}]
def _real_extract(self, url):
query = parse_qs(url)
video_date = query.get('date', [None])[0]
video_id = join_nonempty(query.get('chamber', ['senate'])[0], video_date, delim='_')
webpage = self._download_webpage(url, video_id)
if not video_date:
jwp_date = re.search(r'jwsetup.clipprogdate = \'(?P<date>\d{4}-\d{2}-\d{2})\';', webpage)
if jwp_date:
video_id = f'{video_id}_{jwp_date.group("date")}'
jwplayer_data = self._parse_json(
self._search_regex(r'jwsetup\s*=\s*({(?:.|\n)[^;]+});', webpage, 'player config'),
video_id, transform_source=js_to_json)
title = (self._og_search_title(webpage, default=None)
or self._html_search_regex(r'(?s)<title>(.*?)</title>', webpage, 'video title'))
description = (self._og_search_description(webpage, default=None)
or self._html_search_meta('description', webpage, 'description', default=None))
return {
**self._parse_jwplayer_data(jwplayer_data, video_id, False),
'title': re.sub(r'\s+', ' ', title.split('|')[0]).strip(),
'description': description,
'http_headers': {'Referer': 'https://www.c-span.org/'},
}
+6 -2
View File
@@ -207,10 +207,12 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
video_id, playlist_id = self._match_valid_url(url).groups()
if playlist_id:
if self._yes_playlist(playlist_id, video_id):
if not self.get_param('noplaylist'):
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id)
return self.url_result(
'http://www.dailymotion.com/playlist/' + playlist_id,
'DailymotionPlaylist', playlist_id)
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
password = self.get_param('videopassword')
media = self._call_api(
@@ -259,7 +261,9 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
continue
if media_type == 'application/x-mpegURL':
formats.extend(self._extract_m3u8_formats(
media_url, video_id, 'mp4', live=is_live, m3u8_id='hls', fatal=False))
media_url, video_id, 'mp4',
'm3u8' if is_live else 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
f = {
'url': media_url,
+4 -1
View File
@@ -157,8 +157,11 @@ class DaumListIE(InfoExtractor):
query_dict = parse_qs(url)
if 'clipid' in query_dict:
clip_id = query_dict['clipid'][0]
if not self._yes_playlist(list_id, clip_id):
if self.get_param('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % clip_id)
return self.url_result(DaumClipIE._URL_TEMPLATE % clip_id, 'DaumClip')
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % list_id)
class DaumPlaylistIE(DaumListIE):
-48
View File
@@ -1,48 +0,0 @@
from .common import InfoExtractor
from ..utils import js_to_json, urljoin
class DaystarClipIE(InfoExtractor):
IE_NAME = 'daystar:clip'
_VALID_URL = r'https?://player\.daystar\.tv/(?P<id>\w+)'
_TESTS = [{
'url': 'https://player.daystar.tv/0MTO2ITM',
'info_dict': {
'id': '0MTO2ITM',
'ext': 'mp4',
'title': 'The Dark World of COVID Pt. 1 | Aaron Siri',
'description': 'a420d320dda734e5f29458df3606c5f4',
'thumbnail': r're:^https?://.+\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
src_iframe = self._search_regex(r'\<iframe[^>]+src="([^"]+)"', webpage, 'src iframe')
webpage_iframe = self._download_webpage(
src_iframe.replace('player.php', 'config2.php'), video_id, headers={'Referer': src_iframe})
sources = self._parse_json(self._search_regex(
r'sources\:\s*(\[.*?\])', webpage_iframe, 'm3u8 source'), video_id, transform_source=js_to_json)
formats, subtitles = [], {}
for source in sources:
file = source.get('file')
if file and source.get('type') == 'm3u8':
fmts, subs = self._extract_m3u8_formats_and_subtitles(
urljoin('https://www.lightcast.com/embed/', file),
video_id, 'mp4', fatal=False, headers={'Referer': src_iframe})
formats.extend(fmts)
subtitles = self._merge_subtitles(subtitles, subs)
self._sort_formats(formats)
return {
'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
'thumbnail': self._search_regex(r'image:\s*"([^"]+)', webpage_iframe, 'thumbnail'),
'formats': formats,
'subtitles': subtitles,
}
+16 -21
View File
@@ -20,16 +20,6 @@ class DoodStreamIE(InfoExtractor):
'description': 'Kat Wonders - Monthly May 2020 | DoodStream.com',
'thumbnail': 'https://img.doodcdn.com/snaps/flyus84qgl2fsk4g.jpg',
}
}, {
'url': 'http://dood.watch/d/5s1wmbdacezb',
'md5': '4568b83b31e13242b3f1ff96c55f0595',
'info_dict': {
'id': '5s1wmbdacezb',
'ext': 'mp4',
'title': 'Kat Wonders - Monthly May 2020',
'description': 'Kat Wonders - Monthly May 2020 | DoodStream.com',
'thumbnail': 'https://img.doodcdn.com/snaps/flyus84qgl2fsk4g.jpg',
}
}, {
'url': 'https://dood.to/d/jzrxn12t2s7n',
'md5': '3207e199426eca7c2aa23c2872e6728a',
@@ -44,26 +34,31 @@ class DoodStreamIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
url = f'https://dood.to/e/{video_id}'
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None)
thumb = self._html_search_meta(['og:image', 'twitter:image'], webpage, default=None)
if '/d/' in url:
url = "https://dood.to" + self._html_search_regex(
r'<iframe src="(/e/[a-z0-9]+)"', webpage, 'embed')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_search_meta(['og:title', 'twitter:title'],
webpage, default=None)
thumb = self._html_search_meta(['og:image', 'twitter:image'],
webpage, default=None)
token = self._html_search_regex(r'[?&]token=([a-z0-9]+)[&\']', webpage, 'token')
description = self._html_search_meta(
['og:description', 'description', 'twitter:description'], webpage, default=None)
['og:description', 'description', 'twitter:description'],
webpage, default=None)
auth_url = 'https://dood.to' + self._html_search_regex(
r'(/pass_md5.*?)\'', webpage, 'pass_md5')
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/66.0',
'referer': url
}
pass_md5 = self._html_search_regex(r'(/pass_md5.*?)\'', webpage, 'pass_md5')
final_url = ''.join((
self._download_webpage(f'https://dood.to{pass_md5}', video_id, headers=headers),
*(random.choice(string.ascii_letters + string.digits) for _ in range(10)),
f'?token={token}&expiry={int(time.time() * 1000)}',
))
webpage = self._download_webpage(auth_url, video_id, headers=headers)
final_url = webpage + ''.join([random.choice(string.ascii_letters + string.digits) for _ in range(10)]) + "?token=" + token + "&expiry=" + str(int(time.time() * 1000))
return {
'id': video_id,
-279
View File
@@ -369,222 +369,6 @@ class DiscoveryPlusBaseIE(DPlayBaseIE):
return self._get_disco_api_info(url, self._match_id(url), **self._DISCO_API_PARAMS)
class GoDiscoveryIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:go\.)?discovery\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://go.discovery.com/video/dirty-jobs-discovery-atve-us/rodbuster-galvanizer',
'info_dict': {
'id': '4164906',
'display_id': 'dirty-jobs-discovery-atve-us/rodbuster-galvanizer',
'ext': 'mp4',
'title': 'Rodbuster / Galvanizer',
'description': 'Mike installs rebar with a team of rodbusters, then he galvanizes steel.',
'season_number': 9,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://discovery.com/video/dirty-jobs-discovery-atve-us/rodbuster-galvanizer',
'only_matching': True,
}]
_PRODUCT = 'dsc'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.go.discovery.com',
'realm': 'go',
'country': 'us',
}
class TravelChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?travelchannel\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.travelchannel.com/video/ghost-adventures-travel-channel/ghost-train-of-ely',
'info_dict': {
'id': '2220256',
'display_id': 'ghost-adventures-travel-channel/ghost-train-of-ely',
'ext': 'mp4',
'title': 'Ghost Train of Ely',
'description': 'The crew investigates the dark history of the Nevada Northern Railway.',
'season_number': 24,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.travelchannel.com/video/ghost-adventures-travel-channel/ghost-train-of-ely',
'only_matching': True,
}]
_PRODUCT = 'trav'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.watch.travelchannel.com',
'realm': 'go',
'country': 'us',
}
class CookingChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?cookingchanneltv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.cookingchanneltv.com/video/carnival-eats-cooking-channel/the-postman-always-brings-rice-2348634',
'info_dict': {
'id': '2348634',
'display_id': 'carnival-eats-cooking-channel/the-postman-always-brings-rice-2348634',
'ext': 'mp4',
'title': 'The Postman Always Brings Rice',
'description': 'Noah visits the Maui Fair and the Aurora Winter Festival in Vancouver.',
'season_number': 9,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.cookingchanneltv.com/video/carnival-eats-cooking-channel/the-postman-always-brings-rice-2348634',
'only_matching': True,
}]
_PRODUCT = 'cook'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.watch.cookingchanneltv.com',
'realm': 'go',
'country': 'us',
}
class HGTVUsaIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?hgtv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.hgtv.com/video/home-inspector-joe-hgtv-atve-us/this-mold-house',
'info_dict': {
'id': '4289736',
'display_id': 'home-inspector-joe-hgtv-atve-us/this-mold-house',
'ext': 'mp4',
'title': 'This Mold House',
'description': 'Joe and Noel help take a familys dream home from hazardous to fabulous.',
'season_number': 1,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.hgtv.com/video/home-inspector-joe-hgtv-atve-us/this-mold-house',
'only_matching': True,
}]
_PRODUCT = 'hgtv'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.watch.hgtv.com',
'realm': 'go',
'country': 'us',
}
class FoodNetworkIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:watch\.)?foodnetwork\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://watch.foodnetwork.com/video/kids-baking-championship-food-network/float-like-a-butterfly',
'info_dict': {
'id': '4116449',
'display_id': 'kids-baking-championship-food-network/float-like-a-butterfly',
'ext': 'mp4',
'title': 'Float Like a Butterfly',
'description': 'The 12 kid bakers create colorful carved butterfly cakes.',
'season_number': 10,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.foodnetwork.com/video/kids-baking-championship-food-network/float-like-a-butterfly',
'only_matching': True,
}]
_PRODUCT = 'food'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.watch.foodnetwork.com',
'realm': 'go',
'country': 'us',
}
class DestinationAmericaIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?destinationamerica\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.destinationamerica.com/video/alaska-monsters-destination-america-atve-us/central-alaskas-bigfoot',
'info_dict': {
'id': '4210904',
'display_id': 'alaska-monsters-destination-america-atve-us/central-alaskas-bigfoot',
'ext': 'mp4',
'title': 'Central Alaskas Bigfoot',
'description': 'A team heads to central Alaska to investigate an aggressive Bigfoot.',
'season_number': 1,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://www.destinationamerica.com/video/alaska-monsters-destination-america-atve-us/central-alaskas-bigfoot',
'only_matching': True,
}]
_PRODUCT = 'dam'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.destinationamerica.com',
'realm': 'go',
'country': 'us',
}
class InvestigationDiscoveryIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?investigationdiscovery\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.investigationdiscovery.com/video/unmasked-investigation-discovery/the-killer-clown',
'info_dict': {
'id': '2139409',
'display_id': 'unmasked-investigation-discovery/the-killer-clown',
'ext': 'mp4',
'title': 'The Killer Clown',
'description': 'A wealthy Florida woman is fatally shot in the face by a clown at her door.',
'season_number': 1,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://www.investigationdiscovery.com/video/unmasked-investigation-discovery/the-killer-clown',
'only_matching': True,
}]
_PRODUCT = 'ids'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.investigationdiscovery.com',
'realm': 'go',
'country': 'us',
}
class AmHistoryChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?ahctv\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.ahctv.com/video/modern-sniper-ahc/army',
'info_dict': {
'id': '2309730',
'display_id': 'modern-sniper-ahc/army',
'ext': 'mp4',
'title': 'Army',
'description': 'Snipers today face challenges their predecessors couldve only dreamed of.',
'season_number': 1,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://www.ahctv.com/video/modern-sniper-ahc/army',
'only_matching': True,
}]
_PRODUCT = 'ahc'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.ahctv.com',
'realm': 'go',
'country': 'us',
}
class ScienceChannelIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?sciencechannel\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
@@ -599,9 +383,6 @@ class ScienceChannelIE(DiscoveryPlusBaseIE):
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://www.sciencechannel.com/video/strangest-things-science-atve-us/nazi-mystery-machine',
'only_matching': True,
}]
_PRODUCT = 'sci'
@@ -626,9 +407,6 @@ class DIYNetworkIE(DiscoveryPlusBaseIE):
'episode_number': 2,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://watch.diynetwork.com/video/pool-kings-diy-network/bringing-beach-life-to-texas',
'only_matching': True,
}]
_PRODUCT = 'diy'
@@ -639,33 +417,6 @@ class DIYNetworkIE(DiscoveryPlusBaseIE):
}
class DiscoveryLifeIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoverylife\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://www.discoverylife.com/video/surviving-death-discovery-life-atve-us/bodily-trauma',
'info_dict': {
'id': '2218238',
'display_id': 'surviving-death-discovery-life-atve-us/bodily-trauma',
'ext': 'mp4',
'title': 'Bodily Trauma',
'description': 'Meet three people who tested the limits of the human body.',
'season_number': 1,
'episode_number': 2,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://www.discoverylife.com/video/surviving-death-discovery-life-atve-us/bodily-trauma',
'only_matching': True,
}]
_PRODUCT = 'dlf'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.discoverylife.com',
'realm': 'go',
'country': 'us',
}
class AnimalPlanetIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?animalplanet\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
@@ -680,9 +431,6 @@ class AnimalPlanetIE(DiscoveryPlusBaseIE):
'episode_number': 11,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://www.animalplanet.com/video/north-woods-law-animal-planet/squirrel-showdown',
'only_matching': True,
}]
_PRODUCT = 'apl'
@@ -693,33 +441,6 @@ class AnimalPlanetIE(DiscoveryPlusBaseIE):
}
class TLCIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:go\.)?tlc\.com/video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
'url': 'https://go.tlc.com/video/my-600-lb-life-tlc/melissas-story-part-1',
'info_dict': {
'id': '2206540',
'display_id': 'my-600-lb-life-tlc/melissas-story-part-1',
'ext': 'mp4',
'title': 'Melissas Story (Part 1)',
'description': 'At 650 lbs, Melissa is ready to begin her seven-year weight loss journey.',
'season_number': 1,
'episode_number': 1,
},
'skip': 'Available for Premium users',
}, {
'url': 'https://go.tlc.com/video/my-600-lb-life-tlc/melissas-story-part-1',
'only_matching': True,
}]
_PRODUCT = 'tlc'
_DISCO_API_PARAMS = {
'disco_host': 'us1-prod-direct.tlc.com',
'realm': 'go',
'country': 'us',
}
class DiscoveryPlusIE(DiscoveryPlusBaseIE):
_VALID_URL = r'https?://(?:www\.)?discoveryplus\.com/(?!it/)(?:\w{2}/)?video' + DPlayBaseIE._PATH_REGEX
_TESTS = [{
+2 -2
View File
@@ -56,8 +56,8 @@ class DropboxIE(InfoExtractor):
else:
raise ExtractorError('Password protected video, use --video-password <password>', expected=True)
json_string = self._html_search_regex(r'InitReact\.mountComponent\(.*?,\s*(\{.+\})\s*?\)', webpage, 'Info JSON')
info_json = self._parse_json(json_string, video_id).get('props')
json_string = self._html_search_regex(r'InitReact\.mountComponent.+ "props":(.+), "elem_id"', webpage, 'Info JSON')
info_json = self._parse_json(json_string, video_id)
transcode_url = traverse_obj(info_json, ((None, 'preview'), 'file', 'preview', 'content', 'transcode_url'), get_all=False)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(transcode_url, video_id)
+10 -6
View File
@@ -7,11 +7,13 @@ import re
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..aes import aes_cbc_decrypt
from ..compat import compat_urllib_parse_unquote
from ..utils import (
bytes_to_intlist,
ExtractorError,
int_or_none,
intlist_to_bytes,
float_or_none,
mimetype2ext,
str_or_none,
@@ -189,11 +191,13 @@ class DRTVIE(InfoExtractor):
def decrypt_uri(e):
n = int(e[2:10], 16)
a = e[10 + n:]
data = hex_to_bytes(e[10:10 + n])
key = hashlib.sha256(('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest()
iv = hex_to_bytes(a)
decrypted = unpad_pkcs7(aes_cbc_decrypt_bytes(data, key, iv))
return decrypted.decode('utf-8').split('?')[0]
data = bytes_to_intlist(hex_to_bytes(e[10:10 + n]))
key = bytes_to_intlist(hashlib.sha256(
('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest())
iv = bytes_to_intlist(hex_to_bytes(a))
decrypted = aes_cbc_decrypt(data, key, iv)
return intlist_to_bytes(
decrypted[:-decrypted[-1]]).decode('utf-8').split('?')[0]
for asset in assets:
kind = asset.get('Kind')
+10
View File
@@ -7,6 +7,16 @@ class EngadgetIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?engadget\.com/video/(?P<id>[^/?#]+)'
_TESTS = [{
# video with 5min ID
'url': 'http://www.engadget.com/video/518153925/',
'md5': 'c6820d4828a5064447a4d9fc73f312c9',
'info_dict': {
'id': '518153925',
'ext': 'mp4',
'title': 'Samsung Galaxy Tab Pro 8.4 Review',
},
'add_ie': ['FiveMin'],
}, {
# video with vidible ID
'url': 'https://www.engadget.com/video/57a28462134aa15a39f0421a/',
'only_matching': True,
-316
View File
@@ -1,316 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
clean_html,
determine_ext,
ExtractorError,
dict_get,
int_or_none,
merge_dicts,
parse_qs,
parse_age_limit,
parse_iso8601,
str_or_none,
try_get,
unescapeHTML,
url_or_none,
variadic,
)
class ERTFlixBaseIE(InfoExtractor):
def _call_api(
self, video_id, method='Player/AcquireContent', api_version=1,
param_headers=None, data=None, headers=None, **params):
platform_codename = {'platformCodename': 'www'}
headers_as_param = {'X-Api-Date-Format': 'iso', 'X-Api-Camel-Case': False}
headers_as_param.update(param_headers or {})
headers = headers or {}
if data:
headers['Content-Type'] = headers_as_param['Content-Type'] = 'application/json;charset=utf-8'
data = json.dumps(merge_dicts(platform_codename, data)).encode('utf-8')
query = merge_dicts(
{} if data else platform_codename,
{'$headers': json.dumps(headers_as_param)},
params)
response = self._download_json(
'https://api.app.ertflix.gr/v%s/%s' % (str(api_version), method),
video_id, fatal=False, query=query, data=data, headers=headers)
if try_get(response, lambda x: x['Result']['Success']) is True:
return response
def _call_api_get_tiles(self, video_id, *tile_ids):
requested_tile_ids = [video_id] + list(tile_ids)
requested_tiles = [{'Id': tile_id} for tile_id in requested_tile_ids]
tiles_response = self._call_api(
video_id, method='Tile/GetTiles', api_version=2,
data={'RequestedTiles': requested_tiles})
tiles = try_get(tiles_response, lambda x: x['Tiles'], list) or []
if tile_ids:
if sorted([tile['Id'] for tile in tiles]) != sorted(requested_tile_ids):
raise ExtractorError('Requested tiles not found', video_id=video_id)
return tiles
try:
return next(tile for tile in tiles if tile['Id'] == video_id)
except StopIteration:
raise ExtractorError('No matching tile found', video_id=video_id)
class ERTFlixCodenameIE(ERTFlixBaseIE):
IE_NAME = 'ertflix:codename'
IE_DESC = 'ERTFLIX videos by codename'
_VALID_URL = r'ertflix:(?P<id>[\w-]+)'
_TESTS = [{
'url': 'ertflix:monogramma-praxitelis-tzanoylinos',
'md5': '5b9c2cd171f09126167e4082fc1dd0ef',
'info_dict': {
'id': 'monogramma-praxitelis-tzanoylinos',
'ext': 'mp4',
'title': 'md5:ef0b439902963d56c43ac83c3f41dd0e',
},
},
]
def _extract_formats_and_subs(self, video_id, allow_none=True):
media_info = self._call_api(video_id, codename=video_id)
formats, subs = [], {}
for media_file in try_get(media_info, lambda x: x['MediaFiles'], list) or []:
for media in try_get(media_file, lambda x: x['Formats'], list) or []:
fmt_url = url_or_none(try_get(media, lambda x: x['Url']))
if not fmt_url:
continue
ext = determine_ext(fmt_url)
if ext == 'm3u8':
formats_, subs_ = self._extract_m3u8_formats_and_subtitles(
fmt_url, video_id, m3u8_id='hls', ext='mp4', fatal=False)
elif ext == 'mpd':
formats_, subs_ = self._extract_mpd_formats_and_subtitles(
fmt_url, video_id, mpd_id='dash', fatal=False)
else:
formats.append({
'url': fmt_url,
'format_id': str_or_none(media.get('Id')),
})
continue
formats.extend(formats_)
self._merge_subtitles(subs_, target=subs)
if formats or not allow_none:
self._sort_formats(formats)
return formats, subs
def _real_extract(self, url):
video_id = self._match_id(url)
formats, subs = self._extract_formats_and_subs(video_id)
if formats:
return {
'id': video_id,
'formats': formats,
'subtitles': subs,
'title': self._generic_title(url),
}
class ERTFlixIE(ERTFlixBaseIE):
IE_NAME = 'ertflix'
IE_DESC = 'ERTFLIX videos'
_VALID_URL = r'https?://www\.ertflix\.gr/(?:series|vod)/(?P<id>[a-z]{3}\.\d+)'
_TESTS = [{
'url': 'https://www.ertflix.gr/vod/vod.173258-aoratoi-ergates',
'md5': '6479d5e60fd7e520b07ba5411dcdd6e7',
'info_dict': {
'id': 'aoratoi-ergates',
'ext': 'mp4',
'title': 'md5:c1433d598fbba0211b0069021517f8b4',
'description': 'md5:01a64d113c31957eb7eb07719ab18ff4',
'thumbnail': r're:https?://.+\.jpg',
'episode_id': 'vod.173258',
'timestamp': 1639648800,
'upload_date': '20211216',
'duration': 3166,
'age_limit': 8,
},
}, {
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma',
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
},
'playlist_mincount': 64,
}, {
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma?season=1',
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
},
'playlist_count': 22,
}, {
'url': 'https://www.ertflix.gr/series/ser.3448-monogramma?season=1&season=2021%20-%202022',
'info_dict': {
'id': 'ser.3448',
'age_limit': 8,
'description': 'Η εκπομπή σαράντα ετών που σημάδεψε τον πολιτισμό μας.',
'title': 'Μονόγραμμα',
},
'playlist_mincount': 36,
}, {
'url': 'https://www.ertflix.gr/series/ser.164991-to-diktuo-1?season=1-9',
'info_dict': {
'id': 'ser.164991',
'age_limit': 8,
'description': 'Η πρώτη ελληνική εκπομπή με θεματολογία αποκλειστικά γύρω από το ίντερνετ.',
'title': 'Το δίκτυο',
},
'playlist_mincount': 9,
}]
def _extract_episode(self, episode):
codename = try_get(episode, lambda x: x['Codename'], compat_str)
title = episode.get('Title')
description = clean_html(dict_get(episode, ('ShortDescription', 'TinyDescription', )))
if not codename or not title or not episode.get('HasPlayableStream', True):
return
thumbnail = next((
url_or_none(thumb.get('Url'))
for thumb in variadic(dict_get(episode, ('Images', 'Image')) or {})
if thumb.get('IsMain')),
None)
return {
'_type': 'url_transparent',
'thumbnail': thumbnail,
'id': codename,
'episode_id': episode.get('Id'),
'title': title,
'alt_title': episode.get('Subtitle'),
'description': description,
'timestamp': parse_iso8601(episode.get('PublishDate')),
'duration': episode.get('DurationSeconds'),
'age_limit': self._parse_age_rating(episode),
'url': 'ertflix:%s' % (codename, ),
}
@staticmethod
def _parse_age_rating(info_dict):
return parse_age_limit(
info_dict.get('AgeRating')
or (info_dict.get('IsAdultContent') and 18)
or (info_dict.get('IsKidsContent') and 0))
def _extract_series(self, video_id, season_titles=None, season_numbers=None):
media_info = self._call_api(video_id, method='Tile/GetSeriesDetails', id=video_id)
series = try_get(media_info, lambda x: x['Series'], dict) or {}
series_info = {
'age_limit': self._parse_age_rating(series),
'title': series.get('Title'),
'description': dict_get(series, ('ShortDescription', 'TinyDescription', )),
}
if season_numbers:
season_titles = season_titles or []
for season in try_get(series, lambda x: x['Seasons'], list) or []:
if season.get('SeasonNumber') in season_numbers and season.get('Title'):
season_titles.append(season['Title'])
def gen_episode(m_info, season_titles):
for episode_group in try_get(m_info, lambda x: x['EpisodeGroups'], list) or []:
if season_titles and episode_group.get('Title') not in season_titles:
continue
episodes = try_get(episode_group, lambda x: x['Episodes'], list)
if not episodes:
continue
season_info = {
'season': episode_group.get('Title'),
'season_number': int_or_none(episode_group.get('SeasonNumber')),
}
try:
episodes = [(int(ep['EpisodeNumber']), ep) for ep in episodes]
episodes.sort()
except (KeyError, ValueError):
episodes = enumerate(episodes, 1)
for n, episode in episodes:
info = self._extract_episode(episode)
if info is None:
continue
info['episode_number'] = n
info.update(season_info)
yield info
return self.playlist_result(
gen_episode(media_info, season_titles), playlist_id=video_id, **series_info)
def _real_extract(self, url):
video_id = self._match_id(url)
if video_id.startswith('ser.'):
param_season = parse_qs(url).get('season', [None])
param_season = [
(have_number, int_or_none(v) if have_number else str_or_none(v))
for have_number, v in
[(int_or_none(ps) is not None, ps) for ps in param_season]
if v is not None
]
season_kwargs = {
k: [v for is_num, v in param_season if is_num is c] or None
for k, c in
[('season_titles', False), ('season_numbers', True)]
}
return self._extract_series(video_id, **season_kwargs)
return self._extract_episode(self._call_api_get_tiles(video_id))
class ERTWebtvEmbedIE(InfoExtractor):
IE_NAME = 'ertwebtv:embed'
IE_DESC = 'ert.gr webtv embedded videos'
_BASE_PLAYER_URL_RE = re.escape('//www.ert.gr/webtv/live-uni/vod/dt-uni-vod.php')
_VALID_URL = rf'https?:{_BASE_PLAYER_URL_RE}\?([^#]+&)?f=(?P<id>[^#&]+)'
_TESTS = [{
'url': 'https://www.ert.gr/webtv/live-uni/vod/dt-uni-vod.php?f=trailers/E2251_TO_DIKTYO_E09_16-01_1900.mp4&bgimg=/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg',
'md5': 'f9e9900c25c26f4ecfbddbb4b6305854',
'info_dict': {
'id': 'trailers/E2251_TO_DIKTYO_E09_16-01_1900.mp4',
'title': 'md5:914f06a73cd8b62fbcd6fb90c636e497',
'ext': 'mp4',
'thumbnail': 'https://program.ert.gr/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg'
},
}]
@classmethod
def _extract_urls(cls, webpage):
EMBED_URL_RE = rf'(?:https?:)?{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+'
EMBED_RE = rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{EMBED_URL_RE})(?P=_q1)'
for mobj in re.finditer(EMBED_RE, webpage):
url = unescapeHTML(mobj.group('url'))
if not cls.suitable(url):
continue
yield url
def _real_extract(self, url):
video_id = self._match_id(url)
formats, subs = self._extract_m3u8_formats_and_subtitles(
f'https://mediastream.ert.gr/vodedge/_definst_/mp4:dvrorigin/{video_id}/playlist.m3u8',
video_id, 'mp4')
self._sort_formats(formats)
thumbnail_id = parse_qs(url).get('bgimg', [None])[0]
if thumbnail_id and not thumbnail_id.startswith('http'):
thumbnail_id = f'https://program.ert.gr{thumbnail_id}'
return {
'id': video_id,
'title': f'VOD - {video_id}',
'thumbnail': thumbnail_id,
'formats': formats,
'subtitles': subs,
}
+20 -83
View File
@@ -14,10 +14,6 @@ from .abcotvs import (
ABCOTVSIE,
ABCOTVSClipsIE,
)
from .abematv import (
AbemaTVIE,
AbemaTVTitleIE,
)
from .academicearth import AcademicEarthCourseIE
from .acast import (
ACastIE,
@@ -68,10 +64,6 @@ from .anvato import AnvatoIE
from .aol import AolIE
from .allocine import AllocineIE
from .aliexpress import AliExpressLiveIE
from .alsace20tv import (
Alsace20TVIE,
Alsace20TVEmbedIE,
)
from .apa import APAIE
from .aparat import AparatIE
from .appleconnect import AppleConnectIE
@@ -95,7 +87,6 @@ from .arte import (
ArteTVIE,
ArteTVEmbedIE,
ArteTVPlaylistIE,
ArteTVCategoryIE,
)
from .arnes import ArnesIE
from .asiancrush import (
@@ -127,7 +118,7 @@ from .bandcamp import (
BandcampIE,
BandcampAlbumIE,
BandcampWeeklyIE,
BandcampUserIE,
BandcampMusicIE,
)
from .bannedvideo import BannedVideoIE
from .bbc import (
@@ -151,7 +142,6 @@ from .bfmtv import (
)
from .bibeltv import BibelTVIE
from .bigflix import BigflixIE
from .bigo import BigoIE
from .bild import BildIE
from .bilibili import (
BiliBiliIE,
@@ -204,7 +194,6 @@ from .byutv import BYUtvIE
from .c56 import C56IE
from .cableav import CableAVIE
from .callin import CallinIE
from .caltrans import CaltransIE
from .cam4 import CAM4IE
from .camdemy import (
CamdemyIE,
@@ -311,10 +300,6 @@ from .commonprotocols import (
from .condenast import CondeNastIE
from .contv import CONtvIE
from .corus import CorusIE
from .cpac import (
CPACIE,
CPACPlaylistIE,
)
from .cozytv import CozyTVIE
from .cracked import CrackedIE
from .crackle import CrackleIE
@@ -329,7 +314,7 @@ from .crunchyroll import (
CrunchyrollBetaIE,
CrunchyrollBetaShowIE,
)
from .cspan import CSpanIE, CSpanCongressIE
from .cspan import CSpanIE
from .ctsnews import CtsNewsIE
from .ctv import CTVIE
from .ctvnews import CTVNewsIE
@@ -357,7 +342,6 @@ from .daum import (
DaumPlaylistIE,
DaumUserIE,
)
from .daystar import DaystarClipIE
from .dbtv import DBTVIE
from .dctp import DctpTvIE
from .deezer import (
@@ -377,19 +361,9 @@ from .dplay import (
DPlayIE,
DiscoveryPlusIE,
HGTVDeIE,
GoDiscoveryIE,
TravelChannelIE,
CookingChannelIE,
HGTVUsaIE,
FoodNetworkIE,
InvestigationDiscoveryIE,
DestinationAmericaIE,
AmHistoryChannelIE,
ScienceChannelIE,
DIYNetworkIE,
DiscoveryLifeIE,
AnimalPlanetIE,
TLCIE,
DiscoveryPlusIndiaIE,
DiscoveryNetworksDeIE,
DiscoveryPlusItalyIE,
@@ -413,6 +387,11 @@ from .dumpert import DumpertIE
from .defense import DefenseGouvFrIE
from .digitalconcerthall import DigitalConcertHallIE
from .discovery import DiscoveryIE
from .discoverygo import (
DiscoveryGoIE,
DiscoveryGoPlaylistIE,
)
from .discoveryvr import DiscoveryVRIE
from .disney import DisneyIE
from .dispeak import DigitallySpeakingIE
from .doodstream import DoodStreamIE
@@ -454,11 +433,6 @@ from .eroprofile import (
EroProfileIE,
EroProfileAlbumIE,
)
from .ertgr import (
ERTFlixCodenameIE,
ERTFlixIE,
ERTWebtvEmbedIE,
)
from .escapist import EscapistIE
from .espn import (
ESPNIE,
@@ -488,7 +462,6 @@ from .faz import FazIE
from .fc2 import (
FC2IE,
FC2EmbedIE,
FC2LiveIE,
)
from .fczenit import FczenitIE
from .filmmodu import FilmmoduIE
@@ -498,6 +471,7 @@ from .filmon import (
)
from .filmweb import FilmwebIE
from .firsttv import FirstTVIE
from .fivemin import FiveMinIE
from .fivetv import FiveTVIE
from .flickr import FlickrIE
from .folketinget import FolketingetIE
@@ -520,7 +494,6 @@ from .foxnews import (
FoxNewsArticleIE,
)
from .foxsports import FoxSportsIE
from .fptplay import FptplayIE
from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE
from .francetv import (
@@ -530,6 +503,7 @@ from .francetv import (
)
from .freesound import FreesoundIE
from .freespeech import FreespeechIE
from .freshlive import FreshLiveIE
from .frontendmasters import (
FrontendMastersIE,
FrontendMastersLessonIE,
@@ -564,10 +538,7 @@ from .gazeta import GazetaIE
from .gdcvault import GDCVaultIE
from .gedidigital import GediDigitalIE
from .generic import GenericIE
from .gettr import (
GettrIE,
GettrStreamingIE,
)
from .gettr import GettrIE
from .gfycat import GfycatIE
from .giantbomb import GiantBombIE
from .giga import GigaIE
@@ -604,6 +575,7 @@ from .hidive import HiDiveIE
from .historicfilms import HistoricFilmsIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hitrecord import HitRecordIE
from .hornbunny import HornBunnyIE
from .hotnewhiphop import HotNewHipHopIE
from .hotstar import (
HotStarIE,
@@ -673,6 +645,7 @@ from .iqiyi import (
IqIE,
IqAlbumIE
)
from .ir90tv import Ir90TvIE
from .itv import (
ITVIE,
ITVBTCCIE,
@@ -694,6 +667,7 @@ from .joj import JojIE
from .jwplatform import JWPlatformIE
from .kakao import KakaoIE
from .kaltura import KalturaIE
from .kankan import KankanIE
from .karaoketv import KaraoketvIE
from .karrierevideos import KarriereVideosIE
from .keezmovies import KeezMoviesIE
@@ -849,7 +823,6 @@ from .microsoftvirtualacademy import (
from .mildom import (
MildomIE,
MildomVodIE,
MildomClipIE,
MildomUserVodIE,
)
from .minds import (
@@ -907,14 +880,7 @@ from .mtv import (
MTVItaliaProgrammaIE,
)
from .muenchentv import MuenchenTVIE
from .murrtube import MurrtubeIE, MurrtubeUserIE
from .musescore import MuseScoreIE
from .musicdex import (
MusicdexSongIE,
MusicdexAlbumIE,
MusicdexArtistIE,
MusicdexPlaylistIE,
)
from .mwave import MwaveIE, MwaveMeetGreetIE
from .mxplayer import (
MxplayerIE,
@@ -1002,7 +968,6 @@ from .nexx import (
NexxIE,
NexxEmbedIE,
)
from .nfb import NFBIE
from .nfhsnetwork import NFHSNetworkIE
from .nfl import (
NFLIE,
@@ -1011,9 +976,6 @@ from .nfl import (
from .nhk import (
NhkVodIE,
NhkVodProgramIE,
NhkForSchoolBangumiIE,
NhkForSchoolSubjectIE,
NhkForSchoolProgramListIE,
)
from .nhl import NHLIE
from .nick import (
@@ -1023,16 +985,14 @@ from .nick import (
NickNightIE,
NickRuIE,
)
from .niconico import (
NiconicoIE,
NiconicoPlaylistIE,
NiconicoUserIE,
NiconicoSeriesIE,
NiconicoHistoryIE,
NicovideoSearchDateIE,
NicovideoSearchIE,
NicovideoSearchURLIE,
NicovideoTagURLIE,
)
from .ninecninemedia import (
NineCNineMediaIE,
@@ -1164,7 +1124,6 @@ from .patreon import (
)
from .pbs import PBSIE
from .pearvideo import PearVideoIE
from .peekvids import PeekVidsIE, PlayVidsIE
from .peertube import (
PeerTubeIE,
PeerTubePlaylistIE,
@@ -1183,7 +1142,6 @@ from .periscope import (
from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .piapro import PiaproIE
from .picarto import (
PicartoIE,
PicartoVodIE,
@@ -1345,14 +1303,11 @@ from .reuters import ReutersIE
from .reverbnation import ReverbNationIE
from .rice import RICEIE
from .rmcdecouverte import RMCDecouverteIE
from .ro220 import Ro220IE
from .rockstargames import RockstarGamesIE
from .rokfin import (
RokfinIE,
RokfinStackIE,
RokfinChannelIE,
)
from .roosterteeth import RoosterTeethIE, RoosterTeethSeriesIE
from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rozhlas import RozhlasIE
from .rtbf import RTBFIE
from .rte import RteIE, RteRadioIE
@@ -1403,17 +1358,9 @@ from .megatvcom import (
MegaTVComIE,
MegaTVComEmbedIE,
)
from .ant1newsgr import (
Ant1NewsGrWatchIE,
Ant1NewsGrArticleIE,
Ant1NewsGrEmbedIE,
)
from .rutv import RUTVIE
from .ruutu import RuutuIE
from .ruv import (
RuvIE,
RuvSpilaIE
)
from .ruv import RuvIE
from .safari import (
SafariIE,
SafariApiIE,
@@ -1610,7 +1557,6 @@ from .tele13 import Tele13IE
from .telebruxelles import TeleBruxellesIE
from .telecinco import TelecincoIE
from .telegraaf import TelegraafIE
from .telegram import TelegramEmbedIE
from .telemb import TeleMBIE
from .telemundo import TelemundoIE
from .telequebec import (
@@ -1632,6 +1578,7 @@ from .theplatform import (
ThePlatformIE,
ThePlatformFeedIE,
)
from .thescene import TheSceneIE
from .thestar import TheStarIE
from .thesun import TheSunIE
from .theta import (
@@ -1653,7 +1600,6 @@ from .tiktok import (
TikTokSoundIE,
TikTokEffectIE,
TikTokTagIE,
TikTokVMIE,
DouyinIE,
)
from .tinypic import TinyPicIE
@@ -1851,10 +1797,6 @@ from .vice import (
from .vidbit import VidbitIE
from .viddler import ViddlerIE
from .videa import VideaIE
from .videocampus_sachsen import (
VideocampusSachsenIE,
VideocampusSachsenEmbedIE,
)
from .videodetective import VideoDetectiveIE
from .videofyme import VideofyMeIE
from .videomore import (
@@ -1887,10 +1829,7 @@ from .vimeo import (
VimeoWatchLaterIE,
VHXEmbedIE,
)
from .vimm import (
VimmIE,
VimmRecordingIE,
)
from .vimm import VimmIE
from .vimple import VimpleIE
from .vine import (
VineIE,
@@ -1941,6 +1880,7 @@ from .vrv import (
from .vshare import VShareIE
from .vtm import VTMIE
from .medialaan import MedialaanIE
from .vube import VubeIE
from .vuclip import VuClipIE
from .vupload import VuploadIE
from .vvvvid import (
@@ -2012,7 +1952,6 @@ from .ximalaya import (
XimalayaIE,
XimalayaAlbumIE
)
from .xinpianchang import XinpianchangIE
from .xminus import XMinusIE
from .xnxx import XNXXIE
from .xstream import XstreamIE
@@ -2037,7 +1976,6 @@ from .yandexmusic import (
)
from .yandexvideo import (
YandexVideoIE,
YandexVideoPreviewIE,
ZenYandexIE,
ZenYandexChannelIE,
)
@@ -2070,7 +2008,6 @@ from .youtube import (
YoutubeSearchDateIE,
YoutubeSearchIE,
YoutubeSearchURLIE,
YoutubeMusicSearchURLIE,
YoutubeSubscriptionsIE,
YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE,
+31 -171
View File
@@ -1,23 +1,18 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import hashlib
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_request,
compat_urlparse,
)
from ..utils import (
ExtractorError,
WebSocketsWrapper,
has_websockets,
js_to_json,
sanitized_Request,
std_headers,
traverse_obj,
update_url_query,
urlencode_postdata,
urljoin,
)
@@ -87,33 +82,41 @@ class FC2IE(InfoExtractor):
self._downloader.cookiejar.clear_session_cookies() # must clear
self._login()
title, thumbnail, description = None, None, None
title = 'FC2 video %s' % video_id
thumbnail = None
if webpage is not None:
title = self._html_search_regex(
(r'<h2\s+class="videoCnt_title">([^<]+?)</h2>',
r'\s+href="[^"]+"\s*title="([^"]+?)"\s*rel="nofollow">\s*<img',
# there's two matches in the webpage
r'\s+href="[^"]+"\s*title="([^"]+?)"\s*rel="nofollow">\s*\1'),
webpage,
'title', fatal=False)
title = self._og_search_title(webpage)
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage, default=None)
refer = url.replace('/content/', '/a/content/') if '/a/content/' not in url else url
vidplaylist = self._download_json(
'https://video.fc2.com/api/v3/videoplaylist/%s?sh=1&fs=0' % video_id, video_id,
note='Downloading info page')
vid_url = traverse_obj(vidplaylist, ('playlist', 'nq'))
if not vid_url:
raise ExtractorError('Unable to extract video URL')
vid_url = urljoin('https://video.fc2.com/', vid_url)
mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest()
info_url = (
'http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&'.
format(video_id, mimi, compat_urllib_request.quote(refer, safe=b'').replace('.', '%2E')))
info_webpage = self._download_webpage(
info_url, video_id, note='Downloading info page')
info = compat_urlparse.parse_qs(info_webpage)
if 'err_code' in info:
# most of the time we can still download wideo even if err_code is 403 or 602
self.report_warning(
'Error code was: %s... but still trying' % info['err_code'][0])
if 'filepath' not in info:
raise ExtractorError('Cannot download file. Are you logged in?')
video_url = info['filepath'][0] + '?mid=' + info['mid'][0]
title_info = info.get('title')
if title_info:
title = title_info[0]
return {
'id': video_id,
'title': title,
'url': vid_url,
'ext': 'mp4',
'protocol': 'm3u8_native',
'description': description,
'url': video_url,
'ext': 'flv',
'thumbnail': thumbnail,
}
@@ -154,146 +157,3 @@ class FC2EmbedIE(InfoExtractor):
'title': title,
'thumbnail': thumbnail,
}
class FC2LiveIE(InfoExtractor):
_VALID_URL = r'https?://live\.fc2\.com/(?P<id>\d+)'
IE_NAME = 'fc2:live'
_TESTS = [{
'url': 'https://live.fc2.com/57892267/',
'info_dict': {
'id': '57892267',
'title': 'どこまで・・・',
'uploader': 'あつあげ',
'uploader_id': '57892267',
'thumbnail': r're:https?://.+fc2.+',
},
'skip': 'livestream',
}]
def _real_extract(self, url):
if not has_websockets:
raise ExtractorError('websockets library is not available. Please install it.', expected=True)
video_id = self._match_id(url)
webpage = self._download_webpage('https://live.fc2.com/%s/' % video_id, video_id)
self._set_cookie('live.fc2.com', 'js-player_size', '1')
member_api = self._download_json(
'https://live.fc2.com/api/memberApi.php', video_id, data=urlencode_postdata({
'channel': '1',
'profile': '1',
'user': '1',
'streamid': video_id
}), note='Requesting member info')
control_server = self._download_json(
'https://live.fc2.com/api/getControlServer.php', video_id, note='Downloading ControlServer data',
data=urlencode_postdata({
'channel_id': video_id,
'mode': 'play',
'orz': '',
'channel_version': member_api['data']['channel_data']['version'],
'client_version': '2.1.0\n [1]',
'client_type': 'pc',
'client_app': 'browser_hls',
'ipv6': '',
}), headers={'X-Requested-With': 'XMLHttpRequest'})
self._set_cookie('live.fc2.com', 'l_ortkn', control_server['orz_raw'])
ws_url = update_url_query(control_server['url'], {'control_token': control_server['control_token']})
playlist_data = None
self.to_screen('%s: Fetching HLS playlist info via WebSocket' % video_id)
ws = WebSocketsWrapper(ws_url, {
'Cookie': str(self._get_cookies('https://live.fc2.com/'))[12:],
'Origin': 'https://live.fc2.com',
'Accept': '*/*',
'User-Agent': std_headers['User-Agent'],
})
ws.__enter__()
self.write_debug('[debug] Sending HLS server request')
while True:
recv = ws.recv()
if not recv:
continue
data = self._parse_json(recv, video_id, fatal=False)
if not data or not isinstance(data, dict):
continue
if data.get('name') == 'connect_complete':
break
ws.send(r'{"name":"get_hls_information","arguments":{},"id":1}')
while True:
recv = ws.recv()
if not recv:
continue
data = self._parse_json(recv, video_id, fatal=False)
if not data or not isinstance(data, dict):
continue
if data.get('name') == '_response_' and data.get('id') == 1:
self.write_debug('[debug] Goodbye.')
playlist_data = data
break
elif self._downloader.params.get('verbose', False):
if len(recv) > 100:
recv = recv[:100] + '...'
self.to_screen('[debug] Server said: %s' % recv)
if not playlist_data:
raise ExtractorError('Unable to fetch HLS playlist info via WebSocket')
formats = []
for name, playlists in playlist_data['arguments'].items():
if not isinstance(playlists, list):
continue
for pl in playlists:
if pl.get('status') == 0 and 'master_playlist' in pl.get('url'):
formats.extend(self._extract_m3u8_formats(
pl['url'], video_id, ext='mp4', m3u8_id=name, live=True,
headers={
'Origin': 'https://live.fc2.com',
'Referer': url,
}))
self._sort_formats(formats)
for fmt in formats:
fmt.update({
'protocol': 'fc2_live',
'ws': ws,
})
title = self._html_search_meta(('og:title', 'twitter:title'), webpage, 'live title', fatal=False)
if not title:
title = self._html_extract_title(webpage, 'html title', fatal=False)
if title:
# remove service name in <title>
title = re.sub(r'\s+-\s+.+$', '', title)
uploader = None
if title:
match = self._search_regex(r'^(.+?)\s*\[(.+?)\]$', title, 'title and uploader', default=None, group=(1, 2))
if match and all(match):
title, uploader = match
live_info_view = self._search_regex(r'(?s)liveInfoView\s*:\s*({.+?}),\s*premiumStateView', webpage, 'user info', fatal=False) or None
if live_info_view:
# remove jQuery code from object literal
live_info_view = re.sub(r'\$\(.+?\)[^,]+,', '"",', live_info_view)
live_info_view = self._parse_json(js_to_json(live_info_view), video_id)
return {
'id': video_id,
'title': title or traverse_obj(live_info_view, 'title'),
'description': self._html_search_meta(
('og:description', 'twitter:description'),
webpage, 'live description', fatal=False) or traverse_obj(live_info_view, 'info'),
'formats': formats,
'uploader': uploader or traverse_obj(live_info_view, 'name'),
'uploader_id': video_id,
'thumbnail': traverse_obj(live_info_view, 'thumb'),
'is_live': True,
}
+54
View File
@@ -0,0 +1,54 @@
from __future__ import unicode_literals
from .common import InfoExtractor
class FiveMinIE(InfoExtractor):
IE_NAME = '5min'
_VALID_URL = r'(?:5min:|https?://(?:[^/]*?5min\.com/|delivery\.vidible\.tv/aol)(?:(?:Scripts/PlayerSeed\.js|playerseed/?)?\?.*?playList=)?)(?P<id>\d+)'
_TESTS = [
{
# From http://www.engadget.com/2013/11/15/ipad-mini-retina-display-review/
'url': 'http://pshared.5min.com/Scripts/PlayerSeed.js?sid=281&width=560&height=345&playList=518013791',
'md5': '4f7b0b79bf1a470e5004f7112385941d',
'info_dict': {
'id': '518013791',
'ext': 'mp4',
'title': 'iPad Mini with Retina Display Review',
'description': 'iPad mini with Retina Display review',
'duration': 177,
'uploader': 'engadget',
'upload_date': '20131115',
'timestamp': 1384515288,
},
'params': {
# m3u8 download
'skip_download': True,
}
},
{
# From http://on.aol.com/video/how-to-make-a-next-level-fruit-salad-518086247
'url': '5min:518086247',
'md5': 'e539a9dd682c288ef5a498898009f69e',
'info_dict': {
'id': '518086247',
'ext': 'mp4',
'title': 'How to Make a Next-Level Fruit Salad',
'duration': 184,
},
'skip': 'no longer available',
},
{
'url': 'http://embed.5min.com/518726732/',
'only_matching': True,
},
{
'url': 'http://delivery.vidible.tv/aol?playList=518013791',
'only_matching': True,
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
return self.url_result('aol-video:%s' % video_id)
-102
View File
@@ -1,102 +0,0 @@
# coding: utf-8
from __future__ import unicode_literals
import hashlib
import time
import urllib.parse
from .common import InfoExtractor
from ..utils import (
join_nonempty,
)
class FptplayIE(InfoExtractor):
_VALID_URL = r'https?://fptplay\.vn/(?P<type>xem-video)/[^/]+\-(?P<id>\w+)(?:/tap-(?P<episode>[^/]+)?/?(?:[?#]|$)|)'
_GEO_COUNTRIES = ['VN']
IE_NAME = 'fptplay'
IE_DESC = 'fptplay.vn'
_TESTS = [{
'url': 'https://fptplay.vn/xem-video/nhan-duyen-dai-nhan-xin-dung-buoc-621a123016f369ebbde55945',
'md5': 'ca0ee9bc63446c0c3e9a90186f7d6b33',
'info_dict': {
'id': '621a123016f369ebbde55945',
'ext': 'mp4',
'title': 'Nhân Duyên Đại Nhân Xin Dừng Bước - Ms. Cupid In Love',
'description': 'md5:23cf7d1ce0ade8e21e76ae482e6a8c6c',
},
}, {
'url': 'https://fptplay.vn/xem-video/ma-toi-la-dai-gia-61f3aa8a6b3b1d2e73c60eb5/tap-3',
'md5': 'b35be968c909b3e4e1e20ca45dd261b1',
'info_dict': {
'id': '61f3aa8a6b3b1d2e73c60eb5',
'ext': 'mp4',
'title': 'Má Tôi Là Đại Gia - 3',
'description': 'md5:ff8ba62fb6e98ef8875c42edff641d1c',
},
}, {
'url': 'https://fptplay.vn/xem-video/nha-co-chuyen-hi-alls-well-ends-well-1997-6218995f6af792ee370459f0',
'only_matching': True,
}]
def _real_extract(self, url):
type_url, video_id, episode = self._match_valid_url(url).group('type', 'id', 'episode')
webpage = self._download_webpage(url, video_id=video_id, fatal=False)
info = self._download_json(self.get_api_with_st_token(video_id, episode or 0), video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(info['data']['url'], video_id, 'mp4')
self._sort_formats(formats)
return {
'id': video_id,
'title': join_nonempty(
self._html_search_meta(('og:title', 'twitter:title'), webpage), episode, delim=' - '),
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
'formats': formats,
'subtitles': subtitles,
}
def get_api_with_st_token(self, video_id, episode):
path = f'/api/v6.2_w/stream/vod/{video_id}/{episode}/auto_vip'
timestamp = int(time.time()) + 10800
t = hashlib.md5(f'WEBv6Dkdsad90dasdjlALDDDS{timestamp}{path}'.encode()).hexdigest().upper()
r = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/'
n = [int(f'0x{t[2 * o: 2 * o + 2]}', 16) for o in range(len(t) // 2)]
def convert(e):
t = ''
n = 0
i = [0, 0, 0]
a = [0, 0, 0, 0]
s = len(e)
c = 0
for z in range(s, 0, -1):
if n <= 3:
i[n] = e[c]
n += 1
c += 1
if 3 == n:
a[0] = (252 & i[0]) >> 2
a[1] = ((3 & i[0]) << 4) + ((240 & i[1]) >> 4)
a[2] = ((15 & i[1]) << 2) + ((192 & i[2]) >> 6)
a[3] = (63 & i[2])
for v in range(4):
t += r[a[v]]
n = 0
if n:
for o in range(n, 3):
i[o] = 0
for o in range(n + 1):
a[0] = (252 & i[0]) >> 2
a[1] = ((3 & i[0]) << 4) + ((240 & i[1]) >> 4)
a[2] = ((15 & i[1]) << 2) + ((192 & i[2]) >> 6)
a[3] = (63 & i[2])
t += r[a[o]]
n += 1
while n < 3:
t += ''
n += 1
return t
st_token = convert(n).replace('+', '-').replace('/', '_').replace('=', '')
return f'https://api.fptplay.net{path}?{urllib.parse.urlencode({"st": st_token, "e": timestamp})}'
+80
View File
@@ -0,0 +1,80 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
int_or_none,
try_get,
unified_timestamp,
)
class FreshLiveIE(InfoExtractor):
_VALID_URL = r'https?://freshlive\.tv/[^/]+/(?P<id>\d+)'
_TEST = {
'url': 'https://freshlive.tv/satotv/74712',
'md5': '9f0cf5516979c4454ce982df3d97f352',
'info_dict': {
'id': '74712',
'ext': 'mp4',
'title': 'テスト',
'description': 'テスト',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1511,
'timestamp': 1483619655,
'upload_date': '20170105',
'uploader': 'サトTV',
'uploader_id': 'satotv',
'view_count': int,
'comment_count': int,
'is_live': False,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
options = self._parse_json(
self._search_regex(
r'window\.__CONTEXT__\s*=\s*({.+?});\s*</script>',
webpage, 'initial context'),
video_id)
info = options['context']['dispatcher']['stores']['ProgramStore']['programs'][video_id]
title = info['title']
if info.get('status') == 'upcoming':
raise ExtractorError('Stream %s is upcoming' % video_id, expected=True)
stream_url = info.get('liveStreamUrl') or info['archiveStreamUrl']
is_live = info.get('liveStreamUrl') is not None
formats = self._extract_m3u8_formats(
stream_url, video_id, 'mp4',
'm3u8_native', m3u8_id='hls')
return {
'id': video_id,
'formats': formats,
'title': title,
'description': info.get('description'),
'thumbnail': info.get('thumbnailUrl'),
'duration': int_or_none(info.get('airTime')),
'timestamp': unified_timestamp(info.get('createdAt')),
'uploader': try_get(
info, lambda x: x['channel']['title'], compat_str),
'uploader_id': try_get(
info, lambda x: x['channel']['code'], compat_str),
'uploader_url': try_get(
info, lambda x: x['channel']['permalink'], compat_str),
'view_count': int_or_none(info.get('viewCount')),
'comment_count': int_or_none(info.get('commentCount')),
'tags': info.get('tags', []),
'is_live': is_live,
}
+2 -2
View File
@@ -252,9 +252,9 @@ class FrontendMastersCourseIE(FrontendMastersPageBaseIE):
entries = []
for lesson in lessons:
lesson_name = lesson.get('slug')
lesson_id = lesson.get('hash') or lesson.get('statsId')
if not lesson_id or not lesson_name:
if not lesson_name:
continue
lesson_id = lesson.get('hash') or lesson.get('statsId')
entries.append(self._extract_lesson(chapters, lesson_id, lesson))
title = course.get('title')
+22 -47
View File
@@ -1,12 +1,12 @@
# coding: utf-8
from __future__ import unicode_literals
from ..utils import HEADRequest
from .common import InfoExtractor
class FujiTVFODPlus7IE(InfoExtractor):
_VALID_URL = r'https?://fod\.fujitv\.co\.jp/title/(?P<sid>[0-9a-z]{4})/(?P<id>[0-9a-z]+)'
_BASE_URL = 'https://i.fod.fujitv.co.jp/'
_VALID_URL = r'https?://fod\.fujitv\.co\.jp/title/[0-9a-z]{4}/(?P<id>[0-9a-z]+)'
_BASE_URL = 'http://i.fod.fujitv.co.jp/'
_BITRATE_MAP = {
300: (320, 180),
800: (640, 360),
@@ -16,58 +16,33 @@ class FujiTVFODPlus7IE(InfoExtractor):
}
_TESTS = [{
'url': 'https://fod.fujitv.co.jp/title/5d40/5d40110076',
'url': 'https://fod.fujitv.co.jp/title/5d40/5d40810075',
'info_dict': {
'id': '5d40110076',
'id': '5d40810075',
'title': '5d40810075',
'ext': 'mp4',
'title': '#1318 『まる子、まぼろしの洋館を見る』の巻',
'series': 'ちびまる子ちゃん',
'series_id': '5d40',
'description': 'md5:b3f51dbfdda162ac4f789e0ff4d65750',
'thumbnail': 'https://i.fod.fujitv.co.jp/img/program/5d40/episode/5d40110076_a.jpg',
'format_id': '4000',
'thumbnail': 'http://i.fod.fujitv.co.jp/pc/image/wbtn/wbtn_5d40810075.jpg'
},
}, {
'url': 'https://fod.fujitv.co.jp/title/5d40/5d40810083',
'info_dict': {
'id': '5d40810083',
'ext': 'mp4',
'title': '#1324 『まる子とオニの子』の巻/『結成!2月をムダにしない会』の巻',
'description': 'md5:3972d900b896adc8ab1849e310507efa',
'series': 'ちびまる子ちゃん',
'series_id': '5d40',
'thumbnail': 'https://i.fod.fujitv.co.jp/img/program/5d40/episode/5d40810083_a.jpg'},
'skip': 'Video available only in one week'
'skip': 'Expires after a week'
}]
def _real_extract(self, url):
series_id, video_id = self._match_valid_url(url).groups()
self._request_webpage(HEADRequest(url), video_id)
json_info = {}
token = self._get_cookies(url).get('CT')
if token:
json_info = self._download_json('https://fod-sp.fujitv.co.jp/apps/api/episode/detail/?ep_id=%s&is_premium=false' % video_id, video_id, headers={'x-authorization': f'Bearer {token.value}'}, fatal=False)
else:
self.report_warning(f'The token cookie is needed to extract video metadata. {self._LOGIN_HINTS["cookies"]}')
formats, subtitles = [], {}
src_json = self._download_json(f'{self._BASE_URL}abrjson_v2/tv_android/{video_id}', video_id)
for src in src_json['video_selector']:
if not src.get('url'):
continue
fmt, subs = self._extract_m3u8_formats_and_subtitles(src['url'], video_id, 'mp4')
for f in fmt:
f.update(dict(zip(('height', 'width'),
self._BITRATE_MAP.get(f.get('tbr'), ()))))
formats.extend(fmt)
subtitles = self._merge_subtitles(subtitles, subs)
self._sort_formats(formats, ['tbr'])
video_id = self._match_id(url)
formats = self._extract_m3u8_formats(
self._BASE_URL + 'abr/tv_android/%s.m3u8' % video_id, video_id, 'mp4')
for f in formats:
wh = self._BITRATE_MAP.get(f.get('tbr'))
if wh:
f.update({
'width': wh[0],
'height': wh[1],
})
self._sort_formats(formats)
return {
'id': video_id,
'title': json_info.get('ep_title'),
'series': json_info.get('lu_title'),
'series_id': series_id,
'description': json_info.get('ep_description'),
'title': video_id,
'formats': formats,
'subtitles': subtitles,
'thumbnail': f'{self._BASE_URL}img/program/{series_id}/episode/{video_id}_a.jpg',
'thumbnail': self._BASE_URL + 'pc/image/wbtn/wbtn_%s.jpg' % video_id,
}
+30 -53
View File
@@ -103,7 +103,6 @@ from .videopress import VideoPressIE
from .rutube import RutubeIE
from .glomex import GlomexEmbedIE
from .megatvcom import MegaTVComEmbedIE
from .ant1newsgr import Ant1NewsGrEmbedIE
from .limelight import LimelightBaseIE
from .anvato import AnvatoIE
from .washingtonpost import WashingtonPostIE
@@ -141,7 +140,6 @@ from .medialaan import MedialaanIE
from .simplecast import SimplecastIE
from .wimtv import WimTVIE
from .tvopengr import TVOpenGrEmbedIE
from .ertgr import ERTWebtvEmbedIE
from .tvp import TVPEmbedIE
from .blogger import BloggerIE
from .mainstreaming import MainStreamingIE
@@ -214,7 +212,7 @@ class GenericIE(InfoExtractor):
{
'url': 'http://phihag.de/2014/youtube-dl/rss2.xml',
'info_dict': {
'id': 'https://phihag.de/2014/youtube-dl/rss2.xml',
'id': 'http://phihag.de/2014/youtube-dl/rss2.xml',
'title': 'Zero Punctuation',
'description': 're:.*groundbreaking video review series.*'
},
@@ -259,9 +257,6 @@ class GenericIE(InfoExtractor):
'episode_number': 1,
'season_number': 1,
'age_limit': 0,
'season': 'Season 1',
'direct': True,
'episode': 'Episode 1',
},
}],
'params': {
@@ -278,16 +273,6 @@ class GenericIE(InfoExtractor):
},
'playlist_mincount': 100,
},
# RSS feed with guid
{
'url': 'https://www.omnycontent.com/d/playlist/a7b4f8fe-59d9-4afc-a79a-a90101378abf/bf2c1d80-3656-4449-9d00-a903004e8f84/efbff746-e7c1-463a-9d80-a903004e8f8f/podcast.rss',
'info_dict': {
'id': 'https://www.omnycontent.com/d/playlist/a7b4f8fe-59d9-4afc-a79a-a90101378abf/bf2c1d80-3656-4449-9d00-a903004e8f84/efbff746-e7c1-463a-9d80-a903004e8f8f/podcast.rss',
'description': 'md5:be809a44b63b0c56fb485caf68685520',
'title': 'The Little Red Podcast',
},
'playlist_mincount': 76,
},
# SMIL from http://videolectures.net/promogram_igor_mekjavic_eng
{
'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml',
@@ -1470,6 +1455,24 @@ class GenericIE(InfoExtractor):
'duration': 45.115,
},
},
# 5min embed
{
'url': 'http://techcrunch.com/video/facebook-creates-on-this-day-crunch-report/518726732/',
'md5': '4c6f127a30736b59b3e2c19234ee2bf7',
'info_dict': {
'id': '518726732',
'ext': 'mp4',
'title': 'Facebook Creates "On This Day" | Crunch Report',
'description': 'Amazon updates Fire TV line, Tesla\'s Model X spotted in the wild',
'timestamp': 1427237531,
'uploader': 'Crunch Report',
'upload_date': '20150324',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
# Crooks and Liars embed
{
'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists',
@@ -1920,15 +1923,6 @@ class GenericIE(InfoExtractor):
},
}]
},
{
'url': 'https://www.ertnews.gr/video/manolis-goyalles-o-anthropos-piso-apo-ti-diadiktyaki-vasilopita/',
'info_dict': {
'id': '2022/tv/news-themata-ianouarios/20220114-apotis6-gouales-pita.mp4',
'ext': 'mp4',
'title': 'md5:df64f5b61c06d0e9556c0cdd5cf14464',
'thumbnail': 'https://www.ert.gr/themata/photos/2021/20220114-apotis6-gouales-pita.jpg',
},
},
{
# ThePlatform embedded with whitespaces in URLs
'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm',
@@ -2532,9 +2526,6 @@ class GenericIE(InfoExtractor):
if not next_url:
continue
if it.find('guid').text is not None:
next_url = smuggle_url(next_url, {'force_videoid': it.find('guid').text})
def itunes(key):
return xpath_text(
it, xpath_with_ns('./itunes:%s' % key, NS_MAP),
@@ -3336,6 +3327,12 @@ class GenericIE(InfoExtractor):
if mobj is not None:
return self.url_result(mobj.group('url'))
# Look for 5min embeds
mobj = re.search(
r'<meta[^>]+property="og:video"[^>]+content="https?://embed\.5min\.com/(?P<id>[0-9]+)/?', webpage)
if mobj is not None:
return self.url_result('5min:%s' % mobj.group('id'), 'FiveMin')
# Look for Crooks and Liars embeds
mobj = re.search(
r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1', webpage)
@@ -3545,12 +3542,6 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
megatvcom_urls, video_id, video_title, ie=MegaTVComEmbedIE.ie_key())
# Look for ant1news.gr embeds
ant1newsgr_urls = list(Ant1NewsGrEmbedIE._extract_urls(webpage))
if ant1newsgr_urls:
return self.playlist_from_matches(
ant1newsgr_urls, video_id, video_title, ie=Ant1NewsGrEmbedIE.ie_key())
# Look for WashingtonPost embeds
wapo_urls = WashingtonPostIE._extract_urls(webpage)
if wapo_urls:
@@ -3702,13 +3693,6 @@ class GenericIE(InfoExtractor):
if tvopengr_urls:
return self.playlist_from_matches(tvopengr_urls, video_id, video_title, ie=TVOpenGrEmbedIE.ie_key())
# Look for ert.gr webtv embeds
ertwebtv_urls = list(ERTWebtvEmbedIE._extract_urls(webpage))
if len(ertwebtv_urls) == 1:
return self.url_result(self._proto_relative_url(ertwebtv_urls[0]), video_title=video_title, url_transparent=True)
elif ertwebtv_urls:
return self.playlist_from_matches(ertwebtv_urls, video_id, video_title, ie=ERTWebtvEmbedIE.ie_key())
tvp_urls = TVPEmbedIE._extract_urls(webpage)
if tvp_urls:
return self.playlist_from_matches(tvp_urls, video_id, video_title, ie=TVPEmbedIE.ie_key())
@@ -3814,16 +3798,13 @@ class GenericIE(InfoExtractor):
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(webpage, video_id, default={})
if json_ld.get('url') not in (url, None):
if json_ld.get('url'):
self.report_detected('JSON LD')
if determine_ext(json_ld['url']) == 'm3u8':
if determine_ext(json_ld.get('url')) == 'm3u8':
json_ld['formats'], json_ld['subtitles'] = self._extract_m3u8_formats_and_subtitles(
json_ld['url'], video_id, 'mp4')
json_ld.pop('url')
self._sort_formats(json_ld['formats'])
else:
json_ld['_type'] = 'url_transparent'
json_ld['url'] = smuggle_url(json_ld['url'], {'force_videoid': video_id, 'to_generic': True})
return merge_dicts(json_ld, info_dict)
def check_video(vurl):
@@ -3998,16 +3979,12 @@ class GenericIE(InfoExtractor):
# here's a fun little line of code for you:
video_id = os.path.splitext(video_id)[0]
headers = {
'referer': full_response.geturl()
}
entry_info_dict = {
'id': video_id,
'uploader': video_uploader,
'title': video_title,
'age_limit': age_limit,
'http_headers': headers,
}
if RtmpIE.suitable(video_url):
@@ -4025,11 +4002,11 @@ class GenericIE(InfoExtractor):
elif ext == 'xspf':
return self.playlist_result(self._extract_xspf_playlist(video_url, video_id), video_id)
elif ext == 'm3u8':
entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4', headers=headers)
entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_m3u8_formats_and_subtitles(video_url, video_id, ext='mp4')
elif ext == 'mpd':
entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id, headers=headers)
entry_info_dict['formats'], entry_info_dict['subtitles'] = self._extract_mpd_formats_and_subtitles(video_url, video_id)
elif ext == 'f4m':
entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id, headers=headers)
entry_info_dict['formats'] = self._extract_f4m_formats(video_url, video_id)
elif re.search(r'(?i)\.(?:ism|smil)/manifest', video_url) and video_url != url:
# Just matching .ism/manifest is not enough to be reliably sure
# whether it's actually an ISM manifest or some other streaming
+28 -131
View File
@@ -3,30 +3,22 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
bool_or_none,
ExtractorError,
dict_get,
float_or_none,
int_or_none,
remove_end,
str_or_none,
traverse_obj,
try_get,
url_or_none,
urljoin,
)
class GettrBaseIE(InfoExtractor):
_BASE_REGEX = r'https?://(www\.)?gettr\.com/'
class GettrIE(InfoExtractor):
_VALID_URL = r'https?://(www\.)?gettr\.com/post/(?P<id>[a-z0-9]+)'
_MEDIA_BASE_URL = 'https://media.gettr.com/'
def _call_api(self, path, video_id, *args, **kwargs):
return self._download_json(urljoin('https://api.gettr.com/u/', path), video_id, *args, **kwargs)['result']
class GettrIE(GettrBaseIE):
_VALID_URL = GettrBaseIE._BASE_REGEX + r'post/(?P<id>[a-z0-9]+)'
_TESTS = [{
'url': 'https://www.gettr.com/post/pcf6uv838f',
'info_dict': {
@@ -36,11 +28,9 @@ class GettrIE(GettrBaseIE):
'ext': 'mp4',
'uploader': 'EpochTV',
'uploader_id': 'epochtv',
'upload_date': '20210927',
'thumbnail': r're:^https?://.+/out\.jpg',
'timestamp': 1632782451.058,
'timestamp': 1632782451058,
'duration': 58.5585,
'tags': ['hornofafrica', 'explorations'],
}
}, {
'url': 'https://gettr.com/post/p4iahp',
@@ -51,69 +41,43 @@ class GettrIE(GettrBaseIE):
'ext': 'mp4',
'uploader': 'Neues Forum Freiheit',
'uploader_id': 'nf_freiheit',
'upload_date': '20210718',
'thumbnail': r're:^https?://.+/out\.jpg',
'timestamp': 1626594455.017,
'timestamp': 1626594455017,
'duration': 23,
'tags': 'count:12',
}
}, {
# quote post
'url': 'https://gettr.com/post/pxn5b743a9',
'only_matching': True,
}, {
# quote with video
'url': 'https://gettr.com/post/pxtiiz5ca2',
'only_matching': True,
}, {
# streaming embed
'url': 'https://gettr.com/post/pxlu8p3b13',
'only_matching': True,
}, {
# youtube embed
'url': 'https://gettr.com/post/pv6wp9e24c',
'only_matching': True,
'add_ie': ['Youtube'],
}]
def _real_extract(self, url):
post_id = self._match_id(url)
webpage = self._download_webpage(url, post_id)
api_data = self._call_api('post/%s?incl="poststats|userinfo"' % post_id, post_id)
post_data = api_data.get('data')
user_data = try_get(api_data, lambda x: x['aux']['uinf'][post_data['uid']], dict) or {}
api_data = self._download_json(
'https://api.gettr.com/u/post/%s?incl="poststats|userinfo"' % post_id, post_id)
vid = post_data.get('vid')
ovid = post_data.get('ovid')
post_data = try_get(api_data, lambda x: x['result']['data'])
user_data = try_get(api_data, lambda x: x['result']['aux']['uinf'][post_data['uid']]) or {}
if post_data.get('p_type') == 'stream':
return self.url_result(f'https://gettr.com/streaming/{post_id}', ie='GettrStreaming', video_id=post_id)
if not (ovid or vid):
embed_url = url_or_none(post_data.get('prevsrc'))
shared_post_id = traverse_obj(api_data, ('aux', 'shrdpst', '_id'), ('data', 'rpstIds', 0), expected_type=str)
if embed_url:
return self.url_result(embed_url)
elif shared_post_id:
return self.url_result(f'https://gettr.com/post/{shared_post_id}', ie='Gettr', video_id=shared_post_id)
else:
raise ExtractorError('There\'s no video in this post.')
if post_data.get('nfound'):
raise ExtractorError(post_data.get('txt'), expected=True)
title = description = str_or_none(
post_data.get('txt') or self._og_search_description(webpage))
uploader = str_or_none(
user_data.get('nickname')
or self._search_regex(r'^(.+?) on GETTR', self._og_search_title(webpage, default=''), 'uploader', fatal=False))
or remove_end(self._og_search_title(webpage), ' on GETTR'))
if uploader:
title = '%s - %s' % (uploader, title)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
if not dict_get(post_data, ['vid', 'ovid']):
raise ExtractorError('There\'s no video in this post.')
vid = post_data.get('vid')
ovid = post_data.get('ovid')
formats = self._extract_m3u8_formats(
urljoin(self._MEDIA_BASE_URL, vid), post_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) if vid else ([], {})
entry_protocol='m3u8_native', m3u8_id='hls') if vid else []
if ovid:
formats.append({
@@ -122,6 +86,8 @@ class GettrIE(GettrBaseIE):
'ext': 'mp4',
'width': int_or_none(post_data.get('vid_wid')),
'height': int_or_none(post_data.get('vid_hgt')),
'source_preference': 1,
'quality': 1,
})
self._sort_formats(formats)
@@ -130,84 +96,15 @@ class GettrIE(GettrBaseIE):
'id': post_id,
'title': title,
'description': description,
'formats': formats,
'subtitles': subtitles,
'uploader': uploader,
'thumbnail': url_or_none(
urljoin(self._MEDIA_BASE_URL, post_data.get('main'))
or self._og_search_thumbnail(webpage)),
'timestamp': int_or_none(post_data.get('cdate')),
'uploader_id': str_or_none(
dict_get(user_data, ['_id', 'username'])
or post_data.get('uid')),
'thumbnail': url_or_none(
urljoin(self._MEDIA_BASE_URL, post_data.get('main'))
or self._html_search_meta(['og:image', 'image'], webpage, 'thumbnail', fatal=False)),
'timestamp': float_or_none(dict_get(post_data, ['cdate', 'udate']), scale=1000),
'uploader': uploader,
'formats': formats,
'duration': float_or_none(post_data.get('vid_dur')),
'tags': post_data.get('htgs'),
}
class GettrStreamingIE(GettrBaseIE):
_VALID_URL = GettrBaseIE._BASE_REGEX + r'streaming/(?P<id>[a-z0-9]+)'
_TESTS = [{
'url': 'https://gettr.com/streaming/psoiulc122',
'info_dict': {
'id': 'psoiulc122',
'ext': 'mp4',
'description': 'md5:56bca4b8f48f1743d9fd03d49c723017',
'view_count': int,
'uploader': 'Corona Investigative Committee',
'uploader_id': 'coronacommittee',
'duration': 5180.184,
'thumbnail': r're:^https?://.+',
'title': 'Day 1: Opening Session of the Grand Jury Proceeding',
'timestamp': 1644080997.164,
'upload_date': '20220205',
}
}, {
'url': 'https://gettr.com/streaming/psfmeefcc1',
'info_dict': {
'id': 'psfmeefcc1',
'ext': 'mp4',
'title': 'Session 90: "The Virus Of Power"',
'view_count': int,
'uploader_id': 'coronacommittee',
'description': 'md5:98986acdf656aa836bf36f9c9704c65b',
'uploader': 'Corona Investigative Committee',
'thumbnail': r're:^https?://.+',
'duration': 21872.507,
'timestamp': 1643976662.858,
'upload_date': '20220204',
}
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_info = self._call_api('live/join/%s' % video_id, video_id, data={})
live_info = video_info['broadcast']
live_url = url_or_none(live_info.get('url'))
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
live_url, video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) if live_url else ([], {})
thumbnails = [{
'url': urljoin(self._MEDIA_BASE_URL, thumbnail),
} for thumbnail in try_get(video_info, lambda x: x['postData']['imgs'], list) or []]
self._sort_formats(formats)
return {
'id': video_id,
'title': try_get(video_info, lambda x: x['postData']['ttl'], str),
'description': try_get(video_info, lambda x: x['postData']['dsc'], str),
'formats': formats,
'subtitles': subtitles,
'thumbnails': thumbnails,
'uploader': try_get(video_info, lambda x: x['liveHostInfo']['nickname'], str),
'uploader_id': try_get(video_info, lambda x: x['liveHostInfo']['_id'], str),
'view_count': int_or_none(live_info.get('viewsCount')),
'timestamp': float_or_none(live_info.get('startAt'), scale=1000),
'duration': float_or_none(live_info.get('duration'), scale=1000),
'is_live': bool_or_none(live_info.get('isLive')),
}
+7 -36
View File
@@ -12,7 +12,6 @@ from ..compat import (
compat_str,
)
from ..utils import (
HEADRequest,
ExtractorError,
float_or_none,
orderedSet,
@@ -68,28 +67,11 @@ class GloboIE(InfoExtractor):
}, {
'url': 'globo:3607726',
'only_matching': True,
}, {
'url': 'https://globoplay.globo.com/v/10248083/',
'info_dict': {
'id': '10248083',
'ext': 'mp4',
'title': 'Melhores momentos: Equador 1 x 1 Brasil pelas Eliminatórias da Copa do Mundo 2022',
'duration': 530.964,
'uploader': 'SporTV',
'uploader_id': '698',
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
self._request_webpage(
HEADRequest('https://globo-ab.globo.com/v2/selected-alternatives?experiments=player-isolated-experiment-02&skipImpressions=true'),
video_id, 'Getting cookies')
video = self._download_json(
'http://api.globovideos.com/videos/%s/playlist' % video_id,
video_id)['videos'][0]
@@ -100,7 +82,7 @@ class GloboIE(InfoExtractor):
formats = []
security = self._download_json(
'https://playback.video.globo.com/v2/video-session', video_id, 'Downloading security hash for %s' % video_id,
'https://playback.video.globo.com/v1/video-session', video_id, 'Downloading security hash for %s' % video_id,
headers={'content-type': 'application/json'}, data=json.dumps({
"player_type": "desktop",
"video_id": video_id,
@@ -110,9 +92,7 @@ class GloboIE(InfoExtractor):
"tz": "-3.0:00"
}).encode())
self._request_webpage(HEADRequest(security['sources'][0]['url_template']), video_id, 'Getting locksession cookie')
security_hash = security['sources'][0]['token']
security_hash = security['source']['token']
if not security_hash:
message = security.get('message')
if message:
@@ -135,15 +115,15 @@ class GloboIE(InfoExtractor):
md5_data = (received_md5 + padded_sign_time + '0xAC10FD').encode()
signed_md5 = base64.urlsafe_b64encode(hashlib.md5(md5_data).digest()).decode().strip('=')
signed_hash = hash_prefix + padded_sign_time + signed_md5
source = security['sources'][0]['url_parts']
source = security['source']['url_parts']
resource_url = source['scheme'] + '://' + source['domain'] + source['path']
signed_url = '%s?h=%s&k=html5&a=%s' % (resource_url, signed_hash, 'F' if video.get('subscriber_only') else 'A')
fmts, subtitles = self._extract_m3u8_formats_and_subtitles(
signed_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
formats.extend(fmts)
formats.extend(self._extract_m3u8_formats(
signed_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
self._sort_formats(formats)
subtitles = {}
for resource in video['resources']:
if resource.get('type') == 'subtitle':
subtitles.setdefault(resource.get('language') or 'por', []).append({
@@ -186,7 +166,6 @@ class GloboArticleIE(InfoExtractor):
r'\bvideosIDs\s*:\s*["\']?(\d{7,})',
r'\bdata-id=["\'](\d{7,})',
r'<div[^>]+\bid=["\'](\d{7,})',
r'<bs-player[^>]+\bvideoid=["\'](\d{8,})',
]
_TESTS = [{
@@ -214,14 +193,6 @@ class GloboArticleIE(InfoExtractor):
}, {
'url': 'http://oglobo.globo.com/rio/a-amizade-entre-um-entregador-de-farmacia-um-piano-19946271',
'only_matching': True,
}, {
'url': 'https://ge.globo.com/video/ta-na-area-como-foi-assistir-ao-jogo-do-palmeiras-que-a-globo-nao-passou-10287094.ghtml',
'info_dict': {
'id': 'ta-na-area-como-foi-assistir-ao-jogo-do-palmeiras-que-a-globo-nao-passou-10287094',
'title': 'Tá na Área: como foi assistir ao jogo do Palmeiras que a Globo não passou',
'description': 'md5:2d089d036c4c9675117d3a56f8c61739',
},
'playlist_count': 1,
}]
@classmethod
@@ -237,6 +208,6 @@ class GloboArticleIE(InfoExtractor):
entries = [
self.url_result('globo:%s' % video_id, GloboIE.ie_key())
for video_id in orderedSet(video_ids)]
title = self._og_search_title(webpage)
title = self._og_search_title(webpage, fatal=False)
description = self._html_search_meta('description', webpage)
return self.playlist_result(entries, display_id, title, description)
+35 -30
View File
@@ -7,7 +7,6 @@ import urllib.parse
from .common import InfoExtractor
from ..utils import (
determine_ext,
extract_attributes,
ExtractorError,
int_or_none,
parse_qs,
@@ -178,38 +177,44 @@ class GlomexEmbedIE(GlomexBaseIE):
@classmethod
def _extract_urls(cls, webpage, origin_url):
VALID_SRC = rf'(?:https?:)?{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+'
# https://docs.glomex.com/publisher/video-player-integration/javascript-api/
quot_re = r'["\']'
EMBED_RE = r'''(?x)(?:
<iframe[^>]+?src=(?P<_q1>%(quot_re)s)(?P<url>%(url_re)s)(?P=_q1)|
<(?P<html_tag>glomex-player|div)(?:
data-integration-id=(?P<_q2>%(quot_re)s)(?P<integration_html>(?:(?!(?P=_q2)).)+)(?P=_q2)|
data-playlist-id=(?P<_q3>%(quot_re)s)(?P<id_html>(?:(?!(?P=_q3)).)+)(?P=_q3)|
data-glomex-player=(?P<_q4>%(quot_re)s)(?P<glomex_player>true)(?P=_q4)|
[^>]*?
)+>|
# naive parsing of inline scripts for hard-coded integration parameters
<(?P<script_tag>script)[^<]*?>(?:
(?P<_stjs1>dataset\.)?integrationId\s*(?(_stjs1)=|:)\s*
(?P<_q5>%(quot_re)s)(?P<integration_js>(?:(?!(?P=_q5)).)+)(?P=_q5)\s*(?(_stjs1);|,)?|
(?P<_stjs2>dataset\.)?playlistId\s*(?(_stjs2)=|:)\s*
(?P<_q6>%(quot_re)s)(?P<id_js>(?:(?!(?P=_q6)).)+)(?P=_q6)\s*(?(_stjs2);|,)?|
(?:\s|.)*?
)+</script>
)''' % {'quot_re': r'["\']', 'url_re': VALID_SRC}
regex = fr'''(?x)
<iframe[^>]+?src=(?P<q>{quot_re})(?P<url>
(?:https?:)?{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=q)).)+
)(?P=q)'''
for mobj in re.finditer(regex, webpage):
url = unescapeHTML(mobj.group('url'))
if cls.suitable(url):
for mobj in re.finditer(EMBED_RE, webpage):
mdict = mobj.groupdict()
if mdict.get('url'):
url = unescapeHTML(mdict['url'])
if not cls.suitable(url):
continue
yield cls._smuggle_origin_url(url, origin_url)
regex = fr'''(?x)
<glomex-player [^>]+?>|
<div[^>]* data-glomex-player=(?P<q>{quot_re})true(?P=q)[^>]*>'''
for mobj in re.finditer(regex, webpage):
attrs = extract_attributes(mobj.group(0))
if attrs.get('data-integration-id') and attrs.get('data-playlist-id'):
yield cls.build_player_url(attrs['data-playlist-id'], attrs['data-integration-id'], origin_url)
# naive parsing of inline scripts for hard-coded integration parameters
regex = fr'''(?x)
(?P<is_js>dataset\.)?%s\s*(?(is_js)=|:)\s*
(?P<q>{quot_re})(?P<id>(?:(?!(?P=q)).)+)(?P=q)\s'''
for mobj in re.finditer(r'(?x)<script[^<]*>.+?</script>', webpage):
script = mobj.group(0)
integration_id = re.search(regex % 'integrationId', script)
if not integration_id:
continue
playlist_id = re.search(regex % 'playlistId', script)
if playlist_id:
yield cls.build_player_url(playlist_id, integration_id, origin_url)
elif mdict.get('html_tag'):
if mdict['html_tag'] == 'div' and not mdict.get('glomex_player'):
continue
if not mdict.get('video_id_html') or not mdict.get('integration_html'):
continue
yield cls.build_player_url(mdict['video_id_html'], mdict['integration_html'], origin_url)
elif mdict.get('script_tag'):
if not mdict.get('video_id_js') or not mdict.get('integration_js'):
continue
yield cls.build_player_url(mdict['video_id_js'], mdict['integration_js'], origin_url)
def _real_extract(self, url):
url, origin_url = self._unsmuggle_origin_url(url)
+12 -9
View File
@@ -8,33 +8,36 @@ from .common import SearchInfoExtractor
class GoogleSearchIE(SearchInfoExtractor):
IE_DESC = 'Google Video search'
_MAX_RESULTS = 1000
IE_NAME = 'video.google:search'
_SEARCH_KEY = 'gvsearch'
_TESTS = [{
_WORKING = False
_TEST = {
'url': 'gvsearch15:python language',
'info_dict': {
'id': 'python language',
'title': 'python language',
},
'playlist_count': 15,
}]
_PAGE_SIZE = 100
}
def _search_results(self, query):
for pagenum in itertools.count():
webpage = self._download_webpage(
'http://www.google.com/search', f'gvsearch:{query}',
note=f'Downloading result page {pagenum + 1}',
'http://www.google.com/search',
'gvsearch:' + query,
note='Downloading result page %s' % (pagenum + 1),
query={
'tbm': 'vid',
'q': query,
'start': pagenum * self._PAGE_SIZE,
'num': self._PAGE_SIZE,
'start': pagenum * 10,
'hl': 'en',
})
for url in re.findall(r'<div[^>]* class="dXiKIc"[^>]*><a href="([^"]+)"', webpage):
yield self.url_result(url)
for hit_idx, mobj in enumerate(re.finditer(
r'<h3 class="r"><a href="([^"]+)"', webpage)):
if re.search(f'id="vidthumb{hit_idx + 1}"', webpage):
yield self.url_result(mobj.group(1))
if not re.search(r'id="pnnext"', webpage):
return
+49
View File
@@ -0,0 +1,49 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
)
class HornBunnyIE(InfoExtractor):
_VALID_URL = r'http?://(?:www\.)?hornbunny\.com/videos/(?P<title_dash>[a-z-]+)-(?P<id>\d+)\.html'
_TEST = {
'url': 'http://hornbunny.com/videos/panty-slut-jerk-off-instruction-5227.html',
'md5': 'e20fd862d1894b67564c96f180f43924',
'info_dict': {
'id': '5227',
'ext': 'mp4',
'title': 'panty slut jerk off instruction',
'duration': 550,
'age_limit': 18,
'view_count': int,
'thumbnail': r're:^https?://.*\.jpg$',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
duration = parse_duration(self._search_regex(
r'<strong>Runtime:</strong>\s*([0-9:]+)</div>',
webpage, 'duration', fatal=False))
view_count = int_or_none(self._search_regex(
r'<strong>Views:</strong>\s*(\d+)</div>',
webpage, 'view count', fatal=False))
info_dict.update({
'id': video_id,
'title': title,
'duration': duration,
'view_count': view_count,
'age_limit': 18,
})
return info_dict
+3
View File
@@ -80,6 +80,9 @@ class HuffPostIE(InfoExtractor):
'vcodec': 'none' if key.startswith('audio/') else None,
})
if not formats and data.get('fivemin_id'):
return self.url_result('5min:%s' % data['fivemin_id'])
self._sort_formats(formats)
return {
+5 -2
View File
@@ -64,7 +64,10 @@ class ImgGamingBaseIE(InfoExtractor):
domain, media_type, media_id, playlist_id = self._match_valid_url(url).groups()
if playlist_id:
if self._yes_playlist(playlist_id, media_id):
if self.get_param('noplaylist'):
self.to_screen('Downloading just video %s because of --no-playlist' % media_id)
else:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video' % playlist_id)
media_type, media_id = 'playlist', playlist_id
if media_type == 'playlist':
@@ -96,7 +99,7 @@ class ImgGamingBaseIE(InfoExtractor):
continue
if proto == 'hls':
m3u8_formats = self._extract_m3u8_formats(
media_url, media_id, 'mp4', live=is_live,
media_url, media_id, 'mp4', 'm3u8' if is_live else 'm3u8_native',
m3u8_id='hls', fatal=False, headers=self._MANIFEST_HEADERS)
for f in m3u8_formats:
f.setdefault('http_headers', {}).update(self._MANIFEST_HEADERS)
+50 -93
View File
@@ -17,7 +17,7 @@ from ..utils import (
get_element_by_attribute,
int_or_none,
lowercase_escape,
str_or_none,
std_headers,
str_to_int,
traverse_obj,
url_or_none,
@@ -127,74 +127,6 @@ class InstagramBaseIE(InfoExtractor):
'like_count': self._get_count(node, 'likes', 'preview_like'),
}
def _extract_product_media(self, product_media):
media_id = product_media.get('code') or product_media.get('id')
vcodec = product_media.get('video_codec')
dash_manifest_raw = product_media.get('video_dash_manifest')
videos_list = product_media.get('video_versions')
if not (dash_manifest_raw or videos_list):
return {}
formats = [{
'format_id': format.get('id'),
'url': format.get('url'),
'width': format.get('width'),
'height': format.get('height'),
'vcodec': vcodec,
} for format in videos_list or []]
if dash_manifest_raw:
formats.extend(self._parse_mpd_formats(self._parse_xml(dash_manifest_raw, media_id), mpd_id='dash'))
self._sort_formats(formats)
thumbnails = [{
'url': thumbnail.get('url'),
'width': thumbnail.get('width'),
'height': thumbnail.get('height')
} for thumbnail in traverse_obj(product_media, ('image_versions2', 'candidates')) or []]
return {
'id': media_id,
'duration': float_or_none(product_media.get('video_duration')),
'formats': formats,
'thumbnails': thumbnails
}
def _extract_product(self, product_info):
if isinstance(product_info, list):
product_info = product_info[0]
user_info = product_info.get('user') or {}
info_dict = {
'id': product_info.get('code') or product_info.get('id'),
'title': product_info.get('title') or f'Video by {user_info.get("username")}',
'description': traverse_obj(product_info, ('caption', 'text'), expected_type=str_or_none),
'timestamp': int_or_none(product_info.get('taken_at')),
'channel': user_info.get('username'),
'uploader': user_info.get('full_name'),
'uploader_id': str_or_none(user_info.get('pk')),
'view_count': int_or_none(product_info.get('view_count')),
'like_count': int_or_none(product_info.get('like_count')),
'comment_count': int_or_none(product_info.get('comment_count')),
'http_headers': {
'Referer': 'https://www.instagram.com/',
}
}
carousel_media = product_info.get('carousel_media')
if carousel_media:
return {
'_type': 'playlist',
**info_dict,
'title': f'Post by {user_info.get("username")}',
'entries': [{
**info_dict,
**self._extract_product_media(product_media),
} for product_media in carousel_media],
}
return {
**info_dict,
**self._extract_product_media(product_info)
}
class InstagramIOSIE(InfoExtractor):
IE_DESC = 'IOS instagram:// URL'
@@ -253,9 +185,8 @@ class InstagramIE(InstagramBaseIE):
'duration': 0,
'timestamp': 1371748545,
'upload_date': '20130620',
'uploader_id': '2815873',
'uploader_id': 'naomipq',
'uploader': 'B E A U T Y F O R A S H E S',
'channel': 'naomipq',
'like_count': int,
'comment_count': int,
'comments': list,
@@ -271,9 +202,8 @@ class InstagramIE(InstagramBaseIE):
'duration': 0,
'timestamp': 1453760977,
'upload_date': '20160125',
'uploader_id': '12246775',
'uploader_id': 'britneyspears',
'uploader': 'Britney Spears',
'channel': 'britneyspears',
'like_count': int,
'comment_count': int,
'comments': list,
@@ -319,9 +249,8 @@ class InstagramIE(InstagramBaseIE):
'duration': 53.83,
'timestamp': 1530032919,
'upload_date': '20180626',
'uploader_id': '25025320',
'uploader_id': 'instagram',
'uploader': 'Instagram',
'channel': 'instagram',
'like_count': int,
'comment_count': int,
'comments': list,
@@ -387,19 +316,16 @@ class InstagramIE(InstagramBaseIE):
if not media:
additional_data = self._parse_json(
self._search_regex(
r'window\.__additionalDataLoaded\s*\(\s*[^,]+,\s*({.+?})\s*\);',
r'window\.__additionalDataLoaded\s*\(\s*[^,]+,\s*({.+?})\s*\)\s*;',
webpage, 'additional data', default='{}'),
video_id, fatal=False)
product_item = traverse_obj(additional_data, ('items', 0), expected_type=dict)
if product_item:
return self._extract_product(product_item)
media = traverse_obj(additional_data, ('graphql', 'shortcode_media'), 'shortcode_media', expected_type=dict) or {}
if not media and 'www.instagram.com/accounts/login' in urlh.geturl():
self.raise_login_required('You need to log in to access this content')
username = traverse_obj(media, ('owner', 'username')) or self._search_regex(
r'"owner"\s*:\s*{\s*"username"\s*:\s*"(.+?)"', webpage, 'username', fatal=False)
uploader_id = traverse_obj(media, ('owner', 'username')) or self._search_regex(
r'"owner"\s*:\s*{\s*"username"\s*:\s*"(.+?)"', webpage, 'uploader id', fatal=False)
description = (
traverse_obj(media, ('edge_media_to_caption', 'edges', 0, 'node', 'text'), expected_type=str)
@@ -416,7 +342,7 @@ class InstagramIE(InstagramBaseIE):
if nodes:
return self.playlist_result(
self._extract_nodes(nodes, True), video_id,
format_field(username, template='Post by %s'), description)
format_field(uploader_id, template='Post by %s'), description)
video_url = self._og_search_video_url(webpage, secure=False)
@@ -452,13 +378,12 @@ class InstagramIE(InstagramBaseIE):
return {
'id': video_id,
'formats': formats,
'title': media.get('title') or 'Video by %s' % username,
'title': media.get('title') or 'Video by %s' % uploader_id,
'description': description,
'duration': float_or_none(media.get('video_duration')),
'timestamp': traverse_obj(media, 'taken_at_timestamp', 'date', expected_type=int_or_none),
'uploader_id': traverse_obj(media, ('owner', 'id')),
'uploader_id': uploader_id,
'uploader': traverse_obj(media, ('owner', 'full_name')),
'channel': username,
'like_count': self._get_count(media, 'likes', 'preview_like') or str_to_int(self._search_regex(
r'data-log-event="likeCountClick"[^>]*>[^\d]*([\d,\.]+)', webpage, 'like count', fatal=False)),
'comment_count': self._get_count(media, 'comments', 'preview_comment', 'to_comment', 'to_parent_comment'),
@@ -502,7 +427,7 @@ class InstagramPlaylistBaseIE(InstagramBaseIE):
'%s' % rhx_gis,
'',
'%s:%s' % (rhx_gis, csrf_token),
'%s:%s:%s' % (rhx_gis, csrf_token, self.get_param('http_headers')['User-Agent']),
'%s:%s:%s' % (rhx_gis, csrf_token, std_headers['User-Agent']),
]
# try all of the ways to generate a GIS query, and not only use the
@@ -653,6 +578,7 @@ class InstagramStoryIE(InstagramBaseIE):
'X-ASBD-ID': 198387,
'X-IG-WWW-Claim': 0,
})['reels']
entites = []
full_name = traverse_obj(videos, ('user', 'full_name'))
@@ -666,10 +592,41 @@ class InstagramStoryIE(InstagramBaseIE):
username = traverse_obj(user_info, ('user', 'username')) or username
full_name = traverse_obj(user_info, ('user', 'full_name')) or full_name
highlights = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (str(user_id), 'items'))
return self.playlist_result([{
**self._extract_product(highlight),
'title': f'Story by {username}',
'uploader': full_name,
'uploader_id': user_id,
} for highlight in highlights], playlist_id=story_id, playlist_title=highlight_title)
videos = traverse_obj(videos, (f'highlight:{story_id}', 'items'), (str(user_id), 'items'))
for video_info in videos:
formats = []
if isinstance(video_info, list):
video_info = video_info[0]
vcodec = video_info.get('video_codec')
dash_manifest_raw = video_info.get('video_dash_manifest')
videos_list = video_info.get('video_versions')
if not (dash_manifest_raw or videos_list):
continue
for format in videos_list:
formats.append({
'url': format.get('url'),
'width': format.get('width'),
'height': format.get('height'),
'vcodec': vcodec,
})
if dash_manifest_raw:
formats.extend(self._parse_mpd_formats(self._parse_xml(dash_manifest_raw, story_id), mpd_id='dash'))
self._sort_formats(formats)
thumbnails = [{
'url': thumbnail.get('url'),
'width': thumbnail.get('width'),
'height': thumbnail.get('height')
} for thumbnail in traverse_obj(video_info, ('image_versions2', 'candidates')) or []]
entites.append({
'id': video_info.get('id'),
'title': f'Story by {username}',
'timestamp': int_or_none(video_info.get('taken_at')),
'channel': username,
'uploader': full_name,
'duration': float_or_none(video_info.get('video_duration')),
'uploader_id': user_id,
'thumbnails': thumbnails,
'formats': formats,
})
return self.playlist_result(entites, playlist_id=story_id, playlist_title=highlight_title)
+8 -37
View File
@@ -10,7 +10,6 @@ from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse_urlencode,
compat_urllib_parse_unquote
)
from .openload import PhantomJSwrapper
from ..utils import (
@@ -18,7 +17,6 @@ from ..utils import (
decode_packed_codes,
ExtractorError,
float_or_none,
format_field,
get_element_by_id,
get_element_by_attribute,
int_or_none,
@@ -433,10 +431,6 @@ class IqIE(InfoExtractor):
'format': '500',
},
'expected_warnings': ['format is restricted']
}, {
# VIP-restricted video
'url': 'https://www.iq.com/play/mermaid-in-the-fog-2021-gbdpx13bs4',
'only_matching': True
}]
_BID_TAGS = {
'100': '240P',
@@ -463,8 +457,8 @@ class IqIE(InfoExtractor):
_DASH_JS = '''
console.log(page.evaluate(function() {
var tvid = "%(tvid)s"; var vid = "%(vid)s"; var src = "%(src)s";
var uid = "%(uid)s"; var dfp = "%(dfp)s"; var mode = "%(mode)s"; var lang = "%(lang)s";
var bid_list = %(bid_list)s; var ut_list = %(ut_list)s; var tm = new Date().getTime();
var dfp = "%(dfp)s"; var mode = "%(mode)s"; var lang = "%(lang)s"; var bid_list = %(bid_list)s;
var tm = new Date().getTime();
var cmd5x_func = %(cmd5x_func)s; var cmd5x_exporter = {}; cmd5x_func({}, cmd5x_exporter, {}); var cmd5x = cmd5x_exporter.cmd5x;
var authKey = cmd5x(cmd5x('') + tm + '' + tvid);
var k_uid = Array.apply(null, Array(32)).map(function() {return Math.floor(Math.random() * 15).toString(16)}).join('');
@@ -478,7 +472,7 @@ class IqIE(InfoExtractor):
'src': src,
'vt': 0,
'rs': 1,
'uid': uid,
'uid': 0,
'ori': 'pcw',
'ps': 1,
'k_uid': k_uid,
@@ -515,14 +509,12 @@ class IqIE(InfoExtractor):
'version': '10.0',
'dfp': dfp
}),
'ut': 0, // TODO: Set ut param for VIP members
};
var enc_params = [];
for (var prop in query) {
enc_params.push(encodeURIComponent(prop) + '=' + encodeURIComponent(query[prop]));
}
ut_list.forEach(function(ut) {
enc_params.push('ut=' + ut);
})
var dash_path = '/dash?' + enc_params.join('&'); dash_path += '&vf=' + cmd5x(dash_path);
dash_paths[bid] = dash_path;
});
@@ -579,37 +571,17 @@ class IqIE(InfoExtractor):
page_data = next_props['initialState']['play']
video_info = page_data['curVideoInfo']
uid = traverse_obj(
self._parse_json(
self._get_cookie('I00002', '{}'), video_id, transform_source=compat_urllib_parse_unquote, fatal=False),
('data', 'uid'), default=0)
if uid:
vip_data = self._download_json(
'https://pcw-api.iq.com/api/vtype', video_id, note='Downloading VIP data', errnote='Unable to download VIP data', query={
'batch': 1,
'platformId': 3,
'modeCode': self._get_cookie('mod', 'intl'),
'langCode': self._get_cookie('lang', 'en_us'),
'deviceId': self._get_cookie('QC005', '')
}, fatal=False)
ut_list = traverse_obj(vip_data, ('data', 'all_vip', ..., 'vipType'), expected_type=str_or_none, default=[])
else:
ut_list = ['0']
# bid 0 as an initial format checker
dash_paths = self._parse_json(PhantomJSwrapper(self).get(
url, html='<!DOCTYPE html>', video_id=video_id, note2='Executing signature code', jscode=self._DASH_JS % {
'tvid': video_info['tvId'],
'vid': video_info['vid'],
'src': traverse_obj(next_props, ('initialProps', 'pageProps', 'ptid'),
expected_type=str, default='04022001010011000000'),
'uid': uid,
expected_type=str, default='01010031010018000000'),
'dfp': self._get_cookie('dfp', ''),
'mode': self._get_cookie('mod', 'intl'),
'lang': self._get_cookie('lang', 'en_us'),
'bid_list': '[' + ','.join(['0', *self._BID_TAGS.keys()]) + ']',
'ut_list': '[' + ','.join(ut_list) + ']',
'cmd5x_func': self._extract_cmd5x_function(webpage, video_id),
})[1].strip(), video_id)
@@ -618,10 +590,9 @@ class IqIE(InfoExtractor):
urljoin('https://cache-video.iq.com', dash_paths['0']), video_id,
note='Downloading initial video format info', errnote='Unable to download initial video format info')['data']
preview_time = traverse_obj(
initial_format_data, ('boss_ts', (None, 'data'), ('previewTime', 'rtime')), expected_type=float_or_none, get_all=False)
if traverse_obj(initial_format_data, ('boss_ts', 'data', 'prv'), expected_type=int_or_none):
self.report_warning('This preview video is limited%s' % format_field(preview_time, template=' to %s seconds'))
preview_time = traverse_obj(initial_format_data, ('boss_ts', 'data', 'previewTime'), expected_type=float_or_none)
if preview_time:
self.report_warning(f'This preview video is limited to {preview_time} seconds')
# TODO: Extract audio-only formats
for bid in set(traverse_obj(initial_format_data, ('program', 'video', ..., 'bid'), expected_type=str_or_none, default=[])):
+42
View File
@@ -0,0 +1,42 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import remove_start
class Ir90TvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?90tv\.ir/video/(?P<id>[0-9]+)/.*'
_TESTS = [{
'url': 'http://90tv.ir/video/95719/%D8%B4%D8%A7%DB%8C%D8%B9%D8%A7%D8%AA-%D9%86%D9%82%D9%84-%D9%88-%D8%A7%D9%86%D8%AA%D9%82%D8%A7%D9%84%D8%A7%D8%AA-%D9%85%D9%87%D9%85-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7-940218',
'md5': '411dbd94891381960cb9e13daa47a869',
'info_dict': {
'id': '95719',
'ext': 'mp4',
'title': 'شایعات نقل و انتقالات مهم فوتبال اروپا 94/02/18',
'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
'url': 'http://www.90tv.ir/video/95719/%D8%B4%D8%A7%DB%8C%D8%B9%D8%A7%D8%AA-%D9%86%D9%82%D9%84-%D9%88-%D8%A7%D9%86%D8%AA%D9%82%D8%A7%D9%84%D8%A7%D8%AA-%D9%85%D9%87%D9%85-%D9%81%D9%88%D8%AA%D8%A8%D8%A7%D9%84-%D8%A7%D8%B1%D9%88%D9%BE%D8%A7-940218',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = remove_start(self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title'), '90tv.ir :: ')
video_url = self._search_regex(
r'<source[^>]+src="([^"]+)"', webpage, 'video url')
thumbnail = self._search_regex(r'poster="([^"]+)"', webpage, 'thumbnail url', fatal=False)
return {
'url': video_url,
'id': video_id,
'title': title,
'video_url': video_url,
'thumbnail': thumbnail,
}
+3 -5
View File
@@ -301,7 +301,6 @@ class KalturaIE(InfoExtractor):
data_url = re.sub(r'/flvclipper/.*', '/serveFlavor', data_url)
formats = []
subtitles = {}
for f in flavor_assets:
# Continue if asset is not ready
if f.get('status') != 2:
@@ -345,14 +344,13 @@ class KalturaIE(InfoExtractor):
if '/playManifest/' in data_url:
m3u8_url = sign_url(data_url.replace(
'format/url', 'format/applehttp'))
fmts, subs = self._extract_m3u8_formats_and_subtitles(
formats.extend(self._extract_m3u8_formats(
m3u8_url, entry_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
m3u8_id='hls', fatal=False))
self._sort_formats(formats)
subtitles = {}
if captions:
for caption in captions.get('objects', []):
# Continue if caption is not ready
+48
View File
@@ -0,0 +1,48 @@
from __future__ import unicode_literals
import re
import hashlib
from .common import InfoExtractor
_md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
class KankanIE(InfoExtractor):
_VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
_TEST = {
'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',
'md5': '29aca1e47ae68fc28804aca89f29507e',
'info_dict': {
'id': '48863',
'ext': 'flv',
'title': 'Ready To Go',
},
'skip': 'Only available from China',
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
gcids = re.findall(r'http://.+?/.+?/(.+?)/', surls)
gcid = gcids[-1]
info_url = 'http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid
video_info_page = self._download_webpage(
info_url, video_id, 'Downloading video url info')
ip = self._search_regex(r'ip:"(.+?)"', video_info_page, 'video url ip')
path = self._search_regex(r'path:"(.+?)"', video_info_page, 'video url path')
param1 = self._search_regex(r'param1:(\d+)', video_info_page, 'param1')
param2 = self._search_regex(r'param2:(\d+)', video_info_page, 'param2')
key = _md5('xl_mp43651' + param1 + param2)
video_url = 'http://%s%s?key=%s&key1=%s' % (ip, path, key, param2)
return {
'id': video_id,
'title': title,
'url': video_url,
}
+4 -5
View File
@@ -17,7 +17,6 @@ from ..utils import (
parse_qs,
OnDemandPagedList,
try_get,
UnsupportedError,
urljoin,
)
@@ -197,11 +196,11 @@ class LBRYIE(LBRYBaseIE):
live_data = self._download_json(
f'https://api.live.odysee.com/v1/odysee/live/{claim_id}', claim_id,
note='Downloading livestream JSON metadata')['data']
streaming_url = final_url = live_data.get('url')
if not final_url and not live_data.get('live'):
self.raise_no_formats('This stream is not live', True, claim_id)
if not live_data['live']:
raise ExtractorError('This stream is not live', expected=True)
streaming_url = final_url = live_data['url']
else:
raise UnsupportedError(url)
raise ExtractorError('Unsupported URL', expected=True)
info = self._parse_stream(result, url)
if determine_ext(final_url) == 'm3u8':
+18 -5
View File
@@ -7,7 +7,6 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
traverse_obj,
smuggle_url,
unsmuggle_url,
)
@@ -56,6 +55,9 @@ class LiTVIE(InfoExtractor):
episode_title = program_info['title']
content_id = season_list['contentId']
if prompt:
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (content_id, video_id))
all_episodes = [
self.url_result(smuggle_url(
self._URL_TEMPLATE % (program_info['contentType'], episode['contentId']),
@@ -65,10 +67,16 @@ class LiTVIE(InfoExtractor):
return self.playlist_result(all_episodes, content_id, episode_title)
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
url, data = unsmuggle_url(url, {})
video_id = self._match_id(url)
noplaylist = self.get_param('noplaylist')
noplaylist_prompt = True
if 'force_noplaylist' in data:
noplaylist = data['force_noplaylist']
noplaylist_prompt = False
webpage = self._download_webpage(url, video_id)
program_info = self._parse_json(self._search_regex(
@@ -76,9 +84,14 @@ class LiTVIE(InfoExtractor):
video_id)
season_list = list(program_info.get('seasonList', {}).values())
playlist_id = traverse_obj(season_list, 0, 'contentId')
if self._yes_playlist(playlist_id, video_id, smuggled_data):
return self._extract_playlist(season_list[0], video_id, program_info)
if season_list:
if not noplaylist:
return self._extract_playlist(
season_list[0], video_id, program_info,
prompt=noplaylist_prompt)
if noplaylist_prompt:
self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
# In browsers `getMainUrl` request is always issued. Usually this
# endpoint gives the same result as the data embedded in the webpage.

Some files were not shown because too many files have changed in this diff Show More