R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' into 22tracks

Browse Source
This commit is contained in:
Amish Bhadeshia 2015-03-24 18:28:15 +00:00
commit 8760f03795
532 changed files with 27879 additions and 8124 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored
View File

@ -30,3 +30,6 @@ updates_key.pem
*.swp *.swp
test/testdata test/testdata
.tox .tox
youtube-dl.zsh
.idea
.idea/*

5
.travis.yml
View File

@ -2,14 +2,17 @@ language: python
python: python:
- "2.6" - "2.6"
- "2.7" - "2.7"
- "3.2"
- "3.3" - "3.3"
- "3.4" - "3.4"
before_install:
- sudo apt-get update -qq
- sudo apt-get install -yqq rtmpdump
script: nosetests test --verbose script: nosetests test --verbose
notifications: notifications:
email: email:
- filippo.valsorda@gmail.com - filippo.valsorda@gmail.com
- phihag@phihag.de - phihag@phihag.de
- jaime.marquinez.ferrandiz+travis@gmail.com
- yasoob.khld@gmail.com - yasoob.khld@gmail.com
# irc: # irc:
# channels: # channels:

119
AUTHORS Normal file
View File

@ -0,0 +1,119 @@
Ricardo Garcia Gonzalez
Danny Colligan
Benjamin Johnson
Vasyl' Vavrychuk
Witold Baryluk
Paweł Paprota
Gergely Imreh
Rogério Brito
Philipp Hagemeister
Sören Schulze
Kevin Ngo
Ori Avtalion
shizeeg
Filippo Valsorda
Christian Albrecht
Dave Vasilevsky
Jaime Marquínez Ferrándiz
Jeff Crouse
Osama Khalid
Michael Walter
M. Yasoob Ullah Khalid
Julien Fraichard
Johny Mo Swag
Axel Noack
Albert Kim
Pierre Rudloff
Huarong Huo
Ismael Mejía
Steffan 'Ruirize' James
Andras Elso
Jelle van der Waa
Marcin Cieślak
Anton Larionov
Takuya Tsuchida
Sergey M.
Michael Orlitzky
Chris Gahan
Saimadhav Heblikar
Mike Col
Oleg Prutz
pulpe
Andreas Schmitz
Michael Kaiser
Niklas Laxström
David Triendl
Anthony Weems
David Wagner
Juan C. Olivares
Mattias Harrysson
phaer
Sainyam Kapoor
Nicolas Évrard
Jason Normore
Hoje Lee
Adam Thalhammer
Georg Jähnig
Ralf Haring
Koki Takahashi
Ariset Llerena
Adam Malcontenti-Wilson
Tobias Bell
Naglis Jonaitis
Charles Chen
Hassaan Ali
Dobrosław Żybort
David Fabijan
Sebastian Haas
Alexander Kirk
Erik Johnson
Keith Beckman
Ole Ernst
Aaron McDaniel (mcd1992)
Magnus Kolstad
Hari Padmanaban
Carlos Ramos
5moufl
lenaten
Dennis Scheiba
Damon Timm
winwon
Xavier Beynon
Gabriel Schubiner
xantares
Jan Matějka
Mauroy Sébastien
William Sewell
Dao Hoang Son
Oskar Jauch
Matthew Rayfield
t0mm0
Tithen-Firion
Zack Fernandes
cryptonaut
Adrian Kretz
Mathias Rav
Petr Kutalek
Will Glynn
Max Reimann
Cédric Luthi
Thijs Vermeir
Joel Leclerc
Christopher Krooss
Ondřej Caletka
Dinesh S
Johan K. Jensen
Yen Chi Hsuan
Enam Mijbah Noor
David Luhmer
Shaya Goldberg
Paul Hartmann
Frans de Jonge
Robin de Rooij
Ryan Schmidt
Leslie P. Polzer
Duncan Keall
Alexander Mamay
Devin J. Pohly
Eduardo Ferro Aldama
Jeff Buchbinder

140
CONTRIBUTING.md Normal file
View File

@ -0,0 +1,140 @@
**Please include the full output of youtube-dl when run with `-v`**.
The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
### Is the description of the issue itself sufficient?
We often get issue reports that we cannot really decipher. While in most cases we eventually get the required information after asking back multiple times, this poses an unnecessary drain on our resources. Many contributors, including myself, are also not native speakers, so we may misread some parts.
So please elaborate on what feature you are requesting, or what bug you want to be fixed. Make sure that it's obvious
- What the problem is
- How it could be fixed
- How your proposed solution would look like
If your report is shorter than two lines, it is almost certainly missing some of these, which makes it hard for us to respond to it. We're often too polite to close the issue outright, but the missing info makes misinterpretation likely. As a commiter myself, I often get frustrated by these issues, since the only possible way for me to move forward on them is to ask for clarification over and over.
For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
### Are you using the latest version?
Before reporting any issue, type youtube-dl -U. This should report that you're up-to-date. About 20% of the reports we receive are already fixed, but people are using outdated versions. This goes for feature requests as well.
### Is the issue already documented?
Make sure that someone has not already opened the issue you're trying to open. Search at the top of the window or at https://github.com/rg3/youtube-dl/search?type=Issues . If there is an issue, feel free to write something along the lines of "This affects me as well, with version 2015.01.01. Here is some more information on the issue: ...". While some issues may be old, a new post into them often spurs rapid activity.
### Why are existing options not enough?
Before requesting a new feature, please have a quick peek at [the list of supported options](https://github.com/rg3/youtube-dl/blob/master/README.md#synopsis). Many feature requests are for features that actually exist already! Please, absolutely do show off your work in the issue report and detail how the existing similar options do *not* solve your problem.
### Is there enough context in your bug report?
People want to solve problems, and often think they do us a favor by breaking down their larger problems (e.g. wanting to skip already downloaded files) to a specific request (e.g. requesting us to look whether the file exists before downloading the info page). However, what often happens is that they break down the problem into two steps: One simple, and one impossible (or extremely complicated one).
We are then presented with a very complicated request when the original problem could be solved far easier, e.g. by recording the downloaded video IDs in a separate file. To avoid this, you must include the greater context where it is non-obvious. In particular, every feature request that does not consist of adding support for a new site should contain a use case scenario that explains in what situation the missing feature would be useful.
### Does the issue involve one problem, and one problem only?
Some of our users seem to think there is a limit of issues they can or should open. There is no limit of issues they can or should open. While it may seem appealing to be able to dump all your issues into one ticket, that means that someone who solves one of your issues cannot mark the issue as closed. Typically, reporting a bunch of issues leads to the ticket lingering since nobody wants to attack that behemoth, until someone mercifully splits the issue into multiple ones.
In particular, every site support request issue should only pertain to services at one site (generally under a common domain, but always using the same backend technology). Do not request support for vimeo user videos, Whitehouse podcasts, and Google Plus pages in the same issue. Also, make sure that you don't post bug reports alongside feature requests. As a rule of thumb, a feature request does not include outputs of youtube-dl that are not immediately related to the feature at hand. Do not post reports of a network error alongside the request for a new video service.
### Is anyone going to need the feature?
Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
### Is your question about youtube-dl?
It may sound strange, but some bug reports we receive are completely unrelated to youtube-dl and relate to a different or even the reporter's own application. Please make sure that you are actually using youtube-dl. If you are using a UI for youtube-dl, report the bug to the maintainer of the actual application providing the UI. On the other hand, if your UI for youtube-dl fails in some way you believe is related to youtube-dl, by all means, go ahead and report the bug.
# DEVELOPER INSTRUCTIONS
Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
To run youtube-dl as a developer, you don't need to build anything either. Simply execute
python -m youtube_dl
To run the test, simply invoke your favorite test runner, or execute a test file directly; any of the following work:
python -m unittest discover
python test/test_download.py
nosetests
If you want to create a build of youtube-dl yourself, you'll need
* python
* make
* pandoc
* zip
* nosetests
### Adding support for a new site
If you want to add support for a new site, you can follow this quick list (assuming your service is called `yourextractor`):
1. [Fork this repository](https://github.com/rg3/youtube-dl/fork)
2. Check out the source code with `git clone git@github.com:YOUR_GITHUB_USERNAME/youtube-dl.git`
3. Start a new git branch with `cd youtube-dl; git checkout -b yourextractor`
4. Start with this simple template and save it to `youtube_dl/extractor/yourextractor.py`:
```python
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class YourExtractorIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
_TEST = {
'url': 'http://yourextractor.com/watch/42',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
'info_dict': {
'id': '42',
'ext': 'mp4',
'title': 'Video title goes here',
'thumbnail': 're:^https?://.*\.jpg$',
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
# TODO more properties (see youtube_dl/extractor/common.py)
}
```
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/__init__.py
$ git add youtube_dl/extractor/yourextractor.py
$ git commit -m '[yourextractor] Add new extractor'
$ git push origin yourextractor
10. Finally, [create a pull request](https://help.github.com/articles/creating-a-pull-request). We'll then review and merge it.
In any case, thank you very much for your contributions!

41
Makefile
View File

@ -1,14 +1,13 @@
all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.fish all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish supportedsites
clean: clean:
rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.fish rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe
find -name "*.pyc" -delete
cleanall: clean
rm -f youtube-dl youtube-dl.exe
PREFIX ?= /usr/local PREFIX ?= /usr/local
BINDIR ?= $(PREFIX)/bin BINDIR ?= $(PREFIX)/bin
MANDIR ?= $(PREFIX)/man MANDIR ?= $(PREFIX)/man
SHAREDIR ?= $(PREFIX)/share
PYTHON ?= /usr/bin/env python PYTHON ?= /usr/bin/env python
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
@ -22,23 +21,34 @@ else
endif endif
endif endif
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion install: youtube-dl youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
install -d $(DESTDIR)$(BINDIR) install -d $(DESTDIR)$(BINDIR)
install -m 755 youtube-dl $(DESTDIR)$(BINDIR) install -m 755 youtube-dl $(DESTDIR)$(BINDIR)
install -d $(DESTDIR)$(MANDIR)/man1 install -d $(DESTDIR)$(MANDIR)/man1
install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1 install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1
install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl install -m 644 youtube-dl.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/youtube-dl
install -d $(DESTDIR)$(SHAREDIR)/zsh/site-functions
install -m 644 youtube-dl.zsh $(DESTDIR)$(SHAREDIR)/zsh/site-functions/_youtube-dl
install -d $(DESTDIR)$(SYSCONFDIR)/fish/completions install -d $(DESTDIR)$(SYSCONFDIR)/fish/completions
install -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish install -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish
codetest:
flake8 .
test: test:
#nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test #nosetests --with-coverage --cover-package=youtube_dl --cover-html --verbose --processes 4 test
nosetests --verbose test nosetests --verbose test
$(MAKE) codetest
ot: offlinetest
offlinetest: codetest
nosetests --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
tar: youtube-dl.tar.gz tar: youtube-dl.tar.gz
.PHONY: all clean install test tar bash-completion pypi-files fish-completion .PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest supportedsites
pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish
@ -51,7 +61,13 @@ youtube-dl: youtube_dl/*.py youtube_dl/*/*.py
chmod a+x youtube-dl chmod a+x youtube-dl
README.md: youtube_dl/*.py youtube_dl/*/*.py README.md: youtube_dl/*.py youtube_dl/*/*.py
COLUMNS=80 python -m youtube_dl --help | python devscripts/make_readme.py COLUMNS=80 python youtube_dl/__main__.py --help | python devscripts/make_readme.py
CONTRIBUTING.md: README.md
python devscripts/make_contributing.py README.md CONTRIBUTING.md
supportedsites:
python devscripts/make_supportedsites.py docs/supportedsites.md
README.txt: README.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
@ -66,12 +82,17 @@ youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-co
bash-completion: youtube-dl.bash-completion bash-completion: youtube-dl.bash-completion
youtube-dl.zsh: youtube_dl/*.py youtube_dl/*/*.py devscripts/zsh-completion.in
python devscripts/zsh-completion.py
zsh-completion: youtube-dl.zsh
youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in youtube-dl.fish: youtube_dl/*.py youtube_dl/*/*.py devscripts/fish-completion.in
python devscripts/fish-completion.py python devscripts/fish-completion.py
fish-completion: youtube-dl.fish fish-completion: youtube-dl.fish
youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.fish youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish
@tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \ @tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \
--exclude '*.DS_Store' \ --exclude '*.DS_Store' \
--exclude '*.kate-swp' \ --exclude '*.kate-swp' \
@ -86,5 +107,5 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-
bin devscripts test youtube_dl docs \ bin devscripts test youtube_dl docs \
LICENSE README.md README.txt \ LICENSE README.md README.txt \
Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \ Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \
youtube-dl.fish setup.py \ youtube-dl.zsh youtube-dl.fish setup.py \
youtube-dl youtube-dl

524
README.md
View File

@ -1,7 +1,15 @@
youtube-dl - download videos from youtube.com or other video platforms youtube-dl - download videos from youtube.com or other video platforms
# SYNOPSIS - [INSTALLATION](#installation)
**youtube-dl** [OPTIONS] URL [URL...] - [DESCRIPTION](#description)
- [OPTIONS](#options)
- [CONFIGURATION](#configuration)
- [OUTPUT TEMPLATE](#output-template)
- [VIDEO SELECTION](#video-selection)
- [FAQ](#faq)
- [DEVELOPER INSTRUCTIONS](#developer-instructions)
- [BUGS](#bugs)
- [COPYRIGHT](#copyright)
# INSTALLATION # INSTALLATION
@ -30,162 +38,118 @@ Alternatively, refer to the developer instructions below for how to check out an
# DESCRIPTION # DESCRIPTION
**youtube-dl** is a small command-line program to download videos from **youtube-dl** is a small command-line program to download videos from
YouTube.com and a few more sites. It requires the Python interpreter, version YouTube.com and a few more sites. It requires the Python interpreter, version
2.6, 2.7, or 3.3+, and it is not platform specific. It should work on 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, 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. which means you can modify it, redistribute it or use it however you like.
youtube-dl [OPTIONS] URL [URL...]
# OPTIONS # OPTIONS
-h, --help print this help text and exit -h, --help print this help text and exit
--version print program version and exit --version print program version and exit
-U, --update update this program to latest version. Make -U, --update update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)
sure that you have sufficient permissions -i, --ignore-errors continue on download errors, for example to skip unavailable videos in a playlist
(run with sudo if needed) --abort-on-error Abort downloading of further videos (in the playlist or the command line) if an error occurs
-i, --ignore-errors continue on download errors, for example to
skip unavailable videos in a playlist
--abort-on-error Abort downloading of further videos (in the
playlist or the command line) if an error
occurs
--dump-user-agent display the current browser identification --dump-user-agent display the current browser identification
--list-extractors List all supported extractors and the URLs --list-extractors List all supported extractors and the URLs they would handle
they would handle --extractor-descriptions Output descriptions of all supported extractors
--extractor-descriptions Output descriptions of all supported --default-search PREFIX Use this prefix for unqualified URLs. For example "gvsearch2:" downloads two videos from google videos for youtube-dl "large apple".
extractors Use the value "auto" to let youtube-dl guess ("auto_warning" to emit a warning when guessing). "error" just throws an error. The
--proxy URL Use the specified HTTP/HTTPS proxy. Pass in default value "fixup_error" repairs broken URLs, but emits an error if this is not possible instead of searching.
an empty string (--proxy "") for direct --ignore-config Do not read configuration files. When given in the global configuration file /etc/youtube-dl.conf: Do not read the user configuration
connection in ~/.config/youtube-dl/config (%APPDATA%/youtube-dl/config.txt on Windows)
--socket-timeout None Time to wait before giving up, in seconds --flat-playlist Do not extract the videos of a playlist, only list them.
--default-search PREFIX Use this prefix for unqualified URLs. For --no-color Do not emit color codes in output.
example "gvsearch2:" downloads two videos
from google videos for youtube-dl "large ## Network Options:
apple". Use the value "auto" to let --proxy URL Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection
youtube-dl guess ("auto_warning" to emit a --socket-timeout SECONDS Time to wait before giving up, in seconds
warning when guessing). "error" just throws --source-address IP Client-side IP address to bind to (experimental)
an error. The default value "fixup_error" -4, --force-ipv4 Make all connections via IPv4 (experimental)
repairs broken URLs, but emits an error if -6, --force-ipv6 Make all connections via IPv6 (experimental)
this is not possible instead of searching. --cn-verification-proxy URL Use this proxy to verify the IP address for some Chinese sites. The default proxy specified by --proxy (or none, if the options is
--ignore-config Do not read configuration files. When given not present) is used for the actual downloading. (experimental)
in the global configuration file /etc
/youtube-dl.conf: do not read the user
configuration in ~/.config/youtube-dl.conf
(%APPDATA%/youtube-dl/config.txt on
Windows)
## Video Selection: ## Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1) --playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last) --playlist-end NUMBER playlist video to end at (default is last)
--match-title REGEX download only matching titles (regex or --playlist-items ITEM_SPEC playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8"
caseless sub-string) if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will
--reject-title REGEX skip download for matching titles (regex or download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13.
caseless sub-string) --match-title REGEX download only matching titles (regex or caseless sub-string)
--reject-title REGEX skip download for matching titles (regex or caseless sub-string)
--max-downloads NUMBER Abort after downloading NUMBER files --max-downloads NUMBER Abort after downloading NUMBER files
--min-filesize SIZE Do not download any videos smaller than --min-filesize SIZE Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)
SIZE (e.g. 50k or 44.6m) --max-filesize SIZE Do not download any videos larger than SIZE (e.g. 50k or 44.6m)
--max-filesize SIZE Do not download any videos larger than SIZE
(e.g. 50k or 44.6m)
--date DATE download only videos uploaded in this date --date DATE download only videos uploaded in this date
--datebefore DATE download only videos uploaded on or before --datebefore DATE download only videos uploaded on or before this date (i.e. inclusive)
this date (i.e. inclusive) --dateafter DATE download only videos uploaded on or after this date (i.e. inclusive)
--dateafter DATE download only videos uploaded on or after --min-views COUNT Do not download any videos with less than COUNT views
this date (i.e. inclusive) --max-views COUNT Do not download any videos with more than COUNT views
--min-views COUNT Do not download any videos with less than --match-filter FILTER (Experimental) Generic video filter. Specify any key (see help for -o for a list of available keys) to match if the key is present,
COUNT views !key to check if the key is not present,key > NUMBER (like "comment_count > 12", also works with >=, <, <=, !=, =) to compare against
--max-views COUNT Do not download any videos with more than a number, and & to require multiple matches. Values which are not known are excluded unless you put a question mark (?) after the
COUNT views operator.For example, to only match videos that have been liked more than 100 times and disliked less than 50 times (or the dislike
--no-playlist download only the currently playing video functionality is not available at the given service), but who also have a description, use --match-filter "like_count > 100 &
--age-limit YEARS download only videos suitable for the given dislike_count <? 50 & description" .
age --no-playlist If the URL refers to a video and a playlist, download only the video.
--download-archive FILE Download only videos not listed in the --yes-playlist If the URL refers to a video and a playlist, download the playlist.
archive file. Record the IDs of all --age-limit YEARS download only videos suitable for the given age
downloaded videos in it. --download-archive FILE Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.
--include-ads Download advertisements as well --include-ads Download advertisements as well (experimental)
(experimental)
--youtube-include-dash-manifest Try to download the DASH manifest on
YouTube videos (experimental)
## Download Options: ## Download Options:
-r, --rate-limit LIMIT maximum download rate in bytes per second -r, --rate-limit LIMIT maximum download rate in bytes per second (e.g. 50K or 4.2M)
(e.g. 50K or 4.2M) -R, --retries RETRIES number of retries (default is 10), or "infinite".
-R, --retries RETRIES number of retries (default is 10) --buffer-size SIZE size of download buffer (e.g. 1024 or 16K) (default is 1024)
--buffer-size SIZE size of download buffer (e.g. 1024 or 16K) --no-resize-buffer do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.
(default is 1024) --playlist-reverse Download playlist videos in reverse order
--no-resize-buffer do not automatically adjust the buffer --xattr-set-filesize (experimental) set file xattribute ytdl.filesize with expected filesize
size. By default, the buffer size is --hls-prefer-native (experimental) Use the native HLS downloader instead of ffmpeg.
automatically resized from an initial value --external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,curl,wget
of SIZE. --external-downloader-args ARGS Give these arguments to the external downloader.
## Filesystem Options: ## Filesystem Options:
-a, --batch-file FILE file containing URLs to download ('-' for -a, --batch-file FILE file containing URLs to download ('-' for stdin)
stdin)
--id use only video ID in file name --id use only video ID in file name
-A, --auto-number number downloaded files starting from 00000 -o, --output TEMPLATE output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader
-o, --output TEMPLATE output filename template. Use %(title)s to nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(format)s for
get the title, %(uploader)s for the the format description (like "22 - 1280x720" or "HD"), %(format_id)s for the unique id of the format (like Youtube's itags: "137"),
uploader name, %(uploader_id)s for the %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id,
uploader nickname if different, %(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in,
%(autonumber)s to get an automatically %(playlist_index)s for the position in the playlist. %(height)s and %(width)s for the width and height of the video format.
incremented number, %(ext)s for the %(resolution)s for a textual description of the resolution of the video format. %% for a literal percent. Use - to output to stdout.
filename extension, %(format)s for the Can also be used to download to a different directory, for example with -o '/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
format description (like "22 - 1280x720" or --autonumber-size NUMBER Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given
"HD"), %(format_id)s for the unique id of --restrict-filenames Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames
the format (like Youtube's itags: "137"), -A, --auto-number [deprecated; use -o "%(autonumber)s-%(title)s.%(ext)s" ] number downloaded files starting from 00000
%(upload_date)s for the upload date -t, --title [deprecated] use title in file name (default)
(YYYYMMDD), %(extractor)s for the provider
(youtube, metacafe, etc), %(id)s for the
video id, %(playlist)s for the playlist the
video is in, %(playlist_index)s for the
position in the playlist and %% for a
literal percent. %(height)s and %(width)s
for the width and height of the video
format. %(resolution)s for a textual
description of the resolution of the video
format. Use - to output to stdout. Can also
be used to download to a different
directory, for example with -o '/my/downloa
ds/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
--autonumber-size NUMBER Specifies the number of digits in
%(autonumber)s when it is present in output
filename template or --auto-number option
is given
--restrict-filenames Restrict filenames to only ASCII
characters, and avoid "&" and spaces in
filenames
-t, --title [deprecated] use title in file name
(default)
-l, --literal [deprecated] alias of --title -l, --literal [deprecated] alias of --title
-w, --no-overwrites do not overwrite files -w, --no-overwrites do not overwrite files
-c, --continue force resume of partially downloaded files. -c, --continue force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.
By default, youtube-dl will resume --no-continue do not resume partially downloaded files (restart from beginning)
downloads if possible. --no-part do not use .part files - write directly into output file
--no-continue do not resume partially downloaded files --no-mtime do not use the Last-modified header to set the file modification time
(restart from beginning) --write-description write video description to a .description file
--no-part do not use .part files
--no-mtime do not use the Last-modified header to set
the file modification time
--write-description write video description to a .description
file
--write-info-json write video metadata to a .info.json file --write-info-json write video metadata to a .info.json file
--write-annotations write video annotations to a .annotation --write-annotations write video annotations to a .annotation file
file --load-info FILE json file containing the video information (created with the "--write-json" option)
--write-thumbnail write thumbnail image to disk --cookies FILE file to read cookies from and dump cookie jar in
--load-info FILE json file containing the video information --cache-dir DIR Location in the filesystem where youtube-dl can store some downloaded information permanently. By default $XDG_CACHE_HOME/youtube-dl
(created with the "--write-json" option) or ~/.cache/youtube-dl . At the moment, only YouTube player files (for videos with obfuscated signatures) are cached, but that may
--cookies FILE file to read cookies from and dump cookie change.
jar in
--cache-dir DIR Location in the filesystem where youtube-dl
can store some downloaded information
permanently. By default $XDG_CACHE_HOME
/youtube-dl or ~/.cache/youtube-dl . At the
moment, only YouTube player files (for
videos with obfuscated signatures) are
cached, but that may change.
--no-cache-dir Disable filesystem caching --no-cache-dir Disable filesystem caching
--rm-cache-dir Delete all filesystem cache files --rm-cache-dir Delete all filesystem cache files
## Thumbnail images:
--write-thumbnail write thumbnail image to disk
--write-all-thumbnails write all thumbnail image formats to disk
--list-thumbnails Simulate and list all available thumbnail formats
## Verbosity / Simulation Options: ## Verbosity / Simulation Options:
-q, --quiet activates quiet mode -q, --quiet activates quiet mode
--no-warnings Ignore warnings --no-warnings Ignore warnings
-s, --simulate do not download the video and do not write -s, --simulate do not download the video and do not write anything to disk
anything to disk
--skip-download do not download the video --skip-download do not download the video
-g, --get-url simulate, quiet but print URL -g, --get-url simulate, quiet but print URL
-e, --get-title simulate, quiet but print title -e, --get-title simulate, quiet but print title
@ -195,107 +159,91 @@ which means you can modify it, redistribute it or use it however you like.
--get-duration simulate, quiet but print video length --get-duration simulate, quiet but print video length
--get-filename simulate, quiet but print output filename --get-filename simulate, quiet but print output filename
--get-format simulate, quiet but print output format --get-format simulate, quiet but print output format
-j, --dump-json simulate, quiet but print JSON information. -j, --dump-json simulate, quiet but print JSON information. See --output for a description of available keys.
See --output for a description of available -J, --dump-single-json simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist
keys. information in a single line.
--print-json Be quiet and print the video information as JSON (video is still being downloaded).
--newline output progress bar as new lines --newline output progress bar as new lines
--no-progress do not print progress bar --no-progress do not print progress bar
--console-title display progress in console titlebar --console-title display progress in console titlebar
-v, --verbose print various debugging information -v, --verbose print various debugging information
--dump-intermediate-pages print downloaded pages to debug problems --dump-pages print downloaded pages to debug problems (very verbose)
(very verbose) --write-pages Write downloaded intermediary pages to files in the current directory to debug problems
--write-pages Write downloaded intermediary pages to
files in the current directory to debug
problems
--print-traffic Display sent and read HTTP traffic --print-traffic Display sent and read HTTP traffic
-C, --call-home Contact the youtube-dl server for debugging.
--no-call-home Do NOT contact the youtube-dl server for debugging.
## Workarounds: ## Workarounds:
--encoding ENCODING Force the specified encoding (experimental) --encoding ENCODING Force the specified encoding (experimental)
--no-check-certificate Suppress HTTPS certificate validation. --no-check-certificate Suppress HTTPS certificate validation.
--prefer-insecure Use an unencrypted connection to retrieve --prefer-insecure Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)
information about the video. (Currently
supported only for YouTube)
--user-agent UA specify a custom user agent --user-agent UA specify a custom user agent
--referer REF specify a custom referer, use if the video --referer URL specify a custom referer, use if the video access is restricted to one domain
access is restricted to one domain --add-header FIELD:VALUE specify a custom HTTP header and its value, separated by a colon ':'. You can use this option multiple times
--add-header FIELD:VALUE specify a custom HTTP header and its value, --bidi-workaround Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH
separated by a colon ':'. You can use this --sleep-interval SECONDS Number of seconds to sleep before each download.
option multiple times
--bidi-workaround Work around terminals that lack
bidirectional text support. Requires bidiv
or fribidi executable in PATH
## Video Format Options: ## Video Format Options:
-f, --format FORMAT video format code, specify the order of -f, --format FORMAT video format code, specify the order of preference using slashes, as in -f 22/17/18 . Instead of format codes, you can select by
preference using slashes: "-f 22/17/18". extension for the extensions aac, m4a, mp3, mp4, ogg, wav, webm. You can also use the special names "best", "bestvideo", "bestaudio",
"-f mp4" and "-f flv" are also supported. "worst". You can filter the video results by putting a condition in brackets, as in -f "best[height=720]" (or -f "[filesize>10M]").
You can also use the special names "best", This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec,
"bestvideo", "bestaudio", "worst", vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a
"worstvideo" and "worstaudio". By default, question mark (?) after the operator. You can combine format filters, so -f "[height <=? 720][tbr>500]" selects up to 720p videos
youtube-dl will pick the best quality. (or videos where the height is not known) with a bitrate of at least 500 KBit/s. By default, youtube-dl will pick the best quality.
Use commas to download multiple audio formats, such as -f 136/137/mp4/bestvideo,140/m4a/bestaudio. You can merge the video and audio
of two formats into a single file using -f <video-format>+<audio-format> (requires ffmpeg or avconv), for example -f
bestvideo+bestaudio.
--all-formats download all available video formats --all-formats download all available video formats
--prefer-free-formats prefer free video formats unless a specific --prefer-free-formats prefer free video formats unless a specific one is requested
one is requested
--max-quality FORMAT highest quality format to download --max-quality FORMAT highest quality format to download
-F, --list-formats list all available formats -F, --list-formats list all available formats
--youtube-skip-dash-manifest Do not download the DASH manifest on YouTube videos
--merge-output-format FORMAT If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no
merge is required
## Subtitle Options: ## Subtitle Options:
--write-sub write subtitle file --write-sub write subtitle file
--write-auto-sub write automatic subtitle file (youtube --write-auto-sub write automatic subtitle file (youtube only)
only) --all-subs downloads all the available subtitles of the video
--all-subs downloads all the available subtitles of
the video
--list-subs lists all available subtitles for the video --list-subs lists all available subtitles for the video
--sub-format FORMAT subtitle format (default=srt) ([sbv/vtt] --sub-format FORMAT subtitle format, accepts formats preference, for example: "ass/srt/best"
youtube only) --sub-lang LANGS languages of the subtitles to download (optional) separated by commas, use IETF language tags like 'en,pt'
--sub-lang LANGS languages of the subtitles to download
(optional) separated by commas, use IETF
language tags like 'en,pt'
## Authentication Options: ## Authentication Options:
-u, --username USERNAME account username -u, --username USERNAME login with this account ID
-p, --password PASSWORD account password -p, --password PASSWORD account password. If this option is left out, youtube-dl will ask interactively.
-2, --twofactor TWOFACTOR two-factor auth code -2, --twofactor TWOFACTOR two-factor auth code
-n, --netrc use .netrc authentication data -n, --netrc use .netrc authentication data
--video-password PASSWORD video password (vimeo, smotri) --video-password PASSWORD video password (vimeo, smotri)
## Post-processing Options: ## Post-processing Options:
-x, --extract-audio convert video files to audio-only files -x, --extract-audio convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)
(requires ffmpeg or avconv and ffprobe or --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default
avprobe) --audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K
--audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", (default 5)
"opus", or "wav"; best by default --recode-video FORMAT Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)
--audio-quality QUALITY ffmpeg/avconv audio quality specification, -k, --keep-video keeps the video file on disk after the post-processing; the video is erased by default
insert a value between 0 (better) and 9 --no-post-overwrites do not overwrite post-processed files; the post-processed files are overwritten by default
(worse) for VBR or a specific bitrate like --embed-subs embed subtitles in the video (only for mp4 videos)
128K (default 5)
--recode-video FORMAT Encode the video to another format if
necessary (currently supported:
mp4|flv|ogg|webm|mkv)
-k, --keep-video keeps the video file on disk after the
post-processing; the video is erased by
default
--no-post-overwrites do not overwrite post-processed files; the
post-processed files are overwritten by
default
--embed-subs embed subtitles in the video (only for mp4
videos)
--embed-thumbnail embed thumbnail in the audio as cover art --embed-thumbnail embed thumbnail in the audio as cover art
--add-metadata write metadata to the video file --add-metadata write metadata to the video file
--xattrs write metadata to the video file's xattrs --metadata-from-title FORMAT parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed
(using dublin core and xdg standards) parameters replace existing values. Additional templates: %(album), %(artist). Example: --metadata-from-title "%(artist)s -
--prefer-avconv Prefer avconv over ffmpeg for running the %(title)s" matches a title like "Coldplay - Paradise"
postprocessors (default) --xattrs write metadata to the video file's xattrs (using dublin core and xdg standards)
--prefer-ffmpeg Prefer ffmpeg over avconv for running the --fixup POLICY Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default;
postprocessors fix file if we can, warn otherwise)
--exec CMD Execute a command on the file after --prefer-avconv Prefer avconv over ffmpeg for running the postprocessors (default)
downloading, similar to find's -exec --prefer-ffmpeg Prefer ffmpeg over avconv for running the postprocessors
syntax. Example: --exec 'adb push {} --ffmpeg-location PATH Location of the ffmpeg/avconv binary; either the path to the binary or its containing directory.
/sdcard/Music/ && rm {}' --exec CMD Execute a command on the file after downloading, similar to find's -exec syntax. Example: --exec 'adb push {} /sdcard/Music/ && rm
{}'
--convert-subtitles FORMAT Convert the subtitles to other format (currently supported: srt|ass|vtt)
# CONFIGURATION # CONFIGURATION
You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<Yourname>\youtube-dl.conf`. You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\<user name>\youtube-dl.conf`.
# OUTPUT TEMPLATE # OUTPUT TEMPLATE
@ -345,21 +293,34 @@ $ youtube-dl --dateafter 20000101 --datebefore 20091231
# FAQ # FAQ
### I'm getting an error `Unable to extract OpenGraph title` on YouTube playlists ### How do I update youtube-dl?
YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos. If you've followed [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html), you can simply run `youtube-dl -U` (or, on Linux, `sudo youtube-dl -U`).
If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to report bugs to the Ubuntu packaging guys - all they have to do is update the package to a somewhat recent version. If you have used pip, a simple `sudo pip install -U youtube-dl` is sufficient to update.
Alternatively, uninstall the youtube-dl package and follow [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html). In a pinch, this should do if you used `apt-get` before to install youtube-dl: If you have installed youtube-dl using a package manager like *apt-get* or *yum*, use the standard system update mechanism to update. Note that distribution packages are often outdated. As a rule of thumb, youtube-dl releases at least once a month, and often weekly or even daily. Simply go to http://yt-dl.org/ to find out the current version. Unfortunately, there is nothing we youtube-dl developers can do if your distributions serves a really outdated version. You can (and should) complain to your distribution in their bugtracker or support forum.
As a last resort, you can also uninstall the version installed by your package manager and follow our manual installation instructions. For that, remove the distribution's package, with a line like
sudo apt-get remove -y youtube-dl
Afterwards, simply follow [our manual installation instructions](http://rg3.github.io/youtube-dl/download.html):
``` ```
sudo apt-get remove -y youtube-dl
sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl sudo wget https://yt-dl.org/latest/youtube-dl -O /usr/local/bin/youtube-dl
sudo chmod a+x /usr/local/bin/youtube-dl sudo chmod a+x /usr/local/bin/youtube-dl
hash -r hash -r
``` ```
Again, from then on you'll be able to update with `sudo youtube-dl -U`.
### I'm getting an error `Unable to extract OpenGraph title` on YouTube playlists
YouTube changed their playlist format in March 2014 and later on, so you'll need at least youtube-dl 2014.07.25 to download all YouTube videos.
If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
### Do I always have to pass in `--max-quality FORMAT`, or `-citw`? ### Do I always have to pass in `--max-quality FORMAT`, or `-citw`?
By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, `--max-quality` *limits* the video quality (so if you want the best quality, do NOT pass it in), and the only option out of `-citw` that is regularly useful is `-i`. By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, `--max-quality` *limits* the video quality (so if you want the best quality, do NOT pass it in), and the only option out of `-citw` that is regularly useful is `-i`.
@ -376,17 +337,31 @@ Apparently YouTube requires you to pass a CAPTCHA test if you download too much.
Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/). Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
### The links provided by youtube-dl -g are not working anymore ### I extracted a video URL with -g, but it does not play on another machine / in my webbrowser.
The URLs youtube-dl outputs require the downloader to have the correct cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl. It depends a lot on the service. In many cases, requests for the video (to download/play it) must come from the same IP address and with the same cookies. Use the `--cookies` option to write the required cookies into a file, and advise your downloader to read cookies from that file. Some sites also require a common user agent to be used, use `--dump-user-agent` to see the one in use by youtube-dl.
It may be beneficial to use IPv6; in some cases, the restrictions are only applied to IPv4. Some services (sometimes only for a subset of videos) do not restrict the video URL by IP address, cookie, or user-agent, but these are the exception rather than the rule.
Please bear in mind that some URL protocols are **not** supported by browsers out of the box, including RTMP. If you are using -g, your own downloader must support these as well.
If you want to play the video on a machine that is not running youtube-dl, you can relay the video content from the machine that runs youtube-dl. You can use `-o -` to let youtube-dl stream a video to stdout, or simply allow the player to download the files written by youtube-dl in turn.
### ERROR: no fmt_url_map or conn information found in video info ### ERROR: no fmt_url_map or conn information found in video info
youtube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`. YouTube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
### ERROR: unable to download video ### ### ERROR: unable to download video ###
youtube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`. YouTube requires an additional signature since September 2012 which is not supported by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
### ExtractorError: Could not find JS function u'OF'
In February 2015, the new YouTube player contained a character sequence in a string that was misinterpreted by old versions of youtube-dl. See [above](#how-do-i-update-youtube-dl) for how to update youtube-dl.
### HTTP Error 429: Too Many Requests or 402: Payment Required
These two error codes indicate that the service is blocking your IP address because of overuse. Contact the service and ask them to unblock your IP address, or - if you have acquired a whitelisted IP address already - use the [`--proxy` or `--network-address` options](#network-options) to select another IP address.
### SyntaxError: Non-ASCII character ### ### SyntaxError: Non-ASCII character ###
@ -405,6 +380,53 @@ Since June 2012 (#342) youtube-dl is packed as an executable zipfile, simply unz
To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29). To run the exe you need to install first the [Microsoft Visual C++ 2008 Redistributable Package](http://www.microsoft.com/en-us/download/details.aspx?id=29).
### On Windows, how should I set up ffmpeg and youtube-dl? Where should I put the exe files?
If you put youtube-dl and ffmpeg in the same directory that you're running the command from, it will work, but that's rather cumbersome.
To make a different directory work - either for ffmpeg, or for youtube-dl, or for both - simply create the directory (say, `C:\bin`, or `C:\Users\<User name>\bin`), put all the executables directly in there, and then [set your PATH environment variable](https://www.java.com/en/download/help/path.xml) to include that directory.
From then on, after restarting your shell, you will be able to access both youtube-dl and ffmpeg (and youtube-dl will be able to find ffmpeg) by simply typing `youtube-dl` or `ffmpeg`, no matter what directory you're in.
### How do I put downloads into a specific folder?
Use the `-o` to specify an [output template](#output-template), for example `-o "/home/user/videos/%(title)s-%(id)s.%(ext)s"`. If you want this for all of your downloads, put the option into your [configuration file](#configuration).
### How do I download a video starting with a `-` ?
Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the options with `--`:
youtube-dl -- -wNyEUrxzFU
youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU"
### Can you add support for this anime video site, or site which shows current movies for free?
As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl.
A note on the service that they don't host the infringing content, but just link to those who do, is evidence that the service should **not** be included into youtube-dl. The same goes for any DMCA note when the whole front page of the service is filled with videos they are not allowed to distribute. A "fair use" note is equally unconvincing if the service shows copyright-protected videos in full without authorization.
Support requests for services that **do** purchase the rights to distribute their content are perfectly fine though. If in doubt, you can simply include a source that mentions the legitimate purchase of content.
### How can I speed up work on my issue?
(Also known as: Help, my important issue not being solved!) The youtube-dl core developer team is quite small. While we do our best to solve as many issues as possible, sometimes that can take quite a while. To speed up your issue, here's what you can do:
First of all, please do report the issue [at our issue tracker](https://yt-dl.org/bugs). That allows us to coordinate all efforts by users and developers, and serves as a unified point. Unfortunately, the youtube-dl project has grown too large to use personal email as an effective communication channel.
Please read the [bug reporting instructions](#bugs) below. A lot of bugs lack all the necessary information. If you can, offer proxy, VPN, or shell access to the youtube-dl developers. If you are able to, test the issue from multiple computers in multiple countries to exclude local censorship or misconfiguration issues.
If nobody is interested in solving your issue, you are welcome to take matters into your own hands and submit a pull request (or coerce/pay somebody else to do so).
Feel free to bump the issue from time to time by writing a small comment ("Issue is still present in youtube-dl version ...from France, but fixed from Belgium"), but please not more than once a month. Please do not declare your issue as `important` or `urgent`.
### How can I detect whether a given URL is supported by youtube-dl?
For one, have a look at the [list of supported sites](docs/supportedsites.md). Note that it can sometimes happen that the site changes its URL scheme (say, from http://example.com/video/1234567 to http://example.com/v/1234567 ) and youtube-dl reports an URL of a service in that list as unsupported. In that case, simply report a bug.
It is *not* possible to detect whether a URL is supported or not. That's because youtube-dl contains a generic extractor which matches **all** URLs. You may be tempted to disable, exclude, or remove the generic extractor, but the generic extractor not only allows users to extract videos from lots of websites that embed a video from another service, but may also be used to extract video from a service that it's hosting itself. Therefore, we neither recommend nor support disabling, excluding, or removing the generic extractor.
If you want to find out whether a given URL is supported, simply call youtube-dl with it. If you get no videos back, chances are the URL is either not referring to a video or unsupported. You can find out which by examining the output (if you run youtube-dl on the console) or catching an `UnsupportedError` exception if you run it from a Python program.
# DEVELOPER INSTRUCTIONS # DEVELOPER INSTRUCTIONS
Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution. Most users do not need to build youtube-dl and can [download the builds](http://rg3.github.io/youtube-dl/download.html) or get them from their distribution.
@ -439,8 +461,6 @@ If you want to add support for a new site, you can follow this quick list (assum
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
@ -448,7 +468,7 @@ If you want to add support for a new site, you can follow this quick list (assum
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
_TEST = { _TEST = {
'url': 'http://yourextractor.com/watch/42', 'url': 'http://yourextractor.com/watch/42',
'md5': 'TODO: md5 sum of the first 10KiB of the video file', 'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
'info_dict': { 'info_dict': {
'id': '42', 'id': '42',
'ext': 'mp4', 'ext': 'mp4',
@ -463,24 +483,24 @@ If you want to add support for a new site, you can follow this quick list (assum
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id') webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ... # TODO more code goes here, for example ...
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title') title = self._html_search_regex(r'<h1>(.*?)</h1>', webpage, 'title')
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': self._og_search_description(webpage),
# TODO more properties (see youtube_dl/extractor/common.py) # TODO more properties (see youtube_dl/extractor/common.py)
} }
``` ```
5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py). 5. Add an import in [`youtube_dl/extractor/__init__.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/__init__.py).
6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc. 6. Run `python test/test_download.py TestDownload.test_YourExtractor`. This *should fail* at first, but you can continually re-run it until you're done. If you decide to add more than one test, then rename ``_TEST`` to ``_TESTS`` and make it into a list of dictionaries. The tests will be then be named `TestDownload.test_YourExtractor`, `TestDownload.test_YourExtractor_1`, `TestDownload.test_YourExtractor_2`, etc.
7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want. 7. Have a look at [`youtube_dl/common/extractor/common.py`](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py) for possible helper methods and a [detailed description of what your extractor should return](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/extractor/common.py#L38). Add tests and code for as many as you want.
8. If you can, check the code with [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501). 8. If you can, check the code with [flake8](https://pypi.python.org/pypi/flake8).
9. When the tests pass, [add](https://www.kernel.org/pub/software/scm/git/docs/git-add.html) the new files and [commit](https://www.kernel.org/pub/software/scm/git/docs/git-commit.html) them and [push](https://www.kernel.org/pub/software/scm/git/docs/git-push.html) the result, like this: 9. When the tests pass, [add](http://git-scm.com/docs/git-add) the new files and [commit](http://git-scm.com/docs/git-commit) them and [push](http://git-scm.com/docs/git-push) the result, like this:
$ git add youtube_dl/extractor/__init__.py $ git add youtube_dl/extractor/__init__.py
$ git add youtube_dl/extractor/yourextractor.py $ git add youtube_dl/extractor/yourextractor.py
@ -491,15 +511,69 @@ If you want to add support for a new site, you can follow this quick list (assum
In any case, thank you very much for your contributions! In any case, thank you very much for your contributions!
# EMBEDDING YOUTUBE-DL
youtube-dl makes the best effort to be a good command-line program, and thus should be callable from any programming language. If you encounter any problems parsing its output, feel free to [create a report](https://github.com/rg3/youtube-dl/issues/new).
From a Python program, you can embed youtube-dl in a more powerful fashion, like this:
```python
from __future__ import unicode_literals
import youtube_dl
ydl_opts = {}
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
```
Most likely, you'll want to use various options. For a list of what can be done, have a look at [youtube_dl/YoutubeDL.py](https://github.com/rg3/youtube-dl/blob/master/youtube_dl/YoutubeDL.py#L69). 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:
```python
from __future__ import unicode_literals
import youtube_dl
class MyLogger(object):
def debug(self, msg):
pass
def warning(self, msg):
pass
def error(self, msg):
print(msg)
def my_hook(d):
if d['status'] == 'finished':
print('Done downloading, now converting ...')
ydl_opts = {
'format': 'bestaudio/best',
'postprocessors': [{
'key': 'FFmpegExtractAudio',
'preferredcodec': 'mp3',
'preferredquality': '192',
}],
'logger': MyLogger(),
'progress_hooks': [my_hook],
}
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download(['http://www.youtube.com/watch?v=BaW_jenozKc'])
```
# BUGS # BUGS
Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. Bugs and suggestions should be reported at: <https://github.com/rg3/youtube-dl/issues> . Unless you were prompted so or there is another pertinent reason (e.g. GitHub fails to accept the bug report), please do not send bug reports via personal email. For discussions, join us in the irc channel #youtube-dl on freenode.
Please include the full output of the command when run with `--verbose`. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever. **Please include the full output of youtube-dl when run with `-v`**.
For discussions, join us in the irc channel #youtube-dl on freenode. The output (including the first lines) contain important debugging information. Issues without the full output are often not reproducible and therefore do not get solved in short order, if ever.
When you submit a request, please re-read it once to avoid a couple of mistakes (you can and should use this as a checklist): Please re-read your issue once again to avoid a couple of common mistakes (you can and should use this as a checklist):
### Is the description of the issue itself sufficient? ### Is the description of the issue itself sufficient?
@ -515,7 +589,9 @@ If your report is shorter than two lines, it is almost certainly missing some of
For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information. For bug reports, this means that your report should contain the *complete* output of youtube-dl when called with the -v flag. The error message you get for (most) bugs even says so, but you would not believe how many of our bug reports do not contain this information.
Site support requests **must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL. If your server has multiple IPs or you suspect censorship, adding --call-home may be a good idea to get more diagnostics. If the error is `ERROR: Unable to extract ...` and you cannot reproduce it from multiple countries, add `--dump-pages` (warning: this will yield a rather large output, redirect it to the file `log.txt` by adding `>log.txt 2>&1` to your command-line) or upload the `.dump` files you get when you add `--write-pages` [somewhere](https://gist.github.com/).
**Site support requests must contain an example URL**. An example URL is a URL you might want to download, like http://www.youtube.com/watch?v=BaW_jenozKc . There should be an obvious video present. Except under very special circumstances, the main page of a video service (e.g. http://www.youtube.com/ ) is *not* an example URL.
### Are you using the latest version? ### Are you using the latest version?
@ -543,7 +619,7 @@ In particular, every site support request issue should only pertain to services
### Is anyone going to need the feature? ### Is anyone going to need the feature?
Only post features that you (or an incapicated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them. Only post features that you (or an incapacitated friend you can personally talk to) require. Do not post features because they seem like a good idea. If they are really useful, they will be requested by someone who requires them.
### Is your question about youtube-dl? ### Is your question about youtube-dl?

7
devscripts/bash-completion.py
View File

@ -1,4 +1,6 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals
import os import os
from os.path import dirname as dirn from os.path import dirname as dirn
import sys import sys
@ -9,16 +11,17 @@ import youtube_dl
BASH_COMPLETION_FILE = "youtube-dl.bash-completion" BASH_COMPLETION_FILE = "youtube-dl.bash-completion"
BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in" BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
def build_completion(opt_parser): def build_completion(opt_parser):
opts_flag = [] opts_flag = []
for group in opt_parser.option_groups: for group in opt_parser.option_groups:
for option in group.option_list: for option in group.option_list:
#for every long flag # for every long flag
opts_flag.append(option.get_opt_string()) opts_flag.append(option.get_opt_string())
with open(BASH_COMPLETION_TEMPLATE) as f: with open(BASH_COMPLETION_TEMPLATE) as f:
template = f.read() template = f.read()
with open(BASH_COMPLETION_FILE, "w") as f: with open(BASH_COMPLETION_FILE, "w") as f:
#just using the special char # just using the special char
filled_template = template.replace("{{flags}}", " ".join(opts_flag)) filled_template = template.replace("{{flags}}", " ".join(opts_flag))
f.write(filled_template) f.write(filled_template)

5
devscripts/buildserver.py
View File

@ -142,7 +142,7 @@ def win_service_set_status(handle, status_code):
def win_service_main(service_name, real_main, argc, argv_raw): def win_service_main(service_name, real_main, argc, argv_raw):
try: try:
#args = [argv_raw[i].value for i in range(argc)] # args = [argv_raw[i].value for i in range(argc)]
stop_event = threading.Event() stop_event = threading.Event()
handler = HandlerEx(functools.partial(stop_event, win_service_handler)) handler = HandlerEx(functools.partial(stop_event, win_service_handler))
h = advapi32.RegisterServiceCtrlHandlerExW(service_name, handler, None) h = advapi32.RegisterServiceCtrlHandlerExW(service_name, handler, None)
@ -233,6 +233,7 @@ def rmtree(path):
#============================================================================== #==============================================================================
class BuildError(Exception): class BuildError(Exception):
def __init__(self, output, code=500): def __init__(self, output, code=500):
self.output = output self.output = output
@ -369,7 +370,7 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea
class BuildHTTPRequestHandler(BaseHTTPRequestHandler): class BuildHTTPRequestHandler(BaseHTTPRequestHandler):
actionDict = { 'build': Builder, 'download': Builder } # They're the same, no more caching. actionDict = {'build': Builder, 'download': Builder} # They're the same, no more caching.
def do_GET(self): def do_GET(self):
path = urlparse.urlparse(self.path) path = urlparse.urlparse(self.path)

9
devscripts/check-porn.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals
""" """
This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check
@ -44,12 +45,12 @@ for test in get_testcases():
RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST) RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST)
if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] or
or test['info_dict']['age_limit'] != 18): test['info_dict']['age_limit'] != 18):
print('\nPotential missing age_limit check: {0}'.format(test['name'])) print('\nPotential missing age_limit check: {0}'.format(test['name']))
elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] and
and test['info_dict']['age_limit'] == 18): test['info_dict']['age_limit'] == 18):
print('\nPotential false negative: {0}'.format(test['name'])) print('\nPotential false negative: {0}'.format(test['name']))
else: else:

2
devscripts/fish-completion.py
View File

@ -23,13 +23,13 @@ EXTRA_ARGS = {
'batch-file': ['--require-parameter'], 'batch-file': ['--require-parameter'],
} }
def build_completion(opt_parser): def build_completion(opt_parser):
commands = [] commands = []
for group in opt_parser.option_groups: for group in opt_parser.option_groups:
for option in group.option_list: for option in group.option_list:
long_option = option.get_opt_string().strip('-') long_option = option.get_opt_string().strip('-')
help_msg = shell_quote([option.help])
complete_cmd = ['complete', '--command', 'youtube-dl', '--long-option', long_option] complete_cmd = ['complete', '--command', 'youtube-dl', '--long-option', long_option]
if option._short_opts: if option._short_opts:
complete_cmd += ['--short-option', option._short_opts[0].strip('-')] complete_cmd += ['--short-option', option._short_opts[0].strip('-')]

42
devscripts/generate_aes_testdata.py Normal file
View File

@ -0,0 +1,42 @@
from __future__ import unicode_literals
import codecs
import subprocess
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import intlist_to_bytes
from youtube_dl.aes import aes_encrypt, key_expansion
secret_msg = b'Secret message goes here'
def hex_str(int_list):
return codecs.encode(intlist_to_bytes(int_list), 'hex')
def openssl_encode(algo, key, iv):
cmd = ['openssl', 'enc', '-e', '-' + algo, '-K', hex_str(key), '-iv', hex_str(iv)]
prog = subprocess.Popen(cmd, stdin=subprocess.PIPE, stdout=subprocess.PIPE)
out, _ = prog.communicate(secret_msg)
return out
iv = key = [0x20, 0x15] + 14 * [0]
r = openssl_encode('aes-128-cbc', key, iv)
print('aes_cbc_decrypt')
print(repr(r))
password = key
new_key = aes_encrypt(password, key_expansion(password))
r = openssl_encode('aes-128-ctr', new_key, iv)
print('aes_decrypt_text 16')
print(repr(r))
password = key + 16 * [0]
new_key = aes_encrypt(password, key_expansion(password)) * (32 // 16)
r = openssl_encode('aes-256-ctr', new_key, iv)
print('aes_decrypt_text 32')
print(repr(r))

1
devscripts/gh-pages/add-version.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
from __future__ import unicode_literals
import json import json
import sys import sys

5
devscripts/gh-pages/generate-download.py
View File

@ -1,8 +1,7 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
from __future__ import unicode_literals
import hashlib import hashlib
import shutil
import subprocess
import tempfile
import urllib.request import urllib.request
import json import json

20
devscripts/gh-pages/sign-versions.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
from __future__ import unicode_literals, with_statement
import rsa import rsa
import json import json
@ -11,22 +12,23 @@ except NameError:
versions_info = json.load(open('update/versions.json')) versions_info = json.load(open('update/versions.json'))
if 'signature' in versions_info: if 'signature' in versions_info:
del versions_info['signature'] del versions_info['signature']
print('Enter the PKCS1 private key, followed by a blank line:') print('Enter the PKCS1 private key, followed by a blank line:')
privkey = b'' privkey = b''
while True: while True:
try: try:
line = input() line = input()
except EOFError: except EOFError:
break break
if line == '': if line == '':
break break
privkey += line.encode('ascii') + b'\n' privkey += line.encode('ascii') + b'\n'
privkey = rsa.PrivateKey.load_pkcs1(privkey) privkey = rsa.PrivateKey.load_pkcs1(privkey)
signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).encode('utf-8'), privkey, 'SHA-256')).decode() signature = hexlify(rsa.pkcs1.sign(json.dumps(versions_info, sort_keys=True).encode('utf-8'), privkey, 'SHA-256')).decode()
print('signature: ' + signature) print('signature: ' + signature)
versions_info['signature'] = signature versions_info['signature'] = signature
json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True) with open('update/versions.json', 'w') as versionsf:
json.dump(versions_info, versionsf, indent=4, sort_keys=True)

6
devscripts/gh-pages/update-copyright.py
View File

@ -1,11 +1,11 @@
#!/usr/bin/env python #!/usr/bin/env python
# coding: utf-8 # coding: utf-8
from __future__ import with_statement from __future__ import with_statement, unicode_literals
import datetime import datetime
import glob import glob
import io # For Python 2 compatibilty import io # For Python 2 compatibilty
import os import os
import re import re
@ -13,7 +13,7 @@ year = str(datetime.datetime.now().year)
for fn in glob.glob('*.html*'): for fn in glob.glob('*.html*'):
with io.open(fn, encoding='utf-8') as f: with io.open(fn, encoding='utf-8') as f:
content = f.read() content = f.read()
newc = re.sub(u'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', u'Copyright © 2006-' + year, content) newc = re.sub(r'(?P<copyright>Copyright © 2006-)(?P<year>[0-9]{4})', 'Copyright © 2006-' + year, content)
if content != newc: if content != newc:
tmpFn = fn + '.part' tmpFn = fn + '.part'
with io.open(tmpFn, 'wt', encoding='utf-8') as outf: with io.open(tmpFn, 'wt', encoding='utf-8') as outf:

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

@ -1,4 +1,5 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
from __future__ import unicode_literals
import datetime import datetime
import io import io
@ -73,4 +74,3 @@ atom_template = atom_template.replace('@ENTRIES@', entries_str)
with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file: with io.open('update/releases.atom', 'w', encoding='utf-8') as atom_file:
atom_file.write(atom_template) atom_file.write(atom_template)

6
devscripts/gh-pages/update-sites.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python3 #!/usr/bin/env python3
from __future__ import unicode_literals
import sys import sys
import os import os
@ -9,19 +10,20 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(
import youtube_dl import youtube_dl
def main(): def main():
with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf: with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf:
template = tmplf.read() template = tmplf.read()
ie_htmls = [] ie_htmls = []
for ie in sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower()): for ie in youtube_dl.list_extractors(age_limit=None):
ie_html = '<b>{}</b>'.format(ie.IE_NAME) ie_html = '<b>{}</b>'.format(ie.IE_NAME)
ie_desc = getattr(ie, 'IE_DESC', None) ie_desc = getattr(ie, 'IE_DESC', None)
if ie_desc is False: if ie_desc is False:
continue continue
elif ie_desc is not None: elif ie_desc is not None:
ie_html += ': {}'.format(ie.IE_DESC) ie_html += ': {}'.format(ie.IE_DESC)
if ie.working() == False: if not ie.working():
ie_html += ' (Currently broken)' ie_html += ' (Currently broken)'
ie_htmls.append('<li>{}</li>'.format(ie_html)) ie_htmls.append('<li>{}</li>'.format(ie_html))

32
devscripts/make_contributing.py Executable file
View File

@ -0,0 +1,32 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import io
import optparse
import re
def main():
parser = optparse.OptionParser(usage='%prog INFILE OUTFILE')
options, args = parser.parse_args()
if len(args) != 2:
parser.error('Expected an input and an output filename')
infile, outfile = args
with io.open(infile, encoding='utf-8') as inf:
readme = inf.read()
bug_text = re.search(
r'(?s)#\s*BUGS\s*[^\n]*\s*(.*?)#\s*COPYRIGHT', readme).group(1)
dev_text = re.search(
r'(?s)(#\s*DEVELOPER INSTRUCTIONS.*?)#\s*EMBEDDING YOUTUBE-DL',
readme).group(1)
out = bug_text + dev_text
with io.open(outfile, 'w', encoding='utf-8') as outf:
outf.write(out)
if __name__ == '__main__':
main()

2
devscripts/make_readme.py
View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import io import io
import sys import sys
import re import re

45
devscripts/make_supportedsites.py Normal file
View File

@ -0,0 +1,45 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import io
import optparse
import os
import sys
# Import youtube_dl
ROOT_DIR = os.path.join(os.path.dirname(__file__), '..')
sys.path.append(ROOT_DIR)
import youtube_dl
def main():
parser = optparse.OptionParser(usage='%prog OUTFILE.md')
options, args = parser.parse_args()
if len(args) != 1:
parser.error('Expected an output filename')
outfile, = args
def gen_ies_md(ies):
for ie in ies:
ie_md = '**{0}**'.format(ie.IE_NAME)
ie_desc = getattr(ie, 'IE_DESC', None)
if ie_desc is False:
continue
if ie_desc is not None:
ie_md += ': {0}'.format(ie.IE_DESC)
if not ie.working():
ie_md += ' (Currently broken)'
yield ie_md
ies = sorted(youtube_dl.gen_extractors(), key=lambda i: i.IE_NAME.lower())
out = '# Supported sites\n' + ''.join(
' - ' + md + '\n'
for md in gen_ies_md(ies))
with io.open(outfile, 'w', encoding='utf-8') as outf:
outf.write(out)
if __name__ == '__main__':
main()

16
devscripts/prepare_manpage.py
View File

@ -1,3 +1,4 @@
from __future__ import unicode_literals
import io import io
import os.path import os.path
@ -10,8 +11,19 @@ README_FILE = os.path.join(ROOT_DIR, 'README.md')
with io.open(README_FILE, encoding='utf-8') as f: with io.open(README_FILE, encoding='utf-8') as f:
readme = f.read() readme = f.read()
PREFIX = '%YOUTUBE-DL(1)\n\n# NAME\n' PREFIX = '''%YOUTUBE-DL(1)
readme = re.sub(r'(?s)# INSTALLATION.*?(?=# DESCRIPTION)', '', readme)
# NAME
youtube\-dl \- download videos from youtube.com or other video platforms
# SYNOPSIS
**youtube-dl** \[OPTIONS\] URL [URL...]
'''
readme = re.sub(r'(?s)^.*?(?=# DESCRIPTION)', '', readme)
readme = re.sub(r'\s+youtube-dl \[OPTIONS\] URL \[URL\.\.\.\]', '', readme)
readme = PREFIX + readme readme = PREFIX + readme
if sys.version_info < (3, 0): if sys.version_info < (3, 0):

8
devscripts/release.sh
View File

@ -35,7 +35,7 @@ if [ ! -z "$useless_files" ]; then echo "ERROR: Non-.py files in youtube_dl: $us
if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi if [ ! -f "updates_key.pem" ]; then echo 'ERROR: updates_key.pem missing'; exit 1; fi
/bin/echo -e "\n### First of all, testing..." /bin/echo -e "\n### First of all, testing..."
make cleanall make clean
if $skip_tests ; then if $skip_tests ; then
echo 'SKIPPING TESTS' echo 'SKIPPING TESTS'
else else
@ -45,9 +45,9 @@ fi
/bin/echo -e "\n### Changing version in version.py..." /bin/echo -e "\n### Changing version in version.py..."
sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/version.py
/bin/echo -e "\n### Committing README.md and youtube_dl/version.py..." /bin/echo -e "\n### Committing documentation and youtube_dl/version.py..."
make README.md make README.md CONTRIBUTING.md supportedsites
git add README.md youtube_dl/version.py git add README.md CONTRIBUTING.md docs/supportedsites.md youtube_dl/version.py
git commit -m "release $version" git commit -m "release $version"
/bin/echo -e "\n### Now tagging, signing and pushing..." /bin/echo -e "\n### Now tagging, signing and pushing..."

40
devscripts/transition_helper.py
View File

@ -1,40 +0,0 @@
#!/usr/bin/env python
import sys, os
try:
import urllib.request as compat_urllib_request
except ImportError: # Python 2
import urllib2 as compat_urllib_request
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
sys.stderr.write(u'The new location of the binaries is https://github.com/rg3/youtube-dl/downloads, not the git repository.\n\n')
try:
raw_input()
except NameError: # Python 3
input()
filename = sys.argv[0]
API_URL = "https://api.github.com/repos/rg3/youtube-dl/downloads"
BIN_URL = "https://github.com/downloads/rg3/youtube-dl/youtube-dl"
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
try:
urlh = compat_urllib_request.urlopen(BIN_URL)
newcontent = urlh.read()
urlh.close()
except (IOError, OSError) as err:
sys.exit('ERROR: unable to download latest version')
try:
with open(filename, 'wb') as outf:
outf.write(newcontent)
except (IOError, OSError) as err:
sys.exit('ERROR: unable to overwrite current version')
sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

12
devscripts/transition_helper_exe/setup.py
View File

@ -1,12 +0,0 @@
from distutils.core import setup
import py2exe
py2exe_options = {
"bundle_files": 1,
"compressed": 1,
"optimize": 2,
"dist_dir": '.',
"dll_excludes": ['w9xpopen.exe']
}
setup(console=['youtube-dl.py'], options={ "py2exe": py2exe_options }, zipfile=None)

102
devscripts/transition_helper_exe/youtube-dl.py
View File

@ -1,102 +0,0 @@
#!/usr/bin/env python
import sys, os
import urllib2
import json, hashlib
def rsa_verify(message, signature, key):
from struct import pack
from hashlib import sha256
from sys import version_info
def b(x):
if version_info[0] == 2: return x
else: return x.encode('latin1')
assert(type(message) == type(b('')))
block_size = 0
n = key[0]
while n:
block_size += 1
n >>= 8
signature = pow(int(signature, 16), key[1], key[0])
raw_bytes = []
while signature:
raw_bytes.insert(0, pack("B", signature & 0xFF))
signature >>= 8
signature = (block_size - len(raw_bytes)) * b('\x00') + b('').join(raw_bytes)
if signature[0:2] != b('\x00\x01'): return False
signature = signature[2:]
if not b('\x00') in signature: return False
signature = signature[signature.index(b('\x00'))+1:]
if not signature.startswith(b('\x30\x31\x30\x0D\x06\x09\x60\x86\x48\x01\x65\x03\x04\x02\x01\x05\x00\x04\x20')): return False
signature = signature[19:]
if signature != sha256(message).digest(): return False
return True
sys.stderr.write(u'Hi! We changed distribution method and now youtube-dl needs to update itself one more time.\n')
sys.stderr.write(u'This will only happen once. Simply press enter to go on. Sorry for the trouble!\n')
sys.stderr.write(u'From now on, get the binaries from http://rg3.github.com/youtube-dl/download.html, not from the git repository.\n\n')
raw_input()
filename = sys.argv[0]
UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
JSON_URL = UPDATE_URL + 'versions.json'
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
if not os.access(filename, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % filename)
exe = os.path.abspath(filename)
directory = os.path.dirname(exe)
if not os.access(directory, os.W_OK):
sys.exit('ERROR: no write permissions on %s' % directory)
try:
versions_info = urllib2.urlopen(JSON_URL).read().decode('utf-8')
versions_info = json.loads(versions_info)
except:
sys.exit(u'ERROR: can\'t obtain versions info. Please try again later.')
if not 'signature' in versions_info:
sys.exit(u'ERROR: the versions file is not signed or corrupted. Aborting.')
signature = versions_info['signature']
del versions_info['signature']
if not rsa_verify(json.dumps(versions_info, sort_keys=True), signature, UPDATES_RSA_KEY):
sys.exit(u'ERROR: the versions file signature is invalid. Aborting.')
version = versions_info['versions'][versions_info['latest']]
try:
urlh = urllib2.urlopen(version['exe'][0])
newcontent = urlh.read()
urlh.close()
except (IOError, OSError) as err:
sys.exit('ERROR: unable to download latest version')
newcontent_hash = hashlib.sha256(newcontent).hexdigest()
if newcontent_hash != version['exe'][1]:
sys.exit(u'ERROR: the downloaded file hash does not match. Aborting.')
try:
with open(exe + '.new', 'wb') as outf:
outf.write(newcontent)
except (IOError, OSError) as err:
sys.exit(u'ERROR: unable to write the new version')
try:
bat = os.path.join(directory, 'youtube-dl-updater.bat')
b = open(bat, 'w')
b.write("""
echo Updating youtube-dl...
ping 127.0.0.1 -n 5 -w 1000 > NUL
move /Y "%s.new" "%s"
del "%s"
\n""" %(exe, exe, bat))
b.close()
os.startfile(bat)
except (IOError, OSError) as err:
sys.exit('ERROR: unable to overwrite current version')
sys.stderr.write(u'Done! Now you can run youtube-dl.\n')

28
devscripts/zsh-completion.in Normal file
View File

@ -0,0 +1,28 @@
#compdef youtube-dl
__youtube_dl() {
local curcontext="$curcontext" fileopts diropts cur prev
typeset -A opt_args
fileopts="{{fileopts}}"
diropts="{{diropts}}"
cur=$words[CURRENT]
case $cur in
:)
_arguments '*: :(::ytfavorites ::ytrecommended ::ytsubscriptions ::ytwatchlater ::ythistory)'
;;
*)
prev=$words[CURRENT-1]
if [[ ${prev} =~ ${fileopts} ]]; then
_path_files
elif [[ ${prev} =~ ${diropts} ]]; then
_path_files -/
elif [[ ${prev} == "--recode-video" ]]; then
_arguments '*: :(mp4 flv ogg webm mkv)'
else
_arguments '*: :({{flags}})'
fi
;;
esac
}
__youtube_dl

48
devscripts/zsh-completion.py Executable file
View File

@ -0,0 +1,48 @@
#!/usr/bin/env python
from __future__ import unicode_literals
import os
from os.path import dirname as dirn
import sys
sys.path.append(dirn(dirn((os.path.abspath(__file__)))))
import youtube_dl
ZSH_COMPLETION_FILE = "youtube-dl.zsh"
ZSH_COMPLETION_TEMPLATE = "devscripts/zsh-completion.in"
def build_completion(opt_parser):
opts = [opt for group in opt_parser.option_groups
for opt in group.option_list]
opts_file = [opt for opt in opts if opt.metavar == "FILE"]
opts_dir = [opt for opt in opts if opt.metavar == "DIR"]
fileopts = []
for opt in opts_file:
if opt._short_opts:
fileopts.extend(opt._short_opts)
if opt._long_opts:
fileopts.extend(opt._long_opts)
diropts = []
for opt in opts_dir:
if opt._short_opts:
diropts.extend(opt._short_opts)
if opt._long_opts:
diropts.extend(opt._long_opts)
flags = [opt.get_opt_string() for opt in opts]
with open(ZSH_COMPLETION_TEMPLATE) as f:
template = f.read()
template = template.replace("{{fileopts}}", "|".join(fileopts))
template = template.replace("{{diropts}}", "|".join(diropts))
template = template.replace("{{flags}}", " ".join(flags))
with open(ZSH_COMPLETION_FILE, "w") as f:
f.write(template)
parser = youtube_dl.parseOpts()[0]
build_completion(parser)

4
docs/conf.py
View File

@ -44,8 +44,8 @@ copyright = u'2014, Ricardo Garcia Gonzalez'
# built documents. # built documents.
# #
# The short X.Y version. # The short X.Y version.
import youtube_dl from youtube_dl.version import __version__
version = youtube_dl.__version__ version = __version__
# The full version, including alpha/beta/rc tags. # The full version, including alpha/beta/rc tags.
release = version release = version

596
docs/supportedsites.md Normal file
View File

@ -0,0 +1,596 @@
# Supported sites
- **1tv**: Первый канал
- **1up.com**
- **220.ro**
- **24video**
- **3sat**
- **4tube**
- **56.com**
- **5min**
- **8tracks**
- **9gag**
- **abc.net.au**
- **Abc7News**
- **AcademicEarth:Course**
- **AddAnime**
- **AdobeTV**
- **AdultSwim**
- **Aftenposten**
- **Aftonbladet**
- **AirMozilla**
- **AlJazeera**
- **Allocine**
- **AlphaPorno**
- **anitube.se**
- **AnySex**
- **Aparat**
- **AppleDailyAnimationNews**
- **AppleDailyRealtimeNews**
- **AppleTrailers**
- **archive.org**: archive.org videos
- **ARD**
- **ARD:mediathek**
- **arte.tv**
- **arte.tv:+7**
- **arte.tv:concert**
- **arte.tv:creative**
- **arte.tv:ddc**
- **arte.tv:embed**
- **arte.tv:future**
- **AtresPlayer**
- **ATTTechChannel**
- **audiomack**
- **audiomack:album**
- **Azubu**
- **bambuser**
- **bambuser:channel**
- **Bandcamp**
- **Bandcamp:album**
- **bbc.co.uk**: BBC iPlayer
- **BeatportPro**
- **Beeg**
- **BehindKink**
- **Bet**
- **Bild**: Bild.de
- **BiliBili**
- **blinkx**
- **blip.tv:user**
- **BlipTV**
- **Bloomberg**
- **Bpb**: Bundeszentrale für politische Bildung
- **BR**: Bayerischer Rundfunk Mediathek
- **Break**
- **Brightcove**
- **BuzzFeed**
- **BYUtv**
- **Camdemy**
- **CamdemyFolder**
- **Canal13cl**
- **canalc2.tv**
- **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv
- **CBS**
- **CBSNews**: CBS News
- **CBSSports**
- **CeskaTelevize**
- **channel9**: Channel 9
- **Chilloutzone**
- **chirbit**
- **chirbit:profile**
- **Cinchcast**
- **Cinemassacre**
- **clipfish**
- **cliphunter**
- **Clipsyndicate**
- **Cloudy**
- **Clubic**
- **cmt.com**
- **CNET**
- **CNN**
- **CNNArticle**
- **CNNBlogs**
- **CollegeHumor**
- **CollegeRama**
- **ComCarCoff**
- **ComedyCentral**
- **ComedyCentralShows**: The Daily Show / The Colbert Report
- **CondeNast**: Condé Nast media group: Condé Nast, GQ, Glamour, Vanity Fair, Vogue, W Magazine, WIRED
- **Cracked**
- **Criterion**
- **Crunchyroll**
- **crunchyroll:playlist**
- **CSpan**: C-SPAN
- **CtsNews**
- **culturebox.francetvinfo.fr**
- **dailymotion**
- **dailymotion:playlist**
- **dailymotion:user**
- **daum.net**
- **DBTV**
- **DctpTv**
- **DeezerPlaylist**
- **defense.gouv.fr**
- **Discovery**
- **divxstage**: DivxStage
- **Dotsub**
- **DouyuTV**
- **DRBonanza**
- **Dropbox**
- **DrTuber**
- **DRTV**
- **Dump**
- **dvtv**: http://video.aktualne.cz/
- **EaglePlatform**
- **EbaumsWorld**
- **EchoMsk**
- **eHow**
- **Einthusan**
- **eitb.tv**
- **EllenTV**
- **EllenTV:clips**
- **ElPais**: El País
- **Embedly**
- **EMPFlix**
- **Engadget**
- **Eporner**
- **EroProfile**
- **Escapist**
- **EveryonesMixtape**
- **exfm**: ex.fm
- **ExpoTV**
- **ExtremeTube**
- **facebook**
- **faz.net**
- **fc2**
- **fernsehkritik.tv**
- **fernsehkritik.tv:postecke**
- **Firedrive**
- **Firstpost**
- **Flickr**
- **Folketinget**: Folketinget (ft.dk; Danish parliament)
- **FootyRoom**
- **Foxgay**
- **FoxNews**
- **france2.fr:generation-quoi**
- **FranceCulture**
- **FranceInter**
- **francetv**: France 2, 3, 4, 5 and Ô
- **francetvinfo.fr**
- **Freesound**
- **freespeech.org**
- **FreeVideo**
- **FunnyOrDie**
- **Gamekings**
- **GameOne**
- **gameone:playlist**
- **GameSpot**
- **GameStar**
- **Gametrailers**
- **Gazeta**
- **GDCVault**
- **generic**: Generic downloader that works on some sites
- **GiantBomb**
- **Giga**
- **Glide**: Glide mobile video messages (glide.me)
- **Globo**
- **GodTube**
- **GoldenMoustache**
- **Golem**
- **GorillaVid**: GorillaVid.in, daclips.in, movpod.in and fastvideo.in
- **Goshgay**
- **Grooveshark**
- **Groupon**
- **Hark**
- **HearThisAt**
- **Heise**
- **HellPorno**
- **Helsinki**: helsinki.fi
- **HentaiStigma**
- **HistoricFilms**
- **History**
- **hitbox**
- **hitbox:live**
- **HornBunny**
- **HostingBulk**
- **HotNewHipHop**
- **Howcast**
- **HowStuffWorks**
- **HuffPost**: Huffington Post
- **Hypem**
- **Iconosquare**
- **ign.com**
- **imdb**: Internet Movie Database trailers
- **imdb:list**: Internet Movie Database lists
- **Imgur**
- **Ina**
- **InfoQ**
- **Instagram**
- **instagram:user**: Instagram user profile
- **InternetVideoArchive**
- **IPrima**
- **ivi**: ivi.ru
- **ivi:compilation**: ivi.ru compilations
- **Izlesene**
- **JadoreCettePub**
- **JeuxVideo**
- **Jove**
- **jpopsuki.tv**
- **Jukebox**
- **Kaltura**
- **KanalPlay**: Kanal 5/9/11 Play
- **Kankan**
- **Karaoketv**
- **keek**
- **KeezMovies**
- **KhanAcademy**
- **KickStarter**
- **kontrtube**: KontrTube.ru - Труба зовёт
- **KrasView**: Красвью
- **Ku6**
- **la7.tv**
- **Laola1Tv**
- **Letv**
- **LetvPlaylist**
- **LetvTv**
- **Libsyn**
- **lifenews**: LIFE | NEWS
- **LiveLeak**
- **livestream**
- **livestream:original**
- **LnkGo**
- **lrt.lt**
- **lynda**: lynda.com videos
- **lynda:course**: lynda.com online courses
- **m6**
- **macgamestore**: MacGameStore trailers
- **mailru**: Видео@Mail.Ru
- **Malemotion**
- **MDR**
- **media.ccc.de**
- **metacafe**
- **Metacritic**
- **Mgoon**
- **Minhateca**
- **MinistryGrid**
- **mitele.es**
- **mixcloud**
- **MLB**
- **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
- **Mofosex**
- **Mojvideo**
- **Moniker**: allmyvideos.net and vidspot.net
- **mooshare**: Mooshare.biz
- **Morningstar**: morningstar.com
- **Motherless**
- **Motorsport**: motorsport.com
- **MovieClips**
- **Moviezine**
- **movshare**: MovShare
- **MPORA**
- **MTV**
- **mtviggy.com**
- **mtvservices:embedded**
- **MuenchenTV**: münchen.tv
- **MusicPlayOn**
- **MusicVault**
- **muzu.tv**
- **MySpace**
- **MySpace:album**
- **MySpass**
- **myvideo**
- **MyVidster**
- **n-tv.de**
- **NationalGeographic**
- **Naver**
- **NBA**
- **NBC**
- **NBCNews**
- **ndr**: NDR.de - Mediathek
- **NDTV**
- **NerdCubedFeed**
- **Nerdist**
- **Netzkino**
- **Newgrounds**
- **Newstube**
- **NextMedia**
- **NextMediaActionNews**
- **nfb**: National Film Board of Canada
- **nfl.com**
- **nhl.com**
- **nhl.com:news**: NHL news
- **nhl.com:videocenter**: NHL videocenter category
- **niconico**: ニコニコ動画
- **NiconicoPlaylist**
- **Noco**
- **Normalboots**
- **NosVideo**
- **novamov**: NovaMov
- **Nowness**
- **nowvideo**: NowVideo
- **npo.nl**
- **npo.nl:live**
- **npo.nl:radio**
- **npo.nl:radio:fragment**
- **NRK**
- **NRKPlaylist**
- **NRKTV**
- **ntv.ru**
- **Nuvid**
- **NYTimes**
- **ocw.mit.edu**
- **Odnoklassniki**
- **OktoberfestTV**
- **on.aol.com**
- **Ooyala**
- **OpenFilm**
- **orf:fm4**: radio FM4
- **orf:iptv**: iptv.ORF.at
- **orf:oe1**: Radio Österreich 1
- **orf:tvthek**: ORF TVthek
- **parliamentlive.tv**: UK parliament videos
- **Patreon**
- **PBS**
- **Phoenix**
- **Photobucket**
- **Pladform**
- **PlanetaPlay**
- **play.fm**
- **played.to**
- **Playvid**
- **Playwire**
- **plus.google**: Google Plus
- **pluzz.francetv.fr**
- **podomatic**
- **PornHd**
- **PornHub**
- **PornHubPlaylist**
- **Pornotube**
- **PornoXO**
- **PrimeShareTV**
- **PromptFile**
- **prosiebensat1**: ProSiebenSat.1 Digital
- **Puls4**
- **Pyvideo**
- **QuickVid**
- **R7**
- **radio.de**
- **radiobremen**
- **radiofrance**
- **Rai**
- **RBMARadio**
- **RedTube**
- **Restudy**
- **ReverbNation**
- **RingTV**
- **RottenTomatoes**
- **Roxwel**
- **RTBF**
- **Rte**
- **rtl.nl**: rtl.nl and rtlxl.nl
- **RTL2**
- **RTLnow**
- **RTP**
- **RTS**: RTS.ch
- **rtve.es:alacarta**: RTVE a la carta
- **rtve.es:infantil**: RTVE infantil
- **rtve.es:live**: RTVE.es live streams
- **RUHD**
- **rutube**: Rutube videos
- **rutube:channel**: Rutube channels
- **rutube:embed**: Rutube embedded videos
- **rutube:movie**: Rutube movies
- **rutube:person**: Rutube person videos
- **RUTV**: RUTV.RU
- **Sandia**: Sandia National Laboratories
- **Sapo**: SAPO Vídeos
- **savefrom.net**
- **SBS**: sbs.com.au
- **SciVee**
- **screen.yahoo:search**: Yahoo screen search
- **Screencast**
- **ScreencastOMatic**
- **ScreenwaveMedia**
- **ServingSys**
- **Sexu**
- **SexyKarma**: Sexy Karma and Watch Indian Porn
- **Shared**
- **ShareSix**
- **Sina**
- **Slideshare**
- **Slutload**
- **smotri**: Smotri.com
- **smotri:broadcast**: Smotri.com broadcasts
- **smotri:community**: Smotri.com community videos
- **smotri:user**: Smotri.com user videos
- **Snotr**
- **Sockshare**
- **Sohu**
- **soundcloud**
- **soundcloud:playlist**
- **soundcloud:set**
- **soundcloud:user**
- **soundgasm**
- **soundgasm:profile**
- **southpark.cc.com**
- **southpark.de**
- **Space**
- **Spankwire**
- **Spiegel**
- **Spiegel:Article**: Articles on spiegel.de
- **Spiegeltv**
- **Spike**
- **Sport5**
- **SportBox**
- **SportDeutschland**
- **SRMediathek**: Saarländischer Rundfunk
- **SSA**
- **stanfordoc**: Stanford Open ClassRoom
- **Steam**
- **streamcloud.eu**
- **StreamCZ**
- **StreetVoice**
- **SunPorno**
- **SVTPlay**: SVT Play and Öppet arkiv
- **SWRMediathek**
- **Syfy**
- **SztvHu**
- **Tagesschau**
- **Tapely**
- **Tass**
- **teachertube**: teachertube.com videos
- **teachertube:user:collection**: teachertube.com user and collection videos
- **TeachingChannel**
- **Teamcoco**
- **TeamFour**
- **TechTalks**
- **techtv.mit.edu**
- **TED**
- **tegenlicht.vpro.nl**
- **TeleBruxelles**
- **telecinco.es**
- **TeleMB**
- **TeleTask**
- **TenPlay**
- **TestTube**
- **TF1**
- **TheOnion**
- **ThePlatform**
- **TheSixtyOne**
- **ThisAV**
- **THVideo**
- **THVideoPlaylist**
- **tinypic**: tinypic.com videos
- **tlc.com**
- **tlc.de**
- **TMZ**
- **TNAFlix**
- **tou.tv**
- **Toypics**: Toypics user profile
- **ToypicsUser**: Toypics user profile
- **TrailerAddict** (Currently broken)
- **Trilulilu**
- **TruTube**
- **Tube8**
- **Tudou**
- **Tumblr**
- **TuneIn**
- **Turbo**
- **Tutv**
- **tv.dfb.de**
- **TV4**: tv4.se and tv4play.se
- **tvigle**: Интернет-телевидение Tvigle.ru
- **tvp.pl**
- **tvp.pl:Series**
- **TVPlay**: TV3Play and related services
- **Tweakers**
- **twitch:bookmarks**
- **twitch:chapter**
- **twitch:past_broadcasts**
- **twitch:profile**
- **twitch:stream**
- **twitch:video**
- **twitch:vod**
- **Ubu**
- **udemy**
- **udemy:course**
- **Ultimedia**
- **Unistra**
- **Urort**: NRK P3 Urørt
- **ustream**
- **ustream:channel**
- **Vbox7**
- **VeeHD**
- **Veoh**
- **Vesti**: Вести.Ru
- **Vevo**
- **VGTV**
- **vh1.com**
- **Vice**
- **Viddler**
- **video.google:search**: Google Video search
- **video.mit.edu**
- **VideoBam**
- **VideoDetective**
- **videofy.me**
- **videolectures.net**
- **VideoMega**
- **VideoPremium**
- **VideoTt**: video.tt - Your True Tube
- **videoweed**: VideoWeed
- **Vidme**
- **Vidzi**
- **vier**
- **vier:videos**
- **Viewster**
- **viki**
- **vimeo**
- **vimeo:album**
- **vimeo:channel**
- **vimeo:group**
- **vimeo:likes**: Vimeo user likes
- **vimeo:review**: Review pages on vimeo
- **vimeo:user**
- **vimeo:watchlater**: Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)
- **Vimple**: Vimple.ru
- **Vine**
- **vine:user**
- **vk.com**
- **vk.com:user-videos**: vk.com:All of a user's videos
- **Vodlocker**
- **Vporn**
- **VRT**
- **vube**: Vube.com
- **VuClip**
- **vulture.com**
- **Walla**
- **WashingtonPost**
- **wat.tv**
- **WayOfTheMaster**
- **WDR**
- **wdr:mobile**
- **WDRMaus**: Sendung mit der Maus
- **WebOfStories**
- **Weibo**
- **Wimp**
- **Wistia**
- **WorldStarHipHop**
- **wrzuta.pl**
- **WSJ**: Wall Street Journal
- **XBef**
- **XboxClips**
- **XHamster**
- **XMinus**
- **XNXX**
- **XTube**
- **XTubeUser**: XTube user profile
- **Xuite**
- **XVideos**
- **XXXYMovies**
- **Yahoo**: Yahoo screen and movies
- **Yam**
- **yandexmusic:album**: Яндекс.Музыка - Альбом
- **yandexmusic:playlist**: Яндекс.Музыка - Плейлист
- **yandexmusic:track**: Яндекс.Музыка - Трек
- **YesJapan**
- **Ynet**
- **YouJizz**
- **Youku**
- **YouPorn**
- **YourUpload**
- **youtube**: YouTube.com
- **youtube:channel**: YouTube.com channels
- **youtube:favorites**: YouTube.com favourite videos, ":ytfav" for short (requires authentication)
- **youtube:history**: Youtube watch history, ":ythistory" for short (requires authentication)
- **youtube:playlist**: YouTube.com playlists
- **youtube:recommended**: YouTube.com recommended videos, ":ytrec" for short (requires authentication)
- **youtube:search**: YouTube.com searches
- **youtube:search:date**: YouTube.com searches, newest videos first
- **youtube:search_url**: YouTube.com search URLs
- **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:watch_later**: Youtube watch later list, ":ytwatchlater" for short (requires authentication)
- **Zapiks**
- **ZDF**
- **ZDFChannel**
- **zingmp3:album**: mp3.zing.vn albums
- **zingmp3:song**: mp3.zing.vn songs

4
setup.cfg
View File

@ -1,2 +1,6 @@
[wheel] [wheel]
universal = True universal = True
[flake8]
exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,setup.py,build,.git
ignore = E402,E501,E731

5
setup.py
View File

@ -4,7 +4,6 @@
from __future__ import print_function from __future__ import print_function
import os.path import os.path
import pkg_resources
import warnings import warnings
import sys import sys
@ -103,7 +102,9 @@ setup(
"Programming Language :: Python :: 2.6", "Programming Language :: Python :: 2.6",
"Programming Language :: Python :: 2.7", "Programming Language :: Python :: 2.7",
"Programming Language :: Python :: 3", "Programming Language :: Python :: 3",
"Programming Language :: Python :: 3.3" "Programming Language :: Python :: 3.2",
"Programming Language :: Python :: 3.3",
"Programming Language :: Python :: 3.4",
], ],
**params **params

114
test/helper.py
View File

@ -1,3 +1,5 @@
from __future__ import unicode_literals
import errno import errno
import io import io
import hashlib import hashlib
@ -12,6 +14,7 @@ from youtube_dl import YoutubeDL
from youtube_dl.utils import ( from youtube_dl.utils import (
compat_str, compat_str,
preferredencoding, preferredencoding,
write_string,
) )
@ -40,10 +43,10 @@ def report_warning(message):
If stderr is a tty file the 'WARNING:' will be colored If stderr is a tty file the 'WARNING:' will be colored
''' '''
if sys.stderr.isatty() and os.name != 'nt': if sys.stderr.isatty() and os.name != 'nt':
_msg_header = u'\033[0;33mWARNING:\033[0m' _msg_header = '\033[0;33mWARNING:\033[0m'
else: else:
_msg_header = u'WARNING:' _msg_header = 'WARNING:'
output = u'%s %s\n' % (_msg_header, message) output = '%s %s\n' % (_msg_header, message)
if 'b' in getattr(sys.stderr, 'mode', '') or sys.version_info[0] < 3: if 'b' in getattr(sys.stderr, 'mode', '') or sys.version_info[0] < 3:
output = output.encode(preferredencoding()) output = output.encode(preferredencoding())
sys.stderr.write(output) sys.stderr.write(output)
@ -54,9 +57,9 @@ class FakeYDL(YoutubeDL):
# Different instances of the downloader can't share the same dictionary # Different instances of the downloader can't share the same dictionary
# some test set the "sublang" parameter, which would break the md5 checks. # some test set the "sublang" parameter, which would break the md5 checks.
params = get_params(override=override) params = get_params(override=override)
super(FakeYDL, self).__init__(params) super(FakeYDL, self).__init__(params, auto_init=False)
self.result = [] self.result = []
def to_screen(self, s, skip_eol=None): def to_screen(self, s, skip_eol=None):
print(s) print(s)
@ -69,32 +72,24 @@ class FakeYDL(YoutubeDL):
def expect_warning(self, regex): def expect_warning(self, regex):
# Silence an expected warning matching a regex # Silence an expected warning matching a regex
old_report_warning = self.report_warning old_report_warning = self.report_warning
def report_warning(self, message): def report_warning(self, message):
if re.match(regex, message): return if re.match(regex, message):
return
old_report_warning(message) old_report_warning(message)
self.report_warning = types.MethodType(report_warning, self) self.report_warning = types.MethodType(report_warning, self)
def gettestcases(include_onlymatching=False): def gettestcases(include_onlymatching=False):
for ie in youtube_dl.extractor.gen_extractors(): for ie in youtube_dl.extractor.gen_extractors():
t = getattr(ie, '_TEST', None) for tc in ie.get_testcases(include_onlymatching):
if t: yield tc
assert not hasattr(ie, '_TESTS'), \
'%s has _TEST and _TESTS' % type(ie).__name__
tests = [t]
else:
tests = getattr(ie, '_TESTS', [])
for t in tests:
if not include_onlymatching and t.get('only_matching', False):
continue
t['name'] = type(ie).__name__[:-len('IE')]
yield t
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
def expect_info_dict(self, expected_dict, got_dict): def expect_info_dict(self, got_dict, expected_dict):
for info_field, expected in expected_dict.items(): for info_field, expected in expected_dict.items():
if isinstance(expected, compat_str) and expected.startswith('re:'): if isinstance(expected, compat_str) and expected.startswith('re:'):
got = got_dict.get(info_field) got = got_dict.get(info_field)
@ -103,22 +98,56 @@ def expect_info_dict(self, expected_dict, got_dict):
self.assertTrue( self.assertTrue(
isinstance(got, compat_str), isinstance(got, compat_str),
u'Expected a %s object, but got %s for field %s' % ( 'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, info_field)) compat_str.__name__, type(got).__name__, info_field))
self.assertTrue( self.assertTrue(
match_rex.match(got), match_rex.match(got),
u'field %s (value: %r) should match %r' % (info_field, got, match_str)) 'field %s (value: %r) should match %r' % (info_field, got, match_str))
elif isinstance(expected, compat_str) and expected.startswith('startswith:'):
got = got_dict.get(info_field)
start_str = expected[len('startswith:'):]
self.assertTrue(
isinstance(got, compat_str),
'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, info_field))
self.assertTrue(
got.startswith(start_str),
'field %s (value: %r) should start with %r' % (info_field, got, start_str))
elif isinstance(expected, compat_str) and expected.startswith('contains:'):
got = got_dict.get(info_field)
contains_str = expected[len('contains:'):]
self.assertTrue(
isinstance(got, compat_str),
'Expected a %s object, but got %s for field %s' % (
compat_str.__name__, type(got).__name__, info_field))
self.assertTrue(
contains_str in got,
'field %s (value: %r) should contain %r' % (info_field, got, contains_str))
elif isinstance(expected, type): elif isinstance(expected, type):
got = got_dict.get(info_field) got = got_dict.get(info_field)
self.assertTrue(isinstance(got, expected), self.assertTrue(isinstance(got, expected),
u'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got))) 'Expected type %r for field %s, but got value %r of type %r' % (expected, info_field, got, type(got)))
else: else:
if isinstance(expected, compat_str) and expected.startswith('md5:'): if isinstance(expected, compat_str) and expected.startswith('md5:'):
got = 'md5:' + md5(got_dict.get(info_field)) got = 'md5:' + md5(got_dict.get(info_field))
elif isinstance(expected, compat_str) and expected.startswith('mincount:'):
got = got_dict.get(info_field)
self.assertTrue(
isinstance(got, list),
'Expected field %s to be a list, but it is of type %s' % (
info_field, type(got).__name__))
expected_num = int(expected.partition(':')[2])
assertGreaterEqual(
self, len(got), expected_num,
'Expected %d items in field %s, but only got %d' % (
expected_num, info_field, len(got)
)
)
continue
else: else:
got = got_dict.get(info_field) got = got_dict.get(info_field)
self.assertEqual(expected, got, self.assertEqual(expected, got,
u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got)) 'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
# Check for the presence of mandatory fields # Check for the presence of mandatory fields
if got_dict.get('_type') != 'playlist': if got_dict.get('_type') != 'playlist':
@ -126,15 +155,32 @@ def expect_info_dict(self, expected_dict, got_dict):
self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key) self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
# Check for mandatory fields that are automatically set by YoutubeDL # Check for mandatory fields that are automatically set by YoutubeDL
for key in ['webpage_url', 'extractor', 'extractor_key']: for key in ['webpage_url', 'extractor', 'extractor_key']:
self.assertTrue(got_dict.get(key), u'Missing field: %s' % key) self.assertTrue(got_dict.get(key), 'Missing field: %s' % key)
# Are checkable fields missing from the test case definition? # Are checkable fields missing from the test case definition?
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value)) test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
for key, value in got_dict.items() for key, value in got_dict.items()
if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location')) if value and key in ('id', 'title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location'))
missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys()) missing_keys = set(test_info_dict.keys()) - set(expected_dict.keys())
if missing_keys: if missing_keys:
sys.stderr.write(u'\n"info_dict": ' + json.dumps(test_info_dict, ensure_ascii=False, indent=4) + u'\n') def _repr(v):
if isinstance(v, compat_str):
return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
else:
return repr(v)
info_dict_str = ''
if len(missing_keys) != len(expected_dict):
info_dict_str += ''.join(
' %s: %s,\n' % (_repr(k), _repr(v))
for k, v in test_info_dict.items() if k not in missing_keys)
if info_dict_str:
info_dict_str += '\n'
info_dict_str += ''.join(
' %s: %s,\n' % (_repr(k), _repr(test_info_dict[k]))
for k in missing_keys)
write_string(
'\n\'info_dict\': {\n' + info_dict_str + '},\n', out=sys.stderr)
self.assertFalse( self.assertFalse(
missing_keys, missing_keys,
'Missing keys in test definition: %s' % ( 'Missing keys in test definition: %s' % (
@ -147,7 +193,9 @@ def assertRegexpMatches(self, text, regexp, msg=None):
else: else:
m = re.match(regexp, text) m = re.match(regexp, text)
if not m: if not m:
note = 'Regexp didn\'t match: %r not found in %r' % (regexp, text) note = 'Regexp didn\'t match: %r not found' % (regexp)
if len(text) < 1000:
note += ' in %r' % text
if msg is None: if msg is None:
msg = note msg = note
else: else:
@ -160,3 +208,13 @@ def assertGreaterEqual(self, got, expected, msg=None):
if msg is None: if msg is None:
msg = '%r not greater than or equal to %r' % (got, expected) msg = '%r not greater than or equal to %r' % (got, expected)
self.assertTrue(got >= expected, msg) self.assertTrue(got >= expected, msg)
def expect_warnings(ydl, warnings_re):
real_warning = ydl.report_warning
def _report_warning(w):
if not any(re.search(w_re, w) for w_re in warnings_re):
real_warning(w)
ydl.report_warning = _report_warning

5
test/parameters.json
View File

@ -28,7 +28,7 @@
"retries": 10, "retries": 10,
"simulate": false, "simulate": false,
"subtitleslang": null, "subtitleslang": null,
"subtitlesformat": "srt", "subtitlesformat": "best",
"test": true, "test": true,
"updatetime": true, "updatetime": true,
"usenetrc": false, "usenetrc": false,
@ -39,5 +39,6 @@
"writesubtitles": false, "writesubtitles": false,
"allsubtitles": false, "allsubtitles": false,
"listssubtitles": false, "listssubtitles": false,
"socket_timeout": 20 "socket_timeout": 20,
"fixup": "never"
} }

18
test/swftests/ConstArrayAccess.as Normal file
View File

@ -0,0 +1,18 @@
// input: []
// output: 4
package {
public class ConstArrayAccess {
private static const x:int = 2;
private static const ar:Array = ["42", "3411"];
public static function main():int{
var c:ConstArrayAccess = new ConstArrayAccess();
return c.f();
}
public function f(): int {
return ar[1].length;
}
}
}

12
test/swftests/ConstantInt.as Normal file
View File

@ -0,0 +1,12 @@
// input: []
// output: 2
package {
public class ConstantInt {
private static const x:int = 2;
public static function main():int{
return x;
}
}
}

10
test/swftests/DictCall.as Normal file
View File

@ -0,0 +1,10 @@
// input: [{"x": 1, "y": 2}]
// output: 3
package {
public class DictCall {
public static function main(d:Object):int{
return d.x + d.y;
}
}
}

10
test/swftests/EqualsOperator.as Normal file
View File

@ -0,0 +1,10 @@
// input: []
// output: false
package {
public class EqualsOperator {
public static function main():Boolean{
return 1 == 2;
}
}
}

22
test/swftests/MemberAssignment.as Normal file
View File

@ -0,0 +1,22 @@
// input: [1]
// output: 2
package {
public class MemberAssignment {
public var v:int;
public function g():int {
return this.v;
}
public function f(a:int):int{
this.v = a;
return this.v + this.g();
}
public static function main(a:int): int {
var v:MemberAssignment = new MemberAssignment();
return v.f(a);
}
}
}

24
test/swftests/NeOperator.as Normal file
View File

@ -0,0 +1,24 @@
// input: []
// output: 123
package {
public class NeOperator {
public static function main(): int {
var res:int = 0;
if (1 != 2) {
res += 3;
} else {
res += 4;
}
if (2 != 2) {
res += 10;
} else {
res += 20;
}
if (9 == 9) {
res += 100;
}
return res;
}
}
}

22
test/swftests/PrivateVoidCall.as Normal file
View File

@ -0,0 +1,22 @@
// input: []
// output: 9
package {
public class PrivateVoidCall {
public static function main():int{
var f:OtherClass = new OtherClass();
f.func();
return 9;
}
}
}
class OtherClass {
private function pf():void {
;
}
public function func():void {
this.pf();
}
}

11
test/swftests/StringBasics.as Normal file
View File

@ -0,0 +1,11 @@
// input: []
// output: 3
package {
public class StringBasics {
public static function main():int{
var s:String = "abc";
return s.length;
}
}
}

11
test/swftests/StringCharCodeAt.as Normal file
View File

@ -0,0 +1,11 @@
// input: []
// output: 9897
package {
public class StringCharCodeAt {
public static function main():int{
var s:String = "abc";
return s.charCodeAt(1) * 100 + s.charCodeAt();
}
}
}

11
test/swftests/StringConversion.as Normal file
View File

@ -0,0 +1,11 @@
// input: []
// output: 2
package {
public class StringConversion {
public static function main():int{
var s:String = String(99);
return s.length;
}
}
}

18
test/test_InfoExtractor.py
View File

@ -40,5 +40,23 @@ class TestInfoExtractor(unittest.TestCase):
self.assertEqual(ie._og_search_description(html), 'Some video\'s description ') self.assertEqual(ie._og_search_description(html), 'Some video\'s description ')
self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2') self.assertEqual(ie._og_search_thumbnail(html), 'http://domain.com/pic.jpg?key1=val1&key2=val2')
def test_html_search_meta(self):
ie = self.ie
html = '''
<meta name="a" content="1" />
<meta name='b' content='2'>
<meta name="c" content='3'>
<meta name=d content='4'>
<meta property="e" content='5' >
<meta content="6" name="f">
'''
self.assertEqual(ie._html_search_meta('a', html), '1')
self.assertEqual(ie._html_search_meta('b', html), '2')
self.assertEqual(ie._html_search_meta('c', html), '3')
self.assertEqual(ie._html_search_meta('d', html), '4')
self.assertEqual(ie._html_search_meta('e', html), '5')
self.assertEqual(ie._html_search_meta('f', html), '6')
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

297
test/test_YoutubeDL.py
View File

@ -8,9 +8,15 @@ import sys
import unittest import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import copy
from test.helper import FakeYDL, assertRegexpMatches from test.helper import FakeYDL, assertRegexpMatches
from youtube_dl import YoutubeDL from youtube_dl import YoutubeDL
from youtube_dl.extractor import YoutubeIE from youtube_dl.extractor import YoutubeIE
from youtube_dl.postprocessor.common import PostProcessor
from youtube_dl.utils import match_filter_func
TEST_URL = 'http://localhost/sample.mp4'
class YDL(FakeYDL): class YDL(FakeYDL):
@ -43,8 +49,8 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL() ydl = YDL()
ydl.params['prefer_free_formats'] = True ydl.params['prefer_free_formats'] = True
formats = [ formats = [
{'ext': 'webm', 'height': 460, 'url': 'x'}, {'ext': 'webm', 'height': 460, 'url': TEST_URL},
{'ext': 'mp4', 'height': 460, 'url': 'y'}, {'ext': 'mp4', 'height': 460, 'url': TEST_URL},
] ]
info_dict = _make_result(formats) info_dict = _make_result(formats)
yie = YoutubeIE(ydl) yie = YoutubeIE(ydl)
@ -57,8 +63,8 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL() ydl = YDL()
ydl.params['prefer_free_formats'] = True ydl.params['prefer_free_formats'] = True
formats = [ formats = [
{'ext': 'webm', 'height': 720, 'url': 'a'}, {'ext': 'webm', 'height': 720, 'url': TEST_URL},
{'ext': 'mp4', 'height': 1080, 'url': 'b'}, {'ext': 'mp4', 'height': 1080, 'url': TEST_URL},
] ]
info_dict['formats'] = formats info_dict['formats'] = formats
yie = YoutubeIE(ydl) yie = YoutubeIE(ydl)
@ -71,9 +77,9 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL() ydl = YDL()
ydl.params['prefer_free_formats'] = False ydl.params['prefer_free_formats'] = False
formats = [ formats = [
{'ext': 'webm', 'height': 720, 'url': '_'}, {'ext': 'webm', 'height': 720, 'url': TEST_URL},
{'ext': 'mp4', 'height': 720, 'url': '_'}, {'ext': 'mp4', 'height': 720, 'url': TEST_URL},
{'ext': 'flv', 'height': 720, 'url': '_'}, {'ext': 'flv', 'height': 720, 'url': TEST_URL},
] ]
info_dict['formats'] = formats info_dict['formats'] = formats
yie = YoutubeIE(ydl) yie = YoutubeIE(ydl)
@ -85,8 +91,8 @@ class TestFormatSelection(unittest.TestCase):
ydl = YDL() ydl = YDL()
ydl.params['prefer_free_formats'] = False ydl.params['prefer_free_formats'] = False
formats = [ formats = [
{'ext': 'flv', 'height': 720, 'url': '_'}, {'ext': 'flv', 'height': 720, 'url': TEST_URL},
{'ext': 'webm', 'height': 720, 'url': '_'}, {'ext': 'webm', 'height': 720, 'url': TEST_URL},
] ]
info_dict['formats'] = formats info_dict['formats'] = formats
yie = YoutubeIE(ydl) yie = YoutubeIE(ydl)
@ -130,10 +136,10 @@ class TestFormatSelection(unittest.TestCase):
def test_format_selection(self): def test_format_selection(self):
formats = [ formats = [
{'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': '_'}, {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
{'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': '_'}, {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL},
{'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': '_'}, {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL},
{'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': '_'}, {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL},
] ]
info_dict = _make_result(formats) info_dict = _make_result(formats)
@ -164,10 +170,10 @@ class TestFormatSelection(unittest.TestCase):
def test_format_selection_audio(self): def test_format_selection_audio(self):
formats = [ formats = [
{'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': '_'}, {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': '_'}, {'format_id': 'audio-mid', 'ext': 'webm', 'preference': 2, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': '_'}, {'format_id': 'audio-high', 'ext': 'flv', 'preference': 3, 'vcodec': 'none', 'url': TEST_URL},
{'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': '_'}, {'format_id': 'vid', 'ext': 'mp4', 'preference': 4, 'url': TEST_URL},
] ]
info_dict = _make_result(formats) info_dict = _make_result(formats)
@ -182,8 +188,8 @@ class TestFormatSelection(unittest.TestCase):
self.assertEqual(downloaded['format_id'], 'audio-low') self.assertEqual(downloaded['format_id'], 'audio-low')
formats = [ formats = [
{'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': '_'}, {'format_id': 'vid-low', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL},
{'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': '_'}, {'format_id': 'vid-high', 'ext': 'mp4', 'preference': 2, 'url': TEST_URL},
] ]
info_dict = _make_result(formats) info_dict = _make_result(formats)
@ -192,11 +198,42 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0] downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'vid-high') self.assertEqual(downloaded['format_id'], 'vid-high')
def test_format_selection_audio_exts(self):
formats = [
{'format_id': 'mp3-64', 'ext': 'mp3', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
{'format_id': 'ogg-64', 'ext': 'ogg', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
{'format_id': 'aac-64', 'ext': 'aac', 'abr': 64, 'url': 'http://_', 'vcodec': 'none'},
{'format_id': 'mp3-32', 'ext': 'mp3', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
{'format_id': 'aac-32', 'ext': 'aac', 'abr': 32, 'url': 'http://_', 'vcodec': 'none'},
]
info_dict = _make_result(formats)
ydl = YDL({'format': 'best'})
ie = YoutubeIE(ydl)
ie._sort_formats(info_dict['formats'])
ydl.process_ie_result(copy.deepcopy(info_dict))
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'aac-64')
ydl = YDL({'format': 'mp3'})
ie = YoutubeIE(ydl)
ie._sort_formats(info_dict['formats'])
ydl.process_ie_result(copy.deepcopy(info_dict))
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'mp3-64')
ydl = YDL({'prefer_free_formats': True})
ie = YoutubeIE(ydl)
ie._sort_formats(info_dict['formats'])
ydl.process_ie_result(copy.deepcopy(info_dict))
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'ogg-64')
def test_format_selection_video(self): def test_format_selection_video(self):
formats = [ formats = [
{'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': '_'}, {'format_id': 'dash-video-low', 'ext': 'mp4', 'preference': 1, 'acodec': 'none', 'url': TEST_URL},
{'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': '_'}, {'format_id': 'dash-video-high', 'ext': 'mp4', 'preference': 2, 'acodec': 'none', 'url': TEST_URL},
{'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': '_'}, {'format_id': 'vid', 'ext': 'mp4', 'preference': 3, 'url': TEST_URL},
] ]
info_dict = _make_result(formats) info_dict = _make_result(formats)
@ -218,7 +255,7 @@ class TestFormatSelection(unittest.TestCase):
# 3D # 3D
'85', '84', '102', '83', '101', '82', '100', '85', '84', '102', '83', '101', '82', '100',
# Dash video # Dash video
'138', '137', '248', '136', '247', '135', '246', '137', '248', '136', '247', '135', '246',
'245', '244', '134', '243', '133', '242', '160', '245', '244', '134', '243', '133', '242', '160',
# Dash audio # Dash audio
'141', '172', '140', '171', '139', '141', '172', '140', '171', '139',
@ -248,6 +285,122 @@ class TestFormatSelection(unittest.TestCase):
downloaded = ydl.downloaded_info_dicts[0] downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], f1id) self.assertEqual(downloaded['format_id'], f1id)
def test_format_filtering(self):
formats = [
{'format_id': 'A', 'filesize': 500, 'width': 1000},
{'format_id': 'B', 'filesize': 1000, 'width': 500},
{'format_id': 'C', 'filesize': 1000, 'width': 400},
{'format_id': 'D', 'filesize': 2000, 'width': 600},
{'format_id': 'E', 'filesize': 3000},
{'format_id': 'F'},
{'format_id': 'G', 'filesize': 1000000},
]
for f in formats:
f['url'] = 'http://_/'
f['ext'] = 'unknown'
info_dict = _make_result(formats)
ydl = YDL({'format': 'best[filesize<3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'D')
ydl = YDL({'format': 'best[filesize<=3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'E')
ydl = YDL({'format': 'best[filesize <= ? 3000]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'F')
ydl = YDL({'format': 'best [filesize = 1000] [width>450]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'B')
ydl = YDL({'format': 'best [filesize = 1000] [width!=450]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'C')
ydl = YDL({'format': '[filesize>?1]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'G')
ydl = YDL({'format': '[filesize<1M]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'E')
ydl = YDL({'format': '[filesize<1MiB]'})
ydl.process_ie_result(info_dict)
downloaded = ydl.downloaded_info_dicts[0]
self.assertEqual(downloaded['format_id'], 'G')
class TestYoutubeDL(unittest.TestCase):
def test_subtitles(self):
def s_formats(lang, autocaption=False):
return [{
'ext': ext,
'url': 'http://localhost/video.%s.%s' % (lang, ext),
'_auto': autocaption,
} for ext in ['vtt', 'srt', 'ass']]
subtitles = dict((l, s_formats(l)) for l in ['en', 'fr', 'es'])
auto_captions = dict((l, s_formats(l, True)) for l in ['it', 'pt', 'es'])
info_dict = {
'id': 'test',
'title': 'Test',
'url': 'http://localhost/video.mp4',
'subtitles': subtitles,
'automatic_captions': auto_captions,
'extractor': 'TEST',
}
def get_info(params={}):
params.setdefault('simulate', True)
ydl = YDL(params)
ydl.report_warning = lambda *args, **kargs: None
return ydl.process_video_result(info_dict, download=False)
result = get_info()
self.assertFalse(result.get('requested_subtitles'))
self.assertEqual(result['subtitles'], subtitles)
self.assertEqual(result['automatic_captions'], auto_captions)
result = get_info({'writesubtitles': True})
subs = result['requested_subtitles']
self.assertTrue(subs)
self.assertEqual(set(subs.keys()), set(['en']))
self.assertTrue(subs['en'].get('data') is None)
self.assertEqual(subs['en']['ext'], 'ass')
result = get_info({'writesubtitles': True, 'subtitlesformat': 'foo/srt'})
subs = result['requested_subtitles']
self.assertEqual(subs['en']['ext'], 'srt')
result = get_info({'writesubtitles': True, 'subtitleslangs': ['es', 'fr', 'it']})
subs = result['requested_subtitles']
self.assertTrue(subs)
self.assertEqual(set(subs.keys()), set(['es', 'fr']))
result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
subs = result['requested_subtitles']
self.assertTrue(subs)
self.assertEqual(set(subs.keys()), set(['es', 'pt']))
self.assertFalse(subs['es']['_auto'])
self.assertTrue(subs['pt']['_auto'])
result = get_info({'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']})
subs = result['requested_subtitles']
self.assertTrue(subs)
self.assertEqual(set(subs.keys()), set(['es', 'pt']))
self.assertTrue(subs['es']['_auto'])
self.assertTrue(subs['pt']['_auto'])
def test_add_extra_info(self): def test_add_extra_info(self):
test_dict = { test_dict = {
'extractor': 'Foo', 'extractor': 'Foo',
@ -266,6 +419,7 @@ class TestFormatSelection(unittest.TestCase):
'ext': 'mp4', 'ext': 'mp4',
'width': None, 'width': None,
} }
def fname(templ): def fname(templ):
ydl = YoutubeDL({'outtmpl': templ}) ydl = YoutubeDL({'outtmpl': templ})
return ydl.prepare_filename(info) return ydl.prepare_filename(info)
@ -281,5 +435,102 @@ class TestFormatSelection(unittest.TestCase):
'vbr': 10, 'vbr': 10,
}), '^\s*10k$') }), '^\s*10k$')
def test_postprocessors(self):
filename = 'post-processor-testfile.mp4'
audiofile = filename + '.mp3'
class SimplePP(PostProcessor):
def run(self, info):
with open(audiofile, 'wt') as f:
f.write('EXAMPLE')
info['filepath']
return False, info
def run_pp(params):
with open(filename, 'wt') as f:
f.write('EXAMPLE')
ydl = YoutubeDL(params)
ydl.add_post_processor(SimplePP())
ydl.post_process(filename, {'filepath': filename})
run_pp({'keepvideo': True})
self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
os.unlink(filename)
os.unlink(audiofile)
run_pp({'keepvideo': False})
self.assertFalse(os.path.exists(filename), '%s exists' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
os.unlink(audiofile)
def test_match_filter(self):
class FilterYDL(YDL):
def __init__(self, *args, **kwargs):
super(FilterYDL, self).__init__(*args, **kwargs)
self.params['simulate'] = True
def process_info(self, info_dict):
super(YDL, self).process_info(info_dict)
def _match_entry(self, info_dict, incomplete):
res = super(FilterYDL, self)._match_entry(info_dict, incomplete)
if res is None:
self.downloaded_info_dicts.append(info_dict)
return res
first = {
'id': '1',
'url': TEST_URL,
'title': 'one',
'extractor': 'TEST',
'duration': 30,
'filesize': 10 * 1024,
}
second = {
'id': '2',
'url': TEST_URL,
'title': 'two',
'extractor': 'TEST',
'duration': 10,
'description': 'foo',
'filesize': 5 * 1024,
}
videos = [first, second]
def get_videos(filter_=None):
ydl = FilterYDL({'match_filter': filter_})
for v in videos:
ydl.process_ie_result(v, download=True)
return [v['id'] for v in ydl.downloaded_info_dicts]
res = get_videos()
self.assertEqual(res, ['1', '2'])
def f(v):
if v['id'] == '1':
return None
else:
return 'Video id is not 1'
res = get_videos(f)
self.assertEqual(res, ['1'])
f = match_filter_func('duration < 30')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description = foo')
res = get_videos(f)
self.assertEqual(res, ['2'])
f = match_filter_func('description =? foo')
res = get_videos(f)
self.assertEqual(res, ['1', '2'])
f = match_filter_func('filesize > 5KiB')
res = get_videos(f)
self.assertEqual(res, ['1'])
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

55
test/test_aes.py Normal file
View File

@ -0,0 +1,55 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.aes import aes_decrypt, aes_encrypt, aes_cbc_decrypt, aes_decrypt_text
from youtube_dl.utils import bytes_to_intlist, intlist_to_bytes
import base64
# the encrypted data can be generate with 'devscripts/generate_aes_testdata.py'
class TestAES(unittest.TestCase):
def setUp(self):
self.key = self.iv = [0x20, 0x15] + 14 * [0]
self.secret_msg = b'Secret message goes here'
def test_encrypt(self):
msg = b'message'
key = list(range(16))
encrypted = aes_encrypt(bytes_to_intlist(msg), key)
decrypted = intlist_to_bytes(aes_decrypt(encrypted, key))
self.assertEqual(decrypted, msg)
def test_cbc_decrypt(self):
data = bytes_to_intlist(
b"\x97\x92+\xe5\x0b\xc3\x18\x91ky9m&\xb3\xb5@\xe6'\xc2\x96.\xc8u\x88\xab9-[\x9e|\xf1\xcd"
)
decrypted = intlist_to_bytes(aes_cbc_decrypt(data, self.key, self.iv))
self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8]) +
b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
)
decrypted = (aes_decrypt_text(encrypted, password, 16))
self.assertEqual(decrypted, self.secret_msg)
password = intlist_to_bytes(self.key).decode('utf-8')
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8]) +
b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
)
decrypted = (aes_decrypt_text(encrypted, password, 32))
self.assertEqual(decrypted, self.secret_msg)
if __name__ == '__main__':
unittest.main()

8
test/test_age_restriction.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution # Allow direct execution
import os import os
@ -19,7 +20,7 @@ def _download_restricted(url, filename, age):
'age_limit': age, 'age_limit': age,
'skip_download': True, 'skip_download': True,
'writeinfojson': True, 'writeinfojson': True,
"outtmpl": "%(id)s.%(ext)s", 'outtmpl': '%(id)s.%(ext)s',
} }
ydl = YoutubeDL(params) ydl = YoutubeDL(params)
ydl.add_default_info_extractors() ydl.add_default_info_extractors()
@ -44,11 +45,6 @@ class TestAgeRestriction(unittest.TestCase):
'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
'505835.mp4', 2, old_age=25) '505835.mp4', 2, old_age=25)
def test_pornotube(self):
self._assert_restricted(
'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
'1689755.flv', 13)
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

35
test/test_all_urls.py
View File

@ -14,7 +14,6 @@ from test.helper import gettestcases
from youtube_dl.extractor import ( from youtube_dl.extractor import (
FacebookIE, FacebookIE,
gen_extractors, gen_extractors,
JustinTVIE,
YoutubeIE, YoutubeIE,
) )
@ -32,19 +31,19 @@ class TestAllURLsMatching(unittest.TestCase):
def test_youtube_playlist_matching(self): def test_youtube_playlist_matching(self):
assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist']) assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') #585 assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585
assertPlaylist('PL63F0C78739B09958') assertPlaylist('PL63F0C78739B09958')
assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q') assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668 assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668
self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M')) self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
# Top tracks # Top tracks
assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101') assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
def test_youtube_matching(self): def test_youtube_matching(self):
self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M')) self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668 self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) # 668
self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube']) self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube']) self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube']) self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
@ -72,22 +71,6 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url']) self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url']) self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
def test_justin_tv_channelid_matching(self):
self.assertTrue(JustinTVIE.suitable('justin.tv/vanillatv'))
self.assertTrue(JustinTVIE.suitable('twitch.tv/vanillatv'))
self.assertTrue(JustinTVIE.suitable('www.justin.tv/vanillatv'))
self.assertTrue(JustinTVIE.suitable('www.twitch.tv/vanillatv'))
self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv'))
self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv'))
self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv/'))
self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/'))
def test_justintv_videoid_matching(self):
self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
def test_justin_tv_chapterid_matching(self):
self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
def test_youtube_extract(self): def test_youtube_extract(self):
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id) assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc') assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
@ -119,15 +102,13 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertMatch(':ythistory', ['youtube:history']) self.assertMatch(':ythistory', ['youtube:history'])
self.assertMatch(':thedailyshow', ['ComedyCentralShows']) self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
self.assertMatch(':tds', ['ComedyCentralShows']) self.assertMatch(':tds', ['ComedyCentralShows'])
self.assertMatch(':colbertreport', ['ComedyCentralShows'])
self.assertMatch(':cr', ['ComedyCentralShows'])
def test_vimeo_matching(self): def test_vimeo_matching(self):
self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel']) self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel']) self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo']) self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user']) self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user']) self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review']) self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
# https://github.com/rg3/youtube-dl/issues/1930 # https://github.com/rg3/youtube-dl/issues/1930

46
test/test_compat.py Normal file
View File

@ -0,0 +1,46 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.utils import get_filesystem_encoding
from youtube_dl.compat import (
compat_getenv,
compat_expanduser,
)
class TestCompat(unittest.TestCase):
def test_compat_getenv(self):
test_str = 'тест'
os.environ['YOUTUBE-DL-TEST'] = (
test_str if sys.version_info >= (3, 0)
else test_str.encode(get_filesystem_encoding()))
self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
def test_compat_expanduser(self):
old_home = os.environ.get('HOME')
test_str = 'C:\Documents and Settings\тест\Application Data'
os.environ['HOME'] = (
test_str if sys.version_info >= (3, 0)
else test_str.encode(get_filesystem_encoding()))
self.assertEqual(compat_expanduser('~'), test_str)
os.environ['HOME'] = old_home
def test_all_present(self):
import youtube_dl.compat
all_names = youtube_dl.compat.__all__
present_names = set(filter(
lambda c: '_' in c and not c.startswith('_'),
dir(youtube_dl.compat))) - set(['unicode_literals'])
self.assertEqual(all_names, sorted(present_names))
if __name__ == '__main__':
unittest.main()

47
test/test_download.py
View File

@ -1,5 +1,7 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution # Allow direct execution
import os import os
import sys import sys
@ -8,6 +10,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import ( from test.helper import (
assertGreaterEqual, assertGreaterEqual,
expect_warnings,
get_params, get_params,
gettestcases, gettestcases,
expect_info_dict, expect_info_dict,
@ -22,10 +25,12 @@ import json
import socket import socket
import youtube_dl.YoutubeDL import youtube_dl.YoutubeDL
from youtube_dl.utils import ( from youtube_dl.compat import (
compat_http_client, compat_http_client,
compat_urllib_error, compat_urllib_error,
compat_HTTPError, compat_HTTPError,
)
from youtube_dl.utils import (
DownloadError, DownloadError,
ExtractorError, ExtractorError,
format_bytes, format_bytes,
@ -35,18 +40,22 @@ from youtube_dl.extractor import get_info_extractor
RETRIES = 3 RETRIES = 3
class YoutubeDL(youtube_dl.YoutubeDL): class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
self.to_stderr = self.to_screen self.to_stderr = self.to_screen
self.processed_info_dicts = [] self.processed_info_dicts = []
super(YoutubeDL, self).__init__(*args, **kwargs) super(YoutubeDL, self).__init__(*args, **kwargs)
def report_warning(self, message): def report_warning(self, message):
# Don't accept warnings during tests # Don't accept warnings during tests
raise ExtractorError(message) raise ExtractorError(message)
def process_info(self, info_dict): def process_info(self, info_dict):
self.processed_info_dicts.append(info_dict) self.processed_info_dicts.append(info_dict)
return super(YoutubeDL, self).process_info(info_dict) return super(YoutubeDL, self).process_info(info_dict)
def _file_md5(fn): def _file_md5(fn):
with open(fn, 'rb') as f: with open(fn, 'rb') as f:
return hashlib.md5(f.read()).hexdigest() return hashlib.md5(f.read()).hexdigest()
@ -56,10 +65,13 @@ defs = gettestcases()
class TestDownload(unittest.TestCase): class TestDownload(unittest.TestCase):
maxDiff = None maxDiff = None
def setUp(self): def setUp(self):
self.defs = defs self.defs = defs
### Dynamically generate tests # Dynamically generate tests
def generator(test_case): def generator(test_case):
def test_template(self): def test_template(self):
@ -77,7 +89,7 @@ def generator(test_case):
for tc in test_cases: for tc in test_cases:
info_dict = tc.get('info_dict', {}) info_dict = tc.get('info_dict', {})
if not tc.get('file') and not (info_dict.get('id') and info_dict.get('ext')): if not (info_dict.get('id') and info_dict.get('ext')):
raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?') raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
if 'skip' in test_case: if 'skip' in test_case:
@ -85,7 +97,7 @@ def generator(test_case):
return return
for other_ie in other_ies: for other_ie in other_ies:
if not other_ie.working(): if not other_ie.working():
print_skipping(u'test depends on %sIE, marked as not WORKING' % other_ie.ie_key()) print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
return return
params = get_params(test_case.get('params', {})) params = get_params(test_case.get('params', {}))
@ -93,18 +105,21 @@ def generator(test_case):
params.setdefault('extract_flat', True) params.setdefault('extract_flat', True)
params.setdefault('skip_download', True) params.setdefault('skip_download', True)
ydl = YoutubeDL(params) ydl = YoutubeDL(params, auto_init=False)
ydl.add_default_info_extractors() ydl.add_default_info_extractors()
finished_hook_called = set() finished_hook_called = set()
def _hook(status): def _hook(status):
if status['status'] == 'finished': if status['status'] == 'finished':
finished_hook_called.add(status['filename']) finished_hook_called.add(status['filename'])
ydl.add_progress_hook(_hook) ydl.add_progress_hook(_hook)
expect_warnings(ydl, test_case.get('expected_warnings', []))
def get_tc_filename(tc): def get_tc_filename(tc):
return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {})) return ydl.prepare_filename(tc.get('info_dict', {}))
res_dict = None res_dict = None
def try_rm_tcs_files(tcs=None): def try_rm_tcs_files(tcs=None):
if tcs is None: if tcs is None:
tcs = test_cases tcs = test_cases
@ -128,7 +143,7 @@ def generator(test_case):
raise raise
if try_num == RETRIES: if try_num == RETRIES:
report_warning(u'Failed due to network errors, skipping...') report_warning('Failed due to network errors, skipping...')
return return
print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num)) print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num))
@ -139,7 +154,9 @@ def generator(test_case):
if is_playlist: if is_playlist:
self.assertEqual(res_dict['_type'], 'playlist') self.assertEqual(res_dict['_type'], 'playlist')
expect_info_dict(self, test_case.get('info_dict', {}), res_dict) self.assertTrue('entries' in res_dict)
expect_info_dict(self, res_dict, test_case.get('info_dict', {}))
if 'playlist_mincount' in test_case: if 'playlist_mincount' in test_case:
assertGreaterEqual( assertGreaterEqual(
self, self,
@ -181,14 +198,16 @@ def generator(test_case):
md5_for_file = _file_md5(tc_filename) md5_for_file = _file_md5(tc_filename)
self.assertEqual(md5_for_file, tc['md5']) self.assertEqual(md5_for_file, tc['md5'])
info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json' info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
self.assertTrue(os.path.exists(info_json_fn)) self.assertTrue(
os.path.exists(info_json_fn),
'Missing info file %s' % info_json_fn)
with io.open(info_json_fn, encoding='utf-8') as infof: with io.open(info_json_fn, encoding='utf-8') as infof:
info_dict = json.load(infof) info_dict = json.load(infof)
expect_info_dict(self, tc.get('info_dict', {}), info_dict) expect_info_dict(self, info_dict, tc.get('info_dict', {}))
finally: finally:
try_rm_tcs_files() try_rm_tcs_files()
if is_playlist and res_dict is not None: if is_playlist and res_dict is not None and res_dict.get('entries'):
# Remove all other files that may have been extracted if the # Remove all other files that may have been extracted if the
# extractor returns full results even with extract_flat # extractor returns full results even with extract_flat
res_tcs = [{'info_dict': e} for e in res_dict['entries']] res_tcs = [{'info_dict': e} for e in res_dict['entries']]
@ -196,15 +215,15 @@ def generator(test_case):
return test_template return test_template
### And add them to TestDownload # And add them to TestDownload
for n, test_case in enumerate(defs): for n, test_case in enumerate(defs):
test_method = generator(test_case) test_method = generator(test_case)
tname = 'test_' + str(test_case['name']) tname = 'test_' + str(test_case['name'])
i = 1 i = 1
while hasattr(TestDownload, tname): while hasattr(TestDownload, tname):
tname = 'test_' + str(test_case['name']) + '_' + str(i) tname = 'test_%s_%d' % (test_case['name'], i)
i += 1 i += 1
test_method.__name__ = tname test_method.__name__ = str(tname)
setattr(TestDownload, test_method.__name__, test_method) setattr(TestDownload, test_method.__name__, test_method)
del test_method del test_method

16
test/test_execution.py
View File

@ -1,3 +1,8 @@
#!/usr/bin/env python
# coding: utf-8
from __future__ import unicode_literals
import unittest import unittest
import sys import sys
@ -6,21 +11,30 @@ import subprocess
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
try: try:
_DEV_NULL = subprocess.DEVNULL _DEV_NULL = subprocess.DEVNULL
except AttributeError: except AttributeError:
_DEV_NULL = open(os.devnull, 'wb') _DEV_NULL = open(os.devnull, 'wb')
class TestExecution(unittest.TestCase): class TestExecution(unittest.TestCase):
def test_import(self): def test_import(self):
subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir) subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir)
def test_module_exec(self): def test_module_exec(self):
if sys.version_info >= (2,7): # Python 2.6 doesn't support package execution if sys.version_info >= (2, 7): # Python 2.6 doesn't support package execution
subprocess.check_call([sys.executable, '-m', 'youtube_dl', '--version'], cwd=rootDir, stdout=_DEV_NULL) subprocess.check_call([sys.executable, '-m', 'youtube_dl', '--version'], cwd=rootDir, stdout=_DEV_NULL)
def test_main_exec(self): def test_main_exec(self):
subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL) subprocess.check_call([sys.executable, 'youtube_dl/__main__.py', '--version'], cwd=rootDir, stdout=_DEV_NULL)
def test_cmdline_umlauts(self):
p = subprocess.Popen(
[sys.executable, 'youtube_dl/__main__.py', 'ä', '--version'],
cwd=rootDir, stdout=_DEV_NULL, stderr=subprocess.PIPE)
_, stderr = p.communicate()
self.assertFalse(stderr)
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

119
test/test_http.py Normal file
View File

@ -0,0 +1,119 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl import YoutubeDL
from youtube_dl.compat import compat_http_server, compat_urllib_request
import ssl
import threading
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
def log_message(self, format, *args):
pass
def do_GET(self):
if self.path == '/video.html':
self.send_response(200)
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.end_headers()
self.wfile.write(b'<html><video src="/vid.mp4" /></html>')
elif self.path == '/vid.mp4':
self.send_response(200)
self.send_header('Content-Type', 'video/mp4')
self.end_headers()
self.wfile.write(b'\x00\x00\x00\x00\x20\x66\x74[video]')
else:
assert False
class FakeLogger(object):
def debug(self, msg):
pass
def warning(self, msg):
pass
def error(self, msg):
pass
class TestHTTP(unittest.TestCase):
def setUp(self):
certfn = os.path.join(TEST_DIR, 'testcert.pem')
self.httpd = compat_http_server.HTTPServer(
('localhost', 0), HTTPTestRequestHandler)
self.httpd.socket = ssl.wrap_socket(
self.httpd.socket, certfile=certfn, server_side=True)
self.port = self.httpd.socket.getsockname()[1]
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()
def test_nocheckcertificate(self):
if sys.version_info >= (2, 7, 9): # No certificate checking anyways
ydl = YoutubeDL({'logger': FakeLogger()})
self.assertRaises(
Exception,
ydl.extract_info, 'https://localhost:%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['url'], 'https://localhost:%d/vid.mp4' % self.port)
def _build_proxy_handler(name):
class HTTPTestRequestHandler(compat_http_server.BaseHTTPRequestHandler):
proxy_name = name
def log_message(self, format, *args):
pass
def do_GET(self):
self.send_response(200)
self.send_header('Content-Type', 'text/plain; charset=utf-8')
self.end_headers()
self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode('utf-8'))
return HTTPTestRequestHandler
class TestProxy(unittest.TestCase):
def setUp(self):
self.proxy = compat_http_server.HTTPServer(
('localhost', 0), _build_proxy_handler('normal'))
self.port = self.proxy.socket.getsockname()[1]
self.proxy_thread = threading.Thread(target=self.proxy.serve_forever)
self.proxy_thread.daemon = True
self.proxy_thread.start()
self.cn_proxy = compat_http_server.HTTPServer(
('localhost', 0), _build_proxy_handler('cn'))
self.cn_port = self.cn_proxy.socket.getsockname()[1]
self.cn_proxy_thread = threading.Thread(target=self.cn_proxy.serve_forever)
self.cn_proxy_thread.daemon = True
self.cn_proxy_thread.start()
def test_proxy(self):
cn_proxy = 'localhost:{0}'.format(self.cn_port)
ydl = YoutubeDL({
'proxy': 'localhost:{0}'.format(self.port),
'cn_verification_proxy': cn_proxy,
})
url = 'http://foo.com/bar'
response = ydl.urlopen(url).read().decode('utf-8')
self.assertEqual(response, 'normal: {0}'.format(url))
req = compat_urllib_request.Request(url)
req.add_header('Ytdl-request-proxy', cn_proxy)
response = ydl.urlopen(req).read().decode('utf-8')
self.assertEqual(response, 'cn: {0}'.format(url))
if __name__ == '__main__':
unittest.main()

106
test/test_jsinterp.py Normal file
View File

@ -0,0 +1,106 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.jsinterp import JSInterpreter
class TestJSInterpreter(unittest.TestCase):
def test_basic(self):
jsi = JSInterpreter('function x(){;}')
self.assertEqual(jsi.call_function('x'), None)
jsi = JSInterpreter('function x3(){return 42;}')
self.assertEqual(jsi.call_function('x3'), 42)
def test_calc(self):
jsi = JSInterpreter('function x4(a){return 2*a+1;}')
self.assertEqual(jsi.call_function('x4', 3), 7)
def test_empty_return(self):
jsi = JSInterpreter('function f(){return; y()}')
self.assertEqual(jsi.call_function('f'), None)
def test_morespace(self):
jsi = JSInterpreter('function x (a) { return 2 * a + 1 ; }')
self.assertEqual(jsi.call_function('x', 3), 7)
jsi = JSInterpreter('function f () { x = 2 ; return x; }')
self.assertEqual(jsi.call_function('f'), 2)
def test_strange_chars(self):
jsi = JSInterpreter('function $_xY1 ($_axY1) { var $_axY2 = $_axY1 + 1; return $_axY2; }')
self.assertEqual(jsi.call_function('$_xY1', 20), 21)
def test_operators(self):
jsi = JSInterpreter('function f(){return 1 << 5;}')
self.assertEqual(jsi.call_function('f'), 32)
jsi = JSInterpreter('function f(){return 19 & 21;}')
self.assertEqual(jsi.call_function('f'), 17)
jsi = JSInterpreter('function f(){return 11 >> 2;}')
self.assertEqual(jsi.call_function('f'), 2)
def test_array_access(self):
jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
self.assertEqual(jsi.call_function('f'), [5, 2, 7])
def test_parens(self):
jsi = JSInterpreter('function f(){return (1) + (2) * ((( (( (((((3)))))) )) ));}')
self.assertEqual(jsi.call_function('f'), 7)
jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
self.assertEqual(jsi.call_function('f'), 9)
def test_assignments(self):
jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), 31)
jsi = JSInterpreter('function f(){var x = 20; x += 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), 51)
jsi = JSInterpreter('function f(){var x = 20; x -= 30 + 1; return x;}')
self.assertEqual(jsi.call_function('f'), -11)
def test_comments(self):
'Skipping: Not yet fully implemented'
return
jsi = JSInterpreter('''
function x() {
var x = /* 1 + */ 2;
var y = /* 30
* 40 */ 50;
return x + y;
}
''')
self.assertEqual(jsi.call_function('x'), 52)
jsi = JSInterpreter('''
function f() {
var x = "/*";
var y = 1 /* comment */ + 2;
return y;
}
''')
self.assertEqual(jsi.call_function('f'), 3)
def test_precedence(self):
jsi = JSInterpreter('''
function x() {
var a = [10, 20, 30, 40, 50];
var b = 6;
a[0]=a[b%a.length];
return a;
}''')
self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
if __name__ == '__main__':
unittest.main()

26
test/test_netrc.py Normal file
View File

@ -0,0 +1,26 @@
# coding: utf-8
from __future__ import unicode_literals
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor import (
gen_extractors,
)
class TestNetRc(unittest.TestCase):
def test_netrc_present(self):
for ie in gen_extractors():
if not hasattr(ie, '_login'):
continue
self.assertTrue(
hasattr(ie, '_NETRC_MACHINE'),
'Extractor %s supports login, but is missing a _NETRC_MACHINE property' % ie.IE_NAME)
if __name__ == '__main__':
unittest.main()

17
test/test_postprocessors.py Normal file
View File

@ -0,0 +1,17 @@
#!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.postprocessor import MetadataFromTitlePP
class TestMetadataFromTitle(unittest.TestCase):
def test_format_to_regex(self):
pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
self.assertEqual(pp._titleregex, '(?P<title>.+)\ \-\ (?P<artist>.+)')

360
test/test_subtitles.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution # Allow direct execution
import os import os
@ -15,50 +16,58 @@ from youtube_dl.extractor import (
DailymotionIE, DailymotionIE,
TEDIE, TEDIE,
VimeoIE, VimeoIE,
WallaIE,
CeskaTelevizeIE,
LyndaIE,
NPOIE,
ComedyCentralIE,
NRKTVIE,
RaiIE,
VikiIE,
ThePlatformIE,
RTVEALaCartaIE,
FunnyOrDieIE,
) )
class BaseTestSubtitles(unittest.TestCase): class BaseTestSubtitles(unittest.TestCase):
url = None url = None
IE = None IE = None
def setUp(self): def setUp(self):
self.DL = FakeYDL() self.DL = FakeYDL()
self.ie = self.IE(self.DL) self.ie = self.IE()
self.DL.add_info_extractor(self.ie)
def getInfoDict(self): def getInfoDict(self):
info_dict = self.ie.extract(self.url) info_dict = self.DL.extract_info(self.url, download=False)
return info_dict return info_dict
def getSubtitles(self): def getSubtitles(self):
info_dict = self.getInfoDict() info_dict = self.getInfoDict()
return info_dict['subtitles'] subtitles = info_dict['requested_subtitles']
if not subtitles:
return subtitles
for sub_info in subtitles.values():
if sub_info.get('data') is None:
uf = self.DL.urlopen(sub_info['url'])
sub_info['data'] = uf.read().decode('utf-8')
return dict((l, sub_info['data']) for l, sub_info in subtitles.items())
class TestYoutubeSubtitles(BaseTestSubtitles): class TestYoutubeSubtitles(BaseTestSubtitles):
url = 'QRS8MkLhQmM' url = 'QRS8MkLhQmM'
IE = YoutubeIE IE = YoutubeIE
def test_youtube_no_writesubtitles(self):
self.DL.params['writesubtitles'] = False
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_youtube_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
def test_youtube_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
def test_youtube_allsubtitles(self): def test_youtube_allsubtitles(self):
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 13) self.assertEqual(len(subtitles.keys()), 13)
self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260')
self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d')
for lang in ['it', 'fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
def test_youtube_subtitles_sbv_format(self): def test_youtube_subtitles_sbv_format(self):
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
@ -72,12 +81,6 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06') self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06')
def test_youtube_list_subtitles(self):
self.DL.expect_warning(u'Video doesn\'t have automatic captions')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_youtube_automatic_captions(self): def test_youtube_automatic_captions(self):
self.url = '8YoUxe5ncPo' self.url = '8YoUxe5ncPo'
self.DL.params['writeautomaticsub'] = True self.DL.params['writeautomaticsub'] = True
@ -85,138 +88,66 @@ class TestYoutubeSubtitles(BaseTestSubtitles):
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertTrue(subtitles['it'] is not None) self.assertTrue(subtitles['it'] is not None)
def test_youtube_translated_subtitles(self):
# This video has a subtitles track, which can be translated
self.url = 'Ky9eprVWzlI'
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslangs'] = ['it']
subtitles = self.getSubtitles()
self.assertTrue(subtitles['it'] is not None)
def test_youtube_nosubtitles(self): def test_youtube_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles') self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'n5BB19UTcdA' self.url = 'n5BB19UTcdA'
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0) self.assertFalse(subtitles)
def test_youtube_multiple_langs(self):
self.url = 'QRS8MkLhQmM'
self.DL.params['writesubtitles'] = True
langs = ['it', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
class TestDailymotionSubtitles(BaseTestSubtitles): class TestDailymotionSubtitles(BaseTestSubtitles):
url = 'http://www.dailymotion.com/video/xczg00' url = 'http://www.dailymotion.com/video/xczg00'
IE = DailymotionIE IE = DailymotionIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
def test_allsubtitles(self): def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(len(subtitles.keys()), 5) self.assertTrue(len(subtitles.keys()) >= 6)
self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
def test_list_subtitles(self): self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
self.DL.expect_warning(u'Automatic Captions not supported by this server') for lang in ['es', 'fr', 'de']:
self.DL.params['listsubtitles'] = True self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_nosubtitles(self): def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles') self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv' self.url = 'http://www.dailymotion.com/video/x12u166_le-zapping-tele-star-du-08-aout-2013_tv'
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0) self.assertFalse(subtitles)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
class TestTedSubtitles(BaseTestSubtitles): class TestTedSubtitles(BaseTestSubtitles):
url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html' url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html'
IE = TEDIE IE = TEDIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
def test_allsubtitles(self): def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) >= 28) self.assertTrue(len(subtitles.keys()) >= 28)
self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
def test_list_subtitles(self): self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
self.DL.expect_warning(u'Automatic Captions not supported by this server') for lang in ['es', 'fr', 'de']:
self.DL.params['listsubtitles'] = True self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles()
for lang in langs:
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
class TestBlipTVSubtitles(BaseTestSubtitles): class TestBlipTVSubtitles(BaseTestSubtitles):
url = 'http://blip.tv/a/a-6603250' url = 'http://blip.tv/a/a-6603250'
IE = BlipTVIE IE = BlipTVIE
def test_list_subtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_allsubtitles(self): def test_allsubtitles(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
@ -228,55 +159,178 @@ class TestVimeoSubtitles(BaseTestSubtitles):
url = 'http://vimeo.com/76979871' url = 'http://vimeo.com/76979871'
IE = VimeoIE IE = VimeoIE
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
def test_subtitles_lang(self):
self.DL.params['writesubtitles'] = True
self.DL.params['subtitleslangs'] = ['fr']
subtitles = self.getSubtitles()
self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
def test_allsubtitles(self): def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr'])) self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr']))
self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888')
def test_list_subtitles(self): self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8')
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['listsubtitles'] = True
info_dict = self.getInfoDict()
self.assertEqual(info_dict, None)
def test_automatic_captions(self):
self.DL.expect_warning(u'Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_nosubtitles(self): def test_nosubtitles(self):
self.DL.expect_warning(u'video doesn\'t have subtitles') self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://vimeo.com/56015672' self.url = 'http://vimeo.com/56015672'
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
self.assertEqual(len(subtitles), 0) self.assertFalse(subtitles)
def test_multiple_langs(self):
class TestWallaSubtitles(BaseTestSubtitles):
url = 'http://vod.walla.co.il/movie/2705958/the-yes-men'
IE = WallaIE
def test_allsubtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de'] self.DL.params['allsubtitles'] = True
self.DL.params['subtitleslangs'] = langs
subtitles = self.getSubtitles() subtitles = self.getSubtitles()
for lang in langs: self.assertEqual(set(subtitles.keys()), set(['heb']))
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang) self.assertEqual(md5(subtitles['heb']), 'e758c5d7cb982f6bef14f377ec7a3920')
def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertFalse(subtitles)
class TestCeskaTelevizeSubtitles(BaseTestSubtitles):
url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky'
IE = CeskaTelevizeIE
def test_allsubtitles(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['cs']))
self.assertTrue(len(subtitles['cs']) > 20000)
def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
self.url = 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220'
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertFalse(subtitles)
class TestLyndaSubtitles(BaseTestSubtitles):
url = 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html'
IE = LyndaIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '09bbe67222259bed60deaa26997d73a7')
class TestNPOSubtitles(BaseTestSubtitles):
url = 'http://www.npo.nl/nos-journaal/28-08-2014/POW_00722860'
IE = NPOIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['nl']))
self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4')
class TestMTVSubtitles(BaseTestSubtitles):
url = 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother'
IE = ComedyCentralIE
def getInfoDict(self):
return super(TestMTVSubtitles, self).getInfoDict()['entries'][0]
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'b9f6ca22a6acf597ec76f61749765e65')
class TestNRKSubtitles(BaseTestSubtitles):
url = 'http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1'
IE = NRKTVIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['no']))
self.assertEqual(md5(subtitles['no']), '1d221e6458c95c5494dcd38e6a1f129a')
class TestRaiSubtitles(BaseTestSubtitles):
url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html'
IE = RaiIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['it']))
self.assertEqual(md5(subtitles['it']), 'b1d90a98755126b61e667567a1f6680a')
class TestVikiSubtitles(BaseTestSubtitles):
url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
IE = VikiIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '53cb083a5914b2d84ef1ab67b880d18a')
class TestThePlatformSubtitles(BaseTestSubtitles):
# from http://www.3playmedia.com/services-features/tools/integrations/theplatform/
# (see http://theplatform.com/about/partners/type/subtitles-closed-captioning/)
url = 'theplatform:JFUjUE1_ehvq'
IE = ThePlatformIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), '97e7670cbae3c4d26ae8bcc7fdd78d4b')
class TestRtveSubtitles(BaseTestSubtitles):
url = 'http://www.rtve.es/alacarta/videos/los-misterios-de-laura/misterios-laura-capitulo-32-misterio-del-numero-17-2-parte/2428621/'
IE = RTVEALaCartaIE
def test_allsubtitles(self):
print('Skipping, only available from Spain')
return
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['es']))
self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca')
class TestFunnyOrDieSubtitles(BaseTestSubtitles):
url = 'http://www.funnyordie.com/videos/224829ff6d/judd-apatow-will-direct-your-vine'
IE = FunnyOrDieIE
def test_allsubtitles(self):
self.DL.params['writesubtitles'] = True
self.DL.params['allsubtitles'] = True
subtitles = self.getSubtitles()
self.assertEqual(set(subtitles.keys()), set(['en']))
self.assertEqual(md5(subtitles['en']), 'c5593c193eacd353596c11c2d4f9ecc4')
if __name__ == '__main__': if __name__ == '__main__':

9
test/test_swfinterp.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution # Allow direct execution
import os import os
@ -33,11 +34,13 @@ def _make_testfunc(testfile):
def test_func(self): def test_func(self):
as_file = os.path.join(TEST_DIR, testfile) as_file = os.path.join(TEST_DIR, testfile)
swf_file = os.path.join(TEST_DIR, test_id + '.swf') swf_file = os.path.join(TEST_DIR, test_id + '.swf')
if ((not os.path.exists(swf_file)) if ((not os.path.exists(swf_file)) or
or os.path.getmtime(swf_file) < os.path.getmtime(as_file)): os.path.getmtime(swf_file) < os.path.getmtime(as_file)):
# Recompile # Recompile
try: try:
subprocess.check_call(['mxmlc', '-output', swf_file, as_file]) subprocess.check_call([
'mxmlc', '-output', swf_file,
'-static-link-runtime-shared-libraries', as_file])
except OSError as ose: except OSError as ose:
if ose.errno == errno.ENOENT: if ose.errno == errno.ENOENT:
print('mxmlc not found! Skipping test.') print('mxmlc not found! Skipping test.')

36
test/test_unicode_literals.py
View File

@ -1,23 +1,38 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import io # Allow direct execution
import os import os
import re import sys
import unittest import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import io
import re
rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
IGNORED_FILES = [ IGNORED_FILES = [
'setup.py', # http://bugs.python.org/issue13943 'setup.py', # http://bugs.python.org/issue13943
'conf.py',
'buildserver.py',
] ]
IGNORED_DIRS = [
'.git',
'.tox',
]
from test.helper import assertRegexpMatches
class TestUnicodeLiterals(unittest.TestCase): class TestUnicodeLiterals(unittest.TestCase):
def test_all_files(self): def test_all_files(self):
print('Skipping this test (not yet fully implemented)') for dirpath, dirnames, filenames in os.walk(rootDir):
return for ignore_dir in IGNORED_DIRS:
if ignore_dir in dirnames:
for dirpath, _, filenames in os.walk(rootDir): # If we remove the directory from dirnames os.walk won't
# recurse into it
dirnames.remove(ignore_dir)
for basename in filenames: for basename in filenames:
if not basename.endswith('.py'): if not basename.endswith('.py'):
continue continue
@ -30,10 +45,11 @@ class TestUnicodeLiterals(unittest.TestCase):
if "'" not in code and '"' not in code: if "'" not in code and '"' not in code:
continue continue
imps = 'from __future__ import unicode_literals' assertRegexpMatches(
self.assertTrue( self,
imps in code, code,
' %s missing in %s' % (imps, fn)) r'(?:(?:#.*?|\s*)\n)*from __future__ import (?:[a-z_]+,\s*)*unicode_literals',
'unicode_literals import missing in %s' % fn)
m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code) m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code)
if m is not None: if m is not None:

296
test/test_utils.py
View File

@ -16,33 +16,48 @@ import json
import xml.etree.ElementTree import xml.etree.ElementTree
from youtube_dl.utils import ( from youtube_dl.utils import (
age_restricted,
args_to_str,
clean_html,
DateRange, DateRange,
detect_exe_version,
encodeFilename, encodeFilename,
escape_rfc3986,
escape_url,
ExtractorError,
find_xpath_attr, find_xpath_attr,
fix_xml_ampersands, fix_xml_ampersands,
get_meta_content, InAdvancePagedList,
intlist_to_bytes,
is_html,
js_to_json,
limit_length,
OnDemandPagedList,
orderedSet, orderedSet,
PagedList,
parse_duration, parse_duration,
parse_filesize,
parse_iso8601,
read_batch_urls, read_batch_urls,
sanitize_filename, sanitize_filename,
sanitize_path,
sanitize_url_path_consecutive_slashes,
shell_quote, shell_quote,
smuggle_url, smuggle_url,
str_to_int, str_to_int,
strip_jsonp,
struct_unpack, struct_unpack,
timeconvert, timeconvert,
unescapeHTML, unescapeHTML,
unified_strdate, unified_strdate,
unsmuggle_url, unsmuggle_url,
uppercase_escape,
url_basename, url_basename,
urlencode_postdata, urlencode_postdata,
version_tuple,
xpath_with_ns, xpath_with_ns,
parse_iso8601, xpath_text,
strip_jsonp, render_table,
uppercase_escape, match_str,
limit_length,
escape_rfc3986,
escape_url,
) )
@ -71,6 +86,15 @@ class TestUtil(unittest.TestCase):
tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430' tests = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0446\u0430'
self.assertEqual(sanitize_filename(tests), tests) self.assertEqual(sanitize_filename(tests), tests)
self.assertEqual(
sanitize_filename('New World record at 0:12:34'),
'New World record at 0_12_34')
self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf')
self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf')
self.assertEqual(sanitize_filename('.gasdgf'), 'gasdgf')
self.assertEqual(sanitize_filename('.gasdgf', is_id=True), '.gasdgf')
forbidden = '"\0\\/' forbidden = '"\0\\/'
for fc in forbidden: for fc in forbidden:
for fbc in forbidden: for fbc in forbidden:
@ -111,20 +135,76 @@ class TestUtil(unittest.TestCase):
self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw') self.assertEqual(sanitize_filename('_BD_eEpuzXw', is_id=True), '_BD_eEpuzXw')
self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI') self.assertEqual(sanitize_filename('N0Y__7-UOdI', is_id=True), 'N0Y__7-UOdI')
def test_sanitize_path(self):
if sys.platform != 'win32':
return
self.assertEqual(sanitize_path('abc'), 'abc')
self.assertEqual(sanitize_path('abc/def'), 'abc\\def')
self.assertEqual(sanitize_path('abc\\def'), 'abc\\def')
self.assertEqual(sanitize_path('abc|def'), 'abc#def')
self.assertEqual(sanitize_path('<>:"|?*'), '#######')
self.assertEqual(sanitize_path('C:/abc/def'), 'C:\\abc\\def')
self.assertEqual(sanitize_path('C?:/abc/def'), 'C##\\abc\\def')
self.assertEqual(sanitize_path('\\\\?\\UNC\\ComputerName\\abc'), '\\\\?\\UNC\\ComputerName\\abc')
self.assertEqual(sanitize_path('\\\\?\\UNC/ComputerName/abc'), '\\\\?\\UNC\\ComputerName\\abc')
self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
self.assertEqual(sanitize_path('\\\\?\\C:/abc'), '\\\\?\\C:\\abc')
self.assertEqual(sanitize_path('\\\\?\\C:\\ab?c\\de:f'), '\\\\?\\C:\\ab#c\\de#f')
self.assertEqual(sanitize_path('\\\\?\\C:\\abc'), '\\\\?\\C:\\abc')
self.assertEqual(
sanitize_path('youtube/%(uploader)s/%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s'),
'youtube\\%(uploader)s\\%(autonumber)s-%(title)s-%(upload_date)s.%(ext)s')
self.assertEqual(
sanitize_path('youtube/TheWreckingYard ./00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part'),
'youtube\\TheWreckingYard #\\00001-Not bad, Especially for Free! (1987 Yamaha 700)-20141116.mp4.part')
self.assertEqual(sanitize_path('abc/def...'), 'abc\\def..#')
self.assertEqual(sanitize_path('abc.../def'), 'abc..#\\def')
self.assertEqual(sanitize_path('abc.../def...'), 'abc..#\\def..#')
self.assertEqual(sanitize_path('../abc'), '..\\abc')
self.assertEqual(sanitize_path('../../abc'), '..\\..\\abc')
self.assertEqual(sanitize_path('./abc'), 'abc')
self.assertEqual(sanitize_path('./../abc'), '..\\abc')
def test_sanitize_url_path_consecutive_slashes(self):
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname/foo//bar/filename.html'),
'http://hostname/foo/bar/filename.html')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname//foo/bar/filename.html'),
'http://hostname/foo/bar/filename.html')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname//'),
'http://hostname/')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname/foo/bar/filename.html'),
'http://hostname/foo/bar/filename.html')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname/'),
'http://hostname/')
self.assertEqual(
sanitize_url_path_consecutive_slashes('http://hostname/abc//'),
'http://hostname/abc/')
def test_ordered_set(self): def test_ordered_set(self):
self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7]) self.assertEqual(orderedSet([1, 1, 2, 3, 4, 4, 5, 6, 7, 3, 5]), [1, 2, 3, 4, 5, 6, 7])
self.assertEqual(orderedSet([]), []) self.assertEqual(orderedSet([]), [])
self.assertEqual(orderedSet([1]), [1]) self.assertEqual(orderedSet([1]), [1])
#keep the list ordered # keep the list ordered
self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1]) self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1])
def test_unescape_html(self): def test_unescape_html(self):
self.assertEqual(unescapeHTML('%20;'), '%20;') self.assertEqual(unescapeHTML('%20;'), '%20;')
self.assertEqual( self.assertEqual(
unescapeHTML('&eacute;'), 'é') unescapeHTML('&eacute;'), 'é')
def test_daterange(self): def test_daterange(self):
_20century = DateRange("19000101","20000101") _20century = DateRange("19000101", "20000101")
self.assertFalse("17890714" in _20century) self.assertFalse("17890714" in _20century)
_ac = DateRange("00010101") _ac = DateRange("00010101")
self.assertTrue("19690721" in _ac) self.assertTrue("19690721" in _ac)
@ -136,7 +216,15 @@ class TestUtil(unittest.TestCase):
self.assertEqual(unified_strdate('8/7/2009'), '20090708') self.assertEqual(unified_strdate('8/7/2009'), '20090708')
self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214') self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011') self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
self.assertEqual(unified_strdate('1968 12 10'), '19681210')
self.assertEqual(unified_strdate('1968-12-10'), '19681210') self.assertEqual(unified_strdate('1968-12-10'), '19681210')
self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
self.assertEqual(
unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
'20141126')
self.assertEqual(
unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
'20150202')
def test_find_xpath_attr(self): def test_find_xpath_attr(self):
testxml = '''<root> testxml = '''<root>
@ -151,17 +239,6 @@ class TestUtil(unittest.TestCase):
self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1]) self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1])
self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2]) self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2])
def test_meta_parser(self):
testhtml = '''
<head>
<meta name="description" content="foo &amp; bar">
<meta content='Plato' name='author'/>
</head>
'''
get_meta = lambda name: get_meta_content(name, testhtml)
self.assertEqual(get_meta('description'), 'foo & bar')
self.assertEqual(get_meta('author'), 'Plato')
def test_xpath_with_ns(self): def test_xpath_with_ns(self):
testxml = '''<root xmlns:media="http://example.com/"> testxml = '''<root xmlns:media="http://example.com/">
<media:song> <media:song>
@ -175,8 +252,19 @@ class TestUtil(unittest.TestCase):
self.assertEqual(find('media:song/media:author').text, 'The Author') self.assertEqual(find('media:song/media:author').text, 'The Author')
self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3') self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3')
def test_xpath_text(self):
testxml = '''<root>
<div>
<p>Foo</p>
</div>
</root>'''
doc = xml.etree.ElementTree.fromstring(testxml)
self.assertEqual(xpath_text(doc, 'div/p'), 'Foo')
self.assertTrue(xpath_text(doc, 'div/bar') is None)
self.assertRaises(ExtractorError, xpath_text, doc, 'div/bar', fatal=True)
def test_smuggle_url(self): def test_smuggle_url(self):
data = {u"ö": u"ö", u"abc": [3]} data = {"ö": "ö", "abc": [3]}
url = 'https://foo.bar/baz?x=y#a' url = 'https://foo.bar/baz?x=y#a'
smug_url = smuggle_url(url, data) smug_url = smuggle_url(url, data)
unsmug_url, unsmug_data = unsmuggle_url(smug_url) unsmug_url, unsmug_data = unsmuggle_url(smug_url)
@ -207,6 +295,8 @@ class TestUtil(unittest.TestCase):
def test_parse_duration(self): def test_parse_duration(self):
self.assertEqual(parse_duration(None), None) self.assertEqual(parse_duration(None), None)
self.assertEqual(parse_duration(False), None)
self.assertEqual(parse_duration('invalid'), None)
self.assertEqual(parse_duration('1'), 1) self.assertEqual(parse_duration('1'), 1)
self.assertEqual(parse_duration('1337:12'), 80232) self.assertEqual(parse_duration('1337:12'), 80232)
self.assertEqual(parse_duration('9:12:43'), 33163) self.assertEqual(parse_duration('9:12:43'), 33163)
@ -224,6 +314,13 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_duration('0m0s'), 0) self.assertEqual(parse_duration('0m0s'), 0)
self.assertEqual(parse_duration('0s'), 0) self.assertEqual(parse_duration('0s'), 0)
self.assertEqual(parse_duration('01:02:03.05'), 3723.05) self.assertEqual(parse_duration('01:02:03.05'), 3723.05)
self.assertEqual(parse_duration('T30M38S'), 1838)
self.assertEqual(parse_duration('5 s'), 5)
self.assertEqual(parse_duration('3 min'), 180)
self.assertEqual(parse_duration('2.5 hours'), 9000)
self.assertEqual(parse_duration('02:03:04'), 7384)
self.assertEqual(parse_duration('01:02:03:04'), 93784)
self.assertEqual(parse_duration('1 hour 3 minutes'), 3780)
def test_fix_xml_ampersands(self): def test_fix_xml_ampersands(self):
self.assertEqual( self.assertEqual(
@ -246,10 +343,14 @@ class TestUtil(unittest.TestCase):
for i in range(firstid, upto): for i in range(firstid, upto):
yield i yield i
pl = PagedList(get_page, pagesize) pl = OnDemandPagedList(get_page, pagesize)
got = pl.getslice(*sliceargs) got = pl.getslice(*sliceargs)
self.assertEqual(got, expected) self.assertEqual(got, expected)
iapl = InAdvancePagedList(get_page, size // pagesize + 1, pagesize)
got = iapl.getslice(*sliceargs)
self.assertEqual(got, expected)
testPL(5, 2, (), [0, 1, 2, 3, 4]) testPL(5, 2, (), [0, 1, 2, 3, 4])
testPL(5, 2, (1,), [1, 2, 3, 4]) testPL(5, 2, (1,), [1, 2, 3, 4])
testPL(5, 2, (2,), [2, 3, 4]) testPL(5, 2, (2,), [2, 3, 4])
@ -279,12 +380,17 @@ class TestUtil(unittest.TestCase):
self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266) self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266) self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266) self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
def test_strip_jsonp(self): def test_strip_jsonp(self):
stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);') stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
d = json.loads(stripped) d = json.loads(stripped)
self.assertEqual(d, [{"id": "532cb", "x": 3}]) self.assertEqual(d, [{"id": "532cb", "x": 3}])
stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
d = json.loads(stripped)
self.assertEqual(d, {'STATUS': 'OK'})
def test_uppercase_escape(self): def test_uppercase_escape(self):
self.assertEqual(uppercase_escape('aä'), 'aä') self.assertEqual(uppercase_escape('aä'), 'aä')
self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐')
@ -325,5 +431,147 @@ class TestUtil(unittest.TestCase):
) )
self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0') self.assertEqual(escape_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
def test_js_to_json_realworld(self):
inp = '''{
'clip':{'provider':'pseudo'}
}'''
self.assertEqual(js_to_json(inp), '''{
"clip":{"provider":"pseudo"}
}''')
json.loads(js_to_json(inp))
inp = '''{
'playlist':[{'controls':{'all':null}}]
}'''
self.assertEqual(js_to_json(inp), '''{
"playlist":[{"controls":{"all":null}}]
}''')
inp = '"SAND Number: SAND 2013-7800P\\nPresenter: Tom Russo\\nHabanero Software Training - Xyce Software\\nXyce, Sandia\\u0027s"'
json_code = js_to_json(inp)
self.assertEqual(json.loads(json_code), json.loads(inp))
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"})
on = js_to_json('{"abc": true}')
self.assertEqual(json.loads(on), {'abc': True})
# Ignore JavaScript code as well
on = js_to_json('''{
"x": 1,
y: "a",
z: some.code
}''')
d = json.loads(on)
self.assertEqual(d['x'], 1)
self.assertEqual(d['y'], 'a')
def test_clean_html(self):
self.assertEqual(clean_html('a:\nb'), 'a: b')
self.assertEqual(clean_html('a:\n "b"'), 'a: "b"')
def test_intlist_to_bytes(self):
self.assertEqual(
intlist_to_bytes([0, 1, 127, 128, 255]),
b'\x00\x01\x7f\x80\xff')
def test_args_to_str(self):
self.assertEqual(
args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
'foo ba/r -baz \'2 be\' \'\''
)
def test_parse_filesize(self):
self.assertEqual(parse_filesize(None), None)
self.assertEqual(parse_filesize(''), None)
self.assertEqual(parse_filesize('91 B'), 91)
self.assertEqual(parse_filesize('foobar'), None)
self.assertEqual(parse_filesize('2 MiB'), 2097152)
self.assertEqual(parse_filesize('5 GB'), 5000000000)
self.assertEqual(parse_filesize('1.2Tb'), 1200000000000)
self.assertEqual(parse_filesize('1,24 KB'), 1240)
def test_version_tuple(self):
self.assertEqual(version_tuple('1'), (1,))
self.assertEqual(version_tuple('10.23.344'), (10, 23, 344))
self.assertEqual(version_tuple('10.1-6'), (10, 1, 6)) # avconv style
def test_detect_exe_version(self):
self.assertEqual(detect_exe_version('''ffmpeg version 1.2.1
built on May 27 2013 08:37:26 with gcc 4.7 (Debian 4.7.3-4)
configuration: --prefix=/usr --extra-'''), '1.2.1')
self.assertEqual(detect_exe_version('''ffmpeg version N-63176-g1fb4685
built on May 15 2014 22:09:06 with gcc 4.8.2 (GCC)'''), 'N-63176-g1fb4685')
self.assertEqual(detect_exe_version('''X server found. dri2 connection failed!
Trying to open render node...
Success at /dev/dri/renderD128.
ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
def test_age_restricted(self):
self.assertFalse(age_restricted(None, 10)) # unrestricted content
self.assertFalse(age_restricted(1, None)) # unrestricted policy
self.assertFalse(age_restricted(8, 10))
self.assertTrue(age_restricted(18, 14))
self.assertFalse(age_restricted(18, 18))
def test_is_html(self):
self.assertFalse(is_html(b'\x49\x44\x43<html'))
self.assertTrue(is_html(b'<!DOCTYPE foo>\xaaa'))
self.assertTrue(is_html( # UTF-8 with BOM
b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
self.assertTrue(is_html( # UTF-16-LE
b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
))
self.assertTrue(is_html( # UTF-16-BE
b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
))
self.assertTrue(is_html( # UTF-32-BE
b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
self.assertTrue(is_html( # UTF-32-LE
b'\xFF\xFE\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4\x00\x00\x00'))
def test_render_table(self):
self.assertEqual(
render_table(
['a', 'bcd'],
[[123, 4], [9999, 51]]),
'a bcd\n'
'123 4\n'
'9999 51')
def test_match_str(self):
self.assertRaises(ValueError, match_str, 'xy>foobar', {})
self.assertFalse(match_str('xy', {'x': 1200}))
self.assertTrue(match_str('!xy', {'x': 1200}))
self.assertTrue(match_str('x', {'x': 1200}))
self.assertFalse(match_str('!x', {'x': 1200}))
self.assertTrue(match_str('x', {'x': 0}))
self.assertFalse(match_str('x>0', {'x': 0}))
self.assertFalse(match_str('x>0', {}))
self.assertTrue(match_str('x>?0', {}))
self.assertTrue(match_str('x>1K', {'x': 1200}))
self.assertFalse(match_str('x>2K', {'x': 1200}))
self.assertTrue(match_str('x>=1200 & x < 1300', {'x': 1200}))
self.assertFalse(match_str('x>=1100 & x < 1200', {'x': 1200}))
self.assertFalse(match_str('y=a212', {'y': 'foobar42'}))
self.assertTrue(match_str('y=foobar42', {'y': 'foobar42'}))
self.assertFalse(match_str('y!=foobar42', {'y': 'foobar42'}))
self.assertTrue(match_str('y!=foobar2', {'y': 'foobar42'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 90, 'description': 'foo'}))
self.assertTrue(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'description': 'foo'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 60, 'description': 'foo'}))
self.assertFalse(match_str(
'like_count > 100 & dislike_count <? 50 & description',
{'like_count': 190, 'dislike_count': 10}))
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

27
test/test_write_annotations.py
View File

@ -1,5 +1,6 @@
#!/usr/bin/env python #!/usr/bin/env python
# coding: utf-8 # coding: utf-8
from __future__ import unicode_literals
# Allow direct execution # Allow direct execution
import os import os
@ -31,19 +32,18 @@ params = get_params({
}) })
TEST_ID = 'gr51aVj-mLg' TEST_ID = 'gr51aVj-mLg'
ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml' ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml'
EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label'] EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label']
class TestAnnotations(unittest.TestCase): class TestAnnotations(unittest.TestCase):
def setUp(self): def setUp(self):
# Clear old files # Clear old files
self.tearDown() self.tearDown()
def test_info_json(self): def test_info_json(self):
expected = list(EXPECTED_ANNOTATIONS) #Two annotations could have the same text. expected = list(EXPECTED_ANNOTATIONS) # Two annotations could have the same text.
ie = youtube_dl.extractor.YoutubeIE() ie = youtube_dl.extractor.YoutubeIE()
ydl = YoutubeDL(params) ydl = YoutubeDL(params)
ydl.add_info_extractor(ie) ydl.add_info_extractor(ie)
@ -51,7 +51,7 @@ class TestAnnotations(unittest.TestCase):
self.assertTrue(os.path.exists(ANNOTATIONS_FILE)) self.assertTrue(os.path.exists(ANNOTATIONS_FILE))
annoxml = None annoxml = None
with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof: with io.open(ANNOTATIONS_FILE, 'r', encoding='utf-8') as annof:
annoxml = xml.etree.ElementTree.parse(annof) annoxml = xml.etree.ElementTree.parse(annof)
self.assertTrue(annoxml is not None, 'Failed to parse annotations XML') self.assertTrue(annoxml is not None, 'Failed to parse annotations XML')
root = annoxml.getroot() root = annoxml.getroot()
self.assertEqual(root.tag, 'document') self.assertEqual(root.tag, 'document')
@ -59,18 +59,17 @@ class TestAnnotations(unittest.TestCase):
self.assertEqual(annotationsTag.tag, 'annotations') self.assertEqual(annotationsTag.tag, 'annotations')
annotations = annotationsTag.findall('annotation') annotations = annotationsTag.findall('annotation')
#Not all the annotations have TEXT children and the annotations are returned unsorted. # Not all the annotations have TEXT children and the annotations are returned unsorted.
for a in annotations: for a in annotations:
self.assertEqual(a.tag, 'annotation') self.assertEqual(a.tag, 'annotation')
if a.get('type') == 'text': if a.get('type') == 'text':
textTag = a.find('TEXT') textTag = a.find('TEXT')
text = textTag.text text = textTag.text
self.assertTrue(text in expected) #assertIn only added in python 2.7 self.assertTrue(text in expected) # assertIn only added in python 2.7
#remove the first occurance, there could be more than one annotation with the same text # remove the first occurance, there could be more than one annotation with the same text
expected.remove(text) expected.remove(text)
#We should have seen (and removed) all the expected annotation texts. # We should have seen (and removed) all the expected annotation texts.
self.assertEqual(len(expected), 0, 'Not all expected annotations were found.') self.assertEqual(len(expected), 0, 'Not all expected annotations were found.')
def tearDown(self): def tearDown(self):
try_rm(ANNOTATIONS_FILE) try_rm(ANNOTATIONS_FILE)

75
test/test_write_info_json.py
View File

@ -1,75 +0,0 @@
#!/usr/bin/env python
# coding: utf-8
# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from test.helper import get_params
import io
import json
import youtube_dl.YoutubeDL
import youtube_dl.extractor
class YoutubeDL(youtube_dl.YoutubeDL):
def __init__(self, *args, **kwargs):
super(YoutubeDL, self).__init__(*args, **kwargs)
self.to_stderr = self.to_screen
params = get_params({
'writeinfojson': True,
'skip_download': True,
'writedescription': True,
})
TEST_ID = 'BaW_jenozKc'
INFO_JSON_FILE = TEST_ID + '.info.json'
DESCRIPTION_FILE = TEST_ID + '.mp4.description'
EXPECTED_DESCRIPTION = u'''test chars: "'/\ä↭𝕐
test URL: https://github.com/rg3/youtube-dl/issues/1892
This is a test video for youtube-dl.
For more information, contact phihag@phihag.de .'''
class TestInfoJSON(unittest.TestCase):
def setUp(self):
# Clear old files
self.tearDown()
def test_info_json(self):
ie = youtube_dl.extractor.YoutubeIE()
ydl = YoutubeDL(params)
ydl.add_info_extractor(ie)
ydl.download([TEST_ID])
self.assertTrue(os.path.exists(INFO_JSON_FILE))
with io.open(INFO_JSON_FILE, 'r', encoding='utf-8') as jsonf:
jd = json.load(jsonf)
self.assertEqual(jd['upload_date'], u'20121002')
self.assertEqual(jd['description'], EXPECTED_DESCRIPTION)
self.assertEqual(jd['id'], TEST_ID)
self.assertEqual(jd['extractor'], 'youtube')
self.assertEqual(jd['title'], u'''youtube-dl test video "'/\ä↭𝕐''')
self.assertEqual(jd['uploader'], 'Philipp Hagemeister')
self.assertTrue(os.path.exists(DESCRIPTION_FILE))
with io.open(DESCRIPTION_FILE, 'r', encoding='utf-8') as descf:
descr = descf.read()
self.assertEqual(descr, EXPECTED_DESCRIPTION)
def tearDown(self):
if os.path.exists(INFO_JSON_FILE):
os.remove(INFO_JSON_FILE)
if os.path.exists(DESCRIPTION_FILE):
os.remove(DESCRIPTION_FILE)
if __name__ == '__main__':
unittest.main()

46
test/test_youtube_lists.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals
# Allow direct execution # Allow direct execution
import os import os
@ -10,13 +11,8 @@ from test.helper import FakeYDL
from youtube_dl.extractor import ( from youtube_dl.extractor import (
YoutubeUserIE,
YoutubePlaylistIE, YoutubePlaylistIE,
YoutubeIE, YoutubeIE,
YoutubeChannelIE,
YoutubeShowIE,
YoutubeTopListIE,
YoutubeSearchURLIE,
) )
@ -32,7 +28,7 @@ class TestYoutubeLists(unittest.TestCase):
result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re') result = ie.extract('https://www.youtube.com/watch?v=FXxLjLQi3Fg&list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
self.assertEqual(result['_type'], 'url') self.assertEqual(result['_type'], 'url')
self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg') self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg')
def test_youtube_course(self): def test_youtube_course(self):
dl = FakeYDL() dl = FakeYDL()
ie = YoutubePlaylistIE(dl) ie = YoutubePlaylistIE(dl)
@ -43,28 +39,6 @@ class TestYoutubeLists(unittest.TestCase):
self.assertEqual(len(entries), 25) self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0') self.assertEqual(YoutubeIE().extract_id(entries[-1]['url']), 'rYefUsYuEp0')
def test_youtube_channel(self):
dl = FakeYDL()
ie = YoutubeChannelIE(dl)
#test paginated channel
result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')
self.assertTrue(len(result['entries']) > 90)
#test autogenerated channel
result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
self.assertTrue(len(result['entries']) >= 18)
def test_youtube_user(self):
dl = FakeYDL()
ie = YoutubeUserIE(dl)
result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')
self.assertTrue(len(result['entries']) >= 320)
def test_youtube_show(self):
dl = FakeYDL()
ie = YoutubeShowIE(dl)
result = ie.extract('http://www.youtube.com/show/airdisasters')
self.assertTrue(len(result) >= 3)
def test_youtube_mix(self): def test_youtube_mix(self):
dl = FakeYDL() dl = FakeYDL()
ie = YoutubePlaylistIE(dl) ie = YoutubePlaylistIE(dl)
@ -83,21 +57,5 @@ class TestYoutubeLists(unittest.TestCase):
entries = result['entries'] entries = result['entries']
self.assertEqual(len(entries), 100) self.assertEqual(len(entries), 100)
def test_youtube_toplist(self):
dl = FakeYDL()
ie = YoutubeTopListIE(dl)
result = ie.extract('yttoplist:music:Trending')
entries = result['entries']
self.assertTrue(len(entries) >= 5)
def test_youtube_search_url(self):
dl = FakeYDL()
ie = YoutubeSearchURLIE(dl)
result = ie.extract('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video')
entries = result['entries']
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'youtube-dl test video')
self.assertTrue(len(entries) >= 5)
if __name__ == '__main__': if __name__ == '__main__':
unittest.main() unittest.main()

25
test/test_youtube_signature.py
View File

@ -8,13 +8,13 @@ import sys
import unittest import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import io import io
import re import re
import string import string
from test.helper import FakeYDL
from youtube_dl.extractor import YoutubeIE from youtube_dl.extractor import YoutubeIE
from youtube_dl.utils import compat_str, compat_urlretrieve from youtube_dl.compat import compat_str, compat_urlretrieve
_TESTS = [ _TESTS = [
( (
@ -47,18 +47,6 @@ _TESTS = [
'2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA', '2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA',
'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2', 'A52CB8B320D22032ABB3A41D773D2B6342034902.A22E87CDD37DBE75A5E52412DC874AC16A7CFCA2',
), ),
(
'http://s.ytimg.com/yts/swfbin/player-vfl5vIhK2/watch_as3.swf',
'swf',
86,
'O1I3456789abcde0ghijklmnopqrstuvwxyzABCDEFGHfJKLMN2PQRSTUVWXY\\!"#$%&\'()*+,-./:;<=>?'
),
(
'http://s.ytimg.com/yts/swfbin/player-vflmDyk47/watch_as3.swf',
'swf',
'F375F75BF2AFDAAF2666E43868D46816F83F13E81C46.3725A8218E446A0DECD33F79DC282994D6AA92C92C9',
'9C29AA6D499282CD97F33DCED0A644E8128A5273.64C18E31F38361864D86834E6662FAADFA2FB57F'
),
( (
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js', 'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
'js', 'js',
@ -76,6 +64,12 @@ _TESTS = [
'js', 'js',
'4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288', '4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
'82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B' '82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
'js',
'312AA52209E3623129A412D56A40F11CB0AF14AE.3EE09501CB14E3BCDC3B2AE808BF3F1D14E7FBF12',
'112AA5220913623229A412D56A40F11CB0AF14AE.3EE0950FCB14EEBCDC3B2AE808BF331D14E7FBF3',
) )
] ]
@ -100,7 +94,8 @@ def make_tfunc(url, stype, sig_input, expected_sig):
if not os.path.exists(fn): if not os.path.exists(fn):
compat_urlretrieve(url, fn) compat_urlretrieve(url, fn)
ie = YoutubeIE() ydl = FakeYDL()
ie = YoutubeIE(ydl)
if stype == 'js': if stype == 'js':
with io.open(fn, encoding='utf-8') as testf: with io.open(fn, encoding='utf-8') as testf:
jscode = testf.read() jscode = testf.read()

52
test/testcert.pem Normal file
View File

@ -0,0 +1,52 @@
-----BEGIN PRIVATE KEY-----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-----END PRIVATE KEY-----
-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----

7
tox.ini
View File

@ -1,8 +1,11 @@
[tox] [tox]
envlist = py26,py27,py33 envlist = py26,py27,py33,py34
[testenv] [testenv]
deps = deps =
nose nose
coverage coverage
commands = nosetests --verbose {posargs:test} # --with-coverage --cover-package=youtube_dl --cover-html defaultargs = test --exclude test_download.py --exclude test_age_restriction.py
--exclude test_subtitles.py --exclude test_write_annotations.py
--exclude test_youtube_lists.py
commands = nosetests --verbose {posargs:{[testenv]defaultargs}} # --with-coverage --cover-package=youtube_dl --cover-html
# test.test_download:TestDownload.test_NowVideo # test.test_download:TestDownload.test_NowVideo

891
youtube_dl/YoutubeDL.py
View File

File diff suppressed because it is too large Load Diff

334
youtube_dl/__init__.py
View File

@ -1,84 +1,7 @@
#!/usr/bin/env python #!/usr/bin/env python
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
__authors__ = ( from __future__ import unicode_literals
'Ricardo Garcia Gonzalez',
'Danny Colligan',
'Benjamin Johnson',
'Vasyl\' Vavrychuk',
'Witold Baryluk',
'Paweł Paprota',
'Gergely Imreh',
'Rogério Brito',
'Philipp Hagemeister',
'Sören Schulze',
'Kevin Ngo',
'Ori Avtalion',
'shizeeg',
'Filippo Valsorda',
'Christian Albrecht',
'Dave Vasilevsky',
'Jaime Marquínez Ferrándiz',
'Jeff Crouse',
'Osama Khalid',
'Michael Walter',
'M. Yasoob Ullah Khalid',
'Julien Fraichard',
'Johny Mo Swag',
'Axel Noack',
'Albert Kim',
'Pierre Rudloff',
'Huarong Huo',
'Ismael Mejía',
'Steffan \'Ruirize\' James',
'Andras Elso',
'Jelle van der Waa',
'Marcin Cieślak',
'Anton Larionov',
'Takuya Tsuchida',
'Sergey M.',
'Michael Orlitzky',
'Chris Gahan',
'Saimadhav Heblikar',
'Mike Col',
'Oleg Prutz',
'pulpe',
'Andreas Schmitz',
'Michael Kaiser',
'Niklas Laxström',
'David Triendl',
'Anthony Weems',
'David Wagner',
'Juan C. Olivares',
'Mattias Harrysson',
'phaer',
'Sainyam Kapoor',
'Nicolas Évrard',
'Jason Normore',
'Hoje Lee',
'Adam Thalhammer',
'Georg Jähnig',
'Ralf Haring',
'Koki Takahashi',
'Ariset Llerena',
'Adam Malcontenti-Wilson',
'Tobias Bell',
'Naglis Jonaitis',
'Charles Chen',
'Hassaan Ali',
'Dobrosław Żybort',
'David Fabijan',
'Sebastian Haas',
'Alexander Kirk',
'Erik Johnson',
'Keith Beckman',
'Ole Ernst',
'Aaron McDaniel (mcd1992)',
'Magnus Kolstad',
'Hari Padmanaban',
'Carlos Ramos',
'5moufl',
)
__license__ = 'Public Domain' __license__ = 'Public Domain'
@ -86,19 +9,25 @@ import codecs
import io import io
import os import os
import random import random
import shlex
import sys import sys
from .options import ( from .options import (
parseOpts, parseOpts,
) )
from .utils import ( from .compat import (
compat_expanduser,
compat_getpass, compat_getpass,
compat_print, compat_print,
workaround_optparse_bug9161,
)
from .utils import (
DateRange, DateRange,
DEFAULT_OUTTMPL,
decodeOption, decodeOption,
DEFAULT_OUTTMPL,
DownloadError, DownloadError,
match_filter_func,
MaxDownloadsReached, MaxDownloadsReached,
preferredencoding, preferredencoding,
read_batch_urls, read_batch_urls,
@ -111,18 +40,8 @@ from .update import update_self
from .downloader import ( from .downloader import (
FileDownloader, FileDownloader,
) )
from .extractor import gen_extractors from .extractor import gen_extractors, list_extractors
from .YoutubeDL import YoutubeDL from .YoutubeDL import YoutubeDL
from .postprocessor import (
AtomicParsleyPP,
FFmpegAudioFixPP,
FFmpegMetadataPP,
FFmpegVideoConvertor,
FFmpegExtractAudioPP,
FFmpegEmbedSubtitlePP,
XAttrMetadataPP,
ExecAfterDownloadPP,
)
def _real_main(argv=None): def _real_main(argv=None):
@ -131,7 +50,9 @@ def _real_main(argv=None):
# https://github.com/rg3/youtube-dl/issues/820 # https://github.com/rg3/youtube-dl/issues/820
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None) codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
setproctitle(u'youtube-dl') workaround_optparse_bug9161()
setproctitle('youtube-dl')
parser, opts, args = parseOpts(argv) parser, opts, args = parseOpts(argv)
@ -147,10 +68,10 @@ def _real_main(argv=None):
if opts.headers is not None: if opts.headers is not None:
for h in opts.headers: for h in opts.headers:
if h.find(':', 1) < 0: if h.find(':', 1) < 0:
parser.error(u'wrong header formatting, it should be key:value, not "%s"'%h) parser.error('wrong header formatting, it should be key:value, not "%s"' % h)
key, value = h.split(':', 2) key, value = h.split(':', 2)
if opts.verbose: if opts.verbose:
write_string(u'[debug] Adding header from command line option %s:%s\n'%(key, value)) write_string('[debug] Adding header from command line option %s:%s\n' % (key, value))
std_headers[key] = value std_headers[key] = value
# Dump user agent # Dump user agent
@ -168,94 +89,96 @@ def _real_main(argv=None):
batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore') batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore')
batch_urls = read_batch_urls(batchfd) batch_urls = read_batch_urls(batchfd)
if opts.verbose: if opts.verbose:
write_string(u'[debug] Batch file urls: ' + repr(batch_urls) + u'\n') write_string('[debug] Batch file urls: ' + repr(batch_urls) + '\n')
except IOError: except IOError:
sys.exit(u'ERROR: batch file could not be read') sys.exit('ERROR: batch file could not be read')
all_urls = batch_urls + args all_urls = batch_urls + args
all_urls = [url.strip() for url in all_urls] all_urls = [url.strip() for url in all_urls]
_enc = preferredencoding() _enc = preferredencoding()
all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls] all_urls = [url.decode(_enc, 'ignore') if isinstance(url, bytes) else url for url in all_urls]
extractors = gen_extractors()
if opts.list_extractors: if opts.list_extractors:
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()): for ie in list_extractors(opts.age_limit):
compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
matchedUrls = [url for url in all_urls if ie.suitable(url)] matchedUrls = [url for url in all_urls if ie.suitable(url)]
for mu in matchedUrls: for mu in matchedUrls:
compat_print(u' ' + mu) compat_print(' ' + mu)
sys.exit(0) sys.exit(0)
if opts.list_extractor_descriptions: if opts.list_extractor_descriptions:
for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()): for ie in list_extractors(opts.age_limit):
if not ie._WORKING: if not ie._WORKING:
continue continue
desc = getattr(ie, 'IE_DESC', ie.IE_NAME) desc = getattr(ie, 'IE_DESC', ie.IE_NAME)
if desc is False: if desc is False:
continue continue
if hasattr(ie, 'SEARCH_KEY'): if hasattr(ie, 'SEARCH_KEY'):
_SEARCHES = (u'cute kittens', u'slithering pythons', u'falling cat', u'angry poodle', u'purple fish', u'running tortoise', u'sleeping bunny') _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny', 'burping cow')
_COUNTS = (u'', u'5', u'10', u'all') _COUNTS = ('', '5', '10', 'all')
desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES)) desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES))
compat_print(desc) compat_print(desc)
sys.exit(0) sys.exit(0)
# Conflicting, missing and erroneous options # Conflicting, missing and erroneous options
if opts.usenetrc and (opts.username is not None or opts.password is not None): if opts.usenetrc and (opts.username is not None or opts.password is not None):
parser.error(u'using .netrc conflicts with giving username/password') parser.error('using .netrc conflicts with giving username/password')
if opts.password is not None and opts.username is None: if opts.password is not None and opts.username is None:
parser.error(u'account username missing\n') parser.error('account username missing\n')
if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid): if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
parser.error(u'using output template conflicts with using title, video ID or auto number') parser.error('using output template conflicts with using title, video ID or auto number')
if opts.usetitle and opts.useid: if opts.usetitle and opts.useid:
parser.error(u'using title conflicts with using video ID') parser.error('using title conflicts with using video ID')
if opts.username is not None and opts.password is None: if opts.username is not None and opts.password is None:
opts.password = compat_getpass(u'Type account password and press [Return]: ') opts.password = compat_getpass('Type account password and press [Return]: ')
if opts.ratelimit is not None: if opts.ratelimit is not None:
numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) numeric_limit = FileDownloader.parse_bytes(opts.ratelimit)
if numeric_limit is None: if numeric_limit is None:
parser.error(u'invalid rate limit specified') parser.error('invalid rate limit specified')
opts.ratelimit = numeric_limit opts.ratelimit = numeric_limit
if opts.min_filesize is not None: if opts.min_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.min_filesize) numeric_limit = FileDownloader.parse_bytes(opts.min_filesize)
if numeric_limit is None: if numeric_limit is None:
parser.error(u'invalid min_filesize specified') parser.error('invalid min_filesize specified')
opts.min_filesize = numeric_limit opts.min_filesize = numeric_limit
if opts.max_filesize is not None: if opts.max_filesize is not None:
numeric_limit = FileDownloader.parse_bytes(opts.max_filesize) numeric_limit = FileDownloader.parse_bytes(opts.max_filesize)
if numeric_limit is None: if numeric_limit is None:
parser.error(u'invalid max_filesize specified') parser.error('invalid max_filesize specified')
opts.max_filesize = numeric_limit opts.max_filesize = numeric_limit
if opts.retries is not None: if opts.retries is not None:
try: if opts.retries in ('inf', 'infinite'):
opts.retries = int(opts.retries) opts_retries = float('inf')
except (TypeError, ValueError): else:
parser.error(u'invalid retry count specified') try:
opts_retries = int(opts.retries)
except (TypeError, ValueError):
parser.error('invalid retry count specified')
if opts.buffersize is not None: if opts.buffersize is not None:
numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize) numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
if numeric_buffersize is None: if numeric_buffersize is None:
parser.error(u'invalid buffer size specified') parser.error('invalid buffer size specified')
opts.buffersize = numeric_buffersize opts.buffersize = numeric_buffersize
if opts.playliststart <= 0: if opts.playliststart <= 0:
raise ValueError(u'Playlist start must be positive') raise ValueError('Playlist start must be positive')
if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart: if opts.playlistend not in (-1, None) and opts.playlistend < opts.playliststart:
raise ValueError(u'Playlist end must be greater than playlist start') raise ValueError('Playlist end must be greater than playlist start')
if opts.extractaudio: if opts.extractaudio:
if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']: if opts.audioformat not in ['best', 'aac', 'mp3', 'm4a', 'opus', 'vorbis', 'wav']:
parser.error(u'invalid audio format specified') parser.error('invalid audio format specified')
if opts.audioquality: if opts.audioquality:
opts.audioquality = opts.audioquality.strip('k').strip('K') opts.audioquality = opts.audioquality.strip('k').strip('K')
if not opts.audioquality.isdigit(): if not opts.audioquality.isdigit():
parser.error(u'invalid audio quality specified') parser.error('invalid audio quality specified')
if opts.recodevideo is not None: if opts.recodevideo is not None:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']: if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']:
parser.error(u'invalid video recode format specified') parser.error('invalid video recode format specified')
if opts.convertsubtitles is not None:
if opts.convertsubtitles not in ['srt', 'vtt', 'ass']:
parser.error('invalid subtitle format specified')
if opts.date is not None: if opts.date is not None:
date = DateRange.day(opts.date) date = DateRange.day(opts.date)
else: else:
date = DateRange(opts.dateafter, opts.datebefore) date = DateRange(opts.dateafter, opts.datebefore)
if opts.default_search not in ('auto', 'auto_warning', 'error', 'fixup_error', None) and ':' not in opts.default_search:
parser.error(u'--default-search invalid; did you forget a colon (:) at the end?')
# Do not download videos when there are audio-only formats # Do not download videos when there are audio-only formats
if opts.extractaudio and not opts.keepvideo and opts.format is None: if opts.extractaudio and not opts.keepvideo and opts.format is None:
@ -263,28 +186,87 @@ def _real_main(argv=None):
# --all-sub automatically sets --write-sub if --write-auto-sub is not given # --all-sub automatically sets --write-sub if --write-auto-sub is not given
# this was the old behaviour if only --all-sub was given. # this was the old behaviour if only --all-sub was given.
if opts.allsubtitles and (opts.writeautomaticsub == False): if opts.allsubtitles and not opts.writeautomaticsub:
opts.writesubtitles = True opts.writesubtitles = True
if sys.version_info < (3,): if sys.version_info < (3,):
# In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems) # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
if opts.outtmpl is not None: if opts.outtmpl is not None:
opts.outtmpl = opts.outtmpl.decode(preferredencoding()) opts.outtmpl = opts.outtmpl.decode(preferredencoding())
outtmpl =((opts.outtmpl is not None and opts.outtmpl) outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or
or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s') (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or
or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or
or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or
or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s') (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or
or (opts.useid and u'%(id)s.%(ext)s') (opts.useid and '%(id)s.%(ext)s') or
or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or
or DEFAULT_OUTTMPL) DEFAULT_OUTTMPL)
if not os.path.splitext(outtmpl)[1] and opts.extractaudio: if not os.path.splitext(outtmpl)[1] and opts.extractaudio:
parser.error(u'Cannot download a video and extract audio into the same' parser.error('Cannot download a video and extract audio into the same'
u' file! Use "{0}.%(ext)s" instead of "{0}" as the output' ' file! Use "{0}.%(ext)s" instead of "{0}" as the output'
u' template'.format(outtmpl)) ' template'.format(outtmpl))
any_printing = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson any_getting = opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat or opts.getduration or opts.dumpjson or opts.dump_single_json
download_archive_fn = os.path.expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive any_printing = opts.print_json
download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive
# PostProcessors
postprocessors = []
# Add the metadata pp first, the other pps will copy it
if opts.metafromtitle:
postprocessors.append({
'key': 'MetadataFromTitle',
'titleformat': opts.metafromtitle
})
if opts.addmetadata:
postprocessors.append({'key': 'FFmpegMetadata'})
if opts.extractaudio:
postprocessors.append({
'key': 'FFmpegExtractAudio',
'preferredcodec': opts.audioformat,
'preferredquality': opts.audioquality,
'nopostoverwrites': opts.nopostoverwrites,
})
if opts.recodevideo:
postprocessors.append({
'key': 'FFmpegVideoConvertor',
'preferedformat': opts.recodevideo,
})
if opts.convertsubtitles:
postprocessors.append({
'key': 'FFmpegSubtitlesConvertor',
'format': opts.convertsubtitles,
})
if opts.embedsubtitles:
postprocessors.append({
'key': 'FFmpegEmbedSubtitle',
})
if opts.xattrs:
postprocessors.append({'key': 'XAttrMetadata'})
if opts.embedthumbnail:
if not opts.addmetadata:
postprocessors.append({'key': 'FFmpegAudioFix'})
postprocessors.append({'key': 'AtomicParsley'})
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd:
postprocessors.append({
'key': 'ExecAfterDownload',
'verboseOutput': opts.verbose,
'exec_cmd': opts.exec_cmd,
})
if opts.xattr_set_filesize:
try:
import xattr
xattr # Confuse flake8
except ImportError:
parser.error('setting filesize xattr requested but python-xattr is not available')
external_downloader_args = None
if opts.external_downloader_args:
external_downloader_args = shlex.split(opts.external_downloader_args)
match_filter = (
None if opts.match_filter is None
else match_filter_func(opts.match_filter))
ydl_opts = { ydl_opts = {
'usenetrc': opts.usenetrc, 'usenetrc': opts.usenetrc,
@ -292,7 +274,7 @@ def _real_main(argv=None):
'password': opts.password, 'password': opts.password,
'twofactor': opts.twofactor, 'twofactor': opts.twofactor,
'videopassword': opts.videopassword, 'videopassword': opts.videopassword,
'quiet': (opts.quiet or any_printing), 'quiet': (opts.quiet or any_getting or any_printing),
'no_warnings': opts.no_warnings, 'no_warnings': opts.no_warnings,
'forceurl': opts.geturl, 'forceurl': opts.geturl,
'forcetitle': opts.gettitle, 'forcetitle': opts.gettitle,
@ -302,9 +284,10 @@ def _real_main(argv=None):
'forceduration': opts.getduration, 'forceduration': opts.getduration,
'forcefilename': opts.getfilename, 'forcefilename': opts.getfilename,
'forceformat': opts.getformat, 'forceformat': opts.getformat,
'forcejson': opts.dumpjson, 'forcejson': opts.dumpjson or opts.print_json,
'simulate': opts.simulate, 'dump_single_json': opts.dump_single_json,
'skip_download': (opts.skip_download or opts.simulate or any_printing), 'simulate': opts.simulate or any_getting,
'skip_download': opts.skip_download,
'format': opts.format, 'format': opts.format,
'format_limit': opts.format_limit, 'format_limit': opts.format_limit,
'listformats': opts.listformats, 'listformats': opts.listformats,
@ -314,7 +297,7 @@ def _real_main(argv=None):
'ignoreerrors': opts.ignoreerrors, 'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit, 'ratelimit': opts.ratelimit,
'nooverwrites': opts.nooverwrites, 'nooverwrites': opts.nooverwrites,
'retries': opts.retries, 'retries': opts_retries,
'buffersize': opts.buffersize, 'buffersize': opts.buffersize,
'noresizebuffer': opts.noresizebuffer, 'noresizebuffer': opts.noresizebuffer,
'continuedl': opts.continue_dl, 'continuedl': opts.continue_dl,
@ -322,6 +305,7 @@ def _real_main(argv=None):
'progress_with_newline': opts.progress_with_newline, 'progress_with_newline': opts.progress_with_newline,
'playliststart': opts.playliststart, 'playliststart': opts.playliststart,
'playlistend': opts.playlistend, 'playlistend': opts.playlistend,
'playlistreverse': opts.playlist_reverse,
'noplaylist': opts.noplaylist, 'noplaylist': opts.noplaylist,
'logtostderr': opts.outtmpl == '-', 'logtostderr': opts.outtmpl == '-',
'consoletitle': opts.consoletitle, 'consoletitle': opts.consoletitle,
@ -331,6 +315,7 @@ def _real_main(argv=None):
'writeannotations': opts.writeannotations, 'writeannotations': opts.writeannotations,
'writeinfojson': opts.writeinfojson, 'writeinfojson': opts.writeinfojson,
'writethumbnail': opts.writethumbnail, 'writethumbnail': opts.writethumbnail,
'write_all_thumbnails': opts.write_all_thumbnails,
'writesubtitles': opts.writesubtitles, 'writesubtitles': opts.writesubtitles,
'writeautomaticsub': opts.writeautomaticsub, 'writeautomaticsub': opts.writeautomaticsub,
'allsubtitles': opts.allsubtitles, 'allsubtitles': opts.allsubtitles,
@ -368,36 +353,26 @@ def _real_main(argv=None):
'youtube_include_dash_manifest': opts.youtube_include_dash_manifest, 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest,
'encoding': opts.encoding, 'encoding': opts.encoding,
'exec_cmd': opts.exec_cmd, 'exec_cmd': opts.exec_cmd,
'extract_flat': opts.extract_flat,
'merge_output_format': opts.merge_output_format,
'postprocessors': postprocessors,
'fixup': opts.fixup,
'source_address': opts.source_address,
'call_home': opts.call_home,
'sleep_interval': opts.sleep_interval,
'external_downloader': opts.external_downloader,
'list_thumbnails': opts.list_thumbnails,
'playlist_items': opts.playlist_items,
'xattr_set_filesize': opts.xattr_set_filesize,
'match_filter': match_filter,
'no_color': opts.no_color,
'ffmpeg_location': opts.ffmpeg_location,
'hls_prefer_native': opts.hls_prefer_native,
'external_downloader_args': external_downloader_args,
'cn_verification_proxy': opts.cn_verification_proxy,
} }
with YoutubeDL(ydl_opts) as ydl: with YoutubeDL(ydl_opts) as ydl:
ydl.print_debug_header()
ydl.add_default_info_extractors()
# PostProcessors
# Add the metadata pp first, the other pps will copy it
if opts.addmetadata:
ydl.add_post_processor(FFmpegMetadataPP())
if opts.extractaudio:
ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
if opts.recodevideo:
ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
if opts.embedsubtitles:
ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
if opts.xattrs:
ydl.add_post_processor(XAttrMetadataPP())
if opts.embedthumbnail:
if not opts.addmetadata:
ydl.add_post_processor(FFmpegAudioFixPP())
ydl.add_post_processor(AtomicParsleyPP())
# Please keep ExecAfterDownload towards the bottom as it allows the user to modify the final file in any way.
# So if the user is able to remove the file before your postprocessor runs it might cause a few problems.
if opts.exec_cmd:
ydl.add_post_processor(ExecAfterDownloadPP(
verboseOutput=opts.verbose, exec_cmd=opts.exec_cmd))
# Update version # Update version
if opts.update_self: if opts.update_self:
update_self(ydl.to_screen, opts.verbose) update_self(ydl.to_screen, opts.verbose)
@ -408,18 +383,21 @@ def _real_main(argv=None):
# Maybe do nothing # Maybe do nothing
if (len(all_urls) < 1) and (opts.load_info_filename is None): if (len(all_urls) < 1) and (opts.load_info_filename is None):
if not (opts.update_self or opts.rm_cachedir): if opts.update_self or opts.rm_cachedir:
parser.error(u'you must provide at least one URL')
else:
sys.exit() sys.exit()
ydl.warn_if_short_id(sys.argv[1:] if argv is None else argv)
parser.error(
'You must provide at least one URL.\n'
'Type youtube-dl --help to see a list of all options.')
try: try:
if opts.load_info_filename is not None: if opts.load_info_filename is not None:
retcode = ydl.download_with_info_file(opts.load_info_filename) retcode = ydl.download_with_info_file(opts.load_info_filename)
else: else:
retcode = ydl.download(all_urls) retcode = ydl.download(all_urls)
except MaxDownloadsReached: except MaxDownloadsReached:
ydl.to_screen(u'--max-download limit reached, aborting.') ydl.to_screen('--max-download limit reached, aborting.')
retcode = 101 retcode = 101
sys.exit(retcode) sys.exit(retcode)
@ -431,6 +409,8 @@ def main(argv=None):
except DownloadError: except DownloadError:
sys.exit(1) sys.exit(1)
except SameFileError: except SameFileError:
sys.exit(u'ERROR: fixed output name but more than one file to download') sys.exit('ERROR: fixed output name but more than one file to download')
except KeyboardInterrupt: except KeyboardInterrupt:
sys.exit(u'\nERROR: Interrupted by user') sys.exit('\nERROR: Interrupted by user')
__all__ = ['main', 'YoutubeDL', 'gen_extractors', 'list_extractors']

1
youtube_dl/__main__.py
View File

@ -1,4 +1,5 @@
#!/usr/bin/env python #!/usr/bin/env python
from __future__ import unicode_literals
# Execute with # Execute with
# $ python youtube_dl/__main__.py (2.6+) # $ python youtube_dl/__main__.py (2.6+)

143
youtube_dl/aes.py
View File

@ -1,4 +1,4 @@
__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text'] from __future__ import unicode_literals
import base64 import base64
from math import ceil from math import ceil
@ -7,10 +7,11 @@ from .utils import bytes_to_intlist, intlist_to_bytes
BLOCK_SIZE_BYTES = 16 BLOCK_SIZE_BYTES = 16
def aes_ctr_decrypt(data, key, counter): def aes_ctr_decrypt(data, key, counter):
""" """
Decrypt with aes in counter mode Decrypt with aes in counter mode
@param {int[]} data cipher @param {int[]} data cipher
@param {int[]} key 16/24/32-Byte cipher key @param {int[]} key 16/24/32-Byte cipher key
@param {instance} counter Instance whose next_value function (@returns {int[]} 16-Byte block) @param {instance} counter Instance whose next_value function (@returns {int[]} 16-Byte block)
@ -19,23 +20,24 @@ def aes_ctr_decrypt(data, key, counter):
""" """
expanded_key = key_expansion(key) expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES)) block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
decrypted_data=[] decrypted_data = []
for i in range(block_count): for i in range(block_count):
counter_block = counter.next_value() counter_block = counter.next_value()
block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES] block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
block += [0]*(BLOCK_SIZE_BYTES - len(block)) block += [0] * (BLOCK_SIZE_BYTES - len(block))
cipher_counter_block = aes_encrypt(counter_block, expanded_key) cipher_counter_block = aes_encrypt(counter_block, expanded_key)
decrypted_data += xor(block, cipher_counter_block) decrypted_data += xor(block, cipher_counter_block)
decrypted_data = decrypted_data[:len(data)] decrypted_data = decrypted_data[:len(data)]
return decrypted_data return decrypted_data
def aes_cbc_decrypt(data, key, iv): def aes_cbc_decrypt(data, key, iv):
""" """
Decrypt with aes in CBC mode Decrypt with aes in CBC mode
@param {int[]} data cipher @param {int[]} data cipher
@param {int[]} key 16/24/32-Byte cipher key @param {int[]} key 16/24/32-Byte cipher key
@param {int[]} iv 16-Byte IV @param {int[]} iv 16-Byte IV
@ -43,94 +45,98 @@ def aes_cbc_decrypt(data, key, iv):
""" """
expanded_key = key_expansion(key) expanded_key = key_expansion(key)
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES)) block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
decrypted_data=[] decrypted_data = []
previous_cipher_block = iv previous_cipher_block = iv
for i in range(block_count): for i in range(block_count):
block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES] block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
block += [0]*(BLOCK_SIZE_BYTES - len(block)) block += [0] * (BLOCK_SIZE_BYTES - len(block))
decrypted_block = aes_decrypt(block, expanded_key) decrypted_block = aes_decrypt(block, expanded_key)
decrypted_data += xor(decrypted_block, previous_cipher_block) decrypted_data += xor(decrypted_block, previous_cipher_block)
previous_cipher_block = block previous_cipher_block = block
decrypted_data = decrypted_data[:len(data)] decrypted_data = decrypted_data[:len(data)]
return decrypted_data return decrypted_data
def key_expansion(data): def key_expansion(data):
""" """
Generate key schedule Generate key schedule
@param {int[]} data 16/24/32-Byte cipher key @param {int[]} data 16/24/32-Byte cipher key
@returns {int[]} 176/208/240-Byte expanded key @returns {int[]} 176/208/240-Byte expanded key
""" """
data = data[:] # copy data = data[:] # copy
rcon_iteration = 1 rcon_iteration = 1
key_size_bytes = len(data) key_size_bytes = len(data)
expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES
while len(data) < expanded_key_size_bytes: while len(data) < expanded_key_size_bytes:
temp = data[-4:] temp = data[-4:]
temp = key_schedule_core(temp, rcon_iteration) temp = key_schedule_core(temp, rcon_iteration)
rcon_iteration += 1 rcon_iteration += 1
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
for _ in range(3): for _ in range(3):
temp = data[-4:] temp = data[-4:]
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
if key_size_bytes == 32: if key_size_bytes == 32:
temp = data[-4:] temp = data[-4:]
temp = sub_bytes(temp) temp = sub_bytes(temp)
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0): for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0):
temp = data[-4:] temp = data[-4:]
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes]) data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
data = data[:expanded_key_size_bytes] data = data[:expanded_key_size_bytes]
return data return data
def aes_encrypt(data, expanded_key): def aes_encrypt(data, expanded_key):
""" """
Encrypt one block with aes Encrypt one block with aes
@param {int[]} data 16-Byte state @param {int[]} data 16-Byte state
@param {int[]} expanded_key 176/208/240-Byte expanded key @param {int[]} expanded_key 176/208/240-Byte expanded key
@returns {int[]} 16-Byte cipher @returns {int[]} 16-Byte cipher
""" """
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1 rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES]) data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
for i in range(1, rounds+1): for i in range(1, rounds + 1):
data = sub_bytes(data) data = sub_bytes(data)
data = shift_rows(data) data = shift_rows(data)
if i != rounds: if i != rounds:
data = mix_columns(data) data = mix_columns(data)
data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]) data = xor(data, expanded_key[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES])
return data return data
def aes_decrypt(data, expanded_key): def aes_decrypt(data, expanded_key):
""" """
Decrypt one block with aes Decrypt one block with aes
@param {int[]} data 16-Byte cipher @param {int[]} data 16-Byte cipher
@param {int[]} expanded_key 176/208/240-Byte expanded key @param {int[]} expanded_key 176/208/240-Byte expanded key
@returns {int[]} 16-Byte state @returns {int[]} 16-Byte state
""" """
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1 rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
for i in range(rounds, 0, -1): for i in range(rounds, 0, -1):
data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]) data = xor(data, expanded_key[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES])
if i != rounds: if i != rounds:
data = mix_columns_inv(data) data = mix_columns_inv(data)
data = shift_rows_inv(data) data = shift_rows_inv(data)
data = sub_bytes_inv(data) data = sub_bytes_inv(data)
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES]) data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
return data return data
def aes_decrypt_text(data, password, key_size_bytes): def aes_decrypt_text(data, password, key_size_bytes):
""" """
Decrypt text Decrypt text
@ -138,33 +144,34 @@ def aes_decrypt_text(data, password, key_size_bytes):
- The cipher key is retrieved by encrypting the first 16 Byte of 'password' - The cipher key is retrieved by encrypting the first 16 Byte of 'password'
with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's) with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's)
- Mode of operation is 'counter' - Mode of operation is 'counter'
@param {str} data Base64 encoded string @param {str} data Base64 encoded string
@param {str,unicode} password Password (will be encoded with utf-8) @param {str,unicode} password Password (will be encoded with utf-8)
@param {int} key_size_bytes Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit @param {int} key_size_bytes Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit
@returns {str} Decrypted data @returns {str} Decrypted data
""" """
NONCE_LENGTH_BYTES = 8 NONCE_LENGTH_BYTES = 8
data = bytes_to_intlist(base64.b64decode(data)) data = bytes_to_intlist(base64.b64decode(data))
password = bytes_to_intlist(password.encode('utf-8')) password = bytes_to_intlist(password.encode('utf-8'))
key = password[:key_size_bytes] + [0]*(key_size_bytes - len(password)) key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password))
key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES) key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES)
nonce = data[:NONCE_LENGTH_BYTES] nonce = data[:NONCE_LENGTH_BYTES]
cipher = data[NONCE_LENGTH_BYTES:] cipher = data[NONCE_LENGTH_BYTES:]
class Counter: class Counter:
__value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES) __value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
def next_value(self): def next_value(self):
temp = self.__value temp = self.__value
self.__value = inc(self.__value) self.__value = inc(self.__value)
return temp return temp
decrypted_data = aes_ctr_decrypt(cipher, key, Counter()) decrypted_data = aes_ctr_decrypt(cipher, key, Counter())
plaintext = intlist_to_bytes(decrypted_data) plaintext = intlist_to_bytes(decrypted_data)
return plaintext return plaintext
RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36) RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
@ -200,14 +207,14 @@ SBOX_INV = (0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38, 0xbf, 0x40, 0xa3, 0x
0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef, 0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d, 0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef,
0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61, 0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0, 0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61,
0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d) 0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26, 0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d)
MIX_COLUMN_MATRIX = ((0x2,0x3,0x1,0x1), MIX_COLUMN_MATRIX = ((0x2, 0x3, 0x1, 0x1),
(0x1,0x2,0x3,0x1), (0x1, 0x2, 0x3, 0x1),
(0x1,0x1,0x2,0x3), (0x1, 0x1, 0x2, 0x3),
(0x3,0x1,0x1,0x2)) (0x3, 0x1, 0x1, 0x2))
MIX_COLUMN_MATRIX_INV = ((0xE,0xB,0xD,0x9), MIX_COLUMN_MATRIX_INV = ((0xE, 0xB, 0xD, 0x9),
(0x9,0xE,0xB,0xD), (0x9, 0xE, 0xB, 0xD),
(0xD,0x9,0xE,0xB), (0xD, 0x9, 0xE, 0xB),
(0xB,0xD,0x9,0xE)) (0xB, 0xD, 0x9, 0xE))
RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35, RIJNDAEL_EXP_TABLE = (0x01, 0x03, 0x05, 0x0F, 0x11, 0x33, 0x55, 0xFF, 0x1A, 0x2E, 0x72, 0x96, 0xA1, 0xF8, 0x13, 0x35,
0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA, 0x5F, 0xE1, 0x38, 0x48, 0xD8, 0x73, 0x95, 0xA4, 0xF7, 0x02, 0x06, 0x0A, 0x1E, 0x22, 0x66, 0xAA,
0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31, 0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31,
@ -241,30 +248,37 @@ RIJNDAEL_LOG_TABLE = (0x00, 0x00, 0x19, 0x01, 0x32, 0x02, 0x1a, 0xc6, 0x4b, 0xc7
0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5, 0x44, 0x11, 0x92, 0xd9, 0x23, 0x20, 0x2e, 0x89, 0xb4, 0x7c, 0xb8, 0x26, 0x77, 0x99, 0xe3, 0xa5,
0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07) 0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07)
def sub_bytes(data): def sub_bytes(data):
return [SBOX[x] for x in data] return [SBOX[x] for x in data]
def sub_bytes_inv(data): def sub_bytes_inv(data):
return [SBOX_INV[x] for x in data] return [SBOX_INV[x] for x in data]
def rotate(data): def rotate(data):
return data[1:] + [data[0]] return data[1:] + [data[0]]
def key_schedule_core(data, rcon_iteration): def key_schedule_core(data, rcon_iteration):
data = rotate(data) data = rotate(data)
data = sub_bytes(data) data = sub_bytes(data)
data[0] = data[0] ^ RCON[rcon_iteration] data[0] = data[0] ^ RCON[rcon_iteration]
return data return data
def xor(data1, data2): def xor(data1, data2):
return [x^y for x, y in zip(data1, data2)] return [x ^ y for x, y in zip(data1, data2)]
def rijndael_mul(a, b): def rijndael_mul(a, b):
if(a==0 or b==0): if(a == 0 or b == 0):
return 0 return 0
return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF] return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF]
def mix_column(data, matrix): def mix_column(data, matrix):
data_mixed = [] data_mixed = []
for row in range(4): for row in range(4):
@ -275,36 +289,43 @@ def mix_column(data, matrix):
data_mixed.append(mixed) data_mixed.append(mixed)
return data_mixed return data_mixed
def mix_columns(data, matrix=MIX_COLUMN_MATRIX): def mix_columns(data, matrix=MIX_COLUMN_MATRIX):
data_mixed = [] data_mixed = []
for i in range(4): for i in range(4):
column = data[i*4 : (i+1)*4] column = data[i * 4: (i + 1) * 4]
data_mixed += mix_column(column, matrix) data_mixed += mix_column(column, matrix)
return data_mixed return data_mixed
def mix_columns_inv(data): def mix_columns_inv(data):
return mix_columns(data, MIX_COLUMN_MATRIX_INV) return mix_columns(data, MIX_COLUMN_MATRIX_INV)
def shift_rows(data): def shift_rows(data):
data_shifted = [] data_shifted = []
for column in range(4): for column in range(4):
for row in range(4): for row in range(4):
data_shifted.append( data[((column + row) & 0b11) * 4 + row] ) data_shifted.append(data[((column + row) & 0b11) * 4 + row])
return data_shifted return data_shifted
def shift_rows_inv(data): def shift_rows_inv(data):
data_shifted = [] data_shifted = []
for column in range(4): for column in range(4):
for row in range(4): for row in range(4):
data_shifted.append( data[((column - row) & 0b11) * 4 + row] ) data_shifted.append(data[((column - row) & 0b11) * 4 + row])
return data_shifted return data_shifted
def inc(data): def inc(data):
data = data[:] # copy data = data[:] # copy
for i in range(len(data)-1,-1,-1): for i in range(len(data) - 1, -1, -1):
if data[i] == 255: if data[i] == 255:
data[i] = 0 data[i] = 0
else: else:
data[i] = data[i] + 1 data[i] = data[i] + 1
break break
return data return data
__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text']

9
youtube_dl/cache.py
View File

@ -8,9 +8,8 @@ import re
import shutil import shutil
import traceback import traceback
from .utils import ( from .compat import compat_expanduser, compat_getenv
write_json_file, from .utils import write_json_file
)
class Cache(object): class Cache(object):
@ -20,9 +19,9 @@ class Cache(object):
def _get_root_dir(self): def _get_root_dir(self):
res = self._ydl.params.get('cachedir') res = self._ydl.params.get('cachedir')
if res is None: if res is None:
cache_root = os.environ.get('XDG_CACHE_HOME', '~/.cache') cache_root = compat_getenv('XDG_CACHE_HOME', '~/.cache')
res = os.path.join(cache_root, 'youtube-dl') res = os.path.join(cache_root, 'youtube-dl')
return os.path.expanduser(res) return compat_expanduser(res)
def _get_cache_fn(self, section, key, dtype): def _get_cache_fn(self, section, key, dtype):
assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \ assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \

428
youtube_dl/compat.py Normal file
View File

@ -0,0 +1,428 @@
from __future__ import unicode_literals
import collections
import getpass
import optparse
import os
import re
import shutil
import socket
import subprocess
import sys
try:
import urllib.request as compat_urllib_request
except ImportError: # Python 2
import urllib2 as compat_urllib_request
try:
import urllib.error as compat_urllib_error
except ImportError: # Python 2
import urllib2 as compat_urllib_error
try:
import urllib.parse as compat_urllib_parse
except ImportError: # Python 2
import urllib as compat_urllib_parse
try:
from urllib.parse import urlparse as compat_urllib_parse_urlparse
except ImportError: # Python 2
from urlparse import urlparse as compat_urllib_parse_urlparse
try:
import urllib.parse as compat_urlparse
except ImportError: # Python 2
import urlparse as compat_urlparse
try:
import http.cookiejar as compat_cookiejar
except ImportError: # Python 2
import cookielib as compat_cookiejar
try:
import html.entities as compat_html_entities
except ImportError: # Python 2
import htmlentitydefs as compat_html_entities
try:
import html.parser as compat_html_parser
except ImportError: # Python 2
import HTMLParser as compat_html_parser
try:
import http.client as compat_http_client
except ImportError: # Python 2
import httplib as compat_http_client
try:
from urllib.error import HTTPError as compat_HTTPError
except ImportError: # Python 2
from urllib2 import HTTPError as compat_HTTPError
try:
from urllib.request import urlretrieve as compat_urlretrieve
except ImportError: # Python 2
from urllib import urlretrieve as compat_urlretrieve
try:
from subprocess import DEVNULL
compat_subprocess_get_DEVNULL = lambda: DEVNULL
except ImportError:
compat_subprocess_get_DEVNULL = lambda: open(os.path.devnull, 'w')
try:
import http.server as compat_http_server
except ImportError:
import BaseHTTPServer as compat_http_server
try:
from urllib.parse import unquote as compat_urllib_parse_unquote
except ImportError:
def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'):
if string == '':
return string
res = string.split('%')
if len(res) == 1:
return string
if encoding is None:
encoding = 'utf-8'
if errors is None:
errors = 'replace'
# pct_sequence: contiguous sequence of percent-encoded bytes, decoded
pct_sequence = b''
string = res[0]
for item in res[1:]:
try:
if not item:
raise ValueError
pct_sequence += item[:2].decode('hex')
rest = item[2:]
if not rest:
# This segment was just a single percent-encoded character.
# May be part of a sequence of code units, so delay decoding.
# (Stored in pct_sequence).
continue
except ValueError:
rest = '%' + item
# Encountered non-percent-encoded characters. Flush the current
# pct_sequence.
string += pct_sequence.decode(encoding, errors) + rest
pct_sequence = b''
if pct_sequence:
# Flush the final pct_sequence
string += pct_sequence.decode(encoding, errors)
return string
try:
compat_str = unicode # Python 2
except NameError:
compat_str = str
try:
compat_basestring = basestring # Python 2
except NameError:
compat_basestring = str
try:
compat_chr = unichr # Python 2
except NameError:
compat_chr = chr
try:
from xml.etree.ElementTree import ParseError as compat_xml_parse_error
except ImportError: # Python 2.6
from xml.parsers.expat import ExpatError as compat_xml_parse_error
try:
from urllib.parse import parse_qs as compat_parse_qs
except ImportError: # Python 2
# HACK: The following is the correct parse_qs implementation from cpython 3's stdlib.
# Python 2's version is apparently totally broken
def _parse_qsl(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
qs, _coerce_result = qs, compat_str
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs:
if not name_value and not strict_parsing:
continue
nv = name_value.split('=', 1)
if len(nv) != 2:
if strict_parsing:
raise ValueError("bad query field: %r" % (name_value,))
# Handle case of a control-name with no equal sign
if keep_blank_values:
nv.append('')
else:
continue
if len(nv[1]) or keep_blank_values:
name = nv[0].replace('+', ' ')
name = compat_urllib_parse_unquote(
name, encoding=encoding, errors=errors)
name = _coerce_result(name)
value = nv[1].replace('+', ' ')
value = compat_urllib_parse_unquote(
value, encoding=encoding, errors=errors)
value = _coerce_result(value)
r.append((name, value))
return r
def compat_parse_qs(qs, keep_blank_values=False, strict_parsing=False,
encoding='utf-8', errors='replace'):
parsed_result = {}
pairs = _parse_qsl(qs, keep_blank_values, strict_parsing,
encoding=encoding, errors=errors)
for name, value in pairs:
if name in parsed_result:
parsed_result[name].append(value)
else:
parsed_result[name] = [value]
return parsed_result
try:
from shlex import quote as shlex_quote
except ImportError: # Python < 3.3
def shlex_quote(s):
if re.match(r'^[-_\w./]+$', s):
return s
else:
return "'" + s.replace("'", "'\"'\"'") + "'"
def compat_ord(c):
if type(c) is int:
return c
else:
return ord(c)
if sys.version_info >= (3, 0):
compat_getenv = os.getenv
compat_expanduser = os.path.expanduser
else:
# Environment variables should be decoded with filesystem encoding.
# Otherwise it will fail if any non-ASCII characters present (see #3854 #3217 #2918)
def compat_getenv(key, default=None):
from .utils import get_filesystem_encoding
env = os.getenv(key, default)
if env:
env = env.decode(get_filesystem_encoding())
return env
# HACK: The default implementations of os.path.expanduser from cpython do not decode
# environment variables with filesystem encoding. We will work around this by
# providing adjusted implementations.
# The following are os.path.expanduser implementations from cpython 2.7.8 stdlib
# for different platforms with correct environment variables decoding.
if os.name == 'posix':
def compat_expanduser(path):
"""Expand ~ and ~user constructions. If user or $HOME is unknown,
do nothing."""
if not path.startswith('~'):
return path
i = path.find('/', 1)
if i < 0:
i = len(path)
if i == 1:
if 'HOME' not in os.environ:
import pwd
userhome = pwd.getpwuid(os.getuid()).pw_dir
else:
userhome = compat_getenv('HOME')
else:
import pwd
try:
pwent = pwd.getpwnam(path[1:i])
except KeyError:
return path
userhome = pwent.pw_dir
userhome = userhome.rstrip('/')
return (userhome + path[i:]) or '/'
elif os.name == 'nt' or os.name == 'ce':
def compat_expanduser(path):
"""Expand ~ and ~user constructs.
If user or $HOME is unknown, do nothing."""
if path[:1] != '~':
return path
i, n = 1, len(path)
while i < n and path[i] not in '/\\':
i = i + 1
if 'HOME' in os.environ:
userhome = compat_getenv('HOME')
elif 'USERPROFILE' in os.environ:
userhome = compat_getenv('USERPROFILE')
elif 'HOMEPATH' not in os.environ:
return path
else:
try:
drive = compat_getenv('HOMEDRIVE')
except KeyError:
drive = ''
userhome = os.path.join(drive, compat_getenv('HOMEPATH'))
if i != 1: # ~user
userhome = os.path.join(os.path.dirname(userhome), path[1:i])
return userhome + path[i:]
else:
compat_expanduser = os.path.expanduser
if sys.version_info < (3, 0):
def compat_print(s):
from .utils import preferredencoding
print(s.encode(preferredencoding(), 'xmlcharrefreplace'))
else:
def compat_print(s):
assert isinstance(s, compat_str)
print(s)
try:
subprocess_check_output = subprocess.check_output
except AttributeError:
def subprocess_check_output(*args, **kwargs):
assert 'input' not in kwargs
p = subprocess.Popen(*args, stdout=subprocess.PIPE, **kwargs)
output, _ = p.communicate()
ret = p.poll()
if ret:
raise subprocess.CalledProcessError(ret, p.args, output=output)
return output
if sys.version_info < (3, 0) and sys.platform == 'win32':
def compat_getpass(prompt, *args, **kwargs):
if isinstance(prompt, compat_str):
from .utils import preferredencoding
prompt = prompt.encode(preferredencoding())
return getpass.getpass(prompt, *args, **kwargs)
else:
compat_getpass = getpass.getpass
# Old 2.6 and 2.7 releases require kwargs to be bytes
try:
def _testfunc(x):
pass
_testfunc(**{'x': 0})
except TypeError:
def compat_kwargs(kwargs):
return dict((bytes(k), v) for k, v in kwargs.items())
else:
compat_kwargs = lambda kwargs: kwargs
if sys.version_info < (2, 7):
def compat_socket_create_connection(address, timeout, source_address=None):
host, port = address
err = None
for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
af, socktype, proto, canonname, sa = res
sock = None
try:
sock = socket.socket(af, socktype, proto)
sock.settimeout(timeout)
if source_address:
sock.bind(source_address)
sock.connect(sa)
return sock
except socket.error as _:
err = _
if sock is not None:
sock.close()
if err is not None:
raise err
else:
raise socket.error("getaddrinfo returns an empty list")
else:
compat_socket_create_connection = socket.create_connection
# Fix https://github.com/rg3/youtube-dl/issues/4223
# See http://bugs.python.org/issue9161 for what is broken
def workaround_optparse_bug9161():
op = optparse.OptionParser()
og = optparse.OptionGroup(op, 'foo')
try:
og.add_option('-t')
except TypeError:
real_add_option = optparse.OptionGroup.add_option
def _compat_add_option(self, *args, **kwargs):
enc = lambda v: (
v.encode('ascii', 'replace') if isinstance(v, compat_str)
else v)
bargs = [enc(a) for a in args]
bkwargs = dict(
(k, enc(v)) for k, v in kwargs.items())
return real_add_option(self, *bargs, **bkwargs)
optparse.OptionGroup.add_option = _compat_add_option
if hasattr(shutil, 'get_terminal_size'): # Python >= 3.3
compat_get_terminal_size = shutil.get_terminal_size
else:
_terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines'])
def compat_get_terminal_size():
columns = compat_getenv('COLUMNS', None)
if columns:
columns = int(columns)
else:
columns = None
lines = compat_getenv('LINES', None)
if lines:
lines = int(lines)
else:
lines = None
try:
sp = subprocess.Popen(
['stty', 'size'],
stdout=subprocess.PIPE, stderr=subprocess.PIPE)
out, err = sp.communicate()
lines, columns = map(int, out.split())
except:
pass
return _terminal_size(columns, lines)
__all__ = [
'compat_HTTPError',
'compat_basestring',
'compat_chr',
'compat_cookiejar',
'compat_expanduser',
'compat_get_terminal_size',
'compat_getenv',
'compat_getpass',
'compat_html_entities',
'compat_html_parser',
'compat_http_client',
'compat_http_server',
'compat_kwargs',
'compat_ord',
'compat_parse_qs',
'compat_print',
'compat_socket_create_connection',
'compat_str',
'compat_subprocess_get_DEVNULL',
'compat_urllib_error',
'compat_urllib_parse',
'compat_urllib_parse_unquote',
'compat_urllib_parse_urlparse',
'compat_urllib_request',
'compat_urlparse',
'compat_urlretrieve',
'compat_xml_parse_error',
'shlex_quote',
'subprocess_check_output',
'workaround_optparse_bug9161',
]

47
youtube_dl/downloader/__init__.py
View File

@ -1,29 +1,46 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import FileDownloader from .common import FileDownloader
from .external import get_external_downloader
from .f4m import F4mFD
from .hls import HlsFD from .hls import HlsFD
from .hls import NativeHlsFD
from .http import HttpFD from .http import HttpFD
from .mplayer import MplayerFD from .mplayer import MplayerFD
from .rtmp import RtmpFD from .rtmp import RtmpFD
from .f4m import F4mFD
from ..utils import ( from ..utils import (
determine_ext, determine_protocol,
) )
PROTOCOL_MAP = {
'rtmp': RtmpFD,
'm3u8_native': NativeHlsFD,
'm3u8': HlsFD,
'mms': MplayerFD,
'rtsp': MplayerFD,
'f4m': F4mFD,
}
def get_suitable_downloader(info_dict):
def get_suitable_downloader(info_dict, params={}):
"""Get the downloader class that can handle the info dict.""" """Get the downloader class that can handle the info dict."""
url = info_dict['url'] protocol = determine_protocol(info_dict)
protocol = info_dict.get('protocol') info_dict['protocol'] = protocol
if url.startswith('rtmp'): external_downloader = params.get('external_downloader')
return RtmpFD if external_downloader is not None:
if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'): ed = get_external_downloader(external_downloader)
return HlsFD if ed.supports(info_dict):
if url.startswith('mms') or url.startswith('rtsp'): return ed
return MplayerFD
if determine_ext(url) == 'f4m': if protocol == 'm3u8' and params.get('hls_prefer_native'):
return F4mFD return NativeHlsFD
else:
return HttpFD return PROTOCOL_MAP.get(protocol, HttpFD)
__all__ = [
'get_suitable_downloader',
'FileDownloader',
]

230
youtube_dl/downloader/common.py
View File

@ -1,10 +1,12 @@
from __future__ import division, unicode_literals
import os import os
import re import re
import sys import sys
import time import time
from ..compat import compat_str
from ..utils import ( from ..utils import (
compat_str,
encodeFilename, encodeFilename,
format_bytes, format_bytes,
timeconvert, timeconvert,
@ -23,25 +25,30 @@ class FileDownloader(object):
Available options: Available options:
verbose: Print additional info to stdout. verbose: Print additional info to stdout.
quiet: Do not print messages to stdout. quiet: Do not print messages to stdout.
ratelimit: Download speed limit, in bytes/sec. ratelimit: Download speed limit, in bytes/sec.
retries: Number of times to retry for HTTP error 5xx retries: Number of times to retry for HTTP error 5xx
buffersize: Size of download buffer in bytes. buffersize: Size of download buffer in bytes.
noresizebuffer: Do not automatically resize the download buffer. noresizebuffer: Do not automatically resize the download buffer.
continuedl: Try to continue downloads if possible. continuedl: Try to continue downloads if possible.
noprogress: Do not print the progress bar. noprogress: Do not print the progress bar.
logtostderr: Log messages to stderr instead of stdout. logtostderr: Log messages to stderr instead of stdout.
consoletitle: Display progress in console window's titlebar. consoletitle: Display progress in console window's titlebar.
nopart: Do not use temporary .part files. nopart: Do not use temporary .part files.
updatetime: Use the Last-modified header to set output file timestamps. updatetime: Use the Last-modified header to set output file timestamps.
test: Download only first bytes to test the downloader. test: Download only first bytes to test the downloader.
min_filesize: Skip files smaller than this size min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size max_filesize: Skip files larger than this size
xattr_set_filesize: Set ytdl.filesize user xattribute with expected size.
(experimenatal)
external_downloader_args: A list of additional command-line arguments for the
external downloader.
Subclasses of this one must re-define the real_download method. Subclasses of this one must re-define the real_download method.
""" """
_TEST_FILE_SIZE = 10241
params = None params = None
def __init__(self, ydl, params): def __init__(self, ydl, params):
@ -49,6 +56,7 @@ class FileDownloader(object):
self.ydl = ydl self.ydl = ydl
self._progress_hooks = [] self._progress_hooks = []
self.params = params self.params = params
self.add_progress_hook(self.report_progress)
@staticmethod @staticmethod
def format_seconds(seconds): def format_seconds(seconds):
@ -77,8 +85,10 @@ class FileDownloader(object):
def calc_eta(start, now, total, current): def calc_eta(start, now, total, current):
if total is None: if total is None:
return None return None
if now is None:
now = time.time()
dif = now - start dif = now - start
if current == 0 or dif < 0.001: # One millisecond if current == 0 or dif < 0.001: # One millisecond
return None return None
rate = float(current) / dif rate = float(current) / dif
return int((float(total) - float(current)) / rate) return int((float(total) - float(current)) / rate)
@ -92,7 +102,7 @@ class FileDownloader(object):
@staticmethod @staticmethod
def calc_speed(start, now, bytes): def calc_speed(start, now, bytes):
dif = now - start dif = now - start
if bytes == 0 or dif < 0.001: # One millisecond if bytes == 0 or dif < 0.001: # One millisecond
return None return None
return float(bytes) / dif return float(bytes) / dif
@ -105,7 +115,7 @@ class FileDownloader(object):
@staticmethod @staticmethod
def best_block_size(elapsed_time, bytes): def best_block_size(elapsed_time, bytes):
new_min = max(bytes / 2.0, 1.0) new_min = max(bytes / 2.0, 1.0)
new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB new_max = min(max(bytes * 2.0, 1.0), 4194304) # Do not surpass 4 MB
if elapsed_time < 0.001: if elapsed_time < 0.001:
return int(new_max) return int(new_max)
rate = bytes / elapsed_time rate = bytes / elapsed_time
@ -143,29 +153,30 @@ class FileDownloader(object):
def report_error(self, *args, **kargs): def report_error(self, *args, **kargs):
self.ydl.report_error(*args, **kargs) self.ydl.report_error(*args, **kargs)
def slow_down(self, start_time, byte_counter): def slow_down(self, start_time, now, byte_counter):
"""Sleep if the download speed is over the rate limit.""" """Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit', None) rate_limit = self.params.get('ratelimit', None)
if rate_limit is None or byte_counter == 0: if rate_limit is None or byte_counter == 0:
return return
now = time.time() if now is None:
now = time.time()
elapsed = now - start_time elapsed = now - start_time
if elapsed <= 0.0: if elapsed <= 0.0:
return return
speed = float(byte_counter) / elapsed speed = float(byte_counter) / elapsed
if speed > rate_limit: if speed > rate_limit:
time.sleep((byte_counter - rate_limit * (now - start_time)) / rate_limit) time.sleep(max((byte_counter // rate_limit) - elapsed, 0))
def temp_name(self, filename): def temp_name(self, filename):
"""Returns a temporary filename for the given filename.""" """Returns a temporary filename for the given filename."""
if self.params.get('nopart', False) or filename == u'-' or \ if self.params.get('nopart', False) or filename == '-' or \
(os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))): (os.path.exists(encodeFilename(filename)) and not os.path.isfile(encodeFilename(filename))):
return filename return filename
return filename + u'.part' return filename + '.part'
def undo_temp_name(self, filename): def undo_temp_name(self, filename):
if filename.endswith(u'.part'): if filename.endswith('.part'):
return filename[:-len(u'.part')] return filename[:-len('.part')]
return filename return filename
def try_rename(self, old_filename, new_filename): def try_rename(self, old_filename, new_filename):
@ -174,7 +185,7 @@ class FileDownloader(object):
return return
os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
except (IOError, OSError) as err: except (IOError, OSError) as err:
self.report_error(u'unable to rename file: %s' % compat_str(err)) self.report_error('unable to rename file: %s' % compat_str(err))
def try_utime(self, filename, last_modified_hdr): def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file.""" """Try to set the last-modified time of the given file."""
@ -199,10 +210,10 @@ class FileDownloader(object):
def report_destination(self, filename): def report_destination(self, filename):
"""Report destination filename.""" """Report destination filename."""
self.to_screen(u'[download] Destination: ' + filename) self.to_screen('[download] Destination: ' + filename)
def _report_progress_status(self, msg, is_last_line=False): def _report_progress_status(self, msg, is_last_line=False):
fullmsg = u'[download] ' + msg fullmsg = '[download] ' + msg
if self.params.get('progress_with_newline', False): if self.params.get('progress_with_newline', False):
self.to_screen(fullmsg) self.to_screen(fullmsg)
else: else:
@ -210,76 +221,110 @@ class FileDownloader(object):
prev_len = getattr(self, '_report_progress_prev_line_length', prev_len = getattr(self, '_report_progress_prev_line_length',
0) 0)
if prev_len > len(fullmsg): if prev_len > len(fullmsg):
fullmsg += u' ' * (prev_len - len(fullmsg)) fullmsg += ' ' * (prev_len - len(fullmsg))
self._report_progress_prev_line_length = len(fullmsg) self._report_progress_prev_line_length = len(fullmsg)
clear_line = u'\r' clear_line = '\r'
else: else:
clear_line = (u'\r\x1b[K' if sys.stderr.isatty() else u'\r') clear_line = ('\r\x1b[K' if sys.stderr.isatty() else '\r')
self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line) self.to_screen(clear_line + fullmsg, skip_eol=not is_last_line)
self.to_console_title(u'youtube-dl ' + msg) self.to_console_title('youtube-dl ' + msg)
def report_progress(self, percent, data_len_str, speed, eta): def report_progress(self, s):
"""Report download progress.""" if s['status'] == 'finished':
if self.params.get('noprogress', False): if self.params.get('noprogress', False):
self.to_screen('[download] Download completed')
else:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
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'
self._report_progress_status(
msg_template % s, is_last_line=True)
if self.params.get('noprogress'):
return return
if eta is not None:
eta_str = self.format_eta(eta)
else:
eta_str = 'Unknown ETA'
if percent is not None:
percent_str = self.format_percent(percent)
else:
percent_str = 'Unknown %'
speed_str = self.format_speed(speed)
msg = (u'%s of %s at %s ETA %s' % if s['status'] != 'downloading':
(percent_str, data_len_str, speed_str, eta_str))
self._report_progress_status(msg)
def report_progress_live_stream(self, downloaded_data_len, speed, elapsed):
if self.params.get('noprogress', False):
return return
downloaded_str = format_bytes(downloaded_data_len)
speed_str = self.format_speed(speed)
elapsed_str = FileDownloader.format_seconds(elapsed)
msg = u'%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str)
self._report_progress_status(msg)
def report_finish(self, data_len_str, tot_time): if s.get('eta') is not None:
"""Report download finished.""" s['_eta_str'] = self.format_eta(s['eta'])
if self.params.get('noprogress', False):
self.to_screen(u'[download] Download completed')
else: else:
self._report_progress_status( s['_eta_str'] = 'Unknown ETA'
(u'100%% of %s in %s' %
(data_len_str, self.format_seconds(tot_time))), if s.get('total_bytes') and s.get('downloaded_bytes') is not None:
is_last_line=True) s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes'])
elif s.get('total_bytes_estimate') and s.get('downloaded_bytes') is not None:
s['_percent_str'] = self.format_percent(100 * s['downloaded_bytes'] / s['total_bytes_estimate'])
else:
if s.get('downloaded_bytes') == 0:
s['_percent_str'] = self.format_percent(0)
else:
s['_percent_str'] = 'Unknown %'
if s.get('speed') is not None:
s['_speed_str'] = self.format_speed(s['speed'])
else:
s['_speed_str'] = 'Unknown speed'
if s.get('total_bytes') is not None:
s['_total_bytes_str'] = format_bytes(s['total_bytes'])
msg_template = '%(_percent_str)s of %(_total_bytes_str)s at %(_speed_str)s ETA %(_eta_str)s'
elif s.get('total_bytes_estimate') is not None:
s['_total_bytes_estimate_str'] = format_bytes(s['total_bytes_estimate'])
msg_template = '%(_percent_str)s of ~%(_total_bytes_estimate_str)s at %(_speed_str)s ETA %(_eta_str)s'
else:
if s.get('downloaded_bytes') is not None:
s['_downloaded_bytes_str'] = format_bytes(s['downloaded_bytes'])
if s.get('elapsed'):
s['_elapsed_str'] = self.format_seconds(s['elapsed'])
msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s (%(_elapsed_str)s)'
else:
msg_template = '%(_downloaded_bytes_str)s at %(_speed_str)s'
else:
msg_template = '%(_percent_str)s % at %(_speed_str)s ETA %(_eta_str)s'
self._report_progress_status(msg_template % s)
def report_resuming_byte(self, resume_len): def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte.""" """Report attempt to resume at given byte."""
self.to_screen(u'[download] Resuming download at byte %s' % resume_len) self.to_screen('[download] Resuming download at byte %s' % resume_len)
def report_retry(self, count, retries): def report_retry(self, count, retries):
"""Report retry in case of HTTP error 5xx""" """Report retry in case of HTTP error 5xx"""
self.to_screen(u'[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries)) self.to_screen('[download] Got server HTTP error. Retrying (attempt %d of %d)...' % (count, retries))
def report_file_already_downloaded(self, file_name): def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded.""" """Report file has already been fully downloaded."""
try: try:
self.to_screen(u'[download] %s has already been downloaded' % file_name) self.to_screen('[download] %s has already been downloaded' % file_name)
except UnicodeEncodeError: except UnicodeEncodeError:
self.to_screen(u'[download] The file has already been downloaded') self.to_screen('[download] The file has already been downloaded')
def report_unable_to_resume(self): def report_unable_to_resume(self):
"""Report it was impossible to resume download.""" """Report it was impossible to resume download."""
self.to_screen(u'[download] Unable to resume') self.to_screen('[download] Unable to resume')
def download(self, filename, info_dict): def download(self, filename, info_dict):
"""Download to a filename using the info from info_dict """Download to a filename using the info from info_dict
Return True on success and False otherwise Return True on success and False otherwise
""" """
nooverwrites_and_exists = (
self.params.get('nooverwrites', False) and
os.path.exists(encodeFilename(filename))
)
continuedl_and_exists = (
self.params.get('continuedl', False) and
os.path.isfile(encodeFilename(filename)) and
not self.params.get('nopart', False)
)
# Check file already present # Check file already present
if self.params.get('continuedl', False) and os.path.isfile(encodeFilename(filename)) and not self.params.get('nopart', False): if filename != '-' and nooverwrites_and_exists or continuedl_and_exists:
self.report_file_already_downloaded(filename) self.report_file_already_downloaded(filename)
self._hook_progress({ self._hook_progress({
'filename': filename, 'filename': filename,
@ -288,30 +333,43 @@ class FileDownloader(object):
}) })
return True return True
sleep_interval = self.params.get('sleep_interval')
if sleep_interval:
self.to_screen('[download] Sleeping %s seconds...' % sleep_interval)
time.sleep(sleep_interval)
return self.real_download(filename, info_dict) return self.real_download(filename, info_dict)
def real_download(self, filename, info_dict): def real_download(self, filename, info_dict):
"""Real download process. Redefine in subclasses.""" """Real download process. Redefine in subclasses."""
raise NotImplementedError(u'This method must be implemented by subclasses') raise NotImplementedError('This method must be implemented by subclasses')
def _hook_progress(self, status): def _hook_progress(self, status):
for ph in self._progress_hooks: for ph in self._progress_hooks:
ph(status) ph(status)
def add_progress_hook(self, ph): def add_progress_hook(self, ph):
""" ph gets called on download progress, with a dictionary with the entries # See YoutubeDl.py (search for progress_hooks) for a description of
* filename: The final filename # this interface
* status: One of "downloading" and "finished"
It can also have some of the following entries:
* downloaded_bytes: Bytes on disks
* total_bytes: Total bytes, None if unknown
* tmpfilename: The filename we're currently writing to
* eta: The estimated time in seconds, None if unknown
* speed: The download speed in bytes/second, None if unknown
Hooks are guaranteed to be called at least once (with status "finished")
if the download is successful.
"""
self._progress_hooks.append(ph) self._progress_hooks.append(ph)
def _debug_cmd(self, args, subprocess_encoding, exe=None):
if not self.params.get('verbose', False):
return
if exe is None:
exe = os.path.basename(args[0])
if subprocess_encoding:
str_args = [
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
for a in args]
else:
str_args = args
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
except ImportError:
shell_quote = repr
self.to_screen('[debug] %s command line: %s' % (
exe, shell_quote(str_args)))

135
youtube_dl/downloader/external.py Normal file
View File

@ -0,0 +1,135 @@
from __future__ import unicode_literals
import os.path
import subprocess
import sys
from .common import FileDownloader
from ..utils import (
encodeFilename,
)
class ExternalFD(FileDownloader):
def real_download(self, filename, info_dict):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
retval = self._call_downloader(tmpfilename, info_dict)
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,
'filename': filename,
'status': 'finished',
})
return True
else:
self.to_stderr('\n')
self.report_error('%s exited with code %d' % (
self.get_basename(), retval))
return False
@classmethod
def get_basename(cls):
return cls.__name__[:-2].lower()
@property
def exe(self):
return self.params.get('external_downloader')
@classmethod
def supports(cls, info_dict):
return info_dict['protocol'] in ('http', 'https', 'ftp', 'ftps')
def _source_address(self, command_option):
source_address = self.params.get('source_address')
if source_address is None:
return []
return [command_option, source_address]
def _configuration_args(self, default=[]):
ex_args = self.params.get('external_downloader_args')
if ex_args is None:
return default
assert isinstance(ex_args, list)
return ex_args
def _call_downloader(self, tmpfilename, info_dict):
""" Either overwrite this or implement _make_cmd """
cmd = self._make_cmd(tmpfilename, info_dict)
if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode
# on Python 2.x
# See http://stackoverflow.com/a/9951851/35070
subprocess_encoding = sys.getfilesystemencoding()
cmd = [a.encode(subprocess_encoding, 'ignore') for a in cmd]
else:
subprocess_encoding = None
self._debug_cmd(cmd, subprocess_encoding)
p = subprocess.Popen(
cmd, stderr=subprocess.PIPE)
_, stderr = p.communicate()
if p.returncode != 0:
self.to_stderr(stderr)
return p.returncode
class CurlFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '--location', '-o', tmpfilename]
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._source_address('--interface')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
class WgetFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies']
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._source_address('--bind-address')
cmd += self._configuration_args()
cmd += ['--', info_dict['url']]
return cmd
class Aria2cFD(ExternalFD):
def _make_cmd(self, tmpfilename, info_dict):
cmd = [self.exe, '-c']
cmd += self._configuration_args([
'--min-split-size', '1M', '--max-connection-per-server', '4'])
dn = os.path.dirname(tmpfilename)
if dn:
cmd += ['--dir', dn]
cmd += ['--out', os.path.basename(tmpfilename)]
for key, val in info_dict['http_headers'].items():
cmd += ['--header', '%s: %s' % (key, val)]
cmd += self._source_address('--interface')
cmd += ['--', info_dict['url']]
return cmd
_BY_NAME = dict(
(klass.get_basename(), klass)
for name, klass in globals().items()
if name.endswith('FD') and name != 'ExternalFD'
)
def list_external_downloaders():
return sorted(_BY_NAME.keys())
def get_external_downloader(external_downloader):
""" Given the name of the executable, see whether we support the given
downloader . """
bn = os.path.basename(external_downloader)
return _BY_NAME[bn]

252
youtube_dl/downloader/f4m.py
View File

@ -1,4 +1,4 @@
from __future__ import unicode_literals from __future__ import division, unicode_literals
import base64 import base64
import io import io
@ -9,13 +9,16 @@ import xml.etree.ElementTree as etree
from .common import FileDownloader from .common import FileDownloader
from .http import HttpFD from .http import HttpFD
from ..compat import (
compat_urlparse,
compat_urllib_error,
)
from ..utils import ( from ..utils import (
struct_pack, struct_pack,
struct_unpack, struct_unpack,
compat_urlparse,
format_bytes,
encodeFilename, encodeFilename,
sanitize_open, sanitize_open,
xpath_text,
) )
@ -54,7 +57,7 @@ class FlvReader(io.BytesIO):
if size == 1: if size == 1:
real_size = self.read_unsigned_long_long() real_size = self.read_unsigned_long_long()
header_end = 16 header_end = 16
return real_size, box_type, self.read(real_size-header_end) return real_size, box_type, self.read(real_size - header_end)
def read_asrt(self): def read_asrt(self):
# version # version
@ -119,7 +122,8 @@ class FlvReader(io.BytesIO):
self.read_unsigned_int() # BootstrapinfoVersion self.read_unsigned_int() # BootstrapinfoVersion
# Profile,Live,Update,Reserved # Profile,Live,Update,Reserved
self.read(1) flags = self.read_unsigned_char()
live = flags & 0x20 != 0
# time scale # time scale
self.read_unsigned_int() self.read_unsigned_int()
# CurrentMediaTime # CurrentMediaTime
@ -158,6 +162,7 @@ class FlvReader(io.BytesIO):
return { return {
'segments': segments, 'segments': segments,
'fragments': fragments, 'fragments': fragments,
'live': live,
} }
def read_bootstrap_info(self): def read_bootstrap_info(self):
@ -174,34 +179,47 @@ def build_fragments_list(boot_info):
""" Return a list of (segment, fragment) for each fragment in the video """ """ Return a list of (segment, fragment) for each fragment in the video """
res = [] res = []
segment_run_table = boot_info['segments'][0] segment_run_table = boot_info['segments'][0]
# I've only found videos with one segment
segment_run_entry = segment_run_table['segment_run'][0]
n_frags = segment_run_entry[1]
fragment_run_entry_table = boot_info['fragments'][0]['fragments'] fragment_run_entry_table = boot_info['fragments'][0]['fragments']
first_frag_number = fragment_run_entry_table[0]['first'] first_frag_number = fragment_run_entry_table[0]['first']
for (i, frag_number) in zip(range(1, n_frags+1), itertools.count(first_frag_number)): fragments_counter = itertools.count(first_frag_number)
res.append((1, frag_number)) for segment, fragments_count in segment_run_table['segment_run']:
for _ in range(fragments_count):
res.append((segment, next(fragments_counter)))
if boot_info['live']:
res = res[-2:]
return res return res
def write_flv_header(stream, metadata): def write_unsigned_int(stream, val):
"""Writes the FLV header and the metadata to stream""" stream.write(struct_pack('!I', val))
def write_unsigned_int_24(stream, val):
stream.write(struct_pack('!I', val)[1:])
def write_flv_header(stream):
"""Writes the FLV header to stream"""
# FLV header # FLV header
stream.write(b'FLV\x01') stream.write(b'FLV\x01')
stream.write(b'\x05') stream.write(b'\x05')
stream.write(b'\x00\x00\x00\x09') stream.write(b'\x00\x00\x00\x09')
# FLV File body
stream.write(b'\x00\x00\x00\x00') stream.write(b'\x00\x00\x00\x00')
# FLVTAG
# Script data
stream.write(b'\x12') def write_metadata_tag(stream, metadata):
# Size of the metadata with 3 bytes """Writes optional metadata tag to stream"""
stream.write(struct_pack('!L', len(metadata))[1:]) SCRIPT_TAG = b'\x12'
stream.write(b'\x00\x00\x00\x00\x00\x00\x00') FLV_TAG_HEADER_LEN = 11
stream.write(metadata)
# Magic numbers extracted from the output files produced by AdobeHDS.php if metadata:
#(https://github.com/K-S-V/Scripts) stream.write(SCRIPT_TAG)
stream.write(b'\x00\x00\x01\x73') write_unsigned_int_24(stream, len(metadata))
stream.write(b'\x00\x00\x00\x00\x00\x00\x00')
stream.write(metadata)
write_unsigned_int(stream, FLV_TAG_HEADER_LEN + len(metadata))
def _add_ns(prop): def _add_ns(prop):
@ -218,22 +236,64 @@ class F4mFD(FileDownloader):
A downloader for f4m manifests or AdobeHDS. A downloader for f4m manifests or AdobeHDS.
""" """
def _get_unencrypted_media(self, doc):
media = doc.findall(_add_ns('media'))
if not media:
self.report_error('No media found')
for e in (doc.findall(_add_ns('drmAdditionalHeader')) +
doc.findall(_add_ns('drmAdditionalHeaderSet'))):
# If id attribute is missing it's valid for all media nodes
# without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute
if 'id' not in e.attrib:
self.report_error('Missing ID in f4m DRM')
media = list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and
'drmAdditionalHeaderSetId' not in e.attrib,
media))
if not media:
self.report_error('Unsupported DRM')
return media
def _get_bootstrap_from_url(self, bootstrap_url):
bootstrap = self.ydl.urlopen(bootstrap_url).read()
return read_bootstrap_info(bootstrap)
def _update_live_fragments(self, bootstrap_url, latest_fragment):
fragments_list = []
retries = 30
while (not fragments_list) and (retries > 0):
boot_info = self._get_bootstrap_from_url(bootstrap_url)
fragments_list = build_fragments_list(boot_info)
fragments_list = [f for f in fragments_list if f[1] > latest_fragment]
if not fragments_list:
# Retry after a while
time.sleep(5.0)
retries -= 1
if not fragments_list:
self.report_error('Failed to update fragments')
return fragments_list
def _parse_bootstrap_node(self, node, base_url):
if node.text is None:
bootstrap_url = compat_urlparse.urljoin(
base_url, node.attrib['url'])
boot_info = self._get_bootstrap_from_url(bootstrap_url)
else:
bootstrap_url = None
bootstrap = base64.b64decode(node.text.encode('ascii'))
boot_info = read_bootstrap_info(bootstrap)
return (boot_info, bootstrap_url)
def real_download(self, filename, info_dict): def real_download(self, filename, info_dict):
man_url = info_dict['url'] man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr') requested_bitrate = info_dict.get('tbr')
self.to_screen('[download] Downloading f4m manifest') self.to_screen('[download] Downloading f4m manifest')
manifest = self.ydl.urlopen(man_url).read() manifest = self.ydl.urlopen(man_url).read()
self.report_destination(filename)
http_dl = HttpQuietDownloader(self.ydl,
{
'continuedl': True,
'quiet': True,
'noprogress': True,
'test': self.params.get('test', False),
})
doc = etree.fromstring(manifest) doc = etree.fromstring(manifest)
formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))] formats = [(int(f.attrib.get('bitrate', -1)), f)
for f in self._get_unencrypted_media(doc)]
if requested_bitrate is None: if requested_bitrate is None:
# get the best format # get the best format
formats = sorted(formats, key=lambda f: f[0]) formats = sorted(formats, key=lambda f: f[0])
@ -243,70 +303,129 @@ class F4mFD(FileDownloader):
lambda f: int(f[0]) == requested_bitrate, formats))[0] lambda f: int(f[0]) == requested_bitrate, formats))[0]
base_url = compat_urlparse.urljoin(man_url, media.attrib['url']) base_url = compat_urlparse.urljoin(man_url, media.attrib['url'])
bootstrap = base64.b64decode(doc.find(_add_ns('bootstrapInfo')).text) bootstrap_node = doc.find(_add_ns('bootstrapInfo'))
metadata = base64.b64decode(media.find(_add_ns('metadata')).text) boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, base_url)
boot_info = read_bootstrap_info(bootstrap) 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'))
else:
metadata = None
fragments_list = build_fragments_list(boot_info) fragments_list = build_fragments_list(boot_info)
if self.params.get('test', False): if self.params.get('test', False):
# We only download the first fragment # We only download the first fragment
fragments_list = fragments_list[:1] fragments_list = fragments_list[:1]
total_frags = len(fragments_list) total_frags = len(fragments_list)
# For some akamai manifests we'll need to add a query to the fragment url
akamai_pv = xpath_text(doc, _add_ns('pv-2.0'))
self.report_destination(filename)
http_dl = HttpQuietDownloader(
self.ydl,
{
'continuedl': True,
'quiet': True,
'noprogress': True,
'ratelimit': self.params.get('ratelimit', None),
'test': self.params.get('test', False),
}
)
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
(dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb') (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb')
write_flv_header(dest_stream, metadata)
write_flv_header(dest_stream)
if not live:
write_metadata_tag(dest_stream, metadata)
# This dict stores the download progress, it's updated by the progress # This dict stores the download progress, it's updated by the progress
# hook # hook
state = { state = {
'status': 'downloading',
'downloaded_bytes': 0, 'downloaded_bytes': 0,
'frag_counter': 0, 'frag_index': 0,
'frag_count': total_frags,
'filename': filename,
'tmpfilename': tmpfilename,
} }
start = time.time() start = time.time()
def frag_progress_hook(status): def frag_progress_hook(s):
frag_total_bytes = status.get('total_bytes', 0) if s['status'] not in ('downloading', 'finished'):
estimated_size = (state['downloaded_bytes'] + return
(total_frags - state['frag_counter']) * frag_total_bytes)
if status['status'] == 'finished': frag_total_bytes = s.get('total_bytes', 0)
if s['status'] == 'finished':
state['downloaded_bytes'] += frag_total_bytes state['downloaded_bytes'] += frag_total_bytes
state['frag_counter'] += 1 state['frag_index'] += 1
progress = self.calc_percent(state['frag_counter'], total_frags)
byte_counter = state['downloaded_bytes'] estimated_size = (
(state['downloaded_bytes'] + frag_total_bytes) /
(state['frag_index'] + 1) * total_frags)
time_now = time.time()
state['total_bytes_estimate'] = estimated_size
state['elapsed'] = time_now - start
if s['status'] == 'finished':
progress = self.calc_percent(state['frag_index'], total_frags)
else: else:
frag_downloaded_bytes = status['downloaded_bytes'] frag_downloaded_bytes = s['downloaded_bytes']
byte_counter = state['downloaded_bytes'] + frag_downloaded_bytes
frag_progress = self.calc_percent(frag_downloaded_bytes, frag_progress = self.calc_percent(frag_downloaded_bytes,
frag_total_bytes) frag_total_bytes)
progress = self.calc_percent(state['frag_counter'], total_frags) progress = self.calc_percent(state['frag_index'], total_frags)
progress += frag_progress / float(total_frags) progress += frag_progress / float(total_frags)
eta = self.calc_eta(start, time.time(), estimated_size, byte_counter) state['eta'] = self.calc_eta(
self.report_progress(progress, format_bytes(estimated_size), start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes)
status.get('speed'), eta) state['speed'] = s.get('speed')
self._hook_progress(state)
http_dl.add_progress_hook(frag_progress_hook) http_dl.add_progress_hook(frag_progress_hook)
frags_filenames = [] frags_filenames = []
for (seg_i, frag_i) in fragments_list: while fragments_list:
seg_i, frag_i = fragments_list.pop(0)
name = 'Seg%d-Frag%d' % (seg_i, frag_i) name = 'Seg%d-Frag%d' % (seg_i, frag_i)
url = base_url + name url = base_url + name
if akamai_pv:
url += '?' + akamai_pv.strip(';')
frag_filename = '%s-%s' % (tmpfilename, name) frag_filename = '%s-%s' % (tmpfilename, name)
success = http_dl.download(frag_filename, {'url': url}) try:
if not success: success = http_dl.download(frag_filename, {'url': url})
return False if not success:
with open(frag_filename, 'rb') as down: return False
down_data = down.read() with open(frag_filename, 'rb') as down:
reader = FlvReader(down_data) down_data = down.read()
while True: reader = FlvReader(down_data)
_, box_type, box_data = reader.read_box_info() while True:
if box_type == b'mdat': _, box_type, box_data = reader.read_box_info()
dest_stream.write(box_data) if box_type == b'mdat':
break dest_stream.write(box_data)
frags_filenames.append(frag_filename) break
if live:
os.remove(frag_filename)
else:
frags_filenames.append(frag_filename)
except (compat_urllib_error.HTTPError, ) as err:
if live and (err.code == 404 or err.code == 410):
# We didn't keep up with the live window. Continue
# with the next available fragment.
msg = 'Fragment %d unavailable' % frag_i
self.report_warning(msg)
fragments_list = []
else:
raise
if not fragments_list and live and bootstrap_url:
fragments_list = self._update_live_fragments(bootstrap_url, frag_i)
total_frags += len(fragments_list)
if fragments_list and (fragments_list[0][1] > frag_i + 1):
msg = 'Missed %d fragments' % (fragments_list[0][1] - (frag_i + 1))
self.report_warning(msg)
dest_stream.close() dest_stream.close()
self.report_finish(format_bytes(state['downloaded_bytes']), time.time() - start)
elapsed = time.time() - start
self.try_rename(tmpfilename, filename) self.try_rename(tmpfilename, filename)
for frag_file in frags_filenames: for frag_file in frags_filenames:
os.remove(frag_file) os.remove(frag_file)
@ -317,6 +436,7 @@ class F4mFD(FileDownloader):
'total_bytes': fsize, 'total_bytes': fsize,
'filename': filename, 'filename': filename,
'status': 'finished', 'status': 'finished',
'elapsed': elapsed,
}) })
return True return True

91
youtube_dl/downloader/hls.py
View File

@ -1,9 +1,17 @@
from __future__ import unicode_literals
import os import os
import re
import subprocess import subprocess
from ..postprocessor.ffmpeg import FFmpegPostProcessor
from .common import FileDownloader from .common import FileDownloader
from ..compat import (
compat_urlparse,
compat_urllib_request,
)
from ..utils import ( from ..utils import (
check_executable, encodeArgument,
encodeFilename, encodeFilename,
) )
@ -14,23 +22,21 @@ class HlsFD(FileDownloader):
self.report_destination(filename) self.report_destination(filename)
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
args = [ ffpp = FFmpegPostProcessor(downloader=self)
'-y', '-i', url, '-f', 'mp4', '-c', 'copy', if not ffpp.available:
'-bsf:a', 'aac_adtstoasc', self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
encodeFilename(tmpfilename, for_subprocess=True)]
for program in ['avconv', 'ffmpeg']:
if check_executable(program, ['-version']):
break
else:
self.report_error(u'm3u8 download detected but ffmpeg or avconv could not be found. Please install one.')
return False return False
cmd = [program] + args ffpp.check_version()
retval = subprocess.call(cmd) args = [
encodeArgument(opt)
for opt in (ffpp.executable, '-y', '-i', url, '-f', 'mp4', '-c', 'copy', '-bsf:a', 'aac_adtstoasc')]
args.append(encodeFilename(tmpfilename, True))
retval = subprocess.call(args)
if retval == 0: if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename)) fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen(u'\r[%s] %s bytes' % (cmd[0], fsize)) self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
self.try_rename(tmpfilename, filename) self.try_rename(tmpfilename, filename)
self._hook_progress({ self._hook_progress({
'downloaded_bytes': fsize, 'downloaded_bytes': fsize,
@ -40,6 +46,59 @@ class HlsFD(FileDownloader):
}) })
return True return True
else: else:
self.to_stderr(u"\n") self.to_stderr('\n')
self.report_error(u'%s exited with code %d' % (program, retval)) self.report_error('%s exited with code %d' % (ffpp.basename, retval))
return False return False
class NativeHlsFD(FileDownloader):
""" A more limited implementation that does not require ffmpeg """
def real_download(self, filename, info_dict):
url = info_dict['url']
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
self.to_screen(
'[hlsnative] %s: Downloading m3u8 manifest' % info_dict['id'])
data = self.ydl.urlopen(url).read()
s = data.decode('utf-8', 'ignore')
segment_urls = []
for line in s.splitlines():
line = line.strip()
if line and not line.startswith('#'):
segment_url = (
line
if re.match(r'^https?://', line)
else compat_urlparse.urljoin(url, line))
segment_urls.append(segment_url)
is_test = self.params.get('test', False)
remaining_bytes = self._TEST_FILE_SIZE if is_test else None
byte_counter = 0
with open(tmpfilename, 'wb') as outf:
for i, segurl in enumerate(segment_urls):
self.to_screen(
'[hlsnative] %s: Downloading segment %d / %d' %
(info_dict['id'], i + 1, len(segment_urls)))
seg_req = compat_urllib_request.Request(segurl)
if remaining_bytes is not None:
seg_req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1))
segment = self.ydl.urlopen(seg_req).read()
if remaining_bytes is not None:
segment = segment[:remaining_bytes]
remaining_bytes -= len(segment)
outf.write(segment)
byte_counter += len(segment)
if remaining_bytes is not None and remaining_bytes <= 0:
break
self._hook_progress({
'downloaded_bytes': byte_counter,
'total_bytes': byte_counter,
'filename': filename,
'status': 'finished',
})
self.try_rename(tmpfilename, filename)
return True

91
youtube_dl/downloader/http.py
View File

@ -1,21 +1,23 @@
from __future__ import unicode_literals
import errno
import os import os
import socket
import time import time
from .common import FileDownloader from .common import FileDownloader
from ..utils import ( from ..compat import (
compat_urllib_request, compat_urllib_request,
compat_urllib_error, compat_urllib_error,
)
from ..utils import (
ContentTooShortError, ContentTooShortError,
encodeFilename, encodeFilename,
sanitize_open, sanitize_open,
format_bytes,
) )
class HttpFD(FileDownloader): class HttpFD(FileDownloader):
_TEST_FILE_SIZE = 10241
def real_download(self, filename, info_dict): def real_download(self, filename, info_dict):
url = info_dict['url'] url = info_dict['url']
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
@ -23,10 +25,6 @@ class HttpFD(FileDownloader):
# Do not include the Accept-Encoding header # Do not include the Accept-Encoding header
headers = {'Youtubedl-no-compression': 'True'} headers = {'Youtubedl-no-compression': 'True'}
if 'user_agent' in info_dict:
headers['Youtubedl-user-agent'] = info_dict['user_agent']
if 'http_referer' in info_dict:
headers['Referer'] = info_dict['http_referer']
add_headers = info_dict.get('http_headers') add_headers = info_dict.get('http_headers')
if add_headers: if add_headers:
headers.update(add_headers) headers.update(add_headers)
@ -94,6 +92,8 @@ class HttpFD(FileDownloader):
self._hook_progress({ self._hook_progress({
'filename': filename, 'filename': filename,
'status': 'finished', 'status': 'finished',
'downloaded_bytes': resume_len,
'total_bytes': resume_len,
}) })
return True return True
else: else:
@ -102,13 +102,18 @@ class HttpFD(FileDownloader):
resume_len = 0 resume_len = 0
open_mode = 'wb' open_mode = 'wb'
break break
except socket.error as e:
if e.errno != errno.ECONNRESET:
# Connection reset is no problem, just retry
raise
# Retry # Retry
count += 1 count += 1
if count <= retries: if count <= retries:
self.report_retry(count, retries) self.report_retry(count, retries)
if count > retries: if count > retries:
self.report_error(u'giving up after %s retries' % retries) self.report_error('giving up after %s retries' % retries)
return False return False
data_len = data.info().get('Content-length', None) data_len = data.info().get('Content-length', None)
@ -126,26 +131,30 @@ class HttpFD(FileDownloader):
min_data_len = self.params.get("min_filesize", None) min_data_len = self.params.get("min_filesize", None)
max_data_len = self.params.get("max_filesize", None) max_data_len = self.params.get("max_filesize", None)
if min_data_len is not None and data_len < min_data_len: if min_data_len is not None and data_len < min_data_len:
self.to_screen(u'\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len)) self.to_screen('\r[download] File is smaller than min-filesize (%s bytes < %s bytes). Aborting.' % (data_len, min_data_len))
return False return False
if max_data_len is not None and data_len > max_data_len: if max_data_len is not None and data_len > max_data_len:
self.to_screen(u'\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len)) self.to_screen('\r[download] File is larger than max-filesize (%s bytes > %s bytes). Aborting.' % (data_len, max_data_len))
return False return False
data_len_str = format_bytes(data_len)
byte_counter = 0 + resume_len byte_counter = 0 + resume_len
block_size = self.params.get('buffersize', 1024) block_size = self.params.get('buffersize', 1024)
start = time.time() start = time.time()
# measure time over whole while-loop, so slow_down() and best_block_size() work together properly
now = None # needed for slow_down() in the first loop run
before = start # start measuring
while True: while True:
# Download and write # Download and write
before = time.time()
data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter)) data_block = data.read(block_size if not is_test else min(block_size, data_len - byte_counter))
after = time.time()
if len(data_block) == 0:
break
byte_counter += len(data_block) byte_counter += len(data_block)
# Open file just in time # exit loop when download is finished
if len(data_block) == 0:
break
# Open destination file just in time
if stream is None: if stream is None:
try: try:
(stream, tmpfilename) = sanitize_open(tmpfilename, open_mode) (stream, tmpfilename) = sanitize_open(tmpfilename, open_mode)
@ -153,49 +162,64 @@ class HttpFD(FileDownloader):
filename = self.undo_temp_name(tmpfilename) filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename) self.report_destination(filename)
except (OSError, IOError) as err: except (OSError, IOError) as err:
self.report_error(u'unable to open for writing: %s' % str(err)) self.report_error('unable to open for writing: %s' % str(err))
return False return False
if self.params.get('xattr_set_filesize', False) and data_len is not None:
try:
import xattr
xattr.setxattr(tmpfilename, 'user.ytdl.filesize', str(data_len))
except(OSError, IOError, ImportError) as err:
self.report_error('unable to set filesize xattr: %s' % str(err))
try: try:
stream.write(data_block) stream.write(data_block)
except (IOError, OSError) as err: except (IOError, OSError) as err:
self.to_stderr(u"\n") self.to_stderr('\n')
self.report_error(u'unable to write data: %s' % str(err)) self.report_error('unable to write data: %s' % str(err))
return False return False
# Apply rate limit
self.slow_down(start, now, byte_counter - resume_len)
# end measuring of one loop run
now = time.time()
after = now
# Adjust block size
if not self.params.get('noresizebuffer', False): if not self.params.get('noresizebuffer', False):
block_size = self.best_block_size(after - before, len(data_block)) block_size = self.best_block_size(after - before, len(data_block))
before = after
# Progress message # Progress message
speed = self.calc_speed(start, time.time(), byte_counter - resume_len) speed = self.calc_speed(start, now, byte_counter - resume_len)
if data_len is None: if data_len is None:
eta = percent = None eta = None
else: else:
percent = self.calc_percent(byte_counter, data_len)
eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len) eta = self.calc_eta(start, time.time(), data_len - resume_len, byte_counter - resume_len)
self.report_progress(percent, data_len_str, speed, eta)
self._hook_progress({ self._hook_progress({
'status': 'downloading',
'downloaded_bytes': byte_counter, 'downloaded_bytes': byte_counter,
'total_bytes': data_len, 'total_bytes': data_len,
'tmpfilename': tmpfilename, 'tmpfilename': tmpfilename,
'filename': filename, 'filename': filename,
'status': 'downloading',
'eta': eta, 'eta': eta,
'speed': speed, 'speed': speed,
'elapsed': now - start,
}) })
if is_test and byte_counter == data_len: if is_test and byte_counter == data_len:
break break
# Apply rate limit
self.slow_down(start, byte_counter - resume_len)
if stream is None: if stream is None:
self.to_stderr(u"\n") self.to_stderr('\n')
self.report_error(u'Did not get any data blocks') self.report_error('Did not get any data blocks')
return False return False
if tmpfilename != u'-': if tmpfilename != '-':
stream.close() stream.close()
self.report_finish(data_len_str, (time.time() - start))
if data_len is not None and byte_counter != data_len: if data_len is not None and byte_counter != data_len:
raise ContentTooShortError(byte_counter, int(data_len)) raise ContentTooShortError(byte_counter, int(data_len))
self.try_rename(tmpfilename, filename) self.try_rename(tmpfilename, filename)
@ -209,6 +233,7 @@ class HttpFD(FileDownloader):
'total_bytes': byte_counter, 'total_bytes': byte_counter,
'filename': filename, 'filename': filename,
'status': 'finished', 'status': 'finished',
'elapsed': time.time() - start,
}) })
return True return True

19
youtube_dl/downloader/mplayer.py
View File

@ -1,8 +1,11 @@
from __future__ import unicode_literals
import os import os
import subprocess import subprocess
from .common import FileDownloader from .common import FileDownloader
from ..utils import ( from ..utils import (
check_executable,
encodeFilename, encodeFilename,
) )
@ -13,19 +16,19 @@ class MplayerFD(FileDownloader):
self.report_destination(filename) self.report_destination(filename)
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
args = ['mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy', '-dumpstream', '-dumpfile', tmpfilename, url] args = [
'mplayer', '-really-quiet', '-vo', 'null', '-vc', 'dummy',
'-dumpstream', '-dumpfile', tmpfilename, url]
# Check for mplayer first # Check for mplayer first
try: if not check_executable('mplayer', ['-h']):
subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0])
except (OSError, IOError):
self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0])
return False return False
# Download using mplayer. # Download using mplayer.
retval = subprocess.call(args) retval = subprocess.call(args)
if retval == 0: if retval == 0:
fsize = os.path.getsize(encodeFilename(tmpfilename)) fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen(u'\r[%s] %s bytes' % (args[0], fsize)) self.to_screen('\r[%s] %s bytes' % (args[0], fsize))
self.try_rename(tmpfilename, filename) self.try_rename(tmpfilename, filename)
self._hook_progress({ self._hook_progress({
'downloaded_bytes': fsize, 'downloaded_bytes': fsize,
@ -35,6 +38,6 @@ class MplayerFD(FileDownloader):
}) })
return True return True
else: else:
self.to_stderr(u"\n") self.to_stderr('\n')
self.report_error(u'mplayer exited with code %d' % retval) self.report_error('mplayer exited with code %d' % retval)
return False return False

67
youtube_dl/downloader/rtmp.py
View File

@ -7,14 +7,19 @@ import sys
import time import time
from .common import FileDownloader from .common import FileDownloader
from ..compat import compat_str
from ..utils import ( from ..utils import (
check_executable, check_executable,
compat_str,
encodeFilename, encodeFilename,
format_bytes, get_exe_version,
) )
def rtmpdump_version():
return get_exe_version(
'rtmpdump', ['--help'], r'(?i)RTMPDump\s*v?([0-9a-zA-Z._-]+)')
class RtmpFD(FileDownloader): class RtmpFD(FileDownloader):
def real_download(self, filename, info_dict): def real_download(self, filename, info_dict):
def run_rtmpdump(args): def run_rtmpdump(args):
@ -40,49 +45,49 @@ class RtmpFD(FileDownloader):
continue continue
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line) 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: if mobj:
downloaded_data_len = int(float(mobj.group(1))*1024) downloaded_data_len = int(float(mobj.group(1)) * 1024)
percent = float(mobj.group(2)) percent = float(mobj.group(2))
if not resume_percent: if not resume_percent:
resume_percent = percent resume_percent = percent
resume_downloaded_data_len = downloaded_data_len resume_downloaded_data_len = downloaded_data_len
eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent) time_now = time.time()
speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_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 data_len = None
if percent > 0: if percent > 0:
data_len = int(downloaded_data_len * 100 / percent) data_len = int(downloaded_data_len * 100 / percent)
data_len_str = '~' + format_bytes(data_len)
self.report_progress(percent, data_len_str, speed, eta)
cursor_in_new_line = False
self._hook_progress({ self._hook_progress({
'status': 'downloading',
'downloaded_bytes': downloaded_data_len, 'downloaded_bytes': downloaded_data_len,
'total_bytes': data_len, 'total_bytes_estimate': data_len,
'tmpfilename': tmpfilename, 'tmpfilename': tmpfilename,
'filename': filename, 'filename': filename,
'status': 'downloading',
'eta': eta, 'eta': eta,
'elapsed': time_now - start,
'speed': speed, 'speed': speed,
}) })
cursor_in_new_line = False
else: else:
# no percent for live streams # no percent for live streams
mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line) mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line)
if mobj: if mobj:
downloaded_data_len = int(float(mobj.group(1))*1024) downloaded_data_len = int(float(mobj.group(1)) * 1024)
time_now = time.time() time_now = time.time()
speed = self.calc_speed(start, time_now, downloaded_data_len) speed = self.calc_speed(start, time_now, downloaded_data_len)
self.report_progress_live_stream(downloaded_data_len, speed, time_now - start)
cursor_in_new_line = False
self._hook_progress({ self._hook_progress({
'downloaded_bytes': downloaded_data_len, 'downloaded_bytes': downloaded_data_len,
'tmpfilename': tmpfilename, 'tmpfilename': tmpfilename,
'filename': filename, 'filename': filename,
'status': 'downloading', 'status': 'downloading',
'elapsed': time_now - start,
'speed': speed, 'speed': speed,
}) })
cursor_in_new_line = False
elif self.params.get('verbose', False): elif self.params.get('verbose', False):
if not cursor_in_new_line: if not cursor_in_new_line:
self.to_screen('') self.to_screen('')
cursor_in_new_line = True cursor_in_new_line = True
self.to_screen('[rtmpdump] '+line) self.to_screen('[rtmpdump] ' + line)
proc.wait() proc.wait()
if not cursor_in_new_line: if not cursor_in_new_line:
self.to_screen('') self.to_screen('')
@ -98,6 +103,9 @@ class RtmpFD(FileDownloader):
live = info_dict.get('rtmp_live', False) live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn', None) conn = info_dict.get('rtmp_conn', None)
protocol = info_dict.get('rtmp_protocol', None) protocol = info_dict.get('rtmp_protocol', None)
real_time = info_dict.get('rtmp_real_time', False)
no_resume = info_dict.get('no_resume', False)
continue_dl = info_dict.get('continuedl', False)
self.report_destination(filename) self.report_destination(filename)
tmpfilename = self.temp_name(filename) tmpfilename = self.temp_name(filename)
@ -111,7 +119,9 @@ class RtmpFD(FileDownloader):
# Download using rtmpdump. rtmpdump returns exit code 2 when # Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be # the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK. # possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename] basic_args = [
'rtmpdump', '--verbose', '-r', url,
'-o', encodeFilename(tmpfilename, True)]
if player_url is not None: if player_url is not None:
basic_args += ['--swfVfy', player_url] basic_args += ['--swfVfy', player_url]
if page_url is not None: if page_url is not None:
@ -135,7 +145,14 @@ class RtmpFD(FileDownloader):
basic_args += ['--conn', conn] basic_args += ['--conn', conn]
if protocol is not None: if protocol is not None:
basic_args += ['--protocol', protocol] basic_args += ['--protocol', protocol]
args = basic_args + [[], ['--resume', '--skip', '1']][not live and self.params.get('continuedl', False)] if real_time:
basic_args += ['--realtime']
args = basic_args
if not no_resume and continue_dl and not live:
args += ['--resume']
if not live and continue_dl:
args += ['--skip', '1']
if sys.platform == 'win32' and sys.version_info < (3, 0): if sys.platform == 'win32' and sys.version_info < (3, 0):
# Windows subprocess module does not actually support Unicode # Windows subprocess module does not actually support Unicode
@ -146,19 +163,7 @@ class RtmpFD(FileDownloader):
else: else:
subprocess_encoding = None subprocess_encoding = None
if self.params.get('verbose', False): self._debug_cmd(args, subprocess_encoding, exe='rtmpdump')
if subprocess_encoding:
str_args = [
a.decode(subprocess_encoding) if isinstance(a, bytes) else a
for a in args]
else:
str_args = args
try:
import pipes
shell_quote = lambda args: ' '.join(map(pipes.quote, str_args))
except ImportError:
shell_quote = repr
self.to_screen('[debug] rtmpdump command line: ' + shell_quote(str_args))
RD_SUCCESS = 0 RD_SUCCESS = 0
RD_FAILED = 1 RD_FAILED = 1
@ -174,12 +179,12 @@ class RtmpFD(FileDownloader):
while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live: while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live:
prevsize = os.path.getsize(encodeFilename(tmpfilename)) prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] %s bytes' % prevsize) self.to_screen('[rtmpdump] %s bytes' % prevsize)
time.sleep(5.0) # This seems to be needed time.sleep(5.0) # This seems to be needed
retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED]) retval = run_rtmpdump(basic_args + ['-e'] + [[], ['-k', '1']][retval == RD_FAILED])
cursize = os.path.getsize(encodeFilename(tmpfilename)) cursize = os.path.getsize(encodeFilename(tmpfilename))
if prevsize == cursize and retval == RD_FAILED: if prevsize == cursize and retval == RD_FAILED:
break break
# Some rtmp streams seem abort after ~ 99.8%. Don't complain for those # Some rtmp streams seem abort after ~ 99.8%. Don't complain for those
if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024: if prevsize == cursize and retval == RD_INCOMPLETE and cursize > 1024:
self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.') self.to_screen('[rtmpdump] Could not download the whole video. This can happen for some advertisements.')
retval = RD_SUCCESS retval = RD_SUCCESS

251
youtube_dl/extractor/__init__.py
View File

@ -1,12 +1,19 @@
from __future__ import unicode_literals
from .abc import ABCIE from .abc import ABCIE
from .abc7news import Abc7NewsIE
from .academicearth import AcademicEarthCourseIE from .academicearth import AcademicEarthCourseIE
from .addanime import AddAnimeIE from .addanime import AddAnimeIE
from .adobetv import AdobeTVIE
from .adultswim import AdultSwimIE from .adultswim import AdultSwimIE
from .aftenposten import AftenpostenIE
from .aftonbladet import AftonbladetIE from .aftonbladet import AftonbladetIE
from .airmozilla import AirMozillaIE
from .aljazeera import AlJazeeraIE
from .alphaporno import AlphaPornoIE
from .anitube import AnitubeIE from .anitube import AnitubeIE
from .anysex import AnySexIE from .anysex import AnySexIE
from .aol import AolIE from .aol import AolIE
from .allmyvideos import AllmyvideosIE
from .allocine import AllocineIE from .allocine import AllocineIE
from .aparat import AparatIE from .aparat import AparatIE
from .appletrailers import AppleTrailersIE from .appletrailers import AppleTrailersIE
@ -21,30 +28,48 @@ from .arte import (
ArteTVDDCIE, ArteTVDDCIE,
ArteTVEmbedIE, ArteTVEmbedIE,
) )
from .auengine import AUEngineIE from .atresplayer import AtresPlayerIE
from .atttechchannel import ATTTechChannelIE
from .audiomack import AudiomackIE, AudiomackAlbumIE
from .azubu import AzubuIE
from .bambuser import BambuserIE, BambuserChannelIE from .bambuser import BambuserIE, BambuserChannelIE
from .bandcamp import BandcampIE, BandcampAlbumIE from .bandcamp import BandcampIE, BandcampAlbumIE
from .bbccouk import BBCCoUkIE from .bbccouk import BBCCoUkIE
from .beeg import BeegIE from .beeg import BeegIE
from .behindkink import BehindKinkIE from .behindkink import BehindKinkIE
from .beatportpro import BeatportProIE
from .bet import BetIE
from .bild import BildIE
from .bilibili import BiliBiliIE from .bilibili import BiliBiliIE
from .blinkx import BlinkxIE from .blinkx import BlinkxIE
from .bliptv import BlipTVIE, BlipTVUserIE from .bliptv import BlipTVIE, BlipTVUserIE
from .bloomberg import BloombergIE from .bloomberg import BloombergIE
from .bpb import BpbIE
from .br import BRIE from .br import BRIE
from .breakcom import BreakIE from .breakcom import BreakIE
from .brightcove import BrightcoveIE from .brightcove import BrightcoveIE
from .buzzfeed import BuzzFeedIE
from .byutv import BYUtvIE from .byutv import BYUtvIE
from .c56 import C56IE from .c56 import C56IE
from .camdemy import (
CamdemyIE,
CamdemyFolderIE
)
from .canal13cl import Canal13clIE from .canal13cl import Canal13clIE
from .canalplus import CanalplusIE from .canalplus import CanalplusIE
from .canalc2 import Canalc2IE from .canalc2 import Canalc2IE
from .cbs import CBSIE from .cbs import CBSIE
from .cbsnews import CBSNewsIE from .cbsnews import CBSNewsIE
from .cbssports import CBSSportsIE
from .ccc import CCCIE
from .ceskatelevize import CeskaTelevizeIE from .ceskatelevize import CeskaTelevizeIE
from .channel9 import Channel9IE from .channel9 import Channel9IE
from .chilloutzone import ChilloutzoneIE from .chilloutzone import ChilloutzoneIE
from .cinemassacre import CinemassacreIE from .chirbit import (
ChirbitIE,
ChirbitProfileIE,
)
from .cinchcast import CinchcastIE
from .clipfish import ClipfishIE from .clipfish import ClipfishIE
from .cliphunter import CliphunterIE from .cliphunter import CliphunterIE
from .clipsyndicate import ClipsyndicateIE from .clipsyndicate import ClipsyndicateIE
@ -55,15 +80,22 @@ from .cnet import CNETIE
from .cnn import ( from .cnn import (
CNNIE, CNNIE,
CNNBlogsIE, CNNBlogsIE,
CNNArticleIE,
) )
from .collegehumor import CollegeHumorIE from .collegehumor import CollegeHumorIE
from .collegerama import CollegeRamaIE
from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
from .comcarcoff import ComCarCoffIE
from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
from .condenast import CondeNastIE from .condenast import CondeNastIE
from .cracked import CrackedIE from .cracked import CrackedIE
from .criterion import CriterionIE from .criterion import CriterionIE
from .crunchyroll import CrunchyrollIE from .crunchyroll import (
CrunchyrollIE,
CrunchyrollShowPlaylistIE
)
from .cspan import CSpanIE from .cspan import CSpanIE
from .d8 import D8IE from .ctsnews import CtsNewsIE
from .dailymotion import ( from .dailymotion import (
DailymotionIE, DailymotionIE,
DailymotionPlaylistIE, DailymotionPlaylistIE,
@ -71,18 +103,24 @@ from .dailymotion import (
) )
from .daum import DaumIE from .daum import DaumIE
from .dbtv import DBTVIE from .dbtv import DBTVIE
from .dctp import DctpTvIE
from .deezer import DeezerPlaylistIE from .deezer import DeezerPlaylistIE
from .dfb import DFBIE from .dfb import DFBIE
from .dotsub import DotsubIE from .dotsub import DotsubIE
from .douyutv import DouyuTVIE
from .dreisat import DreiSatIE from .dreisat import DreiSatIE
from .drbonanza import DRBonanzaIE
from .drtuber import DrTuberIE from .drtuber import DrTuberIE
from .drtv import DRTVIE from .drtv import DRTVIE
from .dvtv import DVTVIE
from .dump import DumpIE from .dump import DumpIE
from .defense import DefenseGouvFrIE from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE from .discovery import DiscoveryIE
from .divxstage import DivxStageIE from .divxstage import DivxStageIE
from .dropbox import DropboxIE from .dropbox import DropboxIE
from .eagleplatform import EaglePlatformIE
from .ebaumsworld import EbaumsWorldIE from .ebaumsworld import EbaumsWorldIE
from .echomsk import EchoMskIE
from .ehow import EHowIE from .ehow import EHowIE
from .eighttracks import EightTracksIE from .eighttracks import EightTracksIE
from .einthusan import EinthusanIE from .einthusan import EinthusanIE
@ -92,9 +130,11 @@ from .ellentv import (
EllenTVClipsIE, EllenTVClipsIE,
) )
from .elpais import ElPaisIE from .elpais import ElPaisIE
from .embedly import EmbedlyIE
from .empflix import EMPFlixIE from .empflix import EMPFlixIE
from .engadget import EngadgetIE from .engadget import EngadgetIE
from .eporner import EpornerIE from .eporner import EpornerIE
from .eroprofile import EroProfileIE
from .escapist import EscapistIE from .escapist import EscapistIE
from .everyonesmixtape import EveryonesMixtapeIE from .everyonesmixtape import EveryonesMixtapeIE
from .exfm import ExfmIE from .exfm import ExfmIE
@ -112,7 +152,11 @@ from .fktv import (
FKTVPosteckeIE, FKTVPosteckeIE,
) )
from .flickr import FlickrIE from .flickr import FlickrIE
from .folketinget import FolketingetIE
from .footyroom import FootyRoomIE
from .fourtube import FourTubeIE from .fourtube import FourTubeIE
from .foxgay import FoxgayIE
from .foxnews import FoxNewsIE
from .franceculture import FranceCultureIE from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE from .franceinter import FranceInterIE
from .francetv import ( from .francetv import (
@ -124,6 +168,7 @@ from .francetv import (
) )
from .freesound import FreesoundIE from .freesound import FreesoundIE
from .freespeech import FreespeechIE from .freespeech import FreespeechIE
from .freevideo import FreeVideoIE
from .funnyordie import FunnyOrDieIE from .funnyordie import FunnyOrDieIE
from .gamekings import GamekingsIE from .gamekings import GamekingsIE
from .gameone import ( from .gameone import (
@ -133,17 +178,31 @@ from .gameone import (
from .gamespot import GameSpotIE from .gamespot import GameSpotIE
from .gamestar import GameStarIE from .gamestar import GameStarIE
from .gametrailers import GametrailersIE from .gametrailers import GametrailersIE
from .gazeta import GazetaIE
from .gdcvault import GDCVaultIE from .gdcvault import GDCVaultIE
from .generic import GenericIE from .generic import GenericIE
from .giantbomb import GiantBombIE
from .giga import GigaIE
from .glide import GlideIE
from .globo import GloboIE
from .godtube import GodTubeIE from .godtube import GodTubeIE
from .goldenmoustache import GoldenMoustacheIE
from .golem import GolemIE
from .googleplus import GooglePlusIE from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE from .googlesearch import GoogleSearchIE
from .gorillavid import GorillaVidIE from .gorillavid import GorillaVidIE
from .goshgay import GoshgayIE from .goshgay import GoshgayIE
from .grooveshark import GroovesharkIE from .grooveshark import GroovesharkIE
from .groupon import GrouponIE
from .hark import HarkIE from .hark import HarkIE
from .hearthisat import HearThisAtIE
from .heise import HeiseIE
from .hellporno import HellPornoIE
from .helsinki import HelsinkiIE from .helsinki import HelsinkiIE
from .hentaistigma import HentaiStigmaIE from .hentaistigma import HentaiStigmaIE
from .historicfilms import HistoricFilmsIE
from .history import HistoryIE
from .hitbox import HitboxIE, HitboxLiveIE
from .hornbunny import HornBunnyIE from .hornbunny import HornBunnyIE
from .hostingbulk import HostingBulkIE from .hostingbulk import HostingBulkIE
from .hotnewhiphop import HotNewHipHopIE from .hotnewhiphop import HotNewHipHopIE
@ -157,6 +216,7 @@ from .imdb import (
ImdbIE, ImdbIE,
ImdbListIE ImdbListIE
) )
from .imgur import ImgurIE
from .ina import InaIE from .ina import InaIE
from .infoq import InfoQIE from .infoq import InfoQIE
from .instagram import InstagramIE, InstagramUserIE from .instagram import InstagramIE, InstagramUserIE
@ -171,9 +231,11 @@ from .jadorecettepub import JadoreCettePubIE
from .jeuxvideo import JeuxVideoIE from .jeuxvideo import JeuxVideoIE
from .jove import JoveIE from .jove import JoveIE
from .jukebox import JukeboxIE from .jukebox import JukeboxIE
from .justintv import JustinTVIE
from .jpopsukitv import JpopsukiIE from .jpopsukitv import JpopsukiIE
from .kaltura import KalturaIE
from .kanalplay import KanalPlayIE
from .kankan import KankanIE from .kankan import KankanIE
from .karaoketv import KaraoketvIE
from .keezmovies import KeezMoviesIE from .keezmovies import KeezMoviesIE
from .khanacademy import KhanAcademyIE from .khanacademy import KhanAcademyIE
from .kickstarter import KickStarterIE from .kickstarter import KickStarterIE
@ -182,6 +244,13 @@ from .kontrtube import KontrTubeIE
from .krasview import KrasViewIE from .krasview import KrasViewIE
from .ku6 import Ku6IE from .ku6 import Ku6IE
from .la7 import LA7IE from .la7 import LA7IE
from .laola1tv import Laola1TvIE
from .letv import (
LetvIE,
LetvTvIE,
LetvPlaylistIE
)
from .libsyn import LibsynIE
from .lifenews import LifeNewsIE from .lifenews import LifeNewsIE
from .liveleak import LiveLeakIE from .liveleak import LiveLeakIE
from .livestream import ( from .livestream import (
@ -189,6 +258,8 @@ from .livestream import (
LivestreamOriginalIE, LivestreamOriginalIE,
LivestreamShortenerIE, LivestreamShortenerIE,
) )
from .lnkgo import LnkGoIE
from .lrt import LRTIE
from .lynda import ( from .lynda import (
LyndaIE, LyndaIE,
LyndaCourseIE LyndaCourseIE
@ -200,6 +271,8 @@ from .malemotion import MalemotionIE
from .mdr import MDRIE from .mdr import MDRIE
from .metacafe import MetacafeIE from .metacafe import MetacafeIE
from .metacritic import MetacriticIE from .metacritic import MetacriticIE
from .mgoon import MgoonIE
from .minhateca import MinhatecaIE
from .ministrygrid import MinistryGridIE from .ministrygrid import MinistryGridIE
from .mit import TechTVMITIE, MITIE, OCWMITIE from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mitele import MiTeleIE from .mitele import MiTeleIE
@ -209,6 +282,7 @@ from .mpora import MporaIE
from .moevideo import MoeVideoIE from .moevideo import MoeVideoIE
from .mofosex import MofosexIE from .mofosex import MofosexIE
from .mojvideo import MojvideoIE from .mojvideo import MojvideoIE
from .moniker import MonikerIE
from .mooshare import MooshareIE from .mooshare import MooshareIE
from .morningstar import MorningstarIE from .morningstar import MorningstarIE
from .motherless import MotherlessIE from .motherless import MotherlessIE
@ -221,12 +295,15 @@ from .mtv import (
MTVServicesEmbeddedIE, MTVServicesEmbeddedIE,
MTVIggyIE, MTVIggyIE,
) )
from .muenchentv import MuenchenTVIE
from .musicplayon import MusicPlayOnIE from .musicplayon import MusicPlayOnIE
from .musicvault import MusicVaultIE from .musicvault import MusicVaultIE
from .muzu import MuzuTVIE from .muzu import MuzuTVIE
from .myspace import MySpaceIE from .myspace import MySpaceIE, MySpaceAlbumIE
from .myspass import MySpassIE from .myspass import MySpassIE
from .myvideo import MyVideoIE from .myvideo import MyVideoIE
from .myvidster import MyVidsterIE
from .nationalgeographic import NationalGeographicIE
from .naver import NaverIE from .naver import NaverIE
from .nba import NBAIE from .nba import NBAIE
from .nbc import ( from .nbc import (
@ -235,11 +312,25 @@ from .nbc import (
) )
from .ndr import NDRIE from .ndr import NDRIE
from .ndtv import NDTVIE from .ndtv import NDTVIE
from .netzkino import NetzkinoIE
from .nerdcubed import NerdCubedFeedIE
from .nerdist import NerdistIE
from .newgrounds import NewgroundsIE from .newgrounds import NewgroundsIE
from .newstube import NewstubeIE from .newstube import NewstubeIE
from .nextmedia import (
NextMediaIE,
NextMediaActionNewsIE,
AppleDailyRealtimeNewsIE,
AppleDailyAnimationNewsIE
)
from .nfb import NFBIE from .nfb import NFBIE
from .nhl import NHLIE, NHLVideocenterIE from .nfl import NFLIE
from .niconico import NiconicoIE from .nhl import (
NHLIE,
NHLNewsIE,
NHLVideocenterIE,
)
from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninegag import NineGagIE from .ninegag import NineGagIE
from .noco import NocoIE from .noco import NocoIE
from .normalboots import NormalbootsIE from .normalboots import NormalbootsIE
@ -247,62 +338,98 @@ from .nosvideo import NosVideoIE
from .novamov import NovaMovIE from .novamov import NovaMovIE
from .nowness import NownessIE from .nowness import NownessIE
from .nowvideo import NowVideoIE from .nowvideo import NowVideoIE
from .npo import NPOIE from .npo import (
NPOIE,
NPOLiveIE,
NPORadioIE,
NPORadioFragmentIE,
TegenlichtVproIE,
)
from .nrk import ( from .nrk import (
NRKIE, NRKIE,
NRKPlaylistIE,
NRKTVIE, NRKTVIE,
) )
from .ntv import NTVIE from .ntvde import NTVDeIE
from .ntvru import NTVRuIE
from .nytimes import NYTimesIE from .nytimes import NYTimesIE
from .nuvid import NuvidIE from .nuvid import NuvidIE
from .odnoklassniki import OdnoklassnikiIE
from .oktoberfesttv import OktoberfestTVIE
from .ooyala import OoyalaIE from .ooyala import OoyalaIE
from .openfilm import OpenFilmIE
from .orf import ( from .orf import (
ORFTVthekIE, ORFTVthekIE,
ORFOE1IE, ORFOE1IE,
ORFFM4IE, ORFFM4IE,
ORFIPTVIE,
) )
from .parliamentliveuk import ParliamentLiveUKIE from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE from .patreon import PatreonIE
from .pbs import PBSIE from .pbs import PBSIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE from .photobucket import PhotobucketIE
from .planetaplay import PlanetaPlayIE
from .pladform import PladformIE
from .played import PlayedIE
from .playfm import PlayFMIE from .playfm import PlayFMIE
from .playvid import PlayvidIE from .playvid import PlayvidIE
from .playwire import PlaywireIE
from .podomatic import PodomaticIE from .podomatic import PodomaticIE
from .pornhd import PornHdIE from .pornhd import PornHdIE
from .pornhub import PornHubIE from .pornhub import (
PornHubIE,
PornHubPlaylistIE,
)
from .pornotube import PornotubeIE from .pornotube import PornotubeIE
from .pornoxo import PornoXOIE from .pornoxo import PornoXOIE
from .primesharetv import PrimeShareTVIE
from .promptfile import PromptFileIE from .promptfile import PromptFileIE
from .prosiebensat1 import ProSiebenSat1IE from .prosiebensat1 import ProSiebenSat1IE
from .puls4 import Puls4IE
from .pyvideo import PyvideoIE from .pyvideo import PyvideoIE
from .quickvid import QuickVidIE
from .r7 import R7IE
from .radiode import RadioDeIE
from .radiobremen import RadioBremenIE
from .radiofrance import RadioFranceIE from .radiofrance import RadioFranceIE
from .rai import RaiIE from .rai import RaiIE
from .rbmaradio import RBMARadioIE from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE from .redtube import RedTubeIE
from .restudy import RestudyIE
from .reverbnation import ReverbNationIE from .reverbnation import ReverbNationIE
from .ringtv import RingTVIE from .ringtv import RingTVIE
from .ro220 import Ro220IE from .ro220 import Ro220IE
from .rottentomatoes import RottenTomatoesIE from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE from .roxwel import RoxwelIE
from .rtbf import RTBFIE from .rtbf import RTBFIE
from .rtlnl import RtlXlIE from .rte import RteIE
from .rtlnl import RtlNlIE
from .rtlnow import RTLnowIE from .rtlnow import RTLnowIE
from .rtl2 import RTL2IE
from .rtp import RTPIE
from .rts import RTSIE from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
from .ruhd import RUHDIE from .ruhd import RUHDIE
from .rutube import ( from .rutube import (
RutubeIE, RutubeIE,
RutubeChannelIE, RutubeChannelIE,
RutubeEmbedIE,
RutubeMovieIE, RutubeMovieIE,
RutubePersonIE, RutubePersonIE,
) )
from .rutv import RUTVIE from .rutv import RUTVIE
from .sandia import SandiaIE
from .sapo import SapoIE from .sapo import SapoIE
from .savefrom import SaveFromIE from .savefrom import SaveFromIE
from .sbs import SBSIE from .sbs import SBSIE
from .scivee import SciVeeIE from .scivee import SciVeeIE
from .screencast import ScreencastIE from .screencast import ScreencastIE
from .screencastomatic import ScreencastOMaticIE
from .screenwavemedia import CinemassacreIE, ScreenwaveMediaIE, TeamFourIE
from .servingsys import ServingSysIE from .servingsys import ServingSysIE
from .sexu import SexuIE
from .sexykarma import SexyKarmaIE
from .shared import SharedIE from .shared import SharedIE
from .sharesix import ShareSixIE from .sharesix import ShareSixIE
from .sina import SinaIE from .sina import SinaIE
@ -323,7 +450,10 @@ from .soundcloud import (
SoundcloudUserIE, SoundcloudUserIE,
SoundcloudPlaylistIE SoundcloudPlaylistIE
) )
from .soundgasm import SoundgasmIE from .soundgasm import (
SoundgasmIE,
SoundgasmProfileIE
)
from .southpark import ( from .southpark import (
SouthParkIE, SouthParkIE,
SouthparkDeIE, SouthparkDeIE,
@ -333,16 +463,24 @@ from .spankwire import SpankwireIE
from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegel import SpiegelIE, SpiegelArticleIE
from .spiegeltv import SpiegeltvIE from .spiegeltv import SpiegeltvIE
from .spike import SpikeIE from .spike import SpikeIE
from .sport5 import Sport5IE
from .sportbox import SportBoxIE
from .sportdeutschland import SportDeutschlandIE from .sportdeutschland import SportDeutschlandIE
from .srmediathek import SRMediathekIE
from .ssa import SSAIE
from .stanfordoc import StanfordOpenClassroomIE from .stanfordoc import StanfordOpenClassroomIE
from .steam import SteamIE from .steam import SteamIE
from .streamcloud import StreamcloudIE from .streamcloud import StreamcloudIE
from .streamcz import StreamCZIE from .streamcz import StreamCZIE
from .streetvoice import StreetVoiceIE
from .sunporno import SunPornoIE from .sunporno import SunPornoIE
from .svtplay import SVTPlayIE
from .swrmediathek import SWRMediathekIE from .swrmediathek import SWRMediathekIE
from .syfy import SyfyIE from .syfy import SyfyIE
from .sztvhu import SztvHuIE from .sztvhu import SztvHuIE
from .tagesschau import TagesschauIE from .tagesschau import TagesschauIE
from .tapely import TapelyIE
from .tass import TassIE
from .teachertube import ( from .teachertube import (
TeacherTubeIE, TeacherTubeIE,
TeacherTubeUserIE, TeacherTubeUserIE,
@ -351,15 +489,26 @@ from .teachingchannel import TeachingChannelIE
from .teamcoco import TeamcocoIE from .teamcoco import TeamcocoIE
from .techtalks import TechTalksIE from .techtalks import TechTalksIE
from .ted import TEDIE from .ted import TEDIE
from .telebruxelles import TeleBruxellesIE
from .telecinco import TelecincoIE
from .telemb import TeleMBIE from .telemb import TeleMBIE
from .teletask import TeleTaskIE
from .tenplay import TenPlayIE from .tenplay import TenPlayIE
from .testurl import TestURLIE from .testurl import TestURLIE
from .testtube import TestTubeIE
from .tf1 import TF1IE from .tf1 import TF1IE
from .theonion import TheOnionIE
from .theplatform import ThePlatformIE from .theplatform import ThePlatformIE
from .thesixtyone import TheSixtyOneIE
from .thisav import ThisAVIE from .thisav import ThisAVIE
from .tinypic import TinyPicIE from .tinypic import TinyPicIE
from .tlc import TlcIE, TlcDeIE from .tlc import TlcIE, TlcDeIE
from .tmz import TMZIE
from .tnaflix import TNAFlixIE from .tnaflix import TNAFlixIE
from .thvideo import (
THVideoIE,
THVideoPlaylistIE
)
from .toutv import TouTvIE from .toutv import TouTvIE
from .toypics import ToypicsUserIE, ToypicsIE from .toypics import ToypicsUserIE, ToypicsIE
from .traileraddict import TrailerAddictIE from .traileraddict import TrailerAddictIE
@ -368,16 +517,30 @@ from .trutube import TruTubeIE
from .tube8 import Tube8IE from .tube8 import Tube8IE
from .tudou import TudouIE from .tudou import TudouIE
from .tumblr import TumblrIE from .tumblr import TumblrIE
from .tunein import TuneInIE
from .turbo import TurboIE from .turbo import TurboIE
from .tutv import TutvIE from .tutv import TutvIE
from .tv4 import TV4IE
from .tvigle import TvigleIE from .tvigle import TvigleIE
from .tvp import TvpIE from .tvp import TvpIE, TvpSeriesIE
from .tvplay import TVPlayIE from .tvplay import TVPlayIE
from .tweakers import TweakersIE
from .twentyfourvideo import TwentyFourVideoIE
from .twitch import (
TwitchVideoIE,
TwitchChapterIE,
TwitchVodIE,
TwitchProfileIE,
TwitchPastBroadcastsIE,
TwitchBookmarksIE,
TwitchStreamIE,
)
from .ubu import UbuIE from .ubu import UbuIE
from .udemy import ( from .udemy import (
UdemyIE, UdemyIE,
UdemyCourseIE UdemyCourseIE
) )
from .ultimedia import UltimediaIE
from .unistra import UnistraIE from .unistra import UnistraIE
from .urort import UrortIE from .urort import UrortIE
from .ustream import UstreamIE, UstreamChannelIE from .ustream import UstreamIE, UstreamChannelIE
@ -388,22 +551,28 @@ from .vesti import VestiIE
from .vevo import VevoIE from .vevo import VevoIE
from .vgtv import VGTVIE from .vgtv import VGTVIE
from .vh1 import VH1IE from .vh1 import VH1IE
from .vice import ViceIE
from .viddler import ViddlerIE from .viddler import ViddlerIE
from .videobam import VideoBamIE from .videobam import VideoBamIE
from .videodetective import VideoDetectiveIE from .videodetective import VideoDetectiveIE
from .videolecturesnet import VideoLecturesNetIE from .videolecturesnet import VideoLecturesNetIE
from .videofyme import VideofyMeIE from .videofyme import VideofyMeIE
from .videomega import VideoMegaIE
from .videopremium import VideoPremiumIE from .videopremium import VideoPremiumIE
from .videott import VideoTtIE from .videott import VideoTtIE
from .videoweed import VideoWeedIE from .videoweed import VideoWeedIE
from .vidme import VidmeIE from .vidme import VidmeIE
from .vidzi import VidziIE
from .vier import VierIE, VierVideosIE
from .viewster import ViewsterIE
from .vimeo import ( from .vimeo import (
VimeoIE, VimeoIE,
VimeoChannelIE,
VimeoUserIE,
VimeoAlbumIE, VimeoAlbumIE,
VimeoChannelIE,
VimeoGroupsIE, VimeoGroupsIE,
VimeoLikesIE,
VimeoReviewIE, VimeoReviewIE,
VimeoUserIE,
VimeoWatchLaterIE, VimeoWatchLaterIE,
) )
from .vimple import VimpleIE from .vimple import VimpleIE
@ -412,12 +581,17 @@ from .vine import (
VineUserIE, VineUserIE,
) )
from .viki import VikiIE from .viki import VikiIE
from .vk import VKIE from .vk import (
VKIE,
VKUserVideosIE,
)
from .vodlocker import VodlockerIE from .vodlocker import VodlockerIE
from .vporn import VpornIE from .vporn import VpornIE
from .vrt import VRTIE
from .vube import VubeIE from .vube import VubeIE
from .vuclip import VuClipIE from .vuclip import VuClipIE
from .vulture import VultureIE from .vulture import VultureIE
from .walla import WallaIE
from .washingtonpost import WashingtonPostIE from .washingtonpost import WashingtonPostIE
from .wat import WatIE from .wat import WatIE
from .wayofthemaster import WayOfTheMasterIE from .wayofthemaster import WayOfTheMasterIE
@ -426,25 +600,38 @@ from .wdr import (
WDRMobileIE, WDRMobileIE,
WDRMausIE, WDRMausIE,
) )
from .webofstories import WebOfStoriesIE
from .weibo import WeiboIE from .weibo import WeiboIE
from .wimp import WimpIE from .wimp import WimpIE
from .wistia import WistiaIE from .wistia import WistiaIE
from .worldstarhiphop import WorldStarHipHopIE from .worldstarhiphop import WorldStarHipHopIE
from .wrzuta import WrzutaIE from .wrzuta import WrzutaIE
from .wsj import WSJIE
from .xbef import XBefIE from .xbef import XBefIE
from .xboxclips import XboxClipsIE from .xboxclips import XboxClipsIE
from .xhamster import XHamsterIE from .xhamster import XHamsterIE
from .xminus import XMinusIE
from .xnxx import XNXXIE from .xnxx import XNXXIE
from .xvideos import XVideosIE from .xvideos import XVideosIE
from .xtube import XTubeUserIE, XTubeIE from .xtube import XTubeUserIE, XTubeIE
from .xuite import XuiteIE
from .xxxymovies import XXXYMoviesIE
from .yahoo import ( from .yahoo import (
YahooIE, YahooIE,
YahooNewsIE,
YahooSearchIE, YahooSearchIE,
) )
from .yam import YamIE
from .yandexmusic import (
YandexMusicTrackIE,
YandexMusicAlbumIE,
YandexMusicPlaylistIE,
)
from .yesjapan import YesJapanIE
from .ynet import YnetIE
from .youjizz import YouJizzIE from .youjizz import YouJizzIE
from .youku import YoukuIE from .youku import YoukuIE
from .youporn import YouPornIE from .youporn import YouPornIE
from .yourupload import YourUploadIE
from .youtube import ( from .youtube import (
YoutubeIE, YoutubeIE,
YoutubeChannelIE, YoutubeChannelIE,
@ -457,14 +644,17 @@ from .youtube import (
YoutubeSearchURLIE, YoutubeSearchURLIE,
YoutubeShowIE, YoutubeShowIE,
YoutubeSubscriptionsIE, YoutubeSubscriptionsIE,
YoutubeTopListIE, YoutubeTruncatedIDIE,
YoutubeTruncatedURLIE, YoutubeTruncatedURLIE,
YoutubeUserIE, YoutubeUserIE,
YoutubeWatchLaterIE, YoutubeWatchLaterIE,
) )
from .zapiks import ZapiksIE
from .zdf import ZDFIE from .zdf import ZDFIE, ZDFChannelIE
from .zingmp3 import (
ZingMp3SongIE,
ZingMp3AlbumIE,
)
_ALL_CLASSES = [ _ALL_CLASSES = [
klass klass
@ -481,6 +671,17 @@ def gen_extractors():
return [klass() for klass in _ALL_CLASSES] return [klass() for klass in _ALL_CLASSES]
def list_extractors(age_limit):
"""
Return a list of extractors that are suitable for the given age,
sorted by extractor ID.
"""
return sorted(
filter(lambda ie: ie.is_suitable(age_limit), gen_extractors()),
key=lambda ie: ie.IE_NAME.lower())
def get_info_extractor(ie_name): def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name""" """Returns the info extractor class with the given ie_name"""
return globals()[ie_name+'IE'] return globals()[ie_name + 'IE']

13
youtube_dl/extractor/abc.py
View File

@ -11,19 +11,18 @@ class ABCIE(InfoExtractor):
_VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)' _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://www.abc.net.au/news/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716', 'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334',
'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742', 'md5': 'cb3dd03b18455a661071ee1e28344d9f',
'info_dict': { 'info_dict': {
'id': '5624716', 'id': '5868334',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor', 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone',
'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af', 'description': 'md5:809ad29c67a05f54eb41f2a105693a67',
}, },
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
urls_info_json = self._search_regex( urls_info_json = self._search_regex(

68
youtube_dl/extractor/abc7news.py Normal file
View File

@ -0,0 +1,68 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import parse_iso8601
class Abc7NewsIE(InfoExtractor):
_VALID_URL = r'https?://abc7news\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
'info_dict': {
'id': '472581',
'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
'ext': 'mp4',
'title': 'East Bay museum celebrates history of synthesized music',
'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': 1421123075,
'upload_date': '20150113',
'uploader': 'Jonathan Bloom',
},
'params': {
# m3u8 download
'skip_download': True,
},
},
{
'url': 'http://abc7news.com/472581',
'only_matching': True,
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
m3u8 = self._html_search_meta(
'contentURL', webpage, 'm3u8 url', fatal=True)
formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
self._sort_formats(formats)
title = self._og_search_title(webpage).strip()
description = self._og_search_description(webpage).strip()
thumbnail = self._og_search_thumbnail(webpage)
timestamp = parse_iso8601(self._search_regex(
r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
webpage, 'upload date', fatal=False))
uploader = self._search_regex(
r'rel="author">([^<]+)</a>',
webpage, 'uploader', default=None)
return {
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'formats': formats,
}

8
youtube_dl/extractor/academicearth.py
View File

@ -1,4 +1,5 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
@ -18,15 +19,14 @@ class AcademicEarthCourseIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url) playlist_id = self._match_id(url)
playlist_id = m.group('id')
webpage = self._download_webpage(url, playlist_id) webpage = self._download_webpage(url, playlist_id)
title = self._html_search_regex( title = self._html_search_regex(
r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, u'title') r'<h1 class="playlist-name"[^>]*?>(.*?)</h1>', webpage, 'title')
description = self._html_search_regex( description = self._html_search_regex(
r'<p class="excerpt"[^>]*?>(.*?)</p>', r'<p class="excerpt"[^>]*?>(.*?)</p>',
webpage, u'description', fatal=False) webpage, 'description', fatal=False)
urls = re.findall( urls = re.findall(
r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">', r'<li class="lecture-preview">\s*?<a target="_blank" href="([^"]+)">',
webpage) webpage)

14
youtube_dl/extractor/addanime.py
View File

@ -3,19 +3,19 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..compat import (
compat_HTTPError, compat_HTTPError,
compat_str, compat_str,
compat_urllib_parse, compat_urllib_parse,
compat_urllib_parse_urlparse, compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError, ExtractorError,
) )
class AddAnimeIE(InfoExtractor): class AddAnimeIE(InfoExtractor):
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<id>[\w_]+)(?:.*)'
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
_TEST = { _TEST = {
'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', 'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
'md5': '72954ea10bc979ab5e2eb288b21425a0', 'md5': '72954ea10bc979ab5e2eb288b21425a0',
@ -28,9 +28,9 @@ class AddAnimeIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url)
try: try:
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
except ExtractorError as ee: except ExtractorError as ee:
if not isinstance(ee.cause, compat_HTTPError) or \ if not isinstance(ee.cause, compat_HTTPError) or \
@ -48,7 +48,7 @@ class AddAnimeIE(InfoExtractor):
r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);', r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
redir_webpage) redir_webpage)
if av is None: if av is None:
raise ExtractorError(u'Cannot find redirect math task') raise ExtractorError('Cannot find redirect math task')
av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3)) av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
parsed_url = compat_urllib_parse_urlparse(url) parsed_url = compat_urllib_parse_urlparse(url)

71
youtube_dl/extractor/adobetv.py Normal file
View File

@ -0,0 +1,71 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
parse_duration,
unified_strdate,
str_to_int,
)
class AdobeTVIE(InfoExtractor):
_VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
_TEST = {
'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
'info_dict': {
'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
'ext': 'mp4',
'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
'thumbnail': 're:https?://.*\.jpg$',
'upload_date': '20110914',
'duration': 60,
'view_count': int,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player = self._parse_json(
self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
video_id)
title = player.get('title') or self._search_regex(
r'data-title="([^"]+)"', webpage, 'title')
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(
self._html_search_meta('datepublished', webpage, 'upload date'))
duration = parse_duration(
self._html_search_meta('duration', webpage, 'duration') or
self._search_regex(
r'Runtime:\s*(\d{2}:\d{2}:\d{2})',
webpage, 'duration', fatal=False))
view_count = str_to_int(self._search_regex(
r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
webpage, 'view count'))
formats = [{
'url': source['src'],
'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
'tbr': source.get('bitrate'),
} for source in player['sources']]
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
'formats': formats,
}

216
youtube_dl/extractor/adultswim.py
View File

@ -4,120 +4,170 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
xpath_text,
)
class AdultSwimIE(InfoExtractor): class AdultSwimIE(InfoExtractor):
_VALID_URL = r'https?://video\.adultswim\.com/(?P<path>.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<is_playlist>playlists/)?(?P<show_path>[^/]+)/(?P<episode_path>[^/?#]+)/?'
_TEST = {
'url': 'http://video.adultswim.com/rick-and-morty/close-rick-counters-of-the-rick-kind.html?x=y#title', _TESTS = [{
'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
'playlist': [ 'playlist': [
{ {
'md5': '4da359ec73b58df4575cd01a610ba5dc', 'md5': '247572debc75c7652f253c8daa51a14d',
'info_dict': { 'info_dict': {
'id': '8a250ba1450996e901453d7f02ca02f5', 'id': 'rQxZvXQ4ROaSOqq-or2Mow-0',
'ext': 'flv', 'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 1', 'title': 'Rick and Morty - Pilot Part 1',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
'uploader': 'Rick and Morty', },
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
}, },
{ {
'md5': 'ffbdf55af9331c509d95350bd0cc1819', 'md5': '77b0e037a4b20ec6b98671c4c379f48d',
'info_dict': { 'info_dict': {
'id': '8a250ba1450996e901453d7f4bd102f6', 'id': 'rQxZvXQ4ROaSOqq-or2Mow-3',
'ext': 'flv', 'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 2', 'title': 'Rick and Morty - Pilot Part 4',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', 'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
'uploader': 'Rick and Morty', },
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
}, },
],
'info_dict': {
'id': 'rQxZvXQ4ROaSOqq-or2Mow',
'title': 'Rick and Morty - Pilot',
'description': "Rick moves in with his daughter's family and establishes himself as a bad influence on his grandson, Morty. "
}
}, {
'url': 'http://www.adultswim.com/videos/playlists/american-parenting/putting-francine-out-of-business/',
'playlist': [
{ {
'md5': 'b92409635540304280b4b6c36bd14a0a', 'md5': '2eb5c06d0f9a1539da3718d897f13ec5',
'info_dict': { 'info_dict': {
'id': '8a250ba1450996e901453d7fa73c02f7', 'id': '-t8CamQlQ2aYZ49ItZCFog-0',
'ext': 'flv', 'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 3', 'title': 'American Dad - Putting Francine Out of Business',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?', 'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
'uploader': 'Rick and Morty', },
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
},
{
'md5': 'e8818891d60e47b29cd89d7b0278156d',
'info_dict': {
'id': '8a250ba1450996e901453d7fc8ba02f8',
'ext': 'flv',
'title': 'Rick and Morty Close Rick-Counters of the Rick Kind part 4',
'description': 'Rick has a run in with some old associates, resulting in a fallout with Morty. You got any chips, broh?',
'uploader': 'Rick and Morty',
'thumbnail': 'http://i.cdn.turner.com/asfix/repository/8a250ba13f865824013fc9db8b6b0400/thumbnail_267549017116827057.jpg'
}
} }
] ],
} 'info_dict': {
'id': '-t8CamQlQ2aYZ49ItZCFog',
'title': 'American Dad - Putting Francine Out of Business',
'description': 'Stan hatches a plan to get Francine out of the real estate business.Watch more American Dad on [adult swim].'
},
}, {
'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
'playlist': [
{
'md5': '3e346a2ab0087d687a05e1e7f3b3e529',
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ-0',
'ext': 'flv',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
},
}
],
'info_dict': {
'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
'description': 'Dr. Brule reports live from Wine Country with a special report on wines. \r\nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.\r\n\r\n',
},
}]
_video_extensions = { @staticmethod
'3500': 'flv', def find_video_info(collection, slug):
'640': 'mp4', for video in collection.get('videos'):
'150': 'mp4', if video.get('slug') == slug:
'ipad': 'm3u8', return video
'iphone': 'm3u8'
} @staticmethod
_video_dimensions = { def find_collection_by_linkURL(collections, linkURL):
'3500': (1280, 720), for collection in collections:
'640': (480, 270), if collection.get('linkURL') == linkURL:
'150': (320, 180) return collection
}
@staticmethod
def find_collection_containing_video(collections, slug):
for collection in collections:
for video in collection.get('videos'):
if video.get('slug') == slug:
return collection, video
return None, None
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_path = mobj.group('path') show_path = mobj.group('show_path')
episode_path = mobj.group('episode_path')
is_playlist = True if mobj.group('is_playlist') else False
webpage = self._download_webpage(url, video_path) webpage = self._download_webpage(url, episode_path)
episode_id = self._html_search_regex(
r'<link rel="video_src" href="http://i\.adultswim\.com/adultswim/adultswimtv/tools/swf/viralplayer.swf\?id=([0-9a-f]+?)"\s*/?\s*>',
webpage, 'episode_id')
title = self._og_search_title(webpage)
index_url = 'http://asfix.adultswim.com/asfix-svc/episodeSearch/getEpisodesByIDs?networkName=AS&ids=%s' % episode_id # Extract the value of `bootstrappedData` from the Javascript in the page.
idoc = self._download_xml(index_url, title, 'Downloading episode index', 'Unable to download episode index') bootstrapped_data = self._parse_json(self._search_regex(
r'var bootstrappedData = ({.*});', webpage, 'bootstraped data'), episode_path)
episode_el = idoc.find('.//episode') # Downloading videos from a /videos/playlist/ URL needs to be handled differently.
show_title = episode_el.attrib.get('collectionTitle') # NOTE: We are only downloading one video (the current one) not the playlist
episode_title = episode_el.attrib.get('title') if is_playlist:
thumbnail = episode_el.attrib.get('thumbnailUrl') collections = bootstrapped_data['playlists']['collections']
description = episode_el.find('./description').text.strip() collection = self.find_collection_by_linkURL(collections, show_path)
video_info = self.find_video_info(collection, episode_path)
show_title = video_info['showTitle']
segment_ids = [video_info['videoPlaybackID']]
else:
collections = bootstrapped_data['show']['collections']
collection, video_info = self.find_collection_containing_video(collections, episode_path)
# Video wasn't found in the collections, let's try `slugged_video`.
if video_info is None:
if bootstrapped_data.get('slugged_video', {}).get('slug') == episode_path:
video_info = bootstrapped_data['slugged_video']
else:
raise ExtractorError('Unable to find video info')
show = bootstrapped_data['show']
show_title = show['title']
segment_ids = [clip['videoPlaybackID'] for clip in video_info['clips']]
episode_id = video_info['id']
episode_title = video_info['title']
episode_description = video_info['description']
episode_duration = video_info.get('duration')
entries = [] entries = []
segment_els = episode_el.findall('./segments/segment') for part_num, segment_id in enumerate(segment_ids):
segment_url = 'http://www.adultswim.com/videos/api/v0/assets?id=%s&platform=mobile' % segment_id
for part_num, segment_el in enumerate(segment_els): segment_title = '%s - %s' % (show_title, episode_title)
segment_id = segment_el.attrib.get('id') if len(segment_ids) > 1:
segment_title = '%s %s part %d' % (show_title, episode_title, part_num + 1) segment_title += ' Part %d' % (part_num + 1)
thumbnail = segment_el.attrib.get('thumbnailUrl')
duration = segment_el.attrib.get('duration')
segment_url = 'http://asfix.adultswim.com/asfix-svc/episodeservices/getCvpPlaylist?networkName=AS&id=%s' % segment_id
idoc = self._download_xml( idoc = self._download_xml(
segment_url, segment_title, segment_url, segment_title,
'Downloading segment information', 'Unable to download segment information') 'Downloading segment information', 'Unable to download segment information')
segment_duration = float_or_none(
xpath_text(idoc, './/trt', 'segment duration').strip())
formats = [] formats = []
file_els = idoc.findall('.//files/file') file_els = idoc.findall('.//files/file')
for file_el in file_els: for file_el in file_els:
bitrate = file_el.attrib.get('bitrate') bitrate = file_el.attrib.get('bitrate')
type = file_el.attrib.get('type') ftype = file_el.attrib.get('type')
width, height = self._video_dimensions.get(bitrate, (None, None))
formats.append({ formats.append({
'format_id': '%s-%s' % (bitrate, type), 'format_id': '%s_%s' % (bitrate, ftype),
'url': file_el.text, 'url': file_el.text.strip(),
'ext': self._video_extensions.get(bitrate, 'mp4'),
# The bitrate may not be a number (for example: 'iphone') # The bitrate may not be a number (for example: 'iphone')
'tbr': int(bitrate) if bitrate.isdigit() else None, 'tbr': int(bitrate) if bitrate.isdigit() else None,
'height': height, 'quality': 1 if ftype == 'hd' else -1
'width': width
}) })
self._sort_formats(formats) self._sort_formats(formats)
@ -126,18 +176,16 @@ class AdultSwimIE(InfoExtractor):
'id': segment_id, 'id': segment_id,
'title': segment_title, 'title': segment_title,
'formats': formats, 'formats': formats,
'uploader': show_title, 'duration': segment_duration,
'thumbnail': thumbnail, 'description': episode_description
'duration': duration,
'description': description
}) })
return { return {
'_type': 'playlist', '_type': 'playlist',
'id': episode_id, 'id': episode_id,
'display_id': video_path, 'display_id': episode_path,
'entries': entries, 'entries': entries,
'title': '%s %s' % (show_title, episode_title), 'title': '%s - %s' % (show_title, episode_title),
'description': description, 'description': episode_description,
'thumbnail': thumbnail 'duration': episode_duration
} }

98
youtube_dl/extractor/aftenposten.py Normal file
View File

@ -0,0 +1,98 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_iso8601,
xpath_with_ns,
xpath_text,
find_xpath_attr,
)
class AftenpostenIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?aftenposten\.no/webtv/(?:#!/)?video/(?P<id>\d+)'
_TEST = {
'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
'md5': 'fd828cd29774a729bf4d4425fe192972',
'info_dict': {
'id': '21039',
'ext': 'mov',
'title': 'TRAILER: "Sweatshop" - I can´t take any more',
'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
'timestamp': 1416927969,
'upload_date': '20141125',
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_xml(
'http://frontend.xstream.dk/ap/feed/video/?platform=web&id=%s' % video_id, video_id)
NS_MAP = {
'atom': 'http://www.w3.org/2005/Atom',
'xt': 'http://xstream.dk/',
'media': 'http://search.yahoo.com/mrss/',
}
entry = data.find(xpath_with_ns('./atom:entry', NS_MAP))
title = xpath_text(
entry, xpath_with_ns('./atom:title', NS_MAP), 'title')
description = xpath_text(
entry, xpath_with_ns('./atom:summary', NS_MAP), 'description')
timestamp = parse_iso8601(xpath_text(
entry, xpath_with_ns('./atom:published', NS_MAP), 'upload date'))
formats = []
media_group = entry.find(xpath_with_ns('./media:group', NS_MAP))
for media_content in media_group.findall(xpath_with_ns('./media:content', NS_MAP)):
media_url = media_content.get('url')
if not media_url:
continue
tbr = int_or_none(media_content.get('bitrate'))
mobj = re.search(r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', media_url)
if mobj:
formats.append({
'url': mobj.group('url'),
'play_path': 'mp4:%s' % mobj.group('playpath'),
'app': mobj.group('app'),
'ext': 'flv',
'tbr': tbr,
'format_id': 'rtmp-%d' % tbr,
})
else:
formats.append({
'url': media_url,
'tbr': tbr,
})
self._sort_formats(formats)
link = find_xpath_attr(
entry, xpath_with_ns('./atom:link', NS_MAP), 'rel', 'original')
if link is not None:
formats.append({
'url': link.get('href'),
'format_id': link.get('rel'),
})
thumbnails = [{
'url': splash.get('url'),
'width': int_or_none(splash.get('width')),
'height': int_or_none(splash.get('height')),
} for splash in media_group.findall(xpath_with_ns('./xt:splash', NS_MAP))]
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'formats': formats,
'thumbnails': thumbnails,
}

6
youtube_dl/extractor/aftonbladet.py
View File

@ -1,8 +1,6 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
@ -21,9 +19,7 @@ class AftonbladetIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.search(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
# find internal video meta data # find internal video meta data

74
youtube_dl/extractor/airmozilla.py Normal file
View File

@ -0,0 +1,74 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601,
)
class AirMozillaIE(InfoExtractor):
_VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
_TEST = {
'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
'md5': '2e3e7486ba5d180e829d453875b9b8bf',
'info_dict': {
'id': '6x4q2w',
'ext': 'mp4',
'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+',
'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
'timestamp': 1422487800,
'upload_date': '20150128',
'location': 'SFO Commons',
'duration': 3780,
'view_count': int,
'categories': ['Main'],
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
metadata = self._parse_json(jwconfig, video_id)
formats = [{
'url': source['file'],
'ext': source['type'],
'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
'format': source['label'],
'height': int(source['label'].rstrip('p')),
} for source in metadata['playlist'][0]['sources']]
self._sort_formats(formats)
view_count = int_or_none(self._html_search_regex(
r'Views since archived: ([0-9]+)',
webpage, 'view count', fatal=False))
timestamp = parse_iso8601(self._html_search_regex(
r'<time datetime="(.*?)"', webpage, 'timestamp', fatal=False))
duration = parse_duration(self._search_regex(
r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
webpage, 'duration', fatal=False))
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'url': self._og_search_url(webpage),
'display_id': display_id,
'thumbnail': metadata['playlist'][0].get('image'),
'description': self._og_search_description(webpage),
'timestamp': timestamp,
'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
'duration': duration,
'view_count': view_count,
'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
}

35
youtube_dl/extractor/aljazeera.py Normal file
View File

@ -0,0 +1,35 @@
from __future__ import unicode_literals
from .common import InfoExtractor
class AlJazeeraIE(InfoExtractor):
_VALID_URL = r'http://www\.aljazeera\.com/programmes/.*?/(?P<id>[^/]+)\.html'
_TEST = {
'url': 'http://www.aljazeera.com/programmes/the-slum/2014/08/deliverance-201482883754237240.html',
'info_dict': {
'id': '3792260579001',
'ext': 'mp4',
'title': 'The Slum - Episode 1: Deliverance',
'description': 'As a birth attendant advocating for family planning, Remy is on the frontline of Tondo\'s battle with overcrowding.',
'uploader': 'Al Jazeera English',
},
'add_ie': ['Brightcove'],
}
def _real_extract(self, url):
program_name = self._match_id(url)
webpage = self._download_webpage(url, program_name)
brightcove_id = self._search_regex(
r'RenderPagesVideo\(\'(.+?)\'', webpage, 'brightcove id')
return {
'_type': 'url',
'url': (
'brightcove:'
'playerKey=AQ~~%2CAAAAmtVJIFk~%2CTVGOQ5ZTwJbeMWnq5d_H4MOM57xfzApc'
'&%40videoPlayer={0}'.format(brightcove_id)
),
'ie_key': 'Brightcove',
}

12
youtube_dl/extractor/allocine.py
View File

@ -5,15 +5,14 @@ import re
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str
from ..utils import ( from ..utils import (
compat_str,
qualities, qualities,
determine_ext,
) )
class AllocineIE(InfoExtractor): class AllocineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=)(?P<id>[0-9]+)(?:\.html)?' _VALID_URL = r'https?://(?:www\.)?allocine\.fr/(?P<typ>article|video|film)/(fichearticle_gen_carticle=|player_gen_cmedia=|fichefilm_gen_cfilm=|video-)(?P<id>[0-9]+)(?:\.html)?'
_TESTS = [{ _TESTS = [{
'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html', 'url': 'http://www.allocine.fr/article/fichearticle_gen_carticle=18635087.html',
@ -22,7 +21,7 @@ class AllocineIE(InfoExtractor):
'id': '19546517', 'id': '19546517',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Astérix - Le Domaine des Dieux Teaser VF', 'title': 'Astérix - Le Domaine des Dieux Teaser VF',
'description': 'md5:4a754271d9c6f16c72629a8a993ee884', 'description': 'md5:abcd09ce503c6560512c14ebfdb720d2',
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
}, },
}, { }, {
@ -45,6 +44,9 @@ class AllocineIE(InfoExtractor):
'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac', 'description': 'md5:71742e3a74b0d692c7fce0dd2017a4ac',
'thumbnail': 're:http://.*\.jpg', 'thumbnail': 're:http://.*\.jpg',
}, },
}, {
'url': 'http://www.allocine.fr/video/video-19550147/',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -75,9 +77,7 @@ class AllocineIE(InfoExtractor):
'format_id': format_id, 'format_id': format_id,
'quality': quality(format_id), 'quality': quality(format_id),
'url': v, 'url': v,
'ext': determine_ext(v),
}) })
self._sort_formats(formats) self._sort_formats(formats)
return { return {

77
youtube_dl/extractor/alphaporno.py Normal file
View File

@ -0,0 +1,77 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
parse_duration,
parse_filesize,
int_or_none,
)
class AlphaPornoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
_TEST = {
'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
'info_dict': {
'id': '258807',
'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
'ext': 'mp4',
'title': 'Sensual striptease porn with Samantha Alexandra',
'thumbnail': 're:https?://.*\.jpg$',
'timestamp': 1418694611,
'upload_date': '20141216',
'duration': 387,
'filesize_approx': 54120000,
'tbr': 1145,
'categories': list,
'age_limit': 18,
}
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_regex(
r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
video_url = self._search_regex(
r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
ext = self._html_search_meta(
'encodingFormat', webpage, 'ext', default='.mp4')[1:]
title = self._search_regex(
[r'<meta content="([^"]+)" itemprop="description">',
r'class="title" itemprop="name">([^<]+)<'],
webpage, 'title')
thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
timestamp = parse_iso8601(self._html_search_meta(
'uploadDate', webpage, 'upload date'))
duration = parse_duration(self._html_search_meta(
'duration', webpage, 'duration'))
filesize_approx = parse_filesize(self._html_search_meta(
'contentSize', webpage, 'file size'))
bitrate = int_or_none(self._html_search_meta(
'bitrate', webpage, 'bitrate'))
categories = self._html_search_meta(
'keywords', webpage, 'categories', default='').split(',')
age_limit = self._rta_search(webpage)
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'filesize_approx': filesize_approx,
'tbr': bitrate,
'categories': categories,
'age_limit': age_limit,
}

4
youtube_dl/extractor/anysex.py
View File

@ -35,7 +35,7 @@ class AnySexIE(InfoExtractor):
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title') title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
description = self._html_search_regex( description = self._html_search_regex(
r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False) r'<div class="description"[^>]*>([^<]+)</div>', webpage, 'description', fatal=False)
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False)
@ -43,7 +43,7 @@ class AnySexIE(InfoExtractor):
r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage) r'<a href="http://anysex\.com/categories/[^"]+" title="[^"]*">([^<]+)</a>', webpage)
duration = parse_duration(self._search_regex( duration = parse_duration(self._search_regex(
r'<b>Duration:</b> (\d+:\d+)', webpage, 'duration', fatal=False)) r'<b>Duration:</b> (?:<q itemprop="duration">)?(\d+:\d+)', webpage, 'duration', fatal=False))
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False)) r'<b>Views:</b> (\d+)', webpage, 'view count', fatal=False))

48
youtube_dl/extractor/aol.py
View File

@ -3,7 +3,6 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from .fivemin import FiveMinIE
class AolIE(InfoExtractor): class AolIE(InfoExtractor):
@ -42,31 +41,30 @@ class AolIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
playlist_id = mobj.group('playlist_id') playlist_id = mobj.group('playlist_id')
if playlist_id and not self._downloader.params.get('noplaylist'): if not playlist_id or self._downloader.params.get('noplaylist'):
self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) return self.url_result('5min:%s' % video_id)
webpage = self._download_webpage(url, playlist_id) self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
title = self._html_search_regex(
r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
playlist_html = self._search_regex(
r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
'playlist HTML')
entries = [{
'_type': 'url',
'url': 'aol-video:%s' % m.group('id'),
'ie_key': 'Aol',
} for m in re.finditer(
r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
playlist_html)]
return { webpage = self._download_webpage(url, playlist_id)
'_type': 'playlist', title = self._html_search_regex(
'id': playlist_id, r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
'display_id': mobj.group('playlist_display_id'), playlist_html = self._search_regex(
'title': title, r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
'entries': entries, 'playlist HTML')
} entries = [{
'_type': 'url',
'url': 'aol-video:%s' % m.group('id'),
'ie_key': 'Aol',
} for m in re.finditer(
r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
playlist_html)]
return FiveMinIE._build_result(video_id) return {
'_type': 'playlist',
'id': playlist_id,
'display_id': mobj.group('playlist_display_id'),
'title': title,
'entries': entries,
}

19
youtube_dl/extractor/aparat.py
View File

@ -1,5 +1,4 @@
#coding: utf-8 # coding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
@ -21,13 +20,13 @@ class AparatIE(InfoExtractor):
'id': 'wP8On', 'id': 'wP8On',
'ext': 'mp4', 'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت', 'title': 'تیم گلکسی 11 - زومیت',
'age_limit': 0,
}, },
# 'skip': 'Extremely unreliable', # 'skip': 'Extremely unreliable',
} }
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = m.group('id')
# Note: There is an easier-to-parse configuration at # Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id # http://www.aparat.com/video/video/config/videohash/%video_id
@ -36,19 +35,20 @@ class AparatIE(InfoExtractor):
video_id + '/vt/frame') video_id + '/vt/frame')
webpage = self._download_webpage(embed_url, video_id) webpage = self._download_webpage(embed_url, video_id)
video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage) video_urls = [video_url.replace('\\/', '/') for video_url in re.findall(
r'(?:fileList\[[0-9]+\]\s*=|"file"\s*:)\s*"([^"]+)"', webpage)]
for i, video_url in enumerate(video_urls): for i, video_url in enumerate(video_urls):
req = HEADRequest(video_url) req = HEADRequest(video_url)
res = self._request_webpage( res = self._request_webpage(
req, video_id, note=u'Testing video URL %d' % i, errnote=False) req, video_id, note='Testing video URL %d' % i, errnote=False)
if res: if res:
break break
else: else:
raise ExtractorError(u'No working video URLs found') raise ExtractorError('No working video URLs found')
title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title') title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, 'title')
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False) r'image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False)
return { return {
'id': video_id, 'id': video_id,
@ -56,4 +56,5 @@ class AparatIE(InfoExtractor):
'url': video_url, 'url': video_url,
'ext': 'mp4', 'ext': 'mp4',
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'age_limit': self._family_friendly_search(webpage),
} }

25
youtube_dl/extractor/appletrailers.py
View File

@ -4,16 +4,19 @@ import re
import json import json
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import ( from ..utils import (
compat_urlparse,
int_or_none, int_or_none,
) )
class AppleTrailersIE(InfoExtractor): class AppleTrailersIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)' _VALID_URL = r'https?://(?:www\.)?trailers\.apple\.com/(?:trailers|ca)/(?P<company>[^/]+)/(?P<movie>[^/]+)'
_TEST = { _TESTS = [{
"url": "http://trailers.apple.com/trailers/wb/manofsteel/", "url": "http://trailers.apple.com/trailers/wb/manofsteel/",
'info_dict': {
'id': 'manofsteel',
},
"playlist": [ "playlist": [
{ {
"md5": "d97a8e575432dbcb81b7c3acb741f8a8", "md5": "d97a8e575432dbcb81b7c3acb741f8a8",
@ -60,7 +63,10 @@ class AppleTrailersIE(InfoExtractor):
}, },
}, },
] ]
} }, {
'url': 'http://trailers.apple.com/ca/metropole/autrui/',
'only_matching': True,
}]
_JSON_RE = r'iTunes.playURL\((.*?)\);' _JSON_RE = r'iTunes.playURL\((.*?)\);'
@ -70,15 +76,17 @@ class AppleTrailersIE(InfoExtractor):
uploader_id = mobj.group('company') uploader_id = mobj.group('company')
playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc') playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
def fix_html(s): def fix_html(s):
s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s) s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s) s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
# The ' in the onClick attributes are not escaped, it couldn't be parsed # The ' in the onClick attributes are not escaped, it couldn't be parsed
# like: http://trailers.apple.com/trailers/wb/gravity/ # like: http://trailers.apple.com/trailers/wb/gravity/
def _clean_json(m): def _clean_json(m):
return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;') return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
s = re.sub(self._JSON_RE, _clean_json, s) s = re.sub(self._JSON_RE, _clean_json, s)
s = '<html>' + s + u'</html>' s = '<html>%s</html>' % s
return s return s
doc = self._download_xml(playlist_url, movie, transform_source=fix_html) doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
@ -86,7 +94,7 @@ class AppleTrailersIE(InfoExtractor):
for li in doc.findall('./div/ul/li'): for li in doc.findall('./div/ul/li'):
on_click = li.find('.//a').attrib['onClick'] on_click = li.find('.//a').attrib['onClick']
trailer_info_json = self._search_regex(self._JSON_RE, trailer_info_json = self._search_regex(self._JSON_RE,
on_click, 'trailer info') on_click, 'trailer info')
trailer_info = json.loads(trailer_info_json) trailer_info = json.loads(trailer_info_json)
title = trailer_info['title'] title = trailer_info['title']
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower() video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
@ -120,14 +128,15 @@ class AppleTrailersIE(InfoExtractor):
playlist.append({ playlist.append({
'_type': 'video', '_type': 'video',
'id': video_id, 'id': video_id,
'title': title,
'formats': formats, 'formats': formats,
'title': title, 'title': title,
'duration': duration, 'duration': duration,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'upload_date': upload_date, 'upload_date': upload_date,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'user_agent': 'QuickTime compatible (youtube-dl)', 'http_headers': {
'User-Agent': 'QuickTime compatible (youtube-dl)',
},
}) })
return { return {

52
youtube_dl/extractor/archiveorg.py
View File

@ -1,42 +1,48 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import unified_strdate
unified_strdate,
)
class ArchiveOrgIE(InfoExtractor): class ArchiveOrgIE(InfoExtractor):
IE_NAME = 'archive.org' IE_NAME = 'archive.org'
IE_DESC = 'archive.org videos' IE_DESC = 'archive.org videos'
_VALID_URL = r'(?:https?://)?(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$' _VALID_URL = r'https?://(?:www\.)?archive\.org/details/(?P<id>[^?/]+)(?:[?].*)?$'
_TEST = { _TESTS = [{
"url": "http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect", 'url': 'http://archive.org/details/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
'file': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.ogv',
'md5': '8af1d4cf447933ed3c7f4871162602db', 'md5': '8af1d4cf447933ed3c7f4871162602db',
'info_dict': { 'info_dict': {
"title": "1968 Demo - FJCC Conference Presentation Reel #1", 'id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect',
"description": "Reel 1 of 3: Also known as the \"Mother of All Demos\", Doug Engelbart's presentation at the Fall Joint Computer Conference in San Francisco, December 9, 1968 titled \"A Research Center for Augmenting Human Intellect.\" For this presentation, Doug and his team astonished the audience by not only relating their research, but demonstrating it live. This was the debut of the mouse, interactive computing, hypermedia, computer supported software engineering, video teleconferencing, etc. See also <a href=\"http://dougengelbart.org/firsts/dougs-1968-demo.html\" rel=\"nofollow\">Doug's 1968 Demo page</a> for more background, highlights, links, and the detailed paper published in this conference proceedings. Filmed on 3 reels: Reel 1 | <a href=\"http://www.archive.org/details/XD300-24_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 2</a> | <a href=\"http://www.archive.org/details/XD300-25_68HighlightsAResearchCntAugHumanIntellect\" rel=\"nofollow\">Reel 3</a>", 'ext': 'ogv',
"upload_date": "19681210", 'title': '1968 Demo - FJCC Conference Presentation Reel #1',
"uploader": "SRI International" 'description': 'md5:1780b464abaca9991d8968c877bb53ed',
'upload_date': '19681210',
'uploader': 'SRI International'
} }
} }, {
'url': 'https://archive.org/details/Cops1922',
'md5': '18f2a19e6d89af8425671da1cf3d4e04',
'info_dict': {
'id': 'Cops1922',
'ext': 'ogv',
'title': 'Buster Keaton\'s "Cops" (1922)',
'description': 'md5:70f72ee70882f713d4578725461ffcc3',
}
}]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
json_url = url + ('?' if '?' in url else '&') + 'output=json' json_url = url + ('?' if '?' in url else '&') + 'output=json'
json_data = self._download_webpage(json_url, video_id) data = self._download_json(json_url, video_id)
data = json.loads(json_data)
title = data['metadata']['title'][0] def get_optional(data_dict, field):
description = data['metadata']['description'][0] return data_dict['metadata'].get(field, [None])[0]
uploader = data['metadata']['creator'][0]
upload_date = unified_strdate(data['metadata']['date'][0]) title = get_optional(data, 'title')
description = get_optional(data, 'description')
uploader = get_optional(data, 'creator')
upload_date = unified_strdate(get_optional(data, 'date'))
formats = [ formats = [
{ {

21
youtube_dl/extractor/ard.py
View File

@ -4,16 +4,16 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from .generic import GenericIE
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
ExtractorError, ExtractorError,
qualities, qualities,
compat_urllib_parse_urlparse,
compat_urllib_parse,
int_or_none, int_or_none,
parse_duration, parse_duration,
unified_strdate, unified_strdate,
xpath_text, xpath_text,
parse_xml,
) )
@ -23,13 +23,7 @@ class ARDMediathekIE(InfoExtractor):
_TESTS = [{ _TESTS = [{
'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
'file': '22429276.mp4', 'only_matching': True,
'md5': '469751912f1de0816a9fc9df8336476c',
'info_dict': {
'title': 'Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?',
'description': 'Das Erste Mediathek [ARD]: Vertrauen ist gut, Spionieren ist besser - Geht so deutsch-amerikanische Freundschaft?, Anne Will, Über die Spionage-Affäre diskutieren Clemens Binninger, Katrin Göring-Eckardt, Georg Mascolo, Andrew B. Denison und Constanze Kurz.. Das Video zur Sendung Anne Will am Mittwoch, 16.07.2014',
},
'skip': 'Blocked outside of Germany',
}, { }, {
'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916', 'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
'info_dict': { 'info_dict': {
@ -56,6 +50,14 @@ class ARDMediathekIE(InfoExtractor):
if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage: if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage:
raise ExtractorError('Video %s is no longer available' % video_id, expected=True) raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
if 'Diese Sendung ist für Jugendliche unter 12 Jahren nicht geeignet. Der Clip ist deshalb nur von 20 bis 6 Uhr verfügbar.' in webpage:
raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
if re.search(r'[\?&]rss($|[=&])', url):
doc = parse_xml(webpage)
if doc.tag == 'rss':
return GenericIE()._extract_rss(url, video_id, doc)
title = self._html_search_regex( title = self._html_search_regex(
[r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>', [r'<h1(?:\s+class="boxTopHeadline")?>(.*?)</h1>',
r'<meta name="dcterms.title" content="(.*?)"/>', r'<meta name="dcterms.title" content="(.*?)"/>',
@ -187,4 +189,3 @@ class ARDIE(InfoExtractor):
'upload_date': upload_date, 'upload_date': upload_date,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
} }

140
youtube_dl/extractor/arte.py
View File

@ -5,16 +5,15 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
find_xpath_attr, find_xpath_attr,
unified_strdate, unified_strdate,
determine_ext,
get_element_by_id, get_element_by_id,
compat_str,
get_element_by_attribute, get_element_by_attribute,
int_or_none,
qualities,
) )
# There are different sources of video in arte.tv, the extraction process # There are different sources of video in arte.tv, the extraction process
# is different for each one. The videos usually expire in 7 days, so we can't # is different for each one. The videos usually expire in 7 days, so we can't
# add tests. # add tests.
@ -38,7 +37,7 @@ class ArteTvIE(InfoExtractor):
config_xml_url, video_id, note='Downloading configuration') config_xml_url, video_id, note='Downloading configuration')
formats = [{ formats = [{
'forma_id': q.attrib['quality'], 'format_id': q.attrib['quality'],
# The playpath starts at 'mp4:', if we don't manually # The playpath starts at 'mp4:', if we don't manually
# split the url, rtmpdump will incorrectly parse them # split the url, rtmpdump will incorrectly parse them
'url': q.text.split('mp4:', 1)[0], 'url': q.text.split('mp4:', 1)[0],
@ -86,92 +85,71 @@ class ArteTVPlus7IE(InfoExtractor):
info = self._download_json(json_url, video_id) info = self._download_json(json_url, video_id)
player_info = info['videoJsonPlayer'] player_info = info['videoJsonPlayer']
upload_date_str = player_info.get('shootingDate')
if not upload_date_str:
upload_date_str = player_info.get('VDA', '').split(' ')[0]
title = player_info['VTI'].strip()
subtitle = player_info.get('VSU', '').strip()
if subtitle:
title += ' - %s' % subtitle
info_dict = { info_dict = {
'id': player_info['VID'], 'id': player_info['VID'],
'title': player_info['VTI'], 'title': title,
'description': player_info.get('VDE'), 'description': player_info.get('VDE'),
'upload_date': unified_strdate(player_info.get('VDA', '').split(' ')[0]), 'upload_date': unified_strdate(upload_date_str),
'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'), 'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
} }
qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ'])
all_formats = player_info['VSR'].values() formats = []
# Some formats use the m3u8 protocol for format_id, format_dict in player_info['VSR'].items():
all_formats = list(filter(lambda f: f.get('videoFormat') != 'M3U8', all_formats)) f = dict(format_dict)
def _match_lang(f): versionCode = f.get('versionCode')
if f.get('versionCode') is None:
return True
# Return true if that format is in the language of the url
if lang == 'fr':
l = 'F'
elif lang == 'de':
l = 'A'
else:
l = lang
regexes = [r'VO?%s' % l, r'VO?.-ST%s' % l]
return any(re.match(r, f['versionCode']) for r in regexes)
# Some formats may not be in the same language as the url
# TODO: Might want not to drop videos that does not match requested language
# but to process those formats with lower precedence
formats = filter(_match_lang, all_formats)
formats = list(formats) # in python3 filter returns an iterator
if not formats:
# Some videos are only available in the 'Originalversion'
# they aren't tagged as being in French or German
# Sometimes there are neither videos of requested lang code
# nor original version videos available
# For such cases we just take all_formats as is
formats = all_formats
if not formats:
raise ExtractorError('The formats list is empty')
if re.match(r'[A-Z]Q', formats[0]['quality']) is not None: langcode = {
def sort_key(f): 'fr': 'F',
return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality']) 'de': 'A',
else: }.get(lang, lang)
def sort_key(f): lang_rexs = [r'VO?%s' % langcode, r'VO?.-ST%s' % langcode]
versionCode = f.get('versionCode') lang_pref = (
if versionCode is None: None if versionCode is None else (
versionCode = '' 10 if any(re.match(r, versionCode) for r in lang_rexs)
return ( else -10))
# Sort first by quality source_pref = 0
int(f.get('height', -1)), if versionCode is not None:
int(f.get('bitrate', -1)), # The original version with subtitles has lower relevance
# The original version with subtitles has lower relevance if re.match(r'VO-ST(F|A)', versionCode):
re.match(r'VO-ST(F|A)', versionCode) is None, source_pref -= 10
# The version with sourds/mal subtitles has also lower relevance # The version with sourds/mal subtitles has also lower relevance
re.match(r'VO?(F|A)-STM\1', versionCode) is None, elif re.match(r'VO?(F|A)-STM\1', versionCode):
# Prefer http downloads over m3u8 source_pref -= 9
0 if f['url'].endswith('m3u8') else 1, format = {
)
formats = sorted(formats, key=sort_key)
def _format(format_info):
quality = ''
height = format_info.get('height')
if height is not None:
quality = compat_str(height)
bitrate = format_info.get('bitrate')
if bitrate is not None:
quality += '-%d' % bitrate
if format_info.get('versionCode') is not None:
format_id = '%s-%s' % (quality, format_info['versionCode'])
else:
format_id = quality
info = {
'format_id': format_id, 'format_id': format_id,
'format_note': format_info.get('versionLibelle'), 'preference': -10 if f.get('videoFormat') == 'M3U8' else None,
'width': format_info.get('width'), 'language_preference': lang_pref,
'height': height, 'format_note': '%s, %s' % (f.get('versionCode'), f.get('versionLibelle')),
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
'tbr': int_or_none(f.get('bitrate')),
'quality': qfunc(f.get('quality')),
'source_preference': source_pref,
} }
if format_info['mediaType'] == 'rtmp':
info['url'] = format_info['streamer']
info['play_path'] = 'mp4:' + format_info['url']
info['ext'] = 'flv'
else:
info['url'] = format_info['url']
info['ext'] = determine_ext(info['url'])
return info
info_dict['formats'] = [_format(f) for f in formats]
if f.get('mediaType') == 'rtmp':
format['url'] = f['streamer']
format['play_path'] = 'mp4:' + f['url']
format['ext'] = 'flv'
else:
format['url'] = f['url']
formats.append(format)
self._check_formats(formats, video_id)
self._sort_formats(formats)
info_dict['formats'] = formats
return info_dict return info_dict

163
youtube_dl/extractor/atresplayer.py Normal file
View File

@ -0,0 +1,163 @@
from __future__ import unicode_literals
import time
import hmac
from .common import InfoExtractor
from ..compat import (
compat_str,
compat_urllib_parse,
compat_urllib_request,
)
from ..utils import (
int_or_none,
float_or_none,
xpath_text,
ExtractorError,
)
class AtresPlayerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P<id>.+?)_\d+\.html'
_NETRC_MACHINE = 'atresplayer'
_TESTS = [
{
'url': 'http://www.atresplayer.com/television/programas/el-club-de-la-comedia/temporada-4/capitulo-10-especial-solidario-nochebuena_2014122100174.html',
'md5': 'efd56753cda1bb64df52a3074f62e38a',
'info_dict': {
'id': 'capitulo-10-especial-solidario-nochebuena',
'ext': 'mp4',
'title': 'Especial Solidario de Nochebuena',
'description': 'md5:e2d52ff12214fa937107d21064075bf1',
'duration': 5527.6,
'thumbnail': 're:^https?://.*\.jpg$',
},
},
{
'url': 'http://www.atresplayer.com/television/series/el-secreto-de-puente-viejo/el-chico-de-los-tres-lunares/capitulo-977-29-12-14_2014122400174.html',
'only_matching': True,
},
]
_USER_AGENT = 'Dalvik/1.6.0 (Linux; U; Android 4.3; GT-I9300 Build/JSS15J'
_MAGIC = 'QWtMLXs414Yo+c#_+Q#K@NN)'
_TIMESTAMP_SHIFT = 30000
_TIME_API_URL = 'http://servicios.atresplayer.com/api/admin/time.json'
_URL_VIDEO_TEMPLATE = 'https://servicios.atresplayer.com/api/urlVideo/{1}/{0}/{1}|{2}|{3}.json'
_PLAYER_URL_TEMPLATE = 'https://servicios.atresplayer.com/episode/getplayer.json?episodePk=%s'
_EPISODE_URL_TEMPLATE = 'http://www.atresplayer.com/episodexml/%s'
_LOGIN_URL = 'https://servicios.atresplayer.com/j_spring_security_check'
def _real_initialize(self):
self._login()
def _login(self):
(username, password) = self._get_login_info()
if username is None:
return
login_form = {
'j_username': username,
'j_password': password,
}
request = compat_urllib_request.Request(
self._LOGIN_URL, compat_urllib_parse.urlencode(login_form).encode('utf-8'))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
response = self._download_webpage(
request, None, 'Logging in as %s' % username)
error = self._html_search_regex(
r'(?s)<ul class="list_error">(.+?)</ul>', response, 'error', default=None)
if error:
raise ExtractorError(
'Unable to login: %s' % error, expected=True)
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
episode_id = self._search_regex(
r'episode="([^"]+)"', webpage, 'episode id')
timestamp = int_or_none(self._download_webpage(
self._TIME_API_URL,
video_id, 'Downloading timestamp', fatal=False), 1000, time.time())
timestamp_shifted = compat_str(timestamp + self._TIMESTAMP_SHIFT)
token = hmac.new(
self._MAGIC.encode('ascii'),
(episode_id + timestamp_shifted).encode('utf-8')
).hexdigest()
formats = []
for fmt in ['windows', 'android_tablet']:
request = compat_urllib_request.Request(
self._URL_VIDEO_TEMPLATE.format(fmt, episode_id, timestamp_shifted, token))
request.add_header('User-Agent', self._USER_AGENT)
fmt_json = self._download_json(
request, video_id, 'Downloading %s video JSON' % fmt)
result = fmt_json.get('resultDes')
if result.lower() != 'ok':
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, result), expected=True)
for format_id, video_url in fmt_json['resultObject'].items():
if format_id == 'token' or not video_url.startswith('http'):
continue
if video_url.endswith('/Manifest'):
if 'geodeswowsmpra3player' in video_url:
f4m_path = video_url.split('smil:', 1)[-1].split('free_', 1)[0]
f4m_url = 'http://drg.antena3.com/{0}hds/es/sd.f4m'.format(f4m_path)
# this videos are protected by DRM, the f4m downloader doesn't support them
continue
else:
f4m_url = video_url[:-9] + '/manifest.f4m'
formats.extend(self._extract_f4m_formats(f4m_url, video_id))
else:
formats.append({
'url': video_url,
'format_id': 'android-%s' % format_id,
'preference': 1,
})
self._sort_formats(formats)
player = self._download_json(
self._PLAYER_URL_TEMPLATE % episode_id,
episode_id)
path_data = player.get('pathData')
episode = self._download_xml(
self._EPISODE_URL_TEMPLATE % path_data,
video_id, 'Downloading episode XML')
duration = float_or_none(xpath_text(
episode, './media/asset/info/technical/contentDuration', 'duration'))
art = episode.find('./media/asset/info/art')
title = xpath_text(art, './name', 'title')
description = xpath_text(art, './description', 'description')
thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail')
subtitles = {}
subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle')
if subtitle_url:
subtitles['es'] = [{
'ext': 'srt',
'url': subtitle_url,
}]
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}

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