Madeorsk
/
youtube-dl
mirror of https://codeberg.org/polarisfm/youtube-dl
1
0
Fork 0
Code Issues Releases Wiki Activity

Merge branch 'master' of https://github.com/rg3/youtube-dl into librivox

This commit is contained in:
Petar Kukolj 2018-10-02 01:42:48 +02:00
parent d9f4cc8b3e 66d106f270
commit c8b62b28d6
425 changed files with 21474 additions and 8355 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
.github/ISSUE_TEMPLATE.md vendored
View File

@ -6,12 +6,13 @@
---
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.09.15*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.09.15**
### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.09.26*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected.
- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.09.26**
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
- [ ] Checked that provided video/audio/playlist URLs (if any) are alive and playable in a browser
### What is the purpose of your *issue*?
- [ ] Bug report (encountered problems with youtube-dl)
@ -35,7 +36,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2017.09.15
[debug] youtube-dl version 2018.09.26
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}

1
.github/ISSUE_TEMPLATE_tmpl.md vendored
View File

@ -12,6 +12,7 @@
### Before submitting an *issue* make sure you have:
- [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections
- [ ] [Searched](https://github.com/rg3/youtube-dl/search?type=Issues) the bugtracker for similar issues including closed ones
- [ ] Checked that provided video/audio/playlist URLs (if any) are alive and playable in a browser
### What is the purpose of your *issue*?
- [ ] Bug report (encountered problems with youtube-dl)

1
.github/PULL_REQUEST_TEMPLATE.md vendored
View File

@ -9,6 +9,7 @@
### Before submitting a *pull request* make sure you have:
- [ ] At least skimmed through [adding new extractor tutorial](https://github.com/rg3/youtube-dl#adding-support-for-a-new-site) and [youtube-dl coding conventions](https://github.com/rg3/youtube-dl#youtube-dl-coding-conventions) sections
- [ ] [Searched](https://github.com/rg3/youtube-dl/search?q=is%3Apr&type=Issues) the bugtracker for similar pull requests
- [ ] Checked the code with [flake8](https://pypi.python.org/pypi/flake8)
### In order to be accepted and merged into youtube-dl each piece of code must be in public domain or released under [Unlicense](http://unlicense.org/). Check one of the following options:
- [ ] I am the original author of this code and I am willing to release it under [Unlicense](http://unlicense.org/)

4
.gitignore vendored
View File

@ -47,3 +47,7 @@ youtube-dl.zsh
*.iml
tmp/
venv/
# VS Code related files
.vscode

21
.travis.yml
View File

@ -7,16 +7,21 @@ python:
- "3.4"
- "3.5"
- "3.6"
- "pypy"
- "pypy3"
sudo: false
env:
- YTDL_TEST_SET=core
- YTDL_TEST_SET=download
matrix:
include:
- env: JYTHON=true; YTDL_TEST_SET=core
- env: JYTHON=true; YTDL_TEST_SET=download
fast_finish: true
allow_failures:
- env: YTDL_TEST_SET=download
- env: JYTHON=true; YTDL_TEST_SET=core
- env: JYTHON=true; YTDL_TEST_SET=download
before_install:
- if [ "$JYTHON" == "true" ]; then ./devscripts/install_jython.sh; export PATH="$HOME/jython/bin:$PATH"; fi
script: ./devscripts/run_tests.sh
notifications:
email:
- filippo.valsorda@gmail.com
- yasoob.khld@gmail.com
# irc:
# channels:
# - "irc.freenode.org#youtube-dl"
# skip_join: true

22
AUTHORS
View File

@ -224,3 +224,25 @@ Giuseppe Fabiano
Örn Guðjónsson
Parmjit Virk
Genki Sky
Ľuboš Katrinec
Corey Nicholson
Ashutosh Chaudhary
John Dong
Tatsuyuki Ishi
Daniel Weber
Kay Bouché
Yang Hongbo
Lei Wang
Petr Novák
Leonardo Taccari
Martin Weinelt
Surya Oktafendri
TingPing
Alexandre Macabies
Bastian de Groot
Niklas Haas
András Veres-Szentkirályi
Enes Solak
Nathan Rossi
Thomas van der Berg
Luca Cherubin

1198
ChangeLog
View File

File diff suppressed because it is too large Load Diff

6
MANIFEST.in
View File

@ -1,7 +1,9 @@
include README.md
include test/*.py
include test/*.json
include LICENSE
include AUTHORS
include ChangeLog
include youtube-dl.bash-completion
include youtube-dl.fish
include youtube-dl.1
recursive-include docs Makefile conf.py *.rst
recursive-include test *

25
Makefile
View File

@ -14,6 +14,9 @@ PYTHON ?= /usr/bin/env python
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then echo /etc; else echo $(PREFIX)/etc; fi)
# set markdown input format to "markdown-smart" for pandoc version 2 and to "markdown" for pandoc prior to version 2
MARKDOWN = $(shell if [ `pandoc -v | head -n1 | cut -d" " -f2 | head -c1` = "2" ]; then echo markdown-smart; else echo markdown; fi)
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
install -d $(DESTDIR)$(BINDIR)
install -m 755 youtube-dl $(DESTDIR)$(BINDIR)
@ -36,8 +39,17 @@ test:
ot: offlinetest
# Keep this list in sync with devscripts/run_tests.sh
offlinetest: codetest
$(PYTHON) -m nose --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py --exclude test_iqiyi_sdk_interpreter.py --exclude test_socks.py
$(PYTHON) -m nose --verbose test \
--exclude test_age_restriction.py \
--exclude test_download.py \
--exclude test_iqiyi_sdk_interpreter.py \
--exclude test_socks.py \
--exclude test_subtitles.py \
--exclude test_write_annotations.py \
--exclude test_youtube_lists.py \
--exclude test_youtube_signature.py
tar: youtube-dl.tar.gz
@ -73,11 +85,11 @@ supportedsites:
$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
README.txt: README.md
pandoc -f markdown -t plain README.md -o README.txt
pandoc -f $(MARKDOWN) -t plain README.md -o README.txt
youtube-dl.1: README.md
$(PYTHON) devscripts/prepare_manpage.py youtube-dl.1.temp.md
pandoc -s -f markdown -t man youtube-dl.1.temp.md -o youtube-dl.1
pandoc -s -f $(MARKDOWN) -t man youtube-dl.1.temp.md -o youtube-dl.1
rm -f youtube-dl.1.temp.md
youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-completion.in
@ -101,7 +113,7 @@ _EXTRACTOR_FILES = $(shell find youtube_dl/extractor -iname '*.py' -and -not -in
youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
$(PYTHON) devscripts/make_lazy_extractors.py $@
youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog
youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog AUTHORS
@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
--exclude '*.DS_Store' \
--exclude '*.kate-swp' \
@ -110,11 +122,10 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
--exclude '*~' \
--exclude '__pycache__' \
--exclude '.git' \
--exclude 'testdata' \
--exclude 'docs/_build' \
-- \
bin devscripts test youtube_dl docs \
ChangeLog LICENSE README.md README.txt \
ChangeLog AUTHORS LICENSE README.md README.txt \
Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
youtube-dl.zsh youtube-dl.fish setup.py \
youtube-dl.zsh youtube-dl.fish setup.py setup.cfg \
youtube-dl

54
README.md
View File

@ -1,3 +1,5 @@
[![Build Status](https://travis-ci.org/rg3/youtube-dl.svg?branch=master)](https://travis-ci.org/rg3/youtube-dl)
youtube-dl - download videos from youtube.com or other video platforms
- [INSTALLATION](#installation)
@ -15,7 +17,7 @@ youtube-dl - download videos from youtube.com or other video platforms
# INSTALLATION
To install it right away for all UNIX users (Linux, OS X, etc.), type:
To install it right away for all UNIX users (Linux, macOS, etc.), type:
sudo curl -L https://yt-dl.org/downloads/latest/youtube-dl -o /usr/local/bin/youtube-dl
sudo chmod a+rx /usr/local/bin/youtube-dl
@ -33,7 +35,7 @@ You can also use pip:
This command will update youtube-dl if you have already installed it. See the [pypi page](https://pypi.python.org/pypi/youtube_dl) for more information.
OS X users can install youtube-dl with [Homebrew](https://brew.sh/):
macOS users can install youtube-dl with [Homebrew](https://brew.sh/):
brew install youtube-dl
@ -44,7 +46,7 @@ Or with [MacPorts](https://www.macports.org/):
Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html).
# DESCRIPTION
**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
youtube-dl [OPTIONS] URL [URL...]
@ -91,8 +93,8 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
## Network Options:
--proxy URL Use the specified HTTP/HTTPS/SOCKS proxy.
To enable experimental SOCKS proxy, specify
a proper scheme. For example
To enable SOCKS proxy, specify a proper
scheme. For example
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
@ -104,16 +106,18 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
--geo-verification-proxy URL Use this proxy to verify the IP address for
some geo-restricted sites. The default
proxy specified by --proxy (or none, if the
options is not present) is used for the
option is not present) is used for the
actual downloading.
--geo-bypass Bypass geographic restriction via faking
X-Forwarded-For HTTP header (experimental)
X-Forwarded-For HTTP header
--no-geo-bypass Do not bypass geographic restriction via
faking X-Forwarded-For HTTP header
(experimental)
--geo-bypass-country CODE Force bypass geographic restriction with
explicitly provided two-letter ISO 3166-2
country code (experimental)
country code
--geo-bypass-ip-block IP_BLOCK Force bypass geographic restriction with
explicitly provided IP block in CIDR
notation
## Video Selection:
--playlist-start NUMBER Playlist video to start at (default is 1)
@ -196,10 +200,15 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
size. By default, the buffer size is
automatically resized from an initial value
of SIZE.
--http-chunk-size SIZE Size of a chunk for chunk-based HTTP
downloading (e.g. 10485760 or 10M) (default
is disabled). May be useful for bypassing
bandwidth throttling imposed by a webserver
(experimental)
--playlist-reverse Download playlist videos in reverse order
--playlist-random Download playlist videos in random order
--xattr-set-filesize Set file xattribute ytdl.filesize with
expected file size (experimental)
expected file size
--hls-prefer-native Use the native HLS downloader instead of
ffmpeg
--hls-prefer-ffmpeg Use ffmpeg instead of the native HLS
@ -216,7 +225,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
## Filesystem Options:
-a, --batch-file FILE File containing URLs to download ('-' for
stdin)
stdin), one URL per line. Lines starting
with '#', ';' or ']' are considered as
comments and ignored.
--id Use only video ID in file name
-o, --output TEMPLATE Output filename template, see the "OUTPUT
TEMPLATE" for all the info
@ -416,9 +427,9 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
default; fix file if we can, warn
otherwise)
--prefer-avconv Prefer avconv over ffmpeg for running the
postprocessors (default)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
postprocessors
--prefer-ffmpeg Prefer ffmpeg over avconv for running the
postprocessors (default)
--ffmpeg-location PATH Location of the ffmpeg/avconv binary;
either the path to the binary or its
containing directory.
@ -427,11 +438,11 @@ Alternatively, refer to the [developer instructions](#developer-instructions) fo
syntax. Example: --exec 'adb push {}
/sdcard/Music/ && rm {}'
--convert-subs FORMAT Convert the subtitles to other format
(currently supported: srt|ass|vtt)
(currently supported: srt|ass|vtt|lrc)
# CONFIGURATION
You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux and OS X, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself.
You can configure youtube-dl by placing any supported command line option to a configuration file. On Linux and macOS, the system wide configuration file is located at `/etc/youtube-dl.conf` and the user wide configuration file at `~/.config/youtube-dl/config`. On Windows, the user wide configuration file locations are `%APPDATA%\youtube-dl\config.txt` or `C:\Users\<user name>\youtube-dl.conf`. Note that by default configuration file may not exist so you may need to create it yourself.
For example, with the following configuration file youtube-dl will always extract the audio, not copy the mtime, use a proxy and save all videos under `Movies` directory in your home directory:
```
@ -500,6 +511,8 @@ The basic usage is not to set any template arguments when downloading a single f
- `timestamp` (numeric): UNIX timestamp of the moment the video became available
- `upload_date` (string): Video upload date (YYYYMMDD)
- `uploader_id` (string): Nickname or id of the video uploader
- `channel` (string): Full name of the channel the video is uploaded on
- `channel_id` (string): Id of the channel
- `location` (string): Physical location where the video was filmed
- `duration` (numeric): Length of the video in seconds
- `view_count` (numeric): How many users have watched the video on the platform
@ -509,6 +522,9 @@ The basic usage is not to set any template arguments when downloading a single f
- `average_rating` (numeric): Average rating give by users, the scale used depends on the webpage
- `comment_count` (numeric): Number of comments on the video
- `age_limit` (numeric): Age restriction for the video (years)
- `is_live` (boolean): Whether this video is a live stream or a fixed-length video
- `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL
- `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL
- `format` (string): A human-readable description of the format
- `format_id` (string): Format code specified by `--format`
- `format_note` (string): Additional info about the format
@ -534,6 +550,8 @@ The basic usage is not to set any template arguments when downloading a single f
- `playlist_index` (numeric): Index of the video in the playlist 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
Available for the video that belongs to some logical chapter or section:
@ -854,9 +872,9 @@ Either prepend `https://www.youtube.com/watch?v=` or separate the ID from the op
Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`.
In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox).
In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [cookies.txt](https://addons.mozilla.org/en-US/firefox/addon/cookies-txt/) (for Firefox).
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, Mac OS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, macOS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format.
Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare).
@ -1167,7 +1185,7 @@ with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['https://www.youtube.com/watch?v=BaW_jenozKc'])
```
Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L129-L279). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
Most likely, you'll want to use various options. For a list of options available, have a look at [`youtube_dl/YoutubeDL.py`](https://github.com/rg3/youtube-dl/blob/3e4cedf9e8cd3157df2457df7274d0c842421945/youtube_dl/YoutubeDL.py#L137-L312). For a start, if you want to intercept youtube-dl's output, set a `logger` object.
Here's a more complete example of a program that outputs only errors (and a short message after the download is finished), and downloads/converts the video to an mp3 file:

19
devscripts/gh-pages/generate-download.py
View File

@ -1,27 +1,22 @@
#!/usr/bin/env python3
from __future__ import unicode_literals
import hashlib
import urllib.request
import json
versions_info = json.load(open('update/versions.json'))
version = versions_info['latest']
URL = versions_info['versions'][version]['bin'][0]
data = urllib.request.urlopen(URL).read()
version_dict = versions_info['versions'][version]
# Read template page
with open('download.html.in', 'r', encoding='utf-8') as tmplf:
template = tmplf.read()
sha256sum = hashlib.sha256(data).hexdigest()
template = template.replace('@PROGRAM_VERSION@', version)
template = template.replace('@PROGRAM_URL@', URL)
template = template.replace('@PROGRAM_SHA256SUM@', sha256sum)
template = template.replace('@EXE_URL@', versions_info['versions'][version]['exe'][0])
template = template.replace('@EXE_SHA256SUM@', versions_info['versions'][version]['exe'][1])
template = template.replace('@TAR_URL@', versions_info['versions'][version]['tar'][0])
template = template.replace('@TAR_SHA256SUM@', versions_info['versions'][version]['tar'][1])
template = template.replace('@PROGRAM_URL@', version_dict['bin'][0])
template = template.replace('@PROGRAM_SHA256SUM@', version_dict['bin'][1])
template = template.replace('@EXE_URL@', version_dict['exe'][0])
template = template.replace('@EXE_SHA256SUM@', version_dict['exe'][1])
template = template.replace('@TAR_URL@', version_dict['tar'][0])
template = template.replace('@TAR_SHA256SUM@', version_dict['tar'][1])
with open('download.html', 'w', encoding='utf-8') as dlf:
dlf.write(template)

2
devscripts/gh-pages/update-copyright.py
View File

@ -13,7 +13,7 @@ year = str(datetime.datetime.now().year)
for fn in glob.glob('*.html*'):
with io.open(fn, encoding='utf-8') as f:
content = f.read()
newc = re.sub(r'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', 'Copyright © 2006-' + year, content)
newc = re.sub(r'(?P<copyright>Copyright © 2011-)(?P<year>[0-9]{4})', 'Copyright © 2011-' + year, content)
if content != newc:
tmpFn = fn + '.part'
with io.open(tmpFn, 'wt', encoding='utf-8') as outf:

5
devscripts/install_jython.sh Executable file
View File

@ -0,0 +1,5 @@
#!/bin/bash
wget http://central.maven.org/maven2/org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar
java -jar jython-installer-2.7.1.jar -s -d "$HOME/jython"
$HOME/jython/bin/jython -m pip install nose

3
devscripts/run_tests.sh
View File

@ -1,6 +1,7 @@
#!/bin/bash
DOWNLOAD_TESTS="age_restriction|download|subtitles|write_annotations|iqiyi_sdk_interpreter|youtube_lists"
# Keep this list in sync with the `offlinetest` target in Makefile
DOWNLOAD_TESTS="age_restriction|download|iqiyi_sdk_interpreter|socks|subtitles|write_annotations|youtube_lists|youtube_signature"
test_set=""
multiprocess_args=""

169
docs/supportedsites.md
View File

@ -3,8 +3,7 @@
- **1up.com**
- **20min**
- **220.ro**
- **22tracks:genre**
- **22tracks:track**
- **23video**
- **24video**
- **3qsdn**: 3Q SDN
- **3sat**
@ -12,10 +11,10 @@
- **56.com**
- **5min**
- **6play**
- **7plus**
- **8tracks**
- **91porn**
- **9c9media**
- **9c9media:stack**
- **9gag**
- **9now.com.au**
- **abc.net.au**
@ -36,18 +35,19 @@
- **AdultSwim**
- **aenetworks**: A+E Networks: A&E, Lifetime, History.com, FYI Network
- **afreecatv**: afreecatv.com
- **afreecatv:global**: afreecatv.com
- **AirMozilla**
- **AliExpressLive**
- **AlJazeera**
- **Allocine**
- **AlphaPorno**
- **AMCNetworks**
- **AmericasTestKitchen**
- **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
- **AnimeOnDemand**
- **anitube.se**
- **Anvato**
- **AnySex**
- **APA**
- **Aparat**
- **AppleConnect**
- **AppleDaily**: 臺灣蘋果日報
@ -56,6 +56,7 @@
- **archive.org**: archive.org videos
- **ARD**
- **ARD:mediathek**
- **ARDBetaMediathek**
- **Arkena**
- **arte.tv**
- **arte.tv:+7**
@ -97,9 +98,11 @@
- **bbc.co.uk:article**: BBC articles
- **bbc.co.uk:iplayer:playlist**
- **bbc.co.uk:playlist**
- **BBVTV**
- **Beatport**
- **Beeg**
- **BehindKink**
- **Bellator**
- **BellMedia**
- **Bet**
- **Bigflix**
@ -107,6 +110,8 @@
- **BiliBili**
- **BioBioChileTV**
- **BIQLE**
- **BitChute**
- **BitChuteChannel**
- **BleacherReport**
- **BleacherReportCMS**
- **blinkx**
@ -114,26 +119,31 @@
- **BokeCC**
- **BostonGlobe**
- **Bpb**: Bundeszentrale für politische Bildung
- **BR**: Bayerischer Rundfunk Mediathek
- **BR**: Bayerischer Rundfunk
- **BravoTV**
- **Break**
- **brightcove:legacy**
- **brightcove:new**
- **BRMediathek**: Bayerischer Rundfunk Mediathek
- **bt:article**: Bergens Tidende Articles
- **bt:vestlendingen**: Bergens Tidende - Vestlendingen
- **BusinessInsider**
- **BuzzFeed**
- **BYUtv**
- **BYUtvEvent**
- **Camdemy**
- **CamdemyFolder**
- **CamModels**
- **CamTube**
- **CamWithHer**
- **canalc2.tv**
- **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
- **Canvas**: canvas.be and een.be
- **Canalplus**: mycanal.fr and piwiplus.fr
- **Canvas**
- **CanvasEen**: canvas.be and een.be
- **CarambaTV**
- **CarambaTVPage**
- **CartoonNetwork**
- **cbc.ca**
- **cbc.ca:olympics**
- **cbc.ca:player**
- **cbc.ca:watch**
- **cbc.ca:watch:video**
@ -161,6 +171,7 @@
- **ClipRs**
- **Clipsyndicate**
- **CloserToTruth**
- **CloudflareStream**
- **cloudtime**: CloudTime
- **Cloudy**
- **Clubic**
@ -170,7 +181,6 @@
- **CNN**
- **CNNArticle**
- **CNNBlogs**
- **CollegeRama**
- **ComCarCoff**
- **ComedyCentral**
- **ComedyCentralFullEpisodes**
@ -183,13 +193,13 @@
- **Crackle**
- **Criterion**
- **CrooksAndLiars**
- **Crunchyroll**
- **crunchyroll**
- **crunchyroll:playlist**
- **CSNNE**
- **CSpan**: C-SPAN
- **CtsNews**: 華視新聞
- **CTVNews**
- **culturebox.francetvinfo.fr**
- **Culturebox**
- **CultureUnplugged**
- **curiositystream**
- **curiositystream:collection**
@ -198,9 +208,8 @@
- **dailymotion**
- **dailymotion:playlist**
- **dailymotion:user**
- **DailymotionCloud**
- **Daisuki**
- **DaisukiPlaylist**
- **DaisukiMotto**
- **DaisukiMottoPlaylist**
- **daum.net**
- **daum.net:clip**
- **daum.net:playlist**
@ -211,6 +220,7 @@
- **defense.gouv.fr**
- **democracynow**
- **DHM**: Filmarchiv - Deutsches Historisches Museum
- **Digg**
- **DigitallySpeaking**
- **Digiteka**
- **Discovery**
@ -231,6 +241,7 @@
- **DrTuber**
- **drtv**
- **drtv:live**
- **DTube**
- **Dumpert**
- **dvtv**: http://video.aktualne.cz/
- **dw**
@ -241,10 +252,12 @@
- **egghead:course**: egghead.io course
- **egghead:lesson**: egghead.io lesson
- **eHow**
- **EinsUndEinsTV**
- **Einthusan**
- **eitb.tv**
- **EllenTV**
- **EllenTV:clips**
- **EllenTube**
- **EllenTubePlaylist**
- **EllenTubeVideo**
- **ElPais**: El País
- **Embedly**
- **EMPFlix**
@ -255,10 +268,11 @@
- **ESPN**
- **ESPNArticle**
- **EsriVideo**
- **ETOnline**
- **Europa**
- **EveryonesMixtape**
- **EWETV**
- **ExpoTV**
- **Expressen**
- **ExtremeTube**
- **EyedoTV**
- **facebook**
@ -267,10 +281,10 @@
- **fc2**
- **fc2:embed**
- **Fczenit**
- **fernsehkritik.tv**
- **filmon**
- **filmon:channel**
- **Firstpost**
- **Filmweb**
- **FiveThirtyEight**
- **FiveTV**
- **Flickr**
- **Flipagram**
@ -282,18 +296,24 @@
- **Foxgay**
- **foxnews**: Fox News and Fox Business Video
- **foxnews:article**
- **foxnews:insider**
- **FoxSports**
- **france2.fr:generation-quoi**
- **france2.fr:generation-what**
- **FranceCulture**
- **FranceInter**
- **FranceTV**
- **FranceTVEmbed**
- **francetvinfo.fr**
- **FranceTVJeunesse**
- **FranceTVSite**
- **Freesound**
- **freespeech.org**
- **FreshLive**
- **FrontendMasters**
- **FrontendMastersCourse**
- **FrontendMastersLesson**
- **Funimation**
- **FunkChannel**
- **FunkMix**
- **FunnyOrDie**
- **Fusion**
- **Fux**
@ -301,7 +321,6 @@
- **GameInformer**
- **GameOne**
- **gameone:playlist**
- **Gamersyde**
- **GameSpot**
- **GameStar**
- **Gaskrank**
@ -311,6 +330,7 @@
- **Gfycat**
- **GiantBomb**
- **Giga**
- **GlattvisionTV**
- **Glide**: Glide mobile video messages (glide.me)
- **Globo**
- **GloboArticle**
@ -332,6 +352,7 @@
- **HentaiStigma**
- **hetklokhuis**
- **hgtv.com:show**
- **HiDive**
- **HistoricFilms**
- **history:topic**: History.com Topic
- **hitbox**
@ -340,6 +361,7 @@
- **HornBunny**
- **HotNewHipHop**
- **HotStar**
- **hotstar:playlist**
- **Howcast**
- **HowStuffWorks**
- **HRTi**
@ -355,17 +377,18 @@
- **ImgurAlbum**
- **Ina**
- **Inc**
- **Indavideo**
- **IndavideoEmbed**
- **InfoQ**
- **Instagram**
- **instagram:user**: Instagram user profile
- **Internazionale**
- **InternetVideoArchive**
- **IPrima**
- **iqiyi**: 爱奇艺
- **Ir90Tv**
- **ITTF**
- **ITV**
- **ITVBTCC**
- **ivi**: ivi.ru
- **ivi:compilation**: ivi.ru compilations
- **ivideon**: Ivideon TV
@ -378,8 +401,8 @@
- **Jove**
- **jpopsuki.tv**
- **JWPlatform**
- **Kakao**
- **Kaltura**
- **Kamcord**
- **KanalPlay**: Kanal 5/9/11 Play
- **Kankan**
- **Karaoketv**
@ -389,6 +412,7 @@
- **Ketnet**
- **KhanAcademy**
- **KickStarter**
- **KinoPoisk**
- **KonserthusetPlay**
- **kontrtube**: KontrTube.ru - Труба зовёт
- **KrasView**: Красвью
@ -411,6 +435,7 @@
- **Lecture2Go**
- **LEGO**
- **Lemonde**
- **Lenta**
- **LePlaylist**
- **LetvCloud**: 乐视云
- **Libsyn**
@ -419,6 +444,7 @@
- **limelight**
- **limelight:channel**
- **limelight:channel_list**
- **LineTV**
- **LiTV**
- **LiveLeak**
- **LiveLeakEmbed**
@ -434,16 +460,21 @@
- **m6**
- **macgamestore**: MacGameStore trailers
- **mailru**: Видео@Mail.Ru
- **MakersChannel**
- **mailru:music**: Музыка@Mail.Ru
- **mailru:music:search**: Музыка@Mail.Ru
- **MakerTV**
- **mangomolo:live**
- **mangomolo:video**
- **ManyVids**
- **Markiza**
- **MarkizaPage**
- **massengeschmack.tv**
- **MatchTV**
- **MDR**: MDR.DE and KiKA
- **media.ccc.de**
- **Medialaan**
- **Mediaset**
- **Mediasite**
- **Medici**
- **megaphone.fm**: megaphone.fm embedded players
- **Meipai**: 美拍
@ -467,12 +498,13 @@
- **Mixer:vod**
- **MLB**
- **Mnet**
- **MNetTV**
- **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
- **Mofosex**
- **Mojvideo**
- **Moniker**: allmyvideos.net and vidspot.net
- **Morningstar**: morningstar.com
- **Motherless**
- **MotherlessGroup**
- **Motorsport**: motorsport.com
- **MovieClips**
- **MovieFap**
@ -491,12 +523,14 @@
- **mva:course**: Microsoft Virtual Academy courses
- **Mwave**
- **MwaveMeetGreet**
- **MyChannels**
- **MySpace**
- **MySpace:album**
- **MySpass**
- **Myvi**
- **myvideo** (Currently broken)
- **MyVidster**
- **MyviEmbed**
- **MyVisionTV**
- **n-tv.de**
- **natgeo**
- **natgeo:episodeguide**
@ -505,8 +539,10 @@
- **NBA**
- **NBC**
- **NBCNews**
- **NBCOlympics**
- **nbcolympics**
- **nbcolympics:stream**
- **NBCSports**
- **NBCSportsStream**
- **NBCSportsVPlayer**
- **ndr**: NDR.de - Norddeutscher Rundfunk
- **ndr:embed**
@ -520,6 +556,7 @@
- **netease:program**: 网易云音乐 - 电台节目
- **netease:singer**: 网易云音乐 - 歌手
- **netease:song**: 网易云音乐
- **NetPlus**
- **Netzkino**
- **Newgrounds**
- **NewgroundsPlaylist**
@ -533,11 +570,9 @@
- **nfl.com**
- **NhkVod**
- **nhl.com**
- **nhl.com:news**: NHL news
- **nhl.com:videocenter**
- **nhl.com:videocenter:category**: NHL videocenter category
- **nick.com**
- **nick.de**
- **nickelodeon:br**
- **nickelodeonru**
- **nicknight**
- **niconico**: ニコニコ動画
@ -553,11 +588,10 @@
- **Normalboots**
- **NosVideo**
- **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz
- **NovaEmbed**
- **nowness**
- **nowness:playlist**
- **nowness:series**
- **NowTV** (Currently broken)
- **NowTVList**
- **nowvideo**: NowVideo
- **Noz**
- **npo**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
@ -570,7 +604,9 @@
- **NRKSkole**: NRK Skole
- **NRKTV**: NRK TV and NRK Radio
- **NRKTVDirekte**: NRK TV Direkte and NRK Radio Direkte
- **NRKTVEpisode**
- **NRKTVEpisodes**
- **NRKTVSeason**
- **NRKTVSeries**
- **ntv.ru**
- **Nuvid**
@ -597,21 +633,27 @@
- **orf:iptv**: iptv.ORF.at
- **orf:oe1**: Radio Österreich 1
- **orf:tvthek**: ORF TVthek
- **OsnatelTV**
- **PacktPub**
- **PacktPubCourse**
- **PandaTV**: 熊猫TV
- **pandora.tv**: 판도라TV
- **ParamountNetwork**
- **parliamentlive.tv**: UK parliament videos
- **Patreon**
- **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)
- **pcmag**
- **PearVideo**
- **PeerTube**
- **People**
- **PerformGroup**
- **periscope**: Periscope
- **periscope:user**: Periscope user videos
- **PhilharmonieDeParis**: Philharmonie de Paris
- **phoenix.de**
- **Photobucket**
- **Picarto**
- **PicartoVod**
- **Piksel**
- **Pinkbike**
- **Pladform**
@ -627,6 +669,7 @@
- **Pokemon**
- **PolskieRadio**
- **PolskieRadioCategory**
- **PopcornTV**
- **PornCom**
- **PornerBros**
- **PornFlip**
@ -642,6 +685,8 @@
- **PrimeShareTV**
- **PromptFile**
- **prosiebensat1**: ProSiebenSat.1 Digital
- **puhutv**
- **puhutv:serie**
- **Puls4**
- **Pyvideo**
- **qqmusic**: QQ音乐
@ -649,6 +694,9 @@
- **qqmusic:playlist**: QQ音乐 - 歌单
- **qqmusic:singer**: QQ音乐 - 歌手
- **qqmusic:toplist**: QQ音乐 - 排行榜
- **QuantumTV**
- **Quickline**
- **QuicklineLive**
- **R7**
- **R7Article**
- **radio.de**
@ -660,6 +708,9 @@
- **Rai**
- **RaiPlay**
- **RaiPlayLive**
- **RaiPlayPlaylist**
- **RayWenderlich**
- **RayWenderlichCourse**
- **RBMARadio**
- **RDS**: RDS.ca
- **RedBullTV**
@ -675,7 +726,6 @@
- **revision**
- **revision3:embed**
- **RICE**
- **RingTV**
- **RMCDecouverte**
- **RockstarGames**
- **RoosterTeeth**
@ -696,6 +746,7 @@
- **rtve.es:live**: RTVE.es live streams
- **rtve.es:television**
- **RTVNH**
- **RTVS**
- **Rudo**
- **RUHD**
- **RulePorn**
@ -711,7 +762,7 @@
- **safari**: safaribooksonline.com online video
- **safari:api**
- **safari:course**: safaribooksonline.com online courses
- **Sandia**: Sandia National Laboratories
- **SAKTV**
- **Sapo**: SAPO Vídeos
- **savefrom.net**
- **SBS**: sbs.com.au
@ -724,8 +775,12 @@
- **SenateISVP**
- **SendtoNews**
- **ServingSys**
- **Servus**
- **Sexu**
- **SeznamZpravy**
- **SeznamZpravyArticle**
- **Shahid**
- **ShahidShow**
- **Shared**: shared.sx
- **ShowRoomLive**
- **Sina**
@ -734,6 +789,7 @@
- **skynewsarabia:video**
- **SkySports**
- **Slideshare**
- **SlidesLive**
- **Slutload**
- **smotri**: Smotri.com
- **smotri:broadcast**: Smotri.com broadcasts
@ -760,11 +816,11 @@
- **Spiegel**
- **Spiegel:Article**: Articles on spiegel.de
- **Spiegeltv**
- **Spike**
- **sport.francetvinfo.fr**
- **Sport5**
- **SportBoxEmbed**
- **SportDeutschland**
- **Sportschau**
- **SpringboardPlatform**
- **Sprout**
- **sr:mediathek**: Saarländischer Rundfunk
- **SRGSSR**
@ -777,9 +833,12 @@
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
- **StretchInternet**
- **SunPorno**
- **SVT**
- **SVTPage**
- **SVTPlay**: SVT Play and Öppet arkiv
- **SVTSeries**
- **SWRMediathek**
- **Syfy**
- **SztvHu**
@ -788,7 +847,7 @@
- **tagesschau:player**
- **Tass**
- **TastyTrade**
- **TBS** (Currently broken)
- **TBS**
- **TDSLifeway**
- **teachertube**: teachertube.com videos
- **teachertube:user:collection**: teachertube.com user and collection videos
@ -798,13 +857,17 @@
- **techtv.mit.edu**
- **ted**
- **Tele13**
- **Tele5**
- **TeleBruxelles**
- **Telecinco**: telecinco.es, cuatro.com and mediaset.es
- **Telegraaf**
- **TeleMB**
- **TeleQuebec**
- **TeleQuebecEmission**
- **TeleQuebecLive**
- **TeleTask**
- **Telewebion**
- **TennisTV**
- **TF1**
- **TFO**
- **TheIntercept**
@ -812,7 +875,6 @@
- **ThePlatform**
- **ThePlatformFeed**
- **TheScene**
- **TheSixtyOne**
- **TheStar**
- **TheSun**
- **TheWeatherChannel**
@ -858,11 +920,16 @@
- **tvigle**: Интернет-телевидение Tvigle.ru
- **tvland.com**
- **TVN24**
- **TVNet**
- **TVNoe**
- **TVNow**
- **TVNowList**
- **TVNowShow**
- **tvp**: Telewizja Polska
- **tvp:embed**: Telewizja Polska
- **tvp:series**
- **TVPlayer**
- **TVPlayHome**
- **Tweakers**
- **twitch:chapter**
- **twitch:clips**
@ -880,8 +947,11 @@
- **udemy**
- **udemy:course**
- **UDNEmbed**: 聯合影音
- **UFCTV**
- **UKTVPlay**
- **umg:de**: Universal Music Deutschland
- **Unistra**
- **Unity**
- **uol.com.br**
- **uplynk**
- **uplynk:preplay**
@ -909,7 +979,6 @@
- **vice**
- **vice:article**
- **vice:show**
- **Viceland**
- **Vidbit**
- **Viddler**
- **Videa**
@ -925,6 +994,7 @@
- **VideoPress**
- **videoweed**: VideoWeed
- **Vidio**
- **VidLii**
- **vidme**
- **vidme:user**
- **vidme:user:likes**
@ -949,6 +1019,7 @@
- **Vimple**: Vimple - one-click video hosting
- **Vine**
- **vine:user**
- **Viqeo**
- **Viu**
- **viu:ott**
- **viu:playlist**
@ -965,19 +1036,23 @@
- **VoiceRepublic**
- **Voot**
- **VoxMedia**
- **VoxMediaVolume**
- **Vporn**
- **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
- **Vrak**
- **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be
- **VrtNU**: VrtNU.be
- **vrv**
- **vrv:series**
- **VShare**
- **VTXTV**
- **vube**: Vube.com
- **VuClip**
- **VVVVID**
- **VyboryMos**
- **Vzaar**
- **Walla**
- **WalyTV**
- **washingtonpost**
- **washingtonpost:article**
- **wat.tv**
@ -985,10 +1060,14 @@
- **WatchIndianPorn**: Watch Indian Porn
- **WDR**
- **wdr:mobile**
- **WDRElefant**
- **WDRPage**
- **Webcaster**
- **WebcasterFeed**
- **WebOfStories**
- **WebOfStoriesPlaylist**
- **Weibo**
- **WeiboMobile**
- **WeiqiTV**: WQTV
- **wholecloud**: WholeCloud
- **Wimp**
@ -1008,6 +1087,8 @@
- **xiami:artist**: 虾米音乐 - 歌手
- **xiami:collection**: 虾米音乐 - 精选集
- **xiami:song**: 虾米音乐
- **ximalaya**: 喜马拉雅FM
- **ximalaya:album**: 喜马拉雅FM 专辑
- **XMinus**
- **XNXX**
- **Xstream**
@ -1021,13 +1102,18 @@
- **yandexmusic:album**: Яндекс.Музыка - Альбом
- **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
- **yandexmusic:track**: Яндекс.Музыка - Трек
- **YapFiles**
- **YesJapan**
- **yinyuetai:video**: 音悦Tai
- **Ynet**
- **YouJizz**
- **youku**: 优酷
- **youku:show**
- **YouNowChannel**
- **YouNowLive**
- **YouNowMoment**
- **YouPorn**
- **YourPorn**
- **YourUpload**
- **youtube**: YouTube.com
- **youtube:channel**: YouTube.com channels
@ -1040,13 +1126,14 @@
- **youtube:search**: YouTube.com searches
- **youtube:search:date**: YouTube.com searches, newest videos first
- **youtube:search_url**: YouTube.com search URLs
- **youtube:shared**
- **youtube:show**: YouTube.com (multi-season) shows
- **youtube:subscriptions**: YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)
- **youtube:user**: YouTube.com user videos (URL or "ytuser" keyword)
- **youtube:watchlater**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **Zapiks**
- **Zaq1**
- **Zattoo**
- **ZattooLive**
- **ZDF**
- **ZDFChannel**
- **zingmp3**: mp3.zing.vn

4
setup.cfg
View File

@ -2,5 +2,5 @@
universal = True
[flake8]
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git
ignore = E402,E501,E731
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git,venv
ignore = E402,E501,E731,E741

1
setup.py
View File

@ -109,6 +109,7 @@ setup(
author_email='ytdl@yt-dl.org',
maintainer='Sergey M.',
maintainer_email='dstftw@gmail.com',
license='Unlicense',
packages=[
'youtube_dl',
'youtube_dl.extractor', 'youtube_dl.downloader',

171
test/test_InfoExtractor.py
View File

@ -493,9 +493,20 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
_TEST_CASES = [
(
# https://github.com/rg3/youtube-dl/issues/13919
# Also tests duplicate representation ids, see
# https://github.com/rg3/youtube-dl/issues/15111
'float_duration',
'http://unknown/manifest.mpd',
[{
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'm4a',
'format_id': '318597',
'format_note': 'DASH audio',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'none',
'tbr': 61.587,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': '318597',
@ -562,7 +573,89 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
'width': 1920,
'height': 1080,
}]
),
), (
# https://github.com/rg3/youtube-dl/pull/14844
'urls_only',
'http://unknown/manifest.mpd',
[{
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_144p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 200,
'width': 256,
'height': 144,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_240p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 400,
'width': 424,
'height': 240,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_360p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 800,
'width': 640,
'height': 360,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_480p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 1200,
'width': 856,
'height': 480,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_576p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 1600,
'width': 1024,
'height': 576,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_720p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 2400,
'width': 1280,
'height': 720,
}, {
'manifest_url': 'http://unknown/manifest.mpd',
'ext': 'mp4',
'format_id': 'h264_aac_1080p_m4s',
'format_note': 'DASH video',
'protocol': 'http_dash_segments',
'acodec': 'mp4a.40.2',
'vcodec': 'avc3.42c01e',
'tbr': 4400,
'width': 1920,
'height': 1080,
}]
)
]
for mpd_file, mpd_url, expected_formats in _TEST_CASES:
@ -574,6 +667,82 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
self.ie._sort_formats(formats)
expect_value(self, formats, expected_formats, None)
def test_parse_f4m_formats(self):
_TEST_CASES = [
(
# https://github.com/rg3/youtube-dl/issues/14660
'custom_base_url',
'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m',
[{
'manifest_url': 'http://api.new.livestream.com/accounts/6115179/events/6764928/videos/144884262.f4m',
'ext': 'flv',
'format_id': '2148',
'protocol': 'f4m',
'tbr': 2148,
'width': 1280,
'height': 720,
}]
),
]
for f4m_file, f4m_url, expected_formats in _TEST_CASES:
with io.open('./test/testdata/f4m/%s.f4m' % f4m_file,
mode='r', encoding='utf-8') as f:
formats = self.ie._parse_f4m_formats(
compat_etree_fromstring(f.read().encode('utf-8')),
f4m_url, None)
self.ie._sort_formats(formats)
expect_value(self, formats, expected_formats, None)
def test_parse_xspf(self):
_TEST_CASES = [
(
'foo_xspf',
'https://example.org/src/foo_xspf.xspf',
[{
'id': 'foo_xspf',
'title': 'Pandemonium',
'description': 'Visit http://bigbrother404.bandcamp.com',
'duration': 202.416,
'formats': [{
'manifest_url': 'https://example.org/src/foo_xspf.xspf',
'url': 'https://example.org/src/cd1/track%201.mp3',
}],
}, {
'id': 'foo_xspf',
'title': 'Final Cartridge (Nichico Twelve Remix)',
'description': 'Visit http://bigbrother404.bandcamp.com',
'duration': 255.857,
'formats': [{
'manifest_url': 'https://example.org/src/foo_xspf.xspf',
'url': 'https://example.org/%E3%83%88%E3%83%A9%E3%83%83%E3%82%AF%E3%80%80%EF%BC%92.mp3',
}],
}, {
'id': 'foo_xspf',
'title': 'Rebuilding Nightingale',
'description': 'Visit http://bigbrother404.bandcamp.com',
'duration': 287.915,
'formats': [{
'manifest_url': 'https://example.org/src/foo_xspf.xspf',
'url': 'https://example.org/src/track3.mp3',
}, {
'manifest_url': 'https://example.org/src/foo_xspf.xspf',
'url': 'https://example.com/track3.mp3',
}]
}]
),
]
for xspf_file, xspf_url, expected_entries in _TEST_CASES:
with io.open('./test/testdata/xspf/%s.xspf' % xspf_file,
mode='r', encoding='utf-8') as f:
entries = self.ie._parse_xspf(
compat_etree_fromstring(f.read().encode('utf-8')),
xspf_file, xspf_url=xspf_url, xspf_base_url=xspf_url)
expect_value(self, entries, expected_entries, None)
for i in range(len(entries)):
expect_dict(self, entries[i], expected_entries[i])
if __name__ == '__main__':
unittest.main()

16
test/test_YoutubeDL.py
View File

@ -466,12 +466,18 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({}), 'bestvideo+bestaudio/best')
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo+bestaudio/best')
ydl = YDL({'outtmpl': '-'})
self.assertEqual(ydl._default_format_spec({}), 'best')
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo+bestaudio/best')
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best')
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
class TestYoutubeDL(unittest.TestCase):
@ -770,6 +776,12 @@ class TestYoutubeDL(unittest.TestCase):
result = get_ids({'playlist_items': '10'})
self.assertEqual(result, [])
result = get_ids({'playlist_items': '3-10'})
self.assertEqual(result, [3, 4])
result = get_ids({'playlist_items': '2-4,3-4,3'})
self.assertEqual(result, [2, 3, 4])
def test_urlopen_no_file_protocol(self):
# see https://github.com/rg3/youtube-dl/issues/8227
ydl = YDL()

4
test/test_download.py
View File

@ -92,8 +92,8 @@ class TestDownload(unittest.TestCase):
def generator(test_case, tname):
def test_template(self):
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])]
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])()
other_ies = [get_info_extractor(ie_key)() for ie_key in test_case.get('add_ie', [])]
is_playlist = any(k.startswith('playlist') for k in test_case)
test_cases = test_case.get(
'playlist', [] if is_playlist else [test_case])

125
test/test_downloader_http.py Normal file
View File

@ -0,0 +1,125 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import re
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import try_rm
from youtube_dl import YoutubeDL
from youtube_dl.compat import compat_http_server
from youtube_dl.downloader.http import HttpFD
from youtube_dl.utils import encodeFilename
import ssl
import threading
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
def http_server_port(httpd):
if os.name == 'java' and isinstance(httpd.socket, ssl.SSLSocket):
# In Jython SSLSocket is not a subclass of socket.socket
sock = httpd.socket.sock
else:
sock = httpd.socket
return sock.getsockname()[1]
TEST_SIZE = 10 * 1024
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
def log_message(self, format, *args):
pass
def send_content_range(self, total=None):
range_header = self.headers.get('Range')
start = end = None
if range_header:
mobj = re.search(r'^bytes=(\d+)-(\d+)', range_header)
if mobj:
start = int(mobj.group(1))
end = int(mobj.group(2))
valid_range = start is not None and end is not None
if valid_range:
content_range = 'bytes %d-%d' % (start, end)
if total:
content_range += '/%d' % total
self.send_header('Content-Range', content_range)
return (end - start + 1) if valid_range else total
def serve(self, range=True, content_length=True):
self.send_response(200)
self.send_header('Content-Type', 'video/mp4')
size = TEST_SIZE
if range:
size = self.send_content_range(TEST_SIZE)
if content_length:
self.send_header('Content-Length', size)
self.end_headers()
self.wfile.write(b'#' * size)
def do_GET(self):
if self.path == '/regular':
self.serve()
elif self.path == '/no-content-length':
self.serve(content_length=False)
elif self.path == '/no-range':
self.serve(range=False)
elif self.path == '/no-range-no-content-length':
self.serve(range=False, content_length=False)
else:
assert False
class FakeLogger(object):
def debug(self, msg):
pass
def warning(self, msg):
pass
def error(self, msg):
pass
class TestHttpFD(unittest.TestCase):
def setUp(self):
self.httpd = compat_http_server.HTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()
def download(self, params, ep):
params['logger'] = FakeLogger()
ydl = YoutubeDL(params)
downloader = HttpFD(ydl, params)
filename = 'testfile.mp4'
try_rm(encodeFilename(filename))
self.assertTrue(downloader.real_download(filename, {
'url': 'http://127.0.0.1:%d/%s' % (self.port, ep),
}))
self.assertEqual(os.path.getsize(encodeFilename(filename)), TEST_SIZE)
try_rm(encodeFilename(filename))
def download_all(self, params):
for ep in ('regular', 'no-content-length', 'no-range', 'no-range-no-content-length'):
self.download(params, ep)
def test_regular(self):
self.download_all({})
def test_chunked(self):
self.download_all({
'http_chunk_size': 1000,
})
if __name__ == '__main__':
unittest.main()

26
test/test_http.py
View File

@ -47,7 +47,7 @@ class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
self.end_headers()
return
new_url = 'http://localhost:%d/中文.html' % http_server_port(self.server)
new_url = 'http://127.0.0.1:%d/中文.html' % http_server_port(self.server)
self.send_response(302)
self.send_header(b'Location', new_url.encode('utf-8'))
self.end_headers()
@ -74,7 +74,7 @@ class FakeLogger(object):
class TestHTTP(unittest.TestCase):
def setUp(self):
self.httpd = compat_http_server.HTTPServer(
('localhost', 0), HTTPTestRequestHandler)
('127.0.0.1', 0), HTTPTestRequestHandler)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
@ -86,15 +86,15 @@ class TestHTTP(unittest.TestCase):
return
ydl = YoutubeDL({'logger': FakeLogger()})
r = ydl.extract_info('http://localhost:%d/302' % self.port)
self.assertEqual(r['entries'][0]['url'], 'http://localhost:%d/vid.mp4' % self.port)
r = ydl.extract_info('http://127.0.0.1:%d/302' % self.port)
self.assertEqual(r['entries'][0]['url'], 'http://127.0.0.1:%d/vid.mp4' % self.port)
class TestHTTPS(unittest.TestCase):
def setUp(self):
certfn = os.path.join(TEST_DIR, 'testcert.pem')
self.httpd = compat_http_server.HTTPServer(
('localhost', 0), HTTPTestRequestHandler)
('127.0.0.1', 0), HTTPTestRequestHandler)
self.httpd.socket = ssl.wrap_socket(
self.httpd.socket, certfile=certfn, server_side=True)
self.port = http_server_port(self.httpd)
@ -107,11 +107,11 @@ class TestHTTPS(unittest.TestCase):
ydl = YoutubeDL({'logger': FakeLogger()})
self.assertRaises(
Exception,
ydl.extract_info, 'https://localhost:%d/video.html' % self.port)
ydl.extract_info, 'https://127.0.0.1:%d/video.html' % self.port)
ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
r = ydl.extract_info('https://localhost:%d/video.html' % self.port)
self.assertEqual(r['entries'][0]['url'], 'https://localhost:%d/vid.mp4' % self.port)
r = ydl.extract_info('https://127.0.0.1:%d/video.html' % self.port)
self.assertEqual(r['entries'][0]['url'], 'https://127.0.0.1:%d/vid.mp4' % self.port)
def _build_proxy_handler(name):
@ -132,23 +132,23 @@ def _build_proxy_handler(name):
class TestProxy(unittest.TestCase):
def setUp(self):
self.proxy = compat_http_server.HTTPServer(
('localhost', 0), _build_proxy_handler('normal'))
('127.0.0.1', 0), _build_proxy_handler('normal'))
self.port = http_server_port(self.proxy)
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
self.proxy_thread.daemon = True
self.proxy_thread.start()
self.geo_proxy = compat_http_server.HTTPServer(
('localhost', 0), _build_proxy_handler('geo'))
('127.0.0.1', 0), _build_proxy_handler('geo'))
self.geo_port = http_server_port(self.geo_proxy)
self.geo_proxy_thread = threading.Thread(target=self.geo_proxy.serve_forever)
self.geo_proxy_thread.daemon = True
self.geo_proxy_thread.start()
def test_proxy(self):
geo_proxy = 'localhost:{0}'.format(self.geo_port)
geo_proxy = '127.0.0.1:{0}'.format(self.geo_port)
ydl = YoutubeDL({
'proxy': 'localhost:{0}'.format(self.port),
'proxy': '127.0.0.1:{0}'.format(self.port),
'geo_verification_proxy': geo_proxy,
})
url = 'http://foo.com/bar'
@ -162,7 +162,7 @@ class TestProxy(unittest.TestCase):
def test_proxy_with_idn(self):
ydl = YoutubeDL({
'proxy': 'localhost:{0}'.format(self.port),
'proxy': '127.0.0.1:{0}'.format(self.port),
})
url = 'http://中文.tw/'
response = ydl.urlopen(url).read().decode('utf-8')

4
test/test_subtitles.py
View File

@ -232,7 +232,7 @@ class TestNPOSubtitles(BaseTestSubtitles):
class TestMTVSubtitles(BaseTestSubtitles):
url = 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother'
url = 'http://www.cc.com/video-clips/p63lk0/adam-devine-s-house-party-chasing-white-swans'
IE = ComedyCentralIE
def getInfoDict(self):
@ -243,7 +243,7 @@ class TestMTVSubtitles(BaseTestSubtitles):
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'b9f6ca22a6acf597ec76f61749765e65')
self.assertEqual(md5(subtitles['en']), '78206b8d8a0cfa9da64dc026eea48961')
class TestNRKSubtitles(BaseTestSubtitles):

77
test/test_utils.py
View File

@ -42,6 +42,7 @@ from youtube_dl.utils import (
is_html,
js_to_json,
limit_length,
merge_dicts,
mimetype2ext,
month_by_name,
multipart_encode,
@ -53,10 +54,12 @@ from youtube_dl.utils import (
parse_filesize,
parse_count,
parse_iso8601,
parse_resolution,
pkcs1pad,
read_batch_urls,
sanitize_filename,
sanitize_path,
sanitize_url,
expand_path,
prepend_extension,
replace_extension,
@ -75,6 +78,7 @@ from youtube_dl.utils import (
uppercase_escape,
lowercase_escape,
url_basename,
url_or_none,
base_url,
urljoin,
urlencode_postdata,
@ -219,6 +223,12 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
def test_sanitize_url(self):
self.assertEqual(sanitize_url('//foo.bar'), 'http://foo.bar')
self.assertEqual(sanitize_url('httpss://foo.bar'), 'https://foo.bar')
self.assertEqual(sanitize_url('rmtps://foo.bar'), 'rtmps://foo.bar')
self.assertEqual(sanitize_url('https://foo.bar'), 'https://foo.bar')
def test_expand_path(self):
def env(var):
return '%{0}%'.format(var) if sys.platform == 'win32' else '${0}'.format(var)
@ -343,6 +353,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_timestamp('Feb 7, 2016 at 6:35 pm'), 1454870100)
self.assertEqual(unified_timestamp('2017-03-30T17:52:41Q'), 1490896361)
self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
def test_determine_ext(self):
self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
@ -350,6 +362,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(determine_ext('http://example.com/foo/bar.nonext/?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar/mp4?download', None), None)
self.assertEqual(determine_ext('http://example.com/foo/bar.m3u8//?download'), 'm3u8')
self.assertEqual(determine_ext('foobar', None), None)
def test_find_xpath_attr(self):
testxml = '''<root>
@ -495,6 +508,16 @@ class TestUtil(unittest.TestCase):
self.assertEqual(urljoin('http://foo.de/', ['foobar']), None)
self.assertEqual(urljoin('http://foo.de/a/b/c.txt', '.././../d.txt'), 'http://foo.de/d.txt')
def test_url_or_none(self):
self.assertEqual(url_or_none(None), None)
self.assertEqual(url_or_none(''), None)
self.assertEqual(url_or_none('foo'), None)
self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
self.assertEqual(url_or_none('https://foo.de'), 'https://foo.de')
self.assertEqual(url_or_none('http$://foo.de'), None)
self.assertEqual(url_or_none('http://foo.de'), 'http://foo.de')
self.assertEqual(url_or_none('//foo.de'), '//foo.de')
def test_parse_age_limit(self):
self.assertEqual(parse_age_limit(None), None)
self.assertEqual(parse_age_limit(False), None)
@ -508,6 +531,8 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_age_limit('PG-13'), 13)
self.assertEqual(parse_age_limit('TV-14'), 14)
self.assertEqual(parse_age_limit('TV-MA'), 17)
self.assertEqual(parse_age_limit('TV14'), 14)
self.assertEqual(parse_age_limit('TV_G'), 0)
def test_parse_duration(self):
self.assertEqual(parse_duration(None), None)
@ -540,6 +565,7 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_duration('87 Min.'), 5220)
self.assertEqual(parse_duration('PT1H0.040S'), 3600.04)
self.assertEqual(parse_duration('PT00H03M30SZ'), 210)
self.assertEqual(parse_duration('P0Y0M0DT0H4M20.880S'), 260.88)
def test_fix_xml_ampersands(self):
self.assertEqual(
@ -658,6 +684,17 @@ class TestUtil(unittest.TestCase):
self.assertEqual(dict_get(d, ('b', 'c', key, )), None)
self.assertEqual(dict_get(d, ('b', 'c', key, ), skip_false_values=False), false_value)
def test_merge_dicts(self):
self.assertEqual(merge_dicts({'a': 1}, {'b': 2}), {'a': 1, 'b': 2})
self.assertEqual(merge_dicts({'a': 1}, {'a': 2}), {'a': 1})
self.assertEqual(merge_dicts({'a': 1}, {'a': None}), {'a': 1})
self.assertEqual(merge_dicts({'a': 1}, {'a': ''}), {'a': 1})
self.assertEqual(merge_dicts({'a': 1}, {}), {'a': 1})
self.assertEqual(merge_dicts({'a': None}, {'a': 1}), {'a': 1})
self.assertEqual(merge_dicts({'a': ''}, {'a': 1}), {'a': ''})
self.assertEqual(merge_dicts({'a': ''}, {'a': 'abc'}), {'a': 'abc'})
self.assertEqual(merge_dicts({'a': None}, {'a': ''}, {'a': 'abc'}), {'a': 'abc'})
def test_encode_compat_str(self):
self.assertEqual(encode_compat_str(b'\xd1\x82\xd0\xb5\xd1\x81\xd1\x82', 'utf-8'), 'тест')
self.assertEqual(encode_compat_str('тест', 'utf-8'), 'тест')
@ -691,6 +728,10 @@ class TestUtil(unittest.TestCase):
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
stripped = strip_jsonp('({"status": "success"});')
d = json.loads(stripped)
self.assertEqual(d, {'status': 'success'})
def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@ -744,6 +785,10 @@ class TestUtil(unittest.TestCase):
'vcodec': 'h264',
'acodec': 'aac',
})
self.assertEqual(parse_codecs('av01.0.05M.08'), {
'vcodec': 'av01.0.05M.08',
'acodec': 'none',
})
def test_escape_rfc3986(self):
reserved = "!*'();:@&=+$,/?#[]"
@ -812,6 +857,9 @@ class TestUtil(unittest.TestCase):
inp = '''{"duration": "00:01:07"}'''
self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''')
inp = '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}'''
self.assertEqual(js_to_json(inp), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''')
def test_js_to_json_edgecases(self):
on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
@ -883,6 +931,13 @@ class TestUtil(unittest.TestCase):
on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}')
self.assertEqual(json.loads(on), {'42': 42})
on = js_to_json('{42:4.2e1}')
self.assertEqual(json.loads(on), {'42': 42.0})
def test_js_to_json_malformed(self):
self.assertEqual(js_to_json('42a1'), '42"a1"')
self.assertEqual(js_to_json('42a-1'), '42"a"-1')
def test_extract_attributes(self):
self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
self.assertEqual(extract_attributes("<e x='y'>"), {'x': 'y'})
@ -963,6 +1018,16 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_count('1.1kk '), 1100000)
self.assertEqual(parse_count('1.1kk views'), 1100000)
def test_parse_resolution(self):
self.assertEqual(parse_resolution(None), {})
self.assertEqual(parse_resolution(''), {})
self.assertEqual(parse_resolution('1920x1080'), {'width': 1920, 'height': 1080})
self.assertEqual(parse_resolution('1920×1080'), {'width': 1920, 'height': 1080})
self.assertEqual(parse_resolution('1920 x 1080'), {'width': 1920, 'height': 1080})
self.assertEqual(parse_resolution('720p'), {'height': 720})
self.assertEqual(parse_resolution('4k'), {'height': 2160})
self.assertEqual(parse_resolution('8K'), {'height': 4320})
def test_version_tuple(self):
self.assertEqual(version_tuple('1'), (1,))
self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
@ -1041,6 +1106,18 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 10}))
self.assertTrue(match_str('is_live', {'is_live': True}))
self.assertFalse(match_str('is_live', {'is_live': False}))
self.assertFalse(match_str('is_live', {'is_live': None}))
self.assertFalse(match_str('is_live', {}))
self.assertFalse(match_str('!is_live', {'is_live': True}))
self.assertTrue(match_str('!is_live', {'is_live': False}))
self.assertTrue(match_str('!is_live', {'is_live': None}))
self.assertTrue(match_str('!is_live', {}))
self.assertTrue(match_str('title', {'title': 'abc'}))
self.assertTrue(match_str('title', {'title': ''}))
self.assertFalse(match_str('!title', {'title': 'abc'}))
self.assertFalse(match_str('!title', {'title': ''}))
def test_parse_dfxp_time_expr(self):
self.assertEqual(parse_dfxp_time_expr(None), None)

2
test/test_youtube_lists.py
View File

@ -61,7 +61,7 @@ class TestYoutubeLists(unittest.TestCase):
dl = FakeYDL()
dl.params['extract_flat'] = True
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
result = ie.extract('https://www.youtube.com/playlist?list=PL-KKIb8rvtMSrAO9YFbeM6UQrAqoFTUWv')
self.assertIsPlaylist(result)
for entry in result['entries']:
self.assertTrue(entry.get('title'))

10
test/testdata/f4m/custom_base_url.f4m vendored Normal file
View File

@ -0,0 +1,10 @@
<?xml version="1.0" encoding="UTF-8"?>
<manifest xmlns="http://ns.adobe.com/f4m/1.0">
<streamType>recorded</streamType>
<baseURL>http://vod.livestream.com/events/0000000000673980/</baseURL>
<duration>269.293</duration>
<bootstrapInfo profile="named" id="bootstrap_1">AAAAm2Fic3QAAAAAAAAAAQAAAAPoAAAAAAAEG+0AAAAAAAAAAAAAAAAAAQAAABlhc3J0AAAAAAAAAAABAAAAAQAAAC4BAAAAVmFmcnQAAAAAAAAD6AAAAAAEAAAAAQAAAAAAAAAAAAAXcAAAAC0AAAAAAAQHQAAAE5UAAAAuAAAAAAAEGtUAAAEYAAAAAAAAAAAAAAAAAAAAAAA=</bootstrapInfo>
<media url="b90f532f-b0f6-4f4e-8289-706d490b2fd8_2292" bootstrapInfoId="bootstrap_1" bitrate="2148" width="1280" height="720" videoCodec="avc1.4d401f" audioCodec="mp4a.40.2">
<metadata>AgAKb25NZXRhRGF0YQgAAAAIAAhkdXJhdGlvbgBAcNSwIMSbpgAFd2lkdGgAQJQAAAAAAAAABmhlaWdodABAhoAAAAAAAAAJZnJhbWVyYXRlAEA4/7DoLwW3AA12aWRlb2RhdGFyYXRlAECe1DLgjcobAAx2aWRlb2NvZGVjaWQAQBwAAAAAAAAADWF1ZGlvZGF0YXJhdGUAQGSimlvaPKQADGF1ZGlvY29kZWNpZABAJAAAAAAAAAAACQ==</metadata>
</media>
</manifest>

218
test/testdata/mpd/urls_only.mpd vendored Normal file
View File

@ -0,0 +1,218 @@
<?xml version="1.0" ?>
<MPD maxSegmentDuration="PT0H0M10.000S" mediaPresentationDuration="PT0H4M1.728S" minBufferTime="PT1.500S" profiles="urn:mpeg:dash:profile:isoff-main:2011" type="static" xmlns="urn:mpeg:dash:schema:mpd:2011">
<Period duration="PT0H4M1.728S">
<AdaptationSet bitstreamSwitching="true" lang="und" maxHeight="1080" maxWidth="1920" par="16:9" segmentAlignment="true">
<ContentComponent contentType="video" id="1"/>
<Representation audioSamplingRate="44100" bandwidth="200000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="144" id="h264_aac_144p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="256">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_144p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="240" id="h264_aac_240p_m4s" mimeType="video/mp4" sar="160:159" startWithSAP="1" width="424">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_240p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="800000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="360" id="h264_aac_360p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="640">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_360p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="1200000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="480" id="h264_aac_480p_m4s" mimeType="video/mp4" sar="320:321" startWithSAP="1" width="856">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_480p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="1600000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="576" id="h264_aac_576p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1024">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_576p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="2400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="720" id="h264_aac_720p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1280">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_720p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
<Representation audioSamplingRate="44100" bandwidth="4400000" codecs="avc3.42c01e,mp4a.40.2" frameRate="25" height="1080" id="h264_aac_1080p_m4s" mimeType="video/mp4" sar="1:1" startWithSAP="1" width="1920">
<SegmentList duration="10000" timescale="1000">
<Initialization sourceURL="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/init/432f65a0.mp4"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/0/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/1/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/2/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/3/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/4/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/5/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/6/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/7/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/8/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/9/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/10/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/11/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/12/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/13/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/14/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/15/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/16/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/17/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/18/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/19/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/20/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/21/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/22/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/23/432f65a0.m4s"/>
<SegmentURL media="../vd_5999c902ea707c67d8e267a9_1503250723/h264_aac_1080p_m4s/24/432f65a0.m4s"/>
</SegmentList>
</Representation>
</AdaptationSet>
</Period>
</MPD>

34
test/testdata/xspf/foo_xspf.xspf vendored Normal file
View File

@ -0,0 +1,34 @@
<?xml version="1.0" encoding="UTF-8"?>
<playlist version="1" xmlns="http://xspf.org/ns/0/">
<date>2018-03-09T18:01:43Z</date>
<trackList>
<track>
<location>cd1/track%201.mp3</location>
<title>Pandemonium</title>
<creator>Foilverb</creator>
<annotation>Visit http://bigbrother404.bandcamp.com</annotation>
<album>Pandemonium EP</album>
<trackNum>1</trackNum>
<duration>202416</duration>
</track>
<track>
<location>../%E3%83%88%E3%83%A9%E3%83%83%E3%82%AF%E3%80%80%EF%BC%92.mp3</location>
<title>Final Cartridge (Nichico Twelve Remix)</title>
<annotation>Visit http://bigbrother404.bandcamp.com</annotation>
<creator>Foilverb</creator>
<album>Pandemonium EP</album>
<trackNum>2</trackNum>
<duration>255857</duration>
</track>
<track>
<location>track3.mp3</location>
<location>https://example.com/track3.mp3</location>
<title>Rebuilding Nightingale</title>
<annotation>Visit http://bigbrother404.bandcamp.com</annotation>
<creator>Foilverb</creator>
<album>Pandemonium EP</album>
<trackNum>3</trackNum>
<duration>287915</duration>
</track>
</trackList>
</playlist>

135
youtube_dl/YoutubeDL.py
View File

@ -65,6 +65,7 @@ from .utils import (
locked_file,
make_HTTPS_handler,
MaxDownloadsReached,
orderedSet,
PagedList,
parse_filesize,
PerRequestProxyHandler,
@ -89,10 +90,10 @@ from .utils import (
write_string,
YoutubeDLCookieProcessor,
YoutubeDLHandler,
PhantomJSwrapper,
)
from .cache import Cache
from .extractor import get_info_extractor, gen_extractor_classes, _LAZY_LOADER
from .extractor.openload import PhantomJSwrapper
from .downloader import get_suitable_downloader
from .downloader.rtmp import rtmpdump_version
from .postprocessor import (
@ -210,7 +211,7 @@ class YoutubeDL(object):
At the moment, this is only supported by YouTube.
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. (Experimental)
on geo-restricted sites.
socket_timeout: Time to wait for unresponsive hosts, in seconds
bidi_workaround: Work around buggy terminals without bidirectional text
support, using fridibi
@ -258,7 +259,7 @@ class YoutubeDL(object):
- "warn": only emit a warning
- "detect_or_warn": check whether we can do anything
about it, warn otherwise (default)
source_address: (Experimental) Client-side IP address to bind to.
source_address: Client-side IP address to bind to.
call_home: Boolean, true iff we are allowed to contact the
youtube-dl servers for debugging.
sleep_interval: Number of seconds to sleep before each download when
@ -280,11 +281,14 @@ class YoutubeDL(object):
match_filter_func in utils.py is one example for this.
no_color: Do not emit color codes in output.
geo_bypass: Bypass geographic restriction via faking X-Forwarded-For
HTTP header (experimental)
HTTP header
geo_bypass_country:
Two-letter ISO 3166-2 country code that will be used for
explicit geographic restriction bypassing via faking
X-Forwarded-For HTTP header (experimental)
X-Forwarded-For HTTP header
geo_bypass_ip_block:
IP range in CIDR notation that will be used similarly to
geo_bypass_country
The following options determine which downloader is picked:
external_downloader: Executable of the external downloader to call.
@ -297,13 +301,20 @@ class YoutubeDL(object):
the downloader (see youtube_dl/downloader/common.py):
nopart, updatetime, buffersize, ratelimit, min_filesize, max_filesize, test,
noresizebuffer, retries, continuedl, noprogress, consoletitle,
xattr_set_filesize, external_downloader_args, hls_use_mpegts.
xattr_set_filesize, external_downloader_args, hls_use_mpegts,
http_chunk_size.
The following options are used by the post processors:
prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available,
otherwise prefer avconv.
prefer_ffmpeg: If False, use avconv instead of ffmpeg if both are available,
otherwise prefer ffmpeg.
postprocessor_args: A list of additional command-line arguments for the
postprocessor.
The following options are used by the Youtube extractor:
youtube_include_dash_manifest: If True (default), DASH manifests and related
data will be downloaded and processed by extractor.
You can reduce network I/O by disabling it if you don't
care about DASH.
"""
_NUMERIC_FIELDS = set((
@ -524,6 +535,8 @@ class YoutubeDL(object):
def save_console_title(self):
if not self.params.get('consoletitle', False):
return
if self.params.get('simulate', False):
return
if compat_os_name != 'nt' and 'TERM' in os.environ:
# Save the title on stack
self._write_string('\033[22;0t', self._screen_file)
@ -531,6 +544,8 @@ class YoutubeDL(object):
def restore_console_title(self):
if not self.params.get('consoletitle', False):
return
if self.params.get('simulate', False):
return
if compat_os_name != 'nt' and 'TERM' in os.environ:
# Restore the title from stack
self._write_string('\033[23;0t', self._screen_file)
@ -902,15 +917,25 @@ class YoutubeDL(object):
yield int(item)
else:
yield int(string_segment)
playlistitems = iter_playlistitems(playlistitems_str)
playlistitems = orderedSet(iter_playlistitems(playlistitems_str))
ie_entries = ie_result['entries']
def make_playlistitems_entries(list_ie_entries):
num_entries = len(list_ie_entries)
return [
list_ie_entries[i - 1] for i in playlistitems
if -num_entries <= i - 1 < num_entries]
def report_download(num_entries):
self.to_screen(
'[%s] playlist %s: Downloading %d videos' %
(ie_result['extractor'], playlist, num_entries))
if isinstance(ie_entries, list):
n_all_entries = len(ie_entries)
if playlistitems:
entries = [
ie_entries[i - 1] for i in playlistitems
if -n_all_entries <= i - 1 < n_all_entries]
entries = make_playlistitems_entries(ie_entries)
else:
entries = ie_entries[playliststart:playlistend]
n_entries = len(entries)
@ -928,20 +953,16 @@ class YoutubeDL(object):
entries = ie_entries.getslice(
playliststart, playlistend)
n_entries = len(entries)
self.to_screen(
'[%s] playlist %s: Downloading %d videos' %
(ie_result['extractor'], playlist, n_entries))
report_download(n_entries)
else: # iterable
if playlistitems:
entry_list = list(ie_entries)
entries = [entry_list[i - 1] for i in playlistitems]
entries = make_playlistitems_entries(list(itertools.islice(
ie_entries, 0, max(playlistitems))))
else:
entries = list(itertools.islice(
ie_entries, playliststart, playlistend))
n_entries = len(entries)
self.to_screen(
'[%s] playlist %s: Downloading %d videos' %
(ie_result['extractor'], playlist, n_entries))
report_download(n_entries)
if self.params.get('playlistreverse', False):
entries = entries[::-1]
@ -962,6 +983,8 @@ class YoutubeDL(object):
'playlist': playlist,
'playlist_id': ie_result.get('id'),
'playlist_title': ie_result.get('title'),
'playlist_uploader': ie_result.get('uploader'),
'playlist_uploader_id': ie_result.get('uploader_id'),
'playlist_index': i + playliststart,
'extractor': ie_result['extractor'],
'webpage_url': ie_result['webpage_url'],
@ -1017,7 +1040,7 @@ class YoutubeDL(object):
'!=': operator.ne,
}
operator_rex = re.compile(r'''(?x)\s*
(?P<key>width|height|tbr|abr|vbr|asr|filesize|fps)
(?P<key>width|height|tbr|abr|vbr|asr|filesize|filesize_approx|fps)
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
(?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)
$
@ -1066,22 +1089,27 @@ class YoutubeDL(object):
return _filter
def _default_format_spec(self, info_dict, download=True):
req_format_list = []
def can_have_partial_formats():
if self.params.get('simulate', False):
return True
if not download:
return True
if self.params.get('outtmpl', DEFAULT_OUTTMPL) == '-':
return False
if info_dict.get('is_live'):
return False
def can_merge():
merger = FFmpegMergerPP(self)
return merger.available and merger.can_merge()
if can_have_partial_formats():
req_format_list.append('bestvideo+bestaudio')
req_format_list.append('best')
def prefer_best():
if self.params.get('simulate', False):
return False
if not download:
return False
if self.params.get('outtmpl', DEFAULT_OUTTMPL) == '-':
return True
if info_dict.get('is_live'):
return True
if not can_merge():
return True
return False
req_format_list = ['bestvideo+bestaudio', 'best']
if prefer_best():
req_format_list.reverse()
return '/'.join(req_format_list)
def build_format_selector(self, format_spec):
@ -1454,23 +1482,28 @@ 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])
for cc_kind in ('subtitles', 'automatic_captions'):
cc = info_dict.get(cc_kind)
if cc:
for _, subtitle in cc.items():
for subtitle_format in subtitle:
if subtitle_format.get('url'):
subtitle_format['url'] = sanitize_url(subtitle_format['url'])
if subtitle_format.get('ext') is None:
subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
automatic_captions = info_dict.get('automatic_captions')
subtitles = info_dict.get('subtitles')
if subtitles:
for _, subtitle in subtitles.items():
for subtitle_format in subtitle:
if subtitle_format.get('url'):
subtitle_format['url'] = sanitize_url(subtitle_format['url'])
if subtitle_format.get('ext') is None:
subtitle_format['ext'] = determine_ext(subtitle_format['url']).lower()
if self.params.get('listsubtitles', False):
if 'automatic_captions' in info_dict:
self.list_subtitles(info_dict['id'], info_dict.get('automatic_captions'), 'automatic captions')
self.list_subtitles(
info_dict['id'], automatic_captions, 'automatic captions')
self.list_subtitles(info_dict['id'], subtitles, 'subtitles')
return
info_dict['requested_subtitles'] = self.process_subtitles(
info_dict['id'], subtitles,
info_dict.get('automatic_captions'))
info_dict['id'], subtitles, automatic_captions)
# We now pick which formats have to be downloaded
if info_dict.get('formats') is None:
@ -1828,7 +1861,7 @@ class YoutubeDL(object):
def compatible_formats(formats):
video, audio = formats
# Check extension
video_ext, audio_ext = audio.get('ext'), video.get('ext')
video_ext, audio_ext = video.get('ext'), audio.get('ext')
if video_ext and audio_ext:
COMPATIBLE_EXTS = (
('mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'ismv', 'isma'),
@ -2213,8 +2246,16 @@ class YoutubeDL(object):
sys.exc_clear()
except Exception:
pass
self._write_string('[debug] Python version %s - %s\n' % (
platform.python_version(), platform_name()))
def python_implementation():
impl_name = platform.python_implementation()
if impl_name == 'PyPy' and hasattr(sys, 'pypy_version_info'):
return impl_name + ' version %d.%d.%d' % sys.pypy_version_info[:3]
return impl_name
self._write_string('[debug] Python version %s (%s) - %s\n' % (
platform.python_version(), python_implementation(),
platform_name()))
exe_versions = FFmpegPostProcessor.get_versions(self)
exe_versions['rtmpdump'] = rtmpdump_version()

9
youtube_dl/__init__.py
View File

@ -191,6 +191,11 @@ def _real_main(argv=None):
if numeric_buffersize is None:
parser.error('invalid buffer size specified')
opts.buffersize = numeric_buffersize
if opts.http_chunk_size is not None:
numeric_chunksize = FileDownloader.parse_bytes(opts.http_chunk_size)
if not numeric_chunksize:
parser.error('invalid http chunk size specified')
opts.http_chunk_size = numeric_chunksize
if opts.playliststart <= 0:
raise ValueError('Playlist start must be positive')
if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
@ -206,7 +211,7 @@ def _real_main(argv=None):
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']:
parser.error('invalid video recode format specified')
if opts.convertsubtitles is not None:
if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
parser.error('invalid subtitle format specified')
if opts.date is not None:
@ -346,6 +351,7 @@ def _real_main(argv=None):
'keep_fragments': opts.keep_fragments,
'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer,
'http_chunk_size': opts.http_chunk_size,
'continuedl': opts.continue_dl,
'noprogress': opts.noprogress,
'progress_with_newline': opts.progress_with_newline,
@ -424,6 +430,7 @@ def _real_main(argv=None):
'config_location': opts.config_location,
'geo_bypass': opts.geo_bypass,
'geo_bypass_country': opts.geo_bypass_country,
'geo_bypass_ip_block': opts.geo_bypass_ip_block,
# just for deprecation check
'autonumber': opts.autonumber if opts.autonumber is True else None,
'usetitle': opts.usetitle if opts.usetitle is True else None,

4
youtube_dl/aes.py
View File

@ -1,8 +1,8 @@
from __future__ import unicode_literals
import base64
from math import ceil
from .compat import compat_b64decode
from .utils import bytes_to_intlist, intlist_to_bytes
BLOCK_SIZE_BYTES = 16
@ -180,7 +180,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
"""
NONCE_LENGTH_BYTES = 8
data = bytes_to_intlist(base64.b64decode(data.encode('utf-8')))
data = bytes_to_intlist(compat_b64decode(data))
password = bytes_to_intlist(password.encode('utf-8'))
key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password))

66
youtube_dl/compat.py
View File

@ -1,13 +1,17 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import binascii
import collections
import ctypes
import email
import getpass
import io
import itertools
import optparse
import os
import platform
import re
import shlex
import shutil
@ -15,7 +19,6 @@ import socket
import struct
import subprocess
import sys
import itertools
import xml.etree.ElementTree
@ -2784,6 +2787,12 @@ except NameError: # Python 3
compat_numeric_types = (int, float, complex)
try:
compat_integer_types = (int, long)
except NameError: # Python 3
compat_integer_types = (int, )
if sys.version_info < (2, 7):
def compat_socket_create_connection(address, timeout, source_address=None):
host, port = address
@ -2894,19 +2903,72 @@ except TypeError:
if isinstance(spec, compat_str):
spec = spec.encode('ascii')
return struct.unpack(spec, *args)
class compat_Struct(struct.Struct):
def __init__(self, fmt):
if isinstance(fmt, compat_str):
fmt = fmt.encode('ascii')
super(compat_Struct, self).__init__(fmt)
else:
compat_struct_pack = struct.pack
compat_struct_unpack = struct.unpack
if platform.python_implementation() == 'IronPython' and sys.version_info < (2, 7, 8):
class compat_Struct(struct.Struct):
def unpack(self, string):
if not isinstance(string, buffer): # noqa: F821
string = buffer(string) # noqa: F821
return super(compat_Struct, self).unpack(string)
else:
compat_Struct = struct.Struct
try:
from future_builtins import zip as compat_zip
except ImportError: # not 2.6+ or is 3.x
try:
from itertools import izip as compat_zip # < 2.5 or 3.x
except ImportError:
compat_zip = zip
if sys.version_info < (3, 3):
def compat_b64decode(s, *args, **kwargs):
if isinstance(s, compat_str):
s = s.encode('ascii')
return base64.b64decode(s, *args, **kwargs)
else:
compat_b64decode = base64.b64decode
if platform.python_implementation() == 'PyPy' and sys.pypy_version_info < (5, 4, 0):
# PyPy2 prior to version 5.4.0 expects byte strings as Windows function
# names, see the original PyPy issue [1] and the youtube-dl one [2].
# 1. https://bitbucket.org/pypy/pypy/issues/2360/windows-ctypescdll-typeerror-function-name
# 2. https://github.com/rg3/youtube-dl/pull/4392
def compat_ctypes_WINFUNCTYPE(*args, **kwargs):
real = ctypes.WINFUNCTYPE(*args, **kwargs)
def resf(tpl, *args, **kwargs):
funcname, dll = tpl
return real((str(funcname), dll), *args, **kwargs)
return resf
else:
def compat_ctypes_WINFUNCTYPE(*args, **kwargs):
return ctypes.WINFUNCTYPE(*args, **kwargs)
__all__ = [
'compat_HTMLParseError',
'compat_HTMLParser',
'compat_HTTPError',
'compat_Struct',
'compat_b64decode',
'compat_basestring',
'compat_chr',
'compat_cookiejar',
'compat_cookies',
'compat_ctypes_WINFUNCTYPE',
'compat_etree_fromstring',
'compat_etree_register_namespace',
'compat_expanduser',
@ -2918,6 +2980,7 @@ __all__ = [
'compat_http_client',
'compat_http_server',
'compat_input',
'compat_integer_types',
'compat_itertools_count',
'compat_kwargs',
'compat_numeric_types',
@ -2948,5 +3011,6 @@ __all__ = [
'compat_urlretrieve',
'compat_xml_parse_error',
'compat_xpath',
'compat_zip',
'workaround_optparse_bug9161',
]

13
youtube_dl/downloader/common.py
View File

@ -45,10 +45,12 @@ class FileDownloader(object):
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
(experimental)
external_downloader_args: A list of additional command-line arguments for the
external downloader.
hls_use_mpegts: Use the mpegts container for HLS videos.
http_chunk_size: Size of a chunk for chunk-based HTTP downloading. May be
useful for bypassing bandwidth throttling imposed by
a webserver (experimental)
Subclasses of this one must re-define the real_download method.
"""
@ -246,12 +248,13 @@ class FileDownloader(object):
if self.params.get('noprogress', False):
self.to_screen('[download] Download completed')
else:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
msg_template = '100%%'
if s.get('total_bytes') is not None:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
msg_template += ' of %(_total_bytes_str)s'
if s.get('elapsed') is not None:
s['_elapsed_str'] = self.format_seconds(s['elapsed'])
msg_template = '100%% of %(_total_bytes_str)s in %(_elapsed_str)s'
else:
msg_template = '100%% of %(_total_bytes_str)s'
msg_template += ' in %(_elapsed_str)s'
self._report_progress_status(
msg_template % s, is_last_line=True)

13
youtube_dl/downloader/dash.py
View File

@ -2,7 +2,10 @@ from __future__ import unicode_literals
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..utils import urljoin
from ..utils import (
DownloadError,
urljoin,
)
class DashSegmentsFD(FragmentFD):
@ -57,6 +60,14 @@ class DashSegmentsFD(FragmentFD):
count += 1
if count <= fragment_retries:
self.report_retry_fragment(err, frag_index, count, fragment_retries)
except DownloadError:
# Don't retry fragment if error occurred during HTTP downloading
# itself since it has own retry settings
if not fatal:
self.report_skip_fragment(frag_index)
break
raise
if count > fragment_retries:
if not fatal:
self.report_skip_fragment(frag_index)

23
youtube_dl/downloader/external.py
View File

@ -1,9 +1,10 @@
from __future__ import unicode_literals
import os.path
import re
import subprocess
import sys
import re
import time
from .common import FileDownloader
from ..compat import (
@ -30,6 +31,7 @@ class ExternalFD(FileDownloader):
tmpfilename = self.temp_name(filename)
try:
started = time.time()
retval = self._call_downloader(tmpfilename, info_dict)
except KeyboardInterrupt:
if not info_dict.get('is_live'):
@ -41,15 +43,20 @@ class ExternalFD(FileDownloader):
self.to_screen('[%s] Interrupted by user' % self.get_basename())
if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
status = {
'filename': filename,
'status': 'finished',
})
'elapsed': time.time() - started,
}
if filename != '-':
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('\r[%s] Downloaded %s bytes' % (self.get_basename(), fsize))
self.try_rename(tmpfilename, filename)
status.update({
'downloaded_bytes': fsize,
'total_bytes': fsize,
})
self._hook_progress(status)
return True
else:
self.to_stderr('\n')

31
youtube_dl/downloader/f4m.py
View File

@ -1,12 +1,12 @@
from __future__ import division, unicode_literals
import base64
import io
import itertools
import time
from .fragment import FragmentFD
from ..compat import (
compat_b64decode,
compat_etree_fromstring,
compat_urlparse,
compat_urllib_error,
@ -243,8 +243,17 @@ def remove_encrypted_media(media):
media))
def _add_ns(prop):
return '{http://ns.adobe.com/f4m/1.0}%s' % prop
def _add_ns(prop, ver=1):
return '{http://ns.adobe.com/f4m/%d.0}%s' % (ver, prop)
def get_base_url(manifest):
base_url = xpath_text(
manifest, [_add_ns('baseURL'), _add_ns('baseURL', 2)],
'base URL', default=None)
if base_url:
base_url = base_url.strip()
return base_url
class F4mFD(FragmentFD):
@ -303,7 +312,7 @@ class F4mFD(FragmentFD):
boot_info = self._get_bootstrap_from_url(bootstrap_url)
else:
bootstrap_url = None
bootstrap = base64.b64decode(node.text.encode('ascii'))
bootstrap = compat_b64decode(node.text)
boot_info = read_bootstrap_info(bootstrap)
return boot_info, bootstrap_url
@ -330,17 +339,17 @@ class F4mFD(FragmentFD):
rate, media = list(filter(
lambda f: int(f[0]) == requested_bitrate, formats))[0]
base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
# Prefer baseURL for relative URLs as per 11.2 of F4M 3.0 spec.
man_base_url = get_base_url(doc) or man_url
base_url = compat_urlparse.urljoin(man_base_url, media.attrib['url'])
bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
# From Adobe F4M 3.0 spec:
# The <baseURL> element SHALL be the base URL for all relative
# (HTTP-based) URLs in the manifest. If <baseURL> is not present, said
# URLs should be relative to the location of the containing document.
boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, man_url)
boot_info, bootstrap_url = self._parse_bootstrap_node(
bootstrap_node, man_base_url)
live = boot_info['live']
metadata_node = media.find(_add_ns('metadata'))
if metadata_node is not None:
metadata = base64.b64decode(metadata_node.text.encode('ascii'))
metadata = compat_b64decode(metadata_node.text)
else:
metadata = None

48
youtube_dl/downloader/fragment.py
View File

@ -74,9 +74,14 @@ class FragmentFD(FileDownloader):
return not ctx['live'] and not ctx['tmpfilename'] == '-'
def _read_ytdl_file(self, ctx):
assert 'ytdl_corrupt' not in ctx
stream, _ = sanitize_open(self.ytdl_filename(ctx['filename']), 'r')
ctx['fragment_index'] = json.loads(stream.read())['downloader']['current_fragment']['index']
stream.close()
try:
ctx['fragment_index'] = json.loads(stream.read())['downloader']['current_fragment']['index']
except Exception:
ctx['ytdl_corrupt'] = True
finally:
stream.close()
def _write_ytdl_file(self, ctx):
frag_index_stream, _ = sanitize_open(self.ytdl_filename(ctx['filename']), 'w')
@ -107,19 +112,26 @@ class FragmentFD(FileDownloader):
def _append_fragment(self, ctx, frag_content):
try:
ctx['dest_stream'].write(frag_content)
ctx['dest_stream'].flush()
finally:
if self.__do_ytdl_file(ctx):
self._write_ytdl_file(ctx)
if not self.params.get('keep_fragments', False):
os.remove(ctx['fragment_filename_sanitized'])
os.remove(encodeFilename(ctx['fragment_filename_sanitized']))
del ctx['fragment_filename_sanitized']
def _prepare_frag_download(self, ctx):
if 'live' not in ctx:
ctx['live'] = False
if not ctx['live']:
total_frags_str = '%d' % ctx['total_frags']
ad_frags = ctx.get('ad_frags', 0)
if ad_frags:
total_frags_str += ' (not including %d ad)' % ad_frags
else:
total_frags_str = 'unknown (live)'
self.to_screen(
'[%s] Total fragments: %s'
% (self.FD_NAME, ctx['total_frags'] if not ctx['live'] else 'unknown (live)'))
'[%s] Total fragments: %s' % (self.FD_NAME, total_frags_str))
self.report_destination(ctx['filename'])
dl = HttpQuietDownloader(
self.ydl,
@ -151,11 +163,17 @@ class FragmentFD(FileDownloader):
if self.__do_ytdl_file(ctx):
if os.path.isfile(encodeFilename(self.ytdl_filename(ctx['filename']))):
self._read_ytdl_file(ctx)
if ctx['fragment_index'] > 0 and resume_len == 0:
self.report_error(
'Inconsistent state of incomplete fragment download. '
'Restarting from the beginning...')
is_corrupt = ctx.get('ytdl_corrupt') is True
is_inconsistent = ctx['fragment_index'] > 0 and resume_len == 0
if is_corrupt or is_inconsistent:
message = (
'.ytdl file is corrupt' if is_corrupt else
'Inconsistent state of incomplete fragment download')
self.report_warning(
'%s. Restarting from the beginning...' % message)
ctx['fragment_index'] = resume_len = 0
if 'ytdl_corrupt' in ctx:
del ctx['ytdl_corrupt']
self._write_ytdl_file(ctx)
else:
self._write_ytdl_file(ctx)
@ -234,12 +252,16 @@ class FragmentFD(FileDownloader):
if os.path.isfile(ytdl_filename):
os.remove(ytdl_filename)
elapsed = time.time() - ctx['started']
self.try_rename(ctx['tmpfilename'], ctx['filename'])
fsize = os.path.getsize(encodeFilename(ctx['filename']))
if ctx['tmpfilename'] == '-':
downloaded_bytes = ctx['complete_frags_downloaded_bytes']
else:
self.try_rename(ctx['tmpfilename'], ctx['filename'])
downloaded_bytes = os.path.getsize(encodeFilename(ctx['filename']))
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'downloaded_bytes': downloaded_bytes,
'total_bytes': downloaded_bytes,
'filename': ctx['filename'],
'status': 'finished',
'elapsed': elapsed,

33
youtube_dl/downloader/hls.py
View File

@ -75,15 +75,31 @@ class HlsFD(FragmentFD):
fd.add_progress_hook(ph)
return fd.real_download(filename, info_dict)
total_frags = 0
def is_ad_fragment(s):
return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or
s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad'))
media_frags = 0
ad_frags = 0
ad_frag_next = False
for line in s.splitlines():
line = line.strip()
if line and not line.startswith('#'):
total_frags += 1
if not line:
continue
if line.startswith('#'):
if is_ad_fragment(line):
ad_frags += 1
ad_frag_next = True
continue
if ad_frag_next:
ad_frag_next = False
continue
media_frags += 1
ctx = {
'filename': filename,
'total_frags': total_frags,
'total_frags': media_frags,
'ad_frags': ad_frags,
}
self._prepare_and_start_frag_download(ctx)
@ -101,10 +117,14 @@ class HlsFD(FragmentFD):
decrypt_info = {'METHOD': 'NONE'}
byte_range = {}
frag_index = 0
ad_frag_next = False
for line in s.splitlines():
line = line.strip()
if line:
if not line.startswith('#'):
if ad_frag_next:
ad_frag_next = False
continue
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue
@ -144,7 +164,8 @@ class HlsFD(FragmentFD):
return False
if decrypt_info['METHOD'] == 'AES-128':
iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(decrypt_info['URI']).read()
decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
self._prepare_url(info_dict, decrypt_info['URI'])).read()
frag_content = AES.new(
decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
self._append_fragment(ctx, frag_content)
@ -175,6 +196,8 @@ class HlsFD(FragmentFD):
'start': sub_range_start,
'end': sub_range_start + int(splitted_byte_range[0]),
}
elif is_ad_fragment(line):
ad_frag_next = True
self._finish_frag_download(ctx)

114
youtube_dl/downloader/http.py
View File

@ -4,13 +4,18 @@ import errno
import os
import socket
import time
import random
import re
from .common import FileDownloader
from ..compat import compat_urllib_error
from ..compat import (
compat_str,
compat_urllib_error,
)
from ..utils import (
ContentTooShortError,
encodeFilename,
int_or_none,
sanitize_open,
sanitized_Request,
write_xattr,
@ -38,21 +43,26 @@ class HttpFD(FileDownloader):
add_headers = info_dict.get('http_headers')
if add_headers:
headers.update(add_headers)
basic_request = sanitized_Request(url, None, headers)
request = sanitized_Request(url, None, headers)
is_test = self.params.get('test', False)
if is_test:
request.add_header('Range', 'bytes=0-%s' % str(self._TEST_FILE_SIZE - 1))
chunk_size = self._TEST_FILE_SIZE if is_test else (
info_dict.get('downloader_options', {}).get('http_chunk_size') or
self.params.get('http_chunk_size') or 0)
ctx.open_mode = 'wb'
ctx.resume_len = 0
ctx.data_len = None
ctx.block_size = self.params.get('buffersize', 1024)
ctx.start_time = time.time()
ctx.chunk_size = None
if self.params.get('continuedl', True):
# Establish possible resume length
if os.path.isfile(encodeFilename(ctx.tmpfilename)):
ctx.resume_len = os.path.getsize(encodeFilename(ctx.tmpfilename))
ctx.resume_len = os.path.getsize(
encodeFilename(ctx.tmpfilename))
ctx.is_resume = ctx.resume_len > 0
count = 0
retries = self.params.get('retries', 0)
@ -64,11 +74,36 @@ class HttpFD(FileDownloader):
def __init__(self, source_error):
self.source_error = source_error
class NextFragment(Exception):
pass
def set_range(req, start, end):
range_header = 'bytes=%d-' % start
if end:
range_header += compat_str(end)
req.add_header('Range', range_header)
def establish_connection():
if ctx.resume_len != 0:
self.report_resuming_byte(ctx.resume_len)
request.add_header('Range', 'bytes=%d-' % ctx.resume_len)
ctx.chunk_size = (random.randint(int(chunk_size * 0.95), chunk_size)
if not is_test and chunk_size else chunk_size)
if ctx.resume_len > 0:
range_start = ctx.resume_len
if ctx.is_resume:
self.report_resuming_byte(ctx.resume_len)
ctx.open_mode = 'ab'
elif ctx.chunk_size > 0:
range_start = 0
else:
range_start = None
ctx.is_resume = False
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
ctx.has_range = has_range
request = sanitized_Request(url, None, headers)
if has_range:
set_range(request, range_start, range_end)
# Establish connection
try:
ctx.data = self.ydl.urlopen(request)
@ -77,29 +112,40 @@ class HttpFD(FileDownloader):
# that don't support resuming and serve a whole file with no Content-Range
# set in response despite of requested Range (see
# https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799)
if ctx.resume_len > 0:
if has_range:
content_range = ctx.data.headers.get('Content-Range')
if content_range:
content_range_m = re.search(r'bytes (\d+)-', 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
if content_range_m and ctx.resume_len == int(content_range_m.group(1)):
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 or
# Chunked download and requested piece or
# its part is promised to be served
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
self.report_unable_to_resume()
ctx.resume_len = 0
ctx.open_mode = 'wb'
ctx.data_len = int_or_none(ctx.data.info().get('Content-length', None))
return
except (compat_urllib_error.HTTPError, ) as err:
if (err.code < 500 or err.code >= 600) and err.code != 416:
# Unexpected HTTP error
raise
elif err.code == 416:
if err.code == 416:
# Unable to resume (requested range not satisfiable)
try:
# Open the connection again without the range header
ctx.data = self.ydl.urlopen(basic_request)
ctx.data = self.ydl.urlopen(
sanitized_Request(url, None, headers))
content_length = ctx.data.info()['Content-Length']
except (compat_urllib_error.HTTPError, ) as err:
if err.code < 500 or err.code >= 600:
@ -130,6 +176,9 @@ class HttpFD(FileDownloader):
ctx.resume_len = 0
ctx.open_mode = 'wb'
return
elif err.code < 500 or err.code >= 600:
# Unexpected HTTP error
raise
raise RetryDownload(err)
except socket.error as err:
if err.errno != errno.ECONNRESET:
@ -160,7 +209,7 @@ class HttpFD(FileDownloader):
return False
byte_counter = 0 + ctx.resume_len
block_size = self.params.get('buffersize', 1024)
block_size = ctx.block_size
start = time.time()
# measure time over whole while-loop, so slow_down() and best_block_size() work together properly
@ -168,10 +217,11 @@ class HttpFD(FileDownloader):
before = start # start measuring
def retry(e):
if ctx.tmpfilename != '-':
to_stdout = ctx.tmpfilename == '-'
if not to_stdout:
ctx.stream.close()
ctx.stream = None
ctx.resume_len = os.path.getsize(encodeFilename(ctx.tmpfilename))
ctx.resume_len = byte_counter if to_stdout else os.path.getsize(encodeFilename(ctx.tmpfilename))
raise RetryDownload(e)
while True:
@ -233,25 +283,30 @@ class HttpFD(FileDownloader):
# Progress message
speed = self.calc_speed(start, now, byte_counter - ctx.resume_len)
if data_len is None:
if ctx.data_len is None:
eta = None
else:
eta = self.calc_eta(start, time.time(), data_len - ctx.resume_len, byte_counter - ctx.resume_len)
eta = self.calc_eta(start, time.time(), ctx.data_len - ctx.resume_len, byte_counter - ctx.resume_len)
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': byte_counter,
'total_bytes': data_len,
'total_bytes': ctx.data_len,
'tmpfilename': ctx.tmpfilename,
'filename': ctx.filename,
'eta': eta,
'speed': speed,
'elapsed': now - start,
'elapsed': now - ctx.start_time,
})
if is_test and byte_counter == data_len:
break
if not is_test and ctx.chunk_size and ctx.data_len is not None and byte_counter < ctx.data_len:
ctx.resume_len = byte_counter
# ctx.block_size = block_size
raise NextFragment()
if ctx.stream is None:
self.to_stderr('\n')
self.report_error('Did not get any data blocks')
@ -276,7 +331,7 @@ class HttpFD(FileDownloader):
'total_bytes': byte_counter,
'filename': ctx.filename,
'status': 'finished',
'elapsed': time.time() - start,
'elapsed': time.time() - ctx.start_time,
})
return True
@ -284,13 +339,14 @@ class HttpFD(FileDownloader):
while count <= retries:
try:
establish_connection()
download()
return True
return download()
except RetryDownload as e:
count += 1
if count <= retries:
self.report_retry(e.source_error, count, retries)
continue
except NextFragment:
continue
except SucceedDownload:
return True

28
youtube_dl/downloader/ism.py
View File

@ -1,25 +1,27 @@
from __future__ import unicode_literals
import time
import struct
import binascii
import io
from .fragment import FragmentFD
from ..compat import compat_urllib_error
from ..compat import (
compat_Struct,
compat_urllib_error,
)
u8 = struct.Struct(b'>B')
u88 = struct.Struct(b'>Bx')
u16 = struct.Struct(b'>H')
u1616 = struct.Struct(b'>Hxx')
u32 = struct.Struct(b'>I')
u64 = struct.Struct(b'>Q')
u8 = compat_Struct('>B')
u88 = compat_Struct('>Bx')
u16 = compat_Struct('>H')
u1616 = compat_Struct('>Hxx')
u32 = compat_Struct('>I')
u64 = compat_Struct('>Q')
s88 = struct.Struct(b'>bx')
s16 = struct.Struct(b'>h')
s1616 = struct.Struct(b'>hxx')
s32 = struct.Struct(b'>i')
s88 = compat_Struct('>bx')
s16 = compat_Struct('>h')
s1616 = compat_Struct('>hxx')
s32 = compat_Struct('>i')
unity_matrix = (s32.pack(0x10000) + s32.pack(0) * 3) * 2 + s32.pack(0x40000000)
@ -139,7 +141,7 @@ def write_piff_header(stream, params):
sample_entry_payload += u16.pack(0x18) # depth
sample_entry_payload += s16.pack(-1) # pre defined
codec_private_data = binascii.unhexlify(params['codec_private_data'])
codec_private_data = binascii.unhexlify(params['codec_private_data'].encode('utf-8'))
if fourcc in ('H264', 'AVC1'):
sps, pps = codec_private_data.split(u32.pack(1))[1:]
avcc_payload = u8.pack(1) # configuration version

115
youtube_dl/downloader/rtmp.py
View File

@ -29,66 +29,68 @@ class RtmpFD(FileDownloader):
proc = subprocess.Popen(args, stderr=subprocess.PIPE)
cursor_in_new_line = True
proc_stderr_closed = False
while not proc_stderr_closed:
# read line from stderr
line = ''
while True:
char = proc.stderr.read(1)
if not char:
proc_stderr_closed = True
break
if char in [b'\r', b'\n']:
break
line += char.decode('ascii', 'replace')
if not line:
# proc_stderr_closed is True
continue
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
if mobj:
downloaded_data_len = int(float(mobj.group(1)) * 1024)
percent = float(mobj.group(2))
if not resume_percent:
resume_percent = percent
resume_downloaded_data_len = downloaded_data_len
time_now = time.time()
eta = self.calc_eta(start, time_now, 100 - resume_percent, percent - resume_percent)
speed = self.calc_speed(start, time_now, downloaded_data_len - resume_downloaded_data_len)
data_len = None
if percent > 0:
data_len = int(downloaded_data_len * 100 / percent)
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': downloaded_data_len,
'total_bytes_estimate': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'eta': eta,
'elapsed': time_now - start,
'speed': speed,
})
cursor_in_new_line = False
else:
# no percent for live streams
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
try:
while not proc_stderr_closed:
# read line from stderr
line = ''
while True:
char = proc.stderr.read(1)
if not char:
proc_stderr_closed = True
break
if char in [b'\r', b'\n']:
break
line += char.decode('ascii', 'replace')
if not line:
# proc_stderr_closed is True
continue
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line)
if mobj:
downloaded_data_len = int(float(mobj.group(1)) * 1024)
percent = float(mobj.group(2))
if not resume_percent:
resume_percent = percent
resume_downloaded_data_len = downloaded_data_len
time_now = time.time()
speed = self.calc_speed(start, time_now, downloaded_data_len)
eta = self.calc_eta(start, time_now, 100 - resume_percent, percent - resume_percent)
speed = self.calc_speed(start, time_now, downloaded_data_len - resume_downloaded_data_len)
data_len = None
if percent > 0:
data_len = int(downloaded_data_len * 100 / percent)
self._hook_progress({
'status': 'downloading',
'downloaded_bytes': downloaded_data_len,
'total_bytes_estimate': data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'eta': eta,
'elapsed': time_now - start,
'speed': speed,
})
cursor_in_new_line = False
elif self.params.get('verbose', False):
if not cursor_in_new_line:
self.to_screen('')
cursor_in_new_line = True
self.to_screen('[rtmpdump] ' + line)
proc.wait()
else:
# no percent for live streams
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
if mobj:
downloaded_data_len = int(float(mobj.group(1)) * 1024)
time_now = time.time()
speed = self.calc_speed(start, time_now, downloaded_data_len)
self._hook_progress({
'downloaded_bytes': downloaded_data_len,
'tmpfilename': tmpfilename,
'filename': filename,
'status': 'downloading',
'elapsed': time_now - start,
'speed': speed,
})
cursor_in_new_line = False
elif self.params.get('verbose', False):
if not cursor_in_new_line:
self.to_screen('')
cursor_in_new_line = True
self.to_screen('[rtmpdump] ' + line)
finally:
proc.wait()
if not cursor_in_new_line:
self.to_screen('')
return proc.returncode
@ -163,7 +165,15 @@ class RtmpFD(FileDownloader):
RD_INCOMPLETE = 2
RD_NO_CONNECT = 3
retval = run_rtmpdump(args)
started = time.time()
try:
retval = run_rtmpdump(args)
except KeyboardInterrupt:
if not info_dict.get('is_live'):
raise
retval = RD_SUCCESS
self.to_screen('\n[rtmpdump] Interrupted by user')
if retval == RD_NO_CONNECT:
self.report_error('[rtmpdump] Could not connect to RTMP server.')
@ -171,7 +181,7 @@ class RtmpFD(FileDownloader):
while retval in (RD_INCOMPLETE, RD_FAILED) and not test and not live:
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % prevsize)
self.to_screen('[rtmpdump] Downloaded %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed
args = basic_args + ['--resume']
if retval == RD_FAILED:
@ -188,13 +198,14 @@ class RtmpFD(FileDownloader):
break
if retval == RD_SUCCESS or (test and retval == RD_INCOMPLETE):
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % fsize)
self.to_screen('[rtmpdump] Downloaded %s bytes' % fsize)
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,
'total_bytes': fsize,
'filename': filename,
'status': 'finished',
'elapsed': time.time() - started,
})
return True
else:

88
youtube_dl/extractor/abc.py
View File

@ -1,6 +1,9 @@
from __future__ import unicode_literals
import hashlib
import hmac
import re
import time
from .common import InfoExtractor
from ..compat import compat_str
@ -10,6 +13,8 @@ from ..utils import (
int_or_none,
parse_iso8601,
try_get,
unescapeHTML,
update_url_query,
)
@ -100,46 +105,59 @@ class ABCIE(InfoExtractor):
class ABCIViewIE(InfoExtractor):
IE_NAME = 'abc.net.au:iview'
_VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
_GEO_COUNTRIES = ['AU']
# ABC iview programs are normally available for 14 days only.
_TESTS = [{
'url': 'http://iview.abc.net.au/programs/diaries-of-a-broken-mind/ZX9735A001S00',
'url': 'https://iview.abc.net.au/show/ben-and-hollys-little-kingdom/series/0/video/ZX9371A050S00',
'md5': 'cde42d728b3b7c2b32b1b94b4a548afc',
'info_dict': {
'id': 'ZX9735A001S00',
'id': 'ZX9371A050S00',
'ext': 'mp4',
'title': 'Diaries Of A Broken Mind',
'description': 'md5:7de3903874b7a1be279fe6b68718fc9e',
'upload_date': '20161010',
'uploader_id': 'abc2',
'timestamp': 1476064920,
'title': "Gaston's Birthday",
'series': "Ben And Holly's Little Kingdom",
'description': 'md5:f9de914d02f226968f598ac76f105bcf',
'upload_date': '20180604',
'uploader_id': 'abc4kids',
'timestamp': 1528140219,
},
'params': {
'skip_download': True,
},
'skip': 'Video gone',
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_params = self._parse_json(self._search_regex(
r'videoParams\s*=\s*({.+?});', webpage, 'video params'), video_id)
title = video_params.get('title') or video_params['seriesTitle']
stream = next(s for s in video_params['playlist'] if s.get('type') == 'program')
video_params = self._download_json(
'https://iview.abc.net.au/api/programs/' + video_id, video_id)
title = unescapeHTML(video_params.get('title') or video_params['seriesTitle'])
stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))
format_urls = [
try_get(stream, lambda x: x['hds-unmetered'], compat_str)]
house_number = video_params.get('episodeHouseNumber') or video_id
path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(
int(time.time()), house_number)
sig = hmac.new(
b'android.content.res.Resources',
path.encode('utf-8'), hashlib.sha256).hexdigest()
token = self._download_webpage(
'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
# May have higher quality video
sd_url = try_get(
stream, lambda x: x['streams']['hds']['sd'], compat_str)
if sd_url:
format_urls.append(sd_url.replace('metered', 'um'))
def tokenize_url(url, token):
return update_url_query(url, {
'hdnea': token,
})
formats = []
for format_url in format_urls:
if format_url:
formats.extend(
self._extract_akamai_formats(format_url, video_id))
for sd in ('sd', 'sd-low'):
sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str)
if not sd_url:
continue
formats = self._extract_m3u8_formats(
tokenize_url(sd_url, token), video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
if formats:
break
self._sort_formats(formats)
subtitles = {}
@ -150,18 +168,26 @@ class ABCIViewIE(InfoExtractor):
'ext': 'vtt',
}]
is_live = video_params.get('livestream') == '1'
if is_live:
title = self._live_title(title)
return {
'id': video_id,
'title': title,
'description': self._html_search_meta(['og:description', 'twitter:description'], webpage),
'thumbnail': self._html_search_meta(['og:image', 'twitter:image:src'], webpage),
'description': video_params.get('description'),
'thumbnail': video_params.get('thumbnail'),
'duration': int_or_none(video_params.get('eventDuration')),
'timestamp': parse_iso8601(video_params.get('pubDate'), ' '),
'series': video_params.get('seriesTitle'),
'series': unescapeHTML(video_params.get('seriesTitle')),
'series_id': video_params.get('seriesHouseNumber') or video_id[:7],
'episode_number': int_or_none(self._html_search_meta('episodeNumber', webpage, default=None)),
'episode': self._html_search_meta('episode_title', webpage, default=None),
'season_number': int_or_none(self._search_regex(
r'\bSeries\s+(\d+)\b', title, 'season number', default=None)),
'episode_number': int_or_none(self._search_regex(
r'\bEp\s+(\d+)\b', title, 'episode number', default=None)),
'episode_id': house_number,
'uploader_id': video_params.get('channel'),
'formats': formats,
'subtitles': subtitles,
'is_live': is_live,
}

4
youtube_dl/extractor/abcnews.py
View File

@ -66,7 +66,7 @@ class AbcNewsIE(InfoExtractor):
_TESTS = [{
'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
'info_dict': {
'id': '10498713',
'id': '10505354',
'ext': 'flv',
'display_id': 'dramatic-video-rare-death-job-america',
'title': 'Occupational Hazards',
@ -79,7 +79,7 @@ class AbcNewsIE(InfoExtractor):
}, {
'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
'info_dict': {
'id': '39125818',
'id': '38897857',
'ext': 'mp4',
'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
'title': 'Justin Timberlake Drops Hints For Secret Single',

47
youtube_dl/extractor/acast.py
View File

@ -7,8 +7,10 @@ import functools
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
int_or_none,
parse_iso8601,
try_get,
unified_timestamp,
OnDemandPagedList,
)
@ -24,39 +26,58 @@ class ACastIE(InfoExtractor):
'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
'ext': 'mp3',
'title': '"Where Are You?": Taipei 101, Taiwan',
'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
'timestamp': 1196172000,
'upload_date': '20071127',
'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
'duration': 211,
'creator': 'Concierge',
'series': 'Condé Nast Traveler Podcast',
'episode': '"Where Are You?": Taipei 101, Taiwan',
}
}, {
# test with multiple blings
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'md5': '55c0097badd7095f494c99a172f86501',
'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
'title': '2. Raggarmordet - Röster ur det förflutna',
'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
'timestamp': 1477346700,
'upload_date': '20161024',
'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
'duration': 2797,
'duration': 2766.602563,
'creator': 'Anton Berg & Martin Johnson',
'series': 'Spår',
'episode': '2. Raggarmordet - Röster ur det förflutna',
}
}]
def _real_extract(self, url):
channel, display_id = re.match(self._VALID_URL, url).groups()
s = self._download_json(
'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
display_id)['result']
media_url = s['url']
cast_data = self._download_json(
'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
display_id)['result']
e = cast_data['episode']
title = e['name']
return {
'id': compat_str(cast_data['id']),
'id': compat_str(e['id']),
'display_id': display_id,
'url': [b['audio'] for b in cast_data['blings'] if b['type'] == 'BlingAudio'][0],
'title': cast_data['name'],
'description': cast_data.get('description'),
'thumbnail': cast_data.get('image'),
'timestamp': parse_iso8601(cast_data.get('publishingDate')),
'duration': int_or_none(cast_data.get('duration')),
'url': media_url,
'title': title,
'description': e.get('description') or e.get('summary'),
'thumbnail': e.get('image'),
'timestamp': unified_timestamp(e.get('publishingDate')),
'duration': float_or_none(s.get('duration') or e.get('duration')),
'filesize': int_or_none(e.get('contentLength')),
'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),
'season_number': int_or_none(e.get('seasonNumber')),
'episode': title,
'episode_number': int_or_none(e.get('episodeNumber')),
}

47
youtube_dl/extractor/adn.py
View File

@ -2,17 +2,25 @@
from __future__ import unicode_literals
import base64
import binascii
import json
import os
import random
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt
from ..compat import compat_ord
from ..compat import (
compat_b64decode,
compat_ord,
)
from ..utils import (
bytes_to_intlist,
bytes_to_long,
ExtractorError,
float_or_none,
intlist_to_bytes,
long_to_bytes,
pkcs1pad,
srt_subtitles_timecode,
strip_or_none,
urljoin,
@ -33,6 +41,7 @@ class ADNIE(InfoExtractor):
}
}
_BASE_URL = 'http://animedigitalnetwork.fr'
_RSA_KEY = (0xc35ae1e4356b65a73b551493da94b8cb443491c0aa092a357a5aee57ffc14dda85326f42d716e539a34542a0d3f363adf16c5ec222d713d5997194030ee2e4f0d1fb328c01a81cf6868c090d50de8e169c6b13d1675b9eeed1cbc51e1fffca9b38af07f37abd790924cd3bee59d0257cfda4fe5f3f0534877e21ce5821447d1b, 65537)
def _get_subtitles(self, sub_path, video_id):
if not sub_path:
@ -40,17 +49,15 @@ class ADNIE(InfoExtractor):
enc_subtitles = self._download_webpage(
urljoin(self._BASE_URL, sub_path),
video_id, fatal=False, headers={
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:53.0) Gecko/20100101 Firefox/53.0',
})
video_id, fatal=False)
if not enc_subtitles:
return None
# http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = intlist_to_bytes(aes_cbc_decrypt(
bytes_to_intlist(base64.b64decode(enc_subtitles[24:])),
bytes_to_intlist(b'\x1b\xe0\x29\x61\x38\x94\x24\x00\x12\xbd\xc5\x80\xac\xce\xbe\xb0'),
bytes_to_intlist(base64.b64decode(enc_subtitles[:24]))
bytes_to_intlist(compat_b64decode(enc_subtitles[24:])),
bytes_to_intlist(binascii.unhexlify(self._K + '9032ad7083106400')),
bytes_to_intlist(compat_b64decode(enc_subtitles[:24]))
))
subtitles_json = self._parse_json(
dec_subtitles[:-compat_ord(dec_subtitles[-1])].decode(),
@ -105,15 +112,31 @@ class ADNIE(InfoExtractor):
options = player_config.get('options') or {}
metas = options.get('metas') or {}
title = metas.get('title') or video_info['title']
links = player_config.get('links') or {}
sub_path = player_config.get('subtitles')
error = None
if not links:
links_url = player_config['linksurl']
links_data = self._download_json(urljoin(
self._BASE_URL, links_url), video_id)
links_url = player_config.get('linksurl') or options['videoUrl']
token = options['token']
self._K = ''.join([random.choice('0123456789abcdef') for _ in range(16)])
message = bytes_to_intlist(json.dumps({
'k': self._K,
'e': 60,
't': token,
}))
padded_message = intlist_to_bytes(pkcs1pad(message, 128))
n, e = self._RSA_KEY
encrypted_message = long_to_bytes(pow(bytes_to_long(padded_message), e, n))
authorization = base64.b64encode(encrypted_message).decode()
links_data = self._download_json(
urljoin(self._BASE_URL, links_url), video_id, headers={
'Authorization': 'Bearer ' + authorization,
})
links = links_data.get('links') or {}
metas = metas or links_data.get('meta') or {}
sub_path = (sub_path or links_data.get('subtitles')) + '&token=' + token
error = links_data.get('error')
title = metas.get('title') or video_info['title']
formats = []
for format_id, qualities in links.items():
@ -144,7 +167,7 @@ class ADNIE(InfoExtractor):
'description': strip_or_none(metas.get('summary') or video_info.get('resume')),
'thumbnail': video_info.get('image'),
'formats': formats,
'subtitles': self.extract_subtitles(player_config.get('subtitles'), video_id),
'subtitles': self.extract_subtitles(sub_path, video_id),
'episode': metas.get('subtitle') or video_info.get('videoTitle'),
'series': video_info.get('playlistTitle'),
}

4
youtube_dl/extractor/adobepass.py
View File

@ -1325,8 +1325,8 @@ class AdobePassIE(InfoExtractor):
_DOWNLOADING_LOGIN_PAGE = 'Downloading Provider Login Page'
def _download_webpage_handle(self, *args, **kwargs):
headers = kwargs.get('headers', {})
headers.update(self.geo_verification_headers())
headers = self.geo_verification_headers()
headers.update(kwargs.get('headers', {}))
kwargs['headers'] = headers
return super(AdobePassIE, self)._download_webpage_handle(
*args, **compat_kwargs(kwargs))

3
youtube_dl/extractor/adultswim.py
View File

@ -7,6 +7,7 @@ from .turner import TurnerBaseIE
from ..utils import (
int_or_none,
strip_or_none,
url_or_none,
)
@ -98,7 +99,7 @@ class AdultSwimIE(TurnerBaseIE):
if not video_id:
entries = []
for episode in video_data.get('archiveEpisodes', []):
episode_url = episode.get('url')
episode_url = url_or_none(episode.get('url'))
if not episode_url:
continue
entries.append(self.url_result(

5
youtube_dl/extractor/aenetworks.py
View File

@ -122,7 +122,8 @@ class AENetworksIE(AENetworksBaseIE):
query = {
'mbr': 'true',
'assetTypes': 'high_video_s3'
'assetTypes': 'high_video_ak',
'switch': 'hls_high_ak',
}
video_id = self._html_search_meta('aetn:VideoID', webpage)
media_url = self._search_regex(
@ -131,7 +132,7 @@ class AENetworksIE(AENetworksBaseIE):
r'data-media-url=(["\'])(?P<url>(?:(?!\1).)+?)\1'],
webpage, 'video url', group='url')
theplatform_metadata = self._download_theplatform_metadata(self._search_regex(
r'https?://link.theplatform.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
r'https?://link\.theplatform\.com/s/([^?]+)', media_url, 'theplatform_path'), video_id)
info = self._parse_theplatform_metadata(theplatform_metadata)
if theplatform_metadata.get('AETN$isBehindWall'):
requestor_id = self._DOMAIN_TO_REQUESTOR_ID[domain]

245
youtube_dl/extractor/afreecatv.py
View File

@ -9,6 +9,8 @@ from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
url_or_none,
urlencode_postdata,
xpath_text,
)
@ -28,6 +30,7 @@ class AfreecaTVIE(InfoExtractor):
)
(?P<id>\d+)
'''
_NETRC_MACHINE = 'afreecatv'
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
'md5': 'f72c89fe7ecc14c1b5ce506c4996046e',
@ -138,6 +141,23 @@ class AfreecaTVIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# PARTIAL_ADULT
'url': 'http://vod.afreecatv.com/PLAYER/STATION/32028439',
'info_dict': {
'id': '20180327_27901457_202289533_1',
'ext': 'mp4',
'title': '[생]빨개요♥ (part 1)',
'thumbnail': 're:^https?://(?:video|st)img.afreecatv.com/.*$',
'uploader': '[SA]서아',
'uploader_id': 'bjdyrksu',
'upload_date': '20180327',
'duration': 3601,
},
'params': {
'skip_download': True,
},
'expected_warnings': ['adult content'],
}, {
'url': 'http://www.afreecatv.com/player/Player.swf?szType=szBjId=djleegoon&nStationNo=11273158&nBbsNo=13161095&nTitleNo=36327652',
'only_matching': True,
@ -155,17 +175,107 @@ class AfreecaTVIE(InfoExtractor):
video_key['part'] = int(m.group('part'))
return video_key
def _real_initialize(self):
self._login()
def _login(self):
username, password = self._get_login_info()
if username is None:
return
login_form = {
'szWork': 'login',
'szType': 'json',
'szUid': username,
'szPassword': password,
'isSaveId': 'false',
'szScriptVar': 'oLoginRet',
'szAction': '',
}
response = self._download_json(
'https://login.afreecatv.com/app/LoginAction.php', None,
'Logging in', data=urlencode_postdata(login_form))
_ERRORS = {
-4: 'Your account has been suspended due to a violation of our terms and policies.',
-5: 'https://member.afreecatv.com/app/user_delete_progress.php',
-6: 'https://login.afreecatv.com/membership/changeMember.php',
-8: "Hello! AfreecaTV here.\nThe username you have entered belongs to \n an account that requires a legal guardian's consent. \nIf you wish to use our services without restriction, \nplease make sure to go through the necessary verification process.",
-9: 'https://member.afreecatv.com/app/pop_login_block.php',
-11: 'https://login.afreecatv.com/afreeca/second_login.php',
-12: 'https://member.afreecatv.com/app/user_security.php',
0: 'The username does not exist or you have entered the wrong password.',
-1: 'The username does not exist or you have entered the wrong password.',
-3: 'You have entered your username/password incorrectly.',
-7: 'You cannot use your Global AfreecaTV account to access Korean AfreecaTV.',
-10: 'Sorry for the inconvenience. \nYour account has been blocked due to an unauthorized access. \nPlease contact our Help Center for assistance.',
-32008: 'You have failed to log in. Please contact our Help Center.',
}
result = int_or_none(response.get('RESULT'))
if result != 1:
error = _ERRORS.get(result, 'You have failed to log in.')
raise ExtractorError(
'Unable to login: %s said: %s' % (self.IE_NAME, error),
expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
video_xml = self._download_xml(
'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
video_id, query={'nTitleNo': video_id})
webpage = self._download_webpage(url, video_id)
video_element = video_xml.findall(compat_xpath('./track/video'))[1]
if re.search(r'alert\(["\']This video has been deleted', webpage):
raise ExtractorError(
'Video %s has been deleted' % video_id, expected=True)
station_id = self._search_regex(
r'nStationNo\s*=\s*(\d+)', webpage, 'station')
bbs_id = self._search_regex(
r'nBbsNo\s*=\s*(\d+)', webpage, 'bbs')
video_id = self._search_regex(
r'nTitleNo\s*=\s*(\d+)', webpage, 'title', default=video_id)
partial_view = False
for _ in range(2):
query = {
'nTitleNo': video_id,
'nStationNo': station_id,
'nBbsNo': bbs_id,
}
if partial_view:
query['partialView'] = 'SKIP_ADULT'
video_xml = self._download_xml(
'http://afbbs.afreecatv.com:8080/api/video/get_video_info.php',
video_id, 'Downloading video info XML%s'
% (' (skipping adult)' if partial_view else ''),
video_id, headers={
'Referer': url,
}, query=query)
flag = xpath_text(video_xml, './track/flag', 'flag', default=None)
if flag and flag == 'SUCCEED':
break
if flag == 'PARTIAL_ADULT':
self._downloader.report_warning(
'In accordance with local laws and regulations, underage users are restricted from watching adult content. '
'Only content suitable for all ages will be downloaded. '
'Provide account credentials if you wish to download restricted content.')
partial_view = True
continue
elif flag == 'ADULT':
error = 'Only users older than 19 are able to watch this video. Provide account credentials to download this content.'
else:
error = flag
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, error), expected=True)
else:
raise ExtractorError('Unable to download video info')
video_element = video_xml.findall(compat_xpath('./track/video'))[-1]
if video_element is None or video_element.text is None:
raise ExtractorError('Specified AfreecaTV video does not exist',
expected=True)
raise ExtractorError(
'Video %s video does not exist' % video_id, expected=True)
video_url = video_element.text.strip()
@ -195,7 +305,7 @@ class AfreecaTVIE(InfoExtractor):
file_elements = video_element.findall(compat_xpath('./file'))
one = len(file_elements) == 1
for file_num, file_element in enumerate(file_elements, start=1):
file_url = file_element.text
file_url = url_or_none(file_element.text)
if not file_url:
continue
key = file_element.get('key', '')
@ -203,10 +313,19 @@ class AfreecaTVIE(InfoExtractor):
r'^(\d{8})_', key, 'upload date', default=None)
file_duration = int_or_none(file_element.get('duration'))
format_id = key if key else '%s_%s' % (video_id, file_num)
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
if determine_ext(file_url) == 'm3u8':
formats = self._extract_m3u8_formats(
file_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls',
note='Downloading part %d m3u8 information' % file_num)
else:
formats = [{
'url': file_url,
'format_id': 'http',
}]
if not formats:
continue
self._sort_formats(formats)
file_info = common_entry.copy()
file_info.update({
'id': format_id,
@ -246,107 +365,3 @@ class AfreecaTVIE(InfoExtractor):
})
return info
class AfreecaTVGlobalIE(AfreecaTVIE):
IE_NAME = 'afreecatv:global'
_VALID_URL = r'https?://(?:www\.)?afreeca\.tv/(?P<channel_id>\d+)(?:/v/(?P<video_id>\d+))?'
_TESTS = [{
'url': 'http://afreeca.tv/36853014/v/58301',
'info_dict': {
'id': '58301',
'title': 'tryhard top100',
'uploader_id': '36853014',
'uploader': 'makgi Hearthstone Live!',
},
'playlist_count': 3,
}]
def _real_extract(self, url):
channel_id, video_id = re.match(self._VALID_URL, url).groups()
video_type = 'video' if video_id else 'live'
query = {
'pt': 'view',
'bid': channel_id,
}
if video_id:
query['vno'] = video_id
video_data = self._download_json(
'http://api.afreeca.tv/%s/view_%s.php' % (video_type, video_type),
video_id or channel_id, query=query)['channel']
if video_data.get('result') != 1:
raise ExtractorError('%s said: %s' % (self.IE_NAME, video_data['remsg']))
title = video_data['title']
info = {
'thumbnail': video_data.get('thumb'),
'view_count': int_or_none(video_data.get('vcnt')),
'age_limit': int_or_none(video_data.get('grade')),
'uploader_id': channel_id,
'uploader': video_data.get('cname'),
}
if video_id:
entries = []
for i, f in enumerate(video_data.get('flist', [])):
video_key = self.parse_video_key(f.get('key', ''))
f_url = f.get('file')
if not video_key or not f_url:
continue
entries.append({
'id': '%s_%s' % (video_id, video_key.get('part', i + 1)),
'title': title,
'upload_date': video_key.get('upload_date'),
'duration': int_or_none(f.get('length')),
'url': f_url,
'protocol': 'm3u8_native',
'ext': 'mp4',
})
info.update({
'id': video_id,
'title': title,
'duration': int_or_none(video_data.get('length')),
})
if len(entries) > 1:
info['_type'] = 'multi_video'
info['entries'] = entries
elif len(entries) == 1:
i = entries[0].copy()
i.update(info)
info = i
else:
formats = []
for s in video_data.get('strm', []):
s_url = s.get('purl')
if not s_url:
continue
stype = s.get('stype')
if stype == 'HLS':
formats.extend(self._extract_m3u8_formats(
s_url, channel_id, 'mp4', m3u8_id=stype, fatal=False))
elif stype == 'RTMP':
format_id = [stype]
label = s.get('label')
if label:
format_id.append(label)
formats.append({
'format_id': '-'.join(format_id),
'url': s_url,
'tbr': int_or_none(s.get('bps')),
'height': int_or_none(s.get('brt')),
'ext': 'flv',
'rtmp_live': True,
})
self._sort_formats(formats)
info.update({
'id': channel_id,
'title': self._live_title(title),
'is_live': True,
'formats': formats,
})
return info

5
youtube_dl/extractor/amcnetworks.py
View File

@ -11,7 +11,7 @@ from ..utils import (
class AMCNetworksIE(ThePlatformIE):
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|wetv)\.com/(?:movies|shows(?:/[^/]+)+)/(?P<id>[^/?#]+)'
_VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?:movies|shows(?:/[^/]+)+)/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://www.ifc.com/shows/maron/season-04/episode-01/step-1',
'md5': '',
@ -51,6 +51,9 @@ class AMCNetworksIE(ThePlatformIE):
}, {
'url': 'http://www.wetv.com/shows/la-hair/videos/season-05/episode-09-episode-9-2/episode-9-sneak-peek-3',
'only_matching': True,
}, {
'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
'only_matching': True,
}]
def _real_extract(self, url):

85
youtube_dl/extractor/americastestkitchen.py Normal file
View File

@ -0,0 +1,85 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
try_get,
unified_strdate,
)
class AmericasTestKitchenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?americastestkitchen\.com/(?:episode|videos)/(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.americastestkitchen.com/episode/548-summer-dinner-party',
'md5': 'b861c3e365ac38ad319cfd509c30577f',
'info_dict': {
'id': '1_5g5zua6e',
'title': 'Summer Dinner Party',
'ext': 'mp4',
'description': 'md5:858d986e73a4826979b6a5d9f8f6a1ec',
'thumbnail': r're:^https?://.*\.jpg',
'timestamp': 1497285541,
'upload_date': '20170612',
'uploader_id': 'roger.metcalf@americastestkitchen.com',
'release_date': '20170617',
'series': "America's Test Kitchen",
'season_number': 17,
'episode': 'Summer Dinner Party',
'episode_number': 24,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.americastestkitchen.com/videos/3420-pan-seared-salmon',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
partner_id = self._search_regex(
r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
webpage, 'kaltura partner id')
video_data = self._parse_json(
self._search_regex(
r'window\.__INITIAL_STATE__\s*=\s*({.+?})\s*;\s*</script>',
webpage, 'initial context'),
video_id)
ep_data = try_get(
video_data,
(lambda x: x['episodeDetail']['content']['data'],
lambda x: x['videoDetail']['content']['data']), dict)
ep_meta = ep_data.get('full_video', {})
external_id = ep_data.get('external_id') or ep_meta['external_id']
title = ep_data.get('title') or ep_meta.get('title')
description = clean_html(ep_meta.get('episode_description') or ep_data.get(
'description') or ep_meta.get('description'))
thumbnail = try_get(ep_meta, lambda x: x['photo']['image_url'])
release_date = unified_strdate(ep_data.get('aired_at'))
season_number = int_or_none(ep_meta.get('season_number'))
episode = ep_meta.get('title')
episode_number = int_or_none(ep_meta.get('episode_number'))
return {
'_type': 'url_transparent',
'url': 'kaltura:%s:%s' % (partner_id, external_id),
'ie_key': 'Kaltura',
'title': title,
'description': description,
'thumbnail': thumbnail,
'release_date': release_date,
'series': "America's Test Kitchen",
'season_number': season_number,
'episode': episode,
'episode_number': episode_number,
}

15
youtube_dl/extractor/amp.py
View File

@ -3,11 +3,12 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
mimetype2ext,
determine_ext,
ExtractorError,
int_or_none,
mimetype2ext,
parse_iso8601,
url_or_none,
)
@ -35,7 +36,7 @@ class AMPIE(InfoExtractor):
media_thumbnail = [media_thumbnail]
for thumbnail_data in media_thumbnail:
thumbnail = thumbnail_data.get('@attributes', {})
thumbnail_url = thumbnail.get('url')
thumbnail_url = url_or_none(thumbnail.get('url'))
if not thumbnail_url:
continue
thumbnails.append({
@ -51,7 +52,7 @@ class AMPIE(InfoExtractor):
media_subtitle = [media_subtitle]
for subtitle_data in media_subtitle:
subtitle = subtitle_data.get('@attributes', {})
subtitle_href = subtitle.get('href')
subtitle_href = url_or_none(subtitle.get('href'))
if not subtitle_href:
continue
subtitles.setdefault(subtitle.get('lang') or 'en', []).append({
@ -65,7 +66,7 @@ class AMPIE(InfoExtractor):
media_content = [media_content]
for media_data in media_content:
media = media_data.get('@attributes', {})
media_url = media.get('url')
media_url = url_or_none(media.get('url'))
if not media_url:
continue
ext = mimetype2ext(media.get('type')) or determine_ext(media_url)
@ -79,7 +80,7 @@ class AMPIE(InfoExtractor):
else:
formats.append({
'format_id': media_data.get('media-category', {}).get('@attributes', {}).get('label'),
'url': media['url'],
'url': media_url,
'tbr': int_or_none(media.get('bitrate')),
'filesize': int_or_none(media.get('fileSize')),
'ext': ext,

11
youtube_dl/extractor/animeondemand.py
View File

@ -8,6 +8,7 @@ from ..utils import (
determine_ext,
extract_attributes,
ExtractorError,
url_or_none,
urlencode_postdata,
urljoin,
)
@ -52,7 +53,7 @@ class AnimeOnDemandIE(InfoExtractor):
}]
def _login(self):
(username, password) = self._get_login_info()
username, password = self._get_login_info()
if username is None:
return
@ -78,15 +79,15 @@ class AnimeOnDemandIE(InfoExtractor):
post_url = urljoin(self._LOGIN_URL, post_url)
response = self._download_webpage(
post_url, None, 'Logging in as %s' % username,
post_url, None, 'Logging in',
data=urlencode_postdata(login_form), headers={
'Referer': self._LOGIN_URL,
})
if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')):
error = self._search_regex(
r'<p class="alert alert-danger">(.+?)</p>',
response, 'error', default=None)
r'<p[^>]+\bclass=(["\'])(?:(?!\1).)*\balert\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</p>',
response, 'error', default=None, group='error')
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
@ -165,7 +166,7 @@ class AnimeOnDemandIE(InfoExtractor):
}, fatal=False)
if not playlist:
continue
stream_url = playlist.get('streamurl')
stream_url = url_or_none(playlist.get('streamurl'))
if stream_url:
rtmp = re.search(
r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+/))(?P<playpath>mp[34]:.+)',

52
youtube_dl/extractor/anvato.py
View File

@ -18,6 +18,7 @@ from ..utils import (
int_or_none,
strip_jsonp,
unescapeHTML,
unsmuggle_url,
)
@ -133,9 +134,33 @@ class AnvatoIE(InfoExtractor):
'telemundo': 'anvato_mcp_telemundo_web_prod_c5278d51ad46fda4b6ca3d0ea44a7846a054f582'
}
_API_KEY = '3hwbSuqqT690uxjNYBktSQpa5ZrpYYR0Iofx7NcJHyA'
_ANVP_RE = r'<script[^>]+\bdata-anvp\s*=\s*(["\'])(?P<anvp>(?:(?!\1).)+)\1'
_AUTH_KEY = b'\x31\xc2\x42\x84\x9e\x73\xa0\xce'
_TESTS = [{
# from https://www.boston25news.com/news/watch-humpback-whale-breaches-right-next-to-fishing-boat-near-nh/817484874
'url': 'anvato:8v9BEynrwx8EFLYpgfOWcG1qJqyXKlRM:4465496',
'info_dict': {
'id': '4465496',
'ext': 'mp4',
'title': 'VIDEO: Humpback whale breaches right next to NH boat',
'description': 'VIDEO: Humpback whale breaches right next to NH boat. Footage courtesy: Zach Fahey.',
'duration': 22,
'timestamp': 1534855680,
'upload_date': '20180821',
'uploader': 'ANV',
},
'params': {
'skip_download': True,
},
}, {
# from https://sanfrancisco.cbslocal.com/2016/06/17/source-oakland-cop-on-leave-for-having-girlfriend-help-with-police-reports/
'url': 'anvato:DVzl9QRzox3ZZsP9bNu5Li3X7obQOnqP:3417601',
'only_matching': True,
}]
def __init__(self, *args, **kwargs):
super(AnvatoIE, self).__init__(*args, **kwargs)
self.__server_time = None
@ -168,7 +193,8 @@ class AnvatoIE(InfoExtractor):
'api': {
'anvrid': anvrid,
'anvstk': md5_text('%s|%s|%d|%s' % (
access_key, anvrid, server_time, self._ANVACK_TABLE[access_key])),
access_key, anvrid, server_time,
self._ANVACK_TABLE.get(access_key, self._API_KEY))),
'anvts': server_time,
},
}
@ -197,12 +223,16 @@ class AnvatoIE(InfoExtractor):
'tbr': tbr if tbr != 0 else None,
}
if ext == 'm3u8' or media_format in ('m3u8', 'm3u8-variant'):
if tbr is not None:
a_format.update({
'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
'ext': 'mp4',
})
if media_format == 'm3u8' and tbr is not None:
a_format.update({
'format_id': '-'.join(filter(None, ['hls', compat_str(tbr)])),
'ext': 'mp4',
})
elif media_format == 'm3u8-variant' or ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
elif ext == 'mp3' or media_format == 'mp3':
a_format['vcodec'] = 'none'
else:
@ -271,8 +301,14 @@ class AnvatoIE(InfoExtractor):
anvplayer_data['accessKey'], anvplayer_data['video'])
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
})
mobj = re.match(self._VALID_URL, url)
access_key, video_id = mobj.group('access_key_or_mcp', 'id')
if access_key not in self._ANVACK_TABLE:
access_key = self._MCP_TO_ACCESS_KEY_TABLE[access_key]
access_key = self._MCP_TO_ACCESS_KEY_TABLE.get(
access_key) or access_key
return self._get_anvato_videos(access_key, video_id)

3
youtube_dl/extractor/aol.py
View File

@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
url_or_none,
)
@ -77,7 +78,7 @@ class AolIE(InfoExtractor):
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
for rendition in video_data.get('renditions', []):
video_url = rendition.get('url')
video_url = url_or_none(rendition.get('url'))
if not video_url:
continue
ext = rendition.get('format')

94
youtube_dl/extractor/apa.py Normal file
View File

@ -0,0 +1,94 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
js_to_json,
url_or_none,
)
class APAIE(InfoExtractor):
_VALID_URL = r'https?://[^/]+\.apa\.at/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
_TESTS = [{
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
'md5': '2b12292faeb0a7d930c778c7a5b4759b',
'info_dict': {
'id': 'jjv85FdZ',
'ext': 'mp4',
'title': '"Blau ist mysteriös": Die Blue Man Group im Interview',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 254,
'timestamp': 1519211149,
'upload_date': '20180221',
},
}, {
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
'only_matching': True,
}, {
'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
'only_matching': True,
}, {
'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1',
webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
jwplatform_id = self._search_regex(
r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
'jwplatform id', default=None)
if jwplatform_id:
return self.url_result(
'jwplatform:' + jwplatform_id, ie='JWPlatform',
video_id=video_id)
sources = self._parse_json(
self._search_regex(
r'sources\s*=\s*(\[.+?\])\s*;', webpage, 'sources'),
video_id, transform_source=js_to_json)
formats = []
for source in sources:
if not isinstance(source, dict):
continue
source_url = url_or_none(source.get('file'))
if not source_url:
continue
ext = determine_ext(source_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
else:
formats.append({
'url': source_url,
})
self._sort_formats(formats)
thumbnail = self._search_regex(
r'image\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'thumbnail', fatal=False, group='url')
return {
'id': video_id,
'title': video_id,
'thumbnail': thumbnail,
'formats': formats,
}

3
youtube_dl/extractor/aparat.py
View File

@ -5,6 +5,7 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
mimetype2ext,
url_or_none,
)
@ -43,7 +44,7 @@ class AparatIE(InfoExtractor):
formats = []
for item in file_list[0]:
file_url = item.get('file')
file_url = url_or_none(item.get('file'))
if not file_url:
continue
ext = mimetype2ext(item.get('type'))

4
youtube_dl/extractor/appletrailers.py
View File

@ -117,7 +117,7 @@ class AppleTrailersIE(InfoExtractor):
continue
formats.append({
'format_id': '%s-%s' % (version, size),
'url': re.sub(r'_(\d+p.mov)', r'_h\1', src),
'url': re.sub(r'_(\d+p\.mov)', r'_h\1', src),
'width': int_or_none(size_data.get('width')),
'height': int_or_none(size_data.get('height')),
'language': version[:2],
@ -179,7 +179,7 @@ class AppleTrailersIE(InfoExtractor):
formats = []
for format in settings['metadata']['sizes']:
# The src is a file pointing to the real video file
format_url = re.sub(r'_(\d*p.mov)', r'_h\1', format['src'])
format_url = re.sub(r'_(\d*p\.mov)', r'_h\1', format['src'])
formats.append({
'url': format_url,
'format': format['type'],

2
youtube_dl/extractor/archiveorg.py
View File

@ -41,7 +41,7 @@ class ArchiveOrgIE(InfoExtractor):
webpage = self._download_webpage(
'http://archive.org/embed/' + video_id, video_id)
jwplayer_playlist = self._parse_json(self._search_regex(
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\);",
r"(?s)Play\('[^']+'\s*,\s*(\[.+\])\s*,\s*{.*?}\)",
webpage, 'jwplayer playlist'), video_id)
info = self._parse_jwplayer_data(
{'playlist': jwplayer_playlist}, video_id, base_url=url)

153
youtube_dl/extractor/ard.py
View File

@ -14,66 +14,43 @@ from ..utils import (
unified_strdate,
xpath_text,
update_url_query,
url_or_none,
)
from ..compat import compat_etree_fromstring
class ARDMediathekIE(InfoExtractor):
IE_NAME = 'ARD:mediathek'
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de|one\.ard\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
_TESTS = [{
'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
# available till 26.07.2022
'url': 'http://www.ardmediathek.de/tv/S%C3%9CDLICHT/Was-ist-die-Kunst-der-Zukunft-liebe-Ann/BR-Fernsehen/Video?bcastId=34633636&documentId=44726822',
'info_dict': {
'id': '29582122',
'id': '44726822',
'ext': 'mp4',
'title': 'Ich liebe das Leben trotzdem',
'description': 'md5:45e4c225c72b27993314b31a84a5261c',
'duration': 4557,
'title': 'Was ist die Kunst der Zukunft, liebe Anna McCarthy?',
'description': 'md5:4ada28b3e3b5df01647310e41f3a62f5',
'duration': 1740,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'HTTP Error 404: Not Found',
}
}, {
'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916',
'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e',
'info_dict': {
'id': '29522730',
'ext': 'mp4',
'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)',
'description': 'md5:196392e79876d0ac94c94e8cdb2875f1',
'duration': 5252,
},
'skip': 'HTTP Error 404: Not Found',
'url': 'https://one.ard.de/tv/Mord-mit-Aussicht/Mord-mit-Aussicht-6-39-T%C3%B6dliche-Nach/ONE/Video?bcastId=46384294&documentId=55586872',
'only_matching': True,
}, {
# audio
'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
'md5': '219d94d8980b4f538c7fcb0865eb7f2c',
'info_dict': {
'id': '28488308',
'ext': 'mp3',
'title': 'Tod eines Fußballers',
'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef',
'duration': 3240,
},
'skip': 'HTTP Error 404: Not Found',
'only_matching': True,
}, {
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'only_matching': True,
}, {
# audio
'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
'md5': '4e8f00631aac0395fee17368ac0e9867',
'info_dict': {
'id': '30796318',
'ext': 'mp3',
'title': 'Vor dem Fest',
'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb',
'duration': 3287,
},
'skip': 'Video is no longer available',
'only_matching': True,
}]
def _extract_media_info(self, media_info_url, webpage, video_id):
@ -126,6 +103,8 @@ class ARDMediathekIE(InfoExtractor):
quality = stream.get('_quality')
server = stream.get('_server')
for stream_url in stream_urls:
if not url_or_none(stream_url):
continue
ext = determine_ext(stream_url)
if quality != 'auto' and ext in ('f4m', 'm3u8'):
continue
@ -146,13 +125,11 @@ class ARDMediathekIE(InfoExtractor):
'play_path': stream_url,
'format_id': 'a%s-rtmp-%s' % (num, quality),
}
elif stream_url.startswith('http'):
else:
f = {
'url': stream_url,
'format_id': 'a%s-%s-%s' % (num, ext, quality)
}
else:
continue
m = re.search(r'_(?P<width>\d+)x(?P<height>\d+)\.mp4$', stream_url)
if m:
f.update({
@ -195,7 +172,7 @@ class ARDMediathekIE(InfoExtractor):
title = self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms.title" content="(.*?)"/>',
r'<meta name="dcterms\.title" content="(.*?)"/>',
r'<h4 class="headline">(.*?)</h4>'],
webpage, 'title')
description = self._html_search_meta(
@ -251,20 +228,23 @@ class ARDMediathekIE(InfoExtractor):
class ARDIE(InfoExtractor):
_VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
_TEST = {
'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
'md5': 'd216c3a86493f9322545e045ddc3eb35',
_TESTS = [{
# available till 14.02.2019
'url': 'http://www.daserste.de/information/talk/maischberger/videos/das-groko-drama-zerlegen-sich-die-volksparteien-video-102.html',
'md5': '8e4ec85f31be7c7fc08a26cdbc5a1f49',
'info_dict': {
'display_id': 'die-story-im-ersten-mission-unter-falscher-flagge',
'id': '100',
'display_id': 'das-groko-drama-zerlegen-sich-die-volksparteien-video',
'id': '102',
'ext': 'mp4',
'duration': 2600,
'title': 'Die Story im Ersten: Mission unter falscher Flagge',
'upload_date': '20140804',
'duration': 4435.0,
'title': 'Das GroKo-Drama: Zerlegen sich die Volksparteien?',
'upload_date': '20180214',
'thumbnail': r're:^https?://.*\.jpg$',
},
'skip': 'HTTP Error 404: Not Found',
}
}, {
'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@ -305,3 +285,76 @@ class ARDIE(InfoExtractor):
'upload_date': upload_date,
'thumbnail': thumbnail,
}
class ARDBetaMediathekIE(InfoExtractor):
_VALID_URL = r'https://beta\.ardmediathek\.de/[a-z]+/player/(?P<video_id>[a-zA-Z0-9]+)/(?P<display_id>[^/?#]+)'
_TESTS = [{
'url': 'https://beta.ardmediathek.de/ard/player/Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE/die-robuste-roswita',
'md5': '2d02d996156ea3c397cfc5036b5d7f8f',
'info_dict': {
'display_id': 'die-robuste-roswita',
'id': 'Y3JpZDovL2Rhc2Vyc3RlLmRlL3RhdG9ydC9mYmM4NGM1NC0xNzU4LTRmZGYtYWFhZS0wYzcyZTIxNGEyMDE',
'title': 'Tatort: Die robuste Roswita',
'description': r're:^Der Mord.*trüber ist als die Ilm.',
'duration': 5316,
'thumbnail': 'https://img.ardmediathek.de/standard/00/55/43/59/34/-1774185891/16x9/960?mandant=ard',
'upload_date': '20180826',
'ext': 'mp4',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id')
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
data_json = self._search_regex(r'window\.__APOLLO_STATE__\s*=\s*(\{.*);\n', webpage, 'json')
data = self._parse_json(data_json, display_id)
res = {
'id': video_id,
'display_id': display_id,
}
formats = []
for widget in data.values():
if widget.get('_geoblocked'):
raise ExtractorError('This video is not available due to geoblocking', expected=True)
if '_duration' in widget:
res['duration'] = widget['_duration']
if 'clipTitle' in widget:
res['title'] = widget['clipTitle']
if '_previewImage' in widget:
res['thumbnail'] = widget['_previewImage']
if 'broadcastedOn' in widget:
res['upload_date'] = unified_strdate(widget['broadcastedOn'])
if 'synopsis' in widget:
res['description'] = widget['synopsis']
if '_subtitleUrl' in widget:
res['subtitles'] = {'de': [{
'ext': 'ttml',
'url': widget['_subtitleUrl'],
}]}
if '_quality' in widget:
format_url = widget['_stream']['json'][0]
if format_url.endswith('.f4m'):
formats.extend(self._extract_f4m_formats(
format_url + '?hdcore=3.11.0',
video_id, f4m_id='hds', fatal=False))
elif format_url.endswith('m3u8'):
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
else:
formats.append({
'format_id': 'http-' + widget['_quality'],
'url': format_url,
'preference': 10, # Plain HTTP, that's nice
})
self._sort_formats(formats)
res['formats'] = formats
return res

15
youtube_dl/extractor/arte.py
View File

@ -6,6 +6,7 @@ import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
compat_urllib_parse_urlparse,
)
from ..utils import (
@ -15,6 +16,7 @@ from ..utils import (
int_or_none,
NO_DEFAULT,
qualities,
try_get,
unified_strdate,
)
@ -80,12 +82,15 @@ class ArteTVBaseIE(InfoExtractor):
info = self._download_json(json_url, video_id)
player_info = info['videoJsonPlayer']
vsr = player_info['VSR']
vsr = try_get(player_info, lambda x: x['VSR'], dict)
if not vsr:
raise ExtractorError(
'Video %s is not available' % player_info.get('VID') or video_id,
expected=True)
error = None
if try_get(player_info, lambda x: x['custom_msg']['type']) == 'error':
error = try_get(
player_info, lambda x: x['custom_msg']['msg'], compat_str)
if not error:
error = 'Video %s is not available' % player_info.get('VID') or video_id
raise ExtractorError(error, expected=True)
upload_date_str = player_info.get('shootingDate')
if not upload_date_str:

42
youtube_dl/extractor/asiancrush.py
View File

@ -8,7 +8,6 @@ from .kaltura import KalturaIE
from ..utils import (
extract_attributes,
remove_end,
urlencode_postdata,
)
@ -34,19 +33,40 @@ class AsianCrushIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://www.asiancrush.com/wp-admin/admin-ajax.php', video_id,
data=urlencode_postdata({
'postid': video_id,
'action': 'get_channel_kaltura_vars',
}))
webpage = self._download_webpage(url, video_id)
entry_id = data['entry_id']
entry_id, partner_id, title = [None] * 3
vars = self._parse_json(
self._search_regex(
r'iEmbedVars\s*=\s*({.+?})', webpage, 'embed vars',
default='{}'), video_id, fatal=False)
if vars:
entry_id = vars.get('entry_id')
partner_id = vars.get('partner_id')
title = vars.get('vid_label')
if not entry_id:
entry_id = self._search_regex(
r'\bentry_id["\']\s*:\s*["\'](\d+)', webpage, 'entry id')
player = self._download_webpage(
'https://api.asiancrush.com/embeddedVideoPlayer', video_id,
query={'id': entry_id})
kaltura_id = self._search_regex(
r'entry_id["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1', player,
'kaltura id', group='id')
if not partner_id:
partner_id = self._search_regex(
r'/p(?:artner_id)?/(\d+)', player, 'partner id',
default='513551')
return self.url_result(
'kaltura:%s:%s' % (data['partner_id'], entry_id),
ie=KalturaIE.ie_key(), video_id=entry_id,
video_title=data.get('vid_label'))
'kaltura:%s:%s' % (partner_id, kaltura_id),
ie=KalturaIE.ie_key(), video_id=kaltura_id,
video_title=title)
class AsianCrushPlaylistIE(InfoExtractor):

4
youtube_dl/extractor/atresplayer.py
View File

@ -74,7 +74,7 @@ class AtresPlayerIE(InfoExtractor):
self._login()
def _login(self):
(username, password) = self._get_login_info()
username, password = self._get_login_info()
if username is None:
return
@ -87,7 +87,7 @@ class AtresPlayerIE(InfoExtractor):
self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
request, None, 'Logging in')
error = self._html_search_regex(
r'(?s)<ul[^>]+class="[^"]*\blist_error\b[^"]*">(.+?)</ul>',

48
youtube_dl/extractor/audimedia.py
View File

@ -5,13 +5,12 @@ from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
sanitized_Request,
)
class AudiMediaIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?P<id>[^/?#]+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?audi-mediacenter\.com/(?:en|de)/audimediatv/(?:video/)?(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.audi-mediacenter.com/en/audimediatv/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-1467',
'md5': '79a8b71c46d49042609795ab59779b66',
'info_dict': {
@ -24,41 +23,46 @@ class AudiMediaIE(InfoExtractor):
'duration': 74022,
'view_count': int,
}
}
# extracted from https://audimedia.tv/assets/embed/embedded-player.js (dataSourceAuthToken)
_AUTH_TOKEN = 'e25b42847dba18c6c8816d5d8ce94c326e06823ebf0859ed164b3ba169be97f2'
}, {
'url': 'https://www.audi-mediacenter.com/en/audimediatv/video/60-seconds-of-audi-sport-104-2015-wec-bahrain-rookie-test-2991',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
raw_payload = self._search_regex([
r'class="amtv-embed"[^>]+id="([^"]+)"',
r'class=\\"amtv-embed\\"[^>]+id=\\"([^"]+)\\"',
r'class="amtv-embed"[^>]+id="([0-9a-z-]+)"',
r'id="([0-9a-z-]+)"[^>]+class="amtv-embed"',
r'class=\\"amtv-embed\\"[^>]+id=\\"([0-9a-z-]+)\\"',
r'id=\\"([0-9a-z-]+)\\"[^>]+class=\\"amtv-embed\\"',
r'id=(?:\\)?"(amtve-[a-z]-\d+-[a-z]{2})',
], webpage, 'raw payload')
_, stage_mode, video_id, lang = raw_payload.split('-')
_, stage_mode, video_id, _ = raw_payload.split('-')
# TODO: handle s and e stage_mode (live streams and ended live streams)
if stage_mode not in ('s', 'e'):
request = sanitized_Request(
'https://audimedia.tv/api/video/v1/videos/%s?embed[]=video_versions&embed[]=thumbnail_image&where[content_language_iso]=%s' % (video_id, lang),
headers={'X-Auth-Token': self._AUTH_TOKEN})
json_data = self._download_json(request, video_id)['results']
video_data = self._download_json(
'https://www.audimedia.tv/api/video/v1/videos/' + video_id,
video_id, query={
'embed[]': ['video_versions', 'thumbnail_image'],
})['results']
formats = []
stream_url_hls = json_data.get('stream_url_hls')
stream_url_hls = video_data.get('stream_url_hls')
if stream_url_hls:
formats.extend(self._extract_m3u8_formats(
stream_url_hls, video_id, 'mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
stream_url_hds = json_data.get('stream_url_hds')
stream_url_hds = video_data.get('stream_url_hds')
if stream_url_hds:
formats.extend(self._extract_f4m_formats(
stream_url_hds + '?hdcore=3.4.0',
video_id, f4m_id='hds', fatal=False))
for video_version in json_data.get('video_versions'):
for video_version in video_data.get('video_versions', []):
video_version_url = video_version.get('download_url') or video_version.get('stream_url')
if not video_version_url:
continue
@ -79,11 +83,11 @@ class AudiMediaIE(InfoExtractor):
return {
'id': video_id,
'title': json_data['title'],
'description': json_data.get('subtitle'),
'thumbnail': json_data.get('thumbnail_image', {}).get('file'),
'timestamp': parse_iso8601(json_data.get('publication_date')),
'duration': int_or_none(json_data.get('duration')),
'view_count': int_or_none(json_data.get('view_count')),
'title': video_data['title'],
'description': video_data.get('subtitle'),
'thumbnail': video_data.get('thumbnail_image', {}).get('file'),
'timestamp': parse_iso8601(video_data.get('publication_date')),
'duration': int_or_none(video_data.get('duration')),
'view_count': int_or_none(video_data.get('view_count')),
'formats': formats,
}

2
youtube_dl/extractor/audiomack.py
View File

@ -65,7 +65,7 @@ class AudiomackIE(InfoExtractor):
return {'_type': 'url', 'url': api_response['url'], 'ie_key': 'Soundcloud'}
return {
'id': api_response.get('id', album_url_tag),
'id': compat_str(api_response.get('id', album_url_tag)),
'uploader': api_response.get('artist'),
'title': api_response.get('title'),
'url': api_response['url'],

78
youtube_dl/extractor/aws.py Normal file
View File

@ -0,0 +1,78 @@
# coding: utf-8
from __future__ import unicode_literals
import datetime
import hashlib
import hmac
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
class AWSIE(InfoExtractor):
_AWS_ALGORITHM = 'AWS4-HMAC-SHA256'
_AWS_REGION = 'us-east-1'
def _aws_execute_api(self, aws_dict, video_id, query=None):
query = query or {}
amz_date = datetime.datetime.utcnow().strftime('%Y%m%dT%H%M%SZ')
date = amz_date[:8]
headers = {
'Accept': 'application/json',
'Host': self._AWS_PROXY_HOST,
'X-Amz-Date': amz_date,
'X-Api-Key': self._AWS_API_KEY
}
session_token = aws_dict.get('session_token')
if session_token:
headers['X-Amz-Security-Token'] = session_token
def aws_hash(s):
return hashlib.sha256(s.encode('utf-8')).hexdigest()
# Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html
canonical_querystring = compat_urllib_parse_urlencode(query)
canonical_headers = ''
for header_name, header_value in sorted(headers.items()):
canonical_headers += '%s:%s\n' % (header_name.lower(), header_value)
signed_headers = ';'.join([header.lower() for header in sorted(headers.keys())])
canonical_request = '\n'.join([
'GET',
aws_dict['uri'],
canonical_querystring,
canonical_headers,
signed_headers,
aws_hash('')
])
# Task 2: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-string-to-sign.html
credential_scope_list = [date, self._AWS_REGION, 'execute-api', 'aws4_request']
credential_scope = '/'.join(credential_scope_list)
string_to_sign = '\n'.join([self._AWS_ALGORITHM, amz_date, credential_scope, aws_hash(canonical_request)])
# Task 3: http://docs.aws.amazon.com/general/latest/gr/sigv4-calculate-signature.html
def aws_hmac(key, msg):
return hmac.new(key, msg.encode('utf-8'), hashlib.sha256)
def aws_hmac_digest(key, msg):
return aws_hmac(key, msg).digest()
def aws_hmac_hexdigest(key, msg):
return aws_hmac(key, msg).hexdigest()
k_signing = ('AWS4' + aws_dict['secret_key']).encode('utf-8')
for value in credential_scope_list:
k_signing = aws_hmac_digest(k_signing, value)
signature = aws_hmac_hexdigest(k_signing, string_to_sign)
# Task 4: http://docs.aws.amazon.com/general/latest/gr/sigv4-add-signature-to-request.html
headers['Authorization'] = ', '.join([
'%s Credential=%s/%s' % (self._AWS_ALGORITHM, aws_dict['access_key'], credential_scope),
'SignedHeaders=%s' % signed_headers,
'Signature=%s' % signature,
])
return self._download_json(
'https://%s%s%s' % (self._AWS_PROXY_HOST, aws_dict['uri'], '?' + canonical_querystring if canonical_querystring else ''),
video_id, headers=headers)

2
youtube_dl/extractor/azmedien.py
View File

@ -47,7 +47,7 @@ class AZMedienIE(AZMedienBaseIE):
'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
'info_dict': {
'id': '1_2444peh4',
'ext': 'mov',
'ext': 'mp4',
'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
'uploader_id': 'TeleZ?ri',

4
youtube_dl/extractor/bambuser.py
View File

@ -44,7 +44,7 @@ class BambuserIE(InfoExtractor):
}
def _login(self):
(username, password) = self._get_login_info()
username, password = self._get_login_info()
if username is None:
return
@ -59,7 +59,7 @@ class BambuserIE(InfoExtractor):
self._LOGIN_URL, urlencode_postdata(login_form))
request.add_header('Referer', self._LOGIN_URL)
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
request, None, 'Logging in')
login_error = self._html_search_regex(
r'(?s)<div class="messages error">(.+?)</div>',

223
youtube_dl/extractor/bandcamp.py
View File

@ -1,6 +1,5 @@
from __future__ import unicode_literals
import json
import random
import re
import time
@ -16,14 +15,18 @@ from ..utils import (
int_or_none,
KNOWN_EXTENSIONS,
parse_filesize,
str_or_none,
try_get,
unescapeHTML,
update_url_query,
unified_strdate,
unified_timestamp,
url_or_none,
)
class BandcampIE(InfoExtractor):
_VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P<title>[^/?#&]+)'
_VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<title>[^/?#&]+)'
_TESTS = [{
'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
'md5': 'c557841d5e50261777a6585648adf439',
@ -35,13 +38,44 @@ class BandcampIE(InfoExtractor):
},
'_skip': 'There is a limit of 200 free downloads / month for the test song'
}, {
# free download
'url': 'http://benprunty.bandcamp.com/track/lanius-battle',
'md5': '0369ace6b939f0927e62c67a1a8d9fa7',
'md5': '853e35bf34aa1d6fe2615ae612564b36',
'info_dict': {
'id': '2650410135',
'ext': 'aiff',
'title': 'Ben Prunty - Lanius (Battle)',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Ben Prunty',
'timestamp': 1396508491,
'upload_date': '20140403',
'release_date': '20140403',
'duration': 260.877,
'track': 'Lanius (Battle)',
'track_number': 1,
'track_id': '2650410135',
'artist': 'Ben Prunty',
'album': 'FTL: Advanced Edition Soundtrack',
},
}, {
# no free download, mp3 128
'url': 'https://relapsealumni.bandcamp.com/track/hail-to-fire',
'md5': 'fec12ff55e804bb7f7ebeb77a800c8b7',
'info_dict': {
'id': '2584466013',
'ext': 'mp3',
'title': 'Mastodon - Hail to Fire',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Mastodon',
'timestamp': 1322005399,
'upload_date': '20111122',
'release_date': '20040207',
'duration': 120.79,
'track': 'Hail to Fire',
'track_number': 5,
'track_id': '2584466013',
'artist': 'Mastodon',
'album': 'Call of the Mastodon',
},
}]
@ -50,19 +84,23 @@ class BandcampIE(InfoExtractor):
title = mobj.group('title')
webpage = self._download_webpage(url, title)
thumbnail = self._html_search_meta('og:image', webpage, default=None)
m_download = re.search(r'freeDownloadPage: "(.*?)"', webpage)
if not m_download:
m_trackinfo = re.search(r'trackinfo: (.+),\s*?\n', webpage)
if m_trackinfo:
json_code = m_trackinfo.group(1)
data = json.loads(json_code)[0]
track_id = compat_str(data['id'])
if not data.get('file'):
raise ExtractorError('Not streamable', video_id=track_id, expected=True)
track_id = None
track = None
track_number = None
duration = None
formats = []
for format_id, format_url in data['file'].items():
formats = []
track_info = self._parse_json(
self._search_regex(
r'trackinfo\s*:\s*\[\s*({.+?})\s*\]\s*,\s*?\n',
webpage, 'track info', default='{}'), title)
if track_info:
file_ = track_info.get('file')
if isinstance(file_, dict):
for format_id, format_url in file_.items():
if not url_or_none(format_url):
continue
ext, abr_str = format_id.split('-', 1)
formats.append({
'format_id': format_id,
@ -72,85 +110,110 @@ class BandcampIE(InfoExtractor):
'acodec': ext,
'abr': int_or_none(abr_str),
})
track = track_info.get('title')
track_id = str_or_none(track_info.get('track_id') or track_info.get('id'))
track_number = int_or_none(track_info.get('track_num'))
duration = float_or_none(track_info.get('duration'))
self._sort_formats(formats)
def extract(key):
return self._search_regex(
r'\b%s\s*["\']?\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % key,
webpage, key, default=None, group='value')
return {
'id': track_id,
'title': data['title'],
'thumbnail': thumbnail,
'formats': formats,
'duration': float_or_none(data.get('duration')),
}
else:
raise ExtractorError('No free songs found')
artist = extract('artist')
album = extract('album_title')
timestamp = unified_timestamp(
extract('publish_date') or extract('album_publish_date'))
release_date = unified_strdate(extract('album_release_date'))
download_link = m_download.group(1)
video_id = self._search_regex(
r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
webpage, 'video id')
download_link = self._search_regex(
r'freeDownloadPage\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'download link', default=None, group='url')
if download_link:
track_id = self._search_regex(
r'(?ms)var TralbumData = .*?[{,]\s*id: (?P<id>\d+),?$',
webpage, 'track id')
download_webpage = self._download_webpage(
download_link, video_id, 'Downloading free downloads page')
download_webpage = self._download_webpage(
download_link, track_id, 'Downloading free downloads page')
blob = self._parse_json(
self._search_regex(
r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage,
'blob', group='blob'),
video_id, transform_source=unescapeHTML)
blob = self._parse_json(
self._search_regex(
r'data-blob=(["\'])(?P<blob>{.+?})\1', download_webpage,
'blob', group='blob'),
track_id, transform_source=unescapeHTML)
info = blob['digital_items'][0]
info = try_get(
blob, (lambda x: x['digital_items'][0],
lambda x: x['download_items'][0]), dict)
if info:
downloads = info.get('downloads')
if isinstance(downloads, dict):
if not track:
track = info.get('title')
if not artist:
artist = info.get('artist')
if not thumbnail:
thumbnail = info.get('thumb_url')
downloads = info['downloads']
track = info['title']
download_formats = {}
download_formats_list = blob.get('download_formats')
if isinstance(download_formats_list, list):
for f in blob['download_formats']:
name, ext = f.get('name'), f.get('file_extension')
if all(isinstance(x, compat_str) for x in (name, ext)):
download_formats[name] = ext.strip('.')
artist = info.get('artist')
title = '%s - %s' % (artist, track) if artist else track
for format_id, f in downloads.items():
format_url = f.get('url')
if not format_url:
continue
# Stat URL generation algorithm is reverse engineered from
# download_*_bundle_*.js
stat_url = update_url_query(
format_url.replace('/download/', '/statdownload/'), {
'.rand': int(time.time() * 1000 * random.random()),
})
format_id = f.get('encoding_name') or format_id
stat = self._download_json(
stat_url, track_id, 'Downloading %s JSON' % format_id,
transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
fatal=False)
if not stat:
continue
retry_url = url_or_none(stat.get('retry_url'))
if not retry_url:
continue
formats.append({
'url': self._proto_relative_url(retry_url, 'http:'),
'ext': download_formats.get(format_id),
'format_id': format_id,
'format_note': f.get('description'),
'filesize': parse_filesize(f.get('size_mb')),
'vcodec': 'none',
})
download_formats = {}
for f in blob['download_formats']:
name, ext = f.get('name'), f.get('file_extension')
if all(isinstance(x, compat_str) for x in (name, ext)):
download_formats[name] = ext.strip('.')
formats = []
for format_id, f in downloads.items():
format_url = f.get('url')
if not format_url:
continue
# Stat URL generation algorithm is reverse engineered from
# download_*_bundle_*.js
stat_url = update_url_query(
format_url.replace('/download/', '/statdownload/'), {
'.rand': int(time.time() * 1000 * random.random()),
})
format_id = f.get('encoding_name') or format_id
stat = self._download_json(
stat_url, video_id, 'Downloading %s JSON' % format_id,
transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1],
fatal=False)
if not stat:
continue
retry_url = stat.get('retry_url')
if not isinstance(retry_url, compat_str):
continue
formats.append({
'url': self._proto_relative_url(retry_url, 'http:'),
'ext': download_formats.get(format_id),
'format_id': format_id,
'format_note': f.get('description'),
'filesize': parse_filesize(f.get('size_mb')),
'vcodec': 'none',
})
self._sort_formats(formats)
title = '%s - %s' % (artist, track) if artist else track
if not duration:
duration = float_or_none(self._html_search_meta(
'duration', webpage, default=None))
return {
'id': video_id,
'id': track_id,
'title': title,
'thumbnail': info.get('thumb_url') or thumbnail,
'uploader': info.get('artist'),
'artist': artist,
'thumbnail': thumbnail,
'uploader': artist,
'timestamp': timestamp,
'release_date': release_date,
'duration': duration,
'track': track,
'track_number': track_number,
'track_id': track_id,
'artist': artist,
'album': album,
'formats': formats,
}
@ -306,7 +369,7 @@ class BandcampWeeklyIE(InfoExtractor):
formats = []
for format_id, format_url in show['audio_stream'].items():
if not isinstance(format_url, compat_str):
if not url_or_none(format_url):
continue
for known_ext in KNOWN_EXTENSIONS:
if known_ext in format_id:

103
youtube_dl/extractor/bbc.py
View File

@ -12,6 +12,7 @@ from ..utils import (
float_or_none,
get_element_by_class,
int_or_none,
js_to_json,
parse_duration,
parse_iso8601,
try_get,
@ -20,7 +21,6 @@ from ..utils import (
urljoin,
)
from ..compat import (
compat_etree_fromstring,
compat_HTTPError,
compat_urlparse,
)
@ -29,7 +29,7 @@ from ..compat import (
class BBCCoUkIE(InfoExtractor):
IE_NAME = 'bbc.co.uk'
IE_DESC = 'BBC iPlayer'
_ID_REGEX = r'[pbw][\da-z]{7}'
_ID_REGEX = r'(?:[pbm][\da-z]{7}|w[\da-z]{7,14})'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?bbc\.co\.uk/
@ -236,6 +236,12 @@ class BBCCoUkIE(InfoExtractor):
}, {
'url': 'http://www.bbc.co.uk/programmes/w3csv1y9',
'only_matching': True,
}, {
'url': 'https://www.bbc.co.uk/programmes/m00005xn',
'only_matching': True,
}, {
'url': 'https://www.bbc.co.uk/programmes/w172w4dww1jqt5s',
'only_matching': True,
}]
_USP_RE = r'/([^/]+?)\.ism(?:\.hlsv2\.ism)?/[^/]+\.m3u8'
@ -333,14 +339,9 @@ class BBCCoUkIE(InfoExtractor):
self._raise_extractor_error(last_exception)
def _download_media_selector_url(self, url, programme_id=None):
try:
media_selection = self._download_xml(
url, programme_id, 'Downloading media selection XML')
except ExtractorError as ee:
if isinstance(ee.cause, compat_HTTPError) and ee.cause.code in (403, 404):
media_selection = compat_etree_fromstring(ee.cause.read().decode('utf-8'))
else:
raise
media_selection = self._download_xml(
url, programme_id, 'Downloading media selection XML',
expected_status=(403, 404))
return self._process_media_selector(media_selection, programme_id)
def _process_media_selector(self, media_selection, programme_id):
@ -772,6 +773,28 @@ class BBCIE(BBCCoUkIE):
# single video article embedded with data-media-vpid
'url': 'http://www.bbc.co.uk/sport/rowing/35908187',
'only_matching': True,
}, {
'url': 'https://www.bbc.co.uk/bbcthree/clip/73d0bbd0-abc3-4cea-b3c0-cdae21905eb1',
'info_dict': {
'id': 'p06556y7',
'ext': 'mp4',
'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',
'info_dict': {
'id': 'b0b9z4vz',
'ext': 'mp4',
'title': 'Prom 6: An American in Paris and Turangalila',
'description': 'md5:51cf7d6f5c8553f197e58203bc78dff8',
'uploader': 'Radio 3',
'uploader_id': 'bbc_radio_three',
},
}]
@classmethod
@ -994,6 +1017,66 @@ class BBCIE(BBCCoUkIE):
'subtitles': subtitles,
}
preload_state = self._parse_json(self._search_regex(
r'window\.__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
'preload state', default='{}'), playlist_id, fatal=False)
if preload_state:
current_programme = preload_state.get('programmes', {}).get('current') or {}
programme_id = current_programme.get('id')
if current_programme and programme_id and current_programme.get('type') == 'playable_item':
title = current_programme.get('titles', {}).get('tertiary') or playlist_title
formats, subtitles = self._download_media_selector(programme_id)
self._sort_formats(formats)
synopses = current_programme.get('synopses') or {}
network = current_programme.get('network') or {}
duration = int_or_none(
current_programme.get('duration', {}).get('value'))
thumbnail = None
image_url = current_programme.get('image_url')
if image_url:
thumbnail = image_url.replace('{recipe}', '1920x1920')
return {
'id': programme_id,
'title': title,
'description': dict_get(synopses, ('long', 'medium', 'short')),
'thumbnail': thumbnail,
'duration': duration,
'uploader': network.get('short_title'),
'uploader_id': network.get('id'),
'formats': formats,
'subtitles': subtitles,
}
bbc3_config = self._parse_json(
self._search_regex(
r'(?s)bbcthreeConfig\s*=\s*({.+?})\s*;\s*<', webpage,
'bbcthree config', default='{}'),
playlist_id, transform_source=js_to_json, fatal=False)
if bbc3_config:
bbc3_playlist = try_get(
bbc3_config, lambda x: x['payload']['content']['bbcMedia']['playlist'],
dict)
if bbc3_playlist:
playlist_title = bbc3_playlist.get('title') or playlist_title
thumbnail = bbc3_playlist.get('holdingImageURL')
entries = []
for bbc3_item in bbc3_playlist['items']:
programme_id = bbc3_item.get('versionID')
if not programme_id:
continue
formats, subtitles = self._download_media_selector(programme_id)
self._sort_formats(formats)
entries.append({
'id': programme_id,
'title': playlist_title,
'thumbnail': thumbnail,
'timestamp': timestamp,
'formats': formats,
'subtitles': subtitles,
})
return self.playlist_result(
entries, playlist_id, playlist_title, playlist_description)
def extract_all(pattern):
return list(filter(None, map(
lambda s: self._parse_json(s, playlist_id, fatal=False),

17
youtube_dl/extractor/beeg.py
View File

@ -9,6 +9,7 @@ from ..compat import (
from ..utils import (
int_or_none,
parse_iso8601,
urljoin,
)
@ -36,9 +37,11 @@ class BeegIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
cpl_url = self._search_regex(
r'<script[^>]+src=(["\'])(?P<url>(?:https?:)?//static\.beeg\.com/cpl/\d+\.js.*?)\1',
r'<script[^>]+src=(["\'])(?P<url>(?:/static|(?:https?:)?//static\.beeg\.com)/cpl/\d+\.js.*?)\1',
webpage, 'cpl', default=None, group='url')
cpl_url = urljoin(url, cpl_url)
beeg_version, beeg_salt = [None] * 2
if cpl_url:
@ -54,12 +57,16 @@ class BeegIE(InfoExtractor):
r'beeg_salt\s*=\s*(["\'])(?P<beeg_salt>.+?)\1', cpl, 'beeg salt',
default=None, group='beeg_salt')
beeg_version = beeg_version or '2000'
beeg_version = beeg_version or '2185'
beeg_salt = beeg_salt or 'pmweAkq8lAYKdfWcFCUj0yoVgoPlinamH5UE1CB3H'
video = self._download_json(
'https://api.beeg.com/api/v6/%s/video/%s' % (beeg_version, video_id),
video_id)
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.')
if video:
break
def split(o, e):
def cut(s, x):

20
youtube_dl/extractor/bellmedia.py
View File

@ -12,7 +12,7 @@ class BellMediaIE(InfoExtractor):
(?:
ctv|
tsn|
bnn|
bnn(?:bloomberg)?|
thecomedynetwork|
discovery|
discoveryvelocity|
@ -27,17 +27,16 @@ class BellMediaIE(InfoExtractor):
much\.com
)/.*?(?:\bvid(?:eoid)?=|-vid|~|%7E|/(?:episode)?)(?P<id>[0-9]{6,})'''
_TESTS = [{
'url': 'http://www.ctv.ca/video/player?vid=706966',
'md5': 'ff2ebbeae0aa2dcc32a830c3fd69b7b0',
'url': 'https://www.bnnbloomberg.ca/video/david-cockfield-s-top-picks~1403070',
'md5': '36d3ef559cfe8af8efe15922cd3ce950',
'info_dict': {
'id': '706966',
'ext': 'mp4',
'title': 'Larry Day and Richard Jutras on the TIFF red carpet of \'Stonewall\'',
'description': 'etalk catches up with Larry Day and Richard Jutras on the TIFF red carpet of "Stonewall”.',
'upload_date': '20150919',
'timestamp': 1442624700,
'id': '1403070',
'ext': 'flv',
'title': 'David Cockfield\'s Top Picks',
'description': 'md5:810f7f8c6a83ad5b48677c3f8e5bb2c3',
'upload_date': '20180525',
'timestamp': 1527288600,
},
'expected_warnings': ['HTTP Error 404'],
}, {
'url': 'http://www.thecomedynetwork.ca/video/player?vid=923582',
'only_matching': True,
@ -70,6 +69,7 @@ class BellMediaIE(InfoExtractor):
'investigationdiscovery': 'invdisc',
'animalplanet': 'aniplan',
'etalk': 'ctv',
'bnnbloomberg': 'bnn',
}
def _real_extract(self, url):

10
youtube_dl/extractor/bigflix.py
View File

@ -1,11 +1,13 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..compat import (
compat_b64decode,
compat_urllib_parse_unquote,
)
class BigflixIE(InfoExtractor):
@ -39,8 +41,8 @@ class BigflixIE(InfoExtractor):
webpage, 'title')
def decode_url(quoted_b64_url):
return base64.b64decode(compat_urllib_parse_unquote(
quoted_b64_url).encode('ascii')).decode('utf-8')
return compat_b64decode(compat_urllib_parse_unquote(
quoted_b64_url)).decode('utf-8')
formats = []
for height, encoded_url in re.findall(

145
youtube_dl/extractor/bilibili.py
View File

@ -27,14 +27,14 @@ class BiliBiliIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.bilibili.tv/video/av1074402/',
'md5': '9fa226fe2b8a9a4d5a69b4c6a183417e',
'md5': '5f7d29e1a2872f3df0cf76b1f87d3788',
'info_dict': {
'id': '1074402',
'ext': 'mp4',
'ext': 'flv',
'title': '【金坷垃】金泡沫',
'description': 'md5:ce18c2a2d2193f0df2917d270f2e5923',
'duration': 308.315,
'timestamp': 1398012660,
'duration': 308.067,
'timestamp': 1398012678,
'upload_date': '20140420',
'thumbnail': r're:^https?://.+\.jpg',
'uploader': '菊子桑',
@ -59,17 +59,38 @@ class BiliBiliIE(InfoExtractor):
'url': 'http://www.bilibili.com/video/av8903802/',
'info_dict': {
'id': '8903802',
'ext': 'mp4',
'title': '阿滴英文｜英文歌分享#6 "Closer',
'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',
'uploader': '阿滴英文',
'uploader_id': '65880958',
'timestamp': 1488382620,
'upload_date': '20170301',
},
'params': {
'skip_download': True, # Test metadata only
},
'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, # Test metadata only
},
}, {
'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, # Test metadata only
},
}]
}]
_APP_KEY = '84956560bc028eb7'
@ -92,8 +113,12 @@ class BiliBiliIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
if 'anime/' not in url:
cid = compat_parse_qs(self._search_regex(
cid = self._search_regex(
r'\bcid(?:["\']:|=)(\d+)', webpage, 'cid',
default=None
) or compat_parse_qs(self._search_regex(
[r'EmbedPlayer\([^)]+,\s*"([^"]+)"\)',
r'EmbedPlayer\([^)]+,\s*\\"([^"]+)\\"\)',
r'<iframe[^>]+src="https://secure\.bilibili\.com/secure,([^"]+)"'],
webpage, 'player parameters'))['cid'][0]
else:
@ -102,6 +127,7 @@ class BiliBiliIE(InfoExtractor):
video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id)))
headers = {
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Referer': url
}
headers.update(self.geo_verification_headers())
@ -113,48 +139,66 @@ class BiliBiliIE(InfoExtractor):
self._report_error(js)
cid = js['result']['cid']
payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid)
sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest()
video_info = self._download_json(
'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign),
video_id, note='Downloading video info page',
headers=self.geo_verification_headers())
if 'durl' not in video_info:
self._report_error(video_info)
headers = {
'Referer': url
}
headers.update(self.geo_verification_headers())
entries = []
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
'preference': -2 if 'hd.mp4' in backup_url else -3,
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()
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)
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
'preference': -2 if 'hd.mp4' in backup_url else -3,
})
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
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,
})
title = self._html_search_regex('<h1[^>]*>([^<]+)</h1>', webpage, 'title')
title = self._html_search_regex(
('<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
'(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
group='title')
description = self._html_search_meta('description', webpage)
timestamp = unified_timestamp(self._html_search_regex(
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time', default=None))
r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time',
default=None) or self._html_search_meta(
'uploadDate', webpage, 'timestamp', default=None))
thumbnail = self._html_search_meta(['og:image', 'thumbnailUrl'], webpage)
# TODO 'view_count' requires deobfuscating Javascript
@ -168,13 +212,16 @@ class BiliBiliIE(InfoExtractor):
}
uploader_mobj = re.search(
r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]+title="(?P<name>[^"]+)"',
r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]*>(?P<name>[^<]+)',
webpage)
if uploader_mobj:
info.update({
'uploader': uploader_mobj.group('name'),
'uploader_id': uploader_mobj.group('id'),
})
if not info.get('uploader'):
info['uploader'] = self._html_search_meta(
'author', webpage, 'uploader', default=None)
for entry in entries:
entry.update(info)

120
youtube_dl/extractor/bitchute.py Normal file
View File

@ -0,0 +1,120 @@
# coding: utf-8
from __future__ import unicode_literals
import itertools
import re
from .common import InfoExtractor
from ..utils import urlencode_postdata
class BitChuteIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.bitchute.com/video/szoMrox2JEI/',
'md5': '66c4a70e6bfc40dcb6be3eb1d74939eb',
'info_dict': {
'id': 'szoMrox2JEI',
'ext': 'mp4',
'title': 'Fuck bitches get money',
'description': 'md5:3f21f6fb5b1d17c3dee9cf6b5fe60b3a',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Victoria X Rave',
},
}, {
'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
'only_matching': True,
}, {
'url': 'https://www.bitchute.com/torrent/Zee5BE49045h/szoMrox2JEI.webtorrent',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://www.bitchute.com/video/%s' % video_id, video_id, headers={
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
})
title = self._search_regex(
(r'<[^>]+\bid=["\']video-title[^>]+>([^<]+)', r'<title>([^<]+)'),
webpage, 'title', default=None) or self._html_search_meta(
'description', webpage, 'title',
default=None) or self._og_search_description(webpage)
formats = [
{'url': mobj.group('url')}
for mobj in re.finditer(
r'addWebSeed\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage)]
self._sort_formats(formats)
description = self._html_search_regex(
r'(?s)<div\b[^>]+\bclass=["\']full hidden[^>]+>(.+?)</div>',
webpage, 'description', fatal=False)
thumbnail = self._og_search_thumbnail(
webpage, default=None) or self._html_search_meta(
'twitter:image:src', webpage, 'thumbnail')
uploader = self._html_search_regex(
r'(?s)<p\b[^>]+\bclass=["\']video-author[^>]+>(.+?)</p>', webpage,
'uploader', fatal=False)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'formats': formats,
}
class BitChuteChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
_TEST = {
'url': 'https://www.bitchute.com/channel/victoriaxrave/',
'playlist_mincount': 185,
'info_dict': {
'id': 'victoriaxrave',
},
}
_TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
def _entries(self, channel_id):
channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
offset = 0
for page_num in itertools.count(1):
data = self._download_json(
'%sextend/' % channel_url, channel_id,
'Downloading channel page %d' % page_num,
data=urlencode_postdata({
'csrfmiddlewaretoken': self._TOKEN,
'name': '',
'offset': offset,
}), headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Referer': channel_url,
'X-Requested-With': 'XMLHttpRequest',
'Cookie': 'csrftoken=%s' % self._TOKEN,
})
if data.get('success') is False:
break
html = data.get('html')
if not html:
break
video_ids = re.findall(
r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
html)
if not video_ids:
break
offset += len(video_ids)
for video_id in video_ids:
yield self.url_result(
'https://www.bitchute.com/video/%s' % video_id,
ie=BitChuteIE.ie_key(), video_id=video_id)
def _real_extract(self, url):
channel_id = self._match_id(url)
return self.playlist_result(
self._entries(channel_id), playlist_id=channel_id)

146
youtube_dl/extractor/br.py
View File

@ -1,20 +1,23 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_duration,
parse_iso8601,
xpath_element,
xpath_text,
)
class BRIE(InfoExtractor):
IE_DESC = 'Bayerischer Rundfunk Mediathek'
IE_DESC = 'Bayerischer Rundfunk'
_VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
_TESTS = [
@ -123,10 +126,10 @@ class BRIE(InfoExtractor):
for asset in assets.findall('asset'):
format_url = xpath_text(asset, ['downloadUrl', 'url'])
asset_type = asset.get('type')
if asset_type == 'HDS':
if asset_type.startswith('HDS'):
formats.extend(self._extract_f4m_formats(
format_url + '?hdcore=3.2.0', media_id, f4m_id='hds', fatal=False))
elif asset_type == 'HLS':
elif asset_type.startswith('HLS'):
formats.extend(self._extract_m3u8_formats(
format_url, media_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False))
else:
@ -169,3 +172,140 @@ class BRIE(InfoExtractor):
} for variant in variants.findall('variant') if xpath_text(variant, 'url')]
thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
return thumbnails
class BRMediathekIE(InfoExtractor):
IE_DESC = 'Bayerischer Rundfunk Mediathek'
_VALID_URL = r'https?://(?:www\.)?br\.de/mediathek/video/[^/?&#]*?-(?P<id>av:[0-9a-f]{24})'
_TESTS = [{
'url': 'https://www.br.de/mediathek/video/gesundheit-die-sendung-vom-28112017-av:5a1e6a6e8fce6d001871cc8e',
'md5': 'fdc3d485835966d1622587d08ba632ec',
'info_dict': {
'id': 'av:5a1e6a6e8fce6d001871cc8e',
'ext': 'mp4',
'title': 'Die Sendung vom 28.11.2017',
'description': 'md5:6000cdca5912ab2277e5b7339f201ccc',
'timestamp': 1511942766,
'upload_date': '20171129',
}
}]
def _real_extract(self, url):
clip_id = self._match_id(url)
clip = self._download_json(
'https://proxy-base.master.mango.express/graphql',
clip_id, data=json.dumps({
"query": """{
viewer {
clip(id: "%s") {
title
description
duration
createdAt
ageRestriction
videoFiles {
edges {
node {
publicLocation
fileSize
videoProfile {
width
height
bitrate
encoding
}
}
}
}
captionFiles {
edges {
node {
publicLocation
}
}
}
teaserImages {
edges {
node {
imageFiles {
edges {
node {
publicLocation
width
height
}
}
}
}
}
}
}
}
}""" % clip_id}).encode(), headers={
'Content-Type': 'application/json',
})['data']['viewer']['clip']
title = clip['title']
formats = []
for edge in clip.get('videoFiles', {}).get('edges', []):
node = edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
ext = determine_ext(n_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
n_url, clip_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
else:
video_profile = node.get('videoProfile', {})
tbr = int_or_none(video_profile.get('bitrate'))
format_id = 'http'
if tbr:
format_id += '-%d' % tbr
formats.append({
'format_id': format_id,
'url': n_url,
'width': int_or_none(video_profile.get('width')),
'height': int_or_none(video_profile.get('height')),
'tbr': tbr,
'filesize': int_or_none(node.get('fileSize')),
})
self._sort_formats(formats)
subtitles = {}
for edge in clip.get('captionFiles', {}).get('edges', []):
node = edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
subtitles.setdefault('de', []).append({
'url': n_url,
})
thumbnails = []
for edge in clip.get('teaserImages', {}).get('edges', []):
for image_edge in edge.get('node', {}).get('imageFiles', {}).get('edges', []):
node = image_edge.get('node', {})
n_url = node.get('publicLocation')
if not n_url:
continue
thumbnails.append({
'url': n_url,
'width': int_or_none(node.get('width')),
'height': int_or_none(node.get('height')),
})
return {
'id': clip_id,
'title': title,
'description': clip.get('description'),
'duration': int_or_none(clip.get('duration')),
'timestamp': parse_iso8601(clip.get('createdAt')),
'age_limit': int_or_none(clip.get('ageRestriction')),
'formats': formats,
'subtitles': subtitles,
'thumbnails': thumbnails,
}

146
youtube_dl/extractor/breakcom.py
View File

@ -3,15 +3,15 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
from .youtube import YoutubeIE
from ..utils import (
int_or_none,
parse_age_limit,
url_or_none,
)
class BreakIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?(?P<site>break|screenjunkies)\.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
_VALID_URL = r'https?://(?:www\.)?break\.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
_TESTS = [{
'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
'info_dict': {
@ -19,125 +19,73 @@ class BreakIE(InfoExtractor):
'ext': 'mp4',
'title': 'When Girls Act Like D-Bags',
'age_limit': 13,
},
}, {
# youtube embed
'url': 'http://www.break.com/video/someone-forgot-boat-brakes-work',
'info_dict': {
'id': 'RrrDLdeL2HQ',
'ext': 'mp4',
'title': 'Whale Watching Boat Crashing Into San Diego Dock',
'description': 'md5:afc1b2772f0a8468be51dd80eb021069',
'upload_date': '20160331',
'uploader': 'Steve Holden',
'uploader_id': 'sdholden07',
},
'params': {
'skip_download': True,
}
}, {
'url': 'http://www.screenjunkies.com/video/best-quentin-tarantino-movie-2841915',
'md5': '5c2b686bec3d43de42bde9ec047536b0',
'info_dict': {
'id': '2841915',
'display_id': 'best-quentin-tarantino-movie',
'ext': 'mp4',
'title': 'Best Quentin Tarantino Movie',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 3671,
'age_limit': 13,
'tags': list,
},
}, {
'url': 'http://www.screenjunkies.com/video/honest-trailers-the-dark-knight',
'info_dict': {
'id': '2348808',
'display_id': 'honest-trailers-the-dark-knight',
'ext': 'mp4',
'title': 'Honest Trailers - The Dark Knight',
'thumbnail': r're:^https?://.*\.(?:jpg|png)',
'age_limit': 10,
'tags': list,
},
}, {
# requires subscription but worked around
'url': 'http://www.screenjunkies.com/video/knocking-dead-ep-1-the-show-so-far-3003285',
'info_dict': {
'id': '3003285',
'display_id': 'knocking-dead-ep-1-the-show-so-far',
'ext': 'mp4',
'title': 'State of The Dead Recap: Knocking Dead Pilot',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 3307,
'age_limit': 13,
'tags': list,
},
}, {
'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
'only_matching': True,
}]
_DEFAULT_BITRATES = (48, 150, 320, 496, 864, 2240, 3264)
def _real_extract(self, url):
site, display_id, video_id = re.match(self._VALID_URL, url).groups()
display_id, video_id = re.match(self._VALID_URL, url).groups()
if not video_id:
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
(r'src=["\']/embed/(\d+)', r'data-video-content-id=["\'](\d+)'),
webpage, 'video id')
webpage = self._download_webpage(url, display_id)
webpage = self._download_webpage(
'http://www.%s.com/embed/%s' % (site, video_id),
display_id, 'Downloading video embed page')
embed_vars = self._parse_json(
youtube_url = YoutubeIE._extract_url(webpage)
if youtube_url:
return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
content = self._parse_json(
self._search_regex(
r'(?s)embedVars\s*=\s*({.+?})\s*</script>', webpage, 'embed vars'),
r'(?s)content["\']\s*:\s*(\[.+?\])\s*[,\n]', webpage,
'content'),
display_id)
youtube_id = embed_vars.get('youtubeId')
if youtube_id:
return self.url_result(youtube_id, 'Youtube')
title = embed_vars['contentName']
formats = []
bitrates = []
for f in embed_vars.get('media', []):
if not f.get('uri') or f.get('mediaPurpose') != 'play':
for video in content:
video_url = url_or_none(video.get('url'))
if not video_url:
continue
bitrate = int_or_none(f.get('bitRate'))
if bitrate:
bitrates.append(bitrate)
bitrate = int_or_none(self._search_regex(
r'(\d+)_kbps', video_url, 'tbr', default=None))
formats.append({
'url': f['uri'],
'url': video_url,
'format_id': 'http-%d' % bitrate if bitrate else 'http',
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
'tbr': bitrate,
'format': 'mp4',
})
if not bitrates:
# When subscriptionLevel > 0, i.e. plus subscription is required
# media list will be empty. However, hds and hls uris are still
# available. We can grab them assuming bitrates to be default.
bitrates = self._DEFAULT_BITRATES
auth_token = embed_vars.get('AuthToken')
def construct_manifest_url(base_url, ext):
pieces = [base_url]
pieces.extend([compat_str(b) for b in bitrates])
pieces.append('_kbps.mp4.%s?%s' % (ext, auth_token))
return ','.join(pieces)
if bitrates and auth_token:
hds_url = embed_vars.get('hdsUri')
if hds_url:
formats.extend(self._extract_f4m_formats(
construct_manifest_url(hds_url, 'f4m'),
display_id, f4m_id='hds', fatal=False))
hls_url = embed_vars.get('hlsUri')
if hls_url:
formats.extend(self._extract_m3u8_formats(
construct_manifest_url(hls_url, 'm3u8'),
display_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
self._sort_formats(formats)
title = self._search_regex(
(r'title["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
r'<h1[^>]*>(?P<value>[^<]+)'), webpage, 'title', group='value')
def get(key, name):
return int_or_none(self._search_regex(
r'%s["\']\s*:\s*["\'](\d+)' % key, webpage, name,
default=None))
age_limit = get('ratings', 'age limit')
video_id = video_id or get('pid', 'video id') or display_id
return {
'id': video_id,
'display_id': display_id,
'title': title,
'thumbnail': embed_vars.get('thumbUri'),
'duration': int_or_none(embed_vars.get('videoLengthInSeconds')) or None,
'age_limit': parse_age_limit(embed_vars.get('audienceRating')),
'tags': embed_vars.get('tags', '').split(','),
'thumbnail': self._og_search_thumbnail(webpage),
'age_limit': age_limit,
'formats': formats,
}

141
youtube_dl/extractor/brightcove.py
View File

@ -464,7 +464,7 @@ class BrightcoveNewIE(AdobePassIE):
'timestamp': 1441391203,
'upload_date': '20150904',
'uploader_id': '929656772001',
'formats': 'mincount:22',
'formats': 'mincount:20',
},
}, {
# with rtmp streams
@ -478,7 +478,7 @@ class BrightcoveNewIE(AdobePassIE):
'timestamp': 1433556729,
'upload_date': '20150606',
'uploader_id': '4036320279001',
'formats': 'mincount:41',
'formats': 'mincount:39',
},
'params': {
# m3u8 download
@ -564,59 +564,7 @@ class BrightcoveNewIE(AdobePassIE):
return entries
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
self._initialize_geo_bypass(smuggled_data.get('geo_countries'))
account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(
'http://players.brightcove.net/%s/%s_%s/index.min.js'
% (account_id, player_id, embed), video_id)
policy_key = None
catalog = self._search_regex(
r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
if catalog:
catalog = self._parse_json(
js_to_json(catalog), video_id, fatal=False)
if catalog:
policy_key = catalog.get('policyKey')
if not policy_key:
policy_key = self._search_regex(
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id)
try:
json_data = self._download_json(api_url, video_id, headers={
'Accept': 'application/json;pk=%s' % policy_key
})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
message = json_data.get('message') or json_data['error_code']
if json_data.get('error_subcode') == 'CLIENT_GEO':
self.raise_geo_restricted(msg=message)
raise ExtractorError(message, expected=True)
raise
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
custom_fields = json_data['custom_fields']
tve_token = self._extract_mvpd_auth(
smuggled_data['source_url'], video_id,
custom_fields['bcadobepassrequestorid'],
custom_fields['bcadobepassresourceid'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': 'application/json;pk=%s' % policy_key
}, query={
'tveToken': tve_token,
})
def _parse_brightcove_metadata(self, json_data, video_id, headers={}):
title = json_data['name'].strip()
formats = []
@ -624,7 +572,8 @@ class BrightcoveNewIE(AdobePassIE):
container = source.get('container')
ext = mimetype2ext(source.get('type'))
src = source.get('src')
if ext == 'ism' or container == 'WVM':
# https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object
if ext == 'ism' or container == 'WVM' or source.get('key_systems'):
continue
elif ext == 'm3u8' or container == 'M2TS':
if not src:
@ -681,7 +630,16 @@ class BrightcoveNewIE(AdobePassIE):
'format_id': build_format_id('rtmp'),
})
formats.append(f)
if not formats:
# for sonyliv.com DRM protected videos
s3_source_url = json_data.get('custom_fields', {}).get('s3sourceurl')
if s3_source_url:
formats.append({
'url': s3_source_url,
'format_id': 'source',
})
errors = json_data.get('errors')
if not formats and errors:
error = errors[0]
raise ExtractorError(
@ -689,6 +647,9 @@ class BrightcoveNewIE(AdobePassIE):
self._sort_formats(formats)
for f in formats:
f.setdefault('http_headers', {}).update(headers)
subtitles = {}
for text_track in json_data.get('text_tracks', []):
if text_track.get('src'):
@ -708,9 +669,75 @@ class BrightcoveNewIE(AdobePassIE):
'thumbnail': json_data.get('thumbnail') or json_data.get('poster'),
'duration': duration,
'timestamp': parse_iso8601(json_data.get('published_at')),
'uploader_id': account_id,
'uploader_id': json_data.get('account_id'),
'formats': formats,
'subtitles': subtitles,
'tags': json_data.get('tags', []),
'is_live': is_live,
}
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
self._initialize_geo_bypass({
'countries': smuggled_data.get('geo_countries'),
'ip_blocks': smuggled_data.get('geo_ip_blocks'),
})
account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(
'http://players.brightcove.net/%s/%s_%s/index.min.js'
% (account_id, player_id, embed), video_id)
policy_key = None
catalog = self._search_regex(
r'catalog\(({.+?})\);', webpage, 'catalog', default=None)
if catalog:
catalog = self._parse_json(
js_to_json(catalog), video_id, fatal=False)
if catalog:
policy_key = catalog.get('policyKey')
if not policy_key:
policy_key = self._search_regex(
r'policyKey\s*:\s*(["\'])(?P<pk>.+?)\1',
webpage, 'policy key', group='pk')
api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id)
headers = {
'Accept': 'application/json;pk=%s' % policy_key,
}
referrer = smuggled_data.get('referrer')
if referrer:
headers.update({
'Referer': referrer,
'Origin': re.search(r'https?://[^/]+', referrer).group(0),
})
try:
json_data = self._download_json(api_url, video_id, headers=headers)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
json_data = self._parse_json(e.cause.read().decode(), video_id)[0]
message = json_data.get('message') or json_data['error_code']
if json_data.get('error_subcode') == 'CLIENT_GEO':
self.raise_geo_restricted(msg=message)
raise ExtractorError(message, expected=True)
raise
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
custom_fields = json_data['custom_fields']
tve_token = self._extract_mvpd_auth(
smuggled_data['source_url'], video_id,
custom_fields['bcadobepassrequestorid'],
custom_fields['bcadobepassresourceid'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': 'application/json;pk=%s' % policy_key
}, query={
'tveToken': tve_token,
})
return self._parse_brightcove_metadata(
json_data, video_id, headers=headers)

42
youtube_dl/extractor/businessinsider.py Normal file
View File

@ -0,0 +1,42 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from .jwplatform import JWPlatformIE
class BusinessInsiderIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6',
'md5': 'ca237a53a8eb20b6dc5bd60564d4ab3e',
'info_dict': {
'id': 'hZRllCfw',
'ext': 'mp4',
'title': "Here's how much radiation you're exposed to in everyday life",
'description': 'md5:9a0d6e2c279948aadaa5e84d6d9b99bd',
'upload_date': '20170709',
'timestamp': 1499606400,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.businessinsider.nl/5-scientifically-proven-things-make-you-less-attractive-2017-7/',
'only_matching': True,
}, {
'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
jwplatform_id = self._search_regex(
(r'data-media-id=["\']([a-zA-Z0-9]{8})',
r'id=["\']jwplayer_([a-zA-Z0-9]{8})',
r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})'),
webpage, 'jwplatform id')
return self.url_result(
'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
video_id=video_id)

71
youtube_dl/extractor/byutv.py
View File

@ -3,20 +3,19 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class BYUtvIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
_VALID_URL = r'https?://(?:www\.)?byutv\.org/(?:watch|player)/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
_TESTS = [{
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
'info_dict': {
'id': '6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
'id': 'ZvanRocTpW-G5_yZFeltTAMv6jxOU9KH',
'display_id': 'studio-c-season-5-episode-5',
'ext': 'mp4',
'title': 'Season 5 Episode 5',
'description': 'md5:e07269172baff037f8e8bf9956bc9747',
'thumbnail': r're:^https?://.*\.jpg$',
'description': 'md5:1d31dc18ef4f075b28f6a65937d22c65',
'thumbnail': r're:^https?://.*',
'duration': 1486.486,
},
'params': {
@ -26,6 +25,9 @@ class BYUtvIE(InfoExtractor):
}, {
'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
'only_matching': True,
}, {
'url': 'https://www.byutv.org/player/27741493-dc83-40b0-8420-e7ae38a2ae98/byu-football-toledo-vs-byu-93016?listid=4fe0fee5-0d3c-4a29-b725-e4948627f472&listindex=0&q=toledo',
'only_matching': True,
}]
def _real_extract(self, url):
@ -33,16 +35,16 @@ class BYUtvIE(InfoExtractor):
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
episode_code = self._search_regex(
r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
ep = self._parse_json(
episode_code, display_id, transform_source=lambda s:
re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))
if ep['providerType'] != 'Ooyala':
raise ExtractorError('Unsupported provider %s' % ep['provider'])
ep = self._download_json(
'https://api.byutv.org/api3/catalog/getvideosforcontent', video_id,
query={
'contentid': video_id,
'channel': 'byutv',
'x-byutv-context': 'web$US',
}, headers={
'x-byutv-context': 'web$US',
'x-byutv-platformkey': 'xsaaw9c7y5',
})['ooyalaVOD']
return {
'_type': 'url_transparent',
@ -50,44 +52,7 @@ class BYUtvIE(InfoExtractor):
'url': 'ooyala:%s' % ep['providerId'],
'id': video_id,
'display_id': display_id,
'title': ep['title'],
'title': ep.get('title'),
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
}
class BYUtvEventIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?byutv\.org/watch/event/(?P<id>[0-9a-f-]+)'
_TEST = {
'url': 'http://www.byutv.org/watch/event/29941b9b-8bf6-48d2-aebf-7a87add9e34b',
'info_dict': {
'id': '29941b9b-8bf6-48d2-aebf-7a87add9e34b',
'ext': 'mp4',
'title': 'Toledo vs. BYU (9/30/16)',
},
'params': {
'skip_download': True,
},
'add_ie': ['Ooyala'],
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
ooyala_id = self._search_regex(
r'providerId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
webpage, 'ooyala id', group='id')
title = self._search_regex(
r'class=["\']description["\'][^>]*>\s*<h1>([^<]+)</h1>', webpage,
'title').strip()
return {
'_type': 'url_transparent',
'ie_key': 'Ooyala',
'url': 'ooyala:%s' % ooyala_id,
'id': video_id,
'title': title,
}

96
youtube_dl/extractor/cammodels.py Normal file
View File

@ -0,0 +1,96 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
url_or_none,
)
class CamModelsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?cammodels\.com/cam/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.cammodels.com/cam/AutumnKnight/',
'only_matching': True,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
webpage = self._download_webpage(
url, user_id, headers=self.geo_verification_headers())
manifest_root = self._html_search_regex(
r'manifestUrlRoot=([^&\']+)', webpage, 'manifest', default=None)
if not manifest_root:
ERRORS = (
("I'm offline, but let's stay connected", 'This user is currently offline'),
('in a private show', 'This user is in a private show'),
('is currently performing LIVE', 'This model is currently performing live'),
)
for pattern, message in ERRORS:
if pattern in webpage:
error = message
expected = True
break
else:
error = 'Unable to find manifest URL root'
expected = False
raise ExtractorError(error, expected=expected)
manifest = self._download_json(
'%s%s.json' % (manifest_root, user_id), user_id)
formats = []
for format_id, format_dict in manifest['formats'].items():
if not isinstance(format_dict, dict):
continue
encodings = format_dict.get('encodings')
if not isinstance(encodings, list):
continue
vcodec = format_dict.get('videoCodec')
acodec = format_dict.get('audioCodec')
for media in encodings:
if not isinstance(media, dict):
continue
media_url = url_or_none(media.get('location'))
if not media_url:
continue
format_id_list = [format_id]
height = int_or_none(media.get('videoHeight'))
if height is not None:
format_id_list.append('%dp' % height)
f = {
'url': media_url,
'format_id': '-'.join(format_id_list),
'width': int_or_none(media.get('videoWidth')),
'height': height,
'vbr': int_or_none(media.get('videoKbps')),
'abr': int_or_none(media.get('audioKbps')),
'fps': int_or_none(media.get('fps')),
'vcodec': vcodec,
'acodec': acodec,
}
if 'rtmp' in format_id:
f['ext'] = 'flv'
elif 'hls' in format_id:
f.update({
'ext': 'mp4',
# hls skips fragments, preferring rtmp
'preference': -1,
})
else:
continue
formats.append(f)
self._sort_formats(formats)
return {
'id': user_id,
'title': self._live_title(user_id),
'is_live': True,
'formats': formats,
}

69
youtube_dl/extractor/camtube.py Normal file
View File

@ -0,0 +1,69 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_timestamp,
)
class CamTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|api)\.)?camtube\.co/recordings?/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://camtube.co/recording/minafay-030618-1136-chaturbate-female',
'info_dict': {
'id': '42ad3956-dd5b-445a-8313-803ea6079fac',
'display_id': 'minafay-030618-1136-chaturbate-female',
'ext': 'mp4',
'title': 'minafay-030618-1136-chaturbate-female',
'duration': 1274,
'timestamp': 1528018608,
'upload_date': '20180603',
},
'params': {
'skip_download': True,
},
}]
_API_BASE = 'https://api.camtube.co'
def _real_extract(self, url):
display_id = self._match_id(url)
token = self._download_json(
'%s/rpc/session/new' % self._API_BASE, display_id,
'Downloading session token')['token']
self._set_cookie('api.camtube.co', 'session', token)
video = self._download_json(
'%s/recordings/%s' % (self._API_BASE, display_id), display_id,
headers={'Referer': url})
video_id = video['uuid']
timestamp = unified_timestamp(video.get('createdAt'))
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('viewCount'))
like_count = int_or_none(video.get('likeCount'))
creator = video.get('stageName')
formats = [{
'url': '%s/recordings/%s/manifest.m3u8'
% (self._API_BASE, video_id),
'format_id': 'hls',
'ext': 'mp4',
'protocol': 'm3u8_native',
}]
return {
'id': video_id,
'display_id': display_id,
'title': display_id,
'timestamp': timestamp,
'duration': duration,
'view_count': view_count,
'like_count': like_count,
'creator': creator,
'formats': formats,
}

28
youtube_dl/extractor/canalc2.py
View File

@ -31,6 +31,10 @@ class Canalc2IE(InfoExtractor):
webpage = self._download_webpage(
'http://www.canalc2.tv/video/%s' % video_id, video_id)
title = self._html_search_regex(
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.+?)</h3>',
webpage, 'title')
formats = []
for _, video_url in re.findall(r'file\s*=\s*(["\'])(.+?)\1', webpage):
if video_url.startswith('rtmp://'):
@ -49,17 +53,21 @@ class Canalc2IE(InfoExtractor):
'url': video_url,
'format_id': 'http',
})
self._sort_formats(formats)
title = self._html_search_regex(
r'(?s)class="[^"]*col_description[^"]*">.*?<h3>(.*?)</h3>', webpage, 'title')
duration = parse_duration(self._search_regex(
r'id=["\']video_duree["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False))
if formats:
info = {
'formats': formats,
}
else:
info = self._parse_html5_media_entries(url, webpage, url)[0]
return {
self._sort_formats(info['formats'])
info.update({
'id': video_id,
'title': title,
'duration': duration,
'formats': formats,
}
'duration': parse_duration(self._search_regex(
r'id=["\']video_duree["\'][^>]*>([^<]+)',
webpage, 'duration', fatal=False)),
})
return info

99
youtube_dl/extractor/canalplus.py
View File

@ -4,59 +4,36 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlparse
from ..utils import (
dict_get,
# ExtractorError,
# HEADRequest,
int_or_none,
qualities,
remove_end,
unified_strdate,
)
class CanalplusIE(InfoExtractor):
IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv'
_VALID_URL = r'''(?x)
https?://
(?:
(?:
(?:(?:www|m)\.)?canalplus\.fr|
(?:www\.)?piwiplus\.fr|
(?:www\.)?d8\.tv|
(?:www\.)?c8\.fr|
(?:www\.)?d17\.tv|
(?:(?:football|www)\.)?cstar\.fr|
(?:www\.)?itele\.fr
)/(?:(?:[^/]+/)*(?P<display_id>[^/?#&]+))?(?:\?.*\bvid=(?P<vid>\d+))?|
player\.canalplus\.fr/#/(?P<id>\d+)
)
'''
IE_DESC = 'mycanal.fr and piwiplus.fr'
_VALID_URL = r'https?://(?:www\.)?(?P<site>mycanal|piwiplus)\.fr/(?:[^/]+/)*(?P<display_id>[^?/]+)(?:\.html\?.*\bvid=|/p/)(?P<id>\d+)'
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json'
_SITE_ID_MAP = {
'canalplus': 'cplus',
'mycanal': 'cplus',
'piwiplus': 'teletoon',
'd8': 'd8',
'c8': 'd8',
'd17': 'd17',
'cstar': 'd17',
'itele': 'itele',
}
# Only works for direct mp4 URLs
_GEO_COUNTRIES = ['FR']
_TESTS = [{
'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814',
'url': 'https://www.mycanal.fr/d17-emissions/lolywood/p/1397061',
'info_dict': {
'id': '1405510',
'display_id': 'pid1830-c-zapping',
'id': '1397061',
'display_id': 'lolywood',
'ext': 'mp4',
'title': 'Zapping - 02/07/2016',
'description': 'Le meilleur de toutes les chaînes, tous les jours',
'upload_date': '20160702',
'title': 'Euro 2016 : Je préfère te prévenir - Lolywood - Episode 34',
'description': 'md5:7d97039d455cb29cdba0d652a0efaa5e',
'upload_date': '20160602',
},
}, {
# geo restricted, bypassed
@ -70,64 +47,12 @@ class CanalplusIE(InfoExtractor):
'upload_date': '20140724',
},
'expected_warnings': ['HTTP Error 403: Forbidden'],
}, {
# geo restricted, bypassed
'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html?vid=1443684',
'md5': 'bb6f9f343296ab7ebd88c97b660ecf8d',
'info_dict': {
'id': '1443684',
'display_id': 'pid6318-videos-integrales',
'ext': 'mp4',
'title': 'Guess my iep ! - TPMP - 07/04/2017',
'description': 'md5:6f005933f6e06760a9236d9b3b5f17fa',
'upload_date': '20170407',
},
'expected_warnings': ['HTTP Error 403: Forbidden'],
}, {
'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
'info_dict': {
'id': '1420176',
'display_id': 'rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510',
'ext': 'mp4',
'title': 'L\'invité de Michaël Darmon du 14/10/2016 - ',
'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.',
'upload_date': '20161014',
},
}, {
'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769',
'info_dict': {
'id': '1416769',
'display_id': 'pid7566-feminines-videos',
'ext': 'mp4',
'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016',
'description': 'md5:c3f30f2aaac294c1c969b3294de6904e',
'upload_date': '20160921',
},
'params': {
'skip_download': True,
},
}, {
'url': 'http://m.canalplus.fr/?vid=1398231',
'only_matching': True,
}, {
'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
site, display_id, video_id = re.match(self._VALID_URL, url).groups()
site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]]
# Beware, some subclasses do not define an id group
display_id = remove_end(dict_get(mobj.groupdict(), ('display_id', 'id', 'vid')), '.html')
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
[r'<canal:player[^>]+?videoId=(["\'])(?P<id>\d+)',
r'id=["\']canal_video_player(?P<id>\d+)',
r'data-video=["\'](?P<id>\d+)'],
webpage, 'video id', default=mobj.group('vid'), group='id')
site_id = self._SITE_ID_MAP[site]
info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id)
video_data = self._download_json(info_url, video_id, 'Downloading video JSON')
@ -161,7 +86,7 @@ class CanalplusIE(InfoExtractor):
format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False))
else:
formats.append({
# the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js
# the secret extracted from ya function in http://player.canalplus.fr/common/js/canalPlayer.js
'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes',
'format_id': format_id,
'preference': preference(format_id),

289
youtube_dl/extractor/canvas.py
View File

@ -1,26 +1,113 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import float_or_none
from .gigya import GigyaBaseIE
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
strip_or_none,
float_or_none,
int_or_none,
merge_dicts,
parse_iso8601,
)
class CanvasIE(InfoExtractor):
_VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrtvideo)/assets/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'md5': '90139b746a0a9bd7bb631283f6e2a64e',
'info_dict': {
'id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'display_id': 'md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475',
'ext': 'flv',
'title': 'Nachtwacht: De Greystook',
'description': 'md5:1db3f5dc4c7109c821261e7512975be7',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1468.03,
},
'expected_warnings': ['is not a supported codec', 'Unknown MIME type'],
}, {
'url': 'https://mediazone.vrt.be/api/v1/canvas/assets/mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
site_id, video_id = mobj.group('site_id'), mobj.group('id')
data = self._download_json(
'https://mediazone.vrt.be/api/v1/%s/assets/%s'
% (site_id, video_id), video_id)
title = data['title']
description = data.get('description')
formats = []
for target in data['targetUrls']:
format_url, format_type = target.get('url'), target.get('type')
if not format_url or not format_type:
continue
if format_type == 'HLS':
formats.extend(self._extract_m3u8_formats(
format_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id=format_type, fatal=False))
elif format_type == 'HDS':
formats.extend(self._extract_f4m_formats(
format_url, video_id, f4m_id=format_type, fatal=False))
elif format_type == 'MPEG_DASH':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id=format_type, fatal=False))
elif format_type == 'HSS':
formats.extend(self._extract_ism_formats(
format_url, video_id, ism_id='mss', fatal=False))
else:
formats.append({
'format_id': format_type,
'url': format_url,
})
self._sort_formats(formats)
subtitles = {}
subtitle_urls = data.get('subtitleUrls')
if isinstance(subtitle_urls, list):
for subtitle in subtitle_urls:
subtitle_url = subtitle.get('url')
if subtitle_url and subtitle.get('type') == 'CLOSED':
subtitles.setdefault('nl', []).append({'url': subtitle_url})
return {
'id': video_id,
'display_id': video_id,
'title': title,
'description': description,
'formats': formats,
'duration': float_or_none(data.get('duration'), 1000),
'thumbnail': data.get('posterImageUrl'),
'subtitles': subtitles,
}
class CanvasEenIE(InfoExtractor):
IE_DESC = 'canvas.be and een.be'
_VALID_URL = r'https?://(?:www\.)?(?P<site_id>canvas|een)\.be/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.canvas.be/video/de-afspraak/najaar-2015/de-afspraak-veilt-voor-de-warmste-week',
'md5': 'ea838375a547ac787d4064d8c7860a6c',
'md5': 'ed66976748d12350b118455979cca293',
'info_dict': {
'id': 'mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e',
'display_id': 'de-afspraak-veilt-voor-de-warmste-week',
'ext': 'mp4',
'ext': 'flv',
'title': 'De afspraak veilt voor de Warmste Week',
'description': 'md5:24cb860c320dc2be7358e0e5aa317ba6',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 49.02,
}
},
'expected_warnings': ['is not a supported codec'],
}, {
# with subtitles
'url': 'http://www.canvas.be/video/panorama/2016/pieter-0167',
@ -40,7 +127,8 @@ class CanvasIE(InfoExtractor):
},
'params': {
'skip_download': True,
}
},
'skip': 'Pagina niet gevonden',
}, {
'url': 'https://www.een.be/sorry-voor-alles/herbekijk-sorry-voor-alles',
'info_dict': {
@ -54,7 +142,8 @@ class CanvasIE(InfoExtractor):
},
'params': {
'skip_download': True,
}
},
'skip': 'Episode no longer available',
}, {
'url': 'https://www.canvas.be/check-point/najaar-2016/de-politie-uw-vriend',
'only_matching': True,
@ -66,55 +155,161 @@ class CanvasIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
title = (self._search_regex(
title = strip_or_none(self._search_regex(
r'<h1[^>]+class="video__body__header__title"[^>]*>(.+?)</h1>',
webpage, 'title', default=None) or self._og_search_title(
webpage)).strip()
webpage, default=None))
video_id = self._html_search_regex(
r'data-video=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id', group='id')
data = self._download_json(
'https://mediazone.vrt.be/api/v1/%s/assets/%s'
% (site_id, video_id), display_id)
formats = []
for target in data['targetUrls']:
format_url, format_type = target.get('url'), target.get('type')
if not format_url or not format_type:
continue
if format_type == 'HLS':
formats.extend(self._extract_m3u8_formats(
format_url, display_id, entry_protocol='m3u8_native',
ext='mp4', preference=0, fatal=False, m3u8_id=format_type))
elif format_type == 'HDS':
formats.extend(self._extract_f4m_formats(
format_url, display_id, f4m_id=format_type, fatal=False))
elif format_type == 'MPEG_DASH':
formats.extend(self._extract_mpd_formats(
format_url, display_id, mpd_id=format_type, fatal=False))
else:
formats.append({
'format_id': format_type,
'url': format_url,
})
self._sort_formats(formats)
subtitles = {}
subtitle_urls = data.get('subtitleUrls')
if isinstance(subtitle_urls, list):
for subtitle in subtitle_urls:
subtitle_url = subtitle.get('url')
if subtitle_url and subtitle.get('type') == 'CLOSED':
subtitles.setdefault('nl', []).append({'url': subtitle_url})
r'data-video=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video id',
group='id')
return {
'_type': 'url_transparent',
'url': 'https://mediazone.vrt.be/api/v1/%s/assets/%s' % (site_id, video_id),
'ie_key': CanvasIE.ie_key(),
'id': video_id,
'display_id': display_id,
'title': title,
'description': self._og_search_description(webpage),
'formats': formats,
'duration': float_or_none(data.get('duration'), 1000),
'thumbnail': data.get('posterImageUrl'),
'subtitles': subtitles,
}
class VrtNUIE(GigyaBaseIE):
IE_DESC = 'VrtNU.be'
_VALID_URL = r'https?://(?:www\.)?vrt\.be/(?P<site_id>vrtnu)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.vrt.be/vrtnu/a-z/postbus-x/1/postbus-x-s1a1/',
'info_dict': {
'id': 'pbs-pub-2e2d8c27-df26-45c9-9dc6-90c78153044d$vid-90c932b1-e21d-4fb8-99b1-db7b49cf74de',
'ext': 'flv',
'title': 'De zwarte weduwe',
'description': 'md5:d90c21dced7db869a85db89a623998d4',
'duration': 1457.04,
'thumbnail': r're:^https?://.*\.jpg$',
'season': '1',
'season_number': 1,
'episode_number': 1,
},
'skip': 'This video is only available for registered users'
}]
_NETRC_MACHINE = 'vrtnu'
_APIKEY = '3_0Z2HujMtiWq_pkAjgnS2Md2E11a1AwZjYiBETtwNE-EoEHDINgtnvcAOpNgmrVGy'
_CONTEXT_ID = 'R3595707040'
def _real_initialize(self):
self._login()
def _login(self):
username, password = self._get_login_info()
if username is None:
return
auth_data = {
'APIKey': self._APIKEY,
'targetEnv': 'jssdk',
'loginID': username,
'password': password,
'authMode': 'cookie',
}
auth_info = self._gigya_login(auth_data)
# Sometimes authentication fails for no good reason, retry
login_attempt = 1
while login_attempt <= 3:
try:
# When requesting a token, no actual token is returned, but the
# necessary cookies are set.
self._request_webpage(
'https://token.vrt.be',
None, note='Requesting a token', errnote='Could not get a token',
headers={
'Content-Type': 'application/json',
'Referer': 'https://www.vrt.be/vrtnu/',
},
data=json.dumps({
'uid': auth_info['UID'],
'uidsig': auth_info['UIDSignature'],
'ts': auth_info['signatureTimestamp'],
'email': auth_info['profile']['email'],
}).encode('utf-8'))
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
login_attempt += 1
self.report_warning('Authentication failed')
self._sleep(1, None, msg_template='Waiting for %(timeout)s seconds before trying again')
else:
raise e
else:
break
def _real_extract(self, url):
display_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(url, display_id)
info = self._search_json_ld(webpage, display_id, default={})
# title is optional here since it may be extracted by extractor
# that is delegated from here
title = strip_or_none(self._html_search_regex(
r'(?ms)<h1 class="content__heading">(.+?)</h1>',
webpage, 'title', default=None))
description = self._html_search_regex(
r'(?ms)<div class="content__description">(.+?)</div>',
webpage, 'description', default=None)
season = self._html_search_regex(
[r'''(?xms)<div\ class="tabs__tab\ tabs__tab--active">\s*
<span>seizoen\ (.+?)</span>\s*
</div>''',
r'<option value="seizoen (\d{1,3})" data-href="[^"]+?" selected>'],
webpage, 'season', default=None)
season_number = int_or_none(season)
episode_number = int_or_none(self._html_search_regex(
r'''(?xms)<div\ class="content__episode">\s*
<abbr\ title="aflevering">afl</abbr>\s*<span>(\d+)</span>
</div>''',
webpage, 'episode_number', default=None))
release_date = parse_iso8601(self._html_search_regex(
r'(?ms)<div class="content__broadcastdate">\s*<time\ datetime="(.+?)"',
webpage, 'release_date', default=None))
# If there's a ? or a # in the URL, remove them and everything after
clean_url = urlh.geturl().split('?')[0].split('#')[0].strip('/')
securevideo_url = clean_url + '.mssecurevideo.json'
try:
video = self._download_json(securevideo_url, display_id)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
self.raise_login_required()
raise
# We are dealing with a '../<show>.relevant' URL
redirect_url = video.get('url')
if redirect_url:
return self.url_result(self._proto_relative_url(redirect_url, 'https:'))
# There is only one entry, but with an unknown key, so just get
# the first one
video_id = list(video.values())[0].get('videoid')
return merge_dicts(info, {
'_type': 'url_transparent',
'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id,
'ie_key': CanvasIE.ie_key(),
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'season': season,
'season_number': season_number,
'episode_number': episode_number,
'release_date': release_date,
})

2
youtube_dl/extractor/cartoonnetwork.py
View File

@ -31,7 +31,7 @@ class CartoonNetworkIE(TurnerBaseIE):
'http://www.cartoonnetwork.com/video-seo-svc/episodeservices/getCvpPlaylist?networkName=CN2&' + query, video_id, {
'secure': {
'media_src': 'http://androidhls-secure.cdn.turner.com/toon/big',
'tokenizer_src': 'http://www.cartoonnetwork.com/cntv/mvpd/processors/services/token_ipadAdobe.do',
'tokenizer_src': 'https://token.vgtf.net/token/token_mobile',
},
}, {
'url': url,

137
youtube_dl/extractor/cbc.py
View File

@ -1,10 +1,14 @@
# coding: utf-8
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..compat import (
compat_str,
compat_HTTPError,
)
from ..utils import (
js_to_json,
smuggle_url,
@ -13,8 +17,11 @@ from ..utils import (
xpath_element,
xpath_with_ns,
find_xpath_attr,
orderedSet,
parse_duration,
parse_iso8601,
parse_age_limit,
strip_or_none,
int_or_none,
ExtractorError,
)
@ -124,15 +131,23 @@ class CBCIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
title = self._og_search_title(webpage, default=None) or self._html_search_meta(
'twitter:title', webpage, 'title', default=None) or self._html_search_regex(
r'<title>([^<]+)</title>', webpage, 'title', fatal=False)
entries = [
self._extract_player_init(player_init, display_id)
for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
media_ids = []
for media_id_re in (
r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"',
r'<div[^>]+\bid=["\']player-(\d+)',
r'guid["\']\s*:\s*["\'](\d+)'):
media_ids.extend(re.findall(media_id_re, webpage))
entries.extend([
self.url_result('cbcplayer:%s' % media_id, 'CBCPlayer', media_id)
for media_id in re.findall(r'<iframe[^>]+src="[^"]+?mediaId=(\d+)"', webpage)])
for media_id in orderedSet(media_ids)])
return self.playlist_result(
entries, display_id,
self._og_search_title(webpage, fatal=False),
entries, display_id, strip_or_none(title),
self._og_search_description(webpage))
@ -204,30 +219,48 @@ class CBCWatchBaseIE(InfoExtractor):
def _call_api(self, path, video_id):
url = path if path.startswith('http') else self._API_BASE_URL + path
result = self._download_xml(url, video_id, headers={
'X-Clearleap-DeviceId': self._device_id,
'X-Clearleap-DeviceToken': self._device_token,
})
for _ in range(2):
try:
result = self._download_xml(url, video_id, headers={
'X-Clearleap-DeviceId': self._device_id,
'X-Clearleap-DeviceToken': self._device_token,
})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
# Device token has expired, re-acquiring device token
self._register_device()
continue
raise
error_message = xpath_text(result, 'userMessage') or xpath_text(result, 'systemMessage')
if error_message:
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message))
return result
def _real_initialize(self):
if not self._device_id or not self._device_token:
device = self._downloader.cache.load('cbcwatch', 'device') or {}
self._device_id, self._device_token = device.get('id'), device.get('token')
if not self._device_id or not self._device_token:
result = self._download_xml(
self._API_BASE_URL + 'device/register',
None, data=b'<device><type>web</type></device>')
self._device_id = xpath_text(result, 'deviceId', fatal=True)
self._device_token = xpath_text(result, 'deviceToken', fatal=True)
self._downloader.cache.store(
'cbcwatch', 'device', {
'id': self._device_id,
'token': self._device_token,
})
if self._valid_device_token():
return
device = self._downloader.cache.load('cbcwatch', 'device') or {}
self._device_id, self._device_token = device.get('id'), device.get('token')
if self._valid_device_token():
return
self._register_device()
def _valid_device_token(self):
return self._device_id and self._device_token
def _register_device(self):
self._device_id = self._device_token = None
result = self._download_xml(
self._API_BASE_URL + 'device/register',
None, 'Acquiring device token',
data=b'<device><type>web</type></device>')
self._device_id = xpath_text(result, 'deviceId', fatal=True)
self._device_token = xpath_text(result, 'deviceToken', fatal=True)
self._downloader.cache.store(
'cbcwatch', 'device', {
'id': self._device_id,
'token': self._device_token,
})
def _parse_rss_feed(self, rss):
channel = xpath_element(rss, 'channel', fatal=True)
@ -359,3 +392,63 @@ class CBCWatchIE(CBCWatchBaseIE):
video_id = self._match_id(url)
rss = self._call_api('web/browse/' + video_id, video_id)
return self._parse_rss_feed(rss)
class CBCOlympicsIE(InfoExtractor):
IE_NAME = 'cbc.ca:olympics'
_VALID_URL = r'https?://olympics\.cbc\.ca/video/[^/]+/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://olympics.cbc.ca/video/whats-on-tv/olympic-morning-featuring-the-opening-ceremony/',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._hidden_inputs(webpage)['videoId']
video_doc = self._download_xml(
'https://olympics.cbc.ca/videodata/%s.xml' % video_id, video_id)
title = xpath_text(video_doc, 'title', fatal=True)
is_live = xpath_text(video_doc, 'kind') == 'Live'
if is_live:
title = self._live_title(title)
formats = []
for video_source in video_doc.findall('videoSources/videoSource'):
uri = xpath_text(video_source, 'uri')
if not uri:
continue
tokenize = self._download_json(
'https://olympics.cbc.ca/api/api-akamai/tokenize',
video_id, data=json.dumps({
'VideoSource': uri,
}).encode(), headers={
'Content-Type': 'application/json',
'Referer': url,
# d3.VideoPlayer._init in https://olympics.cbc.ca/components/script/base.js
'Cookie': '_dvp=TK:C0ObxjerU', # AKAMAI CDN cookie
}, fatal=False)
if not tokenize:
continue
content_url = tokenize['ContentUrl']
video_source_format = video_source.get('format')
if video_source_format == 'IIS':
formats.extend(self._extract_ism_formats(
content_url, video_id, ism_id=video_source_format, fatal=False))
else:
formats.extend(self._extract_m3u8_formats(
content_url, video_id, 'mp4',
'm3u8' if is_live else 'm3u8_native',
m3u8_id=video_source_format, fatal=False))
self._sort_formats(formats)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': xpath_text(video_doc, 'description'),
'thumbnail': xpath_text(video_doc, 'thumbnailUrl'),
'duration': parse_duration(xpath_text(video_doc, 'duration')),
'formats': formats,
'is_live': is_live,
}

16
youtube_dl/extractor/cbs.py
View File

@ -2,6 +2,7 @@ from __future__ import unicode_literals
from .theplatform import ThePlatformFeedIE
from ..utils import (
ExtractorError,
int_or_none,
find_xpath_attr,
xpath_element,
@ -61,9 +62,10 @@ class CBSIE(CBSBaseIE):
asset_types = []
subtitles = {}
formats = []
last_e = None
for item in items_data.findall('.//item'):
asset_type = xpath_text(item, 'assetType')
if not asset_type or asset_type in asset_types:
if not asset_type or asset_type in asset_types or asset_type in ('HLS_FPS', 'DASH_CENC'):
continue
asset_types.append(asset_type)
query = {
@ -74,11 +76,17 @@ class CBSIE(CBSBaseIE):
query['formats'] = 'MPEG4,M3U'
elif asset_type in ('RTMP', 'WIFI', '3G'):
query['formats'] = 'MPEG4,FLV'
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query(tp_release_url, query), content_id,
'Downloading %s SMIL data' % asset_type)
try:
tp_formats, tp_subtitles = self._extract_theplatform_smil(
update_url_query(tp_release_url, query), content_id,
'Downloading %s SMIL data' % asset_type)
except ExtractorError as e:
last_e = e
continue
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
if last_e and not formats:
raise last_e
self._sort_formats(formats)
info = self._extract_theplatform_metadata(tp_path, content_id)

4
youtube_dl/extractor/cbsinteractive.py
View File

@ -75,10 +75,10 @@ class CBSInteractiveIE(CBSIE):
webpage = self._download_webpage(url, display_id)
data_json = self._html_search_regex(
r"data-(?:cnet|zdnet)-video(?:-uvp(?:js)?)?-options='([^']+)'",
r"data(?:-(?:cnet|zdnet))?-video(?:-(?:uvp(?:js)?|player))?-options='([^']+)'",
webpage, 'data json')
data = self._parse_json(data_json, display_id)
vdata = data.get('video') or data['videos'][0]
vdata = data.get('video') or (data.get('videos') or data.get('playlist'))[0]
video_id = vdata['mpxRefId']

10
youtube_dl/extractor/cbslocal.py
View File

@ -91,12 +91,10 @@ class CBSLocalIE(AnvatoIE):
info_dict = self._extract_anvato_videos(webpage, display_id)
time_str = self._html_search_regex(
r'class="entry-date">([^<]+)<', webpage, 'released date', default=None)
if time_str:
timestamp = unified_timestamp(time_str)
else:
timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage))
timestamp = unified_timestamp(self._html_search_regex(
r'class="(?:entry|post)-date"[^>]*>([^<]+)', webpage,
'released date', default=None)) or parse_iso8601(
self._html_search_meta('uploadDate', webpage))
info_dict.update({
'display_id': display_id,

23
youtube_dl/extractor/cbssports.py
View File

@ -4,28 +4,35 @@ from .cbs import CBSBaseIE
class CBSSportsIE(CBSBaseIE):
_VALID_URL = r'https?://(?:www\.)?cbssports\.com/video/player/[^/]+/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/(?:video|news)/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'http://www.cbssports.com/video/player/videos/708337219968/0/ben-simmons-the-next-lebron?-not-so-fast',
'url': 'https://www.cbssports.com/nba/video/donovan-mitchell-flashes-star-potential-in-game-2-victory-over-thunder/',
'info_dict': {
'id': '708337219968',
'id': '1214315075735',
'ext': 'mp4',
'title': 'Ben Simmons the next LeBron? Not so fast',
'description': 'md5:854294f627921baba1f4b9a990d87197',
'timestamp': 1466293740,
'upload_date': '20160618',
'title': 'Donovan Mitchell flashes star potential in Game 2 victory over Thunder',
'description': 'md5:df6f48622612c2d6bd2e295ddef58def',
'timestamp': 1524111457,
'upload_date': '20180419',
'uploader': 'CBSI-NEW',
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://www.cbssports.com/nba/news/nba-playoffs-2018-watch-76ers-vs-heat-game-3-series-schedule-tv-channel-online-stream/',
'only_matching': True,
}]
def _extract_video_info(self, filter_query, video_id):
return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
[r'(?:=|%26)pcid%3D(\d+)', r'embedVideo(?:Container)?_(\d+)'],
webpage, 'video id')
return self._extract_video_info('byId=%s' % video_id, video_id)

52
youtube_dl/extractor/ccma.py
View File

@ -5,10 +5,12 @@ import re
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
parse_duration,
parse_iso8601,
clean_html,
parse_resolution,
url_or_none,
)
@ -40,34 +42,42 @@ class CCMAIE(InfoExtractor):
def _real_extract(self, url):
media_type, media_id = re.match(self._VALID_URL, url).groups()
media_data = {}
formats = []
profiles = ['pc'] if media_type == 'audio' else ['mobil', 'pc']
for i, profile in enumerate(profiles):
md = self._download_json('http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
media = self._download_json(
'http://dinamics.ccma.cat/pvideo/media.jsp', media_id, query={
'media': media_type,
'idint': media_id,
'profile': profile,
}, fatal=False)
if md:
media_data = md
media_url = media_data.get('media', {}).get('url')
if media_url:
formats.append({
'format_id': profile,
'url': media_url,
'quality': i,
})
})
formats = []
media_url = media['media']['url']
if isinstance(media_url, list):
for format_ in media_url:
format_url = url_or_none(format_.get('file'))
if not format_url:
continue
label = format_.get('label')
f = parse_resolution(label)
f.update({
'url': format_url,
'format_id': label,
})
formats.append(f)
else:
formats.append({
'url': media_url,
'vcodec': 'none' if media_type == 'audio' else None,
})
self._sort_formats(formats)
informacio = media_data['informacio']
informacio = media['informacio']
title = informacio['titol']
durada = informacio.get('durada', {})
duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text'))
timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc'))
subtitles = {}
subtitols = media_data.get('subtitols', {})
subtitols = media.get('subtitols', {})
if subtitols:
sub_url = subtitols.get('url')
if sub_url:
@ -77,7 +87,7 @@ class CCMAIE(InfoExtractor):
})
thumbnails = []
imatges = media_data.get('imatges', {})
imatges = media.get('imatges', {})
if imatges:
thumbnail_url = imatges.get('url')
if thumbnail_url:
@ -93,7 +103,7 @@ class CCMAIE(InfoExtractor):
'description': clean_html(informacio.get('descripcio')),
'duration': duration,
'timestamp': timestamp,
'thumnails': thumbnails,
'thumbnails': thumbnails,
'subtitles': subtitles,
'formats': formats,
}

0
youtube_dl/extractor/cda.py Executable file → Normal file
View File

16
youtube_dl/extractor/ceskatelevize.py
View File

@ -13,6 +13,7 @@ from ..utils import (
float_or_none,
sanitized_Request,
unescapeHTML,
update_url_query,
urlencode_postdata,
USER_AGENTS,
)
@ -107,7 +108,7 @@ class CeskaTelevizeIE(InfoExtractor):
for user_agent in (None, USER_AGENTS['Safari']):
req = sanitized_Request(
'http://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
'https://www.ceskatelevize.cz/ivysilani/ajax/get-client-playlist',
data=urlencode_postdata(data))
req.add_header('Content-type', 'application/x-www-form-urlencoded')
@ -265,6 +266,10 @@ class CeskaTelevizePoradyIE(InfoExtractor):
# m3u8 download
'skip_download': True,
},
}, {
# iframe embed
'url': 'http://www.ceskatelevize.cz/porady/10614999031-neviditelni/21251212048/',
'only_matching': True,
}]
def _real_extract(self, url):
@ -272,8 +277,11 @@ class CeskaTelevizePoradyIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
data_url = unescapeHTML(self._search_regex(
r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'iframe player url', group='url'))
data_url = update_url_query(unescapeHTML(self._search_regex(
(r'<span[^>]*\bdata-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?ceskatelevize\.cz/ivysilani/embed/iFramePlayer\.php.*?)\1'),
webpage, 'iframe player url', group='url')), query={
'autoStart': 'true',
})
return self.url_result(data_url, ie=CeskaTelevizeIE.ie_key())

6
youtube_dl/extractor/channel9.py
View File

@ -81,6 +81,12 @@ class Channel9IE(InfoExtractor):
_RSS_URL = 'http://channel9.msdn.com/%s/RSS'
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+src=["\'](https?://channel9\.msdn\.com/(?:[^/]+/)+)player\b',
webpage)
def _extract_list(self, video_id, rss_url=None):
if not rss_url:
rss_url = self._RSS_URL % video_id

3
youtube_dl/extractor/chaturbate.py
View File

@ -31,7 +31,8 @@ class ChaturbateIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
webpage = self._download_webpage(
url, video_id, headers=self.geo_verification_headers())
m3u8_urls = []

4
youtube_dl/extractor/chilloutzone.py
View File

@ -1,11 +1,11 @@
from __future__ import unicode_literals
import re
import base64
import json
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..compat import compat_b64decode
from ..utils import (
clean_html,
ExtractorError
@ -58,7 +58,7 @@ class ChilloutzoneIE(InfoExtractor):
base64_video_info = self._html_search_regex(
r'var cozVidData = "(.+?)";', webpage, 'video data')
decoded_video_info = base64.b64decode(base64_video_info.encode('utf-8')).decode('utf-8')
decoded_video_info = compat_b64decode(base64_video_info).decode('utf-8')
video_info_dict = json.loads(decoded_video_info)
# get video information from dict

5
youtube_dl/extractor/chirbit.py
View File

@ -1,10 +1,10 @@
# coding: utf-8
from __future__ import unicode_literals
import base64
import re
from .common import InfoExtractor
from ..compat import compat_b64decode
from ..utils import parse_duration
@ -44,8 +44,7 @@ class ChirbitIE(InfoExtractor):
# Reverse engineered from https://chirb.it/js/chirbit.player.js (look
# for soundURL)
audio_url = base64.b64decode(
data_fd[::-1].encode('ascii')).decode('utf-8')
audio_url = compat_b64decode(data_fd[::-1]).decode('utf-8')
title = self._search_regex(
r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title')

60
youtube_dl/extractor/cloudflarestream.py Normal file
View File

@ -0,0 +1,60 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class CloudflareStreamIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
(?:watch\.)?cloudflarestream\.com/|
embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=
)
(?P<id>[\da-f]+)
'''
_TESTS = [{
'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717',
'info_dict': {
'id': '31c9291ab41fac05471db4e73aa11717',
'ext': 'mp4',
'title': '31c9291ab41fac05471db4e73aa11717',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://watch.cloudflarestream.com/9df17203414fd1db3e3ed74abbe936c1',
'only_matching': True,
}, {
'url': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/manifest/video.mpd',
'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return [
mobj.group('url')
for mobj in re.finditer(
r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1',
webpage)]
def _real_extract(self, url):
video_id = self._match_id(url)
formats = self._extract_m3u8_formats(
'https://cloudflarestream.com/%s/manifest/video.m3u8' % video_id,
video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls',
fatal=False)
formats.extend(self._extract_mpd_formats(
'https://cloudflarestream.com/%s/manifest/video.mpd' % video_id,
video_id, mpd_id='dash', fatal=False))
self._sort_formats(formats)
return {
'id': video_id,
'title': video_id,
'formats': formats,
}

35
youtube_dl/extractor/clyp.py
View File

@ -1,15 +1,19 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urllib_parse_urlparse,
)
from ..utils import (
float_or_none,
parse_iso8601,
unified_timestamp,
)
class ClypIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?clyp\.it/(?P<id>[a-z0-9]+)'
_TEST = {
_TESTS = [{
'url': 'https://clyp.it/ojz2wfah',
'md5': '1d4961036c41247ecfdcc439c0cddcbb',
'info_dict': {
@ -21,13 +25,34 @@ class ClypIE(InfoExtractor):
'timestamp': 1443515251,
'upload_date': '20150929',
},
}
}, {
'url': 'https://clyp.it/b04p1odi?token=b0078e077e15835845c528a44417719d',
'info_dict': {
'id': 'b04p1odi',
'ext': 'mp3',
'title': 'GJ! (Reward Edit)',
'description': 'Metal Resistance (THE ONE edition)',
'duration': 177.789,
'timestamp': 1528241278,
'upload_date': '20180605',
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
audio_id = self._match_id(url)
qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
token = qs.get('token', [None])[0]
query = {}
if token:
query['token'] = token
metadata = self._download_json(
'https://api.clyp.it/%s' % audio_id, audio_id)
'https://api.clyp.it/%s' % audio_id, audio_id, query=query)
formats = []
for secure in ('', 'Secure'):
@ -45,7 +70,7 @@ class ClypIE(InfoExtractor):
title = metadata['Title']
description = metadata.get('Description')
duration = float_or_none(metadata.get('Duration'))
timestamp = parse_iso8601(metadata.get('DateCreated'))
timestamp = unified_timestamp(metadata.get('DateCreated'))
return {
'id': audio_id,

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