diff --git a/.gitignore b/.gitignore index e44977ca3..86312d4e4 100644 --- a/.gitignore +++ b/.gitignore @@ -30,3 +30,4 @@ updates_key.pem *.swp test/testdata .tox +youtube-dl.zsh diff --git a/AUTHORS b/AUTHORS new file mode 100644 index 000000000..d4b0b75fa --- /dev/null +++ b/AUTHORS @@ -0,0 +1,90 @@ +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 diff --git a/Makefile b/Makefile index 6272b826c..3e1debc7e 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ -all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.fish +all: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish 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 cleanall: clean rm -f youtube-dl youtube-dl.exe @@ -9,6 +9,7 @@ cleanall: clean PREFIX ?= /usr/local BINDIR ?= $(PREFIX)/bin MANDIR ?= $(PREFIX)/man +SHAREDIR ?= $(PREFIX)/share PYTHON ?= /usr/bin/env python # set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local @@ -22,13 +23,15 @@ else 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 -m 755 youtube-dl $(DESTDIR)$(BINDIR) install -d $(DESTDIR)$(MANDIR)/man1 install -m 644 youtube-dl.1 $(DESTDIR)$(MANDIR)/man1 install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d 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 -m 644 youtube-dl.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/youtube-dl.fish @@ -38,7 +41,7 @@ test: 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 pypi-files: youtube-dl.bash-completion README.txt youtube-dl.1 youtube-dl.fish @@ -66,12 +69,17 @@ youtube-dl.bash-completion: youtube_dl/*.py youtube_dl/*/*.py devscripts/bash-co 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 python devscripts/fish-completion.py 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 \ --exclude '*.DS_Store' \ --exclude '*.kate-swp' \ @@ -86,5 +94,5 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash- bin devscripts test youtube_dl docs \ LICENSE README.md README.txt \ 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 diff --git a/README.md b/README.md index 5cc959ac5..d6e7ff902 100644 --- a/README.md +++ b/README.md @@ -30,7 +30,7 @@ Alternatively, refer to the developer instructions below for how to check out an # DESCRIPTION **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 -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, which means you can modify it, redistribute it or use it however you like. @@ -69,6 +69,8 @@ which means you can modify it, redistribute it or use it however you like. configuration in ~/.config/youtube-dl.conf (%APPDATA%/youtube-dl/config.txt on Windows) + --flat-playlist Do not extract the videos of a playlist, + only list them. ## Video Selection: --playlist-start NUMBER playlist video to start at (default is 1) @@ -91,7 +93,8 @@ which means you can modify it, redistribute it or use it however you like. COUNT views --max-views COUNT Do not download any videos with more than COUNT views - --no-playlist download only the currently playing video + --no-playlist If the URL refers to a video and a + playlist, download only the video. --age-limit YEARS download only videos suitable for the given age --download-archive FILE Download only videos not listed in the @@ -99,8 +102,6 @@ which means you can modify it, redistribute it or use it however you like. downloaded videos in it. --include-ads Download advertisements as well (experimental) - --youtube-include-dash-manifest Try to download the DASH manifest on - YouTube videos (experimental) ## Download Options: -r, --rate-limit LIMIT maximum download rate in bytes per second @@ -131,17 +132,19 @@ which means you can modify it, redistribute it or use it however you like. %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the - video id, %(playlist)s for the playlist the + video id, %(playlist_title)s, + %(playlist_id)s, or %(playlist)s (=title if + present, ID otherwise) 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 + position in the playlist. %(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' . + format. %% for a literal percent. Use - to + output to stdout. Can also be used to + download to a different directory, for + example with -o '/my/downloads/%(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 @@ -158,7 +161,8 @@ which means you can modify it, redistribute it or use it however you like. downloads if possible. --no-continue do not resume partially downloaded files (restart from beginning) - --no-part do not use .part files + --no-part do not use .part files - write directly + into output file --no-mtime do not use the Last-modified header to set the file modification time --write-description write video description to a .description @@ -198,6 +202,10 @@ which means you can modify it, redistribute it or use it however you like. -j, --dump-json simulate, quiet but print JSON information. See --output for a description of available keys. + -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 information in a single line. --newline output progress bar as new lines --no-progress do not print progress bar --console-title display progress in console titlebar @@ -216,7 +224,7 @@ which means you can modify it, redistribute it or use it however you like. information about the video. (Currently supported only for YouTube) --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 --add-header FIELD:VALUE specify a custom HTTP header and its value, separated by a colon ':'. You can use this @@ -227,17 +235,27 @@ which means you can modify it, redistribute it or use it however you like. ## Video Format Options: -f, --format FORMAT video format code, specify the order of - preference using slashes: "-f 22/17/18". - "-f mp4" and "-f flv" are also supported. - You can also use the special names "best", - "bestvideo", "bestaudio", "worst", - "worstvideo" and "worstaudio". By default, - youtube-dl will pick the best quality. + preference using slashes: -f 22/17/18 . -f + mp4 , -f m4a and -f flv are also + supported. You can also use the special + names "best", "bestvideo", "bestaudio", + "worst", "worstvideo" and "worstaudio". 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 + (requires ffmpeg or + avconv), for example -f + bestvideo+bestaudio. --all-formats download all available video formats --prefer-free-formats prefer free video formats unless a specific one is requested --max-quality FORMAT highest quality format to download -F, --list-formats list all available formats + --youtube-skip-dash-manifest Do not download the DASH manifest on + YouTube videos ## Subtitle Options: --write-sub write subtitle file @@ -253,7 +271,7 @@ which means you can modify it, redistribute it or use it however you like. language tags like 'en,pt' ## Authentication Options: - -u, --username USERNAME account username + -u, --username USERNAME login with this account ID -p, --password PASSWORD account password -2, --twofactor TWOFACTOR two-factor auth code -n, --netrc use .netrc authentication data @@ -264,7 +282,7 @@ which means you can modify it, redistribute it or use it however you like. (requires ffmpeg or avconv and ffprobe or avprobe) --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", - "opus", or "wav"; best by default + "opus", or "wav"; "best" by default --audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like @@ -345,21 +363,34 @@ $ youtube-dl --dateafter 20000101 --datebefore 20091231 # 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 chmod a+x /usr/local/bin/youtube-dl 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`? 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`. @@ -439,8 +470,6 @@ If you want to add support for a new site, you can follow this quick list (assum # coding: utf-8 from __future__ import unicode_literals - import re - from .common import InfoExtractor @@ -448,7 +477,7 @@ 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[0-9]+)' _TEST = { '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': { 'id': '42', 'ext': 'mp4', @@ -463,16 +492,16 @@ If you want to add support for a new site, you can follow this quick list (assum } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) # TODO more code goes here, for example ... - webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'

(.*?)

', webpage, 'title') return { 'id': video_id, 'title': title, + 'description': self._og_search_description(webpage), # TODO more properties (see youtube_dl/extractor/common.py) } ``` @@ -480,7 +509,7 @@ If you want to add support for a new site, you can follow this quick list (assum 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 [pyflakes](https://pypi.python.org/pypi/pyflakes) (a good idea) and [pep8](https://pypi.python.org/pypi/pep8) (optional, ignore E501). -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/yourextractor.py @@ -491,6 +520,20 @@ 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! +# 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: + + 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. + # BUGS Bugs and suggestions should be reported at: . 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. diff --git a/devscripts/bash-completion.py b/devscripts/bash-completion.py index 49287724d..cd26cc089 100755 --- a/devscripts/bash-completion.py +++ b/devscripts/bash-completion.py @@ -1,4 +1,6 @@ #!/usr/bin/env python +from __future__ import unicode_literals + import os from os.path import dirname as dirn import sys @@ -9,16 +11,17 @@ import youtube_dl BASH_COMPLETION_FILE = "youtube-dl.bash-completion" BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in" + def build_completion(opt_parser): opts_flag = [] for group in opt_parser.option_groups: for option in group.option_list: - #for every long flag + # for every long flag opts_flag.append(option.get_opt_string()) with open(BASH_COMPLETION_TEMPLATE) as f: template = f.read() 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)) f.write(filled_template) diff --git a/devscripts/buildserver.py b/devscripts/buildserver.py index e0c3cc83e..7c2f49f8b 100644 --- a/devscripts/buildserver.py +++ b/devscripts/buildserver.py @@ -142,7 +142,7 @@ def win_service_set_status(handle, status_code): def win_service_main(service_name, real_main, argc, argv_raw): 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() handler = HandlerEx(functools.partial(stop_event, win_service_handler)) h = advapi32.RegisterServiceCtrlHandlerExW(service_name, handler, None) @@ -233,6 +233,7 @@ def rmtree(path): #============================================================================== + class BuildError(Exception): def __init__(self, output, code=500): self.output = output @@ -369,7 +370,7 @@ class Builder(PythonBuilder, GITBuilder, YoutubeDLBuilder, DownloadBuilder, Clea 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): path = urlparse.urlparse(self.path) diff --git a/devscripts/check-porn.py b/devscripts/check-porn.py index 86aa37b5f..216282712 100644 --- a/devscripts/check-porn.py +++ b/devscripts/check-porn.py @@ -1,4 +1,5 @@ #!/usr/bin/env python +from __future__ import unicode_literals """ This script employs a VERY basic heuristic ('porn' in webpage.lower()) to check diff --git a/devscripts/fish-completion.py b/devscripts/fish-completion.py index f4aaf0201..c2f238798 100755 --- a/devscripts/fish-completion.py +++ b/devscripts/fish-completion.py @@ -23,13 +23,13 @@ EXTRA_ARGS = { 'batch-file': ['--require-parameter'], } + def build_completion(opt_parser): commands = [] for group in opt_parser.option_groups: for option in group.option_list: long_option = option.get_opt_string().strip('-') - help_msg = shell_quote([option.help]) complete_cmd = ['complete', '--command', 'youtube-dl', '--long-option', long_option] if option._short_opts: complete_cmd += ['--short-option', option._short_opts[0].strip('-')] diff --git a/devscripts/gh-pages/add-version.py b/devscripts/gh-pages/add-version.py index 35865b2f3..867ea0048 100755 --- a/devscripts/gh-pages/add-version.py +++ b/devscripts/gh-pages/add-version.py @@ -1,4 +1,5 @@ #!/usr/bin/env python3 +from __future__ import unicode_literals import json import sys diff --git a/devscripts/gh-pages/generate-download.py b/devscripts/gh-pages/generate-download.py index 55912e12c..392e3ba21 100755 --- a/devscripts/gh-pages/generate-download.py +++ b/devscripts/gh-pages/generate-download.py @@ -1,8 +1,7 @@ #!/usr/bin/env python3 +from __future__ import unicode_literals + import hashlib -import shutil -import subprocess -import tempfile import urllib.request import json diff --git a/devscripts/gh-pages/sign-versions.py b/devscripts/gh-pages/sign-versions.py index 8a824df56..fa389c358 100755 --- a/devscripts/gh-pages/sign-versions.py +++ b/devscripts/gh-pages/sign-versions.py @@ -1,4 +1,5 @@ #!/usr/bin/env python3 +from __future__ import unicode_literals, with_statement import rsa import json @@ -11,22 +12,23 @@ except NameError: versions_info = json.load(open('update/versions.json')) if 'signature' in versions_info: - del versions_info['signature'] + del versions_info['signature'] print('Enter the PKCS1 private key, followed by a blank line:') privkey = b'' while True: - try: - line = input() - except EOFError: - break - if line == '': - break - privkey += line.encode('ascii') + b'\n' + try: + line = input() + except EOFError: + break + if line == '': + break + privkey += line.encode('ascii') + b'\n' 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() print('signature: ' + signature) versions_info['signature'] = signature -json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True) \ No newline at end of file +with open('update/versions.json', 'w') as versionsf: + json.dump(versions_info, versionsf, indent=4, sort_keys=True) diff --git a/devscripts/gh-pages/update-copyright.py b/devscripts/gh-pages/update-copyright.py index 12c2a9194..3663c8afe 100755 --- a/devscripts/gh-pages/update-copyright.py +++ b/devscripts/gh-pages/update-copyright.py @@ -1,11 +1,11 @@ #!/usr/bin/env python # coding: utf-8 -from __future__ import with_statement +from __future__ import with_statement, unicode_literals import datetime import glob -import io # For Python 2 compatibilty +import io # For Python 2 compatibilty import os import re @@ -13,7 +13,7 @@ year = str(datetime.datetime.now().year) for fn in glob.glob('*.html*'): with io.open(fn, encoding='utf-8') as f: content = f.read() - newc = re.sub(u'(?PCopyright © 2006-)(?P[0-9]{4})', u'Copyright © 2006-' + year, content) + newc = re.sub(r'(?PCopyright © 2006-)(?P[0-9]{4})', 'Copyright © 2006-' + year, content) if content != newc: tmpFn = fn + '.part' with io.open(tmpFn, 'wt', encoding='utf-8') as outf: diff --git a/devscripts/gh-pages/update-feed.py b/devscripts/gh-pages/update-feed.py index 0ba15ae0f..e93eb60fb 100755 --- a/devscripts/gh-pages/update-feed.py +++ b/devscripts/gh-pages/update-feed.py @@ -1,4 +1,5 @@ #!/usr/bin/env python3 +from __future__ import unicode_literals import datetime 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: atom_file.write(atom_template) - diff --git a/devscripts/gh-pages/update-sites.py b/devscripts/gh-pages/update-sites.py index 153e15c8a..f0f0481c7 100755 --- a/devscripts/gh-pages/update-sites.py +++ b/devscripts/gh-pages/update-sites.py @@ -1,4 +1,5 @@ #!/usr/bin/env python3 +from __future__ import unicode_literals import sys import os @@ -9,6 +10,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath( import youtube_dl + def main(): with open('supportedsites.html.in', 'r', encoding='utf-8') as tmplf: template = tmplf.read() @@ -21,7 +23,7 @@ def main(): continue elif ie_desc is not None: ie_html += ': {}'.format(ie.IE_DESC) - if ie.working() == False: + if not ie.working(): ie_html += ' (Currently broken)' ie_htmls.append('
  • {}
    • '.format(ie_html)) diff --git a/devscripts/make_readme.py b/devscripts/make_readme.py index 70fa942dd..8fbce0796 100755 --- a/devscripts/make_readme.py +++ b/devscripts/make_readme.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import io import sys import re diff --git a/devscripts/prepare_manpage.py b/devscripts/prepare_manpage.py index d9c857015..f66bebfea 100644 --- a/devscripts/prepare_manpage.py +++ b/devscripts/prepare_manpage.py @@ -1,3 +1,4 @@ +from __future__ import unicode_literals import io import os.path diff --git a/devscripts/transition_helper.py b/devscripts/transition_helper.py deleted file mode 100644 index d5ca2d4ba..000000000 --- a/devscripts/transition_helper.py +++ /dev/null @@ -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') diff --git a/devscripts/transition_helper_exe/setup.py b/devscripts/transition_helper_exe/setup.py deleted file mode 100644 index aaf5c2983..000000000 --- a/devscripts/transition_helper_exe/setup.py +++ /dev/null @@ -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) \ No newline at end of file diff --git a/devscripts/transition_helper_exe/youtube-dl.py b/devscripts/transition_helper_exe/youtube-dl.py deleted file mode 100644 index 6297dfd40..000000000 --- a/devscripts/transition_helper_exe/youtube-dl.py +++ /dev/null @@ -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') diff --git a/devscripts/zsh-completion.in b/devscripts/zsh-completion.in new file mode 100644 index 000000000..b394a1ae7 --- /dev/null +++ b/devscripts/zsh-completion.in @@ -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 \ No newline at end of file diff --git a/devscripts/zsh-completion.py b/devscripts/zsh-completion.py new file mode 100755 index 000000000..f200f2c80 --- /dev/null +++ b/devscripts/zsh-completion.py @@ -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) diff --git a/docs/conf.py b/docs/conf.py index 4a04ad779..594ca61a6 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -44,8 +44,8 @@ copyright = u'2014, Ricardo Garcia Gonzalez' # built documents. # # The short X.Y version. -import youtube_dl -version = youtube_dl.__version__ +from youtube_dl.version import __version__ +version = __version__ # The full version, including alpha/beta/rc tags. release = version diff --git a/setup.py b/setup.py index cf6b92b0f..4686260e0 100644 --- a/setup.py +++ b/setup.py @@ -4,7 +4,6 @@ from __future__ import print_function import os.path -import pkg_resources import warnings import sys @@ -103,7 +102,9 @@ setup( "Programming Language :: Python :: 2.6", "Programming Language :: Python :: 2.7", "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 diff --git a/test/helper.py b/test/helper.py index 19e396270..8af57ead5 100644 --- a/test/helper.py +++ b/test/helper.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import errno import io import hashlib @@ -12,6 +14,7 @@ from youtube_dl import YoutubeDL from youtube_dl.utils import ( compat_str, preferredencoding, + write_string, ) @@ -40,10 +43,10 @@ def report_warning(message): If stderr is a tty file the 'WARNING:' will be colored ''' if sys.stderr.isatty() and os.name != 'nt': - _msg_header = u'\033[0;33mWARNING:\033[0m' + _msg_header = '\033[0;33mWARNING:\033[0m' else: - _msg_header = u'WARNING:' - output = u'%s %s\n' % (_msg_header, message) + _msg_header = 'WARNING:' + output = '%s %s\n' % (_msg_header, message) if 'b' in getattr(sys.stderr, 'mode', '') or sys.version_info[0] < 3: output = output.encode(preferredencoding()) sys.stderr.write(output) @@ -54,9 +57,9 @@ class FakeYDL(YoutubeDL): # Different instances of the downloader can't share the same dictionary # some test set the "sublang" parameter, which would break the md5 checks. params = get_params(override=override) - super(FakeYDL, self).__init__(params) + super(FakeYDL, self).__init__(params, auto_init=False) self.result = [] - + def to_screen(self, s, skip_eol=None): print(s) @@ -69,8 +72,10 @@ class FakeYDL(YoutubeDL): def expect_warning(self, regex): # Silence an expected warning matching a regex old_report_warning = self.report_warning + def report_warning(self, message): - if re.match(regex, message): return + if re.match(regex, message): + return old_report_warning(message) self.report_warning = types.MethodType(report_warning, self) @@ -103,22 +108,22 @@ def expect_info_dict(self, expected_dict, got_dict): self.assertTrue( 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)) self.assertTrue( 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, type): got = got_dict.get(info_field) 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: if isinstance(expected, compat_str) and expected.startswith('md5:'): got = 'md5:' + md5(got_dict.get(info_field)) else: got = got_dict.get(info_field) 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 if got_dict.get('_type') != 'playlist': @@ -127,15 +132,24 @@ def expect_info_dict(self, expected_dict, got_dict): self.assertTrue(any(key in info_dict.keys() and info_dict[key] for key in ('url', 'parts'))) # Check for mandatory fields that are automatically set by YoutubeDL 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? 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() - if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location')) + for key, value in got_dict.items() + if value and key in ('title', 'description', 'uploader', 'upload_date', 'timestamp', 'uploader_id', 'location')) missing_keys = set(test_info_dict.keys()) - set(expected_dict.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 = ''.join( + ' %s: %s,\n' % (_repr(k), _repr(v)) + for k, v in test_info_dict.items()) + write_string( + '\n\'info_dict\': {\n' + info_dict_str + '}\n', out=sys.stderr) self.assertFalse( missing_keys, 'Missing keys in test definition: %s' % ( @@ -161,3 +175,13 @@ def assertGreaterEqual(self, got, expected, msg=None): if msg is None: msg = '%r not greater than or equal to %r' % (got, expected) 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 diff --git a/test/swftests/ConstArrayAccess.as b/test/swftests/ConstArrayAccess.as new file mode 100644 index 000000000..07dc3f460 --- /dev/null +++ b/test/swftests/ConstArrayAccess.as @@ -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; + } +} +} diff --git a/test/swftests/ConstantInt.as b/test/swftests/ConstantInt.as new file mode 100644 index 000000000..e0bbb6166 --- /dev/null +++ b/test/swftests/ConstantInt.as @@ -0,0 +1,12 @@ +// input: [] +// output: 2 + +package { +public class ConstantInt { + private static const x:int = 2; + + public static function main():int{ + return x; + } +} +} diff --git a/test/swftests/DictCall.as b/test/swftests/DictCall.as new file mode 100644 index 000000000..c2d174cc2 --- /dev/null +++ b/test/swftests/DictCall.as @@ -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; + } +} +} diff --git a/test/swftests/EqualsOperator.as b/test/swftests/EqualsOperator.as new file mode 100644 index 000000000..837a69a46 --- /dev/null +++ b/test/swftests/EqualsOperator.as @@ -0,0 +1,10 @@ +// input: [] +// output: false + +package { +public class EqualsOperator { + public static function main():Boolean{ + return 1 == 2; + } +} +} diff --git a/test/swftests/MemberAssignment.as b/test/swftests/MemberAssignment.as new file mode 100644 index 000000000..dcba5e3ff --- /dev/null +++ b/test/swftests/MemberAssignment.as @@ -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); + } +} +} diff --git a/test/swftests/NeOperator.as b/test/swftests/NeOperator.as new file mode 100644 index 000000000..61dcbc4e9 --- /dev/null +++ b/test/swftests/NeOperator.as @@ -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; + } +} +} diff --git a/test/swftests/PrivateVoidCall.as b/test/swftests/PrivateVoidCall.as new file mode 100644 index 000000000..2cc016797 --- /dev/null +++ b/test/swftests/PrivateVoidCall.as @@ -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(); + } +} diff --git a/test/swftests/StringBasics.as b/test/swftests/StringBasics.as new file mode 100644 index 000000000..d27430b13 --- /dev/null +++ b/test/swftests/StringBasics.as @@ -0,0 +1,11 @@ +// input: [] +// output: 3 + +package { +public class StringBasics { + public static function main():int{ + var s:String = "abc"; + return s.length; + } +} +} diff --git a/test/swftests/StringCharCodeAt.as b/test/swftests/StringCharCodeAt.as new file mode 100644 index 000000000..c20d74d65 --- /dev/null +++ b/test/swftests/StringCharCodeAt.as @@ -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(); + } +} +} diff --git a/test/swftests/StringConversion.as b/test/swftests/StringConversion.as new file mode 100644 index 000000000..c976f5042 --- /dev/null +++ b/test/swftests/StringConversion.as @@ -0,0 +1,11 @@ +// input: [] +// output: 2 + +package { +public class StringConversion { + public static function main():int{ + var s:String = String(99); + return s.length; + } +} +} diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index ab61e1976..f8e4f930e 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -266,6 +266,7 @@ class TestFormatSelection(unittest.TestCase): 'ext': 'mp4', 'width': None, } + def fname(templ): ydl = YoutubeDL({'outtmpl': templ}) return ydl.prepare_filename(info) diff --git a/test/test_age_restriction.py b/test/test_age_restriction.py index 71e80b037..5be065c43 100644 --- a/test/test_age_restriction.py +++ b/test/test_age_restriction.py @@ -1,4 +1,5 @@ #!/usr/bin/env python +from __future__ import unicode_literals # Allow direct execution import os @@ -19,7 +20,7 @@ def _download_restricted(url, filename, age): 'age_limit': age, 'skip_download': True, 'writeinfojson': True, - "outtmpl": "%(id)s.%(ext)s", + 'outtmpl': '%(id)s.%(ext)s', } ydl = YoutubeDL(params) ydl.add_default_info_extractors() diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 84b05da39..bd4fe17bf 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -14,7 +14,7 @@ from test.helper import gettestcases from youtube_dl.extractor import ( FacebookIE, gen_extractors, - JustinTVIE, + TwitchIE, YoutubeIE, ) @@ -32,19 +32,19 @@ class TestAllURLsMatching(unittest.TestCase): def test_youtube_playlist_matching(self): assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist']) assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') - assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') #585 + assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585 assertPlaylist('PL63F0C78739B09958') assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q') assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8') 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')) # Top tracks assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101') def test_youtube_matching(self): 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://www.youtube.com/v/BaW_jenozKc', ['youtube']) self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube']) @@ -72,21 +72,17 @@ class TestAllURLsMatching(unittest.TestCase): 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']) - 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_twitch_channelid_matching(self): + self.assertTrue(TwitchIE.suitable('twitch.tv/vanillatv')) + self.assertTrue(TwitchIE.suitable('www.twitch.tv/vanillatv')) + self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/vanillatv')) + self.assertTrue(TwitchIE.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_twitch_videoid_matching(self): + self.assertTrue(TwitchIE.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_twitch_chapterid_matching(self): + self.assertTrue(TwitchIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361')) def test_youtube_extract(self): assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id) diff --git a/test/test_compat.py b/test/test_compat.py new file mode 100644 index 000000000..1eb454e06 --- /dev/null +++ b/test/test_compat.py @@ -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() diff --git a/test/test_download.py b/test/test_download.py index 2b8ac6975..a009aa475 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -1,5 +1,7 @@ #!/usr/bin/env python +from __future__ import unicode_literals + # Allow direct execution import os import sys @@ -8,6 +10,7 @@ sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from test.helper import ( assertGreaterEqual, + expect_warnings, get_params, gettestcases, expect_info_dict, @@ -22,10 +25,12 @@ import json import socket import youtube_dl.YoutubeDL -from youtube_dl.utils import ( +from youtube_dl.compat import ( compat_http_client, compat_urllib_error, compat_HTTPError, +) +from youtube_dl.utils import ( DownloadError, ExtractorError, format_bytes, @@ -35,18 +40,22 @@ from youtube_dl.extractor import get_info_extractor RETRIES = 3 + class YoutubeDL(youtube_dl.YoutubeDL): def __init__(self, *args, **kwargs): self.to_stderr = self.to_screen self.processed_info_dicts = [] super(YoutubeDL, self).__init__(*args, **kwargs) + def report_warning(self, message): # Don't accept warnings during tests raise ExtractorError(message) + def process_info(self, info_dict): self.processed_info_dicts.append(info_dict) return super(YoutubeDL, self).process_info(info_dict) + def _file_md5(fn): with open(fn, 'rb') as f: return hashlib.md5(f.read()).hexdigest() @@ -56,10 +65,13 @@ defs = gettestcases() class TestDownload(unittest.TestCase): maxDiff = None + def setUp(self): self.defs = defs -### Dynamically generate tests +# Dynamically generate tests + + def generator(test_case): def test_template(self): @@ -85,7 +97,7 @@ def generator(test_case): return for other_ie in other_ies: 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 params = get_params(test_case.get('params', {})) @@ -93,18 +105,21 @@ def generator(test_case): params.setdefault('extract_flat', True) params.setdefault('skip_download', True) - ydl = YoutubeDL(params) + ydl = YoutubeDL(params, auto_init=False) ydl.add_default_info_extractors() finished_hook_called = set() + def _hook(status): if status['status'] == 'finished': finished_hook_called.add(status['filename']) ydl.add_progress_hook(_hook) + expect_warnings(ydl, test_case.get('expected_warnings', [])) def get_tc_filename(tc): return tc.get('file') or ydl.prepare_filename(tc.get('info_dict', {})) res_dict = None + def try_rm_tcs_files(tcs=None): if tcs is None: tcs = test_cases @@ -128,7 +143,7 @@ def generator(test_case): raise if try_num == RETRIES: - report_warning(u'Failed due to network errors, skipping...') + report_warning('Failed due to network errors, skipping...') return print('Retrying: {0} failed tries\n\n##########\n\n'.format(try_num)) @@ -139,7 +154,9 @@ def generator(test_case): if is_playlist: self.assertEqual(res_dict['_type'], 'playlist') + self.assertTrue('entries' in res_dict) expect_info_dict(self, test_case.get('info_dict', {}), res_dict) + if 'playlist_mincount' in test_case: assertGreaterEqual( self, @@ -181,14 +198,16 @@ def generator(test_case): md5_for_file = _file_md5(tc_filename) self.assertEqual(md5_for_file, tc['md5']) 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: info_dict = json.load(infof) expect_info_dict(self, tc.get('info_dict', {}), info_dict) finally: 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 # extractor returns full results even with extract_flat res_tcs = [{'info_dict': e} for e in res_dict['entries']] @@ -196,15 +215,15 @@ def generator(test_case): return test_template -### And add them to TestDownload +# And add them to TestDownload for n, test_case in enumerate(defs): test_method = generator(test_case) tname = 'test_' + str(test_case['name']) i = 1 while hasattr(TestDownload, tname): - tname = 'test_' + str(test_case['name']) + '_' + str(i) + tname = 'test_%s_%d' % (test_case['name'], i) i += 1 - test_method.__name__ = tname + test_method.__name__ = str(tname) setattr(TestDownload, test_method.__name__, test_method) del test_method diff --git a/test/test_execution.py b/test/test_execution.py index 2b115fb31..60df187de 100644 --- a/test/test_execution.py +++ b/test/test_execution.py @@ -1,3 +1,6 @@ +#!/usr/bin/env python +from __future__ import unicode_literals + import unittest import sys @@ -6,17 +9,19 @@ import subprocess rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) + try: _DEV_NULL = subprocess.DEVNULL except AttributeError: _DEV_NULL = open(os.devnull, 'wb') + class TestExecution(unittest.TestCase): def test_import(self): subprocess.check_call([sys.executable, '-c', 'import youtube_dl'], cwd=rootDir) 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) def test_main_exec(self): diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 48c302198..2eeb31bc6 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -1,4 +1,5 @@ #!/usr/bin/env python +from __future__ import unicode_literals # Allow direct execution import os @@ -15,12 +16,14 @@ from youtube_dl.extractor import ( DailymotionIE, TEDIE, VimeoIE, + WallaIE, ) class BaseTestSubtitles(unittest.TestCase): url = None IE = None + def setUp(self): self.DL = FakeYDL() self.ie = self.IE(self.DL) @@ -73,7 +76,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles): 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.expect_warning('Video doesn\'t have automatic captions') self.DL.params['listsubtitles'] = True info_dict = self.getInfoDict() self.assertEqual(info_dict, None) @@ -86,7 +89,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles): self.assertTrue(subtitles['it'] is not None) 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.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True @@ -100,7 +103,7 @@ class TestYoutubeSubtitles(BaseTestSubtitles): 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) + self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) class TestDailymotionSubtitles(BaseTestSubtitles): @@ -129,20 +132,20 @@ class TestDailymotionSubtitles(BaseTestSubtitles): self.assertEqual(len(subtitles.keys()), 5) def test_list_subtitles(self): - self.DL.expect_warning(u'Automatic Captions not supported by this server') + self.DL.expect_warning('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.expect_warning('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): - 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.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True @@ -155,7 +158,7 @@ class TestDailymotionSubtitles(BaseTestSubtitles): 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) + self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) class TestTedSubtitles(BaseTestSubtitles): @@ -184,13 +187,13 @@ class TestTedSubtitles(BaseTestSubtitles): self.assertTrue(len(subtitles.keys()) >= 28) def test_list_subtitles(self): - self.DL.expect_warning(u'Automatic Captions not supported by this server') + self.DL.expect_warning('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.expect_warning('Automatic Captions not supported by this server') self.DL.params['writeautomaticsub'] = True self.DL.params['subtitleslang'] = ['en'] subtitles = self.getSubtitles() @@ -202,7 +205,7 @@ class TestTedSubtitles(BaseTestSubtitles): 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) + self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) class TestBlipTVSubtitles(BaseTestSubtitles): @@ -210,13 +213,13 @@ class TestBlipTVSubtitles(BaseTestSubtitles): IE = BlipTVIE def test_list_subtitles(self): - self.DL.expect_warning(u'Automatic Captions not supported by this server') + self.DL.expect_warning('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): - self.DL.expect_warning(u'Automatic Captions not supported by this server') + self.DL.expect_warning('Automatic Captions not supported by this server') self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() @@ -250,20 +253,20 @@ class TestVimeoSubtitles(BaseTestSubtitles): self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr'])) def test_list_subtitles(self): - self.DL.expect_warning(u'Automatic Captions not supported by this server') + self.DL.expect_warning('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.expect_warning('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): - 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.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True @@ -276,7 +279,34 @@ class TestVimeoSubtitles(BaseTestSubtitles): 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) + self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) + + +class TestWallaSubtitles(BaseTestSubtitles): + url = 'http://vod.walla.co.il/movie/2705958/the-yes-men' + IE = WallaIE + + def test_list_subtitles(self): + self.DL.expect_warning('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): + 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(['heb'])) + 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.assertEqual(len(subtitles), 0) if __name__ == '__main__': diff --git a/test/test_swfinterp.py b/test/test_swfinterp.py index b42cd74c7..9f18055e6 100644 --- a/test/test_swfinterp.py +++ b/test/test_swfinterp.py @@ -1,4 +1,5 @@ #!/usr/bin/env python +from __future__ import unicode_literals # Allow direct execution import os @@ -37,7 +38,9 @@ def _make_testfunc(testfile): or os.path.getmtime(swf_file) < os.path.getmtime(as_file)): # Recompile 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: if ose.errno == errno.ENOENT: print('mxmlc not found! Skipping test.') diff --git a/test/test_unicode_literals.py b/test/test_unicode_literals.py index a4ba7bad0..2cc431b0b 100644 --- a/test/test_unicode_literals.py +++ b/test/test_unicode_literals.py @@ -9,14 +9,13 @@ rootDir = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) IGNORED_FILES = [ 'setup.py', # http://bugs.python.org/issue13943 + 'conf.py', + 'buildserver.py', ] class TestUnicodeLiterals(unittest.TestCase): def test_all_files(self): - print('Skipping this test (not yet fully implemented)') - return - for dirpath, _, filenames in os.walk(rootDir): for basename in filenames: if not basename.endswith('.py'): @@ -30,10 +29,10 @@ class TestUnicodeLiterals(unittest.TestCase): if "'" not in code and '"' not in code: continue - imps = 'from __future__ import unicode_literals' - self.assertTrue( - imps in code, - ' %s missing in %s' % (imps, fn)) + self.assertRegexpMatches( + code, + r'(?:#.*\n*)?from __future__ import (?:[a-z_]+,\s*)*unicode_literals', + 'unicode_literals import missing in %s' % fn) m = re.search(r'(?<=\s)u[\'"](?!\)|,|$)', code) if m is not None: diff --git a/test/test_utils.py b/test/test_utils.py index 3efbed29d..baa3a2156 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -16,13 +16,14 @@ import json import xml.etree.ElementTree from youtube_dl.utils import ( + clean_html, DateRange, encodeFilename, find_xpath_attr, fix_xml_ampersands, - get_meta_content, orderedSet, - PagedList, + OnDemandPagedList, + InAdvancePagedList, parse_duration, read_batch_urls, sanitize_filename, @@ -43,6 +44,10 @@ from youtube_dl.utils import ( limit_length, escape_rfc3986, escape_url, + js_to_json, + intlist_to_bytes, + args_to_str, + parse_filesize, ) @@ -115,16 +120,16 @@ class TestUtil(unittest.TestCase): 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([1]), [1]) - #keep the list ordered + # keep the list ordered self.assertEqual(orderedSet([135, 1, 1, 1]), [135, 1]) def test_unescape_html(self): self.assertEqual(unescapeHTML('%20;'), '%20;') self.assertEqual( unescapeHTML('é'), 'é') - + def test_daterange(self): - _20century = DateRange("19000101","20000101") + _20century = DateRange("19000101", "20000101") self.assertFalse("17890714" in _20century) _ac = DateRange("00010101") self.assertTrue("19690721" in _ac) @@ -137,6 +142,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214') self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011') self.assertEqual(unified_strdate('1968-12-10'), '19681210') + self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128') def test_find_xpath_attr(self): testxml = ''' @@ -151,17 +157,6 @@ class TestUtil(unittest.TestCase): self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1]) self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2]) - def test_meta_parser(self): - testhtml = ''' - - - - - ''' - 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): testxml = ''' @@ -176,7 +171,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(find('media:song/url').text, 'http://server.com/download.mp3') 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' smug_url = smuggle_url(url, data) unsmug_url, unsmug_data = unsmuggle_url(smug_url) @@ -224,6 +219,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_duration('0m0s'), 0) self.assertEqual(parse_duration('0s'), 0) self.assertEqual(parse_duration('01:02:03.05'), 3723.05) + self.assertEqual(parse_duration('T30M38S'), 1838) def test_fix_xml_ampersands(self): self.assertEqual( @@ -246,10 +242,14 @@ class TestUtil(unittest.TestCase): for i in range(firstid, upto): yield i - pl = PagedList(get_page, pagesize) + pl = OnDemandPagedList(get_page, pagesize) got = pl.getslice(*sliceargs) 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, (1,), [1, 2, 3, 4]) testPL(5, 2, (2,), [2, 3, 4]) @@ -279,12 +279,17 @@ class TestUtil(unittest.TestCase): 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('2014-03-23T22:04:26Z'), 1395612266) + self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266) def test_strip_jsonp(self): stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);') d = json.loads(stripped) 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): self.assertEqual(uppercase_escape('aä'), 'aä') self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') @@ -325,5 +330,52 @@ class TestUtil(unittest.TestCase): ) 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}}] + }''') + + 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}) + + 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) + if __name__ == '__main__': unittest.main() diff --git a/test/test_write_annotations.py b/test/test_write_annotations.py index eac53b285..780636c77 100644 --- a/test/test_write_annotations.py +++ b/test/test_write_annotations.py @@ -1,5 +1,6 @@ #!/usr/bin/env python # coding: utf-8 +from __future__ import unicode_literals # Allow direct execution import os @@ -31,19 +32,18 @@ params = get_params({ }) - TEST_ID = 'gr51aVj-mLg' ANNOTATIONS_FILE = TEST_ID + '.flv.annotations.xml' EXPECTED_ANNOTATIONS = ['Speech bubble', 'Note', 'Title', 'Spotlight', 'Label'] + class TestAnnotations(unittest.TestCase): def setUp(self): # Clear old files self.tearDown() - 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() ydl = YoutubeDL(params) ydl.add_info_extractor(ie) @@ -51,7 +51,7 @@ class TestAnnotations(unittest.TestCase): self.assertTrue(os.path.exists(ANNOTATIONS_FILE)) annoxml = None 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') root = annoxml.getroot() self.assertEqual(root.tag, 'document') @@ -59,18 +59,17 @@ class TestAnnotations(unittest.TestCase): self.assertEqual(annotationsTag.tag, 'annotations') 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: - self.assertEqual(a.tag, 'annotation') - if a.get('type') == 'text': - textTag = a.find('TEXT') - text = textTag.text - 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 - expected.remove(text) - #We should have seen (and removed) all the expected annotation texts. + self.assertEqual(a.tag, 'annotation') + if a.get('type') == 'text': + textTag = a.find('TEXT') + text = textTag.text + 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 + expected.remove(text) + # We should have seen (and removed) all the expected annotation texts. self.assertEqual(len(expected), 0, 'Not all expected annotations were found.') - def tearDown(self): try_rm(ANNOTATIONS_FILE) diff --git a/test/test_write_info_json.py b/test/test_write_info_json.py index 90426a559..0396ef262 100644 --- a/test/test_write_info_json.py +++ b/test/test_write_info_json.py @@ -1,5 +1,6 @@ #!/usr/bin/env python # coding: utf-8 +from __future__ import unicode_literals # Allow direct execution import os @@ -32,7 +33,7 @@ params = get_params({ TEST_ID = 'BaW_jenozKc' INFO_JSON_FILE = TEST_ID + '.info.json' DESCRIPTION_FILE = TEST_ID + '.mp4.description' -EXPECTED_DESCRIPTION = u'''test chars: "'/\ä↭𝕐 +EXPECTED_DESCRIPTION = '''test chars: "'/\ä↭𝕐 test URL: https://github.com/rg3/youtube-dl/issues/1892 This is a test video for youtube-dl. @@ -53,11 +54,11 @@ class TestInfoJSON(unittest.TestCase): 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['upload_date'], '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['title'], '''youtube-dl test video "'/\ä↭𝕐''') self.assertEqual(jd['uploader'], 'Philipp Hagemeister') self.assertTrue(os.path.exists(DESCRIPTION_FILE)) diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index 1fa99f88b..c889b6f15 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -1,4 +1,5 @@ #!/usr/bin/env python +from __future__ import unicode_literals # Allow direct execution import os @@ -10,13 +11,8 @@ from test.helper import FakeYDL from youtube_dl.extractor import ( - YoutubeUserIE, YoutubePlaylistIE, 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') self.assertEqual(result['_type'], 'url') self.assertEqual(YoutubeIE().extract_id(result['url']), 'FXxLjLQi3Fg') - + def test_youtube_course(self): dl = FakeYDL() ie = YoutubePlaylistIE(dl) @@ -43,28 +39,6 @@ class TestYoutubeLists(unittest.TestCase): self.assertEqual(len(entries), 25) 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): dl = FakeYDL() ie = YoutubePlaylistIE(dl) @@ -83,21 +57,5 @@ class TestYoutubeLists(unittest.TestCase): entries = result['entries'] 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__': unittest.main() diff --git a/test/test_youtube_signature.py b/test/test_youtube_signature.py index 604e76ab6..13d228cd8 100644 --- a/test/test_youtube_signature.py +++ b/test/test_youtube_signature.py @@ -14,7 +14,7 @@ import re import string 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 = [ ( @@ -47,18 +47,6 @@ _TESTS = [ '2ACFC7A61CA478CD21425E5A57EBD73DDC78E22A.2094302436B2D377D14A3BBA23022D023B8BC25AA', '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', 'js', diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 6fd50a506..99fc2f1bd 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -22,12 +22,15 @@ import traceback if os.name == 'nt': import ctypes -from .utils import ( +from .compat import ( compat_cookiejar, + compat_expanduser, compat_http_client, compat_str, compat_urllib_error, compat_urllib_request, +) +from .utils import ( escape_url, ContentTooShortError, date_from_str, @@ -58,11 +61,13 @@ from .utils import ( write_string, YoutubeDLHandler, prepend_extension, + args_to_str, ) from .cache import Cache from .extractor import get_info_extractor, gen_extractors from .downloader import get_suitable_downloader -from .postprocessor import FFmpegMergerPP +from .downloader.rtmp import rtmpdump_version +from .postprocessor import FFmpegMergerPP, FFmpegPostProcessor from .version import __version__ @@ -108,6 +113,8 @@ class YoutubeDL(object): forcefilename: Force printing final filename. forceduration: Force printing duration. forcejson: Force printing info_dict as JSON. + dump_single_json: Force printing the info_dict of the whole playlist + (or video) as a single JSON line. simulate: Do not download the video files. format: Video format code. format_limit: Highest quality format to try. @@ -166,6 +173,8 @@ class YoutubeDL(object): 'auto' for elaborate guessing encoding: Use this encoding instead of the system-specified. extract_flat: Do not resolve URLs, return the immediate result. + Pass in 'in_playlist' to only show this behavior for + playlist items. The following parameters are not used by YoutubeDL itself, they are used by the FileDownloader: @@ -185,7 +194,7 @@ class YoutubeDL(object): _num_downloads = None _screen_file = None - def __init__(self, params=None): + def __init__(self, params=None, auto_init=True): """Create a FileDownloader object with the given options.""" if params is None: params = {} @@ -229,11 +238,11 @@ class YoutubeDL(object): if (sys.version_info >= (3,) and sys.platform != 'win32' and sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] - and not params['restrictfilenames']): + and not params.get('restrictfilenames', False)): # On Python 3, the Unicode filesystem API will throw errors (#1474) self.report_warning( 'Assuming --restrict-filenames since file system encoding ' - 'cannot encode all charactes. ' + 'cannot encode all characters. ' 'Set the LC_ALL environment variable to fix this.') self.params['restrictfilenames'] = True @@ -242,6 +251,26 @@ class YoutubeDL(object): self._setup_opener() + if auto_init: + self.print_debug_header() + self.add_default_info_extractors() + + def warn_if_short_id(self, argv): + # short YouTube ID starting with dash? + idxs = [ + i for i, a in enumerate(argv) + if re.match(r'^-[0-9A-Za-z_-]{10}$', a)] + if idxs: + correct_argv = ( + ['youtube-dl'] + + [a for i, a in enumerate(argv) if i not in idxs] + + ['--'] + [argv[i] for i in idxs] + ) + self.report_warning( + 'Long argument string detected. ' + 'Use -- to separate parameters and URLs, like this:\n%s\n' % + args_to_str(correct_argv)) + def add_info_extractor(self, ie): """Add an InfoExtractor object to the end of the list.""" self._ies.append(ie) @@ -286,7 +315,7 @@ class YoutubeDL(object): self._output_process.stdin.write((message + '\n').encode('utf-8')) self._output_process.stdin.flush() res = ''.join(self._output_channel.readline().decode('utf-8') - for _ in range(line_count)) + for _ in range(line_count)) return res[:-len('\n')] def to_screen(self, message, skip_eol=False): @@ -448,7 +477,7 @@ class YoutubeDL(object): template_dict = collections.defaultdict(lambda: 'NA', template_dict) outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) - tmpl = os.path.expanduser(outtmpl) + tmpl = compat_expanduser(outtmpl) filename = tmpl % template_dict return filename except ValueError as err: @@ -523,7 +552,7 @@ class YoutubeDL(object): try: ie_result = ie.extract(url) - if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) + if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here) break if isinstance(ie_result, list): # Backwards compatibility: old IE result format @@ -536,7 +565,7 @@ class YoutubeDL(object): return self.process_ie_result(ie_result, download, extra_info) else: return ie_result - except ExtractorError as de: # An error we somewhat expected + except ExtractorError as de: # An error we somewhat expected self.report_error(compat_str(de), de.format_traceback()) break except MaxDownloadsReached: @@ -569,8 +598,12 @@ class YoutubeDL(object): result_type = ie_result.get('_type', 'video') - if self.params.get('extract_flat', False): - if result_type in ('url', 'url_transparent'): + if result_type in ('url', 'url_transparent'): + extract_flat = self.params.get('extract_flat', False) + if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or + extract_flat is True): + if self.params.get('forcejson', False): + self.to_stdout(json.dumps(ie_result)) return ie_result if result_type == 'video': @@ -609,7 +642,7 @@ class YoutubeDL(object): return self.process_ie_result( new_result, download=download, extra_info=extra_info) - elif result_type == 'playlist': + elif result_type == 'playlist' or result_type == 'multi_video': # We process each entry in the playlist playlist = ie_result.get('title', None) or ie_result.get('id', None) self.to_screen('[download] Downloading playlist: %s' % playlist) @@ -643,6 +676,8 @@ class YoutubeDL(object): extra = { 'n_entries': n_entries, 'playlist': playlist, + 'playlist_id': ie_result.get('id'), + 'playlist_title': ie_result.get('title'), 'playlist_index': i + playliststart, 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], @@ -662,14 +697,20 @@ class YoutubeDL(object): ie_result['entries'] = playlist_results return ie_result elif result_type == 'compat_list': + self.report_warning( + 'Extractor %s returned a compat_list result. ' + 'It needs to be updated.' % ie_result.get('extractor')) + def _fixup(r): - self.add_extra_info(r, + self.add_extra_info( + r, { 'extractor': ie_result['extractor'], 'webpage_url': ie_result['webpage_url'], 'webpage_url_basename': url_basename(ie_result['webpage_url']), 'extractor_key': ie_result['extractor_key'], - }) + } + ) return r ie_result['entries'] = [ self.process_ie_result(_fixup(r), download, extra_info) @@ -709,7 +750,7 @@ class YoutubeDL(object): if video_formats: return video_formats[0] else: - extensions = ['mp4', 'flv', 'webm', '3gp'] + extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a'] if format_spec in extensions: filter_f = lambda f: f['ext'] == format_spec else: @@ -815,28 +856,36 @@ class YoutubeDL(object): if req_format in ('-1', 'all'): formats_to_download = formats else: - # We can accept formats requested in the format: 34/5/best, we pick - # the first that is available, starting from left - req_formats = req_format.split('/') - for rf in req_formats: - if re.match(r'.+?\+.+?', rf) is not None: - # Two formats have been requested like '137+139' - format_1, format_2 = rf.split('+') - formats_info = (self.select_format(format_1, formats), - self.select_format(format_2, formats)) - if all(formats_info): - selected_format = { - 'requested_formats': formats_info, - 'format': rf, - 'ext': formats_info[0]['ext'], - } + for rfstr in req_format.split(','): + # We can accept formats requested in the format: 34/5/best, we pick + # the first that is available, starting from left + req_formats = rfstr.split('/') + for rf in req_formats: + if re.match(r'.+?\+.+?', rf) is not None: + # Two formats have been requested like '137+139' + format_1, format_2 = rf.split('+') + formats_info = (self.select_format(format_1, formats), + self.select_format(format_2, formats)) + if all(formats_info): + # The first format must contain the video and the + # second the audio + if formats_info[0].get('vcodec') == 'none': + self.report_error('The first format must ' + 'contain the video, try using ' + '"-f %s+%s"' % (format_2, format_1)) + return + selected_format = { + 'requested_formats': formats_info, + 'format': rf, + 'ext': formats_info[0]['ext'], + } + else: + selected_format = None else: - selected_format = None - else: - selected_format = self.select_format(rf, formats) - if selected_format is not None: - formats_to_download = [selected_format] - break + selected_format = self.select_format(rf, formats) + if selected_format is not None: + formats_to_download.append(selected_format) + break if not formats_to_download: raise ExtractorError('requested format not available', expected=True) @@ -902,6 +951,8 @@ class YoutubeDL(object): if self.params.get('forcejson', False): info_dict['_filename'] = filename self.to_stdout(json.dumps(info_dict)) + if self.params.get('dump_single_json', False): + info_dict['_filename'] = filename # Do nothing else if in simulate mode if self.params.get('simulate', False): @@ -967,7 +1018,7 @@ class YoutubeDL(object): else: self.to_screen('[info] Writing video subtitles to: ' + sub_filename) with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: - subfile.write(sub) + subfile.write(sub) except (OSError, IOError): self.report_error('Cannot write subtitles file ' + sub_filename) return @@ -979,7 +1030,7 @@ class YoutubeDL(object): else: self.to_screen('[info] Writing video description metadata as JSON to: ' + infofn) try: - write_json_file(info_dict, encodeFilename(infofn)) + write_json_file(info_dict, infofn) except (OSError, IOError): self.report_error('Cannot write metadata to JSON file ' + infofn) return @@ -999,10 +1050,10 @@ class YoutubeDL(object): with open(thumb_filename, 'wb') as thumbf: shutil.copyfileobj(uf, thumbf) self.to_screen('[%s] %s: Writing thumbnail to: %s' % - (info_dict['extractor'], info_dict['id'], thumb_filename)) + (info_dict['extractor'], info_dict['id'], thumb_filename)) except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: self.report_warning('Unable to download thumbnail "%s": %s' % - (info_dict['thumbnail'], compat_str(err))) + (info_dict['thumbnail'], compat_str(err))) if not self.params.get('skip_download', False): if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)): @@ -1020,11 +1071,11 @@ class YoutubeDL(object): downloaded = [] success = True merger = FFmpegMergerPP(self, not self.params.get('keepvideo')) - if not merger._get_executable(): + if not merger._executable: postprocessors = [] self.report_warning('You have requested multiple ' - 'formats but ffmpeg or avconv are not installed.' - ' The formats won\'t be merged') + 'formats but ffmpeg or avconv are not installed.' + ' The formats won\'t be merged') else: postprocessors = [merger] for f in info_dict['requested_formats']: @@ -1086,13 +1137,16 @@ class YoutubeDL(object): for url in url_list: try: - #It also downloads the videos - self.extract_info(url) + # It also downloads the videos + res = self.extract_info(url) except UnavailableVideoError: self.report_error('unable to download video') except MaxDownloadsReached: self.to_screen('[info] Maximum number of downloaded files reached.') raise + else: + if self.params.get('dump_single_json', False): + self.to_stdout(json.dumps(res)) return self._download_retcode @@ -1216,6 +1270,8 @@ class YoutubeDL(object): res += 'video@' if fdict.get('vbr') is not None: res += '%4dk' % fdict['vbr'] + if fdict.get('fps') is not None: + res += ', %sfps' % fdict['fps'] if fdict.get('acodec') is not None: if res: res += ', ' @@ -1273,12 +1329,13 @@ class YoutubeDL(object): # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991) # To work around aforementioned issue we will replace request's original URL with # percent-encoded one - url = req if isinstance(req, compat_str) else req.get_full_url() + req_is_string = isinstance(req, basestring if sys.version_info < (3, 0) else compat_str) + url = req if req_is_string else req.get_full_url() url_escaped = escape_url(url) # Substitute URL if any change after escaping if url != url_escaped: - if isinstance(req, compat_str): + if req_is_string: req = url_escaped else: req = compat_urllib_request.Request( @@ -1296,11 +1353,13 @@ class YoutubeDL(object): self.report_warning( 'Your Python is broken! Update to a newer and supported version') + stdout_encoding = getattr( + sys.stdout, 'encoding', 'missing (%s)' % type(sys.stdout).__name__) encoding_str = ( '[debug] Encodings: locale %s, fs %s, out %s, pref %s\n' % ( locale.getpreferredencoding(), sys.getfilesystemencoding(), - sys.stdout.encoding, + stdout_encoding, self.get_encoding())) write_string(encoding_str, encoding=None) @@ -1319,8 +1378,19 @@ class YoutubeDL(object): sys.exc_clear() except: pass - self._write_string('[debug] Python version %s - %s' % - (platform.python_version(), platform_name()) + '\n') + self._write_string('[debug] Python version %s - %s\n' % ( + platform.python_version(), platform_name())) + + exe_versions = FFmpegPostProcessor.get_versions() + exe_versions['rtmpdump'] = rtmpdump_version() + exe_str = ', '.join( + '%s %s' % (exe, v) + for exe, v in sorted(exe_versions.items()) + if v + ) + if not exe_str: + exe_str = 'none' + self._write_string('[debug] exe versions: %s\n' % exe_str) proxy_map = {} for handler in self._opener.handlers: diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 76f97e6a4..9475127b0 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -1,82 +1,7 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- -__authors__ = ( - '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', -) +from __future__ import unicode_literals __license__ = 'Public Domain' @@ -90,9 +15,13 @@ import sys from .options import ( parseOpts, ) -from .utils import ( +from .compat import ( + compat_expanduser, compat_getpass, compat_print, + workaround_optparse_bug9161, +) +from .utils import ( DateRange, DEFAULT_OUTTMPL, decodeOption, @@ -130,7 +59,9 @@ def _real_main(argv=None): # https://github.com/rg3/youtube-dl/issues/820 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) @@ -146,10 +77,10 @@ def _real_main(argv=None): if opts.headers is not None: for h in opts.headers: 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) 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 # Dump user agent @@ -167,9 +98,9 @@ def _real_main(argv=None): batchfd = io.open(opts.batchfile, 'r', encoding='utf-8', errors='ignore') batch_urls = read_batch_urls(batchfd) 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: - 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 = [url.strip() for url in all_urls] _enc = preferredencoding() @@ -182,7 +113,7 @@ def _real_main(argv=None): compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else '')) matchedUrls = [url for url in all_urls if ie.suitable(url)] for mu in matchedUrls: - compat_print(u' ' + mu) + compat_print(' ' + mu) sys.exit(0) if opts.list_extractor_descriptions: for ie in sorted(extractors, key=lambda ie: ie.IE_NAME.lower()): @@ -192,69 +123,66 @@ def _real_main(argv=None): if desc is False: continue 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') - _COUNTS = (u'', u'5', u'10', u'all') - desc += u' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES)) + _SEARCHES = ('cute kittens', 'slithering pythons', 'falling cat', 'angry poodle', 'purple fish', 'running tortoise', 'sleeping bunny') + _COUNTS = ('', '5', '10', 'all') + desc += ' (Example: "%s%s:%s" )' % (ie.SEARCH_KEY, random.choice(_COUNTS), random.choice(_SEARCHES)) compat_print(desc) sys.exit(0) - # Conflicting, missing and erroneous options 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: - 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): - 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: - 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: - 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: numeric_limit = FileDownloader.parse_bytes(opts.ratelimit) if numeric_limit is None: - parser.error(u'invalid rate limit specified') + parser.error('invalid rate limit specified') opts.ratelimit = numeric_limit if opts.min_filesize is not None: numeric_limit = FileDownloader.parse_bytes(opts.min_filesize) if numeric_limit is None: - parser.error(u'invalid min_filesize specified') + parser.error('invalid min_filesize specified') opts.min_filesize = numeric_limit if opts.max_filesize is not None: numeric_limit = FileDownloader.parse_bytes(opts.max_filesize) if numeric_limit is None: - parser.error(u'invalid max_filesize specified') + parser.error('invalid max_filesize specified') opts.max_filesize = numeric_limit if opts.retries is not None: try: opts.retries = int(opts.retries) except (TypeError, ValueError): - parser.error(u'invalid retry count specified') + parser.error('invalid retry count specified') if opts.buffersize is not None: numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize) if numeric_buffersize is None: - parser.error(u'invalid buffer size specified') + parser.error('invalid buffer size specified') opts.buffersize = numeric_buffersize 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: - 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.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: opts.audioquality = opts.audioquality.strip('k').strip('K') 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 not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']: - parser.error(u'invalid video recode format specified') + parser.error('invalid video recode format specified') if opts.date is not None: date = DateRange.day(opts.date) else: 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 if opts.extractaudio and not opts.keepvideo and opts.format is None: @@ -262,28 +190,28 @@ def _real_main(argv=None): # --all-sub automatically sets --write-sub if --write-auto-sub is not 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 if sys.version_info < (3,): # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems) if opts.outtmpl is not None: opts.outtmpl = opts.outtmpl.decode(preferredencoding()) - outtmpl =((opts.outtmpl is not None and opts.outtmpl) - or (opts.format == '-1' and opts.usetitle and u'%(title)s-%(id)s-%(format)s.%(ext)s') - or (opts.format == '-1' and u'%(id)s-%(format)s.%(ext)s') - or (opts.usetitle and opts.autonumber and u'%(autonumber)s-%(title)s-%(id)s.%(ext)s') - or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s') - or (opts.useid and u'%(id)s.%(ext)s') - or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s') - or DEFAULT_OUTTMPL) + outtmpl = ((opts.outtmpl is not None and opts.outtmpl) + or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') + or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') + or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') + or (opts.usetitle and '%(title)s-%(id)s.%(ext)s') + or (opts.useid and '%(id)s.%(ext)s') + or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') + or DEFAULT_OUTTMPL) if not os.path.splitext(outtmpl)[1] and opts.extractaudio: - parser.error(u'Cannot download a video and extract audio into the same' - u' file! Use "{0}.%(ext)s" instead of "{0}" as the output' - u' template'.format(outtmpl)) + parser.error('Cannot download a video and extract audio into the same' + ' file! Use "{0}.%(ext)s" instead of "{0}" as the output' + ' 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 - download_archive_fn = os.path.expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive + 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 or opts.dump_single_json + download_archive_fn = compat_expanduser(opts.download_archive) if opts.download_archive is not None else opts.download_archive ydl_opts = { 'usenetrc': opts.usenetrc, @@ -302,8 +230,9 @@ def _real_main(argv=None): 'forcefilename': opts.getfilename, 'forceformat': opts.getformat, 'forcejson': opts.dumpjson, - 'simulate': opts.simulate, - 'skip_download': (opts.skip_download or opts.simulate or any_printing), + 'dump_single_json': opts.dump_single_json, + 'simulate': opts.simulate or any_printing, + 'skip_download': opts.skip_download, 'format': opts.format, 'format_limit': opts.format_limit, 'listformats': opts.listformats, @@ -368,12 +297,10 @@ def _real_main(argv=None): 'youtube_include_dash_manifest': opts.youtube_include_dash_manifest, 'encoding': opts.encoding, 'exec_cmd': opts.exec_cmd, + 'extract_flat': opts.extract_flat, } with YoutubeDL(ydl_opts) as ydl: - ydl.print_debug_header() - ydl.add_default_info_extractors() - # PostProcessors if opts.joinparts: ydl.add_post_processor(FFmpegJoinVideosPP()) @@ -393,7 +320,6 @@ def _real_main(argv=None): 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: @@ -410,18 +336,19 @@ def _real_main(argv=None): # Maybe do nothing if (len(all_urls) < 1) and (opts.load_info_filename is None): - if not (opts.update_self or opts.rm_cachedir): - parser.error(u'you must provide at least one URL') - else: + if opts.update_self or opts.rm_cachedir: 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') + try: if opts.load_info_filename is not None: retcode = ydl.download_with_info_file(opts.load_info_filename) else: retcode = ydl.download(all_urls) except MaxDownloadsReached: - ydl.to_screen(u'--max-download limit reached, aborting.') + ydl.to_screen('--max-download limit reached, aborting.') retcode = 101 sys.exit(retcode) @@ -433,6 +360,6 @@ def main(argv=None): except DownloadError: sys.exit(1) 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: - sys.exit(u'\nERROR: Interrupted by user') + sys.exit('\nERROR: Interrupted by user') diff --git a/youtube_dl/__main__.py b/youtube_dl/__main__.py index 3fe29c91f..65a0f891c 100755 --- a/youtube_dl/__main__.py +++ b/youtube_dl/__main__.py @@ -1,4 +1,5 @@ #!/usr/bin/env python +from __future__ import unicode_literals # Execute with # $ python youtube_dl/__main__.py (2.6+) diff --git a/youtube_dl/aes.py b/youtube_dl/aes.py index e9c5e2152..5efd0f836 100644 --- a/youtube_dl/aes.py +++ b/youtube_dl/aes.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + __all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_cbc_decrypt', 'aes_decrypt_text'] import base64 @@ -7,10 +9,11 @@ from .utils import bytes_to_intlist, intlist_to_bytes BLOCK_SIZE_BYTES = 16 + def aes_ctr_decrypt(data, key, counter): """ Decrypt with aes in counter mode - + @param {int[]} data cipher @param {int[]} key 16/24/32-Byte cipher key @param {instance} counter Instance whose next_value function (@returns {int[]} 16-Byte block) @@ -19,23 +22,24 @@ def aes_ctr_decrypt(data, key, counter): """ expanded_key = key_expansion(key) block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES)) - - decrypted_data=[] + + decrypted_data = [] for i in range(block_count): counter_block = counter.next_value() - block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES] - block += [0]*(BLOCK_SIZE_BYTES - len(block)) - + block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES] + block += [0] * (BLOCK_SIZE_BYTES - len(block)) + cipher_counter_block = aes_encrypt(counter_block, expanded_key) decrypted_data += xor(block, cipher_counter_block) decrypted_data = decrypted_data[:len(data)] - + return decrypted_data + def aes_cbc_decrypt(data, key, iv): """ Decrypt with aes in CBC mode - + @param {int[]} data cipher @param {int[]} key 16/24/32-Byte cipher key @param {int[]} iv 16-Byte IV @@ -43,94 +47,98 @@ def aes_cbc_decrypt(data, key, iv): """ expanded_key = key_expansion(key) block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES)) - - decrypted_data=[] + + decrypted_data = [] previous_cipher_block = iv for i in range(block_count): - block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES] - block += [0]*(BLOCK_SIZE_BYTES - len(block)) - + block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES] + block += [0] * (BLOCK_SIZE_BYTES - len(block)) + decrypted_block = aes_decrypt(block, expanded_key) decrypted_data += xor(decrypted_block, previous_cipher_block) previous_cipher_block = block decrypted_data = decrypted_data[:len(data)] - + return decrypted_data + def key_expansion(data): """ Generate key schedule - + @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 key_size_bytes = len(data) expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES - + while len(data) < expanded_key_size_bytes: temp = data[-4:] temp = key_schedule_core(temp, rcon_iteration) 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): 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: temp = data[-4:] temp = sub_bytes(temp) - 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): + 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): 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] - + return data + def aes_encrypt(data, expanded_key): """ Encrypt one block with aes - + @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 """ rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1 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 = shift_rows(data) if i != rounds: 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 + def aes_decrypt(data, expanded_key): """ Decrypt one block with aes - + @param {int[]} data 16-Byte cipher @param {int[]} expanded_key 176/208/240-Byte expanded key @returns {int[]} 16-Byte state """ rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 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: data = mix_columns_inv(data) data = shift_rows_inv(data) data = sub_bytes_inv(data) data = xor(data, expanded_key[:BLOCK_SIZE_BYTES]) - + return data + def aes_decrypt_text(data, password, key_size_bytes): """ Decrypt text @@ -138,33 +146,34 @@ def aes_decrypt_text(data, password, key_size_bytes): - 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) - Mode of operation is 'counter' - + @param {str} data Base64 encoded string @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 @returns {str} Decrypted data """ NONCE_LENGTH_BYTES = 8 - + data = bytes_to_intlist(base64.b64decode(data)) 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) - + nonce = data[:NONCE_LENGTH_BYTES] cipher = data[NONCE_LENGTH_BYTES:] - + class Counter: - __value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES) + __value = nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES) + def next_value(self): temp = self.__value self.__value = inc(self.__value) return temp - + decrypted_data = aes_ctr_decrypt(cipher, key, Counter()) plaintext = intlist_to_bytes(decrypted_data) - + return plaintext RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36) @@ -200,14 +209,14 @@ 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, 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) -MIX_COLUMN_MATRIX = ((0x2,0x3,0x1,0x1), - (0x1,0x2,0x3,0x1), - (0x1,0x1,0x2,0x3), - (0x3,0x1,0x1,0x2)) -MIX_COLUMN_MATRIX_INV = ((0xE,0xB,0xD,0x9), - (0x9,0xE,0xB,0xD), - (0xD,0x9,0xE,0xB), - (0xB,0xD,0x9,0xE)) +MIX_COLUMN_MATRIX = ((0x2, 0x3, 0x1, 0x1), + (0x1, 0x2, 0x3, 0x1), + (0x1, 0x1, 0x2, 0x3), + (0x3, 0x1, 0x1, 0x2)) +MIX_COLUMN_MATRIX_INV = ((0xE, 0xB, 0xD, 0x9), + (0x9, 0xE, 0xB, 0xD), + (0xD, 0x9, 0xE, 0xB), + (0xB, 0xD, 0x9, 0xE)) 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, 0xE5, 0x34, 0x5C, 0xE4, 0x37, 0x59, 0xEB, 0x26, 0x6A, 0xBE, 0xD9, 0x70, 0x90, 0xAB, 0xE6, 0x31, @@ -241,30 +250,37 @@ 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, 0x67, 0x4a, 0xed, 0xde, 0xc5, 0x31, 0xfe, 0x18, 0x0d, 0x63, 0x8c, 0x80, 0xc0, 0xf7, 0x70, 0x07) + def sub_bytes(data): return [SBOX[x] for x in data] + def sub_bytes_inv(data): return [SBOX_INV[x] for x in data] + def rotate(data): return data[1:] + [data[0]] + def key_schedule_core(data, rcon_iteration): data = rotate(data) data = sub_bytes(data) data[0] = data[0] ^ RCON[rcon_iteration] - + return data + 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): - if(a==0 or b==0): + if(a == 0 or b == 0): return 0 return RIJNDAEL_EXP_TABLE[(RIJNDAEL_LOG_TABLE[a] + RIJNDAEL_LOG_TABLE[b]) % 0xFF] + def mix_column(data, matrix): data_mixed = [] for row in range(4): @@ -275,33 +291,38 @@ def mix_column(data, matrix): data_mixed.append(mixed) return data_mixed + def mix_columns(data, matrix=MIX_COLUMN_MATRIX): data_mixed = [] 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) return data_mixed + def mix_columns_inv(data): return mix_columns(data, MIX_COLUMN_MATRIX_INV) + def shift_rows(data): data_shifted = [] for column 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 + def shift_rows_inv(data): data_shifted = [] for column 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 + def inc(data): - data = data[:] # copy - for i in range(len(data)-1,-1,-1): + data = data[:] # copy + for i in range(len(data) - 1, -1, -1): if data[i] == 255: data[i] = 0 else: diff --git a/youtube_dl/cache.py b/youtube_dl/cache.py index 79ff09f78..5fe839eb1 100644 --- a/youtube_dl/cache.py +++ b/youtube_dl/cache.py @@ -8,9 +8,8 @@ import re import shutil import traceback -from .utils import ( - write_json_file, -) +from .compat import compat_expanduser, compat_getenv +from .utils import write_json_file class Cache(object): @@ -20,9 +19,9 @@ class Cache(object): def _get_root_dir(self): res = self._ydl.params.get('cachedir') 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') - return os.path.expanduser(res) + return compat_expanduser(res) def _get_cache_fn(self, section, key, dtype): assert re.match(r'^[a-zA-Z0-9_.-]+$', section), \ diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py new file mode 100644 index 000000000..27596687d --- /dev/null +++ b/youtube_dl/compat.py @@ -0,0 +1,356 @@ +from __future__ import unicode_literals + +import getpass +import optparse +import os +import re +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: + 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: + 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, unicode + 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: + compat_str = unicode # Python 2 +except NameError: + compat_str = 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 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 not 'HOMEPATH' 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: + (lambda x: x)(**{'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 + + +# 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 + + +__all__ = [ + 'compat_HTTPError', + 'compat_chr', + 'compat_cookiejar', + 'compat_expanduser', + 'compat_getenv', + 'compat_getpass', + 'compat_html_entities', + 'compat_html_parser', + 'compat_http_client', + 'compat_kwargs', + 'compat_ord', + 'compat_parse_qs', + 'compat_print', + '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', +] diff --git a/youtube_dl/downloader/__init__.py b/youtube_dl/downloader/__init__.py index 4ea5811a5..31e28df58 100644 --- a/youtube_dl/downloader/__init__.py +++ b/youtube_dl/downloader/__init__.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals from .common import FileDownloader from .hls import HlsFD +from .hls import NativeHlsFD from .http import HttpFD from .mplayer import MplayerFD from .rtmp import RtmpFD @@ -19,6 +20,8 @@ def get_suitable_downloader(info_dict): if url.startswith('rtmp'): return RtmpFD + if protocol == 'm3u8_native': + return NativeHlsFD if (protocol == 'm3u8') or (protocol is None and determine_ext(url) == 'm3u8'): return HlsFD if url.startswith('mms') or url.startswith('rtsp'): @@ -27,3 +30,8 @@ def get_suitable_downloader(info_dict): return F4mFD else: return HttpFD + +__all__ = [ + 'get_suitable_downloader', + 'FileDownloader', +] diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index 9ce97f5fe..c0af50c59 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re import sys @@ -42,6 +44,7 @@ class FileDownloader(object): Subclasses of this one must re-define the real_download method. """ + _TEST_FILE_SIZE = 10241 params = None def __init__(self, ydl, params): @@ -78,7 +81,7 @@ class FileDownloader(object): if total is None: return None dif = now - start - if current == 0 or dif < 0.001: # One millisecond + if current == 0 or dif < 0.001: # One millisecond return None rate = float(current) / dif return int((float(total) - float(current)) / rate) @@ -92,7 +95,7 @@ class FileDownloader(object): @staticmethod def calc_speed(start, now, bytes): dif = now - start - if bytes == 0 or dif < 0.001: # One millisecond + if bytes == 0 or dif < 0.001: # One millisecond return None return float(bytes) / dif @@ -105,7 +108,7 @@ class FileDownloader(object): @staticmethod def best_block_size(elapsed_time, bytes): 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: return int(new_max) rate = bytes / elapsed_time @@ -158,14 +161,14 @@ class FileDownloader(object): def temp_name(self, 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))): return filename - return filename + u'.part' + return filename + '.part' def undo_temp_name(self, filename): - if filename.endswith(u'.part'): - return filename[:-len(u'.part')] + if filename.endswith('.part'): + return filename[:-len('.part')] return filename def try_rename(self, old_filename, new_filename): @@ -174,7 +177,7 @@ class FileDownloader(object): return os.rename(encodeFilename(old_filename), encodeFilename(new_filename)) 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): """Try to set the last-modified time of the given file.""" @@ -199,10 +202,10 @@ class FileDownloader(object): def report_destination(self, 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): - fullmsg = u'[download] ' + msg + fullmsg = '[download] ' + msg if self.params.get('progress_with_newline', False): self.to_screen(fullmsg) else: @@ -210,13 +213,13 @@ class FileDownloader(object): prev_len = getattr(self, '_report_progress_prev_line_length', 0) if prev_len > len(fullmsg): - fullmsg += u' ' * (prev_len - len(fullmsg)) + fullmsg += ' ' * (prev_len - len(fullmsg)) self._report_progress_prev_line_length = len(fullmsg) - clear_line = u'\r' + clear_line = '\r' 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_console_title(u'youtube-dl ' + msg) + self.to_console_title('youtube-dl ' + msg) def report_progress(self, percent, data_len_str, speed, eta): """Report download progress.""" @@ -232,7 +235,7 @@ class FileDownloader(object): percent_str = 'Unknown %' speed_str = self.format_speed(speed) - msg = (u'%s of %s at %s ETA %s' % + msg = ('%s of %s at %s ETA %s' % (percent_str, data_len_str, speed_str, eta_str)) self._report_progress_status(msg) @@ -242,37 +245,37 @@ class FileDownloader(object): 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) + msg = '%s at %s (%s)' % (downloaded_str, speed_str, elapsed_str) self._report_progress_status(msg) def report_finish(self, data_len_str, tot_time): """Report download finished.""" if self.params.get('noprogress', False): - self.to_screen(u'[download] Download completed') + self.to_screen('[download] Download completed') else: self._report_progress_status( - (u'100%% of %s in %s' % + ('100%% of %s in %s' % (data_len_str, self.format_seconds(tot_time))), is_last_line=True) def report_resuming_byte(self, resume_len): """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): """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): """Report file has already been fully downloaded.""" 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: - 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): """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): """Download to a filename using the info from info_dict @@ -292,7 +295,7 @@ class FileDownloader(object): def real_download(self, filename, info_dict): """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): for ph in self._progress_hooks: diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index 71353f607..7cd22c504 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -16,6 +16,7 @@ from ..utils import ( format_bytes, encodeFilename, sanitize_open, + xpath_text, ) @@ -54,7 +55,7 @@ class FlvReader(io.BytesIO): if size == 1: real_size = self.read_unsigned_long_long() 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): # version @@ -179,7 +180,7 @@ def build_fragments_list(boot_info): n_frags = segment_run_entry[1] fragment_run_entry_table = boot_info['fragments'][0]['fragments'] 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)): + for (i, frag_number) in zip(range(1, n_frags + 1), itertools.count(first_frag_number)): res.append((1, frag_number)) return res @@ -224,13 +225,15 @@ class F4mFD(FileDownloader): self.to_screen('[download] Downloading f4m manifest') manifest = self.ydl.urlopen(man_url).read() self.report_destination(filename) - http_dl = HttpQuietDownloader(self.ydl, + http_dl = HttpQuietDownloader( + self.ydl, { 'continuedl': True, 'quiet': True, 'noprogress': True, 'test': self.params.get('test', False), - }) + } + ) doc = etree.fromstring(manifest) formats = [(int(f.attrib.get('bitrate', -1)), f) for f in doc.findall(_add_ns('media'))] @@ -243,14 +246,23 @@ class F4mFD(FileDownloader): lambda f: int(f[0]) == requested_bitrate, formats))[0] 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')) + if bootstrap_node.text is None: + bootstrap_url = compat_urlparse.urljoin( + base_url, bootstrap_node.attrib['url']) + bootstrap = self.ydl.urlopen(bootstrap_url).read() + else: + bootstrap = base64.b64decode(bootstrap_node.text) metadata = base64.b64decode(media.find(_add_ns('metadata')).text) boot_info = read_bootstrap_info(bootstrap) + fragments_list = build_fragments_list(boot_info) if self.params.get('test', False): # We only download the first fragment fragments_list = fragments_list[:1] 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')) tmpfilename = self.temp_name(filename) (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb') @@ -267,7 +279,7 @@ class F4mFD(FileDownloader): def frag_progress_hook(status): frag_total_bytes = status.get('total_bytes', 0) estimated_size = (state['downloaded_bytes'] + - (total_frags - state['frag_counter']) * frag_total_bytes) + (total_frags - state['frag_counter']) * frag_total_bytes) if status['status'] == 'finished': state['downloaded_bytes'] += frag_total_bytes state['frag_counter'] += 1 @@ -277,19 +289,21 @@ class F4mFD(FileDownloader): frag_downloaded_bytes = status['downloaded_bytes'] byte_counter = state['downloaded_bytes'] + 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 += frag_progress / float(total_frags) eta = self.calc_eta(start, time.time(), estimated_size, byte_counter) self.report_progress(progress, format_bytes(estimated_size), - status.get('speed'), eta) + status.get('speed'), eta) http_dl.add_progress_hook(frag_progress_hook) frags_filenames = [] for (seg_i, frag_i) in fragments_list: name = 'Seg%d-Frag%d' % (seg_i, frag_i) url = base_url + name + if akamai_pv: + url += '?' + akamai_pv.strip(';') frag_filename = '%s-%s' % (tmpfilename, name) success = http_dl.download(frag_filename, {'url': url}) if not success: diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 32852f333..954beffd5 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -1,8 +1,13 @@ +from __future__ import unicode_literals + import os +import re import subprocess from .common import FileDownloader from ..utils import ( + compat_urlparse, + compat_urllib_request, check_executable, encodeFilename, ) @@ -23,14 +28,14 @@ class HlsFD(FileDownloader): 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.') + self.report_error('m3u8 download detected but ffmpeg or avconv could not be found. Please install one.') return False cmd = [program] + args retval = subprocess.call(cmd) if retval == 0: fsize = os.path.getsize(encodeFilename(tmpfilename)) - self.to_screen(u'\r[%s] %s bytes' % (cmd[0], fsize)) + self.to_screen('\r[%s] %s bytes' % (cmd[0], fsize)) self.try_rename(tmpfilename, filename) self._hook_progress({ 'downloaded_bytes': fsize, @@ -40,6 +45,59 @@ class HlsFD(FileDownloader): }) return True else: - self.to_stderr(u"\n") - self.report_error(u'%s exited with code %d' % (program, retval)) + self.to_stderr('\n') + self.report_error('%s exited with code %d' % (program, retval)) 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 diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index 6caf7451e..8491cee8a 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import time @@ -14,8 +16,6 @@ from ..utils import ( class HttpFD(FileDownloader): - _TEST_FILE_SIZE = 10241 - def real_download(self, filename, info_dict): url = info_dict['url'] tmpfilename = self.temp_name(filename) @@ -108,7 +108,7 @@ class HttpFD(FileDownloader): self.report_retry(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 data_len = data.info().get('Content-length', None) @@ -126,10 +126,10 @@ class HttpFD(FileDownloader): min_data_len = self.params.get("min_filesize", None) max_data_len = self.params.get("max_filesize", None) 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 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 data_len_str = format_bytes(data_len) @@ -153,13 +153,13 @@ class HttpFD(FileDownloader): filename = self.undo_temp_name(tmpfilename) self.report_destination(filename) 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 try: stream.write(data_block) except (IOError, OSError) as err: - self.to_stderr(u"\n") - self.report_error(u'unable to write data: %s' % str(err)) + self.to_stderr('\n') + self.report_error('unable to write data: %s' % str(err)) return False if not self.params.get('noresizebuffer', False): block_size = self.best_block_size(after - before, len(data_block)) @@ -190,10 +190,10 @@ class HttpFD(FileDownloader): self.slow_down(start, byte_counter - resume_len) if stream is None: - self.to_stderr(u"\n") - self.report_error(u'Did not get any data blocks') + self.to_stderr('\n') + self.report_error('Did not get any data blocks') return False - if tmpfilename != u'-': + if tmpfilename != '-': stream.close() self.report_finish(data_len_str, (time.time() - start)) if data_len is not None and byte_counter != data_len: diff --git a/youtube_dl/downloader/mplayer.py b/youtube_dl/downloader/mplayer.py index 4de7f15f4..c53195da0 100644 --- a/youtube_dl/downloader/mplayer.py +++ b/youtube_dl/downloader/mplayer.py @@ -1,7 +1,10 @@ +from __future__ import unicode_literals + import os import subprocess from .common import FileDownloader +from ..compat import compat_subprocess_get_DEVNULL from ..utils import ( encodeFilename, ) @@ -13,19 +16,23 @@ class MplayerFD(FileDownloader): self.report_destination(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 try: - subprocess.call(['mplayer', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT) + subprocess.call( + ['mplayer', '-h'], + stdout=compat_subprocess_get_DEVNULL(), stderr=subprocess.STDOUT) except (OSError, IOError): - self.report_error(u'MMS or RTSP download detected but "%s" could not be run' % args[0]) + self.report_error('MMS or RTSP download detected but "%s" could not be run' % args[0]) return False # Download using mplayer. retval = subprocess.call(args) if retval == 0: 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._hook_progress({ 'downloaded_bytes': fsize, @@ -35,6 +42,6 @@ class MplayerFD(FileDownloader): }) return True else: - self.to_stderr(u"\n") - self.report_error(u'mplayer exited with code %d' % retval) + self.to_stderr('\n') + self.report_error('mplayer exited with code %d' % retval) return False diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py index 5eb108302..58ae2005c 100644 --- a/youtube_dl/downloader/rtmp.py +++ b/youtube_dl/downloader/rtmp.py @@ -12,9 +12,15 @@ from ..utils import ( compat_str, 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): def real_download(self, filename, info_dict): def run_rtmpdump(args): @@ -40,13 +46,13 @@ class RtmpFD(FileDownloader): continue mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec \(([0-9]{1,2}\.[0-9])%\)', line) if mobj: - downloaded_data_len = int(float(mobj.group(1))*1024) + downloaded_data_len = int(float(mobj.group(1)) * 1024) percent = float(mobj.group(2)) if not resume_percent: resume_percent = percent resume_downloaded_data_len = downloaded_data_len - eta = self.calc_eta(start, time.time(), 100-resume_percent, percent-resume_percent) - speed = self.calc_speed(start, time.time(), downloaded_data_len-resume_downloaded_data_len) + eta = self.calc_eta(start, time.time(), 100 - resume_percent, percent - resume_percent) + speed = self.calc_speed(start, time.time(), downloaded_data_len - resume_downloaded_data_len) data_len = None if percent > 0: data_len = int(downloaded_data_len * 100 / percent) @@ -66,7 +72,7 @@ class RtmpFD(FileDownloader): # no percent for live streams mobj = re.search(r'([0-9]+\.[0-9]{3}) kB / [0-9]+\.[0-9]{2} sec', line) if mobj: - downloaded_data_len = int(float(mobj.group(1))*1024) + downloaded_data_len = int(float(mobj.group(1)) * 1024) time_now = time.time() speed = self.calc_speed(start, time_now, downloaded_data_len) self.report_progress_live_stream(downloaded_data_len, speed, time_now - start) @@ -82,7 +88,7 @@ class RtmpFD(FileDownloader): if not cursor_in_new_line: self.to_screen('') cursor_in_new_line = True - self.to_screen('[rtmpdump] '+line) + self.to_screen('[rtmpdump] ' + line) proc.wait() if not cursor_in_new_line: self.to_screen('') @@ -174,7 +180,7 @@ class RtmpFD(FileDownloader): while (retval == RD_INCOMPLETE or retval == RD_FAILED) and not test and not live: prevsize = os.path.getsize(encodeFilename(tmpfilename)) 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]) cursize = os.path.getsize(encodeFilename(tmpfilename)) if prevsize == cursize and retval == RD_FAILED: diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e9fceae4c..9387feef1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + from .abc import ABCIE from .academicearth import AcademicEarthCourseIE from .addanime import AddAnimeIE @@ -20,19 +22,23 @@ from .arte import ( ArteTVDDCIE, ArteTVEmbedIE, ) +from .audiomack import AudiomackIE from .auengine import AUEngineIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE from .bbccouk import BBCCoUkIE from .beeg import BeegIE from .behindkink import BehindKinkIE +from .bild import BildIE from .bilibili import BiliBiliIE from .blinkx import BlinkxIE from .bliptv import BlipTVIE, BlipTVUserIE from .bloomberg import BloombergIE +from .bpb import BpbIE from .br import BRIE from .breakcom import BreakIE from .brightcove import BrightcoveIE +from .buzzfeed import BuzzFeedIE from .byutv import BYUtvIE from .c56 import C56IE from .canal13cl import Canal13clIE @@ -60,9 +66,11 @@ from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE from .condenast import CondeNastIE from .cracked import CrackedIE from .criterion import CriterionIE -from .crunchyroll import CrunchyrollIE +from .crunchyroll import ( + CrunchyrollIE, + CrunchyrollShowPlaylistIE +) from .cspan import CSpanIE -from .d8 import D8IE from .dailymotion import ( DailymotionIE, DailymotionPlaylistIE, @@ -111,6 +119,7 @@ from .fktv import ( FKTVPosteckeIE, ) from .flickr import FlickrIE +from .folketinget import FolketingetIE from .fourtube import FourTubeIE from .franceculture import FranceCultureIE from .franceinter import FranceInterIE @@ -123,6 +132,7 @@ from .francetv import ( ) from .freesound import FreesoundIE from .freespeech import FreespeechIE +from .freevideo import FreeVideoIE from .funnyordie import FunnyOrDieIE from .gamekings import GamekingsIE from .gameone import ( @@ -134,13 +144,18 @@ from .gamestar import GameStarIE from .gametrailers import GametrailersIE from .gdcvault import GDCVaultIE from .generic import GenericIE +from .glide import GlideIE +from .globo import GloboIE from .godtube import GodTubeIE +from .goldenmoustache import GoldenMoustacheIE +from .golem import GolemIE from .googleplus import GooglePlusIE from .googlesearch import GoogleSearchIE from .gorillavid import GorillaVidIE from .goshgay import GoshgayIE from .grooveshark import GroovesharkIE from .hark import HarkIE +from .heise import HeiseIE from .helsinki import HelsinkiIE from .hentaistigma import HentaiStigmaIE from .hornbunny import HornBunnyIE @@ -170,7 +185,6 @@ from .jadorecettepub import JadoreCettePubIE from .jeuxvideo import JeuxVideoIE from .jove import JoveIE from .jukebox import JukeboxIE -from .justintv import JustinTVIE from .jpopsukitv import JpopsukiIE from .kankan import KankanIE from .keezmovies import KeezMoviesIE @@ -181,6 +195,7 @@ from .kontrtube import KontrTubeIE from .krasview import KrasViewIE from .ku6 import Ku6IE from .la7 import LA7IE +from .laola1tv import Laola1TvIE from .lifenews import LifeNewsIE from .liveleak import LiveLeakIE from .livestream import ( @@ -188,6 +203,7 @@ from .livestream import ( LivestreamOriginalIE, LivestreamShortenerIE, ) +from .lrt import LRTIE from .lynda import ( LyndaIE, LyndaCourseIE @@ -199,6 +215,7 @@ from .malemotion import MalemotionIE from .mdr import MDRIE from .metacafe import MetacafeIE from .metacritic import MetacriticIE +from .mgoon import MgoonIE from .ministrygrid import MinistryGridIE from .mit import TechTVMITIE, MITIE, OCWMITIE from .mitele import MiTeleIE @@ -208,6 +225,7 @@ from .mpora import MporaIE from .moevideo import MoeVideoIE from .mofosex import MofosexIE from .mojvideo import MojvideoIE +from .moniker import MonikerIE from .mooshare import MooshareIE from .morningstar import MorningstarIE from .motherless import MotherlessIE @@ -220,6 +238,7 @@ from .mtv import ( MTVServicesEmbeddedIE, MTVIggyIE, ) +from .muenchentv import MuenchenTVIE from .musicplayon import MusicPlayOnIE from .musicvault import MusicVaultIE from .muzu import MuzuTVIE @@ -237,8 +256,9 @@ from .ndtv import NDTVIE from .newgrounds import NewgroundsIE from .newstube import NewstubeIE from .nfb import NFBIE +from .nfl import NFLIE from .nhl import NHLIE, NHLVideocenterIE -from .niconico import NiconicoIE +from .niconico import NiconicoIE, NiconicoPlaylistIE from .ninegag import NineGagIE from .noco import NocoIE from .normalboots import NormalbootsIE @@ -246,7 +266,10 @@ from .nosvideo import NosVideoIE from .novamov import NovaMovIE from .nowness import NownessIE from .nowvideo import NowVideoIE -from .npo import NPOIE +from .npo import ( + NPOIE, + TegenlichtVproIE, +) from .nrk import ( NRKIE, NRKTVIE, @@ -254,6 +277,7 @@ from .nrk import ( from .ntv import NTVIE from .nytimes import NYTimesIE from .nuvid import NuvidIE +from .oktoberfesttv import OktoberfestTVIE from .ooyala import OoyalaIE from .orf import ( ORFTVthekIE, @@ -263,7 +287,10 @@ from .orf import ( from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE from .pbs import PBSIE +from .phoenix import PhoenixIE from .photobucket import PhotobucketIE +from .planetaplay import PlanetaPlayIE +from .played import PlayedIE from .playfm import PlayFMIE from .playvid import PlayvidIE from .podomatic import PodomaticIE @@ -274,6 +301,7 @@ from .pornoxo import PornoXOIE from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE from .pyvideo import PyvideoIE +from .quickvid import QuickVidIE from .radiofrance import RadioFranceIE from .rai import RaiIE from .rbmaradio import RBMARadioIE @@ -302,6 +330,8 @@ from .sbs import SBSIE from .scivee import SciVeeIE from .screencast import ScreencastIE from .servingsys import ServingSysIE +from .sexu import SexuIE +from .sexykarma import SexyKarmaIE from .shared import SharedIE from .sharesix import ShareSixIE from .sina import SinaIE @@ -332,7 +362,10 @@ from .spankwire import SpankwireIE from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE from .spike import SpikeIE +from .sport5 import Sport5IE +from .sportbox import SportBoxIE from .sportdeutschland import SportDeutschlandIE +from .srmediathek import SRMediathekIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE from .streamcloud import StreamcloudIE @@ -342,6 +375,8 @@ from .swrmediathek import SWRMediathekIE from .syfy import SyfyIE from .sztvhu import SztvHuIE from .tagesschau import TagesschauIE +from .tapely import TapelyIE +from .tass import TassIE from .teachertube import ( TeacherTubeIE, TeacherTubeUserIE, @@ -350,15 +385,24 @@ from .teachingchannel import TeachingChannelIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .telebruxelles import TeleBruxellesIE +from .telecinco import TelecincoIE from .telemb import TeleMBIE from .tenplay import TenPlayIE from .testurl import TestURLIE from .tf1 import TF1IE +from .theonion import TheOnionIE from .theplatform import ThePlatformIE +from .thesixtyone import TheSixtyOneIE from .thisav import ThisAVIE from .tinypic import TinyPicIE from .tlc import TlcIE, TlcDeIE +from .tmz import TMZIE from .tnaflix import TNAFlixIE +from .thvideo import ( + THVideoIE, + THVideoPlaylistIE +) from .toutv import TouTvIE from .toypics import ToypicsUserIE, ToypicsIE from .traileraddict import TrailerAddictIE @@ -367,11 +411,13 @@ from .trutube import TruTubeIE from .tube8 import Tube8IE from .tudou import TudouIE from .tumblr import TumblrIE +from .tunein import TuneInIE from .turbo import TurboIE from .tutv import TutvIE from .tvigle import TvigleIE from .tvp import TvpIE from .tvplay import TVPlayIE +from .twitch import TwitchIE from .ubu import UbuIE from .udemy import ( UdemyIE, @@ -387,22 +433,26 @@ from .vesti import VestiIE from .vevo import VevoIE from .vgtv import VGTVIE from .vh1 import VH1IE +from .vice import ViceIE from .viddler import ViddlerIE from .videobam import VideoBamIE from .videodetective import VideoDetectiveIE from .videolecturesnet import VideoLecturesNetIE from .videofyme import VideofyMeIE +from .videomega import VideoMegaIE from .videopremium import VideoPremiumIE from .videott import VideoTtIE from .videoweed import VideoWeedIE from .vidme import VidmeIE +from .vidzi import VidziIE from .vimeo import ( VimeoIE, - VimeoChannelIE, - VimeoUserIE, VimeoAlbumIE, + VimeoChannelIE, VimeoGroupsIE, + VimeoLikesIE, VimeoReviewIE, + VimeoUserIE, VimeoWatchLaterIE, ) from .vimple import VimpleIE @@ -411,12 +461,17 @@ from .vine import ( VineUserIE, ) from .viki import VikiIE -from .vk import VKIE +from .vk import ( + VKIE, + VKUserVideosIE, +) from .vodlocker import VodlockerIE from .vporn import VpornIE +from .vrt import VRTIE from .vube import VubeIE from .vuclip import VuClipIE from .vulture import VultureIE +from .walla import WallaIE from .washingtonpost import WashingtonPostIE from .wat import WatIE from .wayofthemaster import WayOfTheMasterIE @@ -433,17 +488,19 @@ from .wrzuta import WrzutaIE from .xbef import XBefIE from .xboxclips import XboxClipsIE from .xhamster import XHamsterIE +from .xminus import XMinusIE from .xnxx import XNXXIE from .xvideos import XVideosIE from .xtube import XTubeUserIE, XTubeIE from .yahoo import ( YahooIE, - YahooNewsIE, YahooSearchIE, ) +from .ynet import YnetIE from .youjizz import YouJizzIE from .youku import YoukuIE from .youporn import YouPornIE +from .yourupload import YourUploadIE from .youtube import ( YoutubeIE, YoutubeChannelIE, @@ -461,9 +518,11 @@ from .youtube import ( YoutubeUserIE, YoutubeWatchLaterIE, ) - from .zdf import ZDFIE - +from .zingmp3 import ( + ZingMp3SongIE, + ZingMp3AlbumIE, +) _ALL_CLASSES = [ klass @@ -482,4 +541,4 @@ def gen_extractors(): def get_info_extractor(ie_name): """Returns the info extractor class with the given ie_name""" - return globals()[ie_name+'IE'] + return globals()[ie_name + 'IE'] diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index 7d89f44ee..dc0fb85d6 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -11,19 +11,18 @@ class ABCIE(InfoExtractor): _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P\d+)' _TEST = { - 'url': 'http://www.abc.net.au/news/2014-07-25/bringing-asylum-seekers-to-australia-would-give/5624716', - 'md5': 'dad6f8ad011a70d9ddf887ce6d5d0742', + 'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334', + 'md5': 'cb3dd03b18455a661071ee1e28344d9f', 'info_dict': { - 'id': '5624716', + 'id': '5868334', 'ext': 'mp4', - 'title': 'Bringing asylum seekers to Australia would give them right to asylum claims: professor', - 'description': 'md5:ba36fa5e27e5c9251fd929d339aea4af', + 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone', + 'description': 'md5:809ad29c67a05f54eb41f2a105693a67', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) urls_info_json = self._search_regex( diff --git a/youtube_dl/extractor/academicearth.py b/youtube_dl/extractor/academicearth.py index c983ef0f5..47313fba8 100644 --- a/youtube_dl/extractor/academicearth.py +++ b/youtube_dl/extractor/academicearth.py @@ -1,4 +1,5 @@ from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -18,15 +19,14 @@ class AcademicEarthCourseIE(InfoExtractor): } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - playlist_id = m.group('id') + playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) title = self._html_search_regex( - r'

    ]*?>(.*?)

    ', webpage, u'title') + r'

    ]*?>(.*?)

    ', webpage, 'title') description = self._html_search_regex( r'

    ]*?>(.*?)

    ', - webpage, u'description', fatal=False) + webpage, 'description', fatal=False) urls = re.findall( r'
  • \s*?', webpage) diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py index fcf296057..203936e54 100644 --- a/youtube_dl/extractor/addanime.py +++ b/youtube_dl/extractor/addanime.py @@ -3,19 +3,19 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_HTTPError, compat_str, compat_urllib_parse, compat_urllib_parse_urlparse, - +) +from ..utils import ( ExtractorError, ) class AddAnimeIE(InfoExtractor): - - _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P[\w_]+)(?:.*)' + _VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video\.php\?(?:.*?)v=(?P[\w_]+)(?:.*)' _TEST = { 'url': 'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9', 'md5': '72954ea10bc979ab5e2eb288b21425a0', @@ -28,9 +28,9 @@ class AddAnimeIE(InfoExtractor): } def _real_extract(self, url): + video_id = self._match_id(url) + try: - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') webpage = self._download_webpage(url, video_id) except ExtractorError as ee: if not isinstance(ee.cause, compat_HTTPError) or \ @@ -48,7 +48,7 @@ class AddAnimeIE(InfoExtractor): r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);', redir_webpage) 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)) parsed_url = compat_urllib_parse_urlparse(url) diff --git a/youtube_dl/extractor/adultswim.py b/youtube_dl/extractor/adultswim.py index b4b40f2d4..0d05cbb4b 100644 --- a/youtube_dl/extractor/adultswim.py +++ b/youtube_dl/extractor/adultswim.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor + class AdultSwimIE(InfoExtractor): _VALID_URL = r'https?://video\.adultswim\.com/(?P.+?)(?:\.html)?(?:\?.*)?(?:#.*)?$' _TEST = { diff --git a/youtube_dl/extractor/allocine.py b/youtube_dl/extractor/allocine.py index 7bd797884..398e93bfb 100644 --- a/youtube_dl/extractor/allocine.py +++ b/youtube_dl/extractor/allocine.py @@ -22,7 +22,7 @@ class AllocineIE(InfoExtractor): 'id': '19546517', 'ext': 'mp4', 'title': 'Astérix - Le Domaine des Dieux Teaser VF', - 'description': 'md5:4a754271d9c6f16c72629a8a993ee884', + 'description': 'md5:abcd09ce503c6560512c14ebfdb720d2', 'thumbnail': 're:http://.*\.jpg', }, }, { diff --git a/youtube_dl/extractor/anysex.py b/youtube_dl/extractor/anysex.py index bc64423a3..ad86d6e58 100644 --- a/youtube_dl/extractor/anysex.py +++ b/youtube_dl/extractor/anysex.py @@ -35,7 +35,7 @@ class AnySexIE(InfoExtractor): title = self._html_search_regex(r'(.*?)', webpage, 'title') description = self._html_search_regex( - r'
    ([^<]+)
    ', webpage, 'description', fatal=False) + r'
    ]*>([^<]+)
    ', webpage, 'description', fatal=False) thumbnail = self._html_search_regex( r'preview_url\s*:\s*\'(.*?)\'', webpage, 'thumbnail', fatal=False) @@ -43,7 +43,7 @@ class AnySexIE(InfoExtractor): r'    ([^<]+)', webpage) duration = parse_duration(self._search_regex( - r'Duration: (\d+:\d+)', webpage, 'duration', fatal=False)) + r'Duration: (?:)?(\d+:\d+)', webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( r'Views: (\d+)', webpage, 'view count', fatal=False)) diff --git a/youtube_dl/extractor/aparat.py b/youtube_dl/extractor/aparat.py index 748608826..15006336f 100644 --- a/youtube_dl/extractor/aparat.py +++ b/youtube_dl/extractor/aparat.py @@ -1,5 +1,4 @@ -#coding: utf-8 - +# coding: utf-8 from __future__ import unicode_literals import re @@ -26,8 +25,7 @@ class AparatIE(InfoExtractor): } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = self._match_id(url) # Note: There is an easier-to-parse configuration at # http://www.aparat.com/video/video/config/videohash/%video_id @@ -40,15 +38,15 @@ class AparatIE(InfoExtractor): for i, video_url in enumerate(video_urls): req = HEADRequest(video_url) 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: break 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( - r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False) + r'\s+image:\s*"([^"]+)"', webpage, 'thumbnail', fatal=False) return { 'id': video_id, diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py index 4359b88d1..0c01fa1a1 100644 --- a/youtube_dl/extractor/appletrailers.py +++ b/youtube_dl/extractor/appletrailers.py @@ -70,15 +70,17 @@ class AppleTrailersIE(InfoExtractor): uploader_id = mobj.group('company') playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc') + def fix_html(s): s = re.sub(r'(?s).*?', '', s) s = re.sub(r'', r'', s) # The ' in the onClick attributes are not escaped, it couldn't be parsed # like: http://trailers.apple.com/trailers/wb/gravity/ + def _clean_json(m): return 'iTunes.playURL(%s);' % m.group(1).replace('\'', ''') s = re.sub(self._JSON_RE, _clean_json, s) - s = '' + s + u'' + s = '%s' % s return s doc = self._download_xml(playlist_url, movie, transform_source=fix_html) @@ -86,7 +88,7 @@ class AppleTrailersIE(InfoExtractor): for li in doc.findall('./div/ul/li'): on_click = li.find('.//a').attrib['onClick'] trailer_info_json = self._search_regex(self._JSON_RE, - on_click, 'trailer info') + on_click, 'trailer info') trailer_info = json.loads(trailer_info_json) title = trailer_info['title'] video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower() diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 54cec1c2f..967bd865c 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -4,16 +4,16 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, qualities, - compat_urllib_parse_urlparse, - compat_urllib_parse, int_or_none, parse_duration, unified_strdate, xpath_text, + parse_xml, ) @@ -56,6 +56,11 @@ class ARDMediathekIE(InfoExtractor): if '>Der gewünschte Beitrag ist nicht mehr verfügbar.<' in webpage: raise ExtractorError('Video %s is no longer available' % 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( [r'(.*?)', r'', @@ -187,4 +192,3 @@ class ARDIE(InfoExtractor): 'upload_date': upload_date, 'thumbnail': thumbnail, } - diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 957d35979..219631b9b 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -5,16 +5,15 @@ import re from .common import InfoExtractor from ..utils import ( - ExtractorError, find_xpath_attr, unified_strdate, - determine_ext, get_element_by_id, - compat_str, 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 # add tests. @@ -86,92 +85,70 @@ class ArteTVPlus7IE(InfoExtractor): info = self._download_json(json_url, video_id) 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 = { 'id': player_info['VID'], - 'title': player_info['VTI'], + 'title': title, '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'), } + qfunc = qualities(['HQ', 'MQ', 'EQ', 'SQ']) - all_formats = player_info['VSR'].values() - # Some formats use the m3u8 protocol - all_formats = list(filter(lambda f: f.get('videoFormat') != 'M3U8', all_formats)) - def _match_lang(f): - 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') + formats = [] + for format_id, format_dict in player_info['VSR'].items(): + f = dict(format_dict) + versionCode = f.get('versionCode') - if re.match(r'[A-Z]Q', formats[0]['quality']) is not None: - def sort_key(f): - return ['HQ', 'MQ', 'EQ', 'SQ'].index(f['quality']) - else: - def sort_key(f): - versionCode = f.get('versionCode') - if versionCode is None: - versionCode = '' - return ( - # Sort first by quality - int(f.get('height', -1)), - int(f.get('bitrate', -1)), - # The original version with subtitles has lower relevance - re.match(r'VO-ST(F|A)', versionCode) is None, - # The version with sourds/mal subtitles has also lower relevance - re.match(r'VO?(F|A)-STM\1', versionCode) is None, - # Prefer http downloads over m3u8 - 0 if f['url'].endswith('m3u8') else 1, - ) - 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 = { + langcode = { + 'fr': 'F', + 'de': 'A', + }.get(lang, lang) + lang_rexs = [r'VO?%s' % langcode, r'VO?.-ST%s' % langcode] + lang_pref = ( + None if versionCode is None else ( + 10 if any(re.match(r, versionCode) for r in lang_rexs) + else -10)) + source_pref = 0 + if versionCode is not None: + # The original version with subtitles has lower relevance + if re.match(r'VO-ST(F|A)', versionCode): + source_pref -= 10 + # The version with sourds/mal subtitles has also lower relevance + elif re.match(r'VO?(F|A)-STM\1', versionCode): + source_pref -= 9 + format = { 'format_id': format_id, - 'format_note': format_info.get('versionLibelle'), - 'width': format_info.get('width'), - 'height': height, + 'preference': -10 if f.get('videoFormat') == 'M3U8' else None, + 'language_preference': lang_pref, + '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['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._sort_formats(formats) + + info_dict['formats'] = formats return info_dict diff --git a/youtube_dl/extractor/audiomack.py b/youtube_dl/extractor/audiomack.py new file mode 100644 index 000000000..eeeec768f --- /dev/null +++ b/youtube_dl/extractor/audiomack.py @@ -0,0 +1,69 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from .soundcloud import SoundcloudIE +from ..utils import ExtractorError + +import time + + +class AudiomackIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?audiomack\.com/song/(?P[\w/-]+)' + IE_NAME = 'audiomack' + _TESTS = [ + # hosted on audiomack + { + 'url': 'http://www.audiomack.com/song/roosh-williams/extraordinary', + 'info_dict': + { + 'id': 'roosh-williams/extraordinary', + 'ext': 'mp3', + 'title': 'Roosh Williams - Extraordinary' + } + }, + # hosted on soundcloud via audiomack + { + 'url': 'http://www.audiomack.com/song/xclusiveszone/take-kare', + 'file': '172419696.mp3', + 'info_dict': + { + 'ext': 'mp3', + 'title': 'Young Thug ft Lil Wayne - Take Kare', + "upload_date": "20141016", + "description": "New track produced by London On Da Track called “Take Kare\"\n\nhttp://instagram.com/theyoungthugworld\nhttps://www.facebook.com/ThuggerThuggerCashMoney\n", + "uploader": "Young Thug World" + } + } + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + api_response = self._download_json( + "http://www.audiomack.com/api/music/url/song/%s?_=%d" % ( + video_id, time.time()), + video_id) + + if "url" not in api_response: + raise ExtractorError("Unable to deduce api url of song") + realurl = api_response["url"] + + # Audiomack wraps a lot of soundcloud tracks in their branded wrapper + # - if so, pass the work off to the soundcloud extractor + if SoundcloudIE.suitable(realurl): + return {'_type': 'url', 'url': realurl, 'ie_key': 'Soundcloud'} + + webpage = self._download_webpage(url, video_id) + artist = self._html_search_regex( + r'(.*?)', webpage, "artist") + songtitle = self._html_search_regex( + r'

    .*?(.*?)

    ', + webpage, "title") + title = artist + " - " + songtitle + + return { + 'id': video_id, + 'title': title, + 'url': realurl, + } diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index 20bf12550..1c765532a 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -24,8 +24,7 @@ class AUEngineIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'(?P<title>.+?)', webpage, 'title') diff --git a/youtube_dl/extractor/bambuser.py b/youtube_dl/extractor/bambuser.py index de5d4faf3..1ca0b7cf2 100644 --- a/youtube_dl/extractor/bambuser.py +++ b/youtube_dl/extractor/bambuser.py @@ -18,7 +18,7 @@ class BambuserIE(InfoExtractor): _TEST = { 'url': 'http://bambuser.com/v/4050584', # MD5 seems to be flaky, see https://travis-ci.org/rg3/youtube-dl/jobs/14051016#L388 - #u'md5': 'fba8f7693e48fd4e8641b3fd5539a641', + # 'md5': 'fba8f7693e48fd4e8641b3fd5539a641', 'info_dict': { 'id': '4050584', 'ext': 'flv', @@ -38,7 +38,7 @@ class BambuserIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') info_url = ('http://player-c.api.bambuser.com/getVideo.json?' - '&api_key=%s&vid=%s' % (self._API_KEY, video_id)) + '&api_key=%s&vid=%s' % (self._API_KEY, video_id)) info_json = self._download_webpage(info_url, video_id) info = json.loads(info_json)['result'] @@ -73,10 +73,11 @@ class BambuserChannelIE(InfoExtractor): urls = [] last_id = '' for i in itertools.count(1): - req_url = ('http://bambuser.com/xhr-api/index.php?username={user}' + req_url = ( + 'http://bambuser.com/xhr-api/index.php?username={user}' '&sort=created&access_mode=0%2C1%2C2&limit={count}' '&method=broadcast&format=json&vid_older_than={last}' - ).format(user=user, count=self._STEP, last=last_id) + ).format(user=user, count=self._STEP, last=last_id) req = compat_urllib_request.Request(req_url) # Without setting this header, we wouldn't get any result req.add_header('Referer', 'http://bambuser.com/channel/%s' % user) diff --git a/youtube_dl/extractor/bandcamp.py b/youtube_dl/extractor/bandcamp.py index c569aa4d2..acddbc8f1 100644 --- a/youtube_dl/extractor/bandcamp.py +++ b/youtube_dl/extractor/bandcamp.py @@ -15,13 +15,23 @@ class BandcampIE(InfoExtractor): _VALID_URL = r'https?://.*?\.bandcamp\.com/track/(?P.*)' _TESTS = [{ 'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song', - 'file': '1812978515.mp3', 'md5': 'c557841d5e50261777a6585648adf439', 'info_dict': { - "title": "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", - "duration": 9.8485, + 'id': '1812978515', + 'ext': 'mp3', + 'title': "youtube-dl \"'/\\\u00e4\u21ad - youtube-dl test song \"'/\\\u00e4\u21ad", + 'duration': 9.8485, }, '_skip': 'There is a limit of 200 free downloads / month for the test song' + }, { + 'url': 'http://benprunty.bandcamp.com/track/lanius-battle', + 'md5': '2b68e5851514c20efdff2afc5603b8b4', + 'info_dict': { + 'id': '2650410135', + 'ext': 'mp3', + 'title': 'Lanius (Battle)', + 'uploader': 'Ben Prunty Music', + }, }] def _real_extract(self, url): @@ -59,9 +69,9 @@ class BandcampIE(InfoExtractor): raise ExtractorError('No free songs found') download_link = m_download.group(1) - video_id = re.search( - r'var TralbumData = {(.*?)id: (?P<id>\d*?)$', - webpage, re.MULTILINE | re.DOTALL).group('id') + video_id = self._search_regex( + r'var TralbumData = {.*?id: (?P<id>\d+),?$', + webpage, 'video id', flags=re.MULTILINE | re.DOTALL) download_webpage = self._download_webpage(download_link, video_id, 'Downloading free downloads page') # We get the dictionary of the track from some javascript code @@ -73,12 +83,12 @@ class BandcampIE(InfoExtractor): initial_url = mp3_info['url'] re_url = r'(?P<server>http://(.*?)\.bandcamp\.com)/download/track\?enc=mp3-320&fsig=(?P<fsig>.*?)&id=(?P<id>.*?)&ts=(?P<ts>.*)$' m_url = re.match(re_url, initial_url) - #We build the url we will use to get the final track url + # We build the url we will use to get the final track url # This url is build in Bandcamp in the script download_bunde_*.js request_url = '%s/statdownload/track?enc=mp3-320&fsig=%s&id=%s&ts=%s&.rand=665028774616&.vrs=1' % (m_url.group('server'), m_url.group('fsig'), video_id, m_url.group('ts')) final_url_webpage = self._download_webpage(request_url, video_id, 'Requesting download url') # If we could correctly generate the .rand field the url would be - #in the "download_url" key + # in the "download_url" key final_url = re.search(r'"retry_url":"(.*?)"', final_url_webpage).group(1) return { @@ -100,20 +110,25 @@ class BandcampAlbumIE(InfoExtractor): 'url': 'http://blazo.bandcamp.com/album/jazz-format-mixtape-vol-1', 'playlist': [ { - 'file': '1353101989.mp3', 'md5': '39bc1eded3476e927c724321ddf116cf', 'info_dict': { + 'id': '1353101989', + 'ext': 'mp3', 'title': 'Intro', } }, { - 'file': '38097443.mp3', 'md5': '1a2c32e2691474643e912cc6cd4bffaa', 'info_dict': { + 'id': '38097443', + 'ext': 'mp3', 'title': 'Kero One - Keep It Alive (Blazo remix)', } }, ], + 'info_dict': { + 'title': 'Jazz Format Mixtape vol.1', + }, 'params': { 'playlistend': 2 }, diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py index 75e608f99..6a507e113 100644 --- a/youtube_dl/extractor/bbccouk.py +++ b/youtube_dl/extractor/bbccouk.py @@ -165,10 +165,10 @@ class BBCCoUkIE(SubtitlesInfoExtractor): webpage = self._download_webpage(url, group_id, 'Downloading video page') if re.search(r'id="emp-error" class="notinuk">', webpage): raise ExtractorError('Currently BBC iPlayer TV programmes are available to play in the UK only', - expected=True) + expected=True) playlist = self._download_xml('http://www.bbc.co.uk/iplayer/playlist/%s' % group_id, group_id, - 'Downloading playlist XML') + 'Downloading playlist XML') no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') if no_items is not None: @@ -195,7 +195,7 @@ class BBCCoUkIE(SubtitlesInfoExtractor): duration = int(item.get('duration')) media_selection = self._download_xml( - 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, + 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, programme_id, 'Downloading media selection XML') for media in self._extract_medias(media_selection): @@ -220,4 +220,4 @@ class BBCCoUkIE(SubtitlesInfoExtractor): 'duration': duration, 'formats': formats, 'subtitles': subtitles, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/beeg.py b/youtube_dl/extractor/beeg.py index 314e37f8b..4e79fea8f 100644 --- a/youtube_dl/extractor/beeg.py +++ b/youtube_dl/extractor/beeg.py @@ -40,7 +40,7 @@ class BeegIE(InfoExtractor): title = self._html_search_regex( r'<title>([^<]+)\s*-\s*beeg\.?', webpage, 'title') - + description = self._html_search_regex( r'[^/]+)-(?P\d+)(?:,auto=true)?\.bild\.html' + IE_DESC = 'Bild.de' + _TEST = { + 'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html', + 'md5': 'dd495cbd99f2413502a1713a1156ac8a', + 'info_dict': { + 'id': '38184146', + 'ext': 'mp4', + 'title': 'BILD hat sie getestet', + 'thumbnail': 'http://bilder.bild.de/fotos/stand-das-koennen-die-neuen-ipads-38184138/Bild/1.bild.jpg', + 'duration': 196, + 'description': 'Mit dem iPad Air 2 und dem iPad Mini 3 hat Apple zwei neue Tablet-Modelle präsentiert. BILD-Reporter Sven Stein durfte die Geräte bereits testen. ', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + xml_url = url.split(".bild.html")[0] + ",view=xml.bild.xml" + doc = self._download_xml(xml_url, video_id) + + duration = int_or_none(doc.attrib.get('duration'), scale=1000) + + return { + 'id': video_id, + 'title': doc.attrib['ueberschrift'], + 'description': doc.attrib.get('text'), + 'url': doc.attrib['src'], + 'thumbnail': doc.attrib.get('img'), + 'duration': duration, + } diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index 57d17bea3..da47f27bd 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -64,6 +64,20 @@ class BlipTVIE(SubtitlesInfoExtractor): 'uploader': 'redvsblue', 'uploader_id': '792887', } + }, + { + 'url': 'http://blip.tv/play/gbk766dkj4Yn', + 'md5': 'fe0a33f022d49399a241e84a8ea8b8e3', + 'info_dict': { + 'id': '1749452', + 'ext': 'mp4', + 'upload_date': '20090208', + 'description': 'Witness the first appearance of the Nostalgia Critic character, as Doug reviews the movie Transformers.', + 'title': 'Nostalgia Critic: Transformers', + 'timestamp': 1234068723, + 'uploader': 'NostalgiaCritic', + 'uploader_id': '246467', + } } ] @@ -71,13 +85,16 @@ class BlipTVIE(SubtitlesInfoExtractor): mobj = re.match(self._VALID_URL, url) lookup_id = mobj.group('lookup_id') - # See https://github.com/rg3/youtube-dl/issues/857 + # See https://github.com/rg3/youtube-dl/issues/857 and + # https://github.com/rg3/youtube-dl/issues/4197 if lookup_id: - info_page = self._download_webpage( - 'http://blip.tv/play/%s.x?p=1' % lookup_id, lookup_id, 'Resolving lookup id') - video_id = self._search_regex(r'data-episode-id="([0-9]+)', info_page, 'video_id') - else: - video_id = mobj.group('id') + urlh = self._request_webpage( + 'http://blip.tv/play/%s' % lookup_id, lookup_id, 'Resolving lookup id') + url = compat_urlparse.urlparse(urlh.geturl()) + qs = compat_urlparse.parse_qs(url.query) + mobj = re.match(self._VALID_URL, qs['file'][0]) + + video_id = mobj.group('id') rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS') @@ -113,7 +130,7 @@ class BlipTVIE(SubtitlesInfoExtractor): msg = self._download_webpage( url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url', video_id, 'Resolving URL for %s' % role) - real_url = compat_urlparse.parse_qs(msg)['message'][0] + real_url = compat_urlparse.parse_qs(msg.strip())['message'][0] media_type = media_content.get('type') if media_type == 'text/srt' or url.endswith('.srt'): @@ -165,9 +182,17 @@ class BlipTVIE(SubtitlesInfoExtractor): class BlipTVUserIE(InfoExtractor): - _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' + _VALID_URL = r'(?:(?:https?://(?:\w+\.)?blip\.tv/)|bliptvuser:)(?!api\.swf)([^/]+)/*$' _PAGE_SIZE = 12 IE_NAME = 'blip.tv:user' + _TEST = { + 'url': 'http://blip.tv/actone', + 'info_dict': { + 'id': 'actone', + 'title': 'Act One: The Series', + }, + 'playlist_count': 5, + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -178,6 +203,7 @@ class BlipTVUserIE(InfoExtractor): page = self._download_webpage(url, username, 'Downloading user page') mobj = re.search(r'data-users-id="([^"]+)"', page) page_base = page_base % mobj.group(1) + title = self._og_search_title(page) # Download video ids using BlipTV Ajax calls. Result size per # query is limited (currently to 12 videos) so we need to query @@ -214,4 +240,5 @@ class BlipTVUserIE(InfoExtractor): urls = ['http://blip.tv/%s' % video_id for video_id in video_ids] url_entries = [self.url_result(vurl, 'BlipTV') for vurl in urls] - return [self.playlist_result(url_entries, playlist_title=username)] + return self.playlist_result( + url_entries, playlist_title=title, playlist_id=username) diff --git a/youtube_dl/extractor/bpb.py b/youtube_dl/extractor/bpb.py new file mode 100644 index 000000000..510813f76 --- /dev/null +++ b/youtube_dl/extractor/bpb.py @@ -0,0 +1,37 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class BpbIE(InfoExtractor): + IE_DESC = 'Bundeszentrale für politische Bildung' + _VALID_URL = r'http://www\.bpb\.de/mediathek/(?P[0-9]+)/' + + _TEST = { + 'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr', + 'md5': '0792086e8e2bfbac9cdf27835d5f2093', + 'info_dict': { + 'id': '297', + 'ext': 'mp4', + 'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR', + 'description': 'Joachim Gauck, erster Beauftragter für die Stasi-Unterlagen, spricht auf dem Geschichtsforum über die friedliche Revolution 1989 und eine "gewisse Traurigkeit" im Umgang mit der DDR-Vergangenheit.' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex( + r'

    (.*?)

    ', webpage, 'title') + video_url = self._html_search_regex( + r'(http://film\.bpb\.de/player/dokument_[0-9]+\.mp4)', + webpage, 'video URL') + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': self._og_search_description(webpage), + } diff --git a/youtube_dl/extractor/br.py b/youtube_dl/extractor/br.py index 4e2960c62..45ba51732 100644 --- a/youtube_dl/extractor/br.py +++ b/youtube_dl/extractor/br.py @@ -1,8 +1,6 @@ # coding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( ExtractorError, @@ -26,6 +24,8 @@ class BRIE(InfoExtractor): 'title': 'Wenn das Traditions-Theater wackelt', 'description': 'Heimatsound-Festival 2014: Wenn das Traditions-Theater wackelt', 'duration': 34, + 'uploader': 'BR', + 'upload_date': '20140802', } }, { @@ -66,8 +66,7 @@ class BRIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('id') + display_id = self._match_id(url) page = self._download_webpage(url, display_id) xml_url = self._search_regex( r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL') diff --git a/youtube_dl/extractor/breakcom.py b/youtube_dl/extractor/breakcom.py index 1bfc9f35b..2c0e5eea2 100644 --- a/youtube_dl/extractor/breakcom.py +++ b/youtube_dl/extractor/breakcom.py @@ -4,37 +4,61 @@ import re import json from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_age_limit, +) class BreakIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)' - _TEST = { + _VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P\d+)' + _TESTS = [{ 'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056', - 'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b', + 'md5': '33aa4ff477ecd124d18d7b5d23b87ce5', 'info_dict': { 'id': '2468056', 'ext': 'mp4', 'title': 'When Girls Act Like D-Bags', } - } + }, { + 'url': 'http://www.break.com/video/ugc/baby-flex-2773063', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1).split("-")[-1] - embed_url = 'http://www.break.com/embed/%s' % video_id - webpage = self._download_webpage(embed_url, video_id) - info_json = self._search_regex(r'var embedVars = ({.*})\s*?', - webpage, 'info json', flags=re.DOTALL) - info = json.loads(info_json) - video_url = info['videoUri'] + video_id = self._match_id(url) + webpage = self._download_webpage( + 'http://www.break.com/embed/%s' % video_id, video_id) + info = json.loads(self._search_regex( + r'var embedVars = ({.*})\s*?', + webpage, 'info json', flags=re.DOTALL)) + youtube_id = info.get('youtubeId') if youtube_id: return self.url_result(youtube_id, 'Youtube') - final_url = video_url + '?' + info['AuthToken'] + formats = [{ + 'url': media['uri'] + '?' + info['AuthToken'], + 'tbr': media['bitRate'], + 'width': media['width'], + 'height': media['height'], + } for media in info['media']] + + if not formats: + formats.append({ + 'url': info['videoUri'] + }) + + self._sort_formats(formats) + + duration = int_or_none(info.get('videoLengthInSeconds')) + age_limit = parse_age_limit(info.get('audienceRating')) + return { 'id': video_id, - 'url': final_url, 'title': info['contentName'], 'thumbnail': info['thumbUri'], + 'duration': duration, + 'age_limit': age_limit, + 'formats': formats, } diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 294670386..2db7f9fef 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -14,6 +14,7 @@ from ..utils import ( compat_str, compat_urllib_request, compat_parse_qs, + compat_urllib_parse_urlparse, determine_ext, ExtractorError, @@ -23,7 +24,7 @@ from ..utils import ( class BrightcoveIE(InfoExtractor): - _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*\?(?P.*)' + _VALID_URL = r'https?://.*brightcove\.com/(services|viewer).*?\?(?P.*)' _FEDERATED_URL_TEMPLATE = 'http://c.brightcove.com/services/viewer/htmlFederated?%s' _TESTS = [ @@ -87,6 +88,15 @@ class BrightcoveIE(InfoExtractor): 'description': 'UCI MTB World Cup 2014: Fort William, UK - Downhill Finals', }, }, + { + # playlist test + # from http://support.brightcove.com/en/video-cloud/docs/playlist-support-single-video-players + 'url': 'http://c.brightcove.com/services/viewer/htmlFederated?playerID=3550052898001&playerKey=AQ%7E%7E%2CAAABmA9XpXk%7E%2C-Kp7jNgisre1fG5OdqpAFUTcs0lP_ZoL', + 'info_dict': { + 'title': 'Sealife', + }, + 'playlist_mincount': 7, + }, ] @classmethod @@ -101,6 +111,8 @@ class BrightcoveIE(InfoExtractor): lambda m: m.group(1) + '/>', object_str) # Fix up some stupid XML, see https://github.com/rg3/youtube-dl/issues/1608 object_str = object_str.replace('<--', ' %s\n%s\n\n' % (i, start, end, text) return output - def _convert_subtitles_to_ass(self, subtitles): + def _convert_subtitles_to_ass(self, sub_root): output = '' def ass_bool(strvalue): @@ -128,10 +127,6 @@ class CrunchyrollIE(InfoExtractor): assvalue = '-1' return assvalue - sub_root = xml.etree.ElementTree.fromstring(subtitles) - if not sub_root: - return output - output = '[Script Info]\n' output += 'Title: %s\n' % sub_root.attrib["title"] output += 'ScriptType: v4.00+\n' @@ -188,7 +183,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text return output - def _real_extract(self,url): + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') @@ -231,18 +226,20 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text formats = [] for fmt in re.findall(r'\?p([0-9]{3,4})=1', webpage): stream_quality, stream_format = self._FORMAT_IDS[fmt] - video_format = fmt+'p' + video_format = fmt + 'p' streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/') # urlencode doesn't work! - streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality='+stream_quality+'&media%5Fid='+stream_id+'&video%5Fformat='+stream_format + streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') streamdata_req.add_header('Content-Length', str(len(streamdata_req.data))) - streamdata = self._download_webpage(streamdata_req, video_id, note='Downloading media info for '+video_format) - video_url = self._search_regex(r'([^<]+)', streamdata, 'video_url') - video_play_path = self._search_regex(r'([^<]+)', streamdata, 'video_play_path') + streamdata = self._download_xml( + streamdata_req, video_id, + note='Downloading media info for %s' % video_format) + video_url = streamdata.find('.//host').text + video_play_path = streamdata.find('.//file').text formats.append({ 'url': video_url, - 'play_path': video_play_path, + 'play_path': video_play_path, 'ext': 'flv', 'format': video_format, 'format_id': video_format, @@ -251,8 +248,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text subtitles = {} sub_format = self._downloader.params.get('subtitlesformat', 'srt') for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): - sub_page = self._download_webpage('http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id='+sub_id,\ - video_id, note='Downloading subtitles for '+sub_name) + sub_page = self._download_webpage( + 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id, + video_id, note='Downloading subtitles for ' + sub_name) id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False) iv = self._search_regex(r'([^<]+)', sub_page, 'subtitle_iv', fatal=False) data = self._search_regex(r'([^<]+)', sub_page, 'subtitle_data', fatal=False) @@ -266,18 +264,60 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) if not lang_code: continue + sub_root = xml.etree.ElementTree.fromstring(subtitle) if sub_format == 'ass': - subtitles[lang_code] = self._convert_subtitles_to_ass(subtitle) + subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root) else: - subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle) + subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root) + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return return { - 'id': video_id, - 'title': video_title, + 'id': video_id, + 'title': video_title, 'description': video_description, - 'thumbnail': video_thumbnail, - 'uploader': video_uploader, + 'thumbnail': video_thumbnail, + 'uploader': video_uploader, 'upload_date': video_upload_date, - 'subtitles': subtitles, - 'formats': formats, + 'subtitles': subtitles, + 'formats': formats, + } + + +class CrunchyrollShowPlaylistIE(InfoExtractor): + IE_NAME = "crunchyroll:playlist" + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.com/(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login))(?P[\w\-]+))/?$' + + _TESTS = [{ + 'url': 'http://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', + 'info_dict': { + 'id': 'a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi', + 'title': 'A Bridge to the Starry Skies - Hoshizora e Kakaru Hashi' + }, + 'playlist_count': 13, + }] + + def _real_extract(self, url): + show_id = self._match_id(url) + + webpage = self._download_webpage(url, show_id) + title = self._html_search_regex( + r'(?s)]*>\s*(.*?)', + webpage, 'title') + episode_paths = re.findall( + r'(?s)
  • ]+>.*?.*)' - _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/d8/%s' - IE_NAME = 'd8.tv' - - _TEST = { - 'url': 'http://www.d8.tv/d8-docs-mags/pid6589-d8-campagne-intime.html', - 'file': '966289.flv', - 'info_dict': { - 'title': 'Campagne intime - Documentaire exceptionnel', - 'description': 'md5:d2643b799fb190846ae09c61e59a859f', - 'upload_date': '20131108', - }, - 'params': { - # rtmp - 'skip_download': True, - }, - 'skip': 'videos get deleted after a while', - } diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 66a8f16d9..936c13cd6 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -1,4 +1,4 @@ -#coding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re @@ -18,6 +18,7 @@ from ..utils import ( unescapeHTML, ) + class DailymotionBaseInfoExtractor(InfoExtractor): @staticmethod def _build_request(url): @@ -27,6 +28,7 @@ class DailymotionBaseInfoExtractor(InfoExtractor): request.add_header('Cookie', 'ff=off') return request + class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): """Information Extractor for Dailymotion""" @@ -82,11 +84,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): ] def _real_extract(self, url): - # Extract id and simplified title from URL - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - + video_id = self._match_id(url) url = 'http://www.dailymotion.com/video/%s' % video_id # Retrieve video webpage to extract further information @@ -98,7 +96,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): # It may just embed a vevo video: m_vevo = re.search( - r'[\w]*)', + r'[\w]*)', webpage) if m_vevo is not None: vevo_id = m_vevo.group('id') @@ -116,7 +114,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): embed_page = self._download_webpage(embed_url, video_id, 'Downloading embed page') info = self._search_regex(r'var info = ({.*?}),$', embed_page, - 'video info', flags=re.MULTILINE) + 'video info', flags=re.MULTILINE) info = json.loads(info) if info.get('error') is not None: msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title'] @@ -147,18 +145,23 @@ class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): self._list_available_subtitles(video_id, webpage) return - view_count = self._search_regex( - r'video_views_count[^>]+>\s+([\d\.,]+)', webpage, 'view count', fatal=False) - if view_count is not None: - view_count = str_to_int(view_count) + view_count = str_to_int(self._search_regex( + r'video_views_count[^>]+>\s+([\d\.,]+)', + webpage, 'view count', fatal=False)) + + title = self._og_search_title(webpage, default=None) + if title is None: + title = self._html_search_regex( + r'(?s)]*>(.*?)', webpage, + 'title') return { - 'id': video_id, + 'id': video_id, 'formats': formats, 'uploader': info['owner.screenname'], - 'upload_date': video_upload_date, - 'title': self._og_search_title(webpage), - 'subtitles': video_subtitles, + 'upload_date': video_upload_date, + 'title': title, + 'subtitles': video_subtitles, 'thumbnail': info['thumbnail_url'], 'age_limit': age_limit, 'view_count': view_count, @@ -205,7 +208,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: break return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') - for video_id in orderedSet(video_ids)] + for video_id in orderedSet(video_ids)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/defense.py b/youtube_dl/extractor/defense.py index c5529f8d4..5e50c63d9 100644 --- a/youtube_dl/extractor/defense.py +++ b/youtube_dl/extractor/defense.py @@ -9,7 +9,7 @@ from .common import InfoExtractor class DefenseGouvFrIE(InfoExtractor): IE_NAME = 'defense.gouv.fr' _VALID_URL = (r'http://.*?\.defense\.gouv\.fr/layout/set/' - r'ligthboxvideo/base-de-medias/webtv/(.*)') + r'ligthboxvideo/base-de-medias/webtv/(.*)') _TEST = { 'url': 'http://www.defense.gouv.fr/layout/set/ligthboxvideo/base-de-medias/webtv/attaque-chimique-syrienne-du-21-aout-2013-1', @@ -26,13 +26,13 @@ class DefenseGouvFrIE(InfoExtractor): video_id = self._search_regex( r"flashvars.pvg_id=\"(\d+)\";", webpage, 'ID') - + json_url = ('http://static.videos.gouv.fr/brightcovehub/export/json/' - + video_id) + + video_id) info = self._download_webpage(json_url, title, - 'Downloading JSON config') + 'Downloading JSON config') video_url = json.loads(info)['renditions'][0]['url'] - + return {'id': video_id, 'ext': 'mp4', 'url': video_url, diff --git a/youtube_dl/extractor/discovery.py b/youtube_dl/extractor/discovery.py index 554df6735..52c2d7ddf 100644 --- a/youtube_dl/extractor/discovery.py +++ b/youtube_dl/extractor/discovery.py @@ -16,9 +16,9 @@ class DiscoveryIE(InfoExtractor): 'ext': 'mp4', 'title': 'MythBusters: Mission Impossible Outtakes', 'description': ('Watch Jamie Hyneman and Adam Savage practice being' - ' each other -- to the point of confusing Jamie\'s dog -- and ' - 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' - ' back.'), + ' each other -- to the point of confusing Jamie\'s dog -- and ' + 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' + ' back.'), 'duration': 156, }, } @@ -29,7 +29,7 @@ class DiscoveryIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_list_json = self._search_regex(r'var videoListJSON = ({.*?});', - webpage, 'video list', flags=re.DOTALL) + webpage, 'video list', flags=re.DOTALL) video_list = json.loads(video_list_json) info = video_list['clips'][0] formats = [] diff --git a/youtube_dl/extractor/divxstage.py b/youtube_dl/extractor/divxstage.py index 4ca3f37a2..b88379e06 100644 --- a/youtube_dl/extractor/divxstage.py +++ b/youtube_dl/extractor/divxstage.py @@ -7,7 +7,7 @@ class DivxStageIE(NovaMovIE): IE_NAME = 'divxstage' IE_DESC = 'DivxStage' - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag)'} + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'divxstage\.(?:eu|net|ch|co|at|ag|to)'} _HOST = 'www.divxstage.eu' @@ -24,4 +24,4 @@ class DivxStageIE(NovaMovIE): 'title': 'youtubedl test video', 'description': 'This is a test video for youtubedl.', } - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/dotsub.py b/youtube_dl/extractor/dotsub.py index 5ae0ad5b6..638bb33cd 100644 --- a/youtube_dl/extractor/dotsub.py +++ b/youtube_dl/extractor/dotsub.py @@ -27,7 +27,7 @@ class DotsubIE(InfoExtractor): video_id = mobj.group('id') info_url = "https://dotsub.com/api/media/%s/metadata" % video_id info = self._download_json(info_url, video_id) - date = time.gmtime(info['dateCreated']/1000) # The timestamp is in miliseconds + date = time.gmtime(info['dateCreated'] / 1000) # The timestamp is in miliseconds return { 'id': video_id, diff --git a/youtube_dl/extractor/dropbox.py b/youtube_dl/extractor/dropbox.py index 1e1763abf..14b6c00b0 100644 --- a/youtube_dl/extractor/dropbox.py +++ b/youtube_dl/extractor/dropbox.py @@ -5,28 +5,33 @@ import os.path import re from .common import InfoExtractor -from ..utils import compat_urllib_parse_unquote +from ..compat import compat_urllib_parse_unquote +from ..utils import url_basename class DropboxIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/s/(?P[a-zA-Z0-9]{15})/(?P[^?#]*)' - _TEST = { - 'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0', - 'info_dict': { - 'id': 'nelirfsxnmcfbfh', - 'ext': 'mp4', - 'title': 'youtube-dl test video \'ä"BaW_jenozKc' - } - } + _VALID_URL = r'https?://(?:www\.)?dropbox[.]com/sh?/(?P<id>[a-zA-Z0-9]{15})/.*' + _TESTS = [ + { + 'url': 'https://www.dropbox.com/s/nelirfsxnmcfbfh/youtube-dl%20test%20video%20%27%C3%A4%22BaW_jenozKc.mp4?dl=0', + 'info_dict': { + 'id': 'nelirfsxnmcfbfh', + 'ext': 'mp4', + 'title': 'youtube-dl test video \'ä"BaW_jenozKc' + } + }, { + 'url': 'https://www.dropbox.com/sh/662glsejgzoj9sr/AAByil3FGH9KFNZ13e08eSa1a/Pregame%20Ceremony%20Program%20PA%2020140518.m4v', + 'only_matching': True, + }, + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - fn = compat_urllib_parse_unquote(mobj.group('title')) + fn = compat_urllib_parse_unquote(url_basename(url)) title = os.path.splitext(fn)[0] - video_url = ( - re.sub(r'[?&]dl=0', '', url) + - ('?' if '?' in url else '&') + 'dl=1') + video_url = re.sub(r'[?&]dl=0', '', url) + video_url += ('?' if '?' not in video_url else '&') + 'dl=1' return { 'id': video_id, diff --git a/youtube_dl/extractor/drtuber.py b/youtube_dl/extractor/drtuber.py index d5bfd7f22..ca274dff6 100644 --- a/youtube_dl/extractor/drtuber.py +++ b/youtube_dl/extractor/drtuber.py @@ -19,7 +19,7 @@ class DrTuberIE(InfoExtractor): 'like_count': int, 'dislike_count': int, 'comment_count': int, - 'categories': list, # NSFW + 'categories': ['Babe', 'Blonde', 'Erotic', 'Outdoor', 'Softcore', 'Solo'], 'thumbnail': 're:https?://.*\.jpg$', 'age_limit': 18, } @@ -52,9 +52,9 @@ class DrTuberIE(InfoExtractor): r'<span class="comments_count">([\d,\.]+)</span>', webpage, 'comment count', fatal=False)) - cats_str = self._html_search_regex( - r'<meta name="keywords" content="([^"]+)"', webpage, 'categories', fatal=False) - categories = None if cats_str is None else cats_str.split(' ') + cats_str = self._search_regex( + r'<span>Categories:</span><div>(.+?)</div>', webpage, 'categories', fatal=False) + categories = [] if not cats_str else re.findall(r'<a title="([^"]+)"', cats_str) return { 'id': video_id, diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index 9d6ce1f48..93b3c9f36 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .subtitles import SubtitlesInfoExtractor from .common import ExtractorError from ..utils import parse_iso8601 @@ -25,8 +23,7 @@ class DRTVIE(SubtitlesInfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) programcard = self._download_json( 'http://www.dr.dk/mu/programcard/expanded/%s' % video_id, video_id, 'Downloading video JSON') @@ -35,7 +32,7 @@ class DRTVIE(SubtitlesInfoExtractor): title = data['Title'] description = data['Description'] - timestamp = parse_iso8601(data['CreatedTime'][:-5]) + timestamp = parse_iso8601(data['CreatedTime']) thumbnail = None duration = None diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index f8f49a013..b766e17f2 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -28,7 +28,7 @@ class EHowIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)', - webpage, 'video URL') + webpage, 'video URL') final_url = compat_urllib_parse.unquote(video_url) uploader = self._html_search_meta('uploader', webpage) title = self._og_search_title(webpage).replace(' | eHow', '') diff --git a/youtube_dl/extractor/eighttracks.py b/youtube_dl/extractor/eighttracks.py index c1b4c729e..f4c1e2a72 100644 --- a/youtube_dl/extractor/eighttracks.py +++ b/youtube_dl/extractor/eighttracks.py @@ -125,7 +125,7 @@ class EightTracksIE(InfoExtractor): info = { 'id': compat_str(track_data['id']), 'url': track_data['track_file_stream_url'], - 'title': track_data['performer'] + u' - ' + track_data['name'], + 'title': track_data['performer'] + ' - ' + track_data['name'], 'raw_title': track_data['name'], 'uploader_id': data['user']['login'], 'ext': 'm4a', diff --git a/youtube_dl/extractor/eitb.py b/youtube_dl/extractor/eitb.py index 4ba323148..2cba82532 100644 --- a/youtube_dl/extractor/eitb.py +++ b/youtube_dl/extractor/eitb.py @@ -1,4 +1,6 @@ # encoding: utf-8 +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -7,20 +9,20 @@ from ..utils import ExtractorError class EitbIE(InfoExtractor): - IE_NAME = u'eitb.tv' + IE_NAME = 'eitb.tv' _VALID_URL = r'https?://www\.eitb\.tv/(eu/bideoa|es/video)/[^/]+/(?P<playlist_id>\d+)/(?P<chapter_id>\d+)' _TEST = { - u'add_ie': ['Brightcove'], - u'url': u'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/', - u'md5': u'edf4436247185adee3ea18ce64c47998', - u'info_dict': { - u'id': u'2743577154001', - u'ext': u'mp4', - u'title': u'60 minutos (Lasa y Zabala, 30 años)', + 'add_ie': ['Brightcove'], + 'url': 'http://www.eitb.tv/es/video/60-minutos-60-minutos-2013-2014/2677100210001/2743577154001/lasa-y-zabala-30-anos/', + 'md5': 'edf4436247185adee3ea18ce64c47998', + 'info_dict': { + 'id': '2743577154001', + 'ext': 'mp4', + 'title': '60 minutos (Lasa y Zabala, 30 años)', # All videos from eitb has this description in the brightcove info - u'description': u'.', - u'uploader': u'Euskal Telebista', + 'description': '.', + 'uploader': 'Euskal Telebista', }, } @@ -30,7 +32,7 @@ class EitbIE(InfoExtractor): webpage = self._download_webpage(url, chapter_id) bc_url = BrightcoveIE._extract_brightcove_url(webpage) if bc_url is None: - raise ExtractorError(u'Could not extract the Brightcove url') + raise ExtractorError('Could not extract the Brightcove url') # The BrightcoveExperience object doesn't contain the video id, we set # it manually bc_url += '&%40videoPlayer={0}'.format(chapter_id) diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index 522aa3d63..4de8d4bc5 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -14,13 +14,13 @@ class EpornerIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P<id>\d+)/(?P<display_id>[\w-]+)' _TEST = { 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', - 'md5': '3b427ae4b9d60619106de3185c2987cd', + 'md5': '39d486f046212d8e1b911c52ab4691f8', 'info_dict': { 'id': '95008', 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Infamous Tiffany Teen Strip Tease Video', - 'duration': 194, + 'duration': 1838, 'view_count': int, 'age_limit': 18, } @@ -57,9 +57,7 @@ class EpornerIE(InfoExtractor): formats.append(fmt) self._sort_formats(formats) - duration = parse_duration(self._search_regex( - r'class="mbtim">([0-9:]+)</div>', webpage, 'duration', - fatal=False)) + duration = parse_duration(self._html_search_meta('duration', webpage)) view_count = str_to_int(self._search_regex( r'id="cinemaviews">\s*([0-9,]+)\s*<small>views', webpage, 'view count', fatal=False)) diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index 14a196ffc..aacbf1414 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -7,6 +7,7 @@ from ..utils import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, + str_to_int, ) @@ -20,6 +21,7 @@ class ExtremeTubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Music Video 14 british euro brit european cumshots swallow', 'uploader': 'unknown', + 'view_count': int, 'age_limit': 18, } }, { @@ -39,8 +41,12 @@ class ExtremeTubeIE(InfoExtractor): video_title = self._html_search_regex( r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title') uploader = self._html_search_regex( - r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader', - fatal=False) + r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>', + webpage, 'uploader', fatal=False) + view_count = str_to_int(self._html_search_regex( + r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>', + webpage, 'view count', fatal=False)) + video_url = compat_urllib_parse.unquote(self._html_search_regex( r'video_url=(.+?)&', webpage, 'video_url')) path = compat_urllib_parse_urlparse(video_url).path @@ -51,6 +57,7 @@ class ExtremeTubeIE(InfoExtractor): 'id': video_id, 'title': video_title, 'uploader': uploader, + 'view_count': view_count, 'url': video_url, 'format': format, 'format_id': format, diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 60e68d98a..2139f68aa 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -5,12 +5,14 @@ import re import socket from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_http_client, compat_str, compat_urllib_error, compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( urlencode_postdata, ExtractorError, limit_length, @@ -35,7 +37,7 @@ class FacebookIE(InfoExtractor): 'id': '637842556329505', 'ext': 'mp4', 'duration': 38, - 'title': 'Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam fin...', + 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam', } }, { 'note': 'Video without discernible title', @@ -58,8 +60,8 @@ class FacebookIE(InfoExtractor): login_page_req = compat_urllib_request.Request(self._LOGIN_URL) login_page_req.add_header('Cookie', 'locale=en_US') login_page = self._download_webpage(login_page_req, None, - note='Downloading login page', - errnote='Unable to download login page') + note='Downloading login page', + errnote='Unable to download login page') lsd = self._search_regex( r'<input type="hidden" name="lsd" value="([^"]*)"', login_page, 'lsd') @@ -75,12 +77,12 @@ class FacebookIE(InfoExtractor): 'legacy_return': '1', 'timezone': '-60', 'trynum': '1', - } + } request = compat_urllib_request.Request(self._LOGIN_URL, urlencode_postdata(login_form)) request.add_header('Content-Type', 'application/x-www-form-urlencoded') try: login_results = self._download_webpage(request, None, - note='Logging in', errnote='unable to fetch login page') + note='Logging in', errnote='unable to fetch login page') if re.search(r'<form(.*)name="login"(.*)</form>', login_results) is not None: self._downloader.report_warning('unable to log in: bad username/password, or exceded login rate limit (~3/min). Check credentials or wait.') return @@ -94,7 +96,7 @@ class FacebookIE(InfoExtractor): check_req = compat_urllib_request.Request(self._CHECKPOINT_URL, urlencode_postdata(check_form)) check_req.add_header('Content-Type', 'application/x-www-form-urlencoded') check_response = self._download_webpage(check_req, None, - note='Confirming login') + note='Confirming login') if re.search(r'id="checkpointSubmitButton"', check_response) is not None: self._downloader.report_warning('Unable to confirm login, you have to login in your brower and authorize the login.') except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: diff --git a/youtube_dl/extractor/faz.py b/youtube_dl/extractor/faz.py index c6ab6952e..3c39ca451 100644 --- a/youtube_dl/extractor/faz.py +++ b/youtube_dl/extractor/faz.py @@ -1,49 +1,48 @@ # encoding: utf-8 -import re +from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import ( - determine_ext, -) class FazIE(InfoExtractor): - IE_NAME = u'faz.net' + IE_NAME = 'faz.net' _VALID_URL = r'https?://www\.faz\.net/multimedia/videos/.*?-(?P<id>\d+)\.html' _TEST = { - u'url': u'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html', - u'file': u'12610585.mp4', - u'info_dict': { - u'title': u'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher', - u'description': u'md5:1453fbf9a0d041d985a47306192ea253', + 'url': 'http://www.faz.net/multimedia/videos/stockholm-chemie-nobelpreis-fuer-drei-amerikanische-forscher-12610585.html', + 'info_dict': { + 'id': '12610585', + 'ext': 'mp4', + 'title': 'Stockholm: Chemie-Nobelpreis für drei amerikanische Forscher', + 'description': 'md5:1453fbf9a0d041d985a47306192ea253', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - self.to_screen(video_id) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - config_xml_url = self._search_regex(r'writeFLV\(\'(.+?)\',', webpage, - u'config xml url') - config = self._download_xml(config_xml_url, video_id, - u'Downloading config xml') + config_xml_url = self._search_regex( + r'writeFLV\(\'(.+?)\',', webpage, 'config xml url') + config = self._download_xml( + config_xml_url, video_id, 'Downloading config xml') encodings = config.find('ENCODINGS') formats = [] - for code in ['LOW', 'HIGH', 'HQ']: + for pref, code in enumerate(['LOW', 'HIGH', 'HQ']): encoding = encodings.find(code) if encoding is None: continue encoding_url = encoding.find('FILENAME').text formats.append({ 'url': encoding_url, - 'ext': determine_ext(encoding_url), 'format_id': code.lower(), + 'quality': pref, }) + self._sort_formats(formats) - descr = self._html_search_regex(r'<p class="Content Copy">(.*?)</p>', webpage, u'description') + descr = self._html_search_regex( + r'<p class="Content Copy">(.*?)</p>', webpage, 'description', fatal=False) return { 'id': video_id, 'title': self._og_search_title(webpage), diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py index c663a0f81..6f5d23559 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -40,7 +40,7 @@ class FC2IE(InfoExtractor): info_url = ( "http://video.fc2.com/ginfo.php?mimi={1:s}&href={2:s}&v={0:s}&fversion=WIN%2011%2C6%2C602%2C180&from=2&otag=0&upid={0:s}&tk=null&". - format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.','%2E'))) + format(video_id, mimi, compat_urllib_request.quote(refer, safe='').replace('.', '%2E'))) info_webpage = self._download_webpage( info_url, video_id, note='Downloading info page') diff --git a/youtube_dl/extractor/firsttv.py b/youtube_dl/extractor/firsttv.py index c2e987ff7..08ceee4ed 100644 --- a/youtube_dl/extractor/firsttv.py +++ b/youtube_dl/extractor/firsttv.py @@ -44,9 +44,9 @@ class FirstTVIE(InfoExtractor): duration = self._og_search_property('video:duration', webpage, 'video duration', fatal=False) like_count = self._html_search_regex(r'title="Понравилось".*?/></label> \[(\d+)\]', - webpage, 'like count', fatal=False) + webpage, 'like count', fatal=False) dislike_count = self._html_search_regex(r'title="Не понравилось".*?/></label> \[(\d+)\]', - webpage, 'dislike count', fatal=False) + webpage, 'dislike count', fatal=False) return { 'id': video_id, @@ -57,4 +57,4 @@ class FirstTVIE(InfoExtractor): 'duration': int_or_none(duration), 'like_count': int_or_none(like_count), 'dislike_count': int_or_none(dislike_count), - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py index 3a50bab5c..f9c127ce6 100644 --- a/youtube_dl/extractor/fivemin.py +++ b/youtube_dl/extractor/fivemin.py @@ -50,7 +50,7 @@ class FiveMinIE(InfoExtractor): video_id = mobj.group('id') embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id embed_page = self._download_webpage(embed_url, video_id, - 'Downloading embed page') + 'Downloading embed page') sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid') query = compat_urllib_parse.urlencode({ 'func': 'GetResults', diff --git a/youtube_dl/extractor/fktv.py b/youtube_dl/extractor/fktv.py index d7048c8c1..d09d1c13a 100644 --- a/youtube_dl/extractor/fktv.py +++ b/youtube_dl/extractor/fktv.py @@ -1,25 +1,27 @@ +from __future__ import unicode_literals + import re import random import json from .common import InfoExtractor from ..utils import ( - determine_ext, get_element_by_id, clean_html, ) class FKTVIE(InfoExtractor): - IE_NAME = u'fernsehkritik.tv' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' + IE_NAME = 'fernsehkritik.tv' + _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/folge-(?P<ep>[0-9]+)(?:/.*)?' _TEST = { - u'url': u'http://fernsehkritik.tv/folge-1', - u'file': u'00011.flv', - u'info_dict': { - u'title': u'Folge 1 vom 10. April 2007', - u'description': u'md5:fb4818139c7cfe6907d4b83412a6864f', + 'url': 'http://fernsehkritik.tv/folge-1', + 'info_dict': { + 'id': '00011', + 'ext': 'flv', + 'title': 'Folge 1 vom 10. April 2007', + 'description': 'md5:fb4818139c7cfe6907d4b83412a6864f', }, } @@ -30,9 +32,9 @@ class FKTVIE(InfoExtractor): server = random.randint(2, 4) video_thumbnail = 'http://fernsehkritik.tv/images/magazin/folge%d.jpg' % episode start_webpage = self._download_webpage('http://fernsehkritik.tv/folge-%d/Start' % episode, - episode) + episode) playlist = self._search_regex(r'playlist = (\[.*?\]);', start_webpage, - u'playlist', flags=re.DOTALL) + 'playlist', flags=re.DOTALL) files = json.loads(re.sub('{[^{}]*?}', '{}', playlist)) # TODO: return a single multipart video videos = [] @@ -42,7 +44,6 @@ class FKTVIE(InfoExtractor): videos.append({ 'id': video_id, 'url': video_url, - 'ext': determine_ext(video_url), 'title': clean_html(get_element_by_id('eptitle', start_webpage)), 'description': clean_html(get_element_by_id('contentlist', start_webpage)), 'thumbnail': video_thumbnail @@ -51,14 +52,15 @@ class FKTVIE(InfoExtractor): class FKTVPosteckeIE(InfoExtractor): - IE_NAME = u'fernsehkritik.tv:postecke' - _VALID_URL = r'(?:http://)?(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)' + IE_NAME = 'fernsehkritik.tv:postecke' + _VALID_URL = r'http://(?:www\.)?fernsehkritik\.tv/inline-video/postecke\.php\?(.*&)?ep=(?P<ep>[0-9]+)(&|$)' _TEST = { - u'url': u'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120', - u'file': u'0120.flv', - u'md5': u'262f0adbac80317412f7e57b4808e5c4', - u'info_dict': { - u"title": u"Postecke 120" + 'url': 'http://fernsehkritik.tv/inline-video/postecke.php?iframe=true&width=625&height=440&ep=120', + 'md5': '262f0adbac80317412f7e57b4808e5c4', + 'info_dict': { + 'id': '0120', + 'ext': 'flv', + 'title': 'Postecke 120', } } @@ -71,8 +73,7 @@ class FKTVPosteckeIE(InfoExtractor): video_url = 'http://dl%d.fernsehkritik.tv/postecke/postecke%d.flv' % (server, episode) video_title = 'Postecke %d' % episode return { - 'id': video_id, - 'url': video_url, - 'ext': determine_ext(video_url), - 'title': video_title, + 'id': video_id, + 'url': video_url, + 'title': video_title, } diff --git a/youtube_dl/extractor/flickr.py b/youtube_dl/extractor/flickr.py index 21ea5ec2b..0c858b654 100644 --- a/youtube_dl/extractor/flickr.py +++ b/youtube_dl/extractor/flickr.py @@ -10,15 +10,15 @@ from ..utils import ( class FlickrIE(InfoExtractor): - """Information Extractor for Flickr videos""" - _VALID_URL = r'(?:https?://)?(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*' + _VALID_URL = r'https?://(?:www\.|secure\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*' _TEST = { 'url': 'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/', - 'file': '5645318632.mp4', 'md5': '6fdc01adbc89d72fc9c4f15b4a4ba87b', 'info_dict': { - "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", - "uploader_id": "forestwander-nature-pictures", + 'id': '5645318632', + 'ext': 'mp4', + "description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up.", + "uploader_id": "forestwander-nature-pictures", "title": "Dark Hollow Waterfalls" } } @@ -37,7 +37,7 @@ class FlickrIE(InfoExtractor): first_xml = self._download_webpage(first_url, video_id, 'Downloading first data webpage') node_id = self._html_search_regex(r'<Item id="id">(\d+-\d+)</Item>', - first_xml, 'node_id') + first_xml, 'node_id') second_url = 'https://secure.flickr.com/video_playlist.gne?node_id=' + node_id + '&tech=flash&mode=playlist&bitrate=700&secret=' + secret + '&rd=video.yahoo.com&noad=1' second_xml = self._download_webpage(second_url, video_id, 'Downloading second data webpage') @@ -49,12 +49,12 @@ class FlickrIE(InfoExtractor): raise ExtractorError('Unable to extract video url') video_url = mobj.group(1) + unescapeHTML(mobj.group(2)) - return [{ - 'id': video_id, - 'url': video_url, - 'ext': 'mp4', - 'title': self._og_search_title(webpage), + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': self._og_search_title(webpage), 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), 'uploader_id': video_uploader_id, - }] + } diff --git a/youtube_dl/extractor/folketinget.py b/youtube_dl/extractor/folketinget.py new file mode 100644 index 000000000..68e2db943 --- /dev/null +++ b/youtube_dl/extractor/folketinget.py @@ -0,0 +1,75 @@ +# -*- coding: utf-8 -*- +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_parse_qs +from ..utils import ( + int_or_none, + parse_duration, + parse_iso8601, + xpath_text, +) + + +class FolketingetIE(InfoExtractor): + IE_DESC = 'Folketinget (ft.dk; Danish parliament)' + _VALID_URL = r'https?://(?:www\.)?ft\.dk/webtv/video/[^?#]*?\.(?P<id>[0-9]+)\.aspx' + _TEST = { + 'url': 'http://www.ft.dk/webtv/video/20141/eru/td.1165642.aspx?as=1#player', + 'info_dict': { + 'id': '1165642', + 'ext': 'mp4', + 'title': 'Åbent samråd i Erhvervsudvalget', + 'description': 'Åbent samråd med erhvervs- og vækstministeren om regeringens politik på teleområdet', + 'view_count': int, + 'width': 768, + 'height': 432, + 'tbr': 928000, + 'timestamp': 1416493800, + 'upload_date': '20141120', + 'duration': 3960, + }, + 'params': { + 'skip_download': 'rtmpdump required', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + description = self._html_search_regex( + r'(?s)<div class="video-item-agenda"[^>]*>(.*?)<', + webpage, 'description', fatal=False) + + player_params = compat_parse_qs(self._search_regex( + r'<embed src="http://ft\.arkena\.tv/flash/ftplayer\.swf\?([^"]+)"', + webpage, 'player params')) + xml_url = player_params['xml'][0] + doc = self._download_xml(xml_url, video_id) + + timestamp = parse_iso8601(xpath_text(doc, './/date')) + duration = parse_duration(xpath_text(doc, './/duration')) + width = int_or_none(xpath_text(doc, './/width')) + height = int_or_none(xpath_text(doc, './/height')) + view_count = int_or_none(xpath_text(doc, './/views')) + + formats = [{ + 'format_id': n.attrib['bitrate'], + 'url': xpath_text(n, './url', fatal=True), + 'tbr': int_or_none(n.attrib['bitrate']), + } for n in doc.findall('.//streams/stream')] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': description, + 'timestamp': timestamp, + 'width': width, + 'height': height, + 'duration': duration, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/fourtube.py b/youtube_dl/extractor/fourtube.py index 7d56b9be9..b22ce2acb 100644 --- a/youtube_dl/extractor/fourtube.py +++ b/youtube_dl/extractor/fourtube.py @@ -55,7 +55,7 @@ class FourTubeIE(InfoExtractor): description = self._html_search_meta('description', webpage, 'description') if description: upload_date = self._search_regex(r'Published Date: (\d{2} [a-zA-Z]{3} \d{4})', description, 'upload date', - fatal=False) + fatal=False) if upload_date: upload_date = unified_strdate(upload_date) view_count = self._search_regex(r'Views: ([\d,\.]+)', description, 'view count', fatal=False) @@ -65,9 +65,9 @@ class FourTubeIE(InfoExtractor): token_url = "http://tkn.4tube.com/{0}/desktop/{1}".format(media_id, "+".join(sources)) headers = { - b'Content-Type': b'application/x-www-form-urlencoded', - b'Origin': b'http://www.4tube.com', - } + b'Content-Type': b'application/x-www-form-urlencoded', + b'Origin': b'http://www.4tube.com', + } token_req = compat_urllib_request.Request(token_url, b'{}', headers) tokens = self._download_json(token_req, video_id) @@ -76,7 +76,7 @@ class FourTubeIE(InfoExtractor): 'format_id': format + 'p', 'resolution': format + 'p', 'quality': int(format), - } for format in sources] + } for format in sources] self._sort_formats(formats) @@ -92,4 +92,4 @@ class FourTubeIE(InfoExtractor): 'duration': duration, 'age_limit': 18, 'webpage_url': webpage_url, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index deb1b0b9d..6613ee17a 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -4,16 +4,21 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import int_or_none class FranceInterIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]{6})' + _VALID_URL = r'http://(?:www\.)?franceinter\.fr/player/reecouter\?play=(?P<id>[0-9]+)' _TEST = { 'url': 'http://www.franceinter.fr/player/reecouter?play=793962', - 'file': '793962.mp3', 'md5': '4764932e466e6f6c79c317d2e74f6884', "info_dict": { - "title": "L’Histoire dans les jeux vidéo", + 'id': '793962', + 'ext': 'mp3', + 'title': 'L’Histoire dans les jeux vidéo', + 'description': 'md5:7e93ddb4451e7530022792240a3049c7', + 'timestamp': 1387369800, + 'upload_date': '20131218', }, } @@ -22,17 +27,26 @@ class FranceInterIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - title = self._html_search_regex( - r'<span class="roll_overflow">(.*?)</span></h1>', webpage, 'title') + path = self._search_regex( - r'&urlAOD=(.*?)&startTime', webpage, 'video url') + r'<a id="player".+?href="([^"]+)"', webpage, 'video url') video_url = 'http://www.franceinter.fr/' + path + title = self._html_search_regex( + r'<span class="title">(.+?)</span>', webpage, 'title') + description = self._html_search_regex( + r'<span class="description">(.*?)</span>', + webpage, 'description', fatal=False) + timestamp = int_or_none(self._search_regex( + r'data-date="(\d+)"', webpage, 'upload date', fatal=False)) + return { 'id': video_id, + 'title': title, + 'description': description, + 'timestamp': timestamp, 'formats': [{ 'url': video_url, 'vcodec': 'none', }], - 'title': title, } diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 1b0e8e5d5..e0420a48f 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -8,45 +8,85 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, + ExtractorError, + clean_html, + parse_duration, + compat_urllib_parse_urlparse, + int_or_none, ) class FranceTVBaseInfoExtractor(InfoExtractor): - def _extract_video(self, video_id): - info = self._download_xml( - 'http://www.francetvinfo.fr/appftv/webservices/video/' - 'getInfosOeuvre.php?id-diffusion=' - + video_id, video_id, 'Downloading XML config') + def _extract_video(self, video_id, catalogue): + info = self._download_json( + 'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s' + % (video_id, catalogue), + video_id, 'Downloading video JSON') - manifest_url = info.find('videos/video/url').text - manifest_url = manifest_url.replace('/z/', '/i/') - - if manifest_url.startswith('rtmp'): - formats = [{'url': manifest_url, 'ext': 'flv'}] + if info.get('status') == 'NOK': + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True) + allowed_countries = info['videos'][0].get('geoblocage') + if allowed_countries: + georestricted = True + geo_info = self._download_json( + 'http://geo.francetv.fr/ws/edgescape.json', video_id, + 'Downloading geo restriction info') + country = geo_info['reponse']['geo_info']['country_code'] + if country not in allowed_countries: + raise ExtractorError( + 'The video is not available from your location', + expected=True) else: - formats = [] - available_formats = self._search_regex(r'/[^,]*,(.*?),k\.mp4', manifest_url, 'available formats') - for index, format_descr in enumerate(available_formats.split(',')): - format_info = { - 'url': manifest_url.replace('manifest.f4m', 'index_%d_av.m3u8' % index), - 'ext': 'mp4', - } - m_resolution = re.search(r'(?P<width>\d+)x(?P<height>\d+)', format_descr) - if m_resolution is not None: - format_info.update({ - 'width': int(m_resolution.group('width')), - 'height': int(m_resolution.group('height')), - }) - formats.append(format_info) + georestricted = False - thumbnail_path = info.find('image').text + formats = [] + for video in info['videos']: + if video['statut'] != 'ONLINE': + continue + video_url = video['url'] + if not video_url: + continue + format_id = video['format'] + if video_url.endswith('.f4m'): + if georestricted: + # See https://github.com/rg3/youtube-dl/issues/3963 + # m3u8 urls work fine + continue + video_url_parsed = compat_urllib_parse_urlparse(video_url) + f4m_url = self._download_webpage( + 'http://hdfauth.francetv.fr/esi/urltokengen2.html?url=%s' % video_url_parsed.path, + video_id, 'Downloading f4m manifest token', fatal=False) + if f4m_url: + f4m_formats = self._extract_f4m_formats(f4m_url, video_id) + for f4m_format in f4m_formats: + f4m_format['preference'] = 1 + formats.extend(f4m_formats) + elif video_url.endswith('.m3u8'): + formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4')) + elif video_url.startswith('rtmp'): + formats.append({ + 'url': video_url, + 'format_id': 'rtmp-%s' % format_id, + 'ext': 'flv', + 'preference': 1, + }) + else: + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'preference': -1, + }) + self._sort_formats(formats) return { 'id': video_id, - 'title': info.find('titre').text, + 'title': info['titre'], + 'description': clean_html(info['synopsis']), + 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']), + 'duration': parse_duration(info['duree']), + 'timestamp': int_or_none(info['diffusion']['timestamp']), 'formats': formats, - 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path), - 'description': info.find('synopsis').text, } @@ -61,7 +101,7 @@ class PluzzIE(FranceTVBaseInfoExtractor): webpage = self._download_webpage(url, title) video_id = self._search_regex( r'data-diffusion="(\d+)"', webpage, 'ID') - return self._extract_video(video_id) + return self._extract_video(video_id, 'Pluzz') class FranceTvInfoIE(FranceTVBaseInfoExtractor): @@ -72,11 +112,10 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): 'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html', 'info_dict': { 'id': '84981923', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Soir 3', - }, - 'params': { - 'skip_download': True, + 'upload_date': '20130826', + 'timestamp': 1377548400, }, }, { 'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html', @@ -88,15 +127,17 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): }, 'params': { 'skip_download': 'HLS (reqires ffmpeg)' - } + }, + 'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.', }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) page_title = mobj.group('title') webpage = self._download_webpage(url, page_title) - video_id = self._search_regex(r'id-video=((?:[^0-9]*?_)?[0-9]+)[@"]', webpage, 'video id') - return self._extract_video(video_id) + video_id, catalogue = self._search_regex( + r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@') + return self._extract_video(video_id, catalogue) class FranceTVIE(FranceTVBaseInfoExtractor): @@ -112,91 +153,77 @@ class FranceTVIE(FranceTVBaseInfoExtractor): # france2 { 'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104', - 'file': '75540104.mp4', + 'md5': 'c03fc87cb85429ffd55df32b9fc05523', 'info_dict': { - 'title': '13h15, le samedi...', - 'description': 'md5:2e5b58ba7a2d3692b35c792be081a03d', - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'id': '109169362', + 'ext': 'flv', + 'title': '13h15, le dimanche...', + 'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7', + 'upload_date': '20140914', + 'timestamp': 1410693600, }, }, # france3 { 'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575', + 'md5': '679bb8f8921f8623bd658fa2f8364da0', 'info_dict': { 'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Le scandale du prix des médicaments', 'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce', - }, - 'params': { - # rtmp download - 'skip_download': True, + 'upload_date': '20131113', + 'timestamp': 1384380000, }, }, # france4 { 'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', + 'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c', 'info_dict': { 'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Hero Corp Making of - Extrait 1', 'description': 'md5:c87d54871b1790679aec1197e73d650a', - }, - 'params': { - # rtmp download - 'skip_download': True, + 'upload_date': '20131106', + 'timestamp': 1383766500, }, }, # france5 { 'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968', + 'md5': '78f0f4064f9074438e660785bbf2c5d9', 'info_dict': { - 'id': '92837968', - 'ext': 'mp4', + 'id': '108961659', + 'ext': 'flv', 'title': 'C à dire ?!', - 'description': 'md5:fb1db1cbad784dcce7c7a7bd177c8e2f', - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'description': 'md5:1a4aeab476eb657bf57c4ff122129f81', + 'upload_date': '20140915', + 'timestamp': 1410795000, }, }, # franceo { 'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013', + 'md5': '52f0bfe202848b15915a2f39aaa8981b', 'info_dict': { - 'id': '92327925', - 'ext': 'mp4', - 'title': 'Infô-Afrique', + 'id': '108634970', + 'ext': 'flv', + 'title': 'Infô Afrique', 'description': 'md5:ebf346da789428841bee0fd2a935ea55', + 'upload_date': '20140915', + 'timestamp': 1410822000, }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - 'skip': 'The id changes frequently', }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj.group('key'): - webpage = self._download_webpage(url, mobj.group('key')) - id_res = [ - (r'''(?x)<div\s+class="video-player">\s* - <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+ - class="francetv-video-player">'''), - (r'<a id="player_direct" href="http://info\.francetelevisions' - '\.fr/\?id-video=([^"/&]+)'), - (r'<a class="video" id="ftv_player_(.+?)"'), - ] - video_id = self._html_search_regex(id_res, webpage, 'video ID') - else: - video_id = mobj.group('id') - return self._extract_video(video_id) + webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id')) + video_id, catalogue = self._html_search_regex( + r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', + webpage, 'video ID').split('@') + return self._extract_video(video_id, catalogue) class GenerationQuoiIE(InfoExtractor): @@ -224,7 +251,7 @@ class GenerationQuoiIE(InfoExtractor): info_json = self._download_webpage(info_url, name) info = json.loads(info_json) return self.url_result('http://www.dailymotion.com/video/%s' % info['id'], - ie='Dailymotion') + ie='Dailymotion') class CultureboxIE(FranceTVBaseInfoExtractor): @@ -232,16 +259,15 @@ class CultureboxIE(FranceTVBaseInfoExtractor): _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)' _TEST = { - 'url': 'http://culturebox.francetvinfo.fr/einstein-on-the-beach-au-theatre-du-chatelet-146813', + 'url': 'http://culturebox.francetvinfo.fr/festivals/dans-les-jardins-de-william-christie/dans-les-jardins-de-william-christie-le-camus-162553', + 'md5': '5ad6dec1ffb2a3fbcb20cc4b744be8d6', 'info_dict': { - 'id': 'EV_6785', - 'ext': 'mp4', - 'title': 'Einstein on the beach au Théâtre du Châtelet', - 'description': 'md5:9ce2888b1efefc617b5e58b3f6200eeb', - }, - 'params': { - # m3u8 download - 'skip_download': True, + 'id': 'EV_22853', + 'ext': 'flv', + 'title': 'Dans les jardins de William Christie - Le Camus', + 'description': 'md5:4710c82315c40f0c865ca8b9a68b5299', + 'upload_date': '20140829', + 'timestamp': 1409317200, }, } @@ -249,5 +275,7 @@ class CultureboxIE(FranceTVBaseInfoExtractor): mobj = re.match(self._VALID_URL, url) name = mobj.group('name') webpage = self._download_webpage(url, name) - video_id = self._search_regex(r'"http://videos\.francetv\.fr/video/(.*?)"', webpage, 'video id') - return self._extract_video(video_id) + video_id, catalogue = self._search_regex( + r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@') + + return self._extract_video(video_id, catalogue) diff --git a/youtube_dl/extractor/freevideo.py b/youtube_dl/extractor/freevideo.py new file mode 100644 index 000000000..f755e3c4a --- /dev/null +++ b/youtube_dl/extractor/freevideo.py @@ -0,0 +1,38 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class FreeVideoIE(InfoExtractor): + _VALID_URL = r'^http://www.freevideo.cz/vase-videa/(?P<id>[^.]+)\.html(?:$|[?#])' + + _TEST = { + 'url': 'http://www.freevideo.cz/vase-videa/vysukany-zadecek-22033.html', + 'info_dict': { + 'id': 'vysukany-zadecek-22033', + 'ext': 'mp4', + "title": "vysukany-zadecek-22033", + "age_limit": 18, + }, + 'skip': 'Blocked outside .cz', + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage, handle = self._download_webpage_handle(url, video_id) + if '//www.czechav.com/' in handle.geturl(): + raise ExtractorError( + 'Access to freevideo is blocked from your location', + expected=True) + + video_url = self._search_regex( + r'\s+url: "(http://[a-z0-9-]+.cdn.freevideo.cz/stream/.*?/video.mp4)"', + webpage, 'video URL') + + return { + 'id': video_id, + 'url': video_url, + 'title': video_id, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/funnyordie.py b/youtube_dl/extractor/funnyordie.py index 721e5fce0..a49fc1151 100644 --- a/youtube_dl/extractor/funnyordie.py +++ b/youtube_dl/extractor/funnyordie.py @@ -8,7 +8,7 @@ from ..utils import ExtractorError class FunnyOrDieIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])' + _VALID_URL = r'https?://(?:www\.)?funnyordie\.com/(?P<type>embed|articles|videos)/(?P<id>[0-9a-f]+)(?:$|[?#/])' _TESTS = [{ 'url': 'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version', 'md5': 'bcd81e0c4f26189ee09be362ad6e6ba9', @@ -21,7 +21,6 @@ class FunnyOrDieIE(InfoExtractor): }, }, { 'url': 'http://www.funnyordie.com/embed/e402820827', - 'md5': 'ff4d83318f89776ed0250634cfaa8d36', 'info_dict': { 'id': 'e402820827', 'ext': 'mp4', @@ -29,6 +28,9 @@ class FunnyOrDieIE(InfoExtractor): 'description': 'Please use this to sell something. www.jonlajoie.com', 'thumbnail': 're:^http:.*\.jpg$', }, + }, { + 'url': 'http://www.funnyordie.com/articles/ebf5e34fc8/10-hours-of-walking-in-nyc-as-a-man', + 'only_matching': True, }] def _real_extract(self, url): @@ -37,7 +39,7 @@ class FunnyOrDieIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - links = re.findall(r'<source src="([^"]+/v)\d+\.([^"]+)" type=\'video', webpage) + links = re.findall(r'<source src="([^"]+/v)[^"]+\.([^"]+)" type=\'video', webpage) if not links: raise ExtractorError('No media links available for %s' % video_id) diff --git a/youtube_dl/extractor/gamekings.py b/youtube_dl/extractor/gamekings.py index 11fee3d31..cf8e90d7d 100644 --- a/youtube_dl/extractor/gamekings.py +++ b/youtube_dl/extractor/gamekings.py @@ -11,7 +11,7 @@ class GamekingsIE(InfoExtractor): 'url': 'http://www.gamekings.tv/videos/phoenix-wright-ace-attorney-dual-destinies-review/', # MD5 is flaky, seems to change regularly # 'md5': '2f32b1f7b80fdc5cb616efb4f387f8a3', - u'info_dict': { + 'info_dict': { 'id': '20130811', 'ext': 'mp4', 'title': 'Phoenix Wright: Ace Attorney \u2013 Dual Destinies Review', diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 3d67b9d60..d570e3f6a 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -8,12 +8,11 @@ from ..utils import ( compat_urllib_parse, compat_urlparse, unescapeHTML, - get_meta_content, ) class GameSpotIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?' + _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?' _TEST = { 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', @@ -26,10 +25,10 @@ class GameSpotIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - page_id = mobj.group('page_id') + page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) - data_video_json = self._search_regex(r'data-video=["\'](.*?)["\']', webpage, 'data video') + data_video_json = self._search_regex( + r'data-video=["\'](.*?)["\']', webpage, 'data video') data_video = json.loads(unescapeHTML(data_video_json)) # Transform the manifest url to a link to the mp4 files @@ -41,7 +40,8 @@ class GameSpotIE(InfoExtractor): http_path = f4m_path[1:].split('/', 1)[1] http_template = re.sub(QUALITIES_RE, r'%s', http_path) http_template = http_template.replace('.csmil/manifest.f4m', '') - http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template) + http_template = compat_urlparse.urljoin( + 'http://video.gamespotcdn.com/', http_template) formats = [] for q in qualities: formats.append({ @@ -52,8 +52,9 @@ class GameSpotIE(InfoExtractor): return { 'id': data_video['guid'], + 'display_id': page_id, 'title': compat_urllib_parse.unquote(data_video['title']), 'formats': formats, - 'description': get_meta_content('description', webpage), + 'description': self._html_search_meta('description', webpage), 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 2bfa20606..328301de3 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -7,11 +7,12 @@ import re from .common import InfoExtractor from .youtube import YoutubeIE -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urlparse, compat_xml_parse_error, - +) +from ..utils import ( determine_ext, ExtractorError, float_or_none, @@ -28,6 +29,7 @@ from .brightcove import BrightcoveIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .smotri import SmotriIE +from .condenast import CondeNastIE class GenericIE(InfoExtractor): @@ -98,6 +100,22 @@ class GenericIE(InfoExtractor): 'uploader': 'Championat', }, }, + { + # https://github.com/rg3/youtube-dl/issues/3541 + 'add_ie': ['Brightcove'], + 'url': 'http://www.kijk.nl/sbs6/leermijvrouwenkennen/videos/jqMiXKAYan2S/aflevering-1', + 'info_dict': { + 'id': '3866516442001', + 'ext': 'mp4', + 'title': 'Leer mij vrouwen kennen: Aflevering 1', + 'description': 'Leer mij vrouwen kennen: Aflevering 1', + 'uploader': 'SBS Broadcasting', + }, + 'skip': 'Restricted to Netherlands', + 'params': { + 'skip_download': True, # m3u8 download + }, + }, # Direct link to a video { 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', @@ -155,7 +173,6 @@ class GenericIE(InfoExtractor): # funnyordie embed { 'url': 'http://www.theguardian.com/world/2014/mar/11/obama-zach-galifianakis-between-two-ferns', - 'md5': '7cf780be104d40fea7bae52eed4a470e', 'info_dict': { 'id': '18e820ec3f', 'ext': 'mp4', @@ -180,13 +197,13 @@ class GenericIE(InfoExtractor): # Embedded TED video { 'url': 'http://en.support.wordpress.com/videos/ted-talks/', - 'md5': 'deeeabcc1085eb2ba205474e7235a3d5', + 'md5': '65fdff94098e4a607385a60c5177c638', 'info_dict': { - 'id': '981', + 'id': '1969', 'ext': 'mp4', - 'title': 'My web playroom', - 'uploader': 'Ze Frank', - 'description': 'md5:ddb2a40ecd6b6a147e400e535874947b', + 'title': 'Hidden miracles of the natural world', + 'uploader': 'Louie Schwartzberg', + 'description': 'md5:8145d19d320ff3e52f28401f4c4283b9', } }, # Embeded Ustream video @@ -226,21 +243,6 @@ class GenericIE(InfoExtractor): 'skip_download': 'Requires rtmpdump' } }, - # smotri embed - { - 'url': 'http://rbctv.rbc.ru/archive/news/562949990879132.shtml', - 'md5': 'ec40048448e9284c9a1de77bb188108b', - 'info_dict': { - 'id': 'v27008541fad', - 'ext': 'mp4', - 'title': 'Крым и Севастополь вошли в состав России', - 'description': 'md5:fae01b61f68984c7bd2fa741e11c3175', - 'duration': 900, - 'upload_date': '20140318', - 'uploader': 'rbctv_2012_4', - 'uploader_id': 'rbctv_2012_4', - }, - }, # Condé Nast embed { 'url': 'http://www.wired.com/2014/04/honda-asimo/', @@ -295,13 +297,13 @@ class GenericIE(InfoExtractor): { 'url': 'https://play.google.com/store/apps/details?id=com.gameloft.android.ANMP.GloftA8HM', 'info_dict': { - 'id': 'jpSGZsgga_I', + 'id': '4vAffPZIT44', 'ext': 'mp4', - 'title': 'Asphalt 8: Airborne - Launch Trailer', + 'title': 'Asphalt 8: Airborne - Update - Welcome to Dubai!', 'uploader': 'Gameloft', 'uploader_id': 'gameloft', - 'upload_date': '20130821', - 'description': 'md5:87bd95f13d8be3e7da87a5f2c443106a', + 'upload_date': '20140828', + 'description': 'md5:c80da9ed3d83ae6d1876c834de03e1c4', }, 'params': { 'skip_download': True, @@ -340,7 +342,7 @@ class GenericIE(InfoExtractor): 'ext': 'mp4', 'age_limit': 18, 'uploader': 'www.handjobhub.com', - 'title': 'Busty Blonde Siri Tit Fuck While Wank at Handjob Hub', + 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com', } }, # RSS feed @@ -382,13 +384,92 @@ class GenericIE(InfoExtractor): 'thumbnail': 're:^https?://.*\.jpg$', }, }, - ] + # Wistia embed + { + 'url': 'http://education-portal.com/academy/lesson/north-american-exploration-failed-colonies-of-spain-france-england.html#lesson', + 'md5': '8788b683c777a5cf25621eaf286d0c23', + 'info_dict': { + 'id': '1cfaf6b7ea', + 'ext': 'mov', + 'title': 'md5:51364a8d3d009997ba99656004b5e20d', + 'duration': 643.0, + 'filesize': 182808282, + 'uploader': 'education-portal.com', + }, + }, + { + 'url': 'http://thoughtworks.wistia.com/medias/uxjb0lwrcz', + 'md5': 'baf49c2baa8a7de5f3fc145a8506dcd4', + 'info_dict': { + 'id': 'uxjb0lwrcz', + 'ext': 'mp4', + 'title': 'Conversation about Hexagonal Rails Part 1 - ThoughtWorks', + 'duration': 1715.0, + 'uploader': 'thoughtworks.wistia.com', + }, + }, + # Direct download with broken HEAD + { + 'url': 'http://ai-radio.org:8000/radio.opus', + 'info_dict': { + 'id': 'radio', + 'ext': 'opus', + 'title': 'radio', + }, + 'params': { + 'skip_download': True, # infinite live stream + }, + 'expected_warnings': [ + r'501.*Not Implemented' + ], + }, + # Soundcloud embed + { + 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/', + 'info_dict': { + 'id': '174391317', + 'ext': 'mp3', + 'description': 'md5:ff867d6b555488ad3c52572bb33d432c', + 'uploader': 'Sophos Security', + 'title': 'Chet Chat 171 - Oct 29, 2014', + 'upload_date': '20141029', + } + }, + # Livestream embed + { + 'url': 'http://www.esa.int/Our_Activities/Space_Science/Rosetta/Philae_comet_touch-down_webcast', + 'info_dict': { + 'id': '67864563', + 'ext': 'flv', + 'upload_date': '20141112', + 'title': 'Rosetta #CometLanding webcast HL 10', + } + }, + # LazyYT + { + 'url': 'http://discourse.ubuntu.com/t/unity-8-desktop-mode-windows-on-mir/1986', + 'info_dict': { + 'title': 'Unity 8 desktop-mode windows on Mir! - Ubuntu Discourse', + }, + 'playlist_mincount': 2, + }, + # Direct link with incorrect MIME type + { + 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', + 'md5': '4ccbebe5f36706d85221f204d7eb5913', + 'info_dict': { + 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', + 'id': '5_Lennart_Poettering_-_Systemd', + 'ext': 'webm', + 'title': '5_Lennart_Poettering_-_Systemd', + 'upload_date': '20141120', + }, + 'expected_warnings': [ + 'URL could be a direct video link, returning it as such.' + ] + } - def report_download_webpage(self, video_id): - """Report webpage download.""" - if not self._downloader.params.get('test', False): - self._downloader.report_warning('Falling back on generic information extractor.') - super(GenericIE, self).report_download_webpage(video_id) + ] def report_following_redirect(self, new_url): """Report information extraction.""" @@ -480,15 +561,17 @@ class GenericIE(InfoExtractor): if default_search in ('error', 'fixup_error'): raise ExtractorError( - ('%r is not a valid URL. ' - 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' - ) % (url, url), expected=True) + '%r is not a valid URL. ' + 'Set --default-search "ytsearch" (or run youtube-dl "ytsearch:%s" ) to search YouTube' + % (url, url), expected=True) else: - assert ':' in default_search + if ':' not in default_search: + default_search += ':' return self.url_result(default_search + url) url, smuggled_data = unsmuggle_url(url) force_videoid = None + is_intentional = smuggled_data and smuggled_data.get('to_generic') if smuggled_data and 'force_videoid' in smuggled_data: force_videoid = smuggled_data['force_videoid'] video_id = force_videoid @@ -498,14 +581,14 @@ class GenericIE(InfoExtractor): self.to_screen('%s: Requesting header' % video_id) head_req = HEADRequest(url) - response = self._request_webpage( + head_response = self._request_webpage( head_req, video_id, note=False, errnote='Could not send HEAD request to %s' % url, fatal=False) - if response is not False: + if head_response is not False: # Check for redirect - new_url = response.geturl() + new_url = head_response.geturl() if url != new_url: self.report_following_redirect(new_url) if force_videoid: @@ -513,30 +596,53 @@ class GenericIE(InfoExtractor): new_url, {'force_videoid': force_videoid}) return self.url_result(new_url) - # Check for direct link to a video - content_type = response.headers.get('Content-Type', '') - m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type) - if m: - upload_date = response.headers.get('Last-Modified') - if upload_date: - upload_date = unified_strdate(upload_date) - return { - 'id': video_id, - 'title': os.path.splitext(url_basename(url))[0], - 'formats': [{ - 'format_id': m.group('format_id'), - 'url': url, - 'vcodec': 'none' if m.group('type') == 'audio' else None - }], - 'upload_date': upload_date, - } + full_response = None + if head_response is False: + full_response = self._request_webpage(url, video_id) + head_response = full_response - try: - webpage = self._download_webpage(url, video_id) - except ValueError: - # since this is the last-resort InfoExtractor, if - # this error is thrown, it'll be thrown here - raise ExtractorError('Failed to download URL: %s' % url) + # Check for direct link to a video + content_type = head_response.headers.get('Content-Type', '') + m = re.match(r'^(?P<type>audio|video|application(?=/ogg$))/(?P<format_id>.+)$', content_type) + if m: + upload_date = unified_strdate( + head_response.headers.get('Last-Modified')) + return { + 'id': video_id, + 'title': os.path.splitext(url_basename(url))[0], + 'direct': True, + 'formats': [{ + 'format_id': m.group('format_id'), + 'url': url, + 'vcodec': 'none' if m.group('type') == 'audio' else None + }], + 'upload_date': upload_date, + } + + if not self._downloader.params.get('test', False) and not is_intentional: + self._downloader.report_warning('Falling back on generic information extractor.') + + if not full_response: + full_response = self._request_webpage(url, video_id) + + # Maybe it's a direct link to a video? + # Be careful not to download the whole thing! + first_bytes = full_response.read(512) + if not re.match(r'^\s*<', first_bytes.decode('utf-8', 'replace')): + self._downloader.report_warning( + 'URL could be a direct video link, returning it as such.') + upload_date = unified_strdate( + head_response.headers.get('Last-Modified')) + return { + 'id': video_id, + 'title': os.path.splitext(url_basename(url))[0], + 'direct': True, + 'url': url, + 'upload_date': upload_date, + } + + webpage = self._webpage_read_content( + full_response, url, video_id, prefix=first_bytes) self.report_extraction(video_id) @@ -584,7 +690,9 @@ class GenericIE(InfoExtractor): # Helper method def _playlist_from_matches(matches, getter, ie=None): - urlrs = orderedSet(self.url_result(getter(m), ie) for m in matches) + urlrs = orderedSet( + self.url_result(self._proto_relative_url(getter(m)), ie) + for m in matches) return self.playlist_result( urlrs, playlist_id=video_id, playlist_title=video_title) @@ -611,13 +719,13 @@ class GenericIE(InfoExtractor): if mobj: player_url = unescapeHTML(mobj.group('url')) surl = smuggle_url(player_url, {'Referer': url}) - return self.url_result(surl, 'Vimeo') + return self.url_result(surl) # Look for embedded (swf embed) Vimeo player mobj = re.search( - r'<embed[^>]+?src="(https?://(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) + r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) if mobj: - return self.url_result(mobj.group(1), 'Vimeo') + return self.url_result(mobj.group(1)) # Look for embedded YouTube player matches = re.findall(r'''(?x) @@ -625,15 +733,22 @@ class GenericIE(InfoExtractor): <iframe[^>]+?src=| data-video-url=| <embed[^>]+?src=| - embedSWF\(?:\s* + embedSWF\(?:\s*| + new\s+SWFObject\( ) (["\']) (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ - (?:embed|v)/.+?) + (?:embed|v|p)/.+?) \1''', webpage) if matches: return _playlist_from_matches( - matches, lambda m: unescapeHTML(m[1]), ie='Youtube') + matches, lambda m: unescapeHTML(m[1])) + + # Look for lazyYT YouTube embed + matches = re.findall( + r'class="lazyYT" data-youtube-id="([^"]+)"', webpage) + if matches: + return _playlist_from_matches(matches, lambda m: unescapeHTML(m)) # Look for embedded Dailymotion player matches = re.findall( @@ -642,23 +757,46 @@ class GenericIE(InfoExtractor): return _playlist_from_matches( matches, lambda m: unescapeHTML(m[1])) + # Look for embedded Dailymotion playlist player (#3822) + m = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?dailymotion\.[a-z]{2,3}/widget/jukebox\?.+?)\1', webpage) + if m: + playlists = re.findall( + r'list\[\]=/playlist/([^/]+)/', unescapeHTML(m.group('url'))) + if playlists: + return _playlist_from_matches( + playlists, lambda p: '//dailymotion.com/playlist/%s' % p) + # Look for embedded Wistia player match = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) + r'<(?:meta[^>]+?content|iframe[^>]+?src)=(["\'])(?P<url>(?:https?:)?//(?:fast\.)?wistia\.net/embed/iframe/.+?)\1', webpage) if match: + embed_url = self._proto_relative_url( + unescapeHTML(match.group('url'))) return { '_type': 'url_transparent', - 'url': unescapeHTML(match.group('url')), + 'url': embed_url, 'ie_key': 'Wistia', 'uploader': video_uploader, 'title': video_title, 'id': video_id, } + match = re.search(r'(?:id=["\']wistia_|data-wistia-?id=["\']|Wistia\.embed\(["\'])(?P<id>[^"\']+)', webpage) + if match: + return { + '_type': 'url_transparent', + 'url': 'http://fast.wistia.net/embed/iframe/{0:}'.format(match.group('id')), + 'ie_key': 'Wistia', + 'uploader': video_uploader, + 'title': video_title, + 'id': match.group('id') + } + # Look for embedded blip.tv player mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage) if mobj: - return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV') + return self.url_result('http://blip.tv/a/a-' + mobj.group(1), 'BlipTV') mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9_]+)', webpage) if mobj: return self.url_result(mobj.group(1), 'BlipTV') @@ -694,7 +832,7 @@ class GenericIE(InfoExtractor): # Look for Ooyala videos mobj = (re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=(?P<ec>[^"&]+)', webpage) or - re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)) + re.search(r'OO.Player.create\([\'"].*?[\'"],\s*[\'"](?P<ec>.{32})[\'"]', webpage)) if mobj is not None: return OoyalaIE._build_url_result(mobj.group('ec')) @@ -788,7 +926,7 @@ class GenericIE(InfoExtractor): # Look for embeded soundcloud player mobj = re.search( - r'<iframe src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"', + r'<iframe\s+(?:[a-zA-Z0-9_-]+="[^"]+"\s+)*src="(?P<url>https?://(?:w\.)?soundcloud\.com/player[^"]+)"', webpage) if mobj is not None: url = unescapeHTML(mobj.group('url')) @@ -825,59 +963,75 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'SBS') mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>https?://m\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', + r'<iframe[^>]+?src=(["\'])(?P<url>https?://m(?:lb)?\.mlb\.com/shared/video/embed/embed\.html\?.+?)\1', webpage) if mobj is not None: return self.url_result(mobj.group('url'), 'MLB') + mobj = re.search( + r'<iframe[^>]+?src=(["\'])(?P<url>%s)\1' % CondeNastIE.EMBED_URL, + webpage) + if mobj is not None: + return self.url_result(self._proto_relative_url(mobj.group('url'), scheme='http:'), 'CondeNast') + + mobj = re.search( + r'<iframe[^>]+src="(?P<url>https?://new\.livestream\.com/[^"]+/player[^"]+)"', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Livestream') + + def check_video(vurl): + vpath = compat_urlparse.urlparse(vurl).path + vext = determine_ext(vpath) + return '.' in vpath and vext not in ('swf', 'png', 'jpg', 'srt', 'sbv', 'sub', 'vtt', 'ttml') + + def filter_video(urls): + return list(filter(check_video, urls)) + # Start with something easy: JW Player in SWFObject - found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) + found = filter_video(re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage)) if not found: # Look for gorilla-vid style embedding - found = re.findall(r'''(?sx) + found = filter_video(re.findall(r'''(?sx) (?: jw_plugins| JWPlayerOptions| jwplayer\s*\(\s*["'][^'"]+["']\s*\)\s*\.setup ) - .*?file\s*:\s*["\'](.*?)["\']''', webpage) + .*?file\s*:\s*["\'](.*?)["\']''', webpage)) if not found: # Broaden the search a little bit - found = re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage) + found = filter_video(re.findall(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)) if not found: # Broaden the findall a little bit: JWPlayer JS loader - found = re.findall(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage) + found = filter_video(re.findall( + r'[^A-Za-z0-9]?file["\']?:\s*["\'](http(?![^\'"]+\.[0-9]+[\'"])[^\'"]+)["\']', webpage)) if not found: # Flow player - found = re.findall(r'''(?xs) + found = filter_video(re.findall(r'''(?xs) flowplayer\("[^"]+",\s* \{[^}]+?\}\s*, \s*{[^}]+? ["']?clip["']?\s*:\s*\{\s* ["']?url["']?\s*:\s*["']([^"']+)["'] - ''', webpage) + ''', webpage)) if not found: # Try to find twitter cards info - found = re.findall(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage) + found = filter_video(re.findall( + r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)) if not found: # We look for Open Graph info: # We have to match any number spaces between elements, some sites try to align them (eg.: statigr.am) m_video_type = re.findall(r'<meta.*?property="og:video:type".*?content="video/(.*?)"', webpage) # We only look in og:video if the MIME type is a video, don't try if it's a Flash player: if m_video_type is not None: - def check_video(vurl): - vpath = compat_urlparse.urlparse(vurl).path - vext = determine_ext(vpath) - return '.' in vpath and vext not in ('swf', 'png', 'jpg') - found = list(filter( - check_video, - re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage))) + found = filter_video(re.findall(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)) if not found: # HTML5 video - found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]+)? src="([^"]+)"', webpage) + found = re.findall(r'(?s)<video[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']', webpage) if not found: found = re.search( r'(?i)<meta\s+(?=(?:[a-z-]+="[^"]+"\s+)*http-equiv="refresh")' - r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'([^\']+)\'"', + r'(?:[a-z-]+="[^"]+"\s+)*?content="[0-9]{,2};url=\'?([^\'"]+)', webpage) if found: new_url = found.group(1) @@ -919,4 +1073,3 @@ class GenericIE(InfoExtractor): '_type': 'playlist', 'entries': entries, } - diff --git a/youtube_dl/extractor/glide.py b/youtube_dl/extractor/glide.py new file mode 100644 index 000000000..9561ed5fb --- /dev/null +++ b/youtube_dl/extractor/glide.py @@ -0,0 +1,40 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class GlideIE(InfoExtractor): + IE_DESC = 'Glide mobile video messages (glide.me)' + _VALID_URL = r'https?://share\.glide\.me/(?P<id>[A-Za-z0-9\-=_+]+)' + _TEST = { + 'url': 'http://share.glide.me/UZF8zlmuQbe4mr+7dCiQ0w==', + 'md5': '4466372687352851af2d131cfaa8a4c7', + 'info_dict': { + 'id': 'UZF8zlmuQbe4mr+7dCiQ0w==', + 'ext': 'mp4', + 'title': 'Damon Timm\'s Glide message', + 'thumbnail': 're:^https?://.*?\.cloudfront\.net/.*\.jpg$', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + title = self._html_search_regex( + r'<title>(.*?)', webpage, 'title') + video_url = self.http_scheme() + self._search_regex( + r'', webpage, 'video URL') + thumbnail_url = self._search_regex( + r']+\bid="(\d+)"', + ] + + _RESIGN_EXPIRATION = 86400 + + _TESTS = [ + { + 'url': 'http://globotv.globo.com/sportv/futebol-nacional/v/os-gols-de-atletico-mg-3-x-2-santos-pela-24a-rodada-do-brasileirao/3654973/', + 'md5': '03ebf41cb7ade43581608b7d9b71fab0', + 'info_dict': { + 'id': '3654973', + 'ext': 'mp4', + 'title': 'Os gols de Atlético-MG 3 x 2 Santos pela 24ª rodada do Brasileirão', + 'duration': 251.585, + 'uploader': 'SporTV', + 'uploader_id': 698, + 'like_count': int, + } + }, + { + 'url': 'http://g1.globo.com/carros/autoesporte/videos/t/exclusivos-do-g1/v/mercedes-benz-gla-passa-por-teste-de-colisao-na-europa/3607726/', + 'md5': 'b3ccc801f75cd04a914d51dadb83a78d', + 'info_dict': { + 'id': '3607726', + 'ext': 'mp4', + 'title': 'Mercedes-Benz GLA passa por teste de colisão na Europa', + 'duration': 103.204, + 'uploader': 'Globo.com', + 'uploader_id': 265, + 'like_count': int, + } + }, + { + 'url': 'http://g1.globo.com/jornal-nacional/noticia/2014/09/novidade-na-fiscalizacao-de-bagagem-pela-receita-provoca-discussoes.html', + 'md5': '307fdeae4390ccfe6ba1aa198cf6e72b', + 'info_dict': { + 'id': '3652183', + 'ext': 'mp4', + 'title': 'Receita Federal explica como vai fiscalizar bagagens de quem retorna ao Brasil de avião', + 'duration': 110.711, + 'uploader': 'Rede Globo', + 'uploader_id': 196, + 'like_count': int, + } + }, + ] + + class MD5(): + HEX_FORMAT_LOWERCASE = 0 + HEX_FORMAT_UPPERCASE = 1 + BASE64_PAD_CHARACTER_DEFAULT_COMPLIANCE = '' + BASE64_PAD_CHARACTER_RFC_COMPLIANCE = '=' + PADDING = '=0xFF01DD' + hexcase = 0 + b64pad = '' + + def __init__(self): + pass + + class JSArray(list): + def __getitem__(self, y): + try: + return list.__getitem__(self, y) + except IndexError: + return 0 + + def __setitem__(self, i, y): + try: + return list.__setitem__(self, i, y) + except IndexError: + self.extend([0] * (i - len(self) + 1)) + self[-1] = y + + @classmethod + def hex_md5(cls, param1): + return cls.rstr2hex(cls.rstr_md5(cls.str2rstr_utf8(param1))) + + @classmethod + def b64_md5(cls, param1, param2=None): + return cls.rstr2b64(cls.rstr_md5(cls.str2rstr_utf8(param1, param2))) + + @classmethod + def any_md5(cls, param1, param2): + return cls.rstr2any(cls.rstr_md5(cls.str2rstr_utf8(param1)), param2) + + @classmethod + def rstr_md5(cls, param1): + return cls.binl2rstr(cls.binl_md5(cls.rstr2binl(param1), len(param1) * 8)) + + @classmethod + def rstr2hex(cls, param1): + _loc_2 = '0123456789ABCDEF' if cls.hexcase else '0123456789abcdef' + _loc_3 = '' + for _loc_5 in range(0, len(param1)): + _loc_4 = compat_ord(param1[_loc_5]) + _loc_3 += _loc_2[_loc_4 >> 4 & 15] + _loc_2[_loc_4 & 15] + return _loc_3 + + @classmethod + def rstr2b64(cls, param1): + _loc_2 = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_' + _loc_3 = '' + _loc_4 = len(param1) + for _loc_5 in range(0, _loc_4, 3): + _loc_6_1 = compat_ord(param1[_loc_5]) << 16 + _loc_6_2 = compat_ord(param1[_loc_5 + 1]) << 8 if _loc_5 + 1 < _loc_4 else 0 + _loc_6_3 = compat_ord(param1[_loc_5 + 2]) if _loc_5 + 2 < _loc_4 else 0 + _loc_6 = _loc_6_1 | _loc_6_2 | _loc_6_3 + for _loc_7 in range(0, 4): + if _loc_5 * 8 + _loc_7 * 6 > len(param1) * 8: + _loc_3 += cls.b64pad + else: + _loc_3 += _loc_2[_loc_6 >> 6 * (3 - _loc_7) & 63] + return _loc_3 + + @staticmethod + def rstr2any(param1, param2): + _loc_3 = len(param2) + _loc_4 = [] + _loc_9 = [0] * ((len(param1) >> 2) + 1) + for _loc_5 in range(0, len(_loc_9)): + _loc_9[_loc_5] = compat_ord(param1[_loc_5 * 2]) << 8 | compat_ord(param1[_loc_5 * 2 + 1]) + + while len(_loc_9) > 0: + _loc_8 = [] + _loc_7 = 0 + for _loc_5 in range(0, len(_loc_9)): + _loc_7 = (_loc_7 << 16) + _loc_9[_loc_5] + _loc_6 = math.floor(_loc_7 / _loc_3) + _loc_7 -= _loc_6 * _loc_3 + if len(_loc_8) > 0 or _loc_6 > 0: + _loc_8[len(_loc_8)] = _loc_6 + + _loc_4[len(_loc_4)] = _loc_7 + _loc_9 = _loc_8 + + _loc_10 = '' + _loc_5 = len(_loc_4) - 1 + while _loc_5 >= 0: + _loc_10 += param2[_loc_4[_loc_5]] + _loc_5 -= 1 + + return _loc_10 + + @classmethod + def str2rstr_utf8(cls, param1, param2=None): + _loc_3 = '' + _loc_4 = -1 + if not param2: + param2 = cls.PADDING + param1 = param1 + param2[1:9] + while True: + _loc_4 += 1 + if _loc_4 >= len(param1): + break + _loc_5 = compat_ord(param1[_loc_4]) + _loc_6 = compat_ord(param1[_loc_4 + 1]) if _loc_4 + 1 < len(param1) else 0 + if 55296 <= _loc_5 <= 56319 and 56320 <= _loc_6 <= 57343: + _loc_5 = 65536 + ((_loc_5 & 1023) << 10) + (_loc_6 & 1023) + _loc_4 += 1 + if _loc_5 <= 127: + _loc_3 += compat_chr(_loc_5) + continue + if _loc_5 <= 2047: + _loc_3 += compat_chr(192 | _loc_5 >> 6 & 31) + compat_chr(128 | _loc_5 & 63) + continue + if _loc_5 <= 65535: + _loc_3 += compat_chr(224 | _loc_5 >> 12 & 15) + compat_chr(128 | _loc_5 >> 6 & 63) + compat_chr( + 128 | _loc_5 & 63) + continue + if _loc_5 <= 2097151: + _loc_3 += compat_chr(240 | _loc_5 >> 18 & 7) + compat_chr(128 | _loc_5 >> 12 & 63) + compat_chr( + 128 | _loc_5 >> 6 & 63) + compat_chr(128 | _loc_5 & 63) + return _loc_3 + + @staticmethod + def rstr2binl(param1): + _loc_2 = [0] * ((len(param1) >> 2) + 1) + for _loc_3 in range(0, len(_loc_2)): + _loc_2[_loc_3] = 0 + for _loc_3 in range(0, len(param1) * 8, 8): + _loc_2[_loc_3 >> 5] |= (compat_ord(param1[_loc_3 // 8]) & 255) << _loc_3 % 32 + return _loc_2 + + @staticmethod + def binl2rstr(param1): + _loc_2 = '' + for _loc_3 in range(0, len(param1) * 32, 8): + _loc_2 += compat_chr(param1[_loc_3 >> 5] >> _loc_3 % 32 & 255) + return _loc_2 + + @classmethod + def binl_md5(cls, param1, param2): + param1 = cls.JSArray(param1) + param1[param2 >> 5] |= 128 << param2 % 32 + param1[(param2 + 64 >> 9 << 4) + 14] = param2 + _loc_3 = 1732584193 + _loc_4 = -271733879 + _loc_5 = -1732584194 + _loc_6 = 271733878 + for _loc_7 in range(0, len(param1), 16): + _loc_8 = _loc_3 + _loc_9 = _loc_4 + _loc_10 = _loc_5 + _loc_11 = _loc_6 + _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 0], 7, -680876936) + _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 1], 12, -389564586) + _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 2], 17, 606105819) + _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 3], 22, -1044525330) + _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 4], 7, -176418897) + _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 5], 12, 1200080426) + _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 6], 17, -1473231341) + _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 7], 22, -45705983) + _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 8], 7, 1770035416) + _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 9], 12, -1958414417) + _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 10], 17, -42063) + _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 11], 22, -1990404162) + _loc_3 = cls.md5_ff(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 12], 7, 1804603682) + _loc_6 = cls.md5_ff(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 13], 12, -40341101) + _loc_5 = cls.md5_ff(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 14], 17, -1502002290) + _loc_4 = cls.md5_ff(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 15], 22, 1236535329) + _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 1], 5, -165796510) + _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 6], 9, -1069501632) + _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 11], 14, 643717713) + _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 0], 20, -373897302) + _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 5], 5, -701558691) + _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 10], 9, 38016083) + _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 15], 14, -660478335) + _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 4], 20, -405537848) + _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 9], 5, 568446438) + _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 14], 9, -1019803690) + _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 3], 14, -187363961) + _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 8], 20, 1163531501) + _loc_3 = cls.md5_gg(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 13], 5, -1444681467) + _loc_6 = cls.md5_gg(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 2], 9, -51403784) + _loc_5 = cls.md5_gg(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 7], 14, 1735328473) + _loc_4 = cls.md5_gg(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 12], 20, -1926607734) + _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 5], 4, -378558) + _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 8], 11, -2022574463) + _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 11], 16, 1839030562) + _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 14], 23, -35309556) + _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 1], 4, -1530992060) + _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 4], 11, 1272893353) + _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 7], 16, -155497632) + _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 10], 23, -1094730640) + _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 13], 4, 681279174) + _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 0], 11, -358537222) + _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 3], 16, -722521979) + _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 6], 23, 76029189) + _loc_3 = cls.md5_hh(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 9], 4, -640364487) + _loc_6 = cls.md5_hh(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 12], 11, -421815835) + _loc_5 = cls.md5_hh(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 15], 16, 530742520) + _loc_4 = cls.md5_hh(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 2], 23, -995338651) + _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 0], 6, -198630844) + _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 7], 10, 1126891415) + _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 14], 15, -1416354905) + _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 5], 21, -57434055) + _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 12], 6, 1700485571) + _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 3], 10, -1894986606) + _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 10], 15, -1051523) + _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 1], 21, -2054922799) + _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 8], 6, 1873313359) + _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 15], 10, -30611744) + _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 6], 15, -1560198380) + _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 13], 21, 1309151649) + _loc_3 = cls.md5_ii(_loc_3, _loc_4, _loc_5, _loc_6, param1[_loc_7 + 4], 6, -145523070) + _loc_6 = cls.md5_ii(_loc_6, _loc_3, _loc_4, _loc_5, param1[_loc_7 + 11], 10, -1120210379) + _loc_5 = cls.md5_ii(_loc_5, _loc_6, _loc_3, _loc_4, param1[_loc_7 + 2], 15, 718787259) + _loc_4 = cls.md5_ii(_loc_4, _loc_5, _loc_6, _loc_3, param1[_loc_7 + 9], 21, -343485551) + _loc_3 = cls.safe_add(_loc_3, _loc_8) + _loc_4 = cls.safe_add(_loc_4, _loc_9) + _loc_5 = cls.safe_add(_loc_5, _loc_10) + _loc_6 = cls.safe_add(_loc_6, _loc_11) + return [_loc_3, _loc_4, _loc_5, _loc_6] + + @classmethod + def md5_cmn(cls, param1, param2, param3, param4, param5, param6): + return cls.safe_add( + cls.bit_rol(cls.safe_add(cls.safe_add(param2, param1), cls.safe_add(param4, param6)), param5), param3) + + @classmethod + def md5_ff(cls, param1, param2, param3, param4, param5, param6, param7): + return cls.md5_cmn(param2 & param3 | ~param2 & param4, param1, param2, param5, param6, param7) + + @classmethod + def md5_gg(cls, param1, param2, param3, param4, param5, param6, param7): + return cls.md5_cmn(param2 & param4 | param3 & ~param4, param1, param2, param5, param6, param7) + + @classmethod + def md5_hh(cls, param1, param2, param3, param4, param5, param6, param7): + return cls.md5_cmn(param2 ^ param3 ^ param4, param1, param2, param5, param6, param7) + + @classmethod + def md5_ii(cls, param1, param2, param3, param4, param5, param6, param7): + return cls.md5_cmn(param3 ^ (param2 | ~param4), param1, param2, param5, param6, param7) + + @classmethod + def safe_add(cls, param1, param2): + _loc_3 = (param1 & 65535) + (param2 & 65535) + _loc_4 = (param1 >> 16) + (param2 >> 16) + (_loc_3 >> 16) + return cls.lshift(_loc_4, 16) | _loc_3 & 65535 + + @classmethod + def bit_rol(cls, param1, param2): + return cls.lshift(param1, param2) | (param1 & 0xFFFFFFFF) >> (32 - param2) + + @staticmethod + def lshift(value, count): + r = (0xFFFFFFFF & value) << count + return -(~(r - 1) & 0xFFFFFFFF) if r > 0x7FFFFFFF else r + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + video_id = self._search_regex(self._VIDEOID_REGEXES, webpage, 'video id') + + video = self._download_json( + self._API_URL_TEMPLATE % video_id, video_id)['videos'][0] + + title = video['title'] + duration = float_or_none(video['duration'], 1000) + like_count = video['likes'] + uploader = video['channel'] + uploader_id = video['channel_id'] + + formats = [] + + for resource in video['resources']: + resource_id = resource.get('_id') + if not resource_id: + continue + + security = self._download_json( + self._SECURITY_URL_TEMPLATE % (video_id, resource_id), + video_id, 'Downloading security hash for %s' % resource_id) + + security_hash = security.get('hash') + if not security_hash: + message = security.get('message') + if message: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, message), expected=True) + continue + + hash_code = security_hash[:2] + received_time = int(security_hash[2:12]) + received_random = security_hash[12:22] + received_md5 = security_hash[22:] + + sign_time = received_time + self._RESIGN_EXPIRATION + padding = '%010d' % random.randint(1, 10000000000) + + signed_md5 = self.MD5.b64_md5(received_md5 + compat_str(sign_time) + padding) + signed_hash = hash_code + compat_str(received_time) + received_random + compat_str(sign_time) + padding + signed_md5 + + formats.append({ + 'url': '%s?h=%s&k=%s' % (resource['url'], signed_hash, 'flash'), + 'format_id': resource_id, + 'height': resource['height'] + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'duration': duration, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'like_count': like_count, + 'formats': formats + } diff --git a/youtube_dl/extractor/godtube.py b/youtube_dl/extractor/godtube.py index 73bd6d890..363dc6608 100644 --- a/youtube_dl/extractor/godtube.py +++ b/youtube_dl/extractor/godtube.py @@ -36,16 +36,16 @@ class GodTubeIE(InfoExtractor): 'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(), video_id, 'Downloading player config XML') - video_url = config.find('.//file').text - uploader = config.find('.//author').text - timestamp = parse_iso8601(config.find('.//date').text) - duration = parse_duration(config.find('.//duration').text) - thumbnail = config.find('.//image').text + video_url = config.find('file').text + uploader = config.find('author').text + timestamp = parse_iso8601(config.find('date').text) + duration = parse_duration(config.find('duration').text) + thumbnail = config.find('image').text media = self._download_xml( 'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML') - title = media.find('.//title').text + title = media.find('title').text return { 'id': video_id, diff --git a/youtube_dl/extractor/goldenmoustache.py b/youtube_dl/extractor/goldenmoustache.py new file mode 100644 index 000000000..10001d4d9 --- /dev/null +++ b/youtube_dl/extractor/goldenmoustache.py @@ -0,0 +1,57 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, +) + + +class GoldenMoustacheIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?goldenmoustache\.com/(?P[\w-]+)-(?P\d+)' + _TESTS = [{ + 'url': 'http://www.goldenmoustache.com/suricate-le-poker-3700/', + 'md5': '0f904432fa07da5054d6c8beb5efb51a', + 'info_dict': { + 'id': '3700', + 'ext': 'mp4', + 'title': 'Suricate - Le Poker', + 'description': 'md5:3d1f242f44f8c8cb0a106f1fd08e5dc9', + 'thumbnail': 're:^https?://.*\.jpg$', + 'view_count': int, + } + }, { + 'url': 'http://www.goldenmoustache.com/le-lab-tout-effacer-mc-fly-et-carlito-55249/', + 'md5': '27f0c50fb4dd5f01dc9082fc67cd5700', + 'info_dict': { + 'id': '55249', + 'ext': 'mp4', + 'title': 'Le LAB - Tout Effacer (Mc Fly et Carlito)', + 'description': 'md5:9b7fbf11023fb2250bd4b185e3de3b2a', + 'thumbnail': 're:^https?://.*\.(?:png|jpg)$', + 'view_count': int, + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + video_url = self._html_search_regex( + r'data-src-type="mp4" data-src="([^"]+)"', webpage, 'video URL') + title = self._html_search_regex( + r'(.*?)(?: - Golden Moustache)?', webpage, 'title') + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + view_count = int_or_none(self._html_search_regex( + r'([0-9]+)\s*VUES', + webpage, 'view count', fatal=False)) + + return { + 'id': video_id, + 'url': video_url, + 'ext': 'mp4', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/golem.py b/youtube_dl/extractor/golem.py new file mode 100644 index 000000000..53714f47f --- /dev/null +++ b/youtube_dl/extractor/golem.py @@ -0,0 +1,69 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + determine_ext, +) + + +class GolemIE(InfoExtractor): + _VALID_URL = r'^https?://video\.golem\.de/.+?/(?P.+?)/' + _TEST = { + 'url': 'http://video.golem.de/handy/14095/iphone-6-und-6-plus-test.html', + 'md5': 'c1a2c0a3c863319651c7c992c5ee29bf', + 'info_dict': { + 'id': '14095', + 'format_id': 'high', + 'ext': 'mp4', + 'title': 'iPhone 6 und 6 Plus - Test', + 'duration': 300.44, + 'filesize': 65309548, + } + } + + _PREFIX = 'http://video.golem.de' + + def _real_extract(self, url): + video_id = self._match_id(url) + + config = self._download_xml( + 'https://video.golem.de/xml/{0}.xml'.format(video_id), video_id) + + info = { + 'id': video_id, + 'title': config.findtext('./title', 'golem'), + 'duration': self._float(config.findtext('./playtime'), 'duration'), + } + + formats = [] + for e in config: + url = e.findtext('./url') + if not url: + continue + + formats.append({ + 'format_id': e.tag, + 'url': compat_urlparse.urljoin(self._PREFIX, url), + 'height': self._int(e.get('height'), 'height'), + 'width': self._int(e.get('width'), 'width'), + 'filesize': self._int(e.findtext('filesize'), 'filesize'), + 'ext': determine_ext(e.findtext('./filename')), + }) + self._sort_formats(formats) + info['formats'] = formats + + thumbnails = [] + for e in config.findall('.//teaser'): + url = e.findtext('./url') + if not url: + continue + thumbnails.append({ + 'url': compat_urlparse.urljoin(self._PREFIX, url), + 'width': self._int(e.get('width'), 'thumbnail width'), + 'height': self._int(e.get('height'), 'thumbnail height'), + }) + info['thumbnails'] = thumbnails + + return info diff --git a/youtube_dl/extractor/googleplus.py b/youtube_dl/extractor/googleplus.py index 07d994b44..fcefe54cd 100644 --- a/youtube_dl/extractor/googleplus.py +++ b/youtube_dl/extractor/googleplus.py @@ -1,13 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import datetime import re +import codecs from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) +from ..utils import unified_strdate class GooglePlusIE(InfoExtractor): @@ -19,74 +17,57 @@ class GooglePlusIE(InfoExtractor): 'info_dict': { 'id': 'ZButuJc6CtH', 'ext': 'flv', + 'title': '嘆きの天使 降臨', 'upload_date': '20120613', 'uploader': '井上ヨシマサ', - 'title': '嘆きの天使 降臨', } } def _real_extract(self, url): - # Extract id from URL - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') + video_id = self._match_id(url) # Step 1, Retrieve post webpage to extract further information webpage = self._download_webpage(url, video_id, 'Downloading entry webpage') - self.report_extraction(video_id) - - # Extract update date - upload_date = self._html_search_regex( + title = self._og_search_description(webpage).splitlines()[0] + upload_date = unified_strdate(self._html_search_regex( r'''(?x) ([0-9]{4}-[0-9]{2}-[0-9]{2})''', - webpage, 'upload date', fatal=False, flags=re.VERBOSE) - if upload_date: - # Convert timestring to a format suitable for filename - upload_date = datetime.datetime.strptime(upload_date, "%Y-%m-%d") - upload_date = upload_date.strftime('%Y%m%d') - - # Extract uploader - uploader = self._html_search_regex(r'rel\="author".*?>(.*?)', - webpage, 'uploader', fatal=False) - - # Extract title - # Get the first line for title - video_title = self._og_search_description(webpage).splitlines()[0] + webpage, 'upload date', fatal=False, flags=re.VERBOSE)) + uploader = self._html_search_regex( + r'rel="author".*?>(.*?)', webpage, 'uploader', fatal=False) # Step 2, Simulate clicking the image box to launch video DOMAIN = 'https://plus.google.com/' - video_page = self._search_regex(r'(?:www\.)? - (?:daclips\.in|gorillavid\.in))/ + (?:daclips\.in|gorillavid\.in|movpod\.in|fastvideo\.in))/ (?:embed-)?(?P[0-9a-zA-Z]+)(?:-[0-9]+x[0-9]+\.html)? ''' + _FILE_NOT_FOUND_REGEX = r'>(?:404 - )?File Not Found<' + _TESTS = [{ 'url': 'http://gorillavid.in/06y9juieqpmi', 'md5': '5ae4a3580620380619678ee4875893ba', 'info_dict': { 'id': '06y9juieqpmi', 'ext': 'flv', - 'title': 'Rebecca Black My Moment Official Music Video Reaction', + 'title': 'Rebecca Black My Moment Official Music Video Reaction-6GK87Rc8bzQ', 'thumbnail': 're:http://.*\.jpg', }, }, { @@ -43,9 +47,22 @@ class GorillaVidIE(InfoExtractor): 'info_dict': { 'id': '3rso4kdn6f9m', 'ext': 'mp4', - 'title': 'Micro Pig piglets ready on 16th July 2009', + 'title': 'Micro Pig piglets ready on 16th July 2009-bG0PdrCdxUc', + 'thumbnail': 're:http://.*\.jpg', + } + }, { + # video with countdown timeout + 'url': 'http://fastvideo.in/1qmdn1lmsmbw', + 'md5': '8b87ec3f6564a3108a0e8e66594842ba', + 'info_dict': { + 'id': '1qmdn1lmsmbw', + 'ext': 'mp4', + 'title': 'Man of Steel - Trailer', 'thumbnail': 're:http://.*\.jpg', }, + }, { + 'url': 'http://movpod.in/0wguyyxi1yca', + 'only_matching': True, }] def _real_extract(self, url): @@ -54,14 +71,23 @@ class GorillaVidIE(InfoExtractor): webpage = self._download_webpage('http://%s/%s' % (mobj.group('host'), video_id), video_id) + if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) + fields = dict(re.findall(r'''(?x)(?:[Ww]ait)?\s*(\d+)\s*(?:seconds?)?', + webpage, 'countdown', default=None)) + if countdown: + self._sleep(countdown, video_id) + post = compat_urllib_parse.urlencode(fields) req = compat_urllib_request.Request(url, post) @@ -69,14 +95,18 @@ class GorillaVidIE(InfoExtractor): webpage = self._download_webpage(req, video_id, 'Downloading video page') - title = self._search_regex(r'style="z-index: [0-9]+;">([0-9a-zA-Z ]+)(?:-.+)?', webpage, 'title') - thumbnail = self._search_regex(r'image:\'(http[^\']+)\',', webpage, 'thumbnail') - url = self._search_regex(r'file: \'(http[^\']+)\',', webpage, 'file url') + title = self._search_regex( + r'style="z-index: [0-9]+;">([^<]+)', + webpage, 'title', default=None) or self._og_search_title(webpage) + video_url = self._search_regex( + r'file\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'file url') + thumbnail = self._search_regex( + r'image\s*:\s*["\'](http[^"\']+)["\'],', webpage, 'thumbnail', fatal=False) formats = [{ 'format_id': 'sd', - 'url': url, - 'ext': determine_ext(url), + 'url': video_url, + 'ext': determine_ext(video_url), 'quality': 1, }] diff --git a/youtube_dl/extractor/goshgay.py b/youtube_dl/extractor/goshgay.py index 7bca21ad0..18474cbb7 100644 --- a/youtube_dl/extractor/goshgay.py +++ b/youtube_dl/extractor/goshgay.py @@ -1,15 +1,11 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( compat_urlparse, - str_to_int, ExtractorError, ) -import json class GoshgayIE(InfoExtractor): @@ -27,36 +23,27 @@ class GoshgayIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._search_regex(r'class="video-title">

    (.+?)<', webpage, 'title') + title = self._og_search_title(webpage) + thumbnail = self._og_search_thumbnail(webpage) + family_friendly = self._html_search_meta( + 'isFamilyFriendly', webpage, default='false') + config_url = self._search_regex( + r"'config'\s*:\s*'([^']+)'", webpage, 'config URL') - player_config = self._search_regex( - r'(?s)jwplayer\("player"\)\.setup\(({.+?})\)', webpage, 'config settings') - player_vars = json.loads(player_config.replace("'", '"')) - width = str_to_int(player_vars.get('width')) - height = str_to_int(player_vars.get('height')) - config_uri = player_vars.get('config') + config = self._download_xml( + config_url, video_id, 'Downloading player config XML') - if config_uri is None: - raise ExtractorError('Missing config URI') - node = self._download_xml(config_uri, video_id, 'Downloading player config XML', - errnote='Unable to download XML') - if node is None: + if config is None: raise ExtractorError('Missing config XML') - if node.tag != 'config': + if config.tag != 'config': raise ExtractorError('Missing config attribute') - fns = node.findall('file') - imgs = node.findall('image') - if len(fns) != 1: + fns = config.findall('file') + if len(fns) < 1: raise ExtractorError('Missing media URI') video_url = fns[0].text - if len(imgs) < 1: - thumbnail = None - else: - thumbnail = imgs[0].text url_comp = compat_urlparse.urlparse(url) ref = "%s://%s%s" % (url_comp[0], url_comp[1], url_comp[2]) @@ -65,9 +52,7 @@ class GoshgayIE(InfoExtractor): 'id': video_id, 'url': video_url, 'title': title, - 'width': width, - 'height': height, 'thumbnail': thumbnail, 'http_referer': ref, - 'age_limit': 18, + 'age_limit': 0 if family_friendly == 'true' else 18, } diff --git a/youtube_dl/extractor/grooveshark.py b/youtube_dl/extractor/grooveshark.py index 726adff77..fff74a70a 100644 --- a/youtube_dl/extractor/grooveshark.py +++ b/youtube_dl/extractor/grooveshark.py @@ -8,12 +8,13 @@ import re from .common import InfoExtractor -from ..utils import ExtractorError, compat_urllib_request, compat_html_parser - -from ..utils import ( +from ..compat import ( + compat_html_parser, compat_urllib_parse, + compat_urllib_request, compat_urlparse, ) +from ..utils import ExtractorError class GroovesharkHtmlParser(compat_html_parser.HTMLParser): diff --git a/youtube_dl/extractor/hark.py b/youtube_dl/extractor/hark.py index 5bdd08afa..b6cc15b6f 100644 --- a/youtube_dl/extractor/hark.py +++ b/youtube_dl/extractor/hark.py @@ -1,37 +1,33 @@ # -*- coding: utf-8 -*- - -import re -import json +from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import determine_ext + class HarkIE(InfoExtractor): - _VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+' + _VALID_URL = r'https?://www\.hark\.com/clips/(?P.+?)-.+' _TEST = { - u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', - u'file': u'mmbzyhkgny.mp3', - u'md5': u'6783a58491b47b92c7c1af5a77d4cbee', - u'info_dict': { - u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013", - u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', - u'duration': 11, + 'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', + 'md5': '6783a58491b47b92c7c1af5a77d4cbee', + 'info_dict': { + 'id': 'mmbzyhkgny', + 'ext': 'mp3', + 'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013', + 'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', + 'duration': 11, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) - json_url = "http://www.hark.com/clips/%s.json" %(video_id) - info_json = self._download_webpage(json_url, video_id) - info = json.loads(info_json) - final_url = info['url'] + video_id = self._match_id(url) + data = self._download_json( + 'http://www.hark.com/clips/%s.json' % video_id, video_id) - return {'id': video_id, - 'url' : final_url, - 'title': info['name'], - 'ext': determine_ext(final_url), - 'description': info['description'], - 'thumbnail': info['image_original'], - 'duration': info['duration'], - } + return { + 'id': video_id, + 'url': data['url'], + 'title': data['name'], + 'description': data.get('description'), + 'thumbnail': data.get('image_original'), + 'duration': data.get('duration'), + } diff --git a/youtube_dl/extractor/heise.py b/youtube_dl/extractor/heise.py new file mode 100644 index 000000000..278d9f527 --- /dev/null +++ b/youtube_dl/extractor/heise.py @@ -0,0 +1,79 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + parse_iso8601, +) + + +class HeiseIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?://(?:www\.)?heise\.de/video/artikel/ + .+?(?P[0-9]+)\.html(?:$|[?#]) + ''' + _TEST = { + 'url': ( + 'http://www.heise.de/video/artikel/Podcast-c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2404147.html' + ), + 'md5': 'ffed432483e922e88545ad9f2f15d30e', + 'info_dict': { + 'id': '2404147', + 'ext': 'mp4', + 'title': ( + "Podcast: c't uplink 3.3 – Owncloud / Tastaturen / Peilsender Smartphone" + ), + 'format_id': 'mp4_720p', + 'timestamp': 1411812600, + 'upload_date': '20140927', + 'description': 'In uplink-Episode 3.3 geht es darum, wie man sich von Cloud-Anbietern emanzipieren kann, worauf man beim Kauf einer Tastatur achten sollte und was Smartphones über uns verraten.', + 'thumbnail': 're:^https?://.*\.jpe?g$', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + container_id = self._search_regex( + r'
    Runtime:\s*([0-9:]+)
    ', webpage, 'duration', fatal=False)) diff --git a/youtube_dl/extractor/hotnewhiphop.py b/youtube_dl/extractor/hotnewhiphop.py index 80b48b1b3..651784b73 100644 --- a/youtube_dl/extractor/hotnewhiphop.py +++ b/youtube_dl/extractor/hotnewhiphop.py @@ -1,12 +1,13 @@ from __future__ import unicode_literals -import re import base64 from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse, compat_urllib_request, +) +from ..utils import ( ExtractorError, HEADRequest, ) @@ -16,25 +17,24 @@ class HotNewHipHopIE(InfoExtractor): _VALID_URL = r'http://www\.hotnewhiphop\.com/.*\.(?P.*)\.html' _TEST = { 'url': 'http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html', - 'file': '1435540.mp3', 'md5': '2c2cd2f76ef11a9b3b581e8b232f3d96', 'info_dict': { + 'id': '1435540', + 'ext': 'mp3', 'title': 'Freddie Gibbs - Lay It Down' } } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') - - webpage_src = self._download_webpage(url, video_id) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) video_url_base64 = self._search_regex( - r'data-path="(.*?)"', webpage_src, u'video URL', fatal=False) + r'data-path="(.*?)"', webpage, 'video URL', default=None) if video_url_base64 is None: video_url = self._search_regex( - r'"contentUrl" content="(.*?)"', webpage_src, u'video URL') + r'"contentUrl" content="(.*?)"', webpage, 'content URL') return self.url_result(video_url, ie='Youtube') reqdata = compat_urllib_parse.urlencode([ @@ -59,11 +59,11 @@ class HotNewHipHopIE(InfoExtractor): if video_url.endswith('.html'): raise ExtractorError('Redirect failed') - video_title = self._og_search_title(webpage_src).strip() + video_title = self._og_search_title(webpage).strip() return { 'id': video_id, 'url': video_url, 'title': video_title, - 'thumbnail': self._og_search_thumbnail(webpage_src), + 'thumbnail': self._og_search_thumbnail(webpage), } diff --git a/youtube_dl/extractor/howcast.py b/youtube_dl/extractor/howcast.py index 6ae04782c..3f7d6666c 100644 --- a/youtube_dl/extractor/howcast.py +++ b/youtube_dl/extractor/howcast.py @@ -13,7 +13,7 @@ class HowcastIE(InfoExtractor): 'info_dict': { 'id': '390161', 'ext': 'mp4', - 'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.', + 'description': 'The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here\'s the proper way to tie a square knot.', 'title': 'How to Tie a Square Knot Properly', } } @@ -27,10 +27,10 @@ class HowcastIE(InfoExtractor): self.report_extraction(video_id) video_url = self._search_regex(r'\'?file\'?: "(http://mobile-media\.howcast\.com/[0-9]+\.mp4)', - webpage, 'video URL') + webpage, 'video URL') video_description = self._html_search_regex(r'(.+?)', + title = self._html_search_regex( + r'(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)', webpage, 'title') - title = re.sub(r'(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)$', '', html_title) uploader_id = self._html_search_regex( r'@([^ ]+)', title, 'uploader name', fatal=False) diff --git a/youtube_dl/extractor/ign.py b/youtube_dl/extractor/ign.py index 9e8b69f57..3db668cd0 100644 --- a/youtube_dl/extractor/ign.py +++ b/youtube_dl/extractor/ign.py @@ -63,14 +63,17 @@ class IGNIE(InfoExtractor): 'id': '078fdd005f6d3c02f63d795faa1b984f', 'ext': 'mp4', 'title': 'Rewind Theater - Wild Trailer Gamescom 2014', - 'description': 'Giant skeletons, bloody hunts, and captivating' - ' natural beauty take our breath away.', + 'description': ( + 'Giant skeletons, bloody hunts, and captivating' + ' natural beauty take our breath away.' + ), }, }, ] def _find_video_id(self, webpage): res_id = [ + r'"video_id"\s*:\s*"(.*?)"', r'data-video-id="(.+?)"', r']*value="[^"]*?url=(https?://www\.ign\.com/videos/.*?)["&]', webpage) if multiple_urls: - return [self.url_result(u, ie='IGN') for u in multiple_urls] + entries = [self.url_result(u, ie='IGN') for u in multiple_urls] + return { + '_type': 'playlist', + 'id': name_or_id, + 'entries': entries, + } video_id = self._find_video_id(webpage) result = self._get_video_info(video_id) description = self._html_search_regex(self._DESCRIPTION_RE, - webpage, 'video description', flags=re.DOTALL) + webpage, 'video description', flags=re.DOTALL) result['description'] = description return result @@ -111,13 +119,13 @@ class IGNIE(InfoExtractor): class OneUPIE(IGNIE): - _VALID_URL = r'https?://gamevideos\.1up\.com/(?Pvideo)/id/(?P.+)' + _VALID_URL = r'https?://gamevideos\.1up\.com/(?Pvideo)/id/(?P.+)\.html' IE_NAME = '1up.com' _DESCRIPTION_RE = r'
    (.+?)
    ' _TESTS = [{ - 'url': 'http://gamevideos.1up.com/video/id/34976', + 'url': 'http://gamevideos.1up.com/video/id/34976.html', 'md5': '68a54ce4ebc772e4b71e3123d413163d', 'info_dict': { 'id': '34976', diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 4536db3bf..f2c1c10f5 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -6,7 +6,6 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, - get_element_by_attribute, ) @@ -27,10 +26,11 @@ class ImdbIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id) - descr = get_element_by_attribute('itemprop', 'description', webpage) + descr = self._html_search_regex( + r'(?s)(.*?)', + webpage, 'description', fatal=False) available_formats = re.findall( r'case \'(?P.*?)\' :$\s+url = \'(?P.*?)\'', webpage, flags=re.MULTILINE) @@ -71,11 +71,9 @@ class ImdbListIE(InfoExtractor): }, 'playlist_count': 7, } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - list_id = mobj.group('id') + def _real_extract(self, url): + list_id = self._match_id(url) webpage = self._download_webpage(url, list_id) entries = [ self.url_result('http://www.imdb.com' + m, 'Imdb') diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 5109f26ce..b020e2621 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -27,9 +27,9 @@ class InstagramIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"', - webpage, 'uploader id', fatal=False) + webpage, 'uploader id', fatal=False) desc = self._search_regex(r'"caption":"(.*?)"', webpage, 'description', - fatal=False) + fatal=False) return { 'id': video_id, diff --git a/youtube_dl/extractor/internetvideoarchive.py b/youtube_dl/extractor/internetvideoarchive.py index 4ddda2f1b..1e4799187 100644 --- a/youtube_dl/extractor/internetvideoarchive.py +++ b/youtube_dl/extractor/internetvideoarchive.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -12,12 +14,13 @@ class InternetVideoArchiveIE(InfoExtractor): _VALID_URL = r'https?://video\.internetvideoarchive\.net/flash/players/.*?\?.*?publishedid.*?' _TEST = { - u'url': u'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?customerid=69249&publishedid=452693&playerid=247', - u'file': u'452693.mp4', - u'info_dict': { - u'title': u'SKYFALL', - u'description': u'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.', - u'duration': 153, + 'url': 'http://video.internetvideoarchive.net/flash/players/flashconfiguration.aspx?customerid=69249&publishedid=452693&playerid=247', + 'info_dict': { + 'id': '452693', + 'ext': 'mp4', + 'title': 'SKYFALL', + 'description': 'In SKYFALL, Bond\'s loyalty to M is tested as her past comes back to haunt her. As MI6 comes under attack, 007 must track down and destroy the threat, no matter how personal the cost.', + 'duration': 149, }, } @@ -29,7 +32,7 @@ class InternetVideoArchiveIE(InfoExtractor): def _clean_query(query): NEEDED_ARGS = ['publishedid', 'customerid'] query_dic = compat_urlparse.parse_qs(query) - cleaned_dic = dict((k,v[0]) for (k,v) in query_dic.items() if k in NEEDED_ARGS) + cleaned_dic = dict((k, v[0]) for (k, v) in query_dic.items() if k in NEEDED_ARGS) # Other player ids return m3u8 urls cleaned_dic['playerid'] = '247' cleaned_dic['videokbrate'] = '100000' @@ -42,22 +45,26 @@ class InternetVideoArchiveIE(InfoExtractor): url = self._build_url(query) flashconfiguration = self._download_xml(url, video_id, - u'Downloading flash configuration') + 'Downloading flash configuration') file_url = flashconfiguration.find('file').text file_url = file_url.replace('/playlist.aspx', '/mrssplaylist.aspx') # Replace some of the parameters in the query to get the best quality # and http links (no m3u8 manifests) file_url = re.sub(r'(?<=\?)(.+)$', - lambda m: self._clean_query(m.group()), - file_url) + lambda m: self._clean_query(m.group()), + file_url) info = self._download_xml(file_url, video_id, - u'Downloading video info') + 'Downloading video info') item = info.find('channel/item') def _bp(p): - return xpath_with_ns(p, - {'media': 'http://search.yahoo.com/mrss/', - 'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats'}) + return xpath_with_ns( + p, + { + 'media': 'http://search.yahoo.com/mrss/', + 'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats', + } + ) formats = [] for content in item.findall(_bp('media:group/media:content')): attr = content.attrib diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index d1defd363..4247d6391 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -54,7 +54,7 @@ class IPrimaIE(InfoExtractor): player_url = ( 'http://embed.livebox.cz/iprimaplay/player-embed-v2.js?__tok%s__=%s' % - (floor(random()*1073741824), floor(random()*1073741824)) + (floor(random() * 1073741824), floor(random() * 1073741824)) ) req = compat_urllib_request.Request(player_url) diff --git a/youtube_dl/extractor/ivi.py b/youtube_dl/extractor/ivi.py index 75b543b7c..f0fba1adb 100644 --- a/youtube_dl/extractor/ivi.py +++ b/youtube_dl/extractor/ivi.py @@ -43,7 +43,7 @@ class IviIE(InfoExtractor): 'thumbnail': 'http://thumbs.ivi.ru/f15.vcp.digitalaccess.ru/contents/8/4/0068dc0677041f3336b7c2baad8fc0.jpg', }, 'skip': 'Only works from Russia', - } + } ] # Sorted by quality @@ -102,7 +102,7 @@ class IviIE(InfoExtractor): compilation = result['compilation'] title = result['title'] - title = '%s - %s' % (compilation, title) if compilation is not None else title + title = '%s - %s' % (compilation, title) if compilation is not None else title previews = result['preview'] previews.sort(key=lambda fmt: self._known_thumbnails.index(fmt['content_format'])) @@ -152,17 +152,17 @@ class IviCompilationIE(InfoExtractor): compilation_id = mobj.group('compilationid') season_id = mobj.group('seasonid') - if season_id is not None: # Season link + if season_id is not None: # Season link season_page = self._download_webpage(url, compilation_id, 'Downloading season %s web page' % season_id) playlist_id = '%s/season%s' % (compilation_id, season_id) playlist_title = self._html_search_meta('title', season_page, 'title') entries = self._extract_entries(season_page, compilation_id) - else: # Compilation link + else: # Compilation link compilation_page = self._download_webpage(url, compilation_id, 'Downloading compilation web page') playlist_id = compilation_id playlist_title = self._html_search_meta('title', compilation_page, 'title') seasons = re.findall(r'[^<]+' % compilation_id, compilation_page) - if len(seasons) == 0: # No seasons in this compilation + if len(seasons) == 0: # No seasons in this compilation entries = self._extract_entries(compilation_page, compilation_id) else: entries = [] @@ -172,4 +172,4 @@ class IviCompilationIE(InfoExtractor): compilation_id, 'Downloading season %s web page' % season_id) entries.extend(self._extract_entries(season_page, compilation_id)) - return self.playlist_result(entries, playlist_id, playlist_title) \ No newline at end of file + return self.playlist_result(entries, playlist_id, playlist_title) diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py index a83dd249f..d16d483ee 100644 --- a/youtube_dl/extractor/izlesene.py +++ b/youtube_dl/extractor/izlesene.py @@ -5,11 +5,11 @@ import re from .common import InfoExtractor from ..utils import ( - get_element_by_id, - parse_iso8601, determine_ext, - int_or_none, float_or_none, + get_element_by_id, + int_or_none, + parse_iso8601, str_to_int, ) @@ -30,7 +30,7 @@ class IzleseneIE(InfoExtractor): 'description': 'md5:253753e2655dde93f59f74b572454f6d', 'thumbnail': 're:^http://.*\.jpg', 'uploader_id': 'pelikzzle', - 'timestamp': 1404298698, + 'timestamp': 1404302298, 'upload_date': '20140702', 'duration': 95.395, 'age_limit': 0, @@ -46,7 +46,7 @@ class IzleseneIE(InfoExtractor): 'description': 'Tarkan Dortmund 2006 Konseri', 'thumbnail': 're:^http://.*\.jpg', 'uploader_id': 'parlayankiz', - 'timestamp': 1163318593, + 'timestamp': 1163322193, 'upload_date': '20061112', 'duration': 253.666, 'age_limit': 0, @@ -55,15 +55,15 @@ class IzleseneIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - url = 'http://www.izlesene.com/video/%s' % video_id + video_id = self._match_id(url) + url = 'http://www.izlesene.com/video/%s' % video_id webpage = self._download_webpage(url, video_id) title = self._og_search_title(webpage) description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) + thumbnail = self._proto_relative_url( + self._og_search_thumbnail(webpage), scheme='http:') uploader = self._html_search_regex( r"adduserUsername\s*=\s*'([^']+)';", diff --git a/youtube_dl/extractor/jadorecettepub.py b/youtube_dl/extractor/jadorecettepub.py index ace08769b..063e86de4 100644 --- a/youtube_dl/extractor/jadorecettepub.py +++ b/youtube_dl/extractor/jadorecettepub.py @@ -45,4 +45,3 @@ class JadoreCettePubIE(InfoExtractor): 'title': title, 'description': description, } - diff --git a/youtube_dl/extractor/jeuxvideo.py b/youtube_dl/extractor/jeuxvideo.py index 188165966..8094cc2e4 100644 --- a/youtube_dl/extractor/jeuxvideo.py +++ b/youtube_dl/extractor/jeuxvideo.py @@ -29,7 +29,7 @@ class JeuxVideoIE(InfoExtractor): xml_link = self._html_search_regex( r'', webpage, 'config URL') - + video_id = self._search_regex( r'http://www\.jeuxvideo\.com/config/\w+/\d+/(.*?)/\d+_player\.xml', xml_link, 'video ID') @@ -38,7 +38,7 @@ class JeuxVideoIE(InfoExtractor): xml_link, title, 'Downloading XML config') info_json = config.find('format.json').text info = json.loads(info_json)['versions'][0] - + video_url = 'http://video720.jeuxvideo.com/' + info['file'] return { diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py index aad782578..122e2dd8c 100644 --- a/youtube_dl/extractor/jpopsukitv.py +++ b/youtube_dl/extractor/jpopsukitv.py @@ -1,8 +1,6 @@ # coding=utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( int_or_none, @@ -12,14 +10,14 @@ from ..utils import ( class JpopsukiIE(InfoExtractor): IE_NAME = 'jpopsuki.tv' - _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P\S+)' + _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/(?:category/)?video/[^/]+/(?P\S+)' _TEST = { 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', 'md5': '88018c0c1a9b1387940e90ec9e7e198e', - 'file': '00be659d23b0b40508169cdee4545771.mp4', 'info_dict': { 'id': '00be659d23b0b40508169cdee4545771', + 'ext': 'mp4', 'title': 'ayumi hamasaki - evolution', 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution', 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', @@ -30,8 +28,7 @@ class JpopsukiIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) @@ -47,11 +44,9 @@ class JpopsukiIE(InfoExtractor): uploader_id = self._html_search_regex( r'
  • from: http:[^"]+\?mdtk=[0-9]+)"', - iframe_html, 'video url') + iframe_html, 'video url') video_url = unescapeHTML(video_url).replace('\/', '/') except RegexNotFoundError: youtube_url = self._search_regex( @@ -49,9 +47,9 @@ class JukeboxIE(InfoExtractor): return self.url_result(youtube_url, ie='Youtube') title = self._html_search_regex(r'

    ([^<]+)

    ', - html, 'title') + html, 'title') artist = self._html_search_regex(r'([^<]+)', - html, 'artist') + html, 'artist') return { 'id': video_id, diff --git a/youtube_dl/extractor/justintv.py b/youtube_dl/extractor/justintv.py deleted file mode 100644 index 27017e89f..000000000 --- a/youtube_dl/extractor/justintv.py +++ /dev/null @@ -1,155 +0,0 @@ -from __future__ import unicode_literals - -import itertools -import json -import os -import re - -from .common import InfoExtractor -from ..utils import ( - compat_str, - ExtractorError, - formatSeconds, -) - - -class JustinTVIE(InfoExtractor): - """Information extractor for justin.tv and twitch.tv""" - # TODO: One broadcast may be split into multiple videos. The key - # 'broadcast_id' is the same for all parts, and 'broadcast_part' - # starts at 1 and increases. Can we treat all parts as one video? - - _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?(?:twitch|justin)\.tv/ - (?: - (?P[^/]+)| - (?:(?:[^/]+)/b/(?P[^/]+))| - (?:(?:[^/]+)/c/(?P[^/]+)) - ) - /?(?:\#.*)?$ - """ - _JUSTIN_PAGE_LIMIT = 100 - IE_NAME = 'justin.tv' - IE_DESC = 'justin.tv and twitch.tv' - _TEST = { - 'url': 'http://www.twitch.tv/thegamedevhub/b/296128360', - 'md5': 'ecaa8a790c22a40770901460af191c9a', - 'info_dict': { - 'id': '296128360', - 'ext': 'flv', - 'upload_date': '20110927', - 'uploader_id': 25114803, - 'uploader': 'thegamedevhub', - 'title': 'Beginner Series - Scripting With Python Pt.1' - } - } - - # Return count of items, list of *valid* items - def _parse_page(self, url, video_id, counter): - info_json = self._download_webpage( - url, video_id, - 'Downloading video info JSON on page %d' % counter, - 'Unable to download video info JSON %d' % counter) - - response = json.loads(info_json) - if type(response) != list: - error_text = response.get('error', 'unknown error') - raise ExtractorError('Justin.tv API: %s' % error_text) - info = [] - for clip in response: - video_url = clip['video_file_url'] - if video_url: - video_extension = os.path.splitext(video_url)[1][1:] - video_date = re.sub('-', '', clip['start_time'][:10]) - video_uploader_id = clip.get('user_id', clip.get('channel_id')) - video_id = clip['id'] - video_title = clip.get('title', video_id) - info.append({ - 'id': compat_str(video_id), - 'url': video_url, - 'title': video_title, - 'uploader': clip.get('channel_name', video_uploader_id), - 'uploader_id': video_uploader_id, - 'upload_date': video_date, - 'ext': video_extension, - }) - return (len(response), info) - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - api_base = 'http://api.justin.tv' - paged = False - if mobj.group('channelid'): - paged = True - video_id = mobj.group('channelid') - api = api_base + '/channel/archives/%s.json' % video_id - elif mobj.group('chapterid'): - chapter_id = mobj.group('chapterid') - - webpage = self._download_webpage(url, chapter_id) - m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage) - if not m: - raise ExtractorError('Cannot find archive of a chapter') - archive_id = m.group(1) - - api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id - doc = self._download_xml( - api, chapter_id, - note='Downloading chapter information', - errnote='Chapter information download failed') - for a in doc.findall('.//archive'): - if archive_id == a.find('./id').text: - break - else: - raise ExtractorError('Could not find chapter in chapter information') - - video_url = a.find('./video_file_url').text - video_ext = video_url.rpartition('.')[2] or 'flv' - - chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id - chapter_info = self._download_json( - chapter_api_url, 'c' + chapter_id, - note='Downloading chapter metadata', - errnote='Download of chapter metadata failed') - - bracket_start = int(doc.find('.//bracket_start').text) - bracket_end = int(doc.find('.//bracket_end').text) - - # TODO determine start (and probably fix up file) - # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457 - #video_url += '?start=' + TODO:start_timestamp - # bracket_start is 13290, but we want 51670615 - self._downloader.report_warning('Chapter detected, but we can just download the whole file. ' - 'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end))) - - info = { - 'id': 'c' + chapter_id, - 'url': video_url, - 'ext': video_ext, - 'title': chapter_info['title'], - 'thumbnail': chapter_info['preview'], - 'description': chapter_info['description'], - 'uploader': chapter_info['channel']['display_name'], - 'uploader_id': chapter_info['channel']['name'], - } - return info - else: - video_id = mobj.group('videoid') - api = api_base + '/broadcast/by_archive/%s.json' % video_id - - entries = [] - offset = 0 - limit = self._JUSTIN_PAGE_LIMIT - for counter in itertools.count(1): - page_url = api + ('?offset=%d&limit=%d' % (offset, limit)) - page_count, page_info = self._parse_page( - page_url, video_id, counter) - entries.extend(page_info) - if not paged or page_count != limit: - break - offset += limit - return { - '_type': 'playlist', - 'id': video_id, - 'entries': entries, - } diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py index 23103b163..dbfe4cc03 100644 --- a/youtube_dl/extractor/kankan.py +++ b/youtube_dl/extractor/kankan.py @@ -10,7 +10,7 @@ _md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest() class KankanIE(InfoExtractor): _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P\d+)\.shtml' - + _TEST = { 'url': 'http://yinyue.kankan.com/vod/48/48863.shtml', 'file': '48863.flv', diff --git a/youtube_dl/extractor/kickstarter.py b/youtube_dl/extractor/kickstarter.py index 56a76380c..7d4b57056 100644 --- a/youtube_dl/extractor/kickstarter.py +++ b/youtube_dl/extractor/kickstarter.py @@ -1,8 +1,6 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -15,28 +13,25 @@ class KickStarterIE(InfoExtractor): 'id': '1404461844', 'ext': 'mp4', 'title': 'Intersection: The Story of Josh Grant by Kyle Cowling', - 'description': 'A unique motocross documentary that examines the ' - 'life and mind of one of sports most elite athletes: Josh Grant.', + 'description': ( + 'A unique motocross documentary that examines the ' + 'life and mind of one of sports most elite athletes: Josh Grant.' + ), }, }, { 'note': 'Embedded video (not using the native kickstarter video service)', 'url': 'https://www.kickstarter.com/projects/597507018/pebble-e-paper-watch-for-iphone-and-android/posts/659178', - 'playlist': [ - { - 'info_dict': { - 'id': '78704821', - 'ext': 'mp4', - 'uploader_id': 'pebble', - 'uploader': 'Pebble Technology', - 'title': 'Pebble iOS Notifications', - } - } - ], + 'info_dict': { + 'id': '78704821', + 'ext': 'mp4', + 'uploader_id': 'pebble', + 'uploader': 'Pebble Technology', + 'title': 'Pebble iOS Notifications', + } }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._html_search_regex( diff --git a/youtube_dl/extractor/kontrtube.py b/youtube_dl/extractor/kontrtube.py index 5341ac773..41fd62009 100644 --- a/youtube_dl/extractor/kontrtube.py +++ b/youtube_dl/extractor/kontrtube.py @@ -34,7 +34,7 @@ class KontrTubeIE(InfoExtractor): video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL') thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False) title = self._html_search_regex( - r'(.+?) - Труба зовёт - Интересный видеохостинг', webpage, 'video title') + r'(.+?)', webpage, 'video title') description = self._html_search_meta('description', webpage, 'video description') mobj = re.search( @@ -63,4 +63,4 @@ class KontrTubeIE(InfoExtractor): 'duration': duration, 'view_count': int_or_none(view_count), 'comment_count': int_or_none(comment_count), - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/ku6.py b/youtube_dl/extractor/ku6.py index 484239b19..a602980a1 100644 --- a/youtube_dl/extractor/ku6.py +++ b/youtube_dl/extractor/ku6.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -18,11 +16,11 @@ class Ku6IE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._search_regex(r'

    (.*?)

    ', webpage, 'title') + + title = self._html_search_regex( + r'

    (.*?)

    ', webpage, 'title') dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id jsonData = self._download_json(dataUrl, video_id) downloadUrl = jsonData['data']['f'] @@ -32,4 +30,3 @@ class Ku6IE(InfoExtractor): 'title': title, 'url': downloadUrl } - diff --git a/youtube_dl/extractor/laola1tv.py b/youtube_dl/extractor/laola1tv.py new file mode 100644 index 000000000..2fd3b4699 --- /dev/null +++ b/youtube_dl/extractor/laola1tv.py @@ -0,0 +1,77 @@ +from __future__ import unicode_literals + +import random +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class Laola1TvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?laola1\.tv/(?P[a-z]+)-(?P[a-z]+)/.*?/(?P[0-9]+)\.html' + _TEST = { + 'url': 'http://www.laola1.tv/de-de/live/bwf-bitburger-open-grand-prix-gold-court-1/250019.html', + 'info_dict': { + 'id': '250019', + 'ext': 'mp4', + 'title': 'Bitburger Open Grand Prix Gold - Court 1', + 'categories': ['Badminton'], + 'uploader': 'BWF - Badminton World Federation', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + } + } + + _BROKEN = True # Not really - extractor works fine, but f4m downloader does not support live streams yet. + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + lang = mobj.group('lang') + portal = mobj.group('portal') + + webpage = self._download_webpage(url, video_id) + iframe_url = self._search_regex( + r']*?class="main_tv_player"[^>]*?src="([^"]+)"', + webpage, 'iframe URL') + + iframe = self._download_webpage( + iframe_url, video_id, note='Downloading iframe') + flashvars_m = re.findall( + r'flashvars\.([_a-zA-Z0-9]+)\s*=\s*"([^"]*)";', iframe) + flashvars = dict((m[0], m[1]) for m in flashvars_m) + + xml_url = ('http://www.laola1.tv/server/hd_video.php?' + + 'play=%s&partner=1&portal=%s&v5ident=&lang=%s' % ( + video_id, portal, lang)) + hd_doc = self._download_xml(xml_url, video_id) + + title = hd_doc.find('.//video/title').text + flash_url = hd_doc.find('.//video/url').text + categories = hd_doc.find('.//video/meta_sports').text.split(',') + uploader = hd_doc.find('.//video/meta_organistation').text + + ident = random.randint(10000000, 99999999) + token_url = '%s&ident=%s&klub=0&unikey=0×tamp=%s&auth=%s' % ( + flash_url, ident, flashvars['timestamp'], flashvars['auth']) + + token_doc = self._download_xml( + token_url, video_id, note='Downloading token') + token_attrib = token_doc.find('.//token').attrib + if token_attrib.get('auth') == 'blocked': + raise ExtractorError('Token error: ' % token_attrib.get('comment')) + + video_url = '%s?hdnea=%s&hdcore=3.2.0' % ( + token_attrib['url'], token_attrib['auth']) + + return { + 'id': video_id, + 'is_live': True, + 'title': title, + 'url': video_url, + 'uploader': uploader, + 'categories': categories, + 'ext': 'mp4', + } diff --git a/youtube_dl/extractor/lifenews.py b/youtube_dl/extractor/lifenews.py index 8d9491f23..1dfe7f77f 100644 --- a/youtube_dl/extractor/lifenews.py +++ b/youtube_dl/extractor/lifenews.py @@ -52,7 +52,7 @@ class LifeNewsIE(InfoExtractor): r'
    \s*(\d+)', webpage, 'comment count', fatal=False) upload_date = self._html_search_regex( - r'
    n?\d+)' + _VALID_URL = r'https?://m(?:lb)?\.mlb\.com/(?:(?:.*?/)?video/(?:topic/[\da-z_-]+/)?v|(?:shared/video/embed/embed\.html|[^/]+/video/play\.jsp)\?.*?\bcontent_id=)(?Pn?\d+)' _TESTS = [ { 'url': 'http://m.mlb.com/sea/video/topic/51231442/v34698933/nymsea-ackley-robs-a-home-run-with-an-amazing-catch/?c_id=sea', @@ -73,6 +72,14 @@ class MLBIE(InfoExtractor): 'url': 'http://m.mlb.com/shared/video/embed/embed.html?content_id=35692085&topic_id=6479266&width=400&height=224&property=mlb', 'only_matching': True, }, + { + 'url': 'http://mlb.mlb.com/shared/video/embed/embed.html?content_id=36599553', + 'only_matching': True, + }, + { + 'url': 'http://mlb.mlb.com/es/video/play.jsp?content_id=36599553', + 'only_matching': True, + }, ] def _real_extract(self, url): @@ -88,8 +95,9 @@ class MLBIE(InfoExtractor): duration = parse_duration(detail.find('./duration').text) timestamp = parse_iso8601(detail.attrib['date'][:-5]) - thumbnail = find_xpath_attr( - detail, './thumbnailScenarios/thumbnailScenario', 'type', '45').text + thumbnails = [{ + 'url': thumbnail.text, + } for thumbnail in detail.findall('./thumbnailScenarios/thumbnailScenario')] formats = [] for media_url in detail.findall('./url'): @@ -116,5 +124,5 @@ class MLBIE(InfoExtractor): 'duration': duration, 'timestamp': timestamp, 'formats': formats, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, } diff --git a/youtube_dl/extractor/mojvideo.py b/youtube_dl/extractor/mojvideo.py index 90b460d65..0ba435dc5 100644 --- a/youtube_dl/extractor/mojvideo.py +++ b/youtube_dl/extractor/mojvideo.py @@ -55,4 +55,4 @@ class MojvideoIE(InfoExtractor): 'title': title, 'thumbnail': thumbnail, 'duration': duration, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/moniker.py b/youtube_dl/extractor/moniker.py new file mode 100644 index 000000000..1c4f589cc --- /dev/null +++ b/youtube_dl/extractor/moniker.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import os.path +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + compat_urllib_request, +) + + +class MonikerIE(InfoExtractor): + IE_DESC = 'allmyvideos.net and vidspot.net' + _VALID_URL = r'https?://(?:www\.)?(?:allmyvideos|vidspot)\.net/(?P[a-zA-Z0-9_-]+)' + + _TESTS = [{ + 'url': 'http://allmyvideos.net/jih3nce3x6wn', + 'md5': '710883dee1bfc370ecf9fa6a89307c88', + 'info_dict': { + 'id': 'jih3nce3x6wn', + 'ext': 'mp4', + 'title': 'youtube-dl test video', + }, + }, { + 'url': 'http://vidspot.net/l2ngsmhs8ci5', + 'md5': '710883dee1bfc370ecf9fa6a89307c88', + 'info_dict': { + 'id': 'l2ngsmhs8ci5', + 'ext': 'mp4', + 'title': 'youtube-dl test video', + }, + }, { + 'url': 'https://www.vidspot.net/l2ngsmhs8ci5', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + orig_webpage = self._download_webpage(url, video_id) + fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage) + data = dict(fields) + + post = compat_urllib_parse.urlencode(data) + headers = { + b'Content-Type': b'application/x-www-form-urlencoded', + } + req = compat_urllib_request.Request(url, post, headers) + webpage = self._download_webpage( + req, video_id, note='Downloading video page ...') + + title = os.path.splitext(data['fname'])[0] + + # Could be several links with different quality + links = re.findall(r'"file" : "?(.+?)",', webpage) + # Assume the links are ordered in quality + formats = [{ + 'url': l, + 'quality': i, + } for i, l in enumerate(links)] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + } diff --git a/youtube_dl/extractor/mooshare.py b/youtube_dl/extractor/mooshare.py index 7d21ea18f..34a4bec3a 100644 --- a/youtube_dl/extractor/mooshare.py +++ b/youtube_dl/extractor/mooshare.py @@ -49,7 +49,7 @@ class MooshareIE(InfoExtractor): page = self._download_webpage(url, video_id, 'Downloading page') if re.search(r'>Video Not Found or Deleted<', page) is not None: - raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) + raise ExtractorError('Video %s does not exist' % video_id, expected=True) hash_key = self._html_search_regex(r'', page, 'hash') title = self._html_search_regex(r'(?m)
    \s*

    Watch ([^<]+)

    ', page, 'title') @@ -111,4 +111,4 @@ class MooshareIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 6229b2173..97d5da626 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -5,20 +5,20 @@ import re from .common import InfoExtractor from ..utils import ( - int_or_none, + str_to_int, unified_strdate, ) class MotherlessIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?motherless\.com/(?P[A-Z0-9]+)' + _VALID_URL = r'http://(?:www\.)?motherless\.com/(?:g/[a-z0-9_]+/)?(?P[A-Z0-9]+)' _TESTS = [ { 'url': 'http://motherless.com/AC3FFE1', - 'md5': '5527fef81d2e529215dad3c2d744a7d9', + 'md5': '310f62e325a9fafe64f68c0bccb6e75f', 'info_dict': { 'id': 'AC3FFE1', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Fucked in the ass while playing PS3', 'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'], 'upload_date': '20100913', @@ -40,33 +40,51 @@ class MotherlessIE(InfoExtractor): 'thumbnail': 're:http://.*\.jpg', 'age_limit': 18, } + }, + { + 'url': 'http://motherless.com/g/cosplay/633979F', + 'md5': '0b2a43f447a49c3e649c93ad1fafa4a0', + 'info_dict': { + 'id': '633979F', + 'ext': 'mp4', + 'title': 'Turtlette', + 'categories': ['superheroine heroine superher'], + 'upload_date': '20140827', + 'uploader_id': 'shade0230', + 'thumbnail': 're:http://.*\.jpg', + 'age_limit': 18, + } } ] - def _real_extract(self,url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + def _real_extract(self, url): + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') - - video_url = self._html_search_regex(r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video_url') + title = self._html_search_regex( + r'id="view-upload-title">\s+([^<]+)<', webpage, 'title') + video_url = self._html_search_regex( + r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL') age_limit = self._rta_search(webpage) + view_count = str_to_int(self._html_search_regex( + r'Views\s+([^<]+)<', + webpage, 'view count', fatal=False)) + like_count = str_to_int(self._html_search_regex( + r'Favorited\s+([^<]+)<', + webpage, 'like count', fatal=False)) - view_count = self._html_search_regex(r'Views\s+([^<]+)<', webpage, 'view_count') - - upload_date = self._html_search_regex(r'Uploaded\s+([^<]+)<', webpage, 'upload_date') + upload_date = self._html_search_regex( + r'Uploaded\s+([^<]+)<', webpage, 'upload date') if 'Ago' in upload_date: days = int(re.search(r'([0-9]+)', upload_date).group(1)) upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d') else: upload_date = unified_strdate(upload_date) - like_count = self._html_search_regex(r'Favorited\s+([^<]+)<', webpage, 'like_count') - comment_count = webpage.count('class="media-comment-contents"') - uploader_id = self._html_search_regex(r'"thumb-member-username">\s+    \s+gsp\..+?/.*)$', rtmp_video_url) if not m: return rtmp_video_url - base = 'http://mtvnmobile.vo.llnwd.net/kip0/_pxn=1+_pxI0=Ripod-h264+_pxL0=undefined+_pxM0=+_pxK=18639+_pxE=mp4/44620/mtvnorigin/' + base = 'http://viacommtvstrmfs.fplive.net/' return base + m.group('finalid') def _get_feed_url(self, uri): @@ -53,23 +53,23 @@ class MTVServicesInfoExtractor(InfoExtractor): # Otherwise we get a webpage that would execute some javascript req.add_header('Youtubedl-user-agent', 'curl/7') webpage = self._download_webpage(req, mtvn_id, - 'Downloading mobile page') + 'Downloading mobile page') metrics_url = unescapeHTML(self._search_regex(r'\d+)' - IE_NAME = u'muzu.tv' + IE_NAME = 'muzu.tv' _TEST = { - u'url': u'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/', - u'file': u'1981454.mp4', - u'md5': u'98f8b2c7bc50578d6a0364fff2bfb000', - u'info_dict': { - u'title': u'Cat Walk (Original Mix)', - u'description': u'md5:90e868994de201b2570e4e5854e19420', - u'uploader': u'MarcAshken featuring SOS', + 'url': 'http://www.muzu.tv/defected/marcashken-featuring-sos-cat-walk-original-mix-music-video/1981454/', + 'md5': '98f8b2c7bc50578d6a0364fff2bfb000', + 'info_dict': { + 'id': '1981454', + 'ext': 'mp4', + 'title': 'Cat Walk (Original Mix)', + 'description': 'md5:90e868994de201b2570e4e5854e19420', + 'uploader': 'MarcAshken featuring SOS', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - info_data = compat_urllib_parse.urlencode({'format': 'json', - 'url': url, - }) - video_info_page = self._download_webpage('http://www.muzu.tv/api/oembed/?%s' % info_data, - video_id, u'Downloading video info') - info = json.loads(video_info_page) + info_data = compat_urllib_parse.urlencode({ + 'format': 'json', + 'url': url, + }) + info = self._download_json( + 'http://www.muzu.tv/api/oembed/?%s' % info_data, + video_id, 'Downloading video info') - player_info_page = self._download_webpage('http://player.muzu.tv/player/playerInit?ai=%s' % video_id, - video_id, u'Downloading player info') - video_info = json.loads(player_info_page)['videos'][0] - for quality in ['1080' , '720', '480', '360']: + player_info = self._download_json( + 'http://player.muzu.tv/player/playerInit?ai=%s' % video_id, + video_id, 'Downloading player info') + video_info = player_info['videos'][0] + for quality in ['1080', '720', '480', '360']: if video_info.get('v%s' % quality): break - data = compat_urllib_parse.urlencode({'ai': video_id, - # Even if each time you watch a video the hash changes, - # it seems to work for different videos, and it will work - # even if you use any non empty string as a hash - 'viewhash': 'VBNff6djeV4HV5TRPW5kOHub2k', - 'device': 'web', - 'qv': quality, - }) - video_url_page = self._download_webpage('http://player.muzu.tv/player/requestVideo?%s' % data, - video_id, u'Downloading video url') - video_url_info = json.loads(video_url_page) + data = compat_urllib_parse.urlencode({ + 'ai': video_id, + # Even if each time you watch a video the hash changes, + # it seems to work for different videos, and it will work + # even if you use any non empty string as a hash + 'viewhash': 'VBNff6djeV4HV5TRPW5kOHub2k', + 'device': 'web', + 'qv': quality, + }) + video_url_info = self._download_json( + 'http://player.muzu.tv/player/requestVideo?%s' % data, + video_id, 'Downloading video url') video_url = video_url_info['url'] - return {'id': video_id, - 'title': info['title'], - 'url': video_url, - 'ext': determine_ext(video_url), - 'thumbnail': info['thumbnail_url'], - 'description': info['description'], - 'uploader': info['author_name'], - } + return { + 'id': video_id, + 'title': info['title'], + 'url': video_url, + 'thumbnail': info['thumbnail_url'], + 'description': info['description'], + 'uploader': info['author_name'], + } diff --git a/youtube_dl/extractor/myspace.py b/youtube_dl/extractor/myspace.py index c16939f54..c3c1a27c3 100644 --- a/youtube_dl/extractor/myspace.py +++ b/youtube_dl/extractor/myspace.py @@ -4,7 +4,7 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_str, ) @@ -52,8 +52,8 @@ class MySpaceIE(InfoExtractor): if mobj.group('mediatype').startswith('music/song'): # songs don't store any useful info in the 'context' variable def search_data(name): - return self._search_regex(r'data-%s="(.*?)"' % name, webpage, - name) + return self._search_regex( + r'data-%s="(.*?)"' % name, webpage, name) streamUrl = search_data('stream-url') info = { 'id': video_id, @@ -62,8 +62,8 @@ class MySpaceIE(InfoExtractor): 'thumbnail': self._og_search_thumbnail(webpage), } else: - context = json.loads(self._search_regex(r'context = ({.*?});', webpage, - u'context')) + context = json.loads(self._search_regex( + r'context = ({.*?});', webpage, 'context')) video = context['video'] streamUrl = video['streamUrl'] info = { diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py index 4fa0575f8..51e540814 100644 --- a/youtube_dl/extractor/myspass.py +++ b/youtube_dl/extractor/myspass.py @@ -13,9 +13,10 @@ class MySpassIE(InfoExtractor): _VALID_URL = r'http://www\.myspass\.de/.*' _TEST = { 'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/', - 'file': '11741.mp4', 'md5': '0b49f4844a068f8b33f4b7c88405862b', 'info_dict': { + 'id': '11741', + 'ext': 'mp4', "description": "Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?", "title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2", }, diff --git a/youtube_dl/extractor/myvideo.py b/youtube_dl/extractor/myvideo.py index ccb5959c4..5e754fcff 100644 --- a/youtube_dl/extractor/myvideo.py +++ b/youtube_dl/extractor/myvideo.py @@ -7,11 +7,12 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_ord, compat_urllib_parse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, ) @@ -32,7 +33,7 @@ class MyVideoIE(InfoExtractor): # Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git # Released into the Public Domain by Tristan Fischer on 2013-05-19 # https://github.com/rg3/youtube-dl/pull/842 - def __rc4crypt(self,data, key): + def __rc4crypt(self, data, key): x = 0 box = list(range(256)) for i in list(range(256)): @@ -48,17 +49,17 @@ class MyVideoIE(InfoExtractor): out += chr(compat_ord(char) ^ box[(box[x] + box[y]) % 256]) return out - def __md5(self,s): + def __md5(self, s): return hashlib.md5(s).hexdigest().encode() - def _real_extract(self,url): + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') GK = ( - b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt' - b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3' - b'TnpsbA0KTVRkbU1tSTRNdz09' + b'WXpnME1EZGhNRGhpTTJNM01XVmhOREU0WldNNVpHTTJOakpt' + b'TW1FMU5tVTBNR05pWkRaa05XRXhNVFJoWVRVd1ptSXhaVEV3' + b'TnpsbA0KTVRkbU1tSTRNdz09' ) # Get video webpage @@ -71,7 +72,7 @@ class MyVideoIE(InfoExtractor): video_url = mobj.group(1) + '.flv' video_title = self._html_search_regex('([^<]+)', - webpage, 'title') + webpage, 'title') return { 'id': video_id, @@ -161,7 +162,7 @@ class MyVideoIE(InfoExtractor): video_swfobj = compat_urllib_parse.unquote(video_swfobj) video_title = self._html_search_regex("(.*?)", - webpage, 'title') + webpage, 'title') return { 'id': video_id, @@ -172,4 +173,3 @@ class MyVideoIE(InfoExtractor): 'play_path': video_playpath, 'player_url': video_swfobj, } - diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index c0231c197..fbe34defd 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, ExtractorError, + clean_html, ) @@ -29,12 +30,17 @@ class NaverIE(InfoExtractor): video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"', - webpage) + webpage) if m_id is None: + m_error = re.search( + r'(?s)
    \s*(?:)?\s*

    (?P.+?)

    \s*
    ', + webpage) + if m_error: + raise ExtractorError(clean_html(m_error.group('msg')), expected=True) raise ExtractorError('couldn\'t extract vid and key') vid = m_id.group(1) key = m_id.group(2) - query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key,}) + query = compat_urllib_parse.urlencode({'vid': vid, 'inKey': key, }) query_urls = compat_urllib_parse.urlencode({ 'masterVid': vid, 'protocol': 'p2p', @@ -59,7 +65,7 @@ class NaverIE(InfoExtractor): if domain.startswith('rtmp'): f.update({ 'ext': 'flv', - 'rtmp_protocol': '1', # rtmpt + 'rtmp_protocol': '1', # rtmpt }) formats.append(f) self._sort_formats(formats) diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 78e650b2d..f69fe0925 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -39,7 +39,6 @@ class NBAIE(InfoExtractor): duration = parse_duration( self._html_search_meta('duration', webpage, 'duration', fatal=False)) - return { 'id': shortened_video_id, 'url': video_url, diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index d2e4acbad..7b5449031 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -16,9 +16,9 @@ class NBCIE(InfoExtractor): _TEST = { 'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188', - 'md5': '54d0fbc33e0b853a65d7b4de5c06d64e', + # md5 checksum is not stable 'info_dict': { - 'id': 'u1RInQZRN7QJ', + 'id': 'bTmnLCvIbaaH', 'ext': 'flv', 'title': 'I Am a Firefighter', 'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.', @@ -26,8 +26,7 @@ class NBCIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url') if theplatform_url.startswith('//'): @@ -57,7 +56,7 @@ class NBCNewsIE(InfoExtractor): 'md5': 'b2421750c9f260783721d898f4c42063', 'info_dict': { 'id': 'I1wpAI_zmhsQ', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'How Twitter Reacted To The Snowden Interview', 'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64', }, @@ -97,6 +96,8 @@ class NBCNewsIE(InfoExtractor): ] for base_url in base_urls: + if not base_url: + continue playlist_url = base_url + '?form=MPXNBCNewsAPI' all_videos = self._download_json(playlist_url, title)['videos'] diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 94d5ba982..f49c66690 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -18,16 +18,16 @@ class NDRIE(InfoExtractor): _TESTS = [ { - 'url': 'http://www.ndr.de/fernsehen/media/dienordreportage325.html', - 'md5': '4a4eeafd17c3058b65f0c8f091355855', + 'url': 'http://www.ndr.de/fernsehen/sendungen/nordmagazin/Kartoffeltage-in-der-Lewitz,nordmagazin25866.html', + 'md5': '5bc5f5b92c82c0f8b26cddca34f8bb2c', 'note': 'Video file', 'info_dict': { - 'id': '325', + 'id': '25866', 'ext': 'mp4', - 'title': 'Blaue Bohnen aus Blocken', - 'description': 'md5:190d71ba2ccddc805ed01547718963bc', - 'duration': 1715, - }, + 'title': 'Kartoffeltage in der Lewitz', + 'description': 'md5:48c4c04dde604c8a9971b3d4e3b9eaa8', + 'duration': 166, + } }, { 'url': 'http://www.ndr.de/info/audio51535.html', @@ -67,7 +67,7 @@ class NDRIE(InfoExtractor): thumbnail = None - video_url = re.search(r'''3: \{src:'(?P    ([^<]+)', - page, 'director name', fatal=False) + page, 'director name', fatal=False) request = compat_urllib_request.Request('https://www.nfb.ca/film/%s/player_config' % video_id, - compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii')) + compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii')) request.add_header('Content-Type', 'application/x-www-form-urlencoded') request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf') @@ -93,4 +93,4 @@ class NFBIE(InfoExtractor): 'uploader': uploader, 'uploader_id': uploader_id, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/nfl.py b/youtube_dl/extractor/nfl.py new file mode 100644 index 000000000..cc7c921c3 --- /dev/null +++ b/youtube_dl/extractor/nfl.py @@ -0,0 +1,144 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse_urlparse, + int_or_none, + remove_end, +) + + +class NFLIE(InfoExtractor): + IE_NAME = 'nfl.com' + _VALID_URL = r'''(?x)https?:// + (?P(?:www\.)?(?:nfl\.com|.*?\.clubs\.nfl\.com))/ + (?:.+?/)* + (?P(?:\d[a-z]{2}\d{13}|\w{8}\-(?:\w{4}\-){3}\w{12}))''' + _TESTS = [ + { + 'url': 'http://www.nfl.com/videos/nfl-game-highlights/0ap3000000398478/Week-3-Redskins-vs-Eagles-highlights', + 'md5': '394ef771ddcd1354f665b471d78ec4c6', + 'info_dict': { + 'id': '0ap3000000398478', + 'ext': 'mp4', + 'title': 'Week 3: Redskins vs. Eagles highlights', + 'description': 'md5:56323bfb0ac4ee5ab24bd05fdf3bf478', + 'upload_date': '20140921', + 'timestamp': 1411337580, + 'thumbnail': 're:^https?://.*\.jpg$', + } + }, + { + 'url': 'http://prod.www.steelers.clubs.nfl.com/video-and-audio/videos/LIVE_Post_Game_vs_Browns/9d72f26a-9e2b-4718-84d3-09fb4046c266', + 'md5': 'cf85bdb4bc49f6e9d3816d130c78279c', + 'info_dict': { + 'id': '9d72f26a-9e2b-4718-84d3-09fb4046c266', + 'ext': 'mp4', + 'title': 'LIVE: Post Game vs. Browns', + 'description': 'md5:6a97f7e5ebeb4c0e69a418a89e0636e8', + 'upload_date': '20131229', + 'timestamp': 1388354455, + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + ] + + @staticmethod + def prepend_host(host, url): + if not url.startswith('http'): + if not url.startswith('/'): + url = '/%s' % url + url = 'http://{0:}{1:}'.format(host, url) + return url + + @staticmethod + def format_from_stream(stream, protocol, host, path_prefix='', + preference=0, note=None): + url = '{protocol:}://{host:}/{prefix:}{path:}'.format( + protocol=protocol, + host=host, + prefix=path_prefix, + path=stream.get('path'), + ) + return { + 'url': url, + 'vbr': int_or_none(stream.get('rate', 0), 1000), + 'preference': preference, + 'format_note': note, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id, host = mobj.group('id'), mobj.group('host') + + webpage = self._download_webpage(url, video_id) + + config_url = NFLIE.prepend_host(host, self._search_regex( + r'(?:config|configURL)\s*:\s*"([^"]+)"', webpage, 'config URL')) + config = self._download_json(config_url, video_id, + note='Downloading player config') + url_template = NFLIE.prepend_host( + host, '{contentURLTemplate:}'.format(**config)) + video_data = self._download_json( + url_template.format(id=video_id), video_id) + + formats = [] + cdn_data = video_data.get('cdnData', {}) + streams = cdn_data.get('bitrateInfo', []) + if cdn_data.get('format') == 'EXTERNAL_HTTP_STREAM': + parts = compat_urllib_parse_urlparse(cdn_data.get('uri')) + protocol, host = parts.scheme, parts.netloc + for stream in streams: + formats.append( + NFLIE.format_from_stream(stream, protocol, host)) + else: + cdns = config.get('cdns') + if not cdns: + raise ExtractorError('Failed to get CDN data', expected=True) + + for name, cdn in cdns.items(): + # LimeLight streams don't seem to work + if cdn.get('name') == 'LIMELIGHT': + continue + + protocol = cdn.get('protocol') + host = remove_end(cdn.get('host', ''), '/') + if not (protocol and host): + continue + + prefix = cdn.get('pathprefix', '') + if prefix and not prefix.endswith('/'): + prefix = '%s/' % prefix + + preference = 0 + if protocol == 'rtmp': + preference = -2 + elif 'prog' in name.lower(): + preference = 1 + + for stream in streams: + formats.append( + NFLIE.format_from_stream(stream, protocol, host, + prefix, preference, name)) + + self._sort_formats(formats) + + thumbnail = None + for q in ('xl', 'l', 'm', 's', 'xs'): + thumbnail = video_data.get('imagePaths', {}).get(q) + if thumbnail: + break + + return { + 'id': video_id, + 'title': video_data.get('headline'), + 'formats': formats, + 'description': video_data.get('caption'), + 'duration': video_data.get('duration'), + 'thumbnail': thumbnail, + 'timestamp': int_or_none(video_data.get('posted'), 1000), + } diff --git a/youtube_dl/extractor/nhl.py b/youtube_dl/extractor/nhl.py index 072d9cf8e..bdcf7e239 100644 --- a/youtube_dl/extractor/nhl.py +++ b/youtube_dl/extractor/nhl.py @@ -4,10 +4,11 @@ import re import json from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urlparse, compat_urllib_parse, - determine_ext, +) +from ..utils import ( unified_strdate, ) @@ -22,21 +23,23 @@ class NHLBaseInfoExtractor(InfoExtractor): self.report_extraction(video_id) initial_video_url = info['publishPoint'] - data = compat_urllib_parse.urlencode({ - 'type': 'fvod', - 'path': initial_video_url.replace('.mp4', '_sd.mp4'), - }) - path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data - path_doc = self._download_xml( - path_url, video_id, 'Downloading final video url') - video_url = path_doc.find('path').text + if info['formats'] == '1': + data = compat_urllib_parse.urlencode({ + 'type': 'fvod', + 'path': initial_video_url.replace('.mp4', '_sd.mp4'), + }) + path_url = 'http://video.nhl.com/videocenter/servlets/encryptvideopath?' + data + path_doc = self._download_xml( + path_url, video_id, 'Downloading final video url') + video_url = path_doc.find('path').text + else: + video_url = initial_video_url join = compat_urlparse.urljoin return { 'id': video_id, 'title': info['name'], 'url': video_url, - 'ext': determine_ext(video_url), 'description': info['description'], 'duration': int(info['duration']), 'thumbnail': join(join(video_url, '/u/'), info['bigImage']), @@ -46,10 +49,11 @@ class NHLBaseInfoExtractor(InfoExtractor): class NHLIE(NHLBaseInfoExtractor): IE_NAME = 'nhl.com' - _VALID_URL = r'https?://video(?P\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P[0-9]+)' + _VALID_URL = r'https?://video(?P\.[^.]*)?\.nhl\.com/videocenter/console(?:\?(?:.*?[?&])?)id=(?P[0-9a-z-]+)' _TESTS = [{ 'url': 'http://video.canucks.nhl.com/videocenter/console?catid=6?id=453614', + 'md5': 'db704a4ea09e8d3988c85e36cc892d09', 'info_dict': { 'id': '453614', 'ext': 'mp4', @@ -58,6 +62,17 @@ class NHLIE(NHLBaseInfoExtractor): 'duration': 18, 'upload_date': '20131006', }, + }, { + 'url': 'http://video.nhl.com/videocenter/console?id=2014020024-628-h', + 'md5': 'd22e82bc592f52d37d24b03531ee9696', + 'info_dict': { + 'id': '2014020024-628-h', + 'ext': 'mp4', + 'title': 'Alex Galchenyuk Goal on Ray Emery (14:40/3rd)', + 'description': 'Home broadcast - Montreal Canadiens at Philadelphia Flyers - October 11, 2014', + 'duration': 0, + 'upload_date': '20141011', + }, }, { 'url': 'http://video.flames.nhl.com/videocenter/console?id=630616', 'only_matching': True, @@ -109,10 +124,10 @@ class NHLVideocenterIE(NHLBaseInfoExtractor): response = self._download_webpage(request_url, playlist_title) response = self._fix_json(response) if not response.strip(): - self._downloader.report_warning(u'Got an empty reponse, trying ' + self._downloader.report_warning('Got an empty reponse, trying ' 'adding the "newvideos" parameter') response = self._download_webpage(request_url + '&newvideos=true', - playlist_title) + playlist_title) response = self._fix_json(response) videos = json.loads(response) diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py index c0c139b5d..1d9c1a096 100644 --- a/youtube_dl/extractor/niconico.py +++ b/youtube_dl/extractor/niconico.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals import re +import json from .common import InfoExtractor from ..utils import ( @@ -11,6 +12,7 @@ from ..utils import ( unified_strdate, parse_duration, int_or_none, + ExtractorError, ) @@ -39,18 +41,17 @@ class NiconicoIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.|secure\.)?nicovideo\.jp/watch/((?:[a-z]{2})?[0-9]+)' _NETRC_MACHINE = 'niconico' - # Determine whether the downloader uses authentication to download video - _AUTHENTICATE = False + # Determine whether the downloader used authentication to download video + _AUTHENTICATED = False def _real_initialize(self): - if self._downloader.params.get('username', None) is not None: - self._AUTHENTICATE = True - - if self._AUTHENTICATE: - self._login() + self._login() def _login(self): (username, password) = self._get_login_info() + # No authentication to be performed + if not username: + return True # Log in login_form_strs = { @@ -68,6 +69,8 @@ class NiconicoIE(InfoExtractor): if re.search(r'(?i)

    Log in error

    ', login_results) is not None: self._downloader.report_warning('unable to log in: bad username or password') return False + # Successful login + self._AUTHENTICATED = True return True def _real_extract(self, url): @@ -82,7 +85,7 @@ class NiconicoIE(InfoExtractor): 'http://ext.nicovideo.jp/api/getthumbinfo/' + video_id, video_id, note='Downloading video info page') - if self._AUTHENTICATE: + if self._AUTHENTICATED: # Get flv info flv_info_webpage = self._download_webpage( 'http://flapi.nicovideo.jp/api/getflv?v=' + video_id, @@ -106,6 +109,9 @@ class NiconicoIE(InfoExtractor): flv_info_request, video_id, note='Downloading flv info', errnote='Unable to download flv info') + if 'deleted=' in flv_info_webpage: + raise ExtractorError('The video has been deleted.', + expected=True) video_real_url = compat_urlparse.parse_qs(flv_info_webpage)['url'][0] # Start extracting information @@ -145,3 +151,37 @@ class NiconicoIE(InfoExtractor): 'duration': duration, 'webpage_url': webpage_url, } + + +class NiconicoPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P\d+)' + + _TEST = { + 'url': 'http://www.nicovideo.jp/mylist/27411728', + 'info_dict': { + 'id': '27411728', + 'title': 'AKB48のオールナイトニッポン', + }, + 'playlist_mincount': 225, + } + + def _real_extract(self, url): + list_id = self._match_id(url) + webpage = self._download_webpage(url, list_id) + + entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);', + webpage, 'entries') + entries = json.loads(entries_json) + entries = [{ + '_type': 'url', + 'ie_key': NiconicoIE.ie_key(), + 'url': ('http://www.nicovideo.jp/watch/%s' % + entry['item_data']['video_id']), + } for entry in entries] + + return { + '_type': 'playlist', + 'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'), + 'id': list_id, + 'entries': entries, + } diff --git a/youtube_dl/extractor/ninegag.py b/youtube_dl/extractor/ninegag.py index 33daa0dec..16a02ad79 100644 --- a/youtube_dl/extractor/ninegag.py +++ b/youtube_dl/extractor/ninegag.py @@ -27,8 +27,7 @@ class NineGagIE(InfoExtractor): "thumbnail": "re:^https?://", }, 'add_ie': ['Youtube'] - }, - { + }, { 'url': 'http://9gag.tv/p/KklwM/alternate-banned-opening-scene-of-gravity?ref=fsidebar', 'info_dict': { 'id': 'KklwM', diff --git a/youtube_dl/extractor/noco.py b/youtube_dl/extractor/noco.py index 959fdf590..7d2ff7b9a 100644 --- a/youtube_dl/extractor/noco.py +++ b/youtube_dl/extractor/noco.py @@ -2,6 +2,8 @@ from __future__ import unicode_literals import re +import time +import hashlib from .common import InfoExtractor from ..utils import ( @@ -17,6 +19,8 @@ from ..utils import ( class NocoIE(InfoExtractor): _VALID_URL = r'http://(?:(?:www\.)?noco\.tv/emission/|player\.noco\.tv/\?idvideo=)(?P\d+)' _LOGIN_URL = 'http://noco.tv/do.php' + _API_URL_TEMPLATE = 'https://api.noco.tv/1.1/%s?ts=%s&tk=%s' + _SUB_LANG_TEMPLATE = '&sub_lang=%s' _NETRC_MACHINE = 'noco' _TEST = { @@ -55,56 +59,91 @@ class NocoIE(InfoExtractor): login = self._download_json(request, None, 'Logging in as %s' % username) if 'erreur' in login: - raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) + raise ExtractorError('Unable to login: %s' % clean_html(login['erreur']), expected=True) + + def _call_api(self, path, video_id, note, sub_lang=None): + ts = compat_str(int(time.time() * 1000)) + tk = hashlib.md5((hashlib.md5(ts.encode('ascii')).hexdigest() + '#8S?uCraTedap6a').encode('ascii')).hexdigest() + url = self._API_URL_TEMPLATE % (path, ts, tk) + if sub_lang: + url += self._SUB_LANG_TEMPLATE % sub_lang + + resp = self._download_json(url, video_id, note) + + if isinstance(resp, dict) and resp.get('error'): + self._raise_error(resp['error'], resp['description']) + + return resp + + def _raise_error(self, error, description): + raise ExtractorError( + '%s returned error: %s - %s' % (self.IE_NAME, error, description), + expected=True) def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - medias = self._download_json( - 'https://api.noco.tv/1.0/video/medias/%s' % video_id, video_id, 'Downloading video JSON') + medias = self._call_api( + 'shows/%s/medias' % video_id, + video_id, 'Downloading video JSON') + + qualities = self._call_api( + 'qualities', + video_id, 'Downloading qualities JSON') formats = [] - for fmt in medias['fr']['video_list']['default']['quality_list']: - format_id = fmt['quality_key'] + for lang, lang_dict in medias['fr']['video_list'].items(): + for format_id, fmt in lang_dict['quality_list'].items(): + format_id_extended = '%s-%s' % (lang, format_id) if lang != 'none' else format_id - file = self._download_json( - 'https://api.noco.tv/1.0/video/file/%s/fr/%s' % (format_id.lower(), video_id), - video_id, 'Downloading %s video JSON' % format_id) + video = self._call_api( + 'shows/%s/video/%s/fr' % (video_id, format_id.lower()), + video_id, 'Downloading %s video JSON' % format_id_extended, + lang if lang != 'none' else None) - file_url = file['file'] - if not file_url: - continue + file_url = video['file'] + if not file_url: + continue - if file_url == 'forbidden': - raise ExtractorError( - '%s returned error: %s - %s' % ( - self.IE_NAME, file['popmessage']['title'], file['popmessage']['message']), - expected=True) + if file_url in ['forbidden', 'not found']: + popmessage = video['popmessage'] + self._raise_error(popmessage['title'], popmessage['message']) - formats.append({ - 'url': file_url, - 'format_id': format_id, - 'width': fmt['res_width'], - 'height': fmt['res_lines'], - 'abr': fmt['audiobitrate'], - 'vbr': fmt['videobitrate'], - 'filesize': fmt['filesize'], - 'format_note': fmt['quality_name'], - 'preference': fmt['priority'], - }) + formats.append({ + 'url': file_url, + 'format_id': format_id_extended, + 'width': fmt['res_width'], + 'height': fmt['res_lines'], + 'abr': fmt['audiobitrate'], + 'vbr': fmt['videobitrate'], + 'filesize': fmt['filesize'], + 'format_note': qualities[format_id]['quality_name'], + 'preference': qualities[format_id]['priority'], + }) self._sort_formats(formats) - show = self._download_json( - 'https://api.noco.tv/1.0/shows/show/%s' % video_id, video_id, 'Downloading show JSON')[0] + show = self._call_api( + 'shows/by_id/%s' % video_id, + video_id, 'Downloading show JSON')[0] - upload_date = unified_strdate(show['indexed']) + upload_date = unified_strdate(show['online_date_start_utc']) uploader = show['partner_name'] uploader_id = show['partner_key'] duration = show['duration_ms'] / 1000.0 - thumbnail = show['screenshot'] + + thumbnails = [] + for thumbnail_key, thumbnail_url in show.items(): + m = re.search(r'^screenshot_(?P\d+)x(?P\d+)$', thumbnail_key) + if not m: + continue + thumbnails.append({ + 'url': thumbnail_url, + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) episode = show.get('show_TT') or show.get('show_OT') family = show.get('family_TT') or show.get('family_OT') @@ -124,10 +163,10 @@ class NocoIE(InfoExtractor): 'id': video_id, 'title': title, 'description': description, - 'thumbnail': thumbnail, + 'thumbnails': thumbnails, 'upload_date': upload_date, 'uploader': uploader, 'uploader_id': uploader_id, 'duration': duration, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/normalboots.py b/youtube_dl/extractor/normalboots.py index 25e71a56e..3d35b11ac 100644 --- a/youtube_dl/extractor/normalboots.py +++ b/youtube_dl/extractor/normalboots.py @@ -31,9 +31,9 @@ class NormalbootsIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_uploader = self._html_search_regex(r'Posted\sby\s(?P[A-Za-z]*)\s    ', - webpage, 'uploader') + webpage, 'uploader') raw_upload_date = self._html_search_regex('[A-Za-z]+, (?P.*)', - webpage, 'date') + webpage, 'date') video_upload_date = unified_strdate(raw_upload_date) player_url = self._html_search_regex(r'[\S]+)"', webpage, 'url') diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 2e7ab1e4f..38d05e466 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -66,4 +66,4 @@ class NovaMovIE(InfoExtractor): 'url': video_url, 'title': title, 'description': description - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py index bfba18418..ecb38de2d 100644 --- a/youtube_dl/extractor/nowvideo.py +++ b/youtube_dl/extractor/nowvideo.py @@ -25,4 +25,4 @@ class NowVideoIE(NovaMovIE): 'title': 'youtubedl test video _BaW_jenozKc.mp4', 'description': 'Description', } - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index 902d62944..ce31694a5 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -5,7 +5,10 @@ import re from .common import InfoExtractor from ..utils import ( unified_strdate, + parse_duration, qualities, + strip_jsonp, + url_basename, ) @@ -13,27 +16,55 @@ class NPOIE(InfoExtractor): IE_NAME = 'npo.nl' _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P[^/?]+)' - _TEST = { - 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', - 'md5': '4b3f9c429157ec4775f2c9cb7b911016', - 'info_dict': { - 'id': 'VPWON_1220719', - 'ext': 'm4v', - 'title': 'Nieuwsuur', - 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', - 'upload_date': '20140622', + _TESTS = [ + { + 'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719', + 'md5': '4b3f9c429157ec4775f2c9cb7b911016', + 'info_dict': { + 'id': 'VPWON_1220719', + 'ext': 'm4v', + 'title': 'Nieuwsuur', + 'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.', + 'upload_date': '20140622', + }, }, - } + { + 'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800', + 'md5': 'da50a5787dbfc1603c4ad80f31c5120b', + 'info_dict': { + 'id': 'VARA_101191800', + 'ext': 'm4v', + 'title': 'De Mega Mike & Mega Thomas show', + 'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4', + 'upload_date': '20090227', + 'duration': 2400, + }, + }, + { + 'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289', + 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', + 'info_dict': { + 'id': 'VPWON_1169289', + 'ext': 'm4v', + 'title': 'Tegenlicht', + 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', + 'upload_date': '20130225', + 'duration': 3000, + }, + } + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + return self._get_info(video_id) + def _get_info(self, video_id): metadata = self._download_json( 'http://e.omroep.nl/metadata/aflevering/%s' % video_id, video_id, # We have to remove the javascript callback - transform_source=lambda j: re.sub(r'parseMetadata\((.*?)\);\n//.*$', r'\1', j) + transform_source=strip_jsonp, ) token_page = self._download_webpage( 'http://ida.omroep.nl/npoplayer/i.js', @@ -43,19 +74,28 @@ class NPOIE(InfoExtractor): token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token') formats = [] - quality = qualities(['adaptive', 'h264_sb', 'h264_bb', 'h264_std']) + quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std']) for format_id in metadata['pubopties']: - streams_info = self._download_json( + format_info = self._download_json( 'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s' % (video_id, format_id, token), - video_id, 'Downloading %s streams info' % format_id) - stream_info = self._download_json( - streams_info['streams'][0] + '&type=json', - video_id, 'Downloading %s stream info' % format_id) + video_id, 'Downloading %s JSON' % format_id) + if format_info.get('error_code', 0) or format_info.get('errorcode', 0): + continue + streams = format_info.get('streams') + if streams: + video_info = self._download_json( + streams[0] + '&type=json', + video_id, 'Downloading %s stream JSON' % format_id) + else: + video_info = format_info + video_url = video_info.get('url') + if not video_url: + continue if format_id == 'adaptive': - formats.extend(self._extract_m3u8_formats(stream_info['url'], video_id)) + formats.extend(self._extract_m3u8_formats(video_url, video_id)) else: formats.append({ - 'url': stream_info['url'], + 'url': video_url, 'format_id': format_id, 'quality': quality(format_id), }) @@ -65,7 +105,35 @@ class NPOIE(InfoExtractor): 'id': video_id, 'title': metadata['titel'], 'description': metadata['info'], - 'thumbnail': metadata['images'][-1]['url'], - 'upload_date': unified_strdate(metadata['gidsdatum']), + 'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'], + 'upload_date': unified_strdate(metadata.get('gidsdatum')), + 'duration': parse_duration(metadata.get('tijdsduur')), 'formats': formats, } + + +class TegenlichtVproIE(NPOIE): + IE_NAME = 'tegenlicht.vpro.nl' + _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?' + + _TESTS = [ + { + 'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html', + 'md5': 'f8065e4e5a7824068ed3c7e783178f2c', + 'info_dict': { + 'id': 'VPWON_1169289', + 'ext': 'm4v', + 'title': 'Tegenlicht', + 'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1', + 'upload_date': '20130225', + }, + }, + ] + + def _real_extract(self, url): + name = url_basename(url) + webpage = self._download_webpage(url, name) + urn = self._html_search_meta('mediaurn', webpage) + info_page = self._download_json( + 'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name) + return self._get_info(info_page['mid']) diff --git a/youtube_dl/extractor/ntv.py b/youtube_dl/extractor/ntv.py index ed60314ec..13c8d79cd 100644 --- a/youtube_dl/extractor/ntv.py +++ b/youtube_dl/extractor/ntv.py @@ -145,4 +145,4 @@ class NTVIE(InfoExtractor): 'duration': duration, 'view_count': view_count, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/nuvid.py b/youtube_dl/extractor/nuvid.py index 58ec81f91..449c8a6a3 100644 --- a/youtube_dl/extractor/nuvid.py +++ b/youtube_dl/extractor/nuvid.py @@ -71,4 +71,4 @@ class NuvidIE(InfoExtractor): 'upload_date': upload_date, 'age_limit': 18, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/nytimes.py b/youtube_dl/extractor/nytimes.py index 7bf105d38..56e1cad3b 100644 --- a/youtube_dl/extractor/nytimes.py +++ b/youtube_dl/extractor/nytimes.py @@ -74,4 +74,4 @@ class NYTimesIE(InfoExtractor): 'duration': duration, 'formats': formats, 'thumbnails': thumbnails, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/oktoberfesttv.py b/youtube_dl/extractor/oktoberfesttv.py new file mode 100644 index 000000000..4a41c0542 --- /dev/null +++ b/youtube_dl/extractor/oktoberfesttv.py @@ -0,0 +1,47 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class OktoberfestTVIE(InfoExtractor): + _VALID_URL = r'https?://www\.oktoberfest-tv\.de/[^/]+/[^/]+/video/(?P[^/?#]+)' + + _TEST = { + 'url': 'http://www.oktoberfest-tv.de/de/kameras/video/hb-zelt', + 'info_dict': { + 'id': 'hb-zelt', + 'ext': 'mp4', + 'title': 're:^Live-Kamera: Hofbräuzelt [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'thumbnail': 're:^https?://.*\.jpg$', + 'is_live': True, + }, + 'params': { + 'skip_download': True, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._live_title(self._html_search_regex( + r'

    .*?(.*?)

    ', webpage, 'title')) + + clip = self._search_regex( + r"clip:\s*\{\s*url:\s*'([^']+)'", webpage, 'clip') + ncurl = self._search_regex( + r"netConnectionUrl:\s*'([^']+)'", webpage, 'rtmp base') + video_url = ncurl + clip + thumbnail = self._search_regex( + r"canvas:\s*\{\s*backgroundImage:\s*'url\(([^)]+)\)'", webpage, + 'thumbnail', fatal=False) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'ext': 'mp4', + 'is_live': True, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 2044e107e..f17a52858 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -43,7 +43,7 @@ class OoyalaIE(InfoExtractor): @classmethod def _build_url_result(cls, embed_code): return cls.url_result(cls._url_for_embed_code(embed_code), - ie=cls.ie_key()) + ie=cls.ie_key()) def _extract_result(self, info, more_info): return { @@ -97,4 +97,3 @@ class OoyalaIE(InfoExtractor): } else: return self._extract_result(videos_info[0], videos_more_info) - diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py index 011e6be13..572a234ad 100644 --- a/youtube_dl/extractor/orf.py +++ b/youtube_dl/extractor/orf.py @@ -178,4 +178,4 @@ class ORFFM4IE(InfoExtractor): 'title': data['title'], 'description': data['subtitle'], 'entries': entries - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 2adfde909..6118ed5c2 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + unified_strdate, US_RATINGS, ) @@ -11,10 +12,10 @@ from ..utils import ( class PBSIE(InfoExtractor): _VALID_URL = r'''(?x)https?:// (?: - # Direct video URL - video\.pbs\.org/(?:viralplayer|video)/(?P[0-9]+)/? | - # Article with embedded player - (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P[^/]+)/?(?:$|[?\#]) | + # Direct video URL + video\.pbs\.org/(?:viralplayer|video)/(?P[0-9]+)/? | + # Article with embedded player (or direct video) + (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player video\.pbs\.org/(?:widget/)?partnerplayer/(?P[^/]+)/ ) @@ -65,10 +66,31 @@ class PBSIE(InfoExtractor): 'duration': 6559, 'thumbnail': 're:^https?://.*\.jpg$', } + }, + { + 'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html', + 'md5': '908f3e5473a693b266b84e25e1cf9703', + 'info_dict': { + 'id': '2365160389', + 'display_id': 'killer-typhoon', + 'ext': 'mp4', + 'description': 'md5:c741d14e979fc53228c575894094f157', + 'title': 'Killer Typhoon', + 'duration': 3172, + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20140122', + } + }, + { + 'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/', + 'info_dict': { + 'id': 'united-states-of-secrets', + }, + 'playlist_count': 2, } ] - def _extract_ids(self, url): + def _extract_webpage(self, url): mobj = re.match(self._VALID_URL, url) presumptive_id = mobj.group('presumptive_id') @@ -76,15 +98,26 @@ class PBSIE(InfoExtractor): if presumptive_id: webpage = self._download_webpage(url, display_id) + upload_date = unified_strdate(self._search_regex( + r']+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage) + if tabbed_videos: + return tabbed_videos, presumptive_id, upload_date + MEDIA_ID_REGEXES = [ r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed r'class="coveplayerid">([^<]+)<', # coveplayer + r'', # jwplayer ] media_id = self._search_regex( MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) if media_id: - return media_id, presumptive_id + return media_id, presumptive_id, upload_date url = self._search_regex( r'', @@ -104,10 +137,16 @@ class PBSIE(InfoExtractor): video_id = mobj.group('id') display_id = video_id - return video_id, display_id + return video_id, display_id, None def _real_extract(self, url): - video_id, display_id = self._extract_ids(url) + video_id, display_id, upload_date = self._extract_webpage(url) + + if isinstance(video_id, list): + entries = [self.url_result( + 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id) + for vid_id in video_id] + return self.playlist_result(entries, display_id) info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id info = self._download_json(info_url, display_id) @@ -119,6 +158,7 @@ class PBSIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'title': info['title'], 'url': info['alternate_encoding']['url'], 'ext': 'mp4', @@ -126,4 +166,5 @@ class PBSIE(InfoExtractor): 'thumbnail': info.get('image_url'), 'duration': info.get('duration'), 'age_limit': age_limit, + 'upload_date': upload_date, } diff --git a/youtube_dl/extractor/phoenix.py b/youtube_dl/extractor/phoenix.py new file mode 100644 index 000000000..a20672c0c --- /dev/null +++ b/youtube_dl/extractor/phoenix.py @@ -0,0 +1,31 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from .zdf import extract_from_xml_url + + +class PhoenixIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?phoenix\.de/content/(?P[0-9]+)' + _TEST = { + 'url': 'http://www.phoenix.de/content/884301', + 'md5': 'ed249f045256150c92e72dbb70eadec6', + 'info_dict': { + 'id': '884301', + 'ext': 'mp4', + 'title': 'Michael Krons mit Hans-Werner Sinn', + 'description': 'Im Dialog - Sa. 25.10.14, 00.00 - 00.35 Uhr', + 'upload_date': '20141025', + 'uploader': 'Im Dialog', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + internal_id = self._search_regex( + r'
    [0-9]+)' + _API_URL = 'http://planetaplay.com/action/playlist/?sng={0:}' + _THUMBNAIL_URL = 'http://planetaplay.com/img/thumb/{thumb:}' + _TEST = { + 'url': 'http://planetaplay.com/?sng=3586', + 'md5': '9d569dceb7251a4e01355d5aea60f9db', + 'info_dict': { + 'id': '3586', + 'ext': 'flv', + 'title': 'md5:e829428ee28b1deed00de90de49d1da1', + } + } + + _SONG_FORMATS = { + 'lq': (0, 'http://www.planetaplay.com/videoplayback/{med_hash:}'), + 'hq': (1, 'http://www.planetaplay.com/videoplayback/hi/{med_hash:}'), + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + response = self._download_json( + self._API_URL.format(video_id), video_id)['response'] + try: + data = response.get('data')[0] + except IndexError: + raise ExtractorError( + '%s: failed to get the playlist' % self.IE_NAME, expected=True) + + title = '{song_artists:} - {sng_name:}'.format(**data) + thumbnail = self._THUMBNAIL_URL.format(**data) + + formats = [] + for format_id, (quality, url_template) in self._SONG_FORMATS.items(): + formats.append({ + 'format_id': format_id, + 'url': url_template.format(**data), + 'quality': quality, + 'ext': 'flv', + }) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/played.py b/youtube_dl/extractor/played.py new file mode 100644 index 000000000..17880471d --- /dev/null +++ b/youtube_dl/extractor/played.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import os.path + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urllib_parse, + compat_urllib_request, +) + + +class PlayedIE(InfoExtractor): + IE_NAME = 'played.to' + _VALID_URL = r'https?://(?:www\.)?played\.to/(?P[a-zA-Z0-9_-]+)' + + _TEST = { + 'url': 'http://played.to/j2f2sfiiukgt', + 'md5': 'c2bd75a368e82980e7257bf500c00637', + 'info_dict': { + 'id': 'j2f2sfiiukgt', + 'ext': 'flv', + 'title': 'youtube-dl_test_video.mp4', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + orig_webpage = self._download_webpage(url, video_id) + + m_error = re.search( + r'(?s)Reason for deletion:.*?]*>(?P[^<]+)', orig_webpage) + if m_error: + raise ExtractorError(m_error.group('msg'), expected=True) + + fields = re.findall( + r'type="hidden" name="([^"]+)"\s+value="([^"]+)">', orig_webpage) + data = dict(fields) + + self._sleep(2, video_id) + + post = compat_urllib_parse.urlencode(data) + headers = { + b'Content-Type': b'application/x-www-form-urlencoded', + } + req = compat_urllib_request.Request(url, post, headers) + webpage = self._download_webpage( + req, video_id, note='Downloading video page ...') + + title = os.path.splitext(data['fname'])[0] + + video_url = self._search_regex( + r'file: "?(.+?)",', webpage, 'video URL') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + } diff --git a/youtube_dl/extractor/playfm.py b/youtube_dl/extractor/playfm.py index 72df4d842..ebc046804 100644 --- a/youtube_dl/extractor/playfm.py +++ b/youtube_dl/extractor/playfm.py @@ -10,6 +10,7 @@ from ..utils import ( ExtractorError, float_or_none, int_or_none, + str_to_int, ) @@ -29,6 +30,7 @@ class PlayFMIE(InfoExtractor): 'duration': 5627.428, 'upload_date': '20140712', 'view_count': int, + 'comment_count': int, 'thumbnail': 're:^https?://.*\.jpg$', }, } @@ -51,7 +53,8 @@ class PlayFMIE(InfoExtractor): recording = rec_doc.find('./recording') title = recording.find('./title').text - view_count = int_or_none(recording.find('./stats/playcount').text) + view_count = str_to_int(recording.find('./stats/playcount').text) + comment_count = str_to_int(recording.find('./stats/comments').text) duration = float_or_none(recording.find('./duration').text, scale=1000) thumbnail = recording.find('./image').text @@ -75,6 +78,7 @@ class PlayFMIE(InfoExtractor): 'title': title, 'upload_date': upload_date, 'view_count': view_count, + 'comment_count': comment_count, 'duration': duration, 'thumbnail': thumbnail, 'uploader': uploader, diff --git a/youtube_dl/extractor/playvid.py b/youtube_dl/extractor/playvid.py index b1322f13f..cd3905acb 100644 --- a/youtube_dl/extractor/playvid.py +++ b/youtube_dl/extractor/playvid.py @@ -4,6 +4,8 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, + clean_html, compat_urllib_parse, ) @@ -28,6 +30,11 @@ class PlayvidIE(InfoExtractor): webpage = self._download_webpage(url, video_id) + m_error = re.search( + r'
    \s*
    \s*
    (?P.+?)
    \s*
    ', webpage) + if m_error: + raise ExtractorError(clean_html(m_error.group('msg')), expected=True) + video_title = None duration = None video_thumbnail = None diff --git a/youtube_dl/extractor/podomatic.py b/youtube_dl/extractor/podomatic.py index ffafd2380..f20946a2b 100644 --- a/youtube_dl/extractor/podomatic.py +++ b/youtube_dl/extractor/podomatic.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import int_or_none + class PodomaticIE(InfoExtractor): IE_NAME = 'podomatic' _VALID_URL = r'^(?Phttps?)://(?P[^.]+)\.podomatic\.com/entry/(?P[^?]+)' diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 48ce6e730..bac484c67 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -4,19 +4,27 @@ import re import json from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + js_to_json, + qualities, + determine_ext, +) class PornHdIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P\d+)' + _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P\d+)(?:/(?P.+))?' _TEST = { 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'md5': '956b8ca569f7f4d8ec563e2c41598441', 'info_dict': { 'id': '1962', + 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'ext': 'mp4', 'title': 'Sierra loves doing laundry', 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', + 'thumbnail': 're:^https?://.*\.jpg', + 'view_count': int, 'age_limit': 18, } } @@ -24,8 +32,9 @@ class PornHdIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + display_id = mobj.group('display_id') - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, display_id or video_id) title = self._html_search_regex( r'(.+) porn HD.+?', webpage, 'title') @@ -33,38 +42,21 @@ class PornHdIE(InfoExtractor): r'
    ([^<]+)
    ', webpage, 'description', fatal=False) view_count = int_or_none(self._html_search_regex( r'(\d+) views\s*', webpage, 'view count', fatal=False)) + thumbnail = self._search_regex( + r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False) - videos = re.findall( - r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage) - - mobj = re.search(r'flashVars = (?P{.+?});', webpage) - if mobj: - flashvars = json.loads(mobj.group('flashvars')) - for key, quality in [('hashlink', 'low'), ('hd', 'high')]: - redirect_url = flashvars.get(key) - if redirect_url: - videos.append(('flv', quality, redirect_url)) - thumbnail = flashvars['urlWallpaper'] - else: - thumbnail = self._og_search_thumbnail(webpage) - - formats = [] - for format_, quality, redirect_url in videos: - format_id = '%s-%s' % (format_.lower(), quality.lower()) - video_url = self._download_webpage( - redirect_url, video_id, 'Downloading %s video link' % format_id, fatal=False) - if not video_url: - continue - formats.append({ - 'url': video_url, - 'ext': format_.lower(), - 'format_id': format_id, - 'quality': 1 if quality.lower() == 'high' else 0, - }) + quality = qualities(['SD', 'HD']) + formats = [{ + 'url': source['file'], + 'format_id': '%s-%s' % (source['label'], determine_ext(source['file'])), + 'quality': quality(source['label']), + } for source in json.loads(js_to_json(self._search_regex( + r"(?s)'sources'\s*:\s*(\[.+?\])", webpage, 'sources')))] self._sort_formats(formats) return { 'id': video_id, + 'display_id': display_id, 'title': title, 'description': description, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 4118ee956..2ca15b717 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -16,13 +16,14 @@ from ..aes import ( class PornHubIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Ppornhub\.com/view_video\.php\?viewkey=(?P[0-9a-f]+))' + _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P[0-9a-f]+)' _TEST = { 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', - 'file': '648719015.mp4', 'md5': '882f488fa1f0026f023f33576004a2ed', 'info_dict': { - "uploader": "BABES-COM", + 'id': '648719015', + 'ext': 'mp4', + "uploader": "Babes", "title": "Seductive Indian beauty strips down and fingers her pink pussy", "age_limit": 18 } @@ -35,9 +36,7 @@ class PornHubIE(InfoExtractor): return count def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') + video_id = self._match_id(url) req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') @@ -45,7 +44,7 @@ class PornHubIE(InfoExtractor): video_title = self._html_search_regex(r'

    ]+>([^<]+)', webpage, 'title') video_uploader = self._html_search_regex( - r'(?s)From: .+?<(?:a href="/users/|]+>(.+?)<', webpage, 'uploader', fatal=False) thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False) if thumbnail: @@ -57,7 +56,7 @@ class PornHubIE(InfoExtractor): comment_count = self._extract_count( r'All comments \(([\d,\.]+)', webpage, 'comment') - video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) + video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) if webpage.find('"encrypted":true') != -1: password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password')) video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) diff --git a/youtube_dl/extractor/pornotube.py b/youtube_dl/extractor/pornotube.py index 04bd3d979..5253aa3d3 100644 --- a/youtube_dl/extractor/pornotube.py +++ b/youtube_dl/extractor/pornotube.py @@ -38,7 +38,7 @@ class PornotubeIE(InfoExtractor): video_url = self._search_regex(VIDEO_URL_RE, webpage, 'video url') video_url = compat_urllib_parse.unquote(video_url) - #Get the uploaded date + # Get the uploaded date VIDEO_UPLOADED_RE = r'
    Added (?P[0-9\/]+) by' upload_date = self._html_search_regex(VIDEO_UPLOADED_RE, webpage, 'upload date', fatal=False) if upload_date: diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py index 463e85501..7fcde086c 100644 --- a/youtube_dl/extractor/promptfile.py +++ b/youtube_dl/extractor/promptfile.py @@ -14,7 +14,6 @@ from ..utils import ( class PromptFileIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P[0-9A-Z\-]+)' - _FILE_NOT_FOUND_REGEX = r'.+
    [^-]' _TEST = { 'url': 'http://www.promptfile.com/l/D21B4746E9-F01462F0FF', 'md5': 'd1451b6302da7215485837aaea882c4c', @@ -27,11 +26,10 @@ class PromptFileIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - if re.search(self._FILE_NOT_FOUND_REGEX, webpage) is not None: + if re.search(r'(?!We are).+

    [^-]', webpage) is not None: raise ExtractorError('Video %s does not exist' % video_id, expected=True) diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 5b2a723c1..32d747ede 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -144,7 +144,7 @@ class ProSiebenSat1IE(InfoExtractor): 'id': '2156342', 'ext': 'mp4', 'title': 'Kurztrips zum Valentinstag', - 'description': 'md5:8ba6301e70351ae0bedf8da00f7ba528', + 'description': 'Romantischer Kurztrip zum Valentinstag? Wir verraten, was sich hier wirklich lohnt.', 'duration': 307.24, }, 'params': { @@ -180,12 +180,10 @@ class ProSiebenSat1IE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - page = self._download_webpage(url, video_id, 'Downloading page') - - clip_id = self._html_search_regex(self._CLIPID_REGEXES, page, 'clip id') + clip_id = self._html_search_regex(self._CLIPID_REGEXES, webpage, 'clip id') access_token = 'testclient' client_name = 'kolibri-1.2.5' @@ -234,12 +232,12 @@ class ProSiebenSat1IE(InfoExtractor): urls = self._download_json(url_api_url, clip_id, 'Downloading urls JSON') - title = self._html_search_regex(self._TITLE_REGEXES, page, 'title') - description = self._html_search_regex(self._DESCRIPTION_REGEXES, page, 'description', fatal=False) - thumbnail = self._og_search_thumbnail(page) + title = self._html_search_regex(self._TITLE_REGEXES, webpage, 'title') + description = self._html_search_regex(self._DESCRIPTION_REGEXES, webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) upload_date = unified_strdate(self._html_search_regex( - self._UPLOAD_DATE_REGEXES, page, 'upload date', default=None)) + self._UPLOAD_DATE_REGEXES, webpage, 'upload date', default=None)) formats = [] @@ -282,4 +280,4 @@ class ProSiebenSat1IE(InfoExtractor): 'upload_date': upload_date, 'duration': duration, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/quickvid.py b/youtube_dl/extractor/quickvid.py new file mode 100644 index 000000000..3bc78060d --- /dev/null +++ b/youtube_dl/extractor/quickvid.py @@ -0,0 +1,51 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urlparse, + determine_ext, + int_or_none, +) + + +class QuickVidIE(InfoExtractor): + _VALID_URL = r'https?://(www\.)?quickvid\.org/watch\.php\?v=(?P[a-zA-Z_0-9-]+)' + _TEST = { + 'url': 'http://quickvid.org/watch.php?v=sUQT3RCG8dx', + 'md5': 'c0c72dd473f260c06c808a05d19acdc5', + 'info_dict': { + 'id': 'sUQT3RCG8dx', + 'ext': 'mp4', + 'title': 'Nick Offerman\'s Summer Reading Recap', + 'thumbnail': 're:^https?://.*\.(?:png|jpg|gif)$', + 'view_count': int, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + title = self._html_search_regex(r'

    (.*?)

    ', webpage, 'title') + view_count = int_or_none(self._html_search_regex( + r'(?s)
    (.*?)
    ', + webpage, 'view count', fatal=False)) + video_code = self._search_regex( + r'(?s)', webpage, 'video code') + formats = [ + { + 'url': compat_urlparse.urljoin(url, src), + 'format_id': determine_ext(src, None), + } for src in re.findall('[0-9]+)' _TEST = { 'url': 'http://www.redtube.com/66418', - 'file': '66418.mp4', - # md5 varies from time to time, as in - # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295 - #'md5': u'7b8c22b5e7098a3e1c09709df1126d2d', 'info_dict': { + 'id': '66418', + 'ext': 'mp4', "title": "Sucked on a toilet", "age_limit": 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') - video_extension = 'mp4' + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - self.report_extraction(video_id) - video_url = self._html_search_regex( - r'', webpage, u'video URL') - + r'', webpage, 'video URL') video_title = self._html_search_regex( r'

    (.+?)

    ', - webpage, u'title') - + webpage, 'title') video_thumbnail = self._og_search_thumbnail(webpage) # No self-labeling, but they describe themselves as @@ -44,7 +33,7 @@ class RedTubeIE(InfoExtractor): return { 'id': video_id, 'url': video_url, - 'ext': video_extension, + 'ext': 'mp4', 'title': video_title, 'thumbnail': video_thumbnail, 'age_limit': age_limit, diff --git a/youtube_dl/extractor/ringtv.py b/youtube_dl/extractor/ringtv.py index 9fbdb9fcb..59dc137cc 100644 --- a/youtube_dl/extractor/ringtv.py +++ b/youtube_dl/extractor/ringtv.py @@ -41,4 +41,3 @@ class RingTVIE(InfoExtractor): 'thumbnail': thumbnail_url, 'description': description, } - diff --git a/youtube_dl/extractor/ro220.py b/youtube_dl/extractor/ro220.py index a6ad59465..962b524e9 100644 --- a/youtube_dl/extractor/ro220.py +++ b/youtube_dl/extractor/ro220.py @@ -1,43 +1,43 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor -from ..utils import ( - clean_html, - compat_parse_qs, -) +from ..compat import compat_urllib_parse_unquote class Ro220IE(InfoExtractor): IE_NAME = '220.ro' - _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P[^/]+)/(?P[^/]+)/(?P[^/]+)' + _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P[^/]+)/(?P[^/]+)/(?P[^/]+)' _TEST = { - "url": "http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/", - 'file': 'LYV6doKo7f.mp4', + 'url': 'http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/', 'md5': '03af18b73a07b4088753930db7a34add', 'info_dict': { - "title": "Luati-le Banii sez 4 ep 1", - "description": "re:^Iata-ne reveniti dupa o binemeritata vacanta\. +Va astept si pe Facebook cu pareri si comentarii.$", + 'id': 'LYV6doKo7f', + 'ext': 'mp4', + 'title': 'Luati-le Banii sez 4 ep 1', + 'description': 're:^Iata-ne reveniti dupa o binemeritata vacanta\. +Va astept si pe Facebook cu pareri si comentarii.$', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - flashVars_str = self._search_regex( - r'rtmpe://(?:[^/]+/){2})(?P.+)', filename.text) @@ -153,4 +153,4 @@ class RTLnowIE(InfoExtractor): 'upload_date': upload_date, 'duration': duration, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 4dd35a47b..0ce22d60c 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -54,7 +54,6 @@ def _decrypt_url(png): return url - class RTVEALaCartaIE(InfoExtractor): IE_NAME = 'rtve.es:alacarta' IE_DESC = 'RTVE a la carta' diff --git a/youtube_dl/extractor/ruhd.py b/youtube_dl/extractor/ruhd.py index 55b58e5e6..0e470e73f 100644 --- a/youtube_dl/extractor/ruhd.py +++ b/youtube_dl/extractor/ruhd.py @@ -1,8 +1,6 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import re - from .common import InfoExtractor @@ -21,19 +19,20 @@ class RUHDIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_url = self._html_search_regex( r'([^<]+)   RUHD.ru - Видео Высокого качества №1 в России!', webpage, 'title') + r'([^<]+)   RUHD.ru - Видео Высокого качества №1 в России!', + webpage, 'title') description = self._html_search_regex( - r'(?s)
    (.+?)', webpage, 'description', fatal=False) + r'(?s)
    (.+?)', + webpage, 'description', fatal=False) thumbnail = self._html_search_regex( - r'[0-9]+)/' + _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/ondemand/video/(?:single/)?(?P[0-9]+)' _TESTS = [{ # Original URL is handled by the generic IE which finds the iframe: @@ -21,12 +21,15 @@ class SBSIE(InfoExtractor): 'md5': '3150cf278965eeabb5b4cea1c963fe0a', 'info_dict': { 'id': '320403011771', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Dingo Conservation', 'description': 'Dingoes are on the brink of extinction; most of the animals we think are dingoes are in fact crossbred with wild dogs. This family run a dingo conservation park to prevent their extinction', 'thumbnail': 're:http://.*\.jpg', }, 'add_ies': ['generic'], + }, { + 'url': 'http://www.sbs.com.au/ondemand/video/320403011771/Dingo-Conservation-The-Feed', + 'only_matching': True, }] def _real_extract(self, url): diff --git a/youtube_dl/extractor/scivee.py b/youtube_dl/extractor/scivee.py index 55a481cc0..3bf93c870 100644 --- a/youtube_dl/extractor/scivee.py +++ b/youtube_dl/extractor/scivee.py @@ -53,4 +53,4 @@ class SciVeeIE(InfoExtractor): 'description': description, 'thumbnail': 'http://www.scivee.tv/assets/videothumb/%s' % video_id, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/screencast.py b/youtube_dl/extractor/screencast.py index 306869e6a..c145f6fc7 100644 --- a/youtube_dl/extractor/screencast.py +++ b/youtube_dl/extractor/screencast.py @@ -96,7 +96,7 @@ class ScreencastIE(InfoExtractor): if title is None: title = self._html_search_regex( [r'Title: ([^<]*)
    ', - r'class="tabSeperator">>    (.*?)<'], + r'class="tabSeperator">>(.*?)<'], webpage, 'title') thumbnail = self._og_search_thumbnail(webpage) description = self._og_search_description(webpage, default=None) diff --git a/youtube_dl/extractor/servingsys.py b/youtube_dl/extractor/servingsys.py index 1dc551d5c..16dc3736b 100644 --- a/youtube_dl/extractor/servingsys.py +++ b/youtube_dl/extractor/servingsys.py @@ -67,5 +67,3 @@ class ServingSysIE(InfoExtractor): 'title': title, 'entries': entries, } - - \ No newline at end of file diff --git a/youtube_dl/extractor/sexu.py b/youtube_dl/extractor/sexu.py new file mode 100644 index 000000000..6365a8779 --- /dev/null +++ b/youtube_dl/extractor/sexu.py @@ -0,0 +1,61 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class SexuIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P\d+)' + _TEST = { + 'url': 'http://sexu.com/961791/', + 'md5': 'ff615aca9691053c94f8f10d96cd7884', + 'info_dict': { + 'id': '961791', + 'ext': 'mp4', + 'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b', + 'description': 'md5:c5ed8625eb386855d5a7967bd7b77a54', + 'categories': list, # NSFW + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + quality_arr = self._search_regex( + r'sources:\s*\[([^\]]+)\]', webpage, 'forrmat string') + formats = [{ + 'url': fmt[0].replace('\\', ''), + 'format_id': fmt[1], + 'height': int(fmt[1][:3]), + } for fmt in re.findall(r'"file":"([^"]+)","label":"([^"]+)"', quality_arr)] + self._sort_formats(formats) + + title = self._html_search_regex( + r'([^<]+)\s*-\s*Sexu\.Com', webpage, 'title') + + description = self._html_search_meta( + 'description', webpage, 'description') + + thumbnail = self._html_search_regex( + r'image:\s*"([^"]+)"', + webpage, 'thumbnail', fatal=False) + + categories_str = self._html_search_meta( + 'keywords', webpage, 'categories') + categories = ( + None if categories_str is None + else categories_str.split(',')) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'categories': categories, + 'formats': formats, + 'age_limit': 18, + } diff --git a/youtube_dl/extractor/sexykarma.py b/youtube_dl/extractor/sexykarma.py new file mode 100644 index 000000000..c833fc8ee --- /dev/null +++ b/youtube_dl/extractor/sexykarma.py @@ -0,0 +1,117 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + unified_strdate, + parse_duration, + int_or_none, +) + + +class SexyKarmaIE(InfoExtractor): + IE_DESC = 'Sexy Karma and Watch Indian Porn' + _VALID_URL = r'https?://(?:www\.)?(?:sexykarma\.com|watchindianporn\.net)/(?:[^/]+/)*video/(?P[^/]+)-(?P[a-zA-Z0-9]+)\.html' + _TESTS = [{ + 'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html', + 'md5': 'b9798e7d1ef1765116a8f516c8091dbd', + 'info_dict': { + 'id': 'yHI70cOyIHt', + 'display_id': 'taking-a-quick-pee', + 'ext': 'mp4', + 'title': 'Taking a quick pee.', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'wildginger7', + 'upload_date': '20141007', + 'duration': 22, + 'view_count': int, + 'comment_count': int, + 'categories': list, + } + }, { + 'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html', + 'md5': 'dd216c68d29b49b12842b9babe762a5d', + 'info_dict': { + 'id': '8Id6EZPbuHf', + 'display_id': 'pot-pixie-tribute', + 'ext': 'mp4', + 'title': 'pot_pixie tribute', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'banffite', + 'upload_date': '20141013', + 'duration': 16, + 'view_count': int, + 'comment_count': int, + 'categories': list, + } + }, { + 'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html', + 'md5': '9afb80675550406ed9a63ac2819ef69d', + 'info_dict': { + 'id': 'dW2mtctxJfs', + 'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number', + 'ext': 'mp4', + 'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'Don', + 'upload_date': '20140213', + 'duration': 83, + 'view_count': int, + 'comment_count': int, + 'categories': list, + } + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_url = self._html_search_regex( + r"url: escape\('([^']+)'\)", webpage, 'url') + + title = self._html_search_regex( + r'

    (.*?)', + webpage, 'title') + thumbnail = self._html_search_regex( + r'\s*(.*?)', + webpage, 'uploader') + upload_date = unified_strdate(self._html_search_regex( + r'Added: (.+?)', webpage, 'upload date', fatal=False)) + + duration = parse_duration(self._search_regex( + r'Time:\s*\s*\s*(.+?)\s*', + webpage, 'duration', fatal=False)) + + view_count = int_or_none(self._search_regex( + r'Views:\s*\s*\s*(\d+)\s*', + webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._search_regex( + r'Comments:\s*\s*\s*(\d+)\s*', + webpage, 'comment count', fatal=False)) + + categories = re.findall( + r'([^<]+)', + webpage) + + return { + 'id': video_id, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count, + 'categories': categories, + } diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index badba2ac6..fdc31603a 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -54,4 +54,4 @@ class SharedIE(InfoExtractor): 'filesize': filesize, 'title': title, 'thumbnail': thumbnail, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/sina.py b/youtube_dl/extractor/sina.py index 2909ef18b..5eadbb7ea 100644 --- a/youtube_dl/extractor/sina.py +++ b/youtube_dl/extractor/sina.py @@ -46,7 +46,7 @@ class SinaIE(InfoExtractor): def _extract_video(self, video_id): data = compat_urllib_parse.urlencode({'vid': video_id}) url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data, - video_id, 'Downloading video url') + video_id, 'Downloading video url') image_page = self._download_webpage( 'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data, video_id, 'Downloading thumbnail info') diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py index e6e7d0865..3df71304d 100644 --- a/youtube_dl/extractor/slutload.py +++ b/youtube_dl/extractor/slutload.py @@ -26,7 +26,7 @@ class SlutloadIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_title = self._html_search_regex(r'

    ([^<]+)', - webpage, 'title').strip() + webpage, 'title').strip() video_url = self._html_search_regex( r'(?s)
    v(?P[0-9]+)[a-z0-9]{4})' + _VALID_URL = r'^https?://(?:www\.)?(?:smotri\.com/video/view/\?id=|pics\.smotri\.com/(?:player|scrubber_custom8)\.swf\?file=)(?Pv(?P[0-9]+)[a-z0-9]{4})' _NETRC_MACHINE = 'smotri' _TESTS = [ @@ -35,7 +34,6 @@ class SmotriIE(InfoExtractor): 'uploader': 'rbc2008', 'uploader_id': 'rbc08', 'upload_date': '20131118', - 'description': 'катастрофа с камер видеонаблюдения, видео катастрофа с камер видеонаблюдения', 'thumbnail': 'http://frame6.loadup.ru/8b/a9/2610366.3.3.jpg', }, }, @@ -50,7 +48,6 @@ class SmotriIE(InfoExtractor): 'uploader': 'Support Photofile@photofile', 'uploader_id': 'support-photofile', 'upload_date': '20070704', - 'description': 'test, видео test', 'thumbnail': 'http://frame4.loadup.ru/03/ed/57591.2.3.jpg', }, }, @@ -66,7 +63,6 @@ class SmotriIE(InfoExtractor): 'uploader_id': 'timoxa40', 'upload_date': '20100404', 'thumbnail': 'http://frame7.loadup.ru/af/3f/1390466.3.3.jpg', - 'description': 'TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1, видео TOCCA_A_NOI_-_LE_COSE_NON_VANNO_CAMBIAMOLE_ORA-1', }, 'params': { 'videopassword': 'qwerty', @@ -85,7 +81,6 @@ class SmotriIE(InfoExtractor): 'upload_date': '20101001', 'thumbnail': 'http://frame3.loadup.ru/75/75/1540889.1.3.jpg', 'age_limit': 18, - 'description': 'этот ролик не покажут по ТВ, видео этот ролик не покажут по ТВ', }, 'params': { 'videopassword': '333' @@ -102,17 +97,11 @@ class SmotriIE(InfoExtractor): 'uploader': 'HannahL', 'uploader_id': 'lisaha95', 'upload_date': '20090331', - 'description': 'Shakira - Don\'t Bother, видео Shakira - Don\'t Bother', 'thumbnail': 'http://frame8.loadup.ru/44/0b/918809.7.3.jpg', }, }, ] - _SUCCESS = 0 - _PASSWORD_NOT_VERIFIED = 1 - _PASSWORD_DETECTED = 2 - _VIDEO_NOT_FOUND = 3 - @classmethod def _extract_url(cls, webpage): mobj = re.search( @@ -137,44 +126,44 @@ class SmotriIE(InfoExtractor): return self._html_search_meta(name, html, display_name) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - real_video_id = mobj.group('realvideoid') + video_id = self._match_id(url) - # Download video JSON data - video_json_url = 'http://smotri.com/vt.php?id=%s' % real_video_id - video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON') - video_json = json.loads(video_json_page) + video_form = { + 'ticket': video_id, + 'video_url': '1', + 'frame_url': '1', + 'devid': 'LoadupFlashPlayer', + 'getvideoinfo': '1', + } - status = video_json['status'] - if status == self._VIDEO_NOT_FOUND: + request = compat_urllib_request.Request( + 'http://smotri.com/video/view/url/bot/', compat_urllib_parse.urlencode(video_form)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + + video = self._download_json(request, video_id, 'Downloading video JSON') + + if video.get('_moderate_no') or not video.get('moderated'): + raise ExtractorError('Video %s has not been approved by moderator' % video_id, expected=True) + + if video.get('error'): raise ExtractorError('Video %s does not exist' % video_id, expected=True) - elif status == self._PASSWORD_DETECTED: # The video is protected by a password, retry with - # video-password set - video_password = self._downloader.params.get('videopassword', None) - if not video_password: - raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) - video_json_url += '&md5pass=%s' % hashlib.md5(video_password.encode('utf-8')).hexdigest() - video_json_page = self._download_webpage(video_json_url, video_id, 'Downloading video JSON (video-password set)') - video_json = json.loads(video_json_page) - status = video_json['status'] - if status == self._PASSWORD_NOT_VERIFIED: - raise ExtractorError('Video password is invalid', expected=True) - if status != self._SUCCESS: - raise ExtractorError('Unexpected status value %s' % status) - - # Extract the URL of the video - video_url = video_json['file_data'] + video_url = video.get('_vidURL') or video.get('_vidURL_mp4') + title = video['title'] + thumbnail = video['_imgURL'] + upload_date = unified_strdate(video['added']) + uploader = video['userNick'] + uploader_id = video['userLogin'] + duration = int_or_none(video['duration']) # Video JSON does not provide enough meta data # We will extract some from the video web page instead - video_page_url = 'http://smotri.com/video/view/?id=%s' % video_id - video_page = self._download_webpage(video_page_url, video_id, 'Downloading video page') + webpage_url = 'http://smotri.com/video/view/?id=%s' % video_id + webpage = self._download_webpage(webpage_url, video_id, 'Downloading video page') # Warning if video is unavailable warning = self._html_search_regex( - r'
    (.*?)
    ', video_page, + r'
    (.*?)
    ', webpage, 'warning message', default=None) if warning is not None: self._downloader.report_warning( @@ -182,84 +171,32 @@ class SmotriIE(InfoExtractor): (video_id, warning)) # Adult content - if re.search('EroConfirmText">', video_page) is not None: + if re.search('EroConfirmText">', webpage) is not None: self.report_age_confirmation() confirm_string = self._html_search_regex( r'' % video_id, - video_page, 'confirm string') - confirm_url = video_page_url + '&confirm=%s' % confirm_string - video_page = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)') + webpage, 'confirm string') + confirm_url = webpage_url + '&confirm=%s' % confirm_string + webpage = self._download_webpage(confirm_url, video_id, 'Downloading video page (age confirmed)') adult_content = True else: adult_content = False - # Extract the rest of meta data - video_title = self._search_meta('name', video_page, 'title') - if not video_title: - video_title = os.path.splitext(url_basename(video_url))[0] - - video_description = self._search_meta('description', video_page) - END_TEXT = ' на сайте Smotri.com' - if video_description and video_description.endswith(END_TEXT): - video_description = video_description[:-len(END_TEXT)] - START_TEXT = 'Смотреть онлайн ролик ' - if video_description and video_description.startswith(START_TEXT): - video_description = video_description[len(START_TEXT):] - video_thumbnail = self._search_meta('thumbnail', video_page) - - upload_date_str = self._search_meta('uploadDate', video_page, 'upload date') - if upload_date_str: - upload_date_m = re.search(r'(?P\d{4})\.(?P\d{2})\.(?P\d{2})T', upload_date_str) - video_upload_date = ( - ( - upload_date_m.group('year') + - upload_date_m.group('month') + - upload_date_m.group('day') - ) - if upload_date_m else None - ) - else: - video_upload_date = None - - duration_str = self._search_meta('duration', video_page) - if duration_str: - duration_m = re.search(r'T(?P[0-9]{2})H(?P[0-9]{2})M(?P[0-9]{2})S', duration_str) - video_duration = ( - ( - (int(duration_m.group('hours')) * 60 * 60) + - (int(duration_m.group('minutes')) * 60) + - int(duration_m.group('seconds')) - ) - if duration_m else None - ) - else: - video_duration = None - - video_uploader = self._html_search_regex( - '
    Автор.*?onmouseover="popup_user_info[^"]+">(.*?)', - video_page, 'uploader', fatal=False, flags=re.MULTILINE|re.DOTALL) - - video_uploader_id = self._html_search_regex( - '
    Автор.*?onmouseover="popup_user_info\\(.*?\'([^\']+)\'\\);">', - video_page, 'uploader id', fatal=False, flags=re.MULTILINE|re.DOTALL) - - video_view_count = self._html_search_regex( + view_count = self._html_search_regex( 'Общее количество просмотров.*?(\\d+)', - video_page, 'view count', fatal=False, flags=re.MULTILINE|re.DOTALL) + webpage, 'view count', fatal=False, flags=re.MULTILINE | re.DOTALL) return { 'id': video_id, 'url': video_url, - 'title': video_title, - 'thumbnail': video_thumbnail, - 'description': video_description, - 'uploader': video_uploader, - 'upload_date': video_upload_date, - 'uploader_id': video_uploader_id, - 'duration': video_duration, - 'view_count': int_or_none(video_view_count), + 'title': title, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'upload_date': upload_date, + 'uploader_id': uploader_id, + 'duration': duration, + 'view_count': int_or_none(view_count), 'age_limit': 18 if adult_content else 0, - 'video_page_url': video_page_url } @@ -275,7 +212,7 @@ class SmotriCommunityIE(InfoExtractor): }, 'playlist_mincount': 4, } - + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) community_id = mobj.group('communityid') @@ -345,7 +282,7 @@ class SmotriBroadcastIE(InfoExtractor): (username, password) = self._get_login_info() if username is None: raise ExtractorError('Erotic broadcasts allowed only for registered users, ' - 'use --username and --password options to provide account credentials.', expected=True) + 'use --username and --password options to provide account credentials.', expected=True) login_form = { 'login-hint53': '1', diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index bebcafb62..07f514a46 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -1,4 +1,5 @@ # encoding: utf-8 +from __future__ import unicode_literals import json import re @@ -11,13 +12,14 @@ class SohuIE(InfoExtractor): _VALID_URL = r'https?://(?Pmy\.)?tv\.sohu\.com/.+?/(?(mytv)|n)(?P\d+)\.shtml.*?' _TEST = { - u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super', - u'file': u'382479172.mp4', - u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7', - u'info_dict': { - u'title': u'MV：Far East Movement《The Illest》', + 'url': 'http://tv.sohu.com/20130724/n382479172.shtml#super', + 'md5': 'bde8d9a6ffd82c63a1eefaef4eeefec7', + 'info_dict': { + 'id': '382479172', + 'ext': 'mp4', + 'title': 'MV：Far East Movement《The Illest》', }, - u'skip': u'Only available from China', + 'skip': 'Only available from China', } def _real_extract(self, url): @@ -26,11 +28,11 @@ class SohuIE(InfoExtractor): if mytv: base_data_url = 'http://my.tv.sohu.com/play/videonew.do?vid=' else: - base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid=' + base_data_url = 'http://hot.vrs.sohu.com/vrs_flash.action?vid=' data_url = base_data_url + str(vid_id) data_json = self._download_webpage( data_url, video_id, - note=u'Downloading JSON data for ' + str(vid_id)) + note='Downloading JSON data for ' + str(vid_id)) return json.loads(data_json) mobj = re.match(self._VALID_URL, url) @@ -39,11 +41,11 @@ class SohuIE(InfoExtractor): webpage = self._download_webpage(url, video_id) raw_title = self._html_search_regex(r'(?s)(.+?)', - webpage, u'video title') + webpage, 'video title') title = raw_title.partition('-')[0].strip() vid = self._html_search_regex(r'var vid ?= ?["\'](\d+)["\']', webpage, - u'video path') + 'video path') data = _fetch_data(vid, mytv) QUALITIES = ('ori', 'super', 'high', 'nor') @@ -51,7 +53,7 @@ class SohuIE(InfoExtractor): for q in QUALITIES if data['data'][q + 'Vid'] != 0] if not vid_ids: - raise ExtractorError(u'No formats available for this video') + raise ExtractorError('No formats available for this video') # For now, we just pick the highest available quality vid_id = vid_ids[-1] @@ -69,7 +71,7 @@ class SohuIE(InfoExtractor): (allot, prot, clipsURL[i], su[i])) part_str = self._download_webpage( part_url, video_id, - note=u'Downloading part %d of %d' % (i+1, part_count)) + note='Downloading part %d of %d' % (i + 1, part_count)) part_info = part_str.split('|') video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3]) diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index b78aed7f0..3c1d058db 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -31,7 +31,8 @@ class SoundcloudIE(InfoExtractor): (?!sets/|likes/?(?:$|[?#])) (?P[\w\d-]+)/? (?P<token>[^?]+?)?(?:[?].*)?$) - |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)) + |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+) + (?:/?\?secret_token=(?P<secret_token>[^&]+?))?$) |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*) ) ''' @@ -39,14 +40,15 @@ class SoundcloudIE(InfoExtractor): _TESTS = [ { 'url': 'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy', - 'file': '62986583.mp3', 'md5': 'ebef0a451b909710ed1d7787dddbf0d7', 'info_dict': { - "upload_date": "20121011", - "description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd", - "uploader": "E.T. ExTerrestrial Music", - "title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1", - "duration": 143, + 'id': '62986583', + 'ext': 'mp3', + 'upload_date': '20121011', + 'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d', + 'uploader': 'E.T. ExTerrestrial Music', + 'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1', + 'duration': 143, } }, # not streamable song @@ -80,6 +82,20 @@ class SoundcloudIE(InfoExtractor): 'duration': 9, }, }, + # private link (alt format) + { + 'url': 'https://api.soundcloud.com/tracks/123998367?secret_token=s-8Pjrp', + 'md5': 'aa0dd32bfea9b0c5ef4f02aacd080604', + 'info_dict': { + 'id': '123998367', + 'ext': 'mp3', + 'title': 'Youtube - Dl Test Video \'\' Ä↭', + 'uploader': 'jaimeMF', + 'description': 'test chars: \"\'/\\ä↭', + 'upload_date': '20131209', + 'duration': 9, + }, + }, # downloadable song { 'url': 'https://soundcloud.com/oddsamples/bus-brakes', @@ -88,7 +104,7 @@ class SoundcloudIE(InfoExtractor): 'id': '128590877', 'ext': 'mp3', 'title': 'Bus Brakes', - 'description': 'md5:0170be75dd395c96025d210d261c784e', + 'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66', 'uploader': 'oddsamples', 'upload_date': '20140109', 'duration': 17, @@ -125,6 +141,7 @@ class SoundcloudIE(InfoExtractor): 'description': info['description'], 'thumbnail': thumbnail, 'duration': int_or_none(info.get('duration'), 1000), + 'webpage_url': info.get('permalink_url'), } formats = [] if info.get('downloadable', False): @@ -142,7 +159,7 @@ class SoundcloudIE(InfoExtractor): # We have to retrieve the url streams_url = ('http://api.soundcloud.com/i1/tracks/{0}/streams?' - 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token)) + 'client_id={1}&secret_token={2}'.format(track_id, self._IPHONE_CLIENT_ID, secret_token)) format_dict = self._download_json( streams_url, track_id, 'Downloading track url') @@ -197,6 +214,9 @@ class SoundcloudIE(InfoExtractor): if track_id is not None: info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID full_title = track_id + token = mobj.group('secret_token') + if token: + info_json_url += "&secret_token=" + token elif mobj.group('player'): query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) return self.url_result(query['url'][0]) @@ -204,14 +224,14 @@ class SoundcloudIE(InfoExtractor): # extract uploader (which is in the url) uploader = mobj.group('uploader') # extract simple title (uploader + slug of song title) - slug_title = mobj.group('title') + slug_title = mobj.group('title') token = mobj.group('token') full_title = resolve_title = '%s/%s' % (uploader, slug_title) if token: resolve_title += '/%s' % token - + self.report_resolve(full_title) - + url = 'http://soundcloud.com/%s' % resolve_title info_json_url = self._resolv_url(url) info = self._download_json(info_json_url, full_title, 'Downloading info JSON') @@ -220,7 +240,7 @@ class SoundcloudIE(InfoExtractor): class SoundcloudSetIE(SoundcloudIE): - _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)' + _VALID_URL = r'https?://(?:www\.)?soundcloud\.com/(?P<uploader>[\w\d-]+)/sets/(?P<slug_title>[\w\d-]+)(?:/(?P<token>[^?/]+))?' IE_NAME = 'soundcloud:set' _TESTS = [{ 'url': 'https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep', @@ -234,14 +254,19 @@ class SoundcloudSetIE(SoundcloudIE): mobj = re.match(self._VALID_URL, url) # extract uploader (which is in the url) - uploader = mobj.group(1) + uploader = mobj.group('uploader') # extract simple title (uploader + slug of song title) - slug_title = mobj.group(2) + slug_title = mobj.group('slug_title') full_title = '%s/sets/%s' % (uploader, slug_title) + url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title) + + token = mobj.group('token') + if token: + full_title += '/' + token + url += '/' + token self.report_resolve(full_title) - url = 'http://soundcloud.com/%s/sets/%s' % (uploader, slug_title) resolv_url = self._resolv_url(url) info = self._download_json(resolv_url, full_title) @@ -252,7 +277,7 @@ class SoundcloudSetIE(SoundcloudIE): return { '_type': 'playlist', - 'entries': [self._extract_info_dict(track) for track in info['tracks']], + 'entries': [self._extract_info_dict(track, secret_token=token) for track in info['tracks']], 'id': info['id'], 'title': info['title'], } @@ -315,34 +340,38 @@ class SoundcloudUserIE(SoundcloudIE): class SoundcloudPlaylistIE(SoundcloudIE): - _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)' + _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$' IE_NAME = 'soundcloud:playlist' - _TESTS = [ - - { - 'url': 'http://api.soundcloud.com/playlists/4110309', - 'info_dict': { - 'id': '4110309', - 'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]', - 'description': 're:.*?TILT Brass - Bowery Poetry Club', - }, - 'playlist_count': 6, - } - ] + _TESTS = [{ + 'url': 'http://api.soundcloud.com/playlists/4110309', + 'info_dict': { + 'id': '4110309', + 'title': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]', + 'description': 're:.*?TILT Brass - Bowery Poetry Club', + }, + 'playlist_count': 6, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) playlist_id = mobj.group('id') base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id) - data = compat_urllib_parse.urlencode({ + data_dict = { 'client_id': self._CLIENT_ID, - }) + } + token = mobj.group('token') + + if token: + data_dict['secret_token'] = token + + data = compat_urllib_parse.urlencode(data_dict) data = self._download_json( base_url + data, playlist_id, 'Downloading playlist') entries = [ - self._extract_info_dict(t, quiet=True) for t in data['tracks']] + self._extract_info_dict(t, quiet=True, secret_token=token) + for t in data['tracks']] return { '_type': 'playlist', diff --git a/youtube_dl/extractor/space.py b/youtube_dl/extractor/space.py index d34aefeaa..c2d0d36a6 100644 --- a/youtube_dl/extractor/space.py +++ b/youtube_dl/extractor/space.py @@ -33,5 +33,6 @@ class SpaceIE(InfoExtractor): # Other videos works fine with the info from the object brightcove_url = BrightcoveIE._extract_brightcove_url(webpage) if brightcove_url is None: - raise ExtractorError(u'The webpage does not contain a video', expected=True) + raise ExtractorError( + 'The webpage does not contain a video', expected=True) return self.url_result(brightcove_url, BrightcoveIE.ie_key()) diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 2007a0013..94602e89e 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -9,7 +9,6 @@ from ..utils import ( compat_urllib_parse, unified_strdate, str_to_int, - int_or_none, ) from ..aes import aes_decrypt_text @@ -40,31 +39,42 @@ class SpankwireIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title') + title = self._html_search_regex( + r'<h1>([^<]+)', webpage, 'title') description = self._html_search_regex( - r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False) + r'<div\s+id="descriptionContent">([^<]+)<', + webpage, 'description', fatal=False) thumbnail = self._html_search_regex( - r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False) + r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']', + webpage, 'thumbnail', fatal=False) uploader = self._html_search_regex( - r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False) + r'by:\s*<a [^>]*>(.+?)</a>', + webpage, 'uploader', fatal=False) uploader_id = self._html_search_regex( - r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"', webpage, 'uploader id', fatal=False) - upload_date = self._html_search_regex(r'</a> on (.+?) at \d+:\d+', webpage, 'upload date', fatal=False) - if upload_date: - upload_date = unified_strdate(upload_date) - - view_count = self._html_search_regex( - r'<div id="viewsCounter"><span>([^<]+)</span> views</div>', webpage, 'view count', fatal=False) - if view_count: - view_count = str_to_int(view_count) - comment_count = int_or_none(self._html_search_regex( - r'<span id="spCommentCount">\s*(\d+)</span> Comments</div>', webpage, 'comment count', fatal=False)) + r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"', + webpage, 'uploader id', fatal=False) + upload_date = unified_strdate(self._html_search_regex( + r'</a> on (.+?) at \d+:\d+', + webpage, 'upload date', fatal=False)) - video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage))) + view_count = str_to_int(self._html_search_regex( + r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>', + webpage, 'view count', fatal=False)) + comment_count = str_to_int(self._html_search_regex( + r'Comments<span[^>]+>\s*\(([\d,\.]+)\)</span>', + webpage, 'comment count', fatal=False)) + + video_urls = list(map( + compat_urllib_parse.unquote, + re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage))) if webpage.find('flashvars\.encrypted = "true"') != -1: - password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ') - video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) + password = self._html_search_regex( + r'flashvars\.video_title = "([^"]+)', + webpage, 'password').replace('+', ' ') + video_urls = list(map( + lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), + video_urls)) formats = [] for video_url in video_urls: diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 9ed7d3b39..1e55a9ffb 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -4,11 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import compat_urlparse +from ..compat import compat_urlparse +from .spiegeltv import SpiegeltvIE class SpiegelIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$' + _VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<id>[0-9]+)(?:-embed)?(?:\.html)?(?:#.*)?$' _TESTS = [{ 'url': 'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html', 'md5': '2c2754212136f35fb4b19767d242f66e', @@ -29,16 +30,28 @@ class SpiegelIE(InfoExtractor): 'description': 'md5:c2322b65e58f385a820c10fa03b2d088', 'duration': 983, }, + }, { + 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-embed.html', + 'md5': 'd8eeca6bfc8f1cd6f490eb1f44695d51', + 'info_dict': { + 'id': '1519126', + 'ext': 'mp4', + 'description': 'SPIEGEL ONLINE-Nutzer durften den deutschen Astronauten Alexander Gerst über sein Leben auf der ISS-Station befragen. Hier kommen seine Antworten auf die besten sechs Fragen.', + 'title': 'Fragen an Astronaut Alexander Gerst: "Bekommen Sie die Tageszeiten mit?"', + } }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('videoID') + video_id = self._match_id(url) + webpage, handle = self._download_webpage_handle(url, video_id) - webpage = self._download_webpage(url, video_id) + # 302 to spiegel.tv, like http://www.spiegel.de/video/der-film-zum-wochenende-die-wahrheit-ueber-maenner-video-99003272.html + if SpiegeltvIE.suitable(handle.geturl()): + return self.url_result(handle.geturl(), 'Spiegeltv') - title = self._html_search_regex( - r'<div class="module-title">(.*?)</div>', webpage, 'title') + title = re.sub(r'\s+', ' ', self._html_search_regex( + r'(?s)<(?:h1|div) class="module-title"[^>]*>(.*?)</(?:h1|div)>', + webpage, 'title')) description = self._html_search_meta('description', webpage, 'description') base_url = self._search_regex( @@ -79,7 +92,7 @@ class SpiegelArticleIE(InfoExtractor): _VALID_URL = 'https?://www\.spiegel\.de/(?!video/)[^?#]*?-(?P<id>[0-9]+)\.html' IE_NAME = 'Spiegel:Article' IE_DESC = 'Articles on spiegel.de' - _TEST = { + _TESTS = [{ 'url': 'http://www.spiegel.de/sport/sonst/badminton-wm-die-randsportart-soll-populaerer-werden-a-987092.html', 'info_dict': { 'id': '1516455', @@ -87,20 +100,34 @@ class SpiegelArticleIE(InfoExtractor): 'title': 'Faszination Badminton: Nennt es bloß nicht Federball', 'description': 're:^Patrick Kämnitz gehört.{100,}', }, - } + }, { + 'url': 'http://www.spiegel.de/wissenschaft/weltall/astronaut-alexander-gerst-antwortet-spiegel-online-lesern-a-989876.html', + 'info_dict': { + + }, + 'playlist_count': 6, + }] def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + + # Single video on top of the page video_link = self._search_regex( r'<a href="([^"]+)" onclick="return spOpenVideo\(this,', webpage, - 'video page URL') - video_url = compat_urlparse.urljoin( - self.http_scheme() + '//spiegel.de/', video_link) + 'video page URL', default=None) + if video_link: + video_url = compat_urlparse.urljoin( + self.http_scheme() + '//spiegel.de/', video_link) + return self.url_result(video_url) - return { - '_type': 'url', - 'url': video_url, - } + # Multiple embedded videos + embeds = re.findall( + r'<div class="vid_holder[0-9]+.*?</div>\s*.*?url\s*=\s*"([^"]+)"', + webpage) + entries = [ + self.url_result(compat_urlparse.urljoin( + self.http_scheme() + '//spiegel.de/', embed_path)) + for embed_path in embeds + ] + return self.playlist_result(entries) diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py index 7f388aced..98cf92d89 100644 --- a/youtube_dl/extractor/spiegeltv.py +++ b/youtube_dl/extractor/spiegeltv.py @@ -1,13 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals -import re from .common import InfoExtractor +from ..utils import float_or_none class SpiegeltvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/filme/(?P<id>[\-a-z0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?spiegel\.tv/(?:#/)?filme/(?P<id>[\-a-z0-9]+)' + _TESTS = [{ 'url': 'http://www.spiegel.tv/filme/flug-mh370/', 'info_dict': { 'id': 'flug-mh370', @@ -20,12 +20,15 @@ class SpiegeltvIE(InfoExtractor): # rtmp download 'skip_download': True, } - } + }, { + 'url': 'http://www.spiegel.tv/#/filme/alleskino-die-wahrheit-ueber-maenner/', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - + if '/#/' in url: + url = url.replace('/#/', '/') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'<h1.*?>(.*?)</h1>', webpage, 'title') @@ -61,12 +64,8 @@ class SpiegeltvIE(InfoExtractor): }) description = media_json['subtitle'] - duration = media_json['duration_in_ms'] / 1000. - - if is_wide: - format = '16x9' - else: - format = '4x3' + duration = float_or_none(media_json.get('duration_in_ms'), scale=1000) + format = '16x9' if is_wide else '4x3' url = server + 'mp4:' + uuid + '_spiegeltv_0500_' + format + '.m4v' @@ -78,4 +77,4 @@ class SpiegeltvIE(InfoExtractor): 'description': description, 'duration': duration, 'thumbnails': thumbnails - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/sport5.py b/youtube_dl/extractor/sport5.py new file mode 100644 index 000000000..dfe50ed45 --- /dev/null +++ b/youtube_dl/extractor/sport5.py @@ -0,0 +1,92 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class Sport5IE(InfoExtractor): + _VALID_URL = r'http://(?:www|vod)?\.sport5\.co\.il/.*\b(?:Vi|docID)=(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://vod.sport5.co.il/?Vc=147&Vi=176331&Page=1', + 'info_dict': { + 'id': 's5-Y59xx1-GUh2', + 'ext': 'mp4', + 'title': 'ולנסיה-קורדובה 0:3', + 'description': 'אלקאסר, גאייה ופגולי סידרו לקבוצה של נונו ניצחון על קורדובה ואת המקום הראשון בליגה', + 'duration': 228, + 'categories': list, + }, + 'skip': 'Blocked outside of Israel', + }, { + 'url': 'http://www.sport5.co.il/articles.aspx?FolderID=3075&docID=176372&lang=HE', + 'info_dict': { + 'id': 's5-SiXxx1-hKh2', + 'ext': 'mp4', + 'title': 'GOALS_CELTIC_270914.mp4', + 'description': '', + 'duration': 87, + 'categories': list, + }, + 'skip': 'Blocked outside of Israel', + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + media_id = mobj.group('id') + + webpage = self._download_webpage(url, media_id) + + video_id = self._html_search_regex('clipId=([\w-]+)', webpage, 'video id') + + metadata = self._download_xml( + 'http://sport5-metadata-rr-d.nsacdn.com/vod/vod/%s/HDS/metadata.xml' % video_id, + video_id) + + error = metadata.find('./Error') + if error is not None: + raise ExtractorError( + '%s returned error: %s - %s' % ( + self.IE_NAME, + error.find('./Name').text, + error.find('./Description').text), + expected=True) + + title = metadata.find('./Title').text + description = metadata.find('./Description').text + duration = int(metadata.find('./Duration').text) + + posters_el = metadata.find('./PosterLinks') + thumbnails = [{ + 'url': thumbnail.text, + 'width': int(thumbnail.get('width')), + 'height': int(thumbnail.get('height')), + } for thumbnail in posters_el.findall('./PosterIMG')] if posters_el is not None else [] + + categories_el = metadata.find('./Categories') + categories = [ + cat.get('name') for cat in categories_el.findall('./Category') + ] if categories_el is not None else [] + + formats = [{ + 'url': fmt.text, + 'ext': 'mp4', + 'vbr': int(fmt.get('bitrate')), + 'width': int(fmt.get('width')), + 'height': int(fmt.get('height')), + } for fmt in metadata.findall('./PlaybackLinks/FileURL')] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnails': thumbnails, + 'duration': duration, + 'categories': categories, + 'formats': formats, + } diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py new file mode 100644 index 000000000..becdf658f --- /dev/null +++ b/youtube_dl/extractor/sportbox.py @@ -0,0 +1,76 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, +) + + +class SportBoxIE(InfoExtractor): + _VALID_URL = r'https?://news\.sportbox\.ru/Vidy_sporta/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)' + _TESTS = [ + { + 'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S', + 'md5': 'ff56a598c2cf411a9a38a69709e97079', + 'info_dict': { + 'id': '80822', + 'ext': 'mp4', + 'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн', + 'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1411896237, + 'upload_date': '20140928', + 'duration': 4846, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4', + 'only_matching': True, + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'src="/vdl/player/media/(\d+)"', webpage, 'video id') + + player = self._download_webpage( + 'http://news.sportbox.ru/vdl/player/media/%s' % video_id, + display_id, 'Downloading player webpage') + + hls = self._search_regex( + r"var\s+original_hls_file\s*=\s*'([^']+)'", player, 'hls file') + + formats = self._extract_m3u8_formats(hls, display_id, 'mp4') + + title = self._html_search_regex( + r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title') + description = self._html_search_regex( + r'(?s)<div itemprop="description">(.+?)</div>', webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + timestamp = parse_iso8601(self._search_regex( + r'<span itemprop="uploadDate">([^<]+)</span>', webpage, 'timestamp', fatal=False)) + duration = parse_duration(self._html_search_regex( + r'<meta itemprop="duration" content="PT([^"]+)">', webpage, 'duration', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/sportdeutschland.py b/youtube_dl/extractor/sportdeutschland.py index 185353bef..057ef5251 100644 --- a/youtube_dl/extractor/sportdeutschland.py +++ b/youtube_dl/extractor/sportdeutschland.py @@ -17,11 +17,11 @@ class SportDeutschlandIE(InfoExtractor): 'info_dict': { 'id': 'live-li-ning-badminton-weltmeisterschaft-2014-kopenhagen', 'ext': 'mp4', - 'title': 'LIVE: Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', + 'title': 're:Li-Ning Badminton Weltmeisterschaft 2014 Kopenhagen', 'categories': ['Badminton'], 'view_count': int, 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 're:^Die Badminton-WM 2014 aus Kopenhagen LIVE', + 'description': 're:Die Badminton-WM 2014 aus Kopenhagen bei Sportdeutschland\.TV', 'timestamp': int, 'upload_date': 're:^201408[23][0-9]$', }, @@ -93,4 +93,3 @@ class SportDeutschlandIE(InfoExtractor): 'rtmp_live': asset.get('live'), 'timestamp': parse_iso8601(asset.get('date')), } - diff --git a/youtube_dl/extractor/srmediathek.py b/youtube_dl/extractor/srmediathek.py new file mode 100644 index 000000000..666a7dcc8 --- /dev/null +++ b/youtube_dl/extractor/srmediathek.py @@ -0,0 +1,43 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import js_to_json + + +class SRMediathekIE(InfoExtractor): + IE_DESC = 'Süddeutscher Rundfunk' + _VALID_URL = r'https?://sr-mediathek\.sr-online\.de/index\.php\?.*?&id=(?P<id>[0-9]+)' + + _TEST = { + 'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455', + 'info_dict': { + 'id': '28455', + 'ext': 'mp4', + 'title': 'sportarena (26.10.2014)', + 'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + murls = json.loads(js_to_json(self._search_regex( + r'var mediaURLs\s*=\s*(.*?);\n', webpage, 'video URLs'))) + formats = [{'url': murl} for murl in murls] + self._sort_formats(formats) + + title = json.loads(js_to_json(self._search_regex( + r'var mediaTitles\s*=\s*(.*?);\n', webpage, 'title')))[0] + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/stanfordoc.py b/youtube_dl/extractor/stanfordoc.py index 44c52c718..4a3d8bb8f 100644 --- a/youtube_dl/extractor/stanfordoc.py +++ b/youtube_dl/extractor/stanfordoc.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -9,24 +11,23 @@ from ..utils import ( class StanfordOpenClassroomIE(InfoExtractor): - IE_NAME = u'stanfordoc' - IE_DESC = u'Stanford Open ClassRoom' - _VALID_URL = r'^(?:https?://)?openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' + IE_NAME = 'stanfordoc' + IE_DESC = 'Stanford Open ClassRoom' + _VALID_URL = r'https?://openclassroom\.stanford\.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$' _TEST = { - u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100', - u'file': u'PracticalUnix_intro-environment.mp4', - u'md5': u'544a9468546059d4e80d76265b0443b8', - u'info_dict': { - u"title": u"Intro Environment" + 'url': 'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100', + 'md5': '544a9468546059d4e80d76265b0443b8', + 'info_dict': { + 'id': 'PracticalUnix_intro-environment', + 'ext': 'mp4', + 'title': 'Intro Environment', } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - if mobj.group('course') and mobj.group('video'): # A specific video + if mobj.group('course') and mobj.group('video'): # A specific video course = mobj.group('course') video = mobj.group('video') info = { @@ -35,7 +36,6 @@ class StanfordOpenClassroomIE(InfoExtractor): 'upload_date': None, } - self.report_extraction(info['id']) baseUrl = 'http://openclassroom.stanford.edu/MainFolder/courses/' + course + '/videos/' xmlUrl = baseUrl + video + '.xml' mdoc = self._download_xml(xmlUrl, info['id']) @@ -43,63 +43,49 @@ class StanfordOpenClassroomIE(InfoExtractor): info['title'] = mdoc.findall('./title')[0].text info['url'] = baseUrl + mdoc.findall('./videoFile')[0].text except IndexError: - raise ExtractorError(u'Invalid metadata XML file') - info['ext'] = info['url'].rpartition('.')[2] - return [info] - elif mobj.group('course'): # A course page + raise ExtractorError('Invalid metadata XML file') + return info + elif mobj.group('course'): # A course page course = mobj.group('course') info = { 'id': course, - 'type': 'playlist', + '_type': 'playlist', 'uploader': None, 'upload_date': None, } - coursepage = self._download_webpage(url, info['id'], - note='Downloading course info page', - errnote='Unable to download course info page') + coursepage = self._download_webpage( + url, info['id'], + note='Downloading course info page', + errnote='Unable to download course info page') - info['title'] = self._html_search_regex('<h1>([^<]+)</h1>', coursepage, 'title', default=info['id']) + info['title'] = self._html_search_regex( + r'<h1>([^<]+)</h1>', coursepage, 'title', default=info['id']) - info['description'] = self._html_search_regex('<description>([^<]+)</description>', - coursepage, u'description', fatal=False) + info['description'] = self._html_search_regex( + r'(?s)<description>([^<]+)</description>', + coursepage, 'description', fatal=False) links = orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) - info['list'] = [ - { - 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), - } - for vpage in links] - results = [] - for entry in info['list']: - assert entry['type'] == 'reference' - results += self.extract(entry['url']) - return results - else: # Root page + info['entries'] = [self.url_result( + 'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l) + ) for l in links] + return info + else: # Root page info = { 'id': 'Stanford OpenClassroom', - 'type': 'playlist', + '_type': 'playlist', 'uploader': None, 'upload_date': None, } + info['title'] = info['id'] rootURL = 'http://openclassroom.stanford.edu/MainFolder/HomePage.php' rootpage = self._download_webpage(rootURL, info['id'], - errnote=u'Unable to download course info page') - - info['title'] = info['id'] + errnote='Unable to download course info page') links = orderedSet(re.findall('<a href="(CoursePage.php\?[^"]+)">', rootpage)) - info['list'] = [ - { - 'type': 'reference', - 'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), - } - for cpage in links] - - results = [] - for entry in info['list']: - assert entry['type'] == 'reference' - results += self.extract(entry['url']) - return results + info['entries'] = [self.url_result( + 'http://openclassroom.stanford.edu/MainFolder/%s' % unescapeHTML(l) + ) for l in links] + return info diff --git a/youtube_dl/extractor/streamcloud.py b/youtube_dl/extractor/streamcloud.py index 172def221..c1178f26d 100644 --- a/youtube_dl/extractor/streamcloud.py +++ b/youtube_dl/extractor/streamcloud.py @@ -13,7 +13,7 @@ from ..utils import ( class StreamcloudIE(InfoExtractor): IE_NAME = 'streamcloud.eu' - _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)/(?P<fname>[^#?]*)\.html' + _VALID_URL = r'https?://streamcloud\.eu/(?P<id>[a-zA-Z0-9_-]+)(?:/(?P<fname>[^#?]*)\.html)?' _TEST = { 'url': 'http://streamcloud.eu/skp9j99s4bpz/youtube-dl_test_video_____________-BaW_jenozKc.mp4.html', @@ -27,8 +27,8 @@ class StreamcloudIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + url = 'http://streamcloud.eu/%s' % video_id orig_webpage = self._download_webpage(url, video_id) diff --git a/youtube_dl/extractor/subtitles.py b/youtube_dl/extractor/subtitles.py index db33745c1..59a51268d 100644 --- a/youtube_dl/extractor/subtitles.py +++ b/youtube_dl/extractor/subtitles.py @@ -1,7 +1,8 @@ +from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( - compat_str, ExtractorError, ) @@ -17,10 +18,10 @@ class SubtitlesInfoExtractor(InfoExtractor): sub_lang_list = self._get_available_subtitles(video_id, webpage) auto_captions_list = self._get_available_automatic_caption(video_id, webpage) sub_lang = ",".join(list(sub_lang_list.keys())) - self.to_screen(u'%s: Available subtitles for video: %s' % + self.to_screen('%s: Available subtitles for video: %s' % (video_id, sub_lang)) auto_lang = ",".join(auto_captions_list.keys()) - self.to_screen(u'%s: Available automatic captions for video: %s' % + self.to_screen('%s: Available automatic captions for video: %s' % (video_id, auto_lang)) def extract_subtitles(self, video_id, webpage): @@ -50,8 +51,8 @@ class SubtitlesInfoExtractor(InfoExtractor): sub_lang_list = {} for sub_lang in requested_langs: - if not sub_lang in available_subs_list: - self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang) + if sub_lang not in available_subs_list: + self._downloader.report_warning('no closed captions found in the specified language "%s"' % sub_lang) continue sub_lang_list[sub_lang] = available_subs_list[sub_lang] @@ -70,10 +71,10 @@ class SubtitlesInfoExtractor(InfoExtractor): try: sub = self._download_subtitle_url(sub_lang, url) except ExtractorError as err: - self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err))) + self._downloader.report_warning('unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err))) return if not sub: - self._downloader.report_warning(u'Did not fetch video subtitles') + self._downloader.report_warning('Did not fetch video subtitles') return return sub @@ -94,5 +95,5 @@ class SubtitlesInfoExtractor(InfoExtractor): Must be redefined by the subclasses that support automatic captions, otherwise it will return {} """ - self._downloader.report_warning(u'Automatic Captions not supported by this server') + self._downloader.report_warning('Automatic Captions not supported by this server') return {} diff --git a/youtube_dl/extractor/sunporno.py b/youtube_dl/extractor/sunporno.py index 7de3c9dd5..263f09b46 100644 --- a/youtube_dl/extractor/sunporno.py +++ b/youtube_dl/extractor/sunporno.py @@ -39,10 +39,10 @@ class SunPornoIE(InfoExtractor): r'poster="([^"]+)"', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._search_regex( - r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False)) + r'Duration:\s*(\d+:\d+)\s*<', webpage, 'duration', fatal=False)) view_count = int_or_none(self._html_search_regex( - r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False)) + r'class="views">\s*(\d+)\s*<', webpage, 'view count', fatal=False)) comment_count = int_or_none(self._html_search_regex( r'(\d+)</b> Comments?', webpage, 'comment count', fatal=False)) diff --git a/youtube_dl/extractor/swrmediathek.py b/youtube_dl/extractor/swrmediathek.py index 13c6ea677..58073eefe 100644 --- a/youtube_dl/extractor/swrmediathek.py +++ b/youtube_dl/extractor/swrmediathek.py @@ -80,7 +80,7 @@ class SWRMediathekIE(InfoExtractor): if media_type == 'Video': fmt.update({ - 'format_note': ['144p', '288p', '544p'][quality-1], + 'format_note': ['144p', '288p', '544p', '720p'][quality - 1], 'vcodec': codec, }) elif media_type == 'Audio': @@ -101,4 +101,4 @@ class SWRMediathekIE(InfoExtractor): 'uploader': attr['channel_title'], 'uploader_id': attr['channel_idkey'], 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/syfy.py b/youtube_dl/extractor/syfy.py index f76b6e2b2..5ca079f88 100644 --- a/youtube_dl/extractor/syfy.py +++ b/youtube_dl/extractor/syfy.py @@ -10,7 +10,6 @@ class SyfyIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.syfy.com/videos/Robot%20Combat%20League/Behind%20the%20Scenes/vid:2631458', - 'md5': 'e07de1d52c7278adbb9b9b1c93a66849', 'info_dict': { 'id': 'NmqMrGnXvmO1', 'ext': 'flv', diff --git a/youtube_dl/extractor/sztvhu.py b/youtube_dl/extractor/sztvhu.py index c9359fafb..aa5964acb 100644 --- a/youtube_dl/extractor/sztvhu.py +++ b/youtube_dl/extractor/sztvhu.py @@ -1,27 +1,24 @@ # -*- coding: utf-8 -*- - -import re +from __future__ import unicode_literals from .common import InfoExtractor -from ..utils import determine_ext class SztvHuIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)' + _VALID_URL = r'http://(?:(?:www\.)?sztv\.hu|www\.tvszombathely\.hu)/(?:[^/]+)/.+-(?P<id>[0-9]+)' _TEST = { - u'url': u'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909', - u'file': u'20130909.mp4', - u'md5': u'a6df607b11fb07d0e9f2ad94613375cb', - u'info_dict': { - u"title": u"Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren", - u"description": u'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...', + 'url': 'http://sztv.hu/hirek/cserkeszek-nepszerusitettek-a-kornyezettudatos-eletmodot-a-savaria-teren-20130909', + 'md5': 'a6df607b11fb07d0e9f2ad94613375cb', + 'info_dict': { + 'id': '20130909', + 'ext': 'mp4', + 'title': 'Cserkészek népszerűsítették a környezettudatos életmódot a Savaria téren', + 'description': 'A zöld nap játékos ismeretterjesztő programjait a Magyar Cserkész Szövetség szervezte, akik az ország nyolc városában adják át tudásukat az érdeklődőknek. A PET...', }, - u'skip': u'Service temporarily disabled as of 2013-11-20' } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) video_file = self._search_regex( r'file: "...:(.*?)",', webpage, 'video file') @@ -39,7 +36,6 @@ class SztvHuIE(InfoExtractor): 'id': video_id, 'url': video_url, 'title': title, - 'ext': determine_ext(video_url), 'description': description, 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/tapely.py b/youtube_dl/extractor/tapely.py new file mode 100644 index 000000000..283e11350 --- /dev/null +++ b/youtube_dl/extractor/tapely.py @@ -0,0 +1,105 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + clean_html, + compat_urllib_request, + float_or_none, + parse_iso8601, +) + + +class TapelyIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tape\.ly/(?P<id>[A-Za-z0-9\-_]+)(?:/(?P<songnr>\d+))?' + _API_URL = 'http://tape.ly/showtape?id={0:}' + _S3_SONG_URL = 'http://mytape.s3.amazonaws.com/{0:}' + _SOUNDCLOUD_SONG_URL = 'http://api.soundcloud.com{0:}' + _TESTS = [ + { + 'url': 'http://tape.ly/my-grief-as-told-by-water', + 'info_dict': { + 'id': 23952, + 'title': 'my grief as told by water', + 'thumbnail': 're:^https?://.*\.png$', + 'uploader_id': 16484, + 'timestamp': 1411848286, + 'description': 'For Robin and Ponkers, whom the tides of life have taken out to sea.', + }, + 'playlist_count': 13, + }, + { + 'url': 'http://tape.ly/my-grief-as-told-by-water/1', + 'md5': '79031f459fdec6530663b854cbc5715c', + 'info_dict': { + 'id': 258464, + 'title': 'Dreaming Awake (My Brightest Diamond)', + 'ext': 'm4a', + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + + playlist_url = self._API_URL.format(display_id) + request = compat_urllib_request.Request(playlist_url) + request.add_header('X-Requested-With', 'XMLHttpRequest') + request.add_header('Accept', 'application/json') + request.add_header('Referer', url) + + playlist = self._download_json(request, display_id) + + tape = playlist['tape'] + + entries = [] + for s in tape['songs']: + song = s['song'] + entry = { + 'id': song['id'], + 'duration': float_or_none(song.get('songduration'), 1000), + 'title': song['title'], + } + if song['source'] == 'S3': + entry.update({ + 'url': self._S3_SONG_URL.format(song['filename']), + }) + entries.append(entry) + elif song['source'] == 'YT': + self.to_screen('YouTube video detected') + yt_id = song['filename'].replace('/youtube/', '') + entry.update(self.url_result(yt_id, 'Youtube', video_id=yt_id)) + entries.append(entry) + elif song['source'] == 'SC': + self.to_screen('SoundCloud song detected') + sc_url = self._SOUNDCLOUD_SONG_URL.format(song['filename']) + entry.update(self.url_result(sc_url, 'Soundcloud')) + entries.append(entry) + else: + self.report_warning('Unknown song source: %s' % song['source']) + + if mobj.group('songnr'): + songnr = int(mobj.group('songnr')) - 1 + try: + return entries[songnr] + except IndexError: + raise ExtractorError( + 'No song with index: %s' % mobj.group('songnr'), + expected=True) + + return { + '_type': 'playlist', + 'id': tape['id'], + 'display_id': display_id, + 'title': tape['name'], + 'entries': entries, + 'thumbnail': tape.get('image_url'), + 'description': clean_html(tape.get('subtext')), + 'like_count': tape.get('likescount'), + 'uploader_id': tape.get('user_id'), + 'timestamp': parse_iso8601(tape.get('published_at')), + } diff --git a/youtube_dl/extractor/tass.py b/youtube_dl/extractor/tass.py new file mode 100644 index 000000000..c4ef70778 --- /dev/null +++ b/youtube_dl/extractor/tass.py @@ -0,0 +1,62 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import json + +from .common import InfoExtractor +from ..utils import ( + js_to_json, + qualities, +) + + +class TassIE(InfoExtractor): + _VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P<id>\d+)' + _TESTS = [ + { + 'url': 'http://tass.ru/obschestvo/1586870', + 'md5': '3b4cdd011bc59174596b6145cda474a4', + 'info_dict': { + 'id': '1586870', + 'ext': 'mp4', + 'title': 'Посетителям московского зоопарка показали красную панду', + 'description': 'Приехавшую из Дублина Зейну можно увидеть в павильоне "Кошки тропиков"', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }, + { + 'url': 'http://itar-tass.com/obschestvo/1600009', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + sources = json.loads(js_to_json(self._search_regex( + r'(?s)sources\s*:\s*(\[.+?\])', webpage, 'sources'))) + + quality = qualities(['sd', 'hd']) + + formats = [] + for source in sources: + video_url = source.get('file') + if not video_url or not video_url.startswith('http') or not video_url.endswith('.mp4'): + continue + label = source.get('label') + formats.append({ + 'url': video_url, + 'format_id': label, + 'quality': quality(label), + }) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + 'formats': formats, + } diff --git a/youtube_dl/extractor/teachertube.py b/youtube_dl/extractor/teachertube.py index 8a95fd656..6c3445d79 100644 --- a/youtube_dl/extractor/teachertube.py +++ b/youtube_dl/extractor/teachertube.py @@ -121,7 +121,7 @@ class TeacherTubeUserIE(InfoExtractor): urls = [] webpage = self._download_webpage(url, user_id) urls.extend(re.findall(self._MEDIA_RE, webpage)) - + pages = re.findall(r'/ajax-user/user-videos/%s\?page=([0-9]+)' % user_id, webpage)[:-1] for p in pages: more = 'http://www.teachertube.com/ajax-user/user-videos/%s?page=%s' % (user_id, p) diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index fa796ce72..5fa67eb8d 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -8,24 +8,23 @@ from .common import InfoExtractor class TeamcocoIE(InfoExtractor): _VALID_URL = r'http://teamcoco\.com/video/(?P<video_id>[0-9]+)?/?(?P<display_id>.*)' _TESTS = [ - { - 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant', - 'file': '80187.mp4', - 'md5': '3f7746aa0dc86de18df7539903d399ea', - 'info_dict': { - 'title': 'Conan Becomes A Mary Kay Beauty Consultant', - 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.' + { + 'url': 'http://teamcoco.com/video/80187/conan-becomes-a-mary-kay-beauty-consultant', + 'file': '80187.mp4', + 'md5': '3f7746aa0dc86de18df7539903d399ea', + 'info_dict': { + 'title': 'Conan Becomes A Mary Kay Beauty Consultant', + 'description': 'Mary Kay is perhaps the most trusted name in female beauty, so of course Conan is a natural choice to sell their products.' + } + }, { + 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush', + 'file': '19705.mp4', + 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a', + 'info_dict': { + "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.", + "title": "Louis C.K. Interview Pt. 1 11/3/11" + } } - }, - { - 'url': 'http://teamcoco.com/video/louis-ck-interview-george-w-bush', - 'file': '19705.mp4', - 'md5': 'cde9ba0fa3506f5f017ce11ead928f9a', - 'info_dict': { - "description": "Louis C.K. got starstruck by George W. Bush, so what? Part one.", - "title": "Louis C.K. Interview Pt. 1 11/3/11" - } - } ] def _real_extract(self, url): @@ -33,7 +32,7 @@ class TeamcocoIE(InfoExtractor): display_id = mobj.group('display_id') webpage = self._download_webpage(url, display_id) - + video_id = mobj.group("video_id") if not video_id: video_id = self._html_search_regex( diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py index 1cca47771..f8a87afda 100644 --- a/youtube_dl/extractor/ted.py +++ b/youtube_dl/extractor/ted.py @@ -33,11 +33,12 @@ class TEDIE(SubtitlesInfoExtractor): 'ext': 'mp4', 'title': 'The illusion of consciousness', 'description': ('Philosopher Dan Dennett makes a compelling ' - 'argument that not only don\'t we understand our own ' - 'consciousness, but that half the time our brains are ' - 'actively fooling us.'), + 'argument that not only don\'t we understand our own ' + 'consciousness, but that half the time our brains are ' + 'actively fooling us.'), 'uploader': 'Dan Dennett', 'width': 854, + 'duration': 1308, } }, { 'url': 'http://www.ted.com/watch/ted-institute/ted-bcg/vishal-sikka-the-beauty-and-power-of-algorithms', @@ -57,6 +58,7 @@ class TEDIE(SubtitlesInfoExtractor): 'title': 'Be passionate. Be courageous. Be your best.', 'uploader': 'Gabby Giffords and Mark Kelly', 'description': 'md5:5174aed4d0f16021b704120360f72b92', + 'duration': 1128, }, }, { 'url': 'http://www.ted.com/playlists/who_are_the_hackers', @@ -65,6 +67,22 @@ class TEDIE(SubtitlesInfoExtractor): 'title': 'Who are the hackers?', }, 'playlist_mincount': 6, + }, { + # contains a youtube video + 'url': 'https://www.ted.com/talks/douglas_adams_parrots_the_universe_and_everything', + 'add_ie': ['Youtube'], + 'info_dict': { + 'id': '_ZG8HBuDjgc', + 'ext': 'mp4', + 'title': 'Douglas Adams: Parrots the Universe and Everything', + 'description': 'md5:01ad1e199c49ac640cb1196c0e9016af', + 'uploader': 'University of California Television (UCTV)', + 'uploader_id': 'UCtelevision', + 'upload_date': '20080522', + }, + 'params': { + 'skip_download': True, + }, }] _NATIVE_FORMATS = { @@ -75,7 +93,7 @@ class TEDIE(SubtitlesInfoExtractor): def _extract_info(self, webpage): info_json = self._search_regex(r'q\("\w+.init",({.+})\)</script>', - webpage, 'info json') + webpage, 'info json') return json.loads(info_json) def _real_extract(self, url): @@ -95,7 +113,7 @@ class TEDIE(SubtitlesInfoExtractor): '''Returns the videos of the playlist''' webpage = self._download_webpage(url, name, - 'Downloading playlist webpage') + 'Downloading playlist webpage') info = self._extract_info(webpage) playlist_info = info['playlist'] @@ -114,6 +132,13 @@ class TEDIE(SubtitlesInfoExtractor): talk_info = self._extract_info(webpage)['talks'][0] + if talk_info.get('external') is not None: + self.to_screen('Found video from %s' % talk_info['external']['service']) + return { + '_type': 'url', + 'url': talk_info['external']['uri'], + } + formats = [{ 'url': format_url, 'format_id': format_id, @@ -149,12 +174,13 @@ class TEDIE(SubtitlesInfoExtractor): thumbnail = 'http://' + thumbnail return { 'id': video_id, - 'title': talk_info['title'], + 'title': talk_info['title'].strip(), 'uploader': talk_info['speaker'], 'thumbnail': thumbnail, 'description': self._og_search_description(webpage), 'subtitles': video_subtitles, 'formats': formats, + 'duration': talk_info.get('duration'), } def _get_available_subtitles(self, video_id, talk_info): diff --git a/youtube_dl/extractor/telebruxelles.py b/youtube_dl/extractor/telebruxelles.py new file mode 100644 index 000000000..a3d05f97d --- /dev/null +++ b/youtube_dl/extractor/telebruxelles.py @@ -0,0 +1,60 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TeleBruxellesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)' + _TESTS = [{ + 'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/', + 'md5': '59439e568c9ee42fb77588b2096b214f', + 'info_dict': { + 'id': '11942', + 'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus', + 'ext': 'flv', + 'title': 'Parlement : Francken et Galant répondent aux interpellations de l’opposition', + 'description': 're:Les auditions des ministres se poursuivent*' + }, + 'params': { + 'skip_download': 'requires rtmpdump' + }, + }, { + 'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/', + 'md5': '181d3fbdcf20b909309e5aef5c6c6047', + 'info_dict': { + 'id': '10091', + 'display_id': 'basket-brussels-bat-mons-80-74', + 'ext': 'flv', + 'title': 'Basket : le Brussels bat Mons 80-74', + 'description': 're:^Ils l\u2019on fait ! En basket, le B*', + }, + 'params': { + 'skip_download': 'requires rtmpdump' + }, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + + article_id = self._html_search_regex( + r"<article id=\"post-(\d+)\"", webpage, 'article ID') + title = self._html_search_regex( + r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title') + description = self._og_search_description(webpage) + + rtmp_url = self._html_search_regex( + r"file: \"(rtmp://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}/vod/mp4:\" \+ \"\w+\" \+ \".mp4)\"", + webpage, 'RTMP url') + rtmp_url = rtmp_url.replace("\" + \"", "") + + return { + 'id': article_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'url': rtmp_url, + 'ext': 'flv', + 'rtmp_live': True # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed + } diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py new file mode 100644 index 000000000..2a2fff5e1 --- /dev/null +++ b/youtube_dl/extractor/telecinco.py @@ -0,0 +1,19 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .mitele import MiTeleIE + + +class TelecincoIE(MiTeleIE): + IE_NAME = 'telecinco.es' + _VALID_URL = r'https?://www\.telecinco\.es/[^/]+/[^/]+/[^/]+/(?P<episode>.*?)\.html' + + _TEST = { + 'url': 'http://www.telecinco.es/robinfood/temporada-01/t01xp14/Bacalao-cocochas-pil-pil_0_1876350223.html', + 'info_dict': { + 'id': 'MDSVID20141015_0058', + 'ext': 'mp4', + 'title': 'Con Martín Berasategui, hacer un bacalao al ...', + 'duration': 662, + }, + } diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index fdae17b1b..6e61cc9e2 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -30,7 +30,7 @@ class TF1IE(InfoExtractor): embed_url = self._html_search_regex( r'"(https://www.wat.tv/embedframe/.*?)"', webpage, 'embed url') embed_page = self._download_webpage(embed_url, video_id, - 'Downloading embed player page') + 'Downloading embed player page') wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id') wat_info = self._download_json( 'http://www.wat.tv/interface/contentv3/%s' % wat_id, video_id) diff --git a/youtube_dl/extractor/theonion.py b/youtube_dl/extractor/theonion.py new file mode 100644 index 000000000..b65d8e03f --- /dev/null +++ b/youtube_dl/extractor/theonion.py @@ -0,0 +1,70 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class TheOnionIE(InfoExtractor): + _VALID_URL = r'(?x)https?://(?:www\.)?theonion\.com/video/[^,]+,(?P<article_id>[0-9]+)/?' + _TEST = { + 'url': 'http://www.theonion.com/video/man-wearing-mm-jacket-gods-image,36918/', + 'md5': '19eaa9a39cf9b9804d982e654dc791ee', + 'info_dict': { + 'id': '2133', + 'ext': 'mp4', + 'title': 'Man Wearing M&M Jacket Apparently Made In God\'s Image', + 'description': 'md5:cc12448686b5600baae9261d3e180910', + 'thumbnail': 're:^https?://.*\.jpg\?\d+$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + article_id = mobj.group('article_id') + + webpage = self._download_webpage(url, article_id) + + video_id = self._search_regex( + r'"videoId":\s(\d+),', webpage, 'video ID') + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + + sources = re.findall(r'<source src="([^"]+)" type="([^"]+)"', webpage) + if not sources: + raise ExtractorError( + 'No sources found for video %s' % video_id, expected=True) + + formats = [] + for src, type_ in sources: + if type_ == 'video/mp4': + formats.append({ + 'format_id': 'mp4_sd', + 'preference': 1, + 'url': src, + }) + elif type_ == 'video/webm': + formats.append({ + 'format_id': 'webm_sd', + 'preference': 0, + 'url': src, + }) + elif type_ == 'application/x-mpegURL': + formats.extend( + self._extract_m3u8_formats(src, video_id, preference=-1)) + else: + self.report_warning( + 'Encountered unexpected format: %s' % type_) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'description': description, + } diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index b6b2dba9c..e2653d62d 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -5,6 +5,8 @@ import json from .common import InfoExtractor from ..utils import ( + compat_str, + determine_ext, ExtractorError, xpath_with_ns, ) @@ -34,9 +36,20 @@ class ThePlatformIE(InfoExtractor): }, } - def _get_info(self, video_id, smil_url): - meta = self._download_xml(smil_url, video_id) + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + if mobj.group('config'): + config_url = url + '&form=json' + config_url = config_url.replace('swf/', 'config/') + config_url = config_url.replace('onsite/', 'onsite/config/') + config = self._download_json(config_url, video_id, 'Downloading config') + smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m' + else: + smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?' + 'format=smil&mbr=true'.format(video_id)) + meta = self._download_xml(smil_url, video_id) try: error_msg = next( n.attrib['abstract'] @@ -55,36 +68,48 @@ class ThePlatformIE(InfoExtractor): body = meta.find(_x('smil:body')) f4m_node = body.find(_x('smil:seq//smil:video')) - if f4m_node is not None: + if f4m_node is not None and '.f4m' in f4m_node.attrib['src']: f4m_url = f4m_node.attrib['src'] if 'manifest.f4m?' not in f4m_url: f4m_url += '?' # the parameters are from syfy.com, other sites may use others, # they also work for nbc.com f4m_url += '&g=UXWGVKRWHFSP&hdcore=3.0.3' - formats = [{ - 'ext': 'flv', - 'url': f4m_url, - }] + formats = self._extract_f4m_formats(f4m_url, video_id) else: - base_url = head.find(_x('smil:meta')).attrib['base'] - switch = body.find(_x('smil:switch')) formats = [] - for f in switch.findall(_x('smil:video')): - attr = f.attrib - width = int(attr['width']) - height = int(attr['height']) - vbr = int(attr['system-bitrate']) // 1000 - format_id = '%dx%d_%dk' % (width, height, vbr) - formats.append({ - 'format_id': format_id, - 'url': base_url, - 'play_path': 'mp4:' + attr['src'], - 'ext': 'flv', - 'width': width, - 'height': height, - 'vbr': vbr, - }) + switch = body.find(_x('smil:switch')) + if switch is not None: + base_url = head.find(_x('smil:meta')).attrib['base'] + for f in switch.findall(_x('smil:video')): + attr = f.attrib + width = int(attr['width']) + height = int(attr['height']) + vbr = int(attr['system-bitrate']) // 1000 + format_id = '%dx%d_%dk' % (width, height, vbr) + formats.append({ + 'format_id': format_id, + 'url': base_url, + 'play_path': 'mp4:' + attr['src'], + 'ext': 'flv', + 'width': width, + 'height': height, + 'vbr': vbr, + }) + else: + switch = body.find(_x('smil:seq//smil:switch')) + for f in switch.findall(_x('smil:video')): + attr = f.attrib + vbr = int(attr['system-bitrate']) // 1000 + ext = determine_ext(attr['src']) + if ext == 'once': + ext = 'mp4' + formats.append({ + 'format_id': compat_str(vbr), + 'url': attr['src'], + 'vbr': vbr, + 'ext': ext, + }) self._sort_formats(formats) return { @@ -93,19 +118,5 @@ class ThePlatformIE(InfoExtractor): 'formats': formats, 'description': info['description'], 'thumbnail': info['defaultThumbnailUrl'], - 'duration': info['duration']//1000, + 'duration': info['duration'] // 1000, } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - if mobj.group('config'): - config_url = url+ '&form=json' - config_url = config_url.replace('swf/', 'config/') - config_url = config_url.replace('onsite/', 'onsite/config/') - config = self._download_json(config_url, video_id, 'Downloading config') - smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m' - else: - smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?' - 'format=smil&mbr=true'.format(video_id)) - return self._get_info(video_id, smil_url) diff --git a/youtube_dl/extractor/thesixtyone.py b/youtube_dl/extractor/thesixtyone.py new file mode 100644 index 000000000..a77c6a2fc --- /dev/null +++ b/youtube_dl/extractor/thesixtyone.py @@ -0,0 +1,100 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import unified_strdate + + +class TheSixtyOneIE(InfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)?thesixtyone\.com/ + (?:.*?/)* + (?: + s| + song/comments/list| + song + )/(?P<id>[A-Za-z0-9]+)/?$''' + _SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}' + _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}.thesixtyone.com/thesixtyone_production/audio/{0:}_stream' + _THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop' + _TESTS = [ + { + 'url': 'http://www.thesixtyone.com/s/SrE3zD7s1jt/', + 'md5': '821cc43b0530d3222e3e2b70bb4622ea', + 'info_dict': { + 'id': 'SrE3zD7s1jt', + 'ext': 'mp3', + 'title': 'CASIO - Unicorn War Mixtape', + 'thumbnail': 're:^https?://.*_desktop$', + 'upload_date': '20071217', + 'duration': 3208, + } + }, + { + 'url': 'http://www.thesixtyone.com/song/comments/list/SrE3zD7s1jt', + 'only_matching': True, + }, + { + 'url': 'http://www.thesixtyone.com/s/ULoiyjuJWli#/s/SrE3zD7s1jt/', + 'only_matching': True, + }, + { + 'url': 'http://www.thesixtyone.com/#/s/SrE3zD7s1jt/', + 'only_matching': True, + }, + { + 'url': 'http://www.thesixtyone.com/song/SrE3zD7s1jt/', + 'only_matching': True, + }, + ] + + _DECODE_MAP = { + "x": "a", + "m": "b", + "w": "c", + "q": "d", + "n": "e", + "p": "f", + "a": "0", + "h": "1", + "e": "2", + "u": "3", + "s": "4", + "i": "5", + "o": "6", + "y": "7", + "r": "8", + "c": "9" + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + song_id = mobj.group('id') + + webpage = self._download_webpage( + self._SONG_URL_TEMPLATE.format(song_id), song_id) + + song_data = json.loads(self._search_regex( + r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data')) + keys = [self._DECODE_MAP.get(s, s) for s in song_data['key']] + url = self._SONG_FILE_URL_TEMPLATE.format( + "".join(reversed(keys)), **song_data) + + formats = [{ + 'format_id': 'sd', + 'url': url, + 'ext': 'mp3', + }] + + return { + 'id': song_id, + 'title': '{artist:} - {name:}'.format(**song_data), + 'formats': formats, + 'comment_count': song_data.get('comments_count'), + 'duration': song_data.get('play_time'), + 'like_count': song_data.get('score'), + 'thumbnail': self._THUMBNAIL_URL_TEMPLATE.format(**song_data), + 'upload_date': unified_strdate(song_data.get('publish_date')), + } diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py index bfb9d2fc9..7f323c938 100644 --- a/youtube_dl/extractor/thisav.py +++ b/youtube_dl/extractor/thisav.py @@ -1,4 +1,4 @@ -#coding: utf-8 +# coding: utf-8 from __future__ import unicode_literals import re @@ -36,12 +36,12 @@ class ThisAVIE(InfoExtractor): r': <a href="http://www.thisav.com/user/[0-9]+/([^"]+)">(?:[^<]+)</a>', webpage, 'uploader id', fatal=False) ext = determine_ext(video_url) - + return { - 'id': video_id, - 'url': video_url, - 'uploader': uploader, + 'id': video_id, + 'url': video_url, + 'uploader': uploader, 'uploader_id': uploader_id, - 'title': title, - 'ext': ext, + 'title': title, + 'ext': ext, } diff --git a/youtube_dl/extractor/thvideo.py b/youtube_dl/extractor/thvideo.py new file mode 100644 index 000000000..496f15d80 --- /dev/null +++ b/youtube_dl/extractor/thvideo.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + unified_strdate +) + + +class THVideoIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?thvideo\.tv/(?:v/th|mobile\.php\?cid=)(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://thvideo.tv/v/th1987/', + 'md5': 'fa107b1f73817e325e9433505a70db50', + 'info_dict': { + 'id': '1987', + 'ext': 'mp4', + 'title': '【动画】秘封活动记录 ～ The Sealed Esoteric History.分镜稿预览', + 'display_id': 'th1987', + 'thumbnail': 'http://thvideo.tv/uploadfile/2014/0722/20140722013459856.jpg', + 'description': '社团京都幻想剧团的第一个东方二次同人动画作品「秘封活动记录 ～ The Sealed Esoteric History.」 本视频是该动画第一期的分镜草稿...', + 'upload_date': '20140722' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + # extract download link from mobile player page + webpage_player = self._download_webpage( + 'http://thvideo.tv/mobile.php?cid=%s-0' % (video_id), + video_id, note='Downloading video source page') + video_url = self._html_search_regex( + r'<source src="(.*?)" type', webpage_player, 'video url') + + # extract video info from main page + webpage = self._download_webpage( + 'http://thvideo.tv/v/th%s' % (video_id), video_id) + title = self._og_search_title(webpage) + display_id = 'th%s' % video_id + thumbnail = self._og_search_thumbnail(webpage) + description = self._og_search_description(webpage) + upload_date = unified_strdate(self._html_search_regex( + r'span itemprop="datePublished" content="(.*?)">', webpage, + 'upload date', fatal=False)) + + return { + 'id': video_id, + 'ext': 'mp4', + 'url': video_url, + 'title': title, + 'display_id': display_id, + 'thumbnail': thumbnail, + 'description': description, + 'upload_date': upload_date + } + + +class THVideoPlaylistIE(InfoExtractor): + _VALID_URL = r'http?://(?:www\.)?thvideo\.tv/mylist(?P<id>[0-9]+)' + _TEST = { + 'url': 'http://thvideo.tv/mylist2', + 'info_dict': { + 'id': '2', + 'title': '幻想万華鏡', + }, + 'playlist_mincount': 23, + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + list_title = self._html_search_regex( + r'<h1 class="show_title">(.*?)<b id', webpage, 'playlist title', + fatal=False) + + entries = [ + self.url_result('http://thvideo.tv/v/th' + id, 'THVideo') + for id in re.findall(r'<dd><a href="http://thvideo.tv/v/th(\d+)/" target=', webpage)] + + return self.playlist_result(entries, playlist_id, list_title) diff --git a/youtube_dl/extractor/tinypic.py b/youtube_dl/extractor/tinypic.py index a4aa25f66..4fe89dbe5 100644 --- a/youtube_dl/extractor/tinypic.py +++ b/youtube_dl/extractor/tinypic.py @@ -26,9 +26,9 @@ class TinyPicIE(InfoExtractor): video_id = mobj.group('id') webpage = self._download_webpage(url, video_id, 'Downloading page') - + mobj = re.search(r'(?m)fo\.addVariable\("file",\s"(?P<fileid>[\da-z]+)"\);\n' - '\s+fo\.addVariable\("s",\s"(?P<serverid>\d+)"\);', webpage) + '\s+fo\.addVariable\("s",\s"(?P<serverid>\d+)"\);', webpage) if mobj is None: raise ExtractorError('Video %s does not exist' % video_id, expected=True) @@ -47,4 +47,4 @@ class TinyPicIE(InfoExtractor): 'url': video_url, 'thumbnail': thumbnail, 'title': title - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/tlc.py b/youtube_dl/extractor/tlc.py index d848ee186..66d159e99 100644 --- a/youtube_dl/extractor/tlc.py +++ b/youtube_dl/extractor/tlc.py @@ -36,9 +36,10 @@ class TlcDeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Breaking Amish: Die Welt da draußen', 'uploader': 'Discovery Networks - Germany', - 'description': 'Vier Amische und eine Mennonitin wagen in New York' + 'description': ( + 'Vier Amische und eine Mennonitin wagen in New York' ' den Sprung in ein komplett anderes Leben. Begleitet sie auf' - ' ihrem spannenden Weg.', + ' ihrem spannenden Weg.'), }, } diff --git a/youtube_dl/extractor/tmz.py b/youtube_dl/extractor/tmz.py new file mode 100644 index 000000000..827aa08a4 --- /dev/null +++ b/youtube_dl/extractor/tmz.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TMZIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tmz\.com/videos/(?P<id>[^/]+)/?' + _TEST = { + 'url': 'http://www.tmz.com/videos/0_okj015ty/', + 'md5': '791204e3bf790b1426cb2db0706184c0', + 'info_dict': { + 'id': '0_okj015ty', + 'url': 'http://tmz.vo.llnwd.net/o28/2014-03/13/0_okj015ty_0_rt8ro3si_2.mp4', + 'ext': 'mp4', + 'title': 'Kim Kardashian\'s Boobs Unlock a Mystery!', + 'description': 'Did Kim Kardasain try to one-up Khloe by one-upping Kylie??? Or is she just showing off her amazing boobs?', + 'thumbnail': 'http://cdnbakmi.kaltura.com/p/591531/sp/59153100/thumbnail/entry_id/0_okj015ty/version/100002/acv/182/width/640', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + return { + 'id': video_id, + 'url': self._html_search_meta('VideoURL', webpage, fatal=True), + 'title': self._og_search_title(webpage), + 'description': self._og_search_description(webpage), + 'thumbnail': self._html_search_meta('ThumbURL', webpage), + } diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index 4956f8577..0ecd695f8 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -71,7 +71,7 @@ class TNAFlixIE(InfoExtractor): fmt['height'] = int(m.group(1)) formats.append(fmt) self._sort_formats(formats) - + return { 'id': video_id, 'display_id': display_id, diff --git a/youtube_dl/extractor/traileraddict.py b/youtube_dl/extractor/traileraddict.py index 11407428b..1c53a3fd0 100644 --- a/youtube_dl/extractor/traileraddict.py +++ b/youtube_dl/extractor/traileraddict.py @@ -25,7 +25,7 @@ class TrailerAddictIE(InfoExtractor): webpage = self._download_webpage(url, name) title = self._search_regex(r'<title>(.+?)', - webpage, 'video title').replace(' - Trailer Addict','') + webpage, 'video title').replace(' - Trailer Addict', '') view_count_str = self._search_regex( r'([0-9,.]+)', webpage, 'view count', fatal=False) @@ -43,12 +43,12 @@ class TrailerAddictIE(InfoExtractor): fvar = "fvar" info_url = "http://www.traileraddict.com/%s.php?tid=%s" % (fvar, str(video_id)) - info_webpage = self._download_webpage(info_url, video_id , "Downloading the info webpage") + info_webpage = self._download_webpage(info_url, video_id, "Downloading the info webpage") final_url = self._search_regex(r'&fileurl=(.+)', - info_webpage, 'Download url').replace('%3F','?') + info_webpage, 'Download url').replace('%3F', '?') thumbnail_url = self._search_regex(r'&image=(.+?)&', - info_webpage, 'thumbnail url') + info_webpage, 'thumbnail url') description = self._html_search_regex( r'(?s)
    .*?
    ]*>(.*?)
    ', diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py index d64aaa41f..220a05b7b 100644 --- a/youtube_dl/extractor/trilulilu.py +++ b/youtube_dl/extractor/trilulilu.py @@ -1,28 +1,28 @@ +from __future__ import unicode_literals + import json -import re from .common import InfoExtractor class TriluliluIE(InfoExtractor): - _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P[^/]+)/(?P[^/]+)' + _VALID_URL = r'https?://(?:www\.)?trilulilu\.ro/video-[^/]+/(?P[^/]+)' _TEST = { - u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1", - u'file': u"big-buck-bunny-1.mp4", - u'info_dict': { - u"title": u"Big Buck Bunny", - u"description": u":) pentru copilul din noi", + 'url': 'http://www.trilulilu.ro/video-animatie/big-buck-bunny-1', + 'info_dict': { + 'id': 'big-buck-bunny-1', + 'ext': 'mp4', + 'title': 'Big Buck Bunny', + 'description': ':) pentru copilul din noi', }, # Server ignores Range headers (--test) - u"params": { - u"skip_download": True + 'params': { + 'skip_download': True } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') - + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) title = self._og_search_title(webpage) @@ -30,20 +30,20 @@ class TriluliluIE(InfoExtractor): description = self._og_search_description(webpage) log_str = self._search_regex( - r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info') + r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, 'log info') log = json.loads(log_str) - format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/' - u'video-formats2' % log) + format_url = ('http://fs%(server)s.trilulilu.ro/%(hash)s/' + 'video-formats2' % log) format_doc = self._download_xml( format_url, video_id, - note=u'Downloading formats', - errnote=u'Error while downloading formats') - + note='Downloading formats', + errnote='Error while downloading formats') + video_url_template = ( - u'http://fs%(server)s.trilulilu.ro/stream.php?type=video' - u'&source=site&hash=%(hash)s&username=%(userid)s&' - u'key=ministhebest&format=%%s&sig=&exp=' % + 'http://fs%(server)s.trilulilu.ro/stream.php?type=video' + '&source=site&hash=%(hash)s&username=%(userid)s&' + 'key=ministhebest&format=%%s&sig=&exp=' % log) formats = [ { @@ -63,4 +63,3 @@ class TriluliluIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, } - diff --git a/youtube_dl/extractor/trutube.py b/youtube_dl/extractor/trutube.py index 57f956683..e7b79243a 100644 --- a/youtube_dl/extractor/trutube.py +++ b/youtube_dl/extractor/trutube.py @@ -1,13 +1,12 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import xpath_text class TruTubeIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?trutube\.tv/video/(?P[0-9]+)/.*' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?trutube\.tv/(?:video/|nuevo/player/embed\.php\?v=)(?P[0-9]+)' + _TESTS = [{ 'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-', 'md5': 'c5b6e301b0a2040b074746cbeaa26ca1', 'info_dict': { @@ -16,29 +15,26 @@ class TruTubeIE(InfoExtractor): 'title': 'Ramses II - Proven To Be A Red Headed Caucasoid', 'thumbnail': 're:^http:.*\.jpg$', } - } + }, { + 'url': 'https://trutube.tv/nuevo/player/embed.php?v=14880', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - video_title = self._og_search_title(webpage).strip() - thumbnail = self._search_regex( - r"var splash_img = '([^']+)';", webpage, 'thumbnail', fatal=False) + config = self._download_xml( + 'https://trutube.tv/nuevo/player/config.php?v=%s' % video_id, + video_id, transform_source=lambda s: s.strip()) - all_formats = re.finditer( - r"var (?P[a-z]+)_video_file\s*=\s*'(?P[^']+)';", webpage) - formats = [{ - 'format_id': m.group('key'), - 'quality': -i, - 'url': m.group('url'), - } for i, m in enumerate(all_formats)] - self._sort_formats(formats) + # filehd is always 404 + video_url = xpath_text(config, './file', 'video URL', fatal=True) + title = xpath_text(config, './title', 'title').strip() + thumbnail = xpath_text(config, './image', ' thumbnail') return { 'id': video_id, - 'title': video_title, - 'formats': formats, + 'url': video_url, + 'title': title, 'thumbnail': thumbnail, } diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index 08a48c05a..64a1e9030 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -14,27 +14,35 @@ from ..aes import aes_decrypt_text class Tube8IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/){2}(?P\d+)' - _TEST = { - 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', - 'md5': '44bf12b98313827dd52d35b8706a4ea0', - 'info_dict': { - 'id': '229795', - 'ext': 'mp4', - 'description': 'hot teen Kasia grinding', - 'uploader': 'unknown', - 'title': 'Kasia music video', - 'age_limit': 18, - } - } + _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P[^/]+)/(?P\d+)' + _TESTS = [ + { + 'url': 'http://www.tube8.com/teen/kasia-music-video/229795/', + 'md5': '44bf12b98313827dd52d35b8706a4ea0', + 'info_dict': { + 'id': '229795', + 'display_id': 'kasia-music-video', + 'ext': 'mp4', + 'description': 'hot teen Kasia grinding', + 'uploader': 'unknown', + 'title': 'Kasia music video', + 'age_limit': 18, + } + }, + { + 'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/', + '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') req = compat_urllib_request.Request(url) req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + webpage = self._download_webpage(req, display_id) flashvars = json.loads(self._html_search_regex( r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars')) @@ -70,6 +78,7 @@ class Tube8IE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'url': video_url, 'title': title, 'description': description, diff --git a/youtube_dl/extractor/tudou.py b/youtube_dl/extractor/tudou.py index 927e0cb03..308a6b850 100644 --- a/youtube_dl/extractor/tudou.py +++ b/youtube_dl/extractor/tudou.py @@ -37,12 +37,12 @@ class TudouIE(InfoExtractor): 'skip': 'Only works from China' }] - def _url_for_id(self, id, quality = None): - info_url = "http://v2.tudou.com/f?id="+str(id) + def _url_for_id(self, id, quality=None): + info_url = "http://v2.tudou.com/f?id=" + str(id) if quality: info_url += '&hd' + quality webpage = self._download_webpage(info_url, id, "Opening the info webpage") - final_url = self._html_search_regex('>(.+?)',webpage, 'video url') + final_url = self._html_search_regex('>(.+?)', webpage, 'video url') return final_url def _real_extract(self, url): @@ -74,7 +74,7 @@ class TudouIE(InfoExtractor): result = [] len_parts = len(parts) if len_parts > 1: - self.to_screen(u'%s: found %s parts' % (video_id, len_parts)) + self.to_screen('%s: found %s parts' % (video_id, len_parts)) for part in parts: part_id = part['k'] final_url = self._url_for_id(part_id, quality) diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index 306fe8974..2a1ae5a71 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -4,9 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - ExtractorError, -) class TumblrIE(InfoExtractor): @@ -18,7 +15,7 @@ class TumblrIE(InfoExtractor): 'id': '54196191430', 'ext': 'mp4', 'title': 'tatiana maslany news, Orphan Black || DVD extra - behind the scenes ↳...', - 'description': 'md5:dfac39636969fe6bf1caa2d50405f069', + 'description': 'md5:37db8211e40b50c7c44e95da14f630b7', 'thumbnail': 're:http://.*\.jpg', } }, { @@ -27,7 +24,7 @@ class TumblrIE(InfoExtractor): 'info_dict': { 'id': '90208453769', 'ext': 'mp4', - 'title': '5SOS STRUM ;)', + 'title': '5SOS STRUM ;]', 'description': 'md5:dba62ac8639482759c8eb10ce474586a', 'thumbnail': 're:http://.*\.jpg', } @@ -41,18 +38,12 @@ class TumblrIE(InfoExtractor): url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) webpage = self._download_webpage(url, video_id) - re_video = r'src=\\x22(?Phttp://%s\.tumblr\.com/video_file/%s/(.*?))\\x22 type=\\x22video/(?P.*?)\\x22' % (blog, video_id) - video = re.search(re_video, webpage) - if video is None: - raise ExtractorError('Unable to extract video') - video_url = video.group('video_url') - ext = video.group('ext') - - video_thumbnail = self._search_regex( - r'posters.*?\[\\x22(.*?)\\x22', - webpage, 'thumbnail', fatal=False) # We pick the first poster - if video_thumbnail: - video_thumbnail = video_thumbnail.replace('\\\\/', '/') + iframe_url = self._search_regex( + r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'', + webpage, 'iframe url') + iframe = self._download_webpage(iframe_url, video_id) + video_url = self._search_regex(r'[0-9]+) + |tun\.in/(?P[A-Za-z0-9]+) + ) + ''' + + _INFO_DICT = { + 'id': '34682', + 'title': 'Jazz 24 on 88.5 Jazz24 - KPLU-HD2', + 'ext': 'AAC', + 'thumbnail': 're:^https?://.*\.png$', + 'location': 'Tacoma, WA', + } + _TESTS = [ + { + 'url': 'http://tunein.com/radio/Jazz24-885-s34682/', + 'info_dict': _INFO_DICT, + 'params': { + 'skip_download': True, # live stream + }, + }, + { # test redirection + 'url': 'http://tun.in/ser7s', + 'info_dict': _INFO_DICT, + 'params': { + 'skip_download': True, # live stream + }, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + redirect_id = mobj.group('redirect_id') + if redirect_id: + # The server doesn't support HEAD requests + urlh = self._request_webpage( + url, redirect_id, note='Downloading redirect page') + url = urlh.geturl() + self.to_screen('Following redirect: %s' % url) + mobj = re.match(self._VALID_URL, url) + station_id = mobj.group('id') + + webpage = self._download_webpage( + url, station_id, note='Downloading station webpage') + + payload = self._html_search_regex( + r'(?m)TuneIn\.payload\s*=\s*(\{[^$]+?)$', webpage, 'JSON data') + json_data = json.loads(payload) + station_info = json_data['Station']['broadcast'] + title = station_info['Title'] + thumbnail = station_info.get('Logo') + location = station_info.get('Location') + streams_url = station_info.get('StreamUrl') + if not streams_url: + raise ExtractorError('No downloadable streams found', + expected=True) + stream_data = self._download_webpage( + streams_url, station_id, note='Downloading stream data') + streams = json.loads(self._search_regex( + r'\((.*)\);', stream_data, 'stream info'))['Streams'] + + is_live = None + formats = [] + for stream in streams: + if stream.get('Type') == 'Live': + is_live = True + formats.append({ + 'abr': stream.get('Bandwidth'), + 'ext': stream.get('MediaType'), + 'acodec': stream.get('MediaType'), + 'vcodec': 'none', + 'url': stream.get('Url'), + # Sometimes streams with the highest quality do not exist + 'preference': stream.get('Reliability'), + }) + self._sort_formats(formats) + + return { + 'id': station_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'location': location, + 'is_live': is_live, + } diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py index dc8697850..d81d1d1a6 100644 --- a/youtube_dl/extractor/tvigle.py +++ b/youtube_dl/extractor/tvigle.py @@ -17,16 +17,16 @@ class TvigleIE(InfoExtractor): _TESTS = [ { - 'url': 'http://www.tvigle.ru/video/brat-2/', - 'md5': '72cb7eab33e54314e1790da402d3c9c3', + 'url': 'http://www.tvigle.ru/video/brat/', + 'md5': 'ff4344a4894b0524441fb6f8218dc716', 'info_dict': { - 'id': '5119390', - 'display_id': 'brat-2', + 'id': '5118490', + 'display_id': 'brat', 'ext': 'mp4', - 'title': 'Брат 2 ', - 'description': 'md5:5751f4fe345a58e1692585c361294bd8', - 'duration': 7356.369, - 'age_limit': 0, + 'title': 'Брат', + 'description': 'md5:d16ac7c0b47052ea51fddb92c4e413eb', + 'duration': 5722.6, + 'age_limit': 16, }, }, { @@ -71,6 +71,7 @@ class TvigleIE(InfoExtractor): 'format_id': '%s-%s' % (vcodec, quality), 'vcodec': vcodec, 'height': int(quality[:-1]), + 'filesize': item['video_files_size'][vcodec][quality], }) self._sort_formats(formats) @@ -83,4 +84,4 @@ class TvigleIE(InfoExtractor): 'duration': duration, 'age_limit': age_limit, 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/tvp.py b/youtube_dl/extractor/tvp.py index bfed9dd04..a64580005 100644 --- a/youtube_dl/extractor/tvp.py +++ b/youtube_dl/extractor/tvp.py @@ -1,40 +1,35 @@ -import json -import re +from __future__ import unicode_literals from .common import InfoExtractor class TvpIE(InfoExtractor): - IE_NAME = u'tvp.pl' + IE_NAME = 'tvp.pl' _VALID_URL = r'https?://www\.tvp\.pl/.*?wideo/(?P\d+)/(?P\d+)' _TEST = { - u'url': u'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238', - u'md5': u'148408967a6a468953c0a75cbdaf0d7a', - u'file': u'12878238.wmv', - u'info_dict': { - u'title': u'31.10.2013 - Odcinek 2', - u'description': u'31.10.2013 - Odcinek 2', + 'url': 'http://www.tvp.pl/warszawa/magazyny/campusnews/wideo/31102013/12878238', + 'md5': '148408967a6a468953c0a75cbdaf0d7a', + 'info_dict': { + 'id': '12878238', + 'ext': 'wmv', + 'title': '31.10.2013 - Odcinek 2', + 'description': '31.10.2013 - Odcinek 2', }, - u'skip': u'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.' + 'skip': 'Download has to use same server IP as extraction. Therefore, a good (load-balancing) DNS resolver will make the download fail.' } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) json_url = 'http://www.tvp.pl/pub/stat/videofileinfo?video_id=%s' % video_id - json_params = self._download_webpage( - json_url, video_id, u"Downloading video metadata") - - params = json.loads(json_params) - self.report_extraction(video_id) + params = self._download_json( + json_url, video_id, "Downloading video metadata") video_url = params['video_url'] - title = self._og_search_title(webpage, fatal=True) return { 'id': video_id, - 'title': title, + 'title': self._og_search_title(webpage), 'ext': 'wmv', 'url': video_url, 'description': self._og_search_description(webpage), diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 445e0ec41..eb9473754 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -4,9 +4,9 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_str from ..utils import ( ExtractorError, - compat_str, parse_iso8601, qualities, ) @@ -176,8 +176,7 @@ class TVPlayIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) video = self._download_json( 'http://playapi.mtgx.tv/v1/videos/%s' % video_id, video_id, 'Downloading video JSON') @@ -208,6 +207,10 @@ class TVPlayIE(InfoExtractor): 'app': m.group('app'), 'play_path': m.group('playpath'), }) + elif video_url.endswith('.f4m'): + formats.extend(self._extract_f4m_formats( + video_url + '?hdcore=3.5.0&plugin=aasp-3.5.0.151.81', video_id)) + continue else: fmt.update({ 'url': video_url, diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py new file mode 100644 index 000000000..36aa1ad6e --- /dev/null +++ b/youtube_dl/extractor/twitch.py @@ -0,0 +1,187 @@ +from __future__ import unicode_literals + +import itertools +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) + + +class TwitchIE(InfoExtractor): + # TODO: One broadcast may be split into multiple videos. The key + # 'broadcast_id' is the same for all parts, and 'broadcast_part' + # starts at 1 and increases. Can we treat all parts as one video? + _VALID_URL = r"""(?x)^(?:http://)?(?:www\.)?twitch\.tv/ + (?: + (?P[^/]+)| + (?:(?:[^/]+)/b/(?P[^/]+))| + (?:(?:[^/]+)/c/(?P[^/]+)) + ) + /?(?:\#.*)?$ + """ + _PAGE_LIMIT = 100 + _API_BASE = 'https://api.twitch.tv' + _TESTS = [{ + 'url': 'http://www.twitch.tv/riotgames/b/577357806', + 'info_dict': { + 'id': 'a577357806', + 'title': 'Worlds Semifinals - Star Horn Royal Club vs. OMG', + }, + 'playlist_mincount': 12, + }, { + 'url': 'http://www.twitch.tv/acracingleague/c/5285812', + 'info_dict': { + 'id': 'c5285812', + 'title': 'ACRL Off Season - Sports Cars @ Nordschleife', + }, + 'playlist_mincount': 3, + }, { + 'url': 'http://www.twitch.tv/vanillatv', + 'info_dict': { + 'id': 'vanillatv', + 'title': 'VanillaTV', + }, + 'playlist_mincount': 412, + }] + + def _handle_error(self, response): + if not isinstance(response, dict): + return + error = response.get('error') + if error: + raise ExtractorError( + '%s returned error: %s - %s' % (self.IE_NAME, error, response.get('message')), + expected=True) + + def _download_json(self, url, video_id, note='Downloading JSON metadata'): + response = super(TwitchIE, self)._download_json(url, video_id, note) + self._handle_error(response) + return response + + def _extract_media(self, item, item_id): + ITEMS = { + 'a': 'video', + 'c': 'chapter', + } + info = self._extract_info(self._download_json( + '%s/kraken/videos/%s%s' % (self._API_BASE, item, item_id), item_id, + 'Downloading %s info JSON' % ITEMS[item])) + response = self._download_json( + '%s/api/videos/%s%s' % (self._API_BASE, item, item_id), item_id, + 'Downloading %s playlist JSON' % ITEMS[item]) + entries = [] + chunks = response['chunks'] + qualities = list(chunks.keys()) + for num, fragment in enumerate(zip(*chunks.values()), start=1): + formats = [] + for fmt_num, fragment_fmt in enumerate(fragment): + format_id = qualities[fmt_num] + fmt = { + 'url': fragment_fmt['url'], + 'format_id': format_id, + 'quality': 1 if format_id == 'live' else 0, + } + m = re.search(r'^(?P\d+)[Pp]', format_id) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + self._sort_formats(formats) + entry = dict(info) + entry['id'] = '%s_%d' % (entry['id'], num) + entry['title'] = '%s part %d' % (entry['title'], num) + entry['formats'] = formats + entries.append(entry) + return self.playlist_result(entries, info['id'], info['title']) + + def _extract_info(self, info): + return { + 'id': info['_id'], + 'title': info['title'], + 'description': info['description'], + 'duration': info['length'], + 'thumbnail': info['preview'], + 'uploader': info['channel']['display_name'], + 'uploader_id': info['channel']['name'], + 'timestamp': parse_iso8601(info['recorded_at']), + 'view_count': info['views'], + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj.group('chapterid'): + return self._extract_media('c', mobj.group('chapterid')) + + """ + webpage = self._download_webpage(url, chapter_id) + m = re.search(r'PP\.archive_id = "([0-9]+)";', webpage) + if not m: + raise ExtractorError('Cannot find archive of a chapter') + archive_id = m.group(1) + + api = api_base + '/broadcast/by_chapter/%s.xml' % chapter_id + doc = self._download_xml( + api, chapter_id, + note='Downloading chapter information', + errnote='Chapter information download failed') + for a in doc.findall('.//archive'): + if archive_id == a.find('./id').text: + break + else: + raise ExtractorError('Could not find chapter in chapter information') + + video_url = a.find('./video_file_url').text + video_ext = video_url.rpartition('.')[2] or 'flv' + + chapter_api_url = 'https://api.twitch.tv/kraken/videos/c' + chapter_id + chapter_info = self._download_json( + chapter_api_url, 'c' + chapter_id, + note='Downloading chapter metadata', + errnote='Download of chapter metadata failed') + + bracket_start = int(doc.find('.//bracket_start').text) + bracket_end = int(doc.find('.//bracket_end').text) + + # TODO determine start (and probably fix up file) + # youtube-dl -v http://www.twitch.tv/firmbelief/c/1757457 + #video_url += '?start=' + TODO:start_timestamp + # bracket_start is 13290, but we want 51670615 + self._downloader.report_warning('Chapter detected, but we can just download the whole file. ' + 'Chapter starts at %s and ends at %s' % (formatSeconds(bracket_start), formatSeconds(bracket_end))) + + info = { + 'id': 'c' + chapter_id, + 'url': video_url, + 'ext': video_ext, + 'title': chapter_info['title'], + 'thumbnail': chapter_info['preview'], + 'description': chapter_info['description'], + 'uploader': chapter_info['channel']['display_name'], + 'uploader_id': chapter_info['channel']['name'], + } + return info + """ + elif mobj.group('videoid'): + return self._extract_media('a', mobj.group('videoid')) + elif mobj.group('channelid'): + channel_id = mobj.group('channelid') + info = self._download_json( + '%s/kraken/channels/%s' % (self._API_BASE, channel_id), + channel_id, 'Downloading channel info JSON') + channel_name = info.get('display_name') or info.get('name') + entries = [] + offset = 0 + limit = self._PAGE_LIMIT + for counter in itertools.count(1): + response = self._download_json( + '%s/kraken/channels/%s/videos/?offset=%d&limit=%d' + % (self._API_BASE, channel_id, offset, limit), + channel_id, 'Downloading channel videos JSON page %d' % counter) + videos = response['videos'] + if not videos: + break + entries.extend([self.url_result(video['url'], 'Twitch') for video in videos]) + offset += limit + return self.playlist_result(entries, channel_id, channel_name) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 054f42725..0e4d386a8 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -40,8 +40,24 @@ class UdemyIE(InfoExtractor): error_str += ' - %s' % error_data.get('formErrors') raise ExtractorError(error_str, expected=True) - def _download_json(self, url, video_id, note='Downloading JSON metadata'): - response = super(UdemyIE, self)._download_json(url, video_id, note) + def _download_json(self, url_or_request, video_id, note='Downloading JSON metadata'): + headers = { + 'X-Udemy-Snail-Case': 'true', + 'X-Requested-With': 'XMLHttpRequest', + } + for cookie in self._downloader.cookiejar: + if cookie.name == 'client_id': + headers['X-Udemy-Client-Id'] = cookie.value + elif cookie.name == 'access_token': + headers['X-Udemy-Bearer-Token'] = cookie.value + + if isinstance(url_or_request, compat_urllib_request.Request): + for header, value in headers.items(): + url_or_request.add_header(header, value) + else: + url_or_request = compat_urllib_request.Request(url_or_request, headers=headers) + + response = super(UdemyIE, self)._download_json(url_or_request, video_id, note) self._handle_error(response) return response @@ -62,7 +78,9 @@ class UdemyIE(InfoExtractor): if login_popup == '
    ': return - csrf = self._html_search_regex(r'.+)"', - webpage, 'title') + webpage, 'title') uploader = self._html_search_regex(r'data-content-type="channel".*?>(?P.*?)', - webpage, 'uploader', fatal=False, flags=re.DOTALL) + webpage, 'uploader', fatal=False, flags=re.DOTALL) thumbnail = self._html_search_regex(r'(.*)', - webpage, 'title').split('/')[0].strip() + webpage, 'title').split('/')[0].strip() info_url = "http://vbox7.com/play/magare.do" data = compat_urllib_parse.urlencode({'as3': '1', 'vid': video_id}) @@ -50,7 +50,6 @@ class Vbox7IE(InfoExtractor): return { 'id': video_id, 'url': final_url, - 'ext': 'flv', 'title': title, 'thumbnail': thumbnail_url, } diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py index 77b1f91ce..94647d1c8 100644 --- a/youtube_dl/extractor/veehd.py +++ b/youtube_dl/extractor/veehd.py @@ -48,11 +48,11 @@ class VeeHDIE(InfoExtractor): video_url = compat_urlparse.unquote(config['clip']['url']) title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0]) uploader_id = self._html_search_regex(r'(.+?)', - webpage, 'uploader') + webpage, 'uploader') thumbnail = self._search_regex(r'(.*?).+)' + + _TEST = { + 'url': 'http://www.vice.com/Fringes/cowboy-capitalists-part-1', + 'info_dict': { + 'id': '43cW1mYzpia9IlestBjVpd23Yu3afAfp', + 'ext': 'mp4', + 'title': 'VICE_COWBOYCAPITALISTS_PART01_v1_VICE_WM_1080p.mov', + }, + 'params': { + # Requires ffmpeg (m3u8 manifest) + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + name = mobj.group('name') + webpage = self._download_webpage(url, name) + try: + embed_code = self._search_regex( + r'embedCode=([^&\'"]+)', webpage, + 'ooyala embed code') + ooyala_url = OoyalaIE._url_for_embed_code(embed_code) + print(ooyala_url) + except ExtractorError: + raise ExtractorError('The page doesn\'t contain a video', expected=True) + return self.url_result(ooyala_url, ie='Ooyala') diff --git a/youtube_dl/extractor/viddler.py b/youtube_dl/extractor/viddler.py index 9328ef4a2..0faa729c6 100644 --- a/youtube_dl/extractor/viddler.py +++ b/youtube_dl/extractor/viddler.py @@ -1,55 +1,85 @@ -import json -import re +from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + float_or_none, + int_or_none, +) class ViddlerIE(InfoExtractor): - _VALID_URL = r'(?Phttps?://(?:www\.)?viddler\.com)/(?:v|embed|player)/(?P[a-z0-9]+)' + _VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P[a-z0-9]+)' _TEST = { - u"url": u"http://www.viddler.com/v/43903784", - u'file': u'43903784.mp4', - u'md5': u'fbbaedf7813e514eb7ca30410f439ac9', - u'info_dict': { - u"title": u"Video Made Easy", - u"uploader": u"viddler", - u"duration": 100.89, + "url": "http://www.viddler.com/v/43903784", + 'md5': 'ae43ad7cb59431ce043f0ff7fa13cbf4', + 'info_dict': { + 'id': '43903784', + 'ext': 'mp4', + "title": "Video Made Easy", + 'description': 'You don\'t need to be a professional to make high-quality video content. Viddler provides some quick and easy tips on how to produce great video content with limited resources. ', + "uploader": "viddler", + 'timestamp': 1335371429, + 'upload_date': '20120425', + "duration": 100.89, + 'thumbnail': 're:^https?://.*\.jpg$', + 'view_count': int, + 'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'], } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - embed_url = mobj.group('domain') + u'/embed/' + video_id - webpage = self._download_webpage(embed_url, video_id) + json_url = ( + 'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?video_id=%s&key=v0vhrt7bg2xq1vyxhkct' % + video_id) + data = self._download_json(json_url, video_id)['video'] - video_sources_code = self._search_regex( - r"(?ms)sources\s*:\s*(\{.*?\})", webpage, u'video URLs') - video_sources = json.loads(video_sources_code.replace("'", '"')) + formats = [] + for filed in data['files']: + if filed.get('status', 'ready') != 'ready': + continue + f = { + 'format_id': filed['profile_id'], + 'format_note': filed['profile_name'], + 'url': self._proto_relative_url(filed['url']), + 'width': int_or_none(filed.get('width')), + 'height': int_or_none(filed.get('height')), + 'filesize': int_or_none(filed.get('size')), + 'ext': filed.get('ext'), + 'source_preference': -1, + } + formats.append(f) - formats = [{ - 'url': video_url, - 'format': format_id, - } for video_url, format_id in video_sources.items()] + if filed.get('cdn_url'): + f = f.copy() + f['url'] = self._proto_relative_url(filed['cdn_url']) + f['format_id'] = filed['profile_id'] + '-cdn' + f['source_preference'] = 1 + formats.append(f) - title = self._html_search_regex( - r"title\s*:\s*'([^']*)'", webpage, u'title') - uploader = self._html_search_regex( - r"authorName\s*:\s*'([^']*)'", webpage, u'uploader', fatal=False) - duration_s = self._html_search_regex( - r"duration\s*:\s*([0-9.]*)", webpage, u'duration', fatal=False) - duration = float(duration_s) if duration_s else None - thumbnail = self._html_search_regex( - r"thumbnail\s*:\s*'([^']*)'", - webpage, u'thumbnail', fatal=False) + if filed.get('html5_video_source'): + f = f.copy() + f['url'] = self._proto_relative_url( + filed['html5_video_source']) + f['format_id'] = filed['profile_id'] + '-html5' + f['source_preference'] = 0 + formats.append(f) + self._sort_formats(formats) + + categories = [ + t.get('text') for t in data.get('tags', []) if 'text' in t] return { '_type': 'video', 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'duration': duration, + 'title': data['title'], 'formats': formats, + 'description': data.get('description'), + 'timestamp': int_or_none(data.get('upload_time')), + 'thumbnail': self._proto_relative_url(data.get('thumbnail_url')), + 'uploader': data.get('author'), + 'duration': float_or_none(data.get('length')), + 'view_count': int_or_none(data.get('view_count')), + 'categories': categories, } diff --git a/youtube_dl/extractor/videobam.py b/youtube_dl/extractor/videobam.py index fed95ef71..0eb3d9414 100644 --- a/youtube_dl/extractor/videobam.py +++ b/youtube_dl/extractor/videobam.py @@ -78,4 +78,4 @@ class VideoBamIE(InfoExtractor): 'view_count': view_count, 'formats': formats, 'age_limit': 18, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/videofyme.py b/youtube_dl/extractor/videofyme.py index f75169041..94f9e9be9 100644 --- a/youtube_dl/extractor/videofyme.py +++ b/youtube_dl/extractor/videofyme.py @@ -1,46 +1,50 @@ -import re +from __future__ import unicode_literals from .common import InfoExtractor from ..utils import ( find_xpath_attr, - determine_ext, + int_or_none, ) + class VideofyMeIE(InfoExtractor): - _VALID_URL = r'https?://(www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P\d+)(&|#|$)' - IE_NAME = u'videofy.me' + _VALID_URL = r'https?://(?:www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P\d+)(&|#|$)' + IE_NAME = 'videofy.me' _TEST = { - u'url': u'http://www.videofy.me/thisisvideofyme/1100701', - u'file': u'1100701.mp4', - u'md5': u'c77d700bdc16ae2e9f3c26019bd96143', - u'info_dict': { - u'title': u'This is VideofyMe', - u'description': None, - u'uploader': u'VideofyMe', - u'uploader_id': u'thisisvideofyme', + 'url': 'http://www.videofy.me/thisisvideofyme/1100701', + 'md5': 'c77d700bdc16ae2e9f3c26019bd96143', + 'info_dict': { + 'id': '1100701', + 'ext': 'mp4', + 'title': 'This is VideofyMe', + 'description': None, + 'uploader': 'VideofyMe', + 'uploader_id': 'thisisvideofyme', + 'view_count': int, }, - + } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id, - video_id) + video_id) video = config.find('video') sources = video.find('sources') - url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key) - for key in ['on', 'av', 'off']] if node is not None) + url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key) + for key in ['on', 'av', 'off']] if node is not None) video_url = url_node.find('url').text + view_count = int_or_none(self._search_regex( + r'([0-9]+)', video.find('views').text, 'view count', fatal=False)) - return {'id': video_id, - 'title': video.find('title').text, - 'url': video_url, - 'ext': determine_ext(video_url), - 'thumbnail': video.find('thumb').text, - 'description': video.find('description').text, - 'uploader': config.find('blog/name').text, - 'uploader_id': video.find('identifier').text, - 'view_count': re.search(r'\d+', video.find('views').text).group(), - } + return { + 'id': video_id, + 'title': video.find('title').text, + 'url': video_url, + 'thumbnail': video.find('thumb').text, + 'description': video.find('description').text, + 'uploader': config.find('blog/name').text, + 'uploader_id': video.find('identifier').text, + 'view_count': view_count, + } diff --git a/youtube_dl/extractor/videomega.py b/youtube_dl/extractor/videomega.py new file mode 100644 index 000000000..29c4e0101 --- /dev/null +++ b/youtube_dl/extractor/videomega.py @@ -0,0 +1,57 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + compat_urllib_parse, + remove_start, +) + + +class VideoMegaIE(InfoExtractor): + _VALID_URL = r'''(?x)https?:// + (?:www\.)?videomega\.tv/ + (?:iframe\.php)?\?ref=(?P[A-Za-z0-9]+) + ''' + _TEST = { + 'url': 'http://videomega.tv/?ref=GKeGPVedBe', + 'md5': '240fb5bcf9199961f48eb17839b084d6', + 'info_dict': { + 'id': 'GKeGPVedBe', + 'ext': 'mp4', + 'title': 'XXL - All Sports United', + 'thumbnail': 're:^https?://.*\.jpg$', + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://videomega.tv/iframe.php?ref={0:}'.format(video_id) + webpage = self._download_webpage(url, video_id) + + escaped_data = self._search_regex( + r'unescape\("([^"]+)"\)', webpage, 'escaped data') + playlist = compat_urllib_parse.unquote(escaped_data) + + thumbnail = self._search_regex( + r'image:\s*"([^"]+)"', playlist, 'thumbnail', fatal=False) + url = self._search_regex(r'file:\s*"([^"]+)"', playlist, 'URL') + title = remove_start(self._html_search_regex( + r'(.*?)', webpage, 'title'), 'VideoMega.tv - ') + + formats = [{ + 'format_id': 'sd', + 'url': url, + }] + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/videopremium.py b/youtube_dl/extractor/videopremium.py index 65463c733..3176e3b9d 100644 --- a/youtube_dl/extractor/videopremium.py +++ b/youtube_dl/extractor/videopremium.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import re import random @@ -5,23 +7,22 @@ from .common import InfoExtractor class VideoPremiumIE(InfoExtractor): - _VALID_URL = r'(?:https?://)?(?:www\.)?videopremium\.(?:tv|me)/(?P\w+)(?:/.*)?' + _VALID_URL = r'https?://(?:www\.)?videopremium\.(?:tv|me)/(?P\w+)(?:/.*)?' _TEST = { - u'url': u'http://videopremium.tv/4w7oadjsf156', - u'file': u'4w7oadjsf156.f4v', - u'info_dict': { - u"title": u"youtube-dl_test_video____a_________-BaW_jenozKc.mp4.mp4" + 'url': 'http://videopremium.tv/4w7oadjsf156', + 'info_dict': { + 'id': '4w7oadjsf156', + 'ext': 'f4v', + 'title': 'youtube-dl_test_video____a_________-BaW_jenozKc.mp4.mp4' }, - u'params': { - u'skip_download': True, + 'params': { + 'skip_download': True, }, - u'skip': u'Test file has been deleted.', + 'skip': 'Test file has been deleted.', } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('id') + video_id = self._match_id(url) webpage_url = 'http://videopremium.tv/' + video_id webpage = self._download_webpage(webpage_url, video_id) @@ -29,17 +30,17 @@ class VideoPremiumIE(InfoExtractor): # Download again, we need a cookie webpage = self._download_webpage( webpage_url, video_id, - note=u'Downloading webpage again (with cookie)') + note='Downloading webpage again (with cookie)') video_title = self._html_search_regex( - r'\s*(.+?)\s*<', webpage, u'video title') + r'\s*(.+?)\s*<', webpage, 'video title') return { - 'id': video_id, - 'url': "rtmp://e%d.md.iplay.md/play" % random.randint(1, 16), - 'play_path': "mp4:%s.f4v" % video_id, - 'page_url': "http://videopremium.tv/" + video_id, - 'player_url': "http://videopremium.tv/uplayer/uppod.swf", - 'ext': 'f4v', - 'title': video_title, + 'id': video_id, + 'url': "rtmp://e%d.md.iplay.md/play" % random.randint(1, 16), + 'play_path': "mp4:%s.f4v" % video_id, + 'page_url': "http://videopremium.tv/" + video_id, + 'player_url': "http://videopremium.tv/uplayer/uppod.swf", + 'ext': 'f4v', + 'title': video_title, } diff --git a/youtube_dl/extractor/videott.py b/youtube_dl/extractor/videott.py index a647807d0..1f938838c 100644 --- a/youtube_dl/extractor/videott.py +++ b/youtube_dl/extractor/videott.py @@ -58,4 +58,4 @@ class VideoTtIE(InfoExtractor): 'like_count': int_or_none(video['liked']), 'dislike_count': int_or_none(video['disliked']), 'formats': formats, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/videoweed.py b/youtube_dl/extractor/videoweed.py index 4a08ddd43..ca2e50935 100644 --- a/youtube_dl/extractor/videoweed.py +++ b/youtube_dl/extractor/videoweed.py @@ -23,4 +23,4 @@ class VideoWeedIE(NovaMovIE): 'title': 'optical illusion dissapeared image magic illusion', 'description': '' }, - } \ No newline at end of file + } diff --git a/youtube_dl/extractor/vidzi.py b/youtube_dl/extractor/vidzi.py new file mode 100644 index 000000000..08a5a7b8d --- /dev/null +++ b/youtube_dl/extractor/vidzi.py @@ -0,0 +1,32 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class VidziIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vidzi\.tv/(?P\w+)' + _TEST = { + 'url': 'http://vidzi.tv/cghql9yq6emu.html', + 'md5': '4f16c71ca0c8c8635ab6932b5f3f1660', + 'info_dict': { + 'id': 'cghql9yq6emu', + 'ext': 'mp4', + 'title': 'youtube-dl test video 1\\\\2\'3/4<5\\\\6ä7↭', + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + video_url = self._html_search_regex( + r'{\s*file\s*:\s*"([^"]+)"\s*}', webpage, 'video url') + title = self._html_search_regex( + r'(?s)

    (.*?)

    ', webpage, 'title') + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index bc01d7fbf..06b0bed41 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -7,18 +7,20 @@ import itertools from .common import InfoExtractor from .subtitles import SubtitlesInfoExtractor -from ..utils import ( +from ..compat import ( compat_HTTPError, compat_urllib_parse, compat_urllib_request, - clean_html, - get_element_by_attribute, + compat_urlparse, +) +from ..utils import ( ExtractorError, + InAdvancePagedList, + int_or_none, RegexNotFoundError, std_headers, unsmuggle_url, urlencode_postdata, - int_or_none, ) @@ -54,7 +56,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): # _VALID_URL matches Vimeo URLs _VALID_URL = r'''(?x) - (?P(?:https?:)?//)? + https?:// (?:(?:www|(?Pplayer))\.)? vimeo(?Ppro)?\.com/ (?!channels/[^/?#]+/?(?:$|[?#])|album/) @@ -89,6 +91,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'uploader_id': 'openstreetmapus', 'uploader': 'OpenStreetMap US', 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', + 'description': 'md5:380943ec71b89736ff4bf27183233d09', 'duration': 1595, }, }, @@ -103,6 +106,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'uploader': 'The BLN & Business of Software', 'uploader_id': 'theblnbusinessofsoftware', 'duration': 3610, + 'description': None, }, }, { @@ -117,6 +121,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'uploader_id': 'user18948128', 'uploader': 'Jaime Marquínez Ferrándiz', 'duration': 10, + 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.', }, 'params': { 'videopassword': 'youtube-dl', @@ -152,6 +157,18 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): 'duration': 62, } }, + { + # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ + 'url': 'https://player.vimeo.com/video/98044508', + 'note': 'The js code contains assignments to the same variable as the config', + 'info_dict': { + 'id': '98044508', + 'ext': 'mp4', + 'title': 'Pier Solar OUYA Official Trailer', + 'uploader': 'Tulio Gonçalves', + 'uploader_id': 'user28849593', + }, + }, ] def _verify_video_password(self, url, video_id, webpage): @@ -203,6 +220,7 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): # Extract ID from URL mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + orig_url = url if mobj.group('pro') or mobj.group('player'): url = 'http://player.vimeo.com/video/' + video_id @@ -238,11 +256,11 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): # We try to find out to which variable is assigned the config dic m_variable_name = re.search('(\w)\.video\.id', webpage) if m_variable_name is not None: - config_re = r'%s=({.+?});' % re.escape(m_variable_name.group(1)) + config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1)) else: config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] config = self._search_regex(config_re, webpage, 'info section', - flags=re.DOTALL) + flags=re.DOTALL) config = json.loads(config) except Exception as e: if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): @@ -273,18 +291,23 @@ class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] # Extract video description - video_description = None - try: - video_description = get_element_by_attribute("class", "description_wrapper", webpage) - if video_description: - video_description = clean_html(video_description) - except AssertionError as err: - # On some pages like (http://player.vimeo.com/video/54469442) the - # html tags are not closed, python 2.6 cannot handle it - if err.args[0] == 'we should not get here!': - pass - else: - raise + + video_description = self._html_search_regex( + r'(?s)]*>(.*?)
    ', + webpage, 'description', default=None) + if not video_description: + video_description = self._html_search_meta( + 'description', webpage, default=None) + if not video_description and mobj.group('pro'): + orig_webpage = self._download_webpage( + orig_url, video_id, + note='Downloading webpage for description', + fatal=False) + if orig_webpage: + video_description = self._html_search_meta( + 'description', orig_webpage, default=None) + if not video_description and not mobj.group('player'): + self._downloader.report_warning('Cannot find video description') # Extract video duration video_duration = int_or_none(config["video"].get("duration")) @@ -491,7 +514,7 @@ class VimeoReviewIE(InfoExtractor): 'info_dict': { 'id': '91613211', 'ext': 'mp4', - 'title': 'Death by dogma versus assembling agile - Sander Hoogendoorn', + 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', 'uploader': 'DevWeek Events', 'duration': 2773, 'thumbnail': 're:^https?://.*\.jpg$', @@ -529,3 +552,58 @@ class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE): def _real_extract(self, url): return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater') + + +class VimeoLikesIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P[0-9]+)/likes/?(?:$|[?#]|sort:)' + IE_NAME = 'vimeo:likes' + IE_DESC = 'Vimeo user likes' + _TEST = { + 'url': 'https://vimeo.com/user755559/likes/', + 'playlist_mincount': 293, + "info_dict": { + "description": "See all the videos urza likes", + "title": 'Videos urza likes', + }, + } + + def _real_extract(self, url): + user_id = self._match_id(url) + webpage = self._download_webpage(url, user_id) + page_count = self._int( + self._search_regex( + r'''(?x)
  • + .*?
    • \s* + ''', webpage, 'page count'), + 'page count', fatal=True) + PAGE_SIZE = 12 + title = self._html_search_regex( + r'(?s)

    (.+?)

    ', webpage, 'title', fatal=False) + description = self._html_search_meta('description', webpage) + + def _get_page(idx): + page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % ( + self.http_scheme(), user_id, idx + 1) + webpage = self._download_webpage( + page_url, user_id, + note='Downloading page %d/%d' % (idx + 1, page_count)) + video_list = self._search_regex( + r'(?s)
      ]*>(.*?)
    ', + webpage, 'video content') + paths = re.findall( + r']*>\s*-?\d+).*?\bid=(?P\d+)|(?:.+?\?.*?z=)?video(?P.*?)(?:\?|%2F|$))' + _VALID_URL = r'https?://(?:m\.)?vk\.com/(?:video_ext\.php\?.*?\boid=(?P-?\d+).*?\bid=(?P\d+)|(?:.+?\?.*?z=)?video(?P[^s].*?)(?:\?|%2F|$))' _NETRC_MACHINE = 'vk' _TESTS = [ @@ -29,17 +30,19 @@ class VKIE(InfoExtractor): 'title': 'ProtivoGunz - Хуёвая песня', 'uploader': 're:Noize MC.*', 'duration': 195, + 'upload_date': '20120212', }, }, { - 'url': 'http://vk.com/video4643923_163339118', - 'md5': 'f79bccb5cd182b1f43502ca5685b2b36', + 'url': 'http://vk.com/video205387401_165548505', + 'md5': '6c0aeb2e90396ba97035b9cbde548700', 'info_dict': { - 'id': '163339118', + 'id': '165548505', 'ext': 'mp4', - 'uploader': 'Elya Iskhakova', - 'title': 'Dream Theater - Hollow Years Live at Budokan 720*', - 'duration': 558, + 'uploader': 'Tom Cruise', + 'title': 'No name', + 'duration': 9, + 'upload_date': '20130721' } }, { @@ -52,9 +55,12 @@ class VKIE(InfoExtractor): 'uploader': 'Vladimir Gavrin', 'title': 'Lin Dan', 'duration': 101, + 'upload_date': '20120730', } }, { + # VIDEO NOW REMOVED + # please update if you find a video whose URL follows the same pattern 'url': 'http://vk.com/video-8871596_164049491', 'md5': 'a590bcaf3d543576c9bd162812387666', 'note': 'Only available for registered users', @@ -64,18 +70,7 @@ class VKIE(InfoExtractor): 'uploader': 'Триллеры', 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]', 'duration': 8352, - }, - 'skip': 'Requires vk account credentials', - }, - { - 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', - 'md5': 'd82c22e449f036282d1d3f7f4d276869', - 'info_dict': { - 'id': '166094326', - 'ext': 'mp4', - 'uploader': 'Киномания - лучшее из мира кино', - 'title': 'Запах женщины (1992)', - 'duration': 9392, + 'upload_date': '20121218' }, 'skip': 'Requires vk account credentials', }, @@ -88,6 +83,7 @@ class VKIE(InfoExtractor): 'uploader': 'Киномания - лучшее из мира кино', 'title': ' ', 'duration': 7291, + 'upload_date': '20140328', }, 'skip': 'Requires vk account credentials', }, @@ -100,9 +96,15 @@ class VKIE(InfoExtractor): 'ext': 'mp4', 'title': 'Книга Илая', 'duration': 6771, + 'upload_date': '20140626', }, 'skip': 'Only works from Russia', }, + { + # removed video, just testing that we match the pattern + 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', + 'only_matching': True, + }, ] def _login(self): @@ -119,7 +121,7 @@ class VKIE(InfoExtractor): } request = compat_urllib_request.Request('https://login.vk.com/?act=login', - compat_urllib_parse.urlencode(login_form).encode('utf-8')) + compat_urllib_parse.urlencode(login_form).encode('utf-8')) login_page = self._download_webpage(request, None, note='Logging in as %s' % username) if re.search(r'onLoginFailed', login_page): @@ -138,9 +140,21 @@ class VKIE(InfoExtractor): info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id info_page = self._download_webpage(info_url, video_id) - if re.search(r'Please log in or <', info_page): - raise ExtractorError('This video is only available for registered users, ' - 'use --username and --password options to provide account credentials.', expected=True) + ERRORS = { + r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': + 'Video %s has been removed from public access due to rightholder complaint.', + + r'Please log in or <': + 'Video %s is only available for registered users, ' + 'use --username and --password options to provide account credentials.', + + r'Unknown error': + 'Video %s does not exist.' + } + + for error_re, error_msg in ERRORS.items(): + if re.search(error_re, info_page): + raise ExtractorError(error_msg % video_id, expected=True) m_yt = re.search(r'src="(http://www.youtube.com/.*?)"', info_page) if m_yt is not None: @@ -159,6 +173,13 @@ class VKIE(InfoExtractor): data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars') data = json.loads(data_json) + # Extract upload date + upload_date = None + mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page) + if mobj is not None: + mobj.group(1) + ' ' + mobj.group(2) + upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2)) + formats = [{ 'format_id': k, 'url': v, @@ -173,5 +194,28 @@ class VKIE(InfoExtractor): 'title': unescapeHTML(data['md_title']), 'thumbnail': data.get('jpg'), 'uploader': data.get('md_author'), - 'duration': data.get('duration') + 'duration': data.get('duration'), + 'upload_date': upload_date, } + + +class VKUserVideosIE(InfoExtractor): + IE_NAME = 'vk.com:user-videos' + IE_DESC = 'vk.com:All of a user\'s videos' + _VALID_URL = r'https?://vk\.com/videos(?P[0-9]+)(?:m\?.*)?' + _TEMPLATE_URL = 'https://vk.com/videos' + _TEST = { + 'url': 'http://vk.com/videos205387401', + 'playlist_mincount': 4, + } + + def _real_extract(self, url): + page_id = self._match_id(url) + page = self._download_webpage(url, page_id) + video_ids = orderedSet( + m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page)) + url_entries = [ + self.url_result( + 'http://vk.com/video' + video_id, 'VK', video_id=video_id) + for video_id in video_ids] + return self.playlist_result(url_entries, page_id) diff --git a/youtube_dl/extractor/vrt.py b/youtube_dl/extractor/vrt.py new file mode 100644 index 000000000..bbd3bbf7b --- /dev/null +++ b/youtube_dl/extractor/vrt.py @@ -0,0 +1,95 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import float_or_none + + +class VRTIE(InfoExtractor): + _VALID_URL = r'https?://(?:deredactie|sporza|cobra)\.be/cm/(?:[^/]+/)+(?P[^/]+)/*' + _TESTS = [ + # deredactie.be + { + 'url': 'http://deredactie.be/cm/vrtnieuws/videozone/programmas/journaal/EP_141025_JOL', + 'md5': '4cebde1eb60a53782d4f3992cbd46ec8', + 'info_dict': { + 'id': '2129880', + 'ext': 'flv', + 'title': 'Het journaal L - 25/10/14', + 'description': None, + 'timestamp': 1414271750.949, + 'upload_date': '20141025', + 'duration': 929, + } + }, + # sporza.be + { + 'url': 'http://sporza.be/cm/sporza/videozone/programmas/extratime/EP_141020_Extra_time', + 'md5': '11f53088da9bf8e7cfc42456697953ff', + 'info_dict': { + 'id': '2124639', + 'ext': 'flv', + 'title': 'Bekijk Extra Time van 20 oktober', + 'description': 'md5:83ac5415a4f1816c6a93f8138aef2426', + 'timestamp': 1413835980.560, + 'upload_date': '20141020', + 'duration': 3238, + } + }, + # cobra.be + { + 'url': 'http://cobra.be/cm/cobra/videozone/rubriek/film-videozone/141022-mv-ellis-cafecorsari', + 'md5': '78a2b060a5083c4f055449a72477409d', + 'info_dict': { + 'id': '2126050', + 'ext': 'flv', + 'title': 'Bret Easton Ellis in Café Corsari', + 'description': 'md5:f699986e823f32fd6036c1855a724ee9', + 'timestamp': 1413967500.494, + 'upload_date': '20141022', + 'duration': 661, + } + }, + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_id = self._search_regex( + r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False) + + formats = [] + mobj = re.search( + r'data-video-iphone-server="(?P[^"]+)"\s+data-video-iphone-path="(?P[^"]+)"', + webpage) + if mobj: + formats.extend(self._extract_m3u8_formats( + '%s/%s' % (mobj.group('server'), mobj.group('path')), + video_id, 'mp4')) + mobj = re.search(r'data-video-src="(?P[^"]+)"', webpage) + if mobj: + formats.extend(self._extract_f4m_formats( + '%s/manifest.f4m' % mobj.group('src'), video_id)) + self._sort_formats(formats) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage, default=None) + thumbnail = self._og_search_thumbnail(webpage) + timestamp = float_or_none(self._search_regex( + r'data-video-sitestat-pubdate="(\d+)"', webpage, 'timestamp', fatal=False), 1000) + duration = float_or_none(self._search_regex( + r'data-video-duration="(\d+)"', webpage, 'duration', fatal=False), 1000) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vube.py b/youtube_dl/extractor/vube.py index 2544c24bd..1b2f731e9 100644 --- a/youtube_dl/extractor/vube.py +++ b/youtube_dl/extractor/vube.py @@ -6,6 +6,7 @@ from .common import InfoExtractor from ..utils import ( int_or_none, compat_str, + ExtractorError, ) @@ -16,6 +17,24 @@ class VubeIE(InfoExtractor): _TESTS = [ { + 'url': 'http://vube.com/trending/William+Wei/Y8NUZ69Tf7?t=s', + 'md5': 'e7aabe1f8f1aa826b9e4735e1f9cee42', + 'info_dict': { + 'id': 'Y8NUZ69Tf7', + 'ext': 'mp4', + 'title': 'Best Drummer Ever [HD]', + 'description': 'md5:2d63c4b277b85c2277761c2cf7337d71', + 'thumbnail': 're:^https?://.*\.jpg', + 'uploader': 'William', + 'timestamp': 1406876915, + 'upload_date': '20140801', + 'duration': 258.051, + 'like_count': int, + 'dislike_count': int, + 'comment_count': int, + 'categories': ['amazing', 'hd', 'best drummer ever', 'william wei', 'bucket drumming', 'street drummer', 'epic street drumming'], + }, + }, { 'url': 'http://vube.com/Chiara+Grispo+Video+Channel/YL2qNPkqon', 'md5': 'db7aba89d4603dadd627e9d1973946fe', 'info_dict': { @@ -32,7 +51,8 @@ class VubeIE(InfoExtractor): 'dislike_count': int, 'comment_count': int, 'categories': ['pop', 'music', 'cover', 'singing', 'jessie j', 'price tag', 'chiara grispo'], - } + }, + 'skip': 'Removed due to DMCA', }, { 'url': 'http://vube.com/SerainaMusic/my-7-year-old-sister-and-i-singing-alive-by-krewella/UeBhTudbfS?t=s&n=1', @@ -51,7 +71,8 @@ class VubeIE(InfoExtractor): 'dislike_count': int, 'comment_count': int, 'categories': ['seraina', 'jessica', 'krewella', 'alive'], - } + }, + 'skip': 'Removed due to DMCA', }, { 'url': 'http://vube.com/vote/Siren+Gene/0nmsMY5vEq?n=2&t=s', 'md5': '0584fc13b50f887127d9d1007589d27f', @@ -69,7 +90,8 @@ class VubeIE(InfoExtractor): 'dislike_count': int, 'comment_count': int, 'categories': ['let it go', 'cover', 'idina menzel', 'frozen', 'singing', 'disney', 'siren gene'], - } + }, + 'skip': 'Removed due to DMCA', } ] @@ -102,6 +124,11 @@ class VubeIE(InfoExtractor): self._sort_formats(formats) + if not formats and video.get('vst') == 'dmca': + raise ExtractorError( + 'This video has been removed in response to a complaint received under the US Digital Millennium Copyright Act.', + expected=True) + title = video['title'] description = video.get('description') thumbnail = self._proto_relative_url(video.get('thumbnail_src'), scheme='http:') diff --git a/youtube_dl/extractor/vuclip.py b/youtube_dl/extractor/vuclip.py index fb0600f1a..ec3c010ad 100644 --- a/youtube_dl/extractor/vuclip.py +++ b/youtube_dl/extractor/vuclip.py @@ -5,6 +5,7 @@ import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse_urlparse, + ExtractorError, parse_duration, qualities, ) @@ -14,13 +15,12 @@ class VuClipIE(InfoExtractor): _VALID_URL = r'http://(?:m\.)?vuclip\.com/w\?.*?cid=(?P[0-9]+)' _TEST = { - 'url': 'http://m.vuclip.com/w?cid=843902317&fid=63532&z=1007&nvar&frm=index.html&bu=4757321434', - 'md5': '92ac9d1ccefec4f0bb474661ab144fcf', + 'url': 'http://m.vuclip.com/w?cid=922692425&fid=70295&z=1010&nvar&frm=index.html', 'info_dict': { - 'id': '843902317', + 'id': '922692425', 'ext': '3gp', - 'title': 'Movie Trailer: Noah', - 'duration': 139, + 'title': 'The Toy Soldiers - Hollywood Movie Trailer', + 'duration': 180, } } @@ -37,16 +37,32 @@ class VuClipIE(InfoExtractor): webpage = self._download_webpage( adfree_url, video_id, note='Download post-ad page') + error_msg = self._html_search_regex( + r'

    (.*?)

    ', webpage, 'error message', + default=None) + if error_msg: + raise ExtractorError( + '%s said: %s' % (self.IE_NAME, error_msg), expected=True) + + # These clowns alternate between two page types links_code = self._search_regex( - r'(?s) + ) + (.*?) + (?: + + ) + ''', webpage, 'links') title = self._html_search_regex( r'(.*?)-\s*Vuclip', webpage, 'title').strip() quality_order = qualities(['Reg', 'Hi']) formats = [] for url, q in re.findall( - r'(?P[^<]+)', links_code): + r'[^"]+)".*?>(?:]*>)?(?P[^<]+)(?:)?', links_code): format_id = compat_urllib_parse_urlparse(url).scheme + '-' + q formats.append({ 'format_id': format_id, @@ -56,7 +72,7 @@ class VuClipIE(InfoExtractor): self._sort_formats(formats) duration = parse_duration(self._search_regex( - r'\(([0-9:]+)\)

    ', webpage, 'duration', fatal=False)) + r'\(([0-9:]+)\)    ', webpage, 'duration', fatal=False)) return { 'id': video_id, diff --git a/youtube_dl/extractor/walla.py b/youtube_dl/extractor/walla.py new file mode 100644 index 000000000..672bda7a7 --- /dev/null +++ b/youtube_dl/extractor/walla.py @@ -0,0 +1,89 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .subtitles import SubtitlesInfoExtractor +from ..utils import ( + xpath_text, + int_or_none, +) + + +class WallaIE(SubtitlesInfoExtractor): + _VALID_URL = r'http://vod\.walla\.co\.il/[^/]+/(?P\d+)/(?P.+)' + _TEST = { + 'url': 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one', + 'info_dict': { + 'id': '2642630', + 'display_id': 'one-direction-all-for-one', + 'ext': 'flv', + 'title': 'וואן דיירקשן: ההיסטריה', + 'description': 'md5:de9e2512a92442574cdb0913c49bc4d8', + 'thumbnail': 're:^https?://.*\.jpg', + 'duration': 3600, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + } + + _SUBTITLE_LANGS = { + 'עברית': 'heb', + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + video = self._download_xml( + 'http://video2.walla.co.il/?w=null/null/%s/@@/video/flv_pl' % video_id, + display_id) + + item = video.find('./items/item') + + title = xpath_text(item, './title', 'title') + description = xpath_text(item, './synopsis', 'description') + thumbnail = xpath_text(item, './preview_pic', 'thumbnail') + duration = int_or_none(xpath_text(item, './duration', 'duration')) + + subtitles = {} + for subtitle in item.findall('./subtitles/subtitle'): + lang = xpath_text(subtitle, './title') + subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = xpath_text(subtitle, './src') + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + subtitles = self.extract_subtitles(video_id, subtitles) + + formats = [] + for quality in item.findall('./qualities/quality'): + format_id = xpath_text(quality, './title') + fmt = { + 'url': 'rtmp://wafla.walla.co.il/vod', + 'play_path': xpath_text(quality, './src'), + 'player_url': 'http://isc.walla.co.il/w9/swf/video_swf/vod/WallaMediaPlayerAvod.swf', + 'page_url': url, + 'ext': 'flv', + 'format_id': xpath_text(quality, './title'), + } + m = re.search(r'^(?P\d+)[Pp]', format_id) + if m: + fmt['height'] = int(m.group('height')) + formats.append(fmt) + self._sort_formats(formats) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles, + } diff --git a/youtube_dl/extractor/wat.py b/youtube_dl/extractor/wat.py index 46b4d9133..bf9e40bad 100644 --- a/youtube_dl/extractor/wat.py +++ b/youtube_dl/extractor/wat.py @@ -5,7 +5,10 @@ import re import hashlib from .common import InfoExtractor -from ..utils import unified_strdate +from ..utils import ( + ExtractorError, + unified_strdate, +) class WatIE(InfoExtractor): @@ -37,6 +40,7 @@ class WatIE(InfoExtractor): 'upload_date': '20140816', 'duration': 2910, }, + 'skip': "Ce contenu n'est pas disponible pour l'instant.", }, ] @@ -57,6 +61,11 @@ class WatIE(InfoExtractor): video_info = self.download_video_info(real_id) + error_desc = video_info.get('error_desc') + if error_desc: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error_desc), expected=True) + geo_list = video_info.get('geoList') country = geo_list[0] if geo_list else '' diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 54d37da61..93a6e6454 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -224,4 +224,4 @@ class WDRMausIE(InfoExtractor): 'upload_date': upload_date, } -# TODO test _1 \ No newline at end of file +# TODO test _1 diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py index b24297a40..20bb039d3 100644 --- a/youtube_dl/extractor/weibo.py +++ b/youtube_dl/extractor/weibo.py @@ -41,7 +41,7 @@ class WeiboIE(InfoExtractor): videos_urls = sorted(videos_urls, key=lambda u: 'video.sina.com' in u) player_url = videos_urls[-1] m_sina = re.match(r'https?://video\.sina\.com\.cn/v/b/(\d+)-\d+\.html', - player_url) + player_url) if m_sina is not None: self.to_screen('Sina video detected') sina_id = m_sina.group(1) diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index c27dda944..d6dec25ca 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -37,7 +37,7 @@ class WimpIE(InfoExtractor): video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) video_url = self._search_regex( - r's1\.addVariable\("file",\s*"([^"]+)"\);', webpage, 'video URL') + r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", webpage, 'video URL') if YoutubeIE.suitable(video_url): self.to_screen('Found YouTube video') return { diff --git a/youtube_dl/extractor/wistia.py b/youtube_dl/extractor/wistia.py index e6bfa9e14..748443f81 100644 --- a/youtube_dl/extractor/wistia.py +++ b/youtube_dl/extractor/wistia.py @@ -1,13 +1,14 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor +from ..utils import ExtractorError, compat_urllib_request class WistiaIE(InfoExtractor): _VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P[a-z0-9]+)' + _API_URL = 'http://fast.wistia.com/embed/medias/{0:}.json' _TEST = { 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt', @@ -24,11 +25,13 @@ class WistiaIE(InfoExtractor): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - data_json = self._html_search_regex( - r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data') - - data = json.loads(data_json) + request = compat_urllib_request.Request(self._API_URL.format(video_id)) + request.add_header('Referer', url) # Some videos require this. + data_json = self._download_json(request, video_id) + if data_json.get('error'): + raise ExtractorError('Error while getting the playlist', + expected=True) + data = data_json['media'] formats = [] thumbnails = [] diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py index 4e89acd81..d5c26a032 100644 --- a/youtube_dl/extractor/worldstarhiphop.py +++ b/youtube_dl/extractor/worldstarhiphop.py @@ -13,37 +13,35 @@ class WorldStarHipHopIE(InfoExtractor): "info_dict": { "id": "wshh6a7q1ny0G34ZwuIO", "ext": "mp4", - "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" + "title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" } } def _real_extract(self, url): - m = re.match(self._VALID_URL, url) - video_id = m.group('id') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - webpage_src = self._download_webpage(url, video_id) - - m_vevo_id = re.search(r'videoId=(.*?)&?', - webpage_src) + m_vevo_id = re.search(r'videoId=(.*?)&?', webpage) if m_vevo_id is not None: return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo') video_url = self._search_regex( - r'so\.addVariable\("file","(.*?)"\)', webpage_src, 'video URL') + r'so\.addVariable\("file","(.*?)"\)', webpage, 'video URL') if 'youtube' in video_url: return self.url_result(video_url, ie='Youtube') video_title = self._html_search_regex( - r"(.*)", webpage_src, 'title') + r'(?s)
    \s*

    (.*?)

    ', + webpage, 'title') # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video. thumbnail = self._html_search_regex( - r'rel="image_src" href="(.*)" />', webpage_src, 'thumbnail', + r'rel="image_src" href="(.*)" />', webpage, 'thumbnail', fatal=False) if not thumbnail: - _title = r"""candytitles.*>(.*)""" - mobj = re.search(_title, webpage_src) + _title = r'candytitles.*>(.*)' + mobj = re.search(_title, webpage) if mobj is not None: video_title = mobj.group(1) @@ -53,4 +51,3 @@ class WorldStarHipHopIE(InfoExtractor): 'title': video_title, 'thumbnail': thumbnail, } - diff --git a/youtube_dl/extractor/wrzuta.py b/youtube_dl/extractor/wrzuta.py index 34dd6d952..c42764921 100644 --- a/youtube_dl/extractor/wrzuta.py +++ b/youtube_dl/extractor/wrzuta.py @@ -27,15 +27,15 @@ class WrzutaIE(InfoExtractor): 'description': 'md5:7fb5ef3c21c5893375fda51d9b15d9cd', }, }, { - 'url': 'http://w729.wrzuta.pl/audio/9oXJqdcndqv/david_guetta_amp_showtek_ft._vassy_-_bad', - 'md5': '1e546a18e1c22ac6e9adce17b8961ff5', + 'url': 'http://jolka85.wrzuta.pl/audio/063jOPX5ue2/liber_natalia_szroeder_-_teraz_ty', + 'md5': 'bc78077859bea7bcfe4295d7d7fc9025', 'info_dict': { - 'id': '9oXJqdcndqv', + 'id': '063jOPX5ue2', 'ext': 'ogg', - 'title': 'David Guetta & Showtek ft. Vassy - Bad', - 'duration': 270, - 'uploader_id': 'w729', - 'description': 'md5:4628f01c666bbaaecefa83476cfa794a', + 'title': 'Liber & Natalia Szroeder - Teraz Ty', + 'duration': 203, + 'uploader_id': 'jolka85', + 'description': 'md5:2d2b6340f9188c8c4cd891580e481096', }, }] @@ -49,16 +49,17 @@ class WrzutaIE(InfoExtractor): quality = qualities(['SD', 'MQ', 'HQ', 'HD']) - audio_table = {'flv': 'mp3', 'webm': 'ogg'} + audio_table = {'flv': 'mp3', 'webm': 'ogg', '???': 'mp3'} embedpage = self._download_json('http://www.wrzuta.pl/npp/embed/%s/%s' % (uploader, video_id), video_id) formats = [] for media in embedpage['url']: + fmt = media['type'].split('@')[0] if typ == 'audio': - ext = audio_table[media['type'].split('@')[0]] + ext = audio_table.get(fmt, fmt) else: - ext = media['type'].split('@')[0] + ext = fmt formats.append({ 'format_id': '%s_%s' % (ext, media['quality'].lower()), diff --git a/youtube_dl/extractor/xbef.py b/youtube_dl/extractor/xbef.py index 71bd7c463..1b4e88365 100644 --- a/youtube_dl/extractor/xbef.py +++ b/youtube_dl/extractor/xbef.py @@ -47,4 +47,3 @@ class XBefIE(InfoExtractor): 'thumbnail': thumbnail, 'age_limit': 18, } - diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 4e8fbde8d..6b37bcbc9 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -42,7 +42,7 @@ class XHamsterIE(InfoExtractor): } ] - def _real_extract(self,url): + def _real_extract(self, url): def extract_video_url(webpage): mp4 = re.search(r'', webpage) if mp4 is None: @@ -67,17 +67,17 @@ class XHamsterIE(InfoExtractor): description = mobj.group(1) if mobj else None upload_date = self._html_search_regex(r'hint=\'(\d{4}-\d{2}-\d{2}) \d{2}:\d{2}:\d{2} [A-Z]{3,4}\'', - webpage, 'upload date', fatal=False) + webpage, 'upload date', fatal=False) if upload_date: upload_date = unified_strdate(upload_date) uploader_id = self._html_search_regex(r']+>(?P[^<]+)', - webpage, 'uploader id', default='anonymous') + webpage, 'uploader id', default='anonymous') thumbnail = self._html_search_regex(r'', webpage, 'thumbnail', fatal=False) duration = parse_duration(self._html_search_regex(r'Runtime: (\d+:\d+)
    ', - webpage, 'duration', fatal=False)) + webpage, 'duration', fatal=False)) view_count = self._html_search_regex(r'Views: ([^<]+)

    ', webpage, 'view count', fatal=False) if view_count: diff --git a/youtube_dl/extractor/xminus.py b/youtube_dl/extractor/xminus.py new file mode 100644 index 000000000..a3fd8f48c --- /dev/null +++ b/youtube_dl/extractor/xminus.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_chr, + compat_ord, +) +from ..utils import ( + int_or_none, + parse_filesize, +) + + +class XMinusIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?x-minus\.org/track/(?P[0-9]+)' + _TEST = { + 'url': 'http://x-minus.org/track/4542/%D0%BF%D0%B5%D1%81%D0%B5%D0%BD%D0%BA%D0%B0-%D1%88%D0%BE%D1%84%D0%B5%D1%80%D0%B0.html', + 'md5': '401a15f2d2dcf6d592cb95528d72a2a8', + 'info_dict': { + 'id': '4542', + 'ext': 'mp3', + 'title': 'Леонид Агутин-Песенка шофера', + 'duration': 156, + 'tbr': 320, + 'filesize_approx': 5900000, + 'view_count': int, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + artist = self._html_search_regex( + r'minus_track\.artist="(.+?)"', webpage, 'artist') + title = artist + '-' + self._html_search_regex( + r'minus_track\.title="(.+?)"', webpage, 'title') + duration = int_or_none(self._html_search_regex( + r'minus_track\.dur_sec=\'([0-9]*?)\'', + webpage, 'duration', fatal=False)) + filesize_approx = parse_filesize(self._html_search_regex( + r'
    \s*([0-9.]+\s*[a-zA-Z][bB])', + webpage, 'approximate filesize', fatal=False)) + tbr = int_or_none(self._html_search_regex( + r'
    \s*([0-9]+)\s*kbps', + webpage, 'bitrate', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'
    (.*?)\s+-\s+XNXX.COM', - webpage, 'title') + webpage, 'title') video_thumbnail = self._search_regex(r'url_bigthumb=(.*?)&', - webpage, 'thumbnail', fatal=False) + webpage, 'thumbnail', fatal=False) return { 'id': video_id, diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 273d93d9e..38448e7c0 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -20,7 +20,7 @@ class XTubeIE(InfoExtractor): 'id': 'kVTUy_G222_', 'ext': 'mp4', 'title': 'strange erotica', - 'description': 'surreal gay themed erotica...almost an ET kind of thing', + 'description': 'http://www.xtube.com an ET kind of thing', 'uploader': 'greenshowers', 'duration': 450, 'age_limit': 18, @@ -97,7 +97,7 @@ class XTubeUserIE(InfoExtractor): url, username, note='Retrieving profile page') video_count = int(self._search_regex( - r'%s\'s Videos \(([0-9]+)\)'%username, profile_page, + r'%s\'s Videos \(([0-9]+)\)' % username, profile_page, 'video count')) PAGE_SIZE = 25 diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 3ab6017cd..0fdb12243 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -1,3 +1,4 @@ +# coding: utf-8 from __future__ import unicode_literals import itertools @@ -6,6 +7,7 @@ import re from .common import InfoExtractor, SearchInfoExtractor from ..utils import ( + ExtractorError, compat_urllib_parse, compat_urlparse, clean_html, @@ -15,7 +17,7 @@ from ..utils import ( class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'(?Phttps?://(?:screen|movies)\.yahoo\.com/.*?-(?P[0-9]+)(?:-[a-z]+)?\.html)' + _VALID_URL = r'(?P(?Phttps?://(?:[a-zA-Z]{2}\.)?[\da-zA-Z_-]+\.yahoo\.com)/(?:[^/]+/)*(?P.+?)-(?P[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', @@ -25,6 +27,7 @@ class YahooIE(InfoExtractor): 'ext': 'mp4', 'title': 'Julian Smith & Travis Legg Watch Julian Smith', 'description': 'Julian and Travis watch Julian Smith', + 'duration': 6863, }, }, { @@ -34,19 +37,10 @@ class YahooIE(InfoExtractor): 'id': 'd1dedf8c-d58c-38c3-8963-e899929ae0a9', 'ext': 'mp4', 'title': 'Codefellas - The Cougar Lies with Spanish Moss', - 'description': 'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', + 'description': 'md5:66b627ab0a282b26352136ca96ce73c1', + 'duration': 151, }, }, - { - 'url': 'https://movies.yahoo.com/video/world-loves-spider-man-190819223.html', - 'md5': '410b7104aa9893b765bc22787a22f3d9', - 'info_dict': { - 'id': '516ed8e2-2c4f-339f-a211-7a8b49d30845', - 'ext': 'mp4', - 'title': 'The World Loves Spider-Man', - 'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''', - } - }, { 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', 'md5': '60e8ac193d8fb71997caa8fce54c6460', @@ -55,15 +49,95 @@ class YahooIE(InfoExtractor): 'ext': 'mp4', 'title': "Yahoo Saves 'Community'", 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + 'duration': 170, } }, + { + 'url': 'https://tw.screen.yahoo.com/taipei-opinion-poll/選情站報-街頭民調-台北市篇-102823042.html', + 'md5': '92a7fdd8a08783c68a174d7aa067dde8', + 'info_dict': { + 'id': '7a23b569-7bea-36cb-85b9-bd5301a0a1fb', + 'ext': 'mp4', + 'title': '選情站報 街頭民調 台北市篇', + 'description': '選情站報 街頭民調 台北市篇', + 'duration': 429, + } + }, + { + 'url': 'https://uk.screen.yahoo.com/editor-picks/cute-raccoon-freed-drain-using-091756545.html', + 'md5': '0b51660361f0e27c9789e7037ef76f4b', + 'info_dict': { + 'id': 'b3affa53-2e14-3590-852b-0e0db6cd1a58', + 'ext': 'mp4', + 'title': 'Cute Raccoon Freed From Drain\u00a0Using Angle Grinder', + 'description': 'md5:f66c890e1490f4910a9953c941dee944', + 'duration': 97, + } + }, + { + 'url': 'https://ca.sports.yahoo.com/video/program-makes-hockey-more-affordable-013127711.html', + 'md5': '57e06440778b1828a6079d2f744212c4', + 'info_dict': { + 'id': 'c9fa2a36-0d4d-3937-b8f6-cc0fb1881e73', + 'ext': 'mp4', + 'title': 'Program that makes hockey more affordable not offered in Manitoba', + 'description': 'md5:c54a609f4c078d92b74ffb9bf1f496f4', + 'duration': 121, + } + }, { + 'url': 'https://ca.finance.yahoo.com/news/20-most-valuable-brands-world-112600775.html', + 'md5': '3e401e4eed6325aa29d9b96125fd5b4f', + 'info_dict': { + 'id': 'c1b4c09c-8ed8-3b65-8b05-169c55358a83', + 'ext': 'mp4', + 'title': "Apple Is The World's Most Valuable Brand", + 'description': 'md5:73eabc1a11c6f59752593b2ceefa1262', + 'duration': 21, + } + }, { + 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', + 'md5': '67010fdf3a08d290e060a4dd96baa07b', + 'info_dict': { + 'id': 'f885cf7f-43d4-3450-9fac-46ac30ece521', + 'ext': 'mp4', + 'title': 'China Moses Is Crazy About the Blues', + 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', + 'duration': 128, + } + }, { + 'url': 'https://in.lifestyle.yahoo.com/video/connect-dots-dark-side-virgo-090247395.html', + 'md5': 'd9a083ccf1379127bf25699d67e4791b', + 'info_dict': { + 'id': '52aeeaa3-b3d1-30d8-9ef8-5d0cf05efb7c', + 'ext': 'mp4', + 'title': 'Connect the Dots: Dark Side of Virgo', + 'description': 'md5:1428185051cfd1949807ad4ff6d3686a', + 'duration': 201, + } + }, { + 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', + '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') url = mobj.group('url') - webpage = self._download_webpage(url, video_id) + host = mobj.group('host') + webpage = self._download_webpage(url, display_id) + + # Look for iframed media first + iframe_m = re.search(r']+src="(/video/.+?-\d+\.html\?format=embed.*?)"', webpage) + if iframe_m: + iframepage = self._download_webpage( + host + iframe_m.group(1), display_id, 'Downloading iframe webpage') + items_json = self._search_regex( + r'mediaItems: (\[.+?\])$', iframepage, 'items', flags=re.MULTILINE, default=None) + if items_json: + items = json.loads(items_json) + video_id = items[0]['id'] + return self._get_info(video_id, display_id, webpage) items_json = self._search_regex( r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE, @@ -74,20 +148,22 @@ class YahooIE(InfoExtractor): r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', r'"first_videoid"\s*:\s*"([^"]+)"', ] - long_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') - video_id = long_id + video_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') else: items = json.loads(items_json) info = items['mediaItems']['query']['results']['mediaObj'][0] # The 'meta' field is not always in the video webpage, we request it # from another page - long_id = info['id'] - return self._get_info(long_id, video_id, webpage) + video_id = info['id'] + return self._get_info(video_id, display_id, webpage) - def _get_info(self, long_id, video_id, webpage): + def _get_info(self, video_id, display_id, webpage): + region = self._search_regex( + r'\\?"region\\?"\s*:\s*\\?"([^"]+?)\\?"', + webpage, 'region', fatal=False, default='US') query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' - ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"' - ' AND protocol="http"' % long_id) + ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="%s"' + ' AND protocol="http"' % (video_id, region)) data = compat_urllib_parse.urlencode({ 'q': query, 'env': 'prod', @@ -95,9 +171,17 @@ class YahooIE(InfoExtractor): }) query_result = self._download_json( 'http://video.query.yahoo.com/v1/public/yql?' + data, - video_id, 'Downloading video info') + display_id, 'Downloading video info') + info = query_result['query']['results']['mediaObj'][0] - meta = info['meta'] + meta = info.get('meta') + + if not meta: + msg = info['status'].get('msg') + if msg: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, msg), expected=True) + raise ExtractorError('Unable to extract media object meta') formats = [] for s in info['streams']: @@ -124,36 +208,15 @@ class YahooIE(InfoExtractor): return { 'id': video_id, + 'display_id': display_id, 'title': meta['title'], 'formats': formats, 'description': clean_html(meta['description']), 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), + 'duration': int_or_none(meta.get('duration')), } -class YahooNewsIE(YahooIE): - IE_NAME = 'yahoo:news' - _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P\d*?)\.html' - - _TESTS = [{ - 'url': 'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', - 'md5': '67010fdf3a08d290e060a4dd96baa07b', - 'info_dict': { - 'id': '104538833', - 'ext': 'mp4', - 'title': 'China Moses Is Crazy About the Blues', - 'description': 'md5:9900ab8cd5808175c7b3fe55b979bed0', - }, - }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) - long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, 'long id') - return self._get_info(long_id, video_id, webpage) - - class YahooSearchIE(SearchInfoExtractor): IE_DESC = 'Yahoo screen search' _MAX_RESULTS = 1000 @@ -166,7 +229,7 @@ class YahooSearchIE(SearchInfoExtractor): for pagenum in itertools.count(0): result_url = 'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30) info = self._download_json(result_url, query, - note='Downloading results page '+str(pagenum+1)) + note='Downloading results page ' + str(pagenum + 1)) m = info['m'] results = info['results'] diff --git a/youtube_dl/extractor/ynet.py b/youtube_dl/extractor/ynet.py new file mode 100644 index 000000000..7b621a9e3 --- /dev/null +++ b/youtube_dl/extractor/ynet.py @@ -0,0 +1,50 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..utils import compat_urllib_parse + + +class YnetIE(InfoExtractor): + _VALID_URL = r'http://(?:.+?\.)?ynet\.co\.il/(?:.+?/)?0,7340,(?PL(?:-[0-9]+)+),00\.html' + _TESTS = [ + { + 'url': 'http://hot.ynet.co.il/home/0,7340,L-11659-99244,00.html', + 'info_dict': { + 'id': 'L-11659-99244', + 'ext': 'flv', + 'title': 'איש לא יודע מאיפה באנו', + 'thumbnail': 're:^https?://.*\.jpg', + } + }, { + 'url': 'http://hot.ynet.co.il/home/0,7340,L-8859-84418,00.html', + 'info_dict': { + 'id': 'L-8859-84418', + 'ext': 'flv', + 'title': "צפו: הנשיקה הלוהטת של תורגי' ויוליה פלוטקין", + 'thumbnail': 're:^https?://.*\.jpg', + } + } + ] + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + content = compat_urllib_parse.unquote_plus(self._og_search_video_url(webpage)) + config = json.loads(self._search_regex(r'config=({.+?})$', content, 'video config')) + f4m_url = config['clip']['url'] + title = self._og_search_title(webpage) + m = re.search(r'ynet - HOT -- (["\']+)(?P.+?)\1', title) + if m: + title = m.group('title') + + return { + 'id': video_id, + 'title': title, + 'formats': self._extract_f4m_formats(f4m_url, video_id), + 'thumbnail': self._og_search_thumbnail(webpage), + } diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py index b86331e3c..c642075dc 100644 --- a/youtube_dl/extractor/youjizz.py +++ b/youtube_dl/extractor/youjizz.py @@ -9,40 +9,30 @@ from ..utils import ( class YouJizzIE(InfoExtractor): - _VALID_URL = r'^https?://(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+)\.html$' + _VALID_URL = r'https?://(?:\w+\.)?youjizz\.com/videos/[^/#?]+-(?P<id>[0-9]+)\.html(?:$|[?#])' _TEST = { 'url': 'http://www.youjizz.com/videos/zeichentrick-1-2189178.html', - 'file': '2189178.flv', 'md5': '07e15fa469ba384c7693fd246905547c', 'info_dict': { + 'id': '2189178', + 'ext': 'flv', "title": "Zeichentrick 1", "age_limit": 18, } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - - video_id = mobj.group('videoid') - - # Get webpage content + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - age_limit = self._rta_search(webpage) + video_title = self._html_search_regex( + r'<title>\s*(.*)\s*', webpage, 'title') - # Get the video title - video_title = self._html_search_regex(r'(?P<title>.*)', - webpage, 'title').strip() - - # Get the embed page - result = re.search(r'https?://www.youjizz.com/videos/embed/(?P[0-9]+)', webpage) - if result is None: - raise ExtractorError('ERROR: unable to extract embed page') - - embed_page_url = result.group(0).strip() - video_id = result.group('videoid') - - webpage = self._download_webpage(embed_page_url, video_id) + embed_page_url = self._search_regex( + r'(https?://www.youjizz.com/videos/embed/[0-9]+)', + webpage, 'embed page') + webpage = self._download_webpage( + embed_page_url, video_id, note='downloading embed page') # Get the video URL m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P.+?)"\);', webpage) diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index a8fd40c83..97b98bbe8 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -1,6 +1,7 @@ # coding: utf-8 -import json +from __future__ import unicode_literals + import math import random import re @@ -13,35 +14,42 @@ from ..utils import ( class YoukuIE(InfoExtractor): - _VALID_URL = r'(?:(?:http://)?(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)|youku:)(?P[A-Za-z0-9]+)(?:\.html|/v\.swf|)' - _TEST = { - u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html", - u"file": u"XNDgyMDQ2NTQw_part00.flv", - u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b", - u"params": {u"test": False}, - u"info_dict": { - u"title": u"youtube-dl test video \"'/\\ä↭𝕐" + _VALID_URL = r'''(?x) + (?: + http://(?:v|player)\.youku\.com/(?:v_show/id_|player\.php/sid/)| + youku:) + (?P[A-Za-z0-9]+)(?:\.html|/v\.swf|) + ''' + _TEST = { + 'url': 'http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html', + 'md5': 'ffe3f2e435663dc2d1eea34faeff5b5b', + 'params': { + 'test': False + }, + 'info_dict': { + 'id': 'XNDgyMDQ2NTQw_part00', + 'ext': 'flv', + 'title': 'youtube-dl test video "\'/\\ä↭𝕐' } } - def _gen_sid(self): nowTime = int(time.time() * 1000) - random1 = random.randint(1000,1998) - random2 = random.randint(1000,9999) + random1 = random.randint(1000, 1998) + random2 = random.randint(1000, 9999) - return "%d%d%d" %(nowTime,random1,random2) + return "%d%d%d" % (nowTime, random1, random2) def _get_file_ID_mix_string(self, seed): mixed = [] source = list("abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ/\:._-1234567890") seed = float(seed) for i in range(len(source)): - seed = (seed * 211 + 30031) % 65536 - index = math.floor(seed / 65536 * len(source)) + seed = (seed * 211 + 30031) % 65536 + index = math.floor(seed / 65536 * len(source)) mixed.append(source[int(index)]) source.remove(source[int(index)]) - #return ''.join(mixed) + # return ''.join(mixed) return mixed def _get_file_id(self, fileId, seed): @@ -55,60 +63,52 @@ class YoukuIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - video_id = mobj.group('ID') + video_id = mobj.group('id') info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id - jsondata = self._download_webpage(info_url, video_id) + config = self._download_json(info_url, video_id) - self.report_extraction(video_id) - try: - config = json.loads(jsondata) - error_code = config['data'][0].get('error_code') - if error_code: - # -8 means blocked outside China. - error = config['data'][0].get('error') # Chinese and English, separated by newline. - raise ExtractorError(error or u'Server reported error %i' % error_code, - expected=True) + error_code = config['data'][0].get('error_code') + if error_code: + # -8 means blocked outside China. + error = config['data'][0].get('error') # Chinese and English, separated by newline. + raise ExtractorError(error or 'Server reported error %i' % error_code, + expected=True) - video_title = config['data'][0]['title'] - seed = config['data'][0]['seed'] + video_title = config['data'][0]['title'] + seed = config['data'][0]['seed'] - format = self._downloader.params.get('format', None) - supported_format = list(config['data'][0]['streamfileids'].keys()) + format = self._downloader.params.get('format', None) + supported_format = list(config['data'][0]['streamfileids'].keys()) - if format is None or format == 'best': - if 'hd2' in supported_format: - format = 'hd2' - else: - format = 'flv' - ext = u'flv' - elif format == 'worst': - format = 'mp4' - ext = u'mp4' + # TODO proper format selection + if format is None or format == 'best': + if 'hd2' in supported_format: + format = 'hd2' else: format = 'flv' - ext = u'flv' + ext = 'flv' + elif format == 'worst': + format = 'mp4' + ext = 'mp4' + else: + format = 'flv' + ext = 'flv' + fileid = config['data'][0]['streamfileids'][format] + keys = [s['k'] for s in config['data'][0]['segs'][format]] + # segs is usually a dictionary, but an empty *list* if an error occured. - fileid = config['data'][0]['streamfileids'][format] - keys = [s['k'] for s in config['data'][0]['segs'][format]] - # segs is usually a dictionary, but an empty *list* if an error occured. - except (UnicodeDecodeError, ValueError, KeyError): - raise ExtractorError(u'Unable to extract info section') - - files_info=[] + files_info = [] sid = self._gen_sid() fileid = self._get_file_id(fileid, seed) - #column 8,9 of fileid represent the segment number - #fileid[7:9] should be changed + # column 8,9 of fileid represent the segment number + # fileid[7:9] should be changed for index, key in enumerate(keys): - temp_fileid = '%s%02X%s' % (fileid[0:8], index, fileid[10:]) - download_url = 'http://f.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) + download_url = 'http://k.youku.com/player/getFlvPath/sid/%s_%02X/st/flv/fileid/%s?k=%s' % (sid, index, temp_fileid, key) info = { 'id': '%s_part%02d' % (video_id, index), diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index 7bfda45e7..8123928be 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -49,7 +49,7 @@ class YouPornIE(InfoExtractor): try: params = json.loads(json_params) except: - raise ExtractorError(u'Invalid JSON') + raise ExtractorError('Invalid JSON') self.report_extraction(video_id) try: @@ -64,7 +64,7 @@ class YouPornIE(InfoExtractor): # Get all of the links from the page DOWNLOAD_LIST_RE = r'(?s)
      (?P.*?)
    ' download_list_html = self._search_regex(DOWNLOAD_LIST_RE, - webpage, 'download list').strip() + webpage, 'download list').strip() LINK_RE = r'    ' links = re.findall(LINK_RE, download_list_html) @@ -73,7 +73,7 @@ class YouPornIE(InfoExtractor): for encrypted_link in encrypted_links: link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8') links.append(link) - + formats = [] for link in links: # A link looks like this: @@ -103,8 +103,8 @@ class YouPornIE(InfoExtractor): self._sort_formats(formats) if not formats: - raise ExtractorError(u'ERROR: no known formats available for video') - + raise ExtractorError('ERROR: no known formats available for video') + return { 'id': video_id, 'uploader': video_uploader, diff --git a/youtube_dl/extractor/yourupload.py b/youtube_dl/extractor/yourupload.py new file mode 100644 index 000000000..40fc4165f --- /dev/null +++ b/youtube_dl/extractor/yourupload.py @@ -0,0 +1,58 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class YourUploadIE(InfoExtractor): + _VALID_URL = r'''(?x)https?://(?:www\.)? + (?:yourupload\.com/watch| + embed\.yourupload\.com| + embed\.yucache\.net + )/(?P[A-Za-z0-9]+) + ''' + _TESTS = [ + { + 'url': 'http://yourupload.com/watch/14i14h', + 'md5': 'bf5c2f95c4c917536e80936af7bc51e1', + 'info_dict': { + 'id': '14i14h', + 'ext': 'mp4', + 'title': 'BigBuckBunny_320x180.mp4', + 'thumbnail': 're:^https?://.*\.jpe?g', + } + }, + { + 'url': 'http://embed.yourupload.com/14i14h', + 'only_matching': True, + }, + { + 'url': 'http://embed.yucache.net/14i14h?client_file_id=803349', + 'only_matching': True, + }, + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + url = 'http://embed.yucache.net/{0:}'.format(video_id) + webpage = self._download_webpage(url, video_id) + + title = self._og_search_title(webpage) + thumbnail = self._og_search_thumbnail(webpage) + url = self._og_search_video_url(webpage) + + formats = [{ + 'format_id': 'sd', + 'url': url, + }] + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index b54c69122..96b49fed1 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -7,6 +7,7 @@ import itertools import json import os.path import re +import time import traceback from .common import InfoExtractor, SearchInfoExtractor @@ -26,28 +27,26 @@ from ..utils import ( get_element_by_attribute, ExtractorError, int_or_none, - PagedList, + OnDemandPagedList, unescapeHTML, unified_strdate, orderedSet, uppercase_escape, ) + class YoutubeBaseInfoExtractor(InfoExtractor): """Provide base functions for Youtube extractors""" _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor' - _LANG_URL = r'https://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' - _AGE_URL = 'https://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' _NETRC_MACHINE = 'youtube' # If True it will raise an error if no login info is provided _LOGIN_REQUIRED = False def _set_language(self): - return bool(self._download_webpage( - self._LANG_URL, None, - note=u'Setting language', errnote='unable to set language', - fatal=False)) + self._set_cookie('.youtube.com', 'PREF', 'f1=50000000&hl=en', + # YouTube sets the expire time to about two months + expire_time=time.time() + 60*24*3600) def _login(self): """ @@ -61,13 +60,13 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # No authentication to be performed if username is None: if self._LOGIN_REQUIRED: - raise ExtractorError(u'No login info available, needed for using %s.' % self.IE_NAME, expected=True) + raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) return True login_page = self._download_webpage( self._LOGIN_URL, None, - note=u'Downloading login page', - errnote=u'unable to fetch login page', fatal=False) + note='Downloading login page', + errnote='unable to fetch login page', fatal=False) if login_page is False: return @@ -76,41 +75,41 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # Log in login_form_strs = { - 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', - 'Email': username, - 'GALX': galx, - 'Passwd': password, + 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', + 'Email': username, + 'GALX': galx, + 'Passwd': password, - 'PersistentCookie': 'yes', - '_utf8': '霱', - 'bgresponse': 'js_disabled', - 'checkConnection': '', - 'checkedDomains': 'youtube', - 'dnConn': '', - 'pstMsg': '0', - 'rmShown': '1', - 'secTok': '', - 'signIn': 'Sign in', - 'timeStmp': '', - 'service': 'youtube', - 'uilel': '3', - 'hl': 'en_US', + 'PersistentCookie': 'yes', + '_utf8': '霱', + 'bgresponse': 'js_disabled', + 'checkConnection': '', + 'checkedDomains': 'youtube', + 'dnConn': '', + 'pstMsg': '0', + 'rmShown': '1', + 'secTok': '', + 'signIn': 'Sign in', + 'timeStmp': '', + 'service': 'youtube', + 'uilel': '3', + 'hl': 'en_US', } # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode # chokes on unicode - login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in login_form_strs.items()) + login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') req = compat_urllib_request.Request(self._LOGIN_URL, login_data) login_results = self._download_webpage( req, None, - note=u'Logging in', errnote=u'unable to log in', fatal=False) + note='Logging in', errnote='unable to log in', fatal=False) if login_results is False: return False if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: - raise ExtractorError(u'Please use your account password and a two-factor code instead of an application-specific password.', expected=True) + raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True) # Two-Factor # TODO add SMS and phone call support - these require making a request and then prompting the user @@ -119,19 +118,19 @@ class YoutubeBaseInfoExtractor(InfoExtractor): tfa_code = self._get_tfa_info() if tfa_code is None: - self._downloader.report_warning(u'Two-factor authentication required. Provide it with --twofactor ') - self._downloader.report_warning(u'(Note that only TOTP (Google Authenticator App) codes work at this time.)') + self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor ') + self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)') return False # Unlike the first login form, secTok and timeStmp are both required for the TFA form match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) if match is None: - self._downloader.report_warning(u'Failed to get secTok - did the page structure change?') + self._downloader.report_warning('Failed to get secTok - did the page structure change?') secTok = match.group(1) match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) if match is None: - self._downloader.report_warning(u'Failed to get timeStmp - did the page structure change?') + self._downloader.report_warning('Failed to get timeStmp - did the page structure change?') timeStmp = match.group(1) tfa_form_strs = { @@ -149,53 +148,38 @@ class YoutubeBaseInfoExtractor(InfoExtractor): 'service': 'youtube', 'hl': 'en_US', } - tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k,v in tfa_form_strs.items()) + tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items()) tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) tfa_results = self._download_webpage( tfa_req, None, - note=u'Submitting TFA code', errnote=u'unable to submit tfa', fatal=False) + note='Submitting TFA code', errnote='unable to submit tfa', fatal=False) if tfa_results is False: return False if re.search(r'(?i)]* id="gaia_secondfactorform"', tfa_results) is not None: - self._downloader.report_warning(u'Two-factor code expired. Please try again, or use a one-use backup code instead.') + self._downloader.report_warning('Two-factor code expired. Please try again, or use a one-use backup code instead.') return False if re.search(r'(?i)]* id="gaia_loginform"', tfa_results) is not None: - self._downloader.report_warning(u'unable to log in - did the page structure change?') + self._downloader.report_warning('unable to log in - did the page structure change?') return False if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None: - self._downloader.report_warning(u'Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.') + self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.') return False if re.search(r'(?i)]* id="gaia_loginform"', login_results) is not None: - self._downloader.report_warning(u'unable to log in: bad username or password') + self._downloader.report_warning('unable to log in: bad username or password') return False return True - def _confirm_age(self): - age_form = { - 'next_url': '/', - 'action_confirm': 'Confirm', - } - req = compat_urllib_request.Request(self._AGE_URL, - compat_urllib_parse.urlencode(age_form).encode('ascii')) - - self._download_webpage( - req, None, - note=u'Confirming age', errnote=u'Unable to confirm age') - return True - def _real_initialize(self): if self._downloader is None: return - if not self._set_language(): - return + self._set_language() if not self._login(): return - self._confirm_age() class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): @@ -211,7 +195,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: - (?:(?:v|embed|e)/) # v/ or embed/ or e/ + (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |(?: # or the v= param in all its forms (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) (?:\?|\#!?) # the params delimiter ? or # or #! @@ -273,6 +257,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '138': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, + '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, + '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'}, # Dash mp4 audio '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50}, @@ -286,6 +273,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, + '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'}, '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, @@ -295,11 +283,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, + '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, + '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, # Dash webm audio '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, + # Dash webm audio with opus inside + '249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}, + '250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}, + '251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}, + # RTMP (unnamed) '_rtmp': {'protocol': 'rtmp'}, } @@ -307,69 +302,74 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): IE_NAME = 'youtube' _TESTS = [ { - u"url": u"http://www.youtube.com/watch?v=BaW_jenozKc", - u"file": u"BaW_jenozKc.mp4", - u"info_dict": { - u"title": u"youtube-dl test video \"'/\\ä↭𝕐", - u"uploader": u"Philipp Hagemeister", - u"uploader_id": u"phihag", - u"upload_date": u"20121002", - u"description": u"test chars: \"'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .", - u"categories": [u'Science & Technology'], + 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc', + 'info_dict': { + 'id': 'BaW_jenozKc', + 'ext': 'mp4', + 'title': 'youtube-dl test video "\'/\\ä↭𝕐', + 'uploader': 'Philipp Hagemeister', + 'uploader_id': 'phihag', + 'upload_date': '20121002', + 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', + 'categories': ['Science & Technology'], 'like_count': int, 'dislike_count': int, } }, { - u"url": u"http://www.youtube.com/watch?v=UxxajLWwzqY", - u"file": u"UxxajLWwzqY.mp4", - u"note": u"Test generic use_cipher_signature video (#897)", - u"info_dict": { - u"upload_date": u"20120506", - u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]", - u"description": u"md5:fea86fda2d5a5784273df5c7cc994d9f", - u"uploader": u"Icona Pop", - u"uploader_id": u"IconaPop" + 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY', + 'note': 'Test generic use_cipher_signature video (#897)', + 'info_dict': { + 'id': 'UxxajLWwzqY', + 'ext': 'mp4', + 'upload_date': '20120506', + 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', + 'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f', + 'uploader': 'Icona Pop', + 'uploader_id': 'IconaPop', } }, { - u"url": u"https://www.youtube.com/watch?v=07FYdnEawAQ", - u"file": u"07FYdnEawAQ.mp4", - u"note": u"Test VEVO video with age protection (#956)", - u"info_dict": { - u"upload_date": u"20130703", - u"title": u"Justin Timberlake - Tunnel Vision (Explicit)", - u"description": u"md5:64249768eec3bc4276236606ea996373", - u"uploader": u"justintimberlakeVEVO", - u"uploader_id": u"justintimberlakeVEVO" + 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', + 'note': 'Test VEVO video with age protection (#956)', + 'info_dict': { + 'id': '07FYdnEawAQ', + 'ext': 'mp4', + 'upload_date': '20130703', + 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', + 'description': 'md5:64249768eec3bc4276236606ea996373', + 'uploader': 'justintimberlakeVEVO', + 'uploader_id': 'justintimberlakeVEVO', } }, { - u"url": u"//www.YouTube.com/watch?v=yZIXLfi8CZQ", - u"file": u"yZIXLfi8CZQ.mp4", - u"note": u"Embed-only video (#1746)", - u"info_dict": { - u"upload_date": u"20120608", - u"title": u"Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012", - u"description": u"md5:09b78bd971f1e3e289601dfba15ca4f7", - u"uploader": u"SET India", - u"uploader_id": u"setindia" + 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', + 'note': 'Embed-only video (#1746)', + 'info_dict': { + 'id': 'yZIXLfi8CZQ', + 'ext': 'mp4', + 'upload_date': '20120608', + 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', + 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', + 'uploader': 'SET India', + 'uploader_id': 'setindia' } }, { - u"url": u"http://www.youtube.com/watch?v=a9LDPn-MO4I", - u"file": u"a9LDPn-MO4I.m4a", - u"note": u"256k DASH audio (format 141) via DASH manifest", - u"info_dict": { - u"upload_date": "20121002", - u"uploader_id": "8KVIDEO", - u"description": '', - u"uploader": "8KVIDEO", - u"title": "UHDTV TEST 8K VIDEO.mp4" + 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I', + 'note': '256k DASH audio (format 141) via DASH manifest', + 'info_dict': { + 'id': 'a9LDPn-MO4I', + 'ext': 'm4a', + 'upload_date': '20121002', + 'uploader_id': '8KVIDEO', + 'description': '', + 'uploader': '8KVIDEO', + 'title': 'UHDTV TEST 8K VIDEO.mp4' }, - u"params": { - u"youtube_include_dash_manifest": True, - u"format": "141", + 'params': { + 'youtube_include_dash_manifest': True, + 'format': '141', }, }, # DASH manifest with encrypted signature @@ -384,11 +384,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'uploader_id': 'AfrojackVEVO', 'upload_date': '20131011', }, - u"params": { + 'params': { 'youtube_include_dash_manifest': True, 'format': '141', }, }, + # Controversy video + { + 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', + 'info_dict': { + 'id': 'T4XJQO3qol8', + 'ext': 'mp4', + 'upload_date': '20100909', + 'uploader': 'The Amazing Atheist', + 'uploader_id': 'TheAmazingAtheist', + 'title': 'Burning Everyone\'s Koran', + 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html', + } + } ] def __init__(self, *args, **kwargs): @@ -397,19 +410,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def report_video_info_webpage_download(self, video_id): """Report attempt to download video info webpage.""" - self.to_screen(u'%s: Downloading video info webpage' % video_id) + self.to_screen('%s: Downloading video info webpage' % video_id) def report_information_extraction(self, video_id): """Report attempt to extract video information.""" - self.to_screen(u'%s: Extracting video information' % video_id) + self.to_screen('%s: Extracting video information' % video_id) def report_unavailable_format(self, video_id, format): """Report extracted video URL.""" - self.to_screen(u'%s: Format %s not available' % (video_id, format)) + self.to_screen('%s: Format %s not available' % (video_id, format)) def report_rtmp_download(self): """Indicate the download will use the RTMP protocol.""" - self.to_screen(u'RTMP download detected') + self.to_screen('RTMP download detected') def _signature_cache_id(self, example_sig): """ Return a string representation of a signature """ @@ -429,21 +442,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): player_type, player_id, self._signature_cache_id(example_sig)) assert os.path.basename(func_id) == func_id - cache_spec = self._downloader.cache.load(u'youtube-sigfuncs', func_id) + cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) if cache_spec is not None: return lambda s: ''.join(s[i] for i in cache_spec) if player_type == 'js': code = self._download_webpage( player_url, video_id, - note=u'Downloading %s player %s' % (player_type, player_id), - errnote=u'Download of %s failed' % player_url) + note='Downloading %s player %s' % (player_type, player_id), + errnote='Download of %s failed' % player_url) res = self._parse_sig_js(code) elif player_type == 'swf': urlh = self._request_webpage( player_url, video_id, - note=u'Downloading %s player %s' % (player_type, player_id), - errnote=u'Download of %s failed' % player_url) + note='Downloading %s player %s' % (player_type, player_id), + errnote='Download of %s failed' % player_url) code = urlh.read() res = self._parse_sig_swf(code) else: @@ -454,15 +467,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): cache_res = res(test_string) cache_spec = [ord(c) for c in cache_res] - self._downloader.cache.store(u'youtube-sigfuncs', func_id, cache_spec) + self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) return res def _print_sig_code(self, func, example_sig): def gen_sig_code(idxs): def _genslice(start, end, step): starts = '' if start == 0 else str(start) - ends = (u':%d' % (end+step)) if end + step >= 0 else ':' - steps = '' if step == 1 else (u':%d' % step) + ends = (':%d' % (end + step)) if end + step >= 0 else ':' + steps = '' if step == 1 else (':%d' % step) return 's[%s%s%s]' % (starts, ends, steps) step = None @@ -492,14 +505,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): expr_code = ' + '.join(gen_sig_code(cache_spec)) signature_id_tuple = '(%s)' % ( ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) - code = (u'if tuple(len(p) for p in s.split(\'.\')) == %s:\n' + code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' ' return %s\n') % (signature_id_tuple, expr_code) - self.to_screen(u'Extracted signature function:\n' + code) + self.to_screen('Extracted signature function:\n' + code) def _parse_sig_js(self, jscode): funcname = self._search_regex( - r'signature=([$a-zA-Z]+)', jscode, - 'Initial JS player signature function name') + r'\.sig\|\|([a-zA-Z0-9]+)\(', jscode, + 'Initial JS player signature function name') jsi = JSInterpreter(jscode) initial_function = jsi.extract_function(funcname) @@ -516,9 +529,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): """Turn the encrypted s field into a working signature""" if player_url is None: - raise ExtractorError(u'Cannot decrypt signature without player_url') + raise ExtractorError('Cannot decrypt signature without player_url') - if player_url.startswith(u'//'): + if player_url.startswith('//'): player_url = 'https:' + player_url try: player_id = (player_url, self._signature_cache_id(s)) @@ -542,7 +555,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, video_id, note=False) except ExtractorError as err: - self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err)) + self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) return {} lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list) @@ -560,7 +573,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url = 'https://www.youtube.com/api/timedtext?' + params sub_lang_list[lang] = url if not sub_lang_list: - self._downloader.report_warning(u'video doesn\'t have subtitles') + self._downloader.report_warning('video doesn\'t have subtitles') return {} return sub_lang_list @@ -568,7 +581,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): """We need the webpage for getting the captions url, pass it as an argument to speed up the process.""" sub_format = self._downloader.params.get('subtitlesformat', 'srt') - self.to_screen(u'%s: Looking for automatic captions' % video_id) + self.to_screen('%s: Looking for automatic captions' % video_id) mobj = re.search(r';ytplayer.config = ({.*?});', webpage) err_msg = 'Couldn\'t find automatic captions for %s' % video_id if mobj is None: @@ -576,9 +589,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): return {} player_config = json.loads(mobj.group(1)) try: - args = player_config[u'args'] - caption_url = args[u'ttsurl'] - timestamp = args[u'timestamp'] + args = player_config['args'] + caption_url = args['ttsurl'] + timestamp = args['timestamp'] # We get the available subtitles list_params = compat_urllib_parse.urlencode({ 'type': 'list', @@ -588,8 +601,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): list_url = caption_url + '&' + list_params caption_list = self._download_xml(list_url, video_id) original_lang_node = caption_list.find('track') - if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr' : - self._downloader.report_warning(u'Video doesn\'t have automatic captions') + if original_lang_node is None or original_lang_node.attrib.get('kind') != 'asr': + self._downloader.report_warning('Video doesn\'t have automatic captions') return {} original_lang = original_lang_node.attrib['lang_code'] @@ -615,16 +628,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def extract_id(cls, url): mobj = re.match(cls._VALID_URL, url, re.VERBOSE) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) video_id = mobj.group(2) return video_id def _extract_from_m3u8(self, manifest_url, video_id): url_map = {} + def _get_urls(_manifest): lines = _manifest.split('\n') urls = filter(lambda l: l and not l.startswith('#'), - lines) + lines) return urls manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest') formats_urls = _get_urls(manifest) @@ -635,7 +649,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): def _extract_annotations(self, video_id): url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id - return self._download_webpage(url, video_id, note=u'Searching for annotations.', errnote=u'Unable to download video annotations.') + return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') def _real_extract(self, url): proto = ( @@ -649,7 +663,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): video_id = self.extract_id(url) # Get video webpage - url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1' % video_id + url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id video_webpage = self._download_webpage(url, video_id) # Attempt to extract SWF player URL @@ -662,7 +676,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # Get video info self.report_video_info_webpage_download(video_id) if re.search(r'player-age-gate-content">', video_webpage) is not None: - self.report_age_confirmation() age_gate = True # We simulate the access to the video from www.youtube.com/v/{video_id} # this can be viewed without login into Youtube @@ -670,21 +683,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'video_id': video_id, 'eurl': 'https://youtube.googleapis.com/v/' + video_id, 'sts': self._search_regex( - r'"sts"\s*:\s*(\d+)', video_webpage, 'sts'), + r'"sts"\s*:\s*(\d+)', video_webpage, 'sts', default=''), }) video_info_url = proto + '://www.youtube.com/get_video_info?' + data - video_info_webpage = self._download_webpage(video_info_url, video_id, - note=False, - errnote='unable to download video info webpage') + video_info_webpage = self._download_webpage( + video_info_url, video_id, + note='Refetching age-gated info webpage', + errnote='unable to download video info webpage') video_info = compat_parse_qs(video_info_webpage) else: age_gate = False for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: video_info_url = (proto + '://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' - % (video_id, el_type)) + % (video_id, el_type)) video_info_webpage = self._download_webpage(video_info_url, video_id, - note=False, - errnote='unable to download video info webpage') + note=False, + errnote='unable to download video info webpage') video_info = compat_parse_qs(video_info_webpage) if 'token' in video_info: break @@ -705,14 +719,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # Check for "rental" videos if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: - raise ExtractorError(u'"rental" videos not supported') + raise ExtractorError('"rental" videos not supported') # Start extracting information self.report_information_extraction(video_id) # uploader if 'author' not in video_info: - raise ExtractorError(u'Unable to extract uploader name') + raise ExtractorError('Unable to extract uploader name') video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) # uploader_id @@ -721,13 +735,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if mobj is not None: video_uploader_id = mobj.group(1) else: - self._downloader.report_warning(u'unable to extract uploader nickname') + self._downloader.report_warning('unable to extract uploader nickname') # title if 'title' in video_info: video_title = video_info['title'][0] else: - self._downloader.report_warning(u'Unable to extract video title') + self._downloader.report_warning('Unable to extract video title') video_title = '_' # thumbnail image @@ -737,7 +751,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if m_thumb is not None: video_thumbnail = m_thumb.group(1) elif 'thumbnail_url' not in video_info: - self._downloader.report_warning(u'unable to extract video thumbnail') + self._downloader.report_warning('unable to extract video thumbnail') video_thumbnail = None else: # don't panic if we can't find it video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) @@ -791,8 +805,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): if count is not None: return int(count.replace(',', '')) return None - like_count = _extract_count(u'like') - dislike_count = _extract_count(u'dislike') + like_count = _extract_count('like') + dislike_count = _extract_count('dislike') # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) @@ -802,7 +816,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): return if 'length_seconds' not in video_info: - self._downloader.report_warning(u'unable to extract video duration') + self._downloader.report_warning('unable to extract video duration') video_duration = None else: video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])) @@ -810,7 +824,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # annotations video_annotations = None if self._downloader.params.get('writeannotations', False): - video_annotations = self._extract_annotations(video_id) + video_annotations = self._extract_annotations(video_id) # Decide which formats to download try: @@ -823,11 +837,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): # Easy way to know if the 's' value is in url_encoded_fmt_stream_map # this signatures are encrypted if 'url_encoded_fmt_stream_map' not in args: - raise ValueError(u'No stream_map present') # caught below + raise ValueError('No stream_map present') # caught below re_signature = re.compile(r'[&,]s=') m_s = re_signature.search(args['url_encoded_fmt_stream_map']) if m_s is not None: - self.to_screen(u'%s: Encrypted signatures detected.' % video_id) + self.to_screen('%s: Encrypted signatures detected.' % video_id) video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']] m_s = re_signature.search(args.get('adaptive_fmts', '')) if m_s is not None: @@ -860,7 +874,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): 'player_url': player_url, }] elif len(video_info.get('url_encoded_fmt_stream_map', [])) >= 1 or len(video_info.get('adaptive_fmts', [])) >= 1: - encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts',[''])[0] + encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] if 'rtmpe%3Dyes' in encoded_url_map: raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) url_map = {} @@ -905,8 +919,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): player_desc = 'html5 player %s' % player_version parts_sizes = self._signature_cache_id(encrypted_sig) - self.to_screen(u'{%s} signature length %s, %s' % - (format_id, parts_sizes, player_desc)) + self.to_screen('{%s} signature length %s, %s' % + (format_id, parts_sizes, player_desc)) signature = self._decrypt_signature( encrypted_sig, video_id, player_url, age_gate) @@ -920,10 +934,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): url_map = self._extract_from_m3u8(manifest_url, video_id) formats = _map_to_format_list(url_map) else: - raise ExtractorError(u'no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') + raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') # Look for the DASH manifest - if (self._downloader.params.get('youtube_include_dash_manifest', False)): + if self._downloader.params.get('youtube_include_dash_manifest', True): try: # The DASH manifest used needs to be the one from the original video_webpage. # The one found in get_video_info seems to be using different signatures. @@ -934,6 +948,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): dash_manifest_url = video_info.get('dashmpd')[0] else: dash_manifest_url = ytplayer_config['args']['dashmpd'] + def decrypt_sig(mobj): s = mobj.group(1) dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) @@ -941,9 +956,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url) dash_doc = self._download_xml( dash_manifest_url, video_id, - note=u'Downloading DASH manifest', - errnote=u'Could not download DASH manifest') - for r in dash_doc.findall(u'.//{urn:mpeg:DASH:schema:MPD:2011}Representation'): + note='Downloading DASH manifest', + errnote='Could not download DASH manifest') + for r in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}Representation'): url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') if url_el is None: continue @@ -969,30 +984,31 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): existing_format.update(f) except (ExtractorError, KeyError) as e: - self.report_warning(u'Skipping DASH manifest: %s' % e, video_id) + self.report_warning('Skipping DASH manifest: %r' % e, video_id) self._sort_formats(formats) return { - 'id': video_id, - 'uploader': video_uploader, - 'uploader_id': video_uploader_id, - 'upload_date': upload_date, - 'title': video_title, - 'thumbnail': video_thumbnail, - 'description': video_description, - 'categories': video_categories, - 'subtitles': video_subtitles, - 'duration': video_duration, - 'age_limit': 18 if age_gate else 0, - 'annotations': video_annotations, + 'id': video_id, + 'uploader': video_uploader, + 'uploader_id': video_uploader_id, + 'upload_date': upload_date, + 'title': video_title, + 'thumbnail': video_thumbnail, + 'description': video_description, + 'categories': video_categories, + 'subtitles': video_subtitles, + 'duration': video_duration, + 'age_limit': 18 if age_gate else 0, + 'annotations': video_annotations, 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, - 'view_count': view_count, + 'view_count': view_count, 'like_count': like_count, 'dislike_count': dislike_count, - 'formats': formats, + 'formats': formats, } + class YoutubePlaylistIE(YoutubeBaseInfoExtractor): IE_DESC = 'YouTube.com playlists' _VALID_URL = r"""(?x)(?: @@ -1000,13 +1016,13 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): (?:\w+\.)? youtube\.com/ (?: - (?:course|view_play_list|my_playlists|artist|playlist|watch) + (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries) \? (?:.*?&)*? (?:p|a|list)= | p/ ) ( (?:PL|LL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,} - # Top tracks, they can also include dots + # Top tracks, they can also include dots |(?:MC)[\w\.]* ) .* @@ -1021,6 +1037,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', 'info_dict': { 'title': 'ytdl test PL', + 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', }, 'playlist_count': 3, }, { @@ -1040,7 +1057,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): 'note': 'issue #673', 'url': 'PLBB231211A4F62143', 'info_dict': { - 'title': 'Team Fortress 2 (Class-based LP)', + 'title': '[OLD]Team Fortress 2 (Class-based LP)', }, 'playlist_mincount': 26, }, { @@ -1056,6 +1073,20 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): 'title': 'YDL_safe_search', }, 'playlist_count': 2, + }, { + 'note': 'embedded', + 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', + 'playlist_count': 4, + 'info_dict': { + 'title': 'JODA15', + } + }, { + 'note': 'Embedded SWF player', + 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', + 'playlist_count': 4, + 'info_dict': { + 'title': 'JODA7', + } }] def _real_initialize(self): @@ -1090,7 +1121,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): # Extract playlist id mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) playlist_id = mobj.group(1) or mobj.group(2) # Check if it's a video-specific URL @@ -1098,17 +1129,17 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): if 'v' in query_dict: video_id = query_dict['v'][0] if self._downloader.params.get('noplaylist'): - self.to_screen(u'Downloading just video %s because of --no-playlist' % video_id) + self.to_screen('Downloading just video %s because of --no-playlist' % video_id) return self.url_result(video_id, 'Youtube', video_id=video_id) else: - self.to_screen(u'Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) + self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) if playlist_id.startswith('RD'): # Mixes require a custom extraction process return self._extract_mix(playlist_id) if playlist_id.startswith('TL'): - raise ExtractorError(u'For downloading YouTube.com top lists, use ' - 'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True) + raise ExtractorError('For downloading YouTube.com top lists, use ' + 'the "yttoplist" keyword, for example "youtube-dl \'yttoplist:music:Top Tracks\'"', expected=True) url = self._TEMPLATE_URL % playlist_id page = self._download_webpage(url, playlist_id) @@ -1152,21 +1183,30 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): class YoutubeTopListIE(YoutubePlaylistIE): IE_NAME = 'youtube:toplist' - IE_DESC = (u'YouTube.com top lists, "yttoplist:{channel}:{list title}"' - ' (Example: "yttoplist:music:Top Tracks")') + IE_DESC = ('YouTube.com top lists, "yttoplist:{channel}:{list title}"' + ' (Example: "yttoplist:music:Top Tracks")') _VALID_URL = r'yttoplist:(?P.*?):(?P.*?)$' - _TESTS = [] + _TESTS = [{ + 'url': 'yttoplist:music:Trending', + 'playlist_mincount': 5, + 'skip': 'Only works for logged-in users', + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) channel = mobj.group('chann') title = mobj.group('title') query = compat_urllib_parse.urlencode({'title': title}) - playlist_re = 'href="([^"]+?%s.*?)"' % re.escape(query) - channel_page = self._download_webpage('https://www.youtube.com/%s' % channel, title) - link = self._html_search_regex(playlist_re, channel_page, 'list') + channel_page = self._download_webpage( + 'https://www.youtube.com/%s' % channel, title) + link = self._html_search_regex( + r'''(?x) + <a\s+href="([^"]+)".*?>\s* + <span\s+class="branded-page-module-title-text">\s* + <span[^>]*>.*?%s.*?</span>''' % re.escape(query), + channel_page, 'list') url = compat_urlparse.urljoin('https://www.youtube.com/', link) - + video_re = r'data-index="\d+".*?data-video-id="([0-9A-Za-z_-]{11})"' ids = [] # sometimes the webpage doesn't contain the videos @@ -1190,6 +1230,11 @@ class YoutubeChannelIE(InfoExtractor): _MORE_PAGES_INDICATOR = 'yt-uix-load-more' _MORE_PAGES_URL = 'https://www.youtube.com/c4_browse_ajax?action_load_more_videos=1&flow=list&paging=%s&view=0&sort=da&channel_id=%s' IE_NAME = 'youtube:channel' + _TESTS = [{ + 'note': 'paginated channel', + 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', + 'playlist_mincount': 91, + }] def extract_videos_from_page(self, page): ids_in_page = [] @@ -1202,7 +1247,7 @@ class YoutubeChannelIE(InfoExtractor): # Extract channel id mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) # Download channel page channel_id = mobj.group(1) @@ -1224,16 +1269,16 @@ class YoutubeChannelIE(InfoExtractor): for pagenum in itertools.count(1): url = self._MORE_PAGES_URL % (pagenum, channel_id) page = self._download_json( - url, channel_id, note=u'Downloading page #%s' % pagenum, + url, channel_id, note='Downloading page #%s' % pagenum, transform_source=uppercase_escape) ids_in_page = self.extract_videos_from_page(page['content_html']) video_ids.extend(ids_in_page) - + if self._MORE_PAGES_INDICATOR not in page['load_more_widget_html']: break - self._downloader.to_screen(u'[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) + self._downloader.to_screen('[youtube] Channel %s: Found %i videos' % (channel_id, len(video_ids))) url_entries = [self.url_result(video_id, 'Youtube', video_id=video_id) for video_id in video_ids] @@ -1248,19 +1293,32 @@ class YoutubeUserIE(InfoExtractor): _GDATA_URL = 'https://gdata.youtube.com/feeds/api/users/%s/uploads?max-results=%d&start-index=%d&alt=json' IE_NAME = 'youtube:user' + _TESTS = [{ + 'url': 'https://www.youtube.com/user/TheLinuxFoundation', + 'playlist_mincount': 320, + 'info_dict': { + 'title': 'TheLinuxFoundation', + } + }, { + 'url': 'ytuser:phihag', + 'only_matching': True, + }] + @classmethod def suitable(cls, url): # Don't return True if the url can be extracted with other youtube # extractor, the regex would is too permissive and it would match. other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) - if any(ie.suitable(url) for ie in other_ies): return False - else: return super(YoutubeUserIE, cls).suitable(url) + if any(ie.suitable(url) for ie in other_ies): + return False + else: + return super(YoutubeUserIE, cls).suitable(url) def _real_extract(self, url): # Extract username mobj = re.match(self._VALID_URL, url) if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) + raise ExtractorError('Invalid URL: %s' % url) username = mobj.group(1) @@ -1281,7 +1339,7 @@ class YoutubeUserIE(InfoExtractor): try: response = json.loads(page) except ValueError as err: - raise ExtractorError(u'Invalid JSON in API response: ' + compat_str(err)) + raise ExtractorError('Invalid JSON in API response: ' + compat_str(err)) if 'entry' not in response['feed']: return @@ -1297,7 +1355,7 @@ class YoutubeUserIE(InfoExtractor): 'id': video_id, 'title': title, } - url_results = PagedList(download_page, self._GDATA_PAGE_SIZE) + url_results = OnDemandPagedList(download_page, self._GDATA_PAGE_SIZE) return self.playlist_result(url_results, playlist_title=username) @@ -1322,9 +1380,9 @@ class YoutubeSearchIE(SearchInfoExtractor): compat_urllib_parse.quote_plus(query.encode('utf-8')), (PAGE_SIZE * pagenum) + 1) data_json = self._download_webpage( - result_url, video_id=u'query "%s"' % query, - note=u'Downloading page %s' % (pagenum + 1), - errnote=u'Unable to download API page') + result_url, video_id='query "%s"' % query, + note='Downloading page %s' % (pagenum + 1), + errnote='Unable to download API page') data = json.loads(data_json) api_response = data['data'] @@ -1356,6 +1414,13 @@ class YoutubeSearchURLIE(InfoExtractor): IE_DESC = 'YouTube.com search URLs' IE_NAME = 'youtube:search_url' _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)' + _TESTS = [{ + 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', + 'playlist_mincount': 5, + 'info_dict': { + 'title': 'youtube-dl test video', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -1390,17 +1455,38 @@ class YoutubeSearchURLIE(InfoExtractor): class YoutubeShowIE(InfoExtractor): IE_DESC = 'YouTube.com (multi-season) shows' - _VALID_URL = r'https?://www\.youtube\.com/show/(.*)' + _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)' IE_NAME = 'youtube:show' + _TESTS = [{ + 'url': 'http://www.youtube.com/show/airdisasters', + 'playlist_mincount': 3, + 'info_dict': { + 'id': 'airdisasters', + 'title': 'Air Disasters', + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - show_name = mobj.group(1) - webpage = self._download_webpage(url, show_name, 'Downloading show webpage') + playlist_id = mobj.group('id') + webpage = self._download_webpage( + url, playlist_id, 'Downloading show webpage') # There's one playlist for each season of the show m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage)) - self.to_screen(u'%s: Found %s seasons' % (show_name, len(m_seasons))) - return [self.url_result('https://www.youtube.com' + season.group(1), 'YoutubePlaylist') for season in m_seasons] + self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons))) + entries = [ + self.url_result( + 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist') + for season in m_seasons + ] + title = self._og_search_title(webpage, fatal=False) + + return { + '_type': 'playlist', + 'id': playlist_id, + 'title': title, + 'entries': entries, + } class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): @@ -1432,8 +1518,8 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): paging = 0 for i in itertools.count(1): info = self._download_json(self._FEED_TEMPLATE % paging, - '%s feed' % self._FEED_NAME, - 'Downloading page %s' % i) + '%s feed' % self._FEED_NAME, + 'Downloading page %s' % i) feed_html = info.get('feed_html') or info.get('content_html') load_more_widget_html = info.get('load_more_widget_html') or feed_html m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) @@ -1449,29 +1535,33 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): paging = mobj.group('paging') return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) + class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): - IE_DESC = 'YouTube.com recommended videos, "ytrec" keyword (requires authentication)' + IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' _FEED_NAME = 'recommended' _PLAYLIST_TITLE = 'Youtube Recommended videos' + class YoutubeWatchLaterIE(YoutubeFeedsInfoExtractor): - IE_DESC = 'Youtube watch later list, "ytwatchlater" keyword (requires authentication)' + IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/feed/watch_later|:ytwatchlater' _FEED_NAME = 'watch_later' _PLAYLIST_TITLE = 'Youtube Watch Later' _PERSONAL_FEED = True + class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): - IE_DESC = 'Youtube watch history, "ythistory" keyword (requires authentication)' + IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' _FEED_NAME = 'history' _PERSONAL_FEED = True _PLAYLIST_TITLE = 'Youtube Watch History' + class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): IE_NAME = 'youtube:favorites' - IE_DESC = 'YouTube.com favourite videos, "ytfav" keyword (requires authentication)' + IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?' _LOGIN_REQUIRED = True diff --git a/youtube_dl/extractor/zdf.py b/youtube_dl/extractor/zdf.py index 3b1ac4e9f..9ff00e26c 100644 --- a/youtube_dl/extractor/zdf.py +++ b/youtube_dl/extractor/zdf.py @@ -10,8 +10,84 @@ from ..utils import ( ) +def extract_from_xml_url(ie, video_id, xml_url): + doc = ie._download_xml( + xml_url, video_id, + note='Downloading video info', + errnote='Failed to download video info') + + title = doc.find('.//information/title').text + description = doc.find('.//information/detail').text + duration = int(doc.find('.//details/lengthSec').text) + uploader_node = doc.find('.//details/originChannelTitle') + uploader = None if uploader_node is None else uploader_node.text + uploader_id_node = doc.find('.//details/originChannelId') + uploader_id = None if uploader_id_node is None else uploader_id_node.text + upload_date = unified_strdate(doc.find('.//details/airtime').text) + + def xml_to_format(fnode): + video_url = fnode.find('url').text + is_available = 'http://www.metafilegenerator' not in video_url + + format_id = fnode.attrib['basetype'] + format_m = re.match(r'''(?x) + (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_ + (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+) + ''', format_id) + + ext = format_m.group('container') + proto = format_m.group('proto').lower() + + quality = fnode.find('./quality').text + abr = int(fnode.find('./audioBitrate').text) // 1000 + vbr_node = fnode.find('./videoBitrate') + vbr = None if vbr_node is None else int(vbr_node.text) // 1000 + + width_node = fnode.find('./width') + width = None if width_node is None else int_or_none(width_node.text) + height_node = fnode.find('./height') + height = None if height_node is None else int_or_none(height_node.text) + + format_note = '' + if not format_note: + format_note = None + + return { + 'format_id': format_id + '-' + quality, + 'url': video_url, + 'ext': ext, + 'acodec': format_m.group('acodec'), + 'vcodec': format_m.group('vcodec'), + 'abr': abr, + 'vbr': vbr, + 'width': width, + 'height': height, + 'filesize': int_or_none(fnode.find('./filesize').text), + 'format_note': format_note, + 'protocol': proto, + '_available': is_available, + } + + format_nodes = doc.findall('.//formitaeten/formitaet') + formats = list(filter( + lambda f: f['_available'], + map(xml_to_format, format_nodes))) + ie._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'duration': duration, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'upload_date': upload_date, + 'formats': formats, + } + + class ZDFIE(InfoExtractor): - _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<video_id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?' + _VALID_URL = r'^https?://www\.zdf\.de/ZDFmediathek(?P<hash>#)?/(.*beitrag/(?:video/)?)(?P<id>[0-9]+)(?:/[^/?]+)?(?:\?.*)?' _TEST = { 'url': 'http://www.zdf.de/ZDFmediathek/beitrag/video/2037704/ZDFspezial---Ende-des-Machtpokers--?bc=sts;stt', @@ -29,81 +105,7 @@ class ZDFIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('video_id') + video_id = self._match_id(url) xml_url = 'http://www.zdf.de/ZDFmediathek/xmlservice/web/beitragsDetails?ak=web&id=%s' % video_id - doc = self._download_xml( - xml_url, video_id, - note='Downloading video info', - errnote='Failed to download video info') - - title = doc.find('.//information/title').text - description = doc.find('.//information/detail').text - duration = int(doc.find('.//details/lengthSec').text) - uploader_node = doc.find('.//details/originChannelTitle') - uploader = None if uploader_node is None else uploader_node.text - uploader_id_node = doc.find('.//details/originChannelId') - uploader_id = None if uploader_id_node is None else uploader_id_node.text - upload_date = unified_strdate(doc.find('.//details/airtime').text) - - def xml_to_format(fnode): - video_url = fnode.find('url').text - is_available = 'http://www.metafilegenerator' not in video_url - - format_id = fnode.attrib['basetype'] - format_m = re.match(r'''(?x) - (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_ - (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+) - ''', format_id) - - ext = format_m.group('container') - proto = format_m.group('proto').lower() - - quality = fnode.find('./quality').text - abr = int(fnode.find('./audioBitrate').text) // 1000 - vbr_node = fnode.find('./videoBitrate') - vbr = None if vbr_node is None else int(vbr_node.text) // 1000 - - width_node = fnode.find('./width') - width = None if width_node is None else int_or_none(width_node.text) - height_node = fnode.find('./height') - height = None if height_node is None else int_or_none(height_node.text) - - format_note = '' - if not format_note: - format_note = None - - return { - 'format_id': format_id + '-' + quality, - 'url': video_url, - 'ext': ext, - 'acodec': format_m.group('acodec'), - 'vcodec': format_m.group('vcodec'), - 'abr': abr, - 'vbr': vbr, - 'width': width, - 'height': height, - 'filesize': int_or_none(fnode.find('./filesize').text), - 'format_note': format_note, - 'protocol': proto, - '_available': is_available, - } - - format_nodes = doc.findall('.//formitaeten/formitaet') - formats = list(filter( - lambda f: f['_available'], - map(xml_to_format, format_nodes))) - - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'duration': duration, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'upload_date': upload_date, - 'formats': formats, - } \ No newline at end of file + return extract_from_xml_url(self, video_id, xml_url) diff --git a/youtube_dl/extractor/zingmp3.py b/youtube_dl/extractor/zingmp3.py new file mode 100644 index 000000000..1afbe68ed --- /dev/null +++ b/youtube_dl/extractor/zingmp3.py @@ -0,0 +1,107 @@ +# coding=utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class ZingMp3BaseInfoExtractor(InfoExtractor): + + @staticmethod + def _extract_item(item): + title = item.find('./title').text.strip() + source = item.find('./source').text + extension = item.attrib['type'] + thumbnail = item.find('./backimage').text + + return { + 'title': title, + 'url': source, + 'ext': extension, + 'thumbnail': thumbnail, + } + + def _extract_player_xml(self, player_xml_url, id, playlist_title=None): + player_xml = self._download_xml(player_xml_url, id, 'Downloading Player XML') + items = player_xml.findall('./item') + + if len(items) == 1: + # one single song + data = self._extract_item(items[0]) + data['id'] = id + + return data + else: + # playlist of songs + entries = [] + + for i, item in enumerate(items, 1): + entry = self._extract_item(item) + entry['id'] = '%s-%d' % (id, i) + entries.append(entry) + + return { + '_type': 'playlist', + 'id': id, + 'title': playlist_title, + 'entries': entries, + } + + +class ZingMp3SongIE(ZingMp3BaseInfoExtractor): + _VALID_URL = r'https?://mp3\.zing\.vn/bai-hat/(?P<slug>[^/]+)/(?P<song_id>\w+)\.html' + _TESTS = [{ + 'url': 'http://mp3.zing.vn/bai-hat/Xa-Mai-Xa-Bao-Thy/ZWZB9WAB.html', + 'md5': 'ead7ae13693b3205cbc89536a077daed', + 'info_dict': { + 'id': 'ZWZB9WAB', + 'title': 'Xa Mãi Xa', + 'ext': 'mp3', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + }] + IE_NAME = 'zingmp3:song' + IE_DESC = 'mp3.zing.vn songs' + + def _real_extract(self, url): + matched = re.match(self._VALID_URL, url) + slug = matched.group('slug') + song_id = matched.group('song_id') + + webpage = self._download_webpage( + 'http://mp3.zing.vn/bai-hat/%s/%s.html' % (slug, song_id), song_id) + + player_xml_url = self._search_regex( + r'&xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url') + + return self._extract_player_xml(player_xml_url, song_id) + + +class ZingMp3AlbumIE(ZingMp3BaseInfoExtractor): + _VALID_URL = r'https?://mp3\.zing\.vn/album/(?P<slug>[^/]+)/(?P<album_id>\w+)\.html' + _TESTS = [{ + 'url': 'http://mp3.zing.vn/album/Lau-Dai-Tinh-Ai-Bang-Kieu-Minh-Tuyet/ZWZBWDAF.html', + 'info_dict': { + '_type': 'playlist', + 'id': 'ZWZBWDAF', + 'title': 'Lâu Đài Tình Ái - Bằng Kiều ft. Minh Tuyết | Album 320 lossless', + }, + 'playlist_count': 10, + }] + IE_NAME = 'zingmp3:album' + IE_DESC = 'mp3.zing.vn albums' + + def _real_extract(self, url): + matched = re.match(self._VALID_URL, url) + slug = matched.group('slug') + album_id = matched.group('album_id') + + webpage = self._download_webpage( + 'http://mp3.zing.vn/album/%s/%s.html' % (slug, album_id), album_id) + player_xml_url = self._search_regex( + r'&xmlURL=(?P<xml_url>[^&]+)&', webpage, 'player xml url') + + return self._extract_player_xml( + player_xml_url, album_id, + playlist_title=self._og_search_title(webpage)) diff --git a/youtube_dl/jsinterp.py b/youtube_dl/jsinterp.py index c40cd376d..b4617fbad 100644 --- a/youtube_dl/jsinterp.py +++ b/youtube_dl/jsinterp.py @@ -61,7 +61,7 @@ class JSInterpreter(object): pass m = re.match( - r'^(?P<var>[a-zA-Z0-9_]+)\.(?P<member>[^(]+)(?:\(+(?P<args>[^()]*)\))?$', + r'^(?P<var>[$a-zA-Z0-9_]+)\.(?P<member>[^(]+)(?:\(+(?P<args>[^()]*)\))?$', expr) if m: variable = m.group('var') diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 4234593dc..11a9e5268 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -5,6 +5,11 @@ import optparse import shlex import sys +from .compat import ( + compat_expanduser, + compat_getenv, + compat_kwargs, +) from .utils import ( get_term_width, write_string, @@ -27,19 +32,19 @@ def parseOpts(overrideArguments=None): return res def _readUserConf(): - xdg_config_home = os.environ.get('XDG_CONFIG_HOME') + xdg_config_home = compat_getenv('XDG_CONFIG_HOME') if xdg_config_home: userConfFile = os.path.join(xdg_config_home, 'youtube-dl', 'config') if not os.path.isfile(userConfFile): userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf') else: - userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl', 'config') + userConfFile = os.path.join(compat_expanduser('~'), '.config', 'youtube-dl', 'config') if not os.path.isfile(userConfFile): - userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf') + userConfFile = os.path.join(compat_expanduser('~'), '.config', 'youtube-dl.conf') userConf = _readOptions(userConfFile, None) if userConf is None: - appdata_dir = os.environ.get('appdata') + appdata_dir = compat_getenv('appdata') if appdata_dir: userConf = _readOptions( os.path.join(appdata_dir, 'youtube-dl', 'config'), @@ -51,11 +56,11 @@ def parseOpts(overrideArguments=None): if userConf is None: userConf = _readOptions( - os.path.join(os.path.expanduser('~'), 'youtube-dl.conf'), + os.path.join(compat_expanduser('~'), 'youtube-dl.conf'), default=None) if userConf is None: userConf = _readOptions( - os.path.join(os.path.expanduser('~'), 'youtube-dl.conf.txt'), + os.path.join(compat_expanduser('~'), 'youtube-dl.conf.txt'), default=None) if userConf is None: @@ -75,7 +80,8 @@ def parseOpts(overrideArguments=None): if len(opts) > 1: opts.insert(1, ', ') - if option.takes_value(): opts.append(' %s' % option.metavar) + if option.takes_value(): + opts.append(' %s' % option.metavar) return "".join(opts) @@ -87,68 +93,69 @@ def parseOpts(overrideArguments=None): for private_opt in ['-p', '--password', '-u', '--username', '--video-password']: try: i = opts.index(private_opt) - opts[i+1] = '<PRIVATE>' + opts[i + 1] = 'PRIVATE' except ValueError: pass return opts - max_width = 80 - max_help_position = 80 - # No need to wrap help messages if we're on a wide console columns = get_term_width() - if columns: max_width = columns + max_width = columns if columns else 80 + max_help_position = 80 fmt = optparse.IndentedHelpFormatter(width=max_width, max_help_position=max_help_position) fmt.format_option_strings = _format_option_string kw = { - 'version' : __version__, - 'formatter' : fmt, - 'usage' : '%prog [options] url [url...]', - 'conflict_handler' : 'resolve', + 'version': __version__, + 'formatter': fmt, + 'usage': '%prog [options] url [url...]', + 'conflict_handler': 'resolve', } - parser = optparse.OptionParser(**kw) + parser = optparse.OptionParser(**compat_kwargs(kw)) - # option groups - general = optparse.OptionGroup(parser, 'General Options') - selection = optparse.OptionGroup(parser, 'Video Selection') - authentication = optparse.OptionGroup(parser, 'Authentication Options') - video_format = optparse.OptionGroup(parser, 'Video Format Options') - subtitles = optparse.OptionGroup(parser, 'Subtitle Options') - downloader = optparse.OptionGroup(parser, 'Download Options') - postproc = optparse.OptionGroup(parser, 'Post-processing Options') - filesystem = optparse.OptionGroup(parser, 'Filesystem Options') - workarounds = optparse.OptionGroup(parser, 'Workarounds') - verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') - - general.add_option('-h', '--help', - action='help', help='print this help text and exit') - general.add_option('-v', '--version', - action='version', help='print program version and exit') - general.add_option('-U', '--update', - action='store_true', dest='update_self', help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)') - general.add_option('-i', '--ignore-errors', - action='store_true', dest='ignoreerrors', help='continue on download errors, for example to skip unavailable videos in a playlist', default=False) - general.add_option('--abort-on-error', - action='store_false', dest='ignoreerrors', - help='Abort downloading of further videos (in the playlist or the command line) if an error occurs') - general.add_option('--dump-user-agent', - action='store_true', dest='dump_user_agent', - help='display the current browser identification', default=False) - general.add_option('--list-extractors', - action='store_true', dest='list_extractors', - help='List all supported extractors and the URLs they would handle', default=False) - general.add_option('--extractor-descriptions', - action='store_true', dest='list_extractor_descriptions', - help='Output descriptions of all supported extractors', default=False) + general = optparse.OptionGroup(parser, 'General Options') general.add_option( - '--proxy', dest='proxy', default=None, metavar='URL', + '-h', '--help', + action='help', + help='print this help text and exit') + general.add_option( + '-v', '--version', + action='version', + help='print program version and exit') + general.add_option( + '-U', '--update', + action='store_true', dest='update_self', + help='update this program to latest version. Make sure that you have sufficient permissions (run with sudo if needed)') + general.add_option( + '-i', '--ignore-errors', + action='store_true', dest='ignoreerrors', default=False, + help='continue on download errors, for example to skip unavailable videos in a playlist') + general.add_option( + '--abort-on-error', + action='store_false', dest='ignoreerrors', + help='Abort downloading of further videos (in the playlist or the command line) if an error occurs') + general.add_option( + '--dump-user-agent', + action='store_true', dest='dump_user_agent', default=False, + help='display the current browser identification') + general.add_option( + '--list-extractors', + action='store_true', dest='list_extractors', default=False, + help='List all supported extractors and the URLs they would handle') + general.add_option( + '--extractor-descriptions', + action='store_true', dest='list_extractor_descriptions', default=False, + help='Output descriptions of all supported extractors') + general.add_option( + '--proxy', dest='proxy', + default=None, metavar='URL', help='Use the specified HTTP/HTTPS proxy. Pass in an empty string (--proxy "") for direct connection') general.add_option( - '--socket-timeout', dest='socket_timeout', - type=float, default=None, help=u'Time to wait before giving up, in seconds') + '--socket-timeout', + dest='socket_timeout', type=float, default=None, + help='Time to wait before giving up, in seconds') general.add_option( '--default-search', dest='default_search', metavar='PREFIX', @@ -157,7 +164,13 @@ def parseOpts(overrideArguments=None): '--ignore-config', action='store_true', help='Do not read configuration files. When given 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)') + general.add_option( + '--flat-playlist', + action='store_const', dest='extract_flat', const='in_playlist', + default=False, + help='Do not extract the videos of a playlist, only list them.') + selection = optparse.OptionGroup(parser, 'Video Selection') selection.add_option( '--playlist-start', dest='playliststart', metavar='NUMBER', default=1, type=int, @@ -166,245 +179,387 @@ def parseOpts(overrideArguments=None): '--playlist-end', dest='playlistend', metavar='NUMBER', default=None, type=int, help='playlist video to end at (default is last)') - selection.add_option('--match-title', dest='matchtitle', metavar='REGEX',help='download only matching titles (regex or caseless sub-string)') - selection.add_option('--reject-title', dest='rejecttitle', metavar='REGEX',help='skip download for matching titles (regex or caseless sub-string)') - selection.add_option('--max-downloads', metavar='NUMBER', - dest='max_downloads', type=int, default=None, - help='Abort after downloading NUMBER files') - selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None) - selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None) - selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None) selection.add_option( - '--datebefore', metavar='DATE', dest='datebefore', default=None, + '--match-title', + dest='matchtitle', metavar='REGEX', + help='download only matching titles (regex or caseless sub-string)') + selection.add_option( + '--reject-title', + dest='rejecttitle', metavar='REGEX', + help='skip download for matching titles (regex or caseless sub-string)') + selection.add_option( + '--max-downloads', + dest='max_downloads', metavar='NUMBER', type=int, default=None, + help='Abort after downloading NUMBER files') + selection.add_option( + '--min-filesize', + metavar='SIZE', dest='min_filesize', default=None, + help='Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)') + selection.add_option( + '--max-filesize', + metavar='SIZE', dest='max_filesize', default=None, + help='Do not download any videos larger than SIZE (e.g. 50k or 44.6m)') + selection.add_option( + '--date', + metavar='DATE', dest='date', default=None, + help='download only videos uploaded in this date') + selection.add_option( + '--datebefore', + metavar='DATE', dest='datebefore', default=None, help='download only videos uploaded on or before this date (i.e. inclusive)') selection.add_option( - '--dateafter', metavar='DATE', dest='dateafter', default=None, + '--dateafter', + metavar='DATE', dest='dateafter', default=None, help='download only videos uploaded on or after this date (i.e. inclusive)') selection.add_option( - '--min-views', metavar='COUNT', dest='min_views', - default=None, type=int, - help="Do not download any videos with less than COUNT views",) + '--min-views', + metavar='COUNT', dest='min_views', default=None, type=int, + help='Do not download any videos with less than COUNT views',) selection.add_option( - '--max-views', metavar='COUNT', dest='max_views', - default=None, type=int, - help="Do not download any videos with more than COUNT views",) - selection.add_option('--no-playlist', action='store_true', dest='noplaylist', help='download only the currently playing video', default=False) - selection.add_option('--age-limit', metavar='YEARS', dest='age_limit', - help='download only videos suitable for the given age', - default=None, type=int) - selection.add_option('--download-archive', metavar='FILE', - dest='download_archive', - help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.') + '--max-views', + metavar='COUNT', dest='max_views', default=None, type=int, + help='Do not download any videos with more than COUNT views') selection.add_option( - '--include-ads', dest='include_ads', - action='store_true', + '--no-playlist', + action='store_true', dest='noplaylist', default=False, + help='If the URL refers to a video and a playlist, download only the video.') + selection.add_option( + '--age-limit', + metavar='YEARS', dest='age_limit', default=None, type=int, + help='download only videos suitable for the given age') + selection.add_option( + '--download-archive', metavar='FILE', + dest='download_archive', + help='Download only videos not listed in the archive file. Record the IDs of all downloaded videos in it.') + selection.add_option( + '--include-ads', + dest='include_ads', action='store_true', help='Download advertisements as well (experimental)') - selection.add_option( - '--youtube-include-dash-manifest', action='store_true', - dest='youtube_include_dash_manifest', default=False, - help='Try to download the DASH manifest on YouTube videos (experimental)') - authentication.add_option('-u', '--username', - dest='username', metavar='USERNAME', help='account username') - authentication.add_option('-p', '--password', - dest='password', metavar='PASSWORD', help='account password') - authentication.add_option('-2', '--twofactor', - dest='twofactor', metavar='TWOFACTOR', help='two-factor auth code') - authentication.add_option('-n', '--netrc', - action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False) - authentication.add_option('--video-password', - dest='videopassword', metavar='PASSWORD', help='video password (vimeo, smotri)') + authentication = optparse.OptionGroup(parser, 'Authentication Options') + authentication.add_option( + '-u', '--username', + dest='username', metavar='USERNAME', + help='login with this account ID') + authentication.add_option( + '-p', '--password', + dest='password', metavar='PASSWORD', + help='account password') + authentication.add_option( + '-2', '--twofactor', + dest='twofactor', metavar='TWOFACTOR', + help='two-factor auth code') + authentication.add_option( + '-n', '--netrc', + action='store_true', dest='usenetrc', default=False, + help='use .netrc authentication data') + authentication.add_option( + '--video-password', + dest='videopassword', metavar='PASSWORD', + help='video password (vimeo, smotri)') + video_format = optparse.OptionGroup(parser, 'Video Format Options') + video_format.add_option( + '-f', '--format', + action='store', dest='format', metavar='FORMAT', default=None, + help=( + 'video format code, specify the order of preference using' + ' slashes: -f 22/17/18 . -f mp4 , -f m4a and -f flv are also' + ' supported. You can also use the special names "best",' + ' "bestvideo", "bestaudio", "worst", "worstvideo" and' + ' "worstaudio". 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.')) + video_format.add_option( + '--all-formats', + action='store_const', dest='format', const='all', + help='download all available video formats') + video_format.add_option( + '--prefer-free-formats', + action='store_true', dest='prefer_free_formats', default=False, + help='prefer free video formats unless a specific one is requested') + video_format.add_option( + '--max-quality', + action='store', dest='format_limit', metavar='FORMAT', + help='highest quality format to download') + video_format.add_option( + '-F', '--list-formats', + action='store_true', dest='listformats', + help='list all available formats') + video_format.add_option( + '--youtube-include-dash-manifest', + action='store_true', dest='youtube_include_dash_manifest', default=True, + help=optparse.SUPPRESS_HELP) + video_format.add_option( + '--youtube-skip-dash-manifest', + action='store_false', dest='youtube_include_dash_manifest', + help='Do not download the DASH manifest on YouTube videos') - video_format.add_option('-f', '--format', - action='store', dest='format', metavar='FORMAT', default=None, - help='video format code, specify the order of preference using slashes: "-f 22/17/18". "-f mp4" and "-f flv" are also supported. You can also use the special names "best", "bestvideo", "bestaudio", "worst", "worstvideo" and "worstaudio". By default, youtube-dl will pick the best quality.') - video_format.add_option('--all-formats', - action='store_const', dest='format', help='download all available video formats', const='all') - video_format.add_option('--prefer-free-formats', - action='store_true', dest='prefer_free_formats', default=False, help='prefer free video formats unless a specific one is requested') - video_format.add_option('--max-quality', - action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download') - video_format.add_option('-F', '--list-formats', - action='store_true', dest='listformats', help='list all available formats') + subtitles = optparse.OptionGroup(parser, 'Subtitle Options') + subtitles.add_option( + '--write-sub', '--write-srt', + action='store_true', dest='writesubtitles', default=False, + help='write subtitle file') + subtitles.add_option( + '--write-auto-sub', '--write-automatic-sub', + action='store_true', dest='writeautomaticsub', default=False, + help='write automatic subtitle file (youtube only)') + subtitles.add_option( + '--all-subs', + action='store_true', dest='allsubtitles', default=False, + help='downloads all the available subtitles of the video') + subtitles.add_option( + '--list-subs', + action='store_true', dest='listsubtitles', default=False, + help='lists all available subtitles for the video') + subtitles.add_option( + '--sub-format', + action='store', dest='subtitlesformat', metavar='FORMAT', default='srt', + help='subtitle format (default=srt) ([sbv/vtt] youtube only)') + subtitles.add_option( + '--sub-lang', '--sub-langs', '--srt-lang', + action='callback', dest='subtitleslangs', metavar='LANGS', type='str', + default=[], callback=_comma_separated_values_options_callback, + help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'') - subtitles.add_option('--write-sub', '--write-srt', - action='store_true', dest='writesubtitles', - help='write subtitle file', default=False) - subtitles.add_option('--write-auto-sub', '--write-automatic-sub', - action='store_true', dest='writeautomaticsub', - help='write automatic subtitle file (youtube only)', default=False) - subtitles.add_option('--all-subs', - action='store_true', dest='allsubtitles', - help='downloads all the available subtitles of the video', default=False) - subtitles.add_option('--list-subs', - action='store_true', dest='listsubtitles', - help='lists all available subtitles for the video', default=False) - subtitles.add_option('--sub-format', - action='store', dest='subtitlesformat', metavar='FORMAT', - help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt') - subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang', - action='callback', dest='subtitleslangs', metavar='LANGS', type='str', - default=[], callback=_comma_separated_values_options_callback, - help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'') - - downloader.add_option('-r', '--rate-limit', - dest='ratelimit', metavar='LIMIT', help='maximum download rate in bytes per second (e.g. 50K or 4.2M)') - downloader.add_option('-R', '--retries', - dest='retries', metavar='RETRIES', help='number of retries (default is %default)', default=10) - downloader.add_option('--buffer-size', - dest='buffersize', metavar='SIZE', help='size of download buffer (e.g. 1024 or 16K) (default is %default)', default="1024") - downloader.add_option('--no-resize-buffer', - action='store_true', dest='noresizebuffer', - help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.', default=False) - downloader.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP) + downloader = optparse.OptionGroup(parser, 'Download Options') + downloader.add_option( + '-r', '--rate-limit', + dest='ratelimit', metavar='LIMIT', + help='maximum download rate in bytes per second (e.g. 50K or 4.2M)') + downloader.add_option( + '-R', '--retries', + dest='retries', metavar='RETRIES', default=10, + help='number of retries (default is %default)') + downloader.add_option( + '--buffer-size', + dest='buffersize', metavar='SIZE', default='1024', + help='size of download buffer (e.g. 1024 or 16K) (default is %default)') + downloader.add_option( + '--no-resize-buffer', + action='store_true', dest='noresizebuffer', default=False, + help='do not automatically adjust the buffer size. By default, the buffer size is automatically resized from an initial value of SIZE.') + downloader.add_option( + '--test', + action='store_true', dest='test', default=False, + help=optparse.SUPPRESS_HELP) + workarounds = optparse.OptionGroup(parser, 'Workarounds') workarounds.add_option( - '--encoding', dest='encoding', metavar='ENCODING', + '--encoding', + dest='encoding', metavar='ENCODING', help='Force the specified encoding (experimental)') workarounds.add_option( - '--no-check-certificate', action='store_true', - dest='no_check_certificate', default=False, + '--no-check-certificate', + action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.') workarounds.add_option( - '--prefer-insecure', '--prefer-unsecure', action='store_true', dest='prefer_insecure', + '--prefer-insecure', + '--prefer-unsecure', action='store_true', dest='prefer_insecure', help='Use an unencrypted connection to retrieve information about the video. (Currently supported only for YouTube)') workarounds.add_option( - '--user-agent', metavar='UA', - dest='user_agent', help='specify a custom user agent') + '--user-agent', + metavar='UA', dest='user_agent', + help='specify a custom user agent') workarounds.add_option( - '--referer', metavar='REF', - dest='referer', default=None, + '--referer', + metavar='URL', dest='referer', default=None, help='specify a custom referer, use if the video access is restricted to one domain', ) workarounds.add_option( - '--add-header', metavar='FIELD:VALUE', - dest='headers', action='append', + '--add-header', + metavar='FIELD:VALUE', dest='headers', action='append', help='specify a custom HTTP header and its value, separated by a colon \':\'. You can use this option multiple times', ) workarounds.add_option( - '--bidi-workaround', dest='bidi_workaround', action='store_true', - help=u'Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH') + '--bidi-workaround', + dest='bidi_workaround', action='store_true', + help='Work around terminals that lack bidirectional text support. Requires bidiv or fribidi executable in PATH') - verbosity.add_option('-q', '--quiet', - action='store_true', dest='quiet', help='activates quiet mode', default=False) + verbosity = optparse.OptionGroup(parser, 'Verbosity / Simulation Options') + verbosity.add_option( + '-q', '--quiet', + action='store_true', dest='quiet', default=False, + help='activates quiet mode') verbosity.add_option( '--no-warnings', dest='no_warnings', action='store_true', default=False, help='Ignore warnings') - verbosity.add_option('-s', '--simulate', - action='store_true', dest='simulate', help='do not download the video and do not write anything to disk', default=False) - verbosity.add_option('--skip-download', - action='store_true', dest='skip_download', help='do not download the video', default=False) - verbosity.add_option('-g', '--get-url', - action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False) - verbosity.add_option('-e', '--get-title', - action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False) - verbosity.add_option('--get-id', - action='store_true', dest='getid', help='simulate, quiet but print id', default=False) - verbosity.add_option('--get-thumbnail', - action='store_true', dest='getthumbnail', - help='simulate, quiet but print thumbnail URL', default=False) - verbosity.add_option('--get-description', - action='store_true', dest='getdescription', - help='simulate, quiet but print video description', default=False) - verbosity.add_option('--get-duration', - action='store_true', dest='getduration', - help='simulate, quiet but print video length', default=False) - verbosity.add_option('--get-filename', - action='store_true', dest='getfilename', - help='simulate, quiet but print output filename', default=False) - verbosity.add_option('--get-format', - action='store_true', dest='getformat', - help='simulate, quiet but print output format', default=False) - verbosity.add_option('-j', '--dump-json', - action='store_true', dest='dumpjson', - help='simulate, quiet but print JSON information. See --output for a description of available keys.', default=False) - verbosity.add_option('--newline', - action='store_true', dest='progress_with_newline', help='output progress bar as new lines', default=False) - verbosity.add_option('--no-progress', - action='store_true', dest='noprogress', help='do not print progress bar', default=False) - verbosity.add_option('--console-title', - action='store_true', dest='consoletitle', - help='display progress in console titlebar', default=False) - verbosity.add_option('-v', '--verbose', - action='store_true', dest='verbose', help='print various debugging information', default=False) - verbosity.add_option('--dump-intermediate-pages', - action='store_true', dest='dump_intermediate_pages', default=False, - help='print downloaded pages to debug problems (very verbose)') - verbosity.add_option('--write-pages', - action='store_true', dest='write_pages', default=False, - help='Write downloaded intermediary pages to files in the current directory to debug problems') - verbosity.add_option('--youtube-print-sig-code', - action='store_true', dest='youtube_print_sig_code', default=False, - help=optparse.SUPPRESS_HELP) - verbosity.add_option('--print-traffic', - dest='debug_printtraffic', action='store_true', default=False, - help='Display sent and read HTTP traffic') + verbosity.add_option( + '-s', '--simulate', + action='store_true', dest='simulate', default=False, + help='do not download the video and do not write anything to disk',) + verbosity.add_option( + '--skip-download', + action='store_true', dest='skip_download', default=False, + help='do not download the video',) + verbosity.add_option( + '-g', '--get-url', + action='store_true', dest='geturl', default=False, + help='simulate, quiet but print URL') + verbosity.add_option( + '-e', '--get-title', + action='store_true', dest='gettitle', default=False, + help='simulate, quiet but print title') + verbosity.add_option( + '--get-id', + action='store_true', dest='getid', default=False, + help='simulate, quiet but print id') + verbosity.add_option( + '--get-thumbnail', + action='store_true', dest='getthumbnail', default=False, + help='simulate, quiet but print thumbnail URL') + verbosity.add_option( + '--get-description', + action='store_true', dest='getdescription', default=False, + help='simulate, quiet but print video description') + verbosity.add_option( + '--get-duration', + action='store_true', dest='getduration', default=False, + help='simulate, quiet but print video length') + verbosity.add_option( + '--get-filename', + action='store_true', dest='getfilename', default=False, + help='simulate, quiet but print output filename') + verbosity.add_option( + '--get-format', + action='store_true', dest='getformat', default=False, + help='simulate, quiet but print output format') + verbosity.add_option( + '-j', '--dump-json', + action='store_true', dest='dumpjson', default=False, + help='simulate, quiet but print JSON information. See --output for a description of available keys.') + verbosity.add_option( + '-J', '--dump-single-json', + action='store_true', dest='dump_single_json', default=False, + help='simulate, quiet but print JSON information for each command-line argument. If the URL refers to a playlist, dump the whole playlist information in a single line.') + verbosity.add_option( + '--newline', + action='store_true', dest='progress_with_newline', default=False, + help='output progress bar as new lines') + verbosity.add_option( + '--no-progress', + action='store_true', dest='noprogress', default=False, + help='do not print progress bar') + verbosity.add_option( + '--console-title', + action='store_true', dest='consoletitle', default=False, + help='display progress in console titlebar') + verbosity.add_option( + '-v', '--verbose', + action='store_true', dest='verbose', default=False, + help='print various debugging information') + verbosity.add_option( + '--dump-intermediate-pages', + action='store_true', dest='dump_intermediate_pages', default=False, + help='print downloaded pages to debug problems (very verbose)') + verbosity.add_option( + '--write-pages', + action='store_true', dest='write_pages', default=False, + help='Write downloaded intermediary pages to files in the current directory to debug problems') + verbosity.add_option( + '--youtube-print-sig-code', + action='store_true', dest='youtube_print_sig_code', default=False, + help=optparse.SUPPRESS_HELP) + verbosity.add_option( + '--print-traffic', + dest='debug_printtraffic', action='store_true', default=False, + help='Display sent and read HTTP traffic') - - filesystem.add_option('-a', '--batch-file', - dest='batchfile', metavar='FILE', help='file containing URLs to download (\'-\' for stdin)') - filesystem.add_option('--id', - action='store_true', dest='useid', help='use only video ID in file name', default=False) - filesystem.add_option('-A', '--auto-number', - action='store_true', dest='autonumber', - help='number downloaded files starting from 00000', default=False) - filesystem.add_option('-o', '--output', - dest='outtmpl', metavar='TEMPLATE', - help=('output filename template. Use %(title)s to get the title, ' - '%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, ' - '%(autonumber)s to get an automatically incremented number, ' - '%(ext)s for the filename extension, ' - '%(format)s for the format description (like "22 - 1280x720" or "HD"), ' - '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), ' - '%(upload_date)s for the upload date (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/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')) - filesystem.add_option('--autonumber-size', - dest='autonumber_size', metavar='NUMBER', - help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given') - filesystem.add_option('--restrict-filenames', - action='store_true', dest='restrictfilenames', - help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False) - filesystem.add_option('-t', '--title', - action='store_true', dest='usetitle', help='[deprecated] use title in file name (default)', default=False) - filesystem.add_option('-l', '--literal', - action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False) - filesystem.add_option('-w', '--no-overwrites', - action='store_true', dest='nooverwrites', help='do not overwrite files', default=False) - filesystem.add_option('-c', '--continue', - action='store_true', dest='continue_dl', help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.', default=True) - filesystem.add_option('--no-continue', - action='store_false', dest='continue_dl', - help='do not resume partially downloaded files (restart from beginning)') - filesystem.add_option('--no-part', - action='store_true', dest='nopart', help='do not use .part files', default=False) - filesystem.add_option('--no-mtime', - action='store_false', dest='updatetime', - help='do not use the Last-modified header to set the file modification time', default=True) - filesystem.add_option('--write-description', - action='store_true', dest='writedescription', - help='write video description to a .description file', default=False) - filesystem.add_option('--write-info-json', - action='store_true', dest='writeinfojson', - help='write video metadata to a .info.json file', default=False) - filesystem.add_option('--write-annotations', - action='store_true', dest='writeannotations', - help='write video annotations to a .annotation file', default=False) - filesystem.add_option('--write-thumbnail', - action='store_true', dest='writethumbnail', - help='write thumbnail image to disk', default=False) - filesystem.add_option('--load-info', - dest='load_info_filename', metavar='FILE', - help='json file containing the video information (created with the "--write-json" option)') - filesystem.add_option('--cookies', - dest='cookiefile', metavar='FILE', help='file to read cookies from and dump cookie jar in') + filesystem = optparse.OptionGroup(parser, 'Filesystem Options') + filesystem.add_option( + '-a', '--batch-file', + dest='batchfile', metavar='FILE', + help='file containing URLs to download (\'-\' for stdin)') + filesystem.add_option( + '--id', default=False, + action='store_true', dest='useid', help='use only video ID in file name') + filesystem.add_option( + '-A', '--auto-number', + action='store_true', dest='autonumber', default=False, + help='number downloaded files starting from 00000') + filesystem.add_option( + '-o', '--output', + dest='outtmpl', metavar='TEMPLATE', + help=('output filename template. Use %(title)s to get the title, ' + '%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, ' + '%(autonumber)s to get an automatically incremented number, ' + '%(ext)s for the filename extension, ' + '%(format)s for the format description (like "22 - 1280x720" or "HD"), ' + '%(format_id)s for the unique id of the format (like Youtube\'s itags: "137"), ' + '%(upload_date)s for the upload date (YYYYMMDD), ' + '%(extractor)s for the provider (youtube, metacafe, etc), ' + '%(id)s for the video id, ' + '%(playlist_title)s, %(playlist_id)s, or %(playlist)s (=title if present, ID otherwise) for the playlist the video is in, ' + '%(playlist_index)s for the position in the playlist. ' + '%(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. ' + '%% for a literal percent. ' + 'Use - to output to stdout. Can also be used to download to a different directory, ' + 'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')) + filesystem.add_option( + '--autonumber-size', + dest='autonumber_size', metavar='NUMBER', + help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --auto-number option is given') + filesystem.add_option( + '--restrict-filenames', + action='store_true', dest='restrictfilenames', default=False, + help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames') + filesystem.add_option( + '-t', '--title', + action='store_true', dest='usetitle', default=False, + help='[deprecated] use title in file name (default)') + filesystem.add_option( + '-l', '--literal', default=False, + action='store_true', dest='usetitle', + help='[deprecated] alias of --title') + filesystem.add_option( + '-w', '--no-overwrites', + action='store_true', dest='nooverwrites', default=False, + help='do not overwrite files') + filesystem.add_option( + '-c', '--continue', + action='store_true', dest='continue_dl', default=True, + help='force resume of partially downloaded files. By default, youtube-dl will resume downloads if possible.') + filesystem.add_option( + '--no-continue', + action='store_false', dest='continue_dl', + help='do not resume partially downloaded files (restart from beginning)') + filesystem.add_option( + '--no-part', + action='store_true', dest='nopart', default=False, + help='do not use .part files - write directly into output file') + filesystem.add_option( + '--no-mtime', + action='store_false', dest='updatetime', default=True, + help='do not use the Last-modified header to set the file modification time') + filesystem.add_option( + '--write-description', + action='store_true', dest='writedescription', default=False, + help='write video description to a .description file') + filesystem.add_option( + '--write-info-json', + action='store_true', dest='writeinfojson', default=False, + help='write video metadata to a .info.json file') + filesystem.add_option( + '--write-annotations', + action='store_true', dest='writeannotations', default=False, + help='write video annotations to a .annotation file') + filesystem.add_option( + '--write-thumbnail', + action='store_true', dest='writethumbnail', default=False, + help='write thumbnail image to disk') + filesystem.add_option( + '--load-info', + dest='load_info_filename', metavar='FILE', + help='json file containing the video information (created with the "--write-json" option)') + filesystem.add_option( + '--cookies', + dest='cookiefile', metavar='FILE', + help='file to read cookies from and dump cookie jar in') filesystem.add_option( '--cache-dir', dest='cachedir', default=None, metavar='DIR', help='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.') @@ -412,39 +567,66 @@ def parseOpts(overrideArguments=None): '--no-cache-dir', action='store_const', const=False, dest='cachedir', help='Disable filesystem caching') filesystem.add_option( - '--rm-cache-dir', action='store_true', dest='rm_cachedir', + '--rm-cache-dir', + action='store_true', dest='rm_cachedir', help='Delete all filesystem cache files') - - postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False, - help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)') - postproc.add_option('--audio-format', metavar='FORMAT', dest='audioformat', default='best', - help='"best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; best by default') - postproc.add_option('--audio-quality', metavar='QUALITY', dest='audioquality', default='5', - help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5)') - postproc.add_option('--recode-video', metavar='FORMAT', dest='recodevideo', default=None, - help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)') - postproc.add_option('--join-parts', action='store_true', dest='joinparts', default=False, - help='Join the video parts if the video is splitted in different parts.') - postproc.add_option('-k', '--keep-video', action='store_true', dest='keepvideo', default=False, - help='keeps the video file on disk after the post-processing; the video is erased by default') - postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False, - help='do not overwrite post-processed files; the post-processed files are overwritten by default') - postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False, - help='embed subtitles in the video (only for mp4 videos)') - postproc.add_option('--embed-thumbnail', action='store_true', dest='embedthumbnail', default=False, - help='embed thumbnail in the audio as cover art') - postproc.add_option('--add-metadata', action='store_true', dest='addmetadata', default=False, - help='write metadata to the video file') - postproc.add_option('--xattrs', action='store_true', dest='xattrs', default=False, - help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)') - postproc.add_option('--prefer-avconv', action='store_false', dest='prefer_ffmpeg', + postproc = optparse.OptionGroup(parser, 'Post-processing Options') + postproc.add_option( + '-x', '--extract-audio', + action='store_true', dest='extractaudio', default=False, + help='convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe)') + postproc.add_option( + '--audio-format', metavar='FORMAT', dest='audioformat', default='best', + help='"best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "%default" by default') + postproc.add_option( + '--audio-quality', metavar='QUALITY', + dest='audioquality', default='5', + help='ffmpeg/avconv audio quality specification, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default %default)') + postproc.add_option( + '--recode-video', + metavar='FORMAT', dest='recodevideo', default=None, + help='Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv)') + postproc.add_option( + '--join-parts', + action='store_true', dest='joinparts', default=False, + help='Join the video parts if the video is splitted in different parts.') + postproc.add_option( + '-k', '--keep-video', + action='store_true', dest='keepvideo', default=False, + help='keeps the video file on disk after the post-processing; the video is erased by default') + postproc.add_option( + '--no-post-overwrites', + action='store_true', dest='nopostoverwrites', default=False, + help='do not overwrite post-processed files; the post-processed files are overwritten by default') + postproc.add_option( + '--embed-subs', + action='store_true', dest='embedsubtitles', default=False, + help='embed subtitles in the video (only for mp4 videos)') + postproc.add_option( + '--embed-thumbnail', + action='store_true', dest='embedthumbnail', default=False, + help='embed thumbnail in the audio as cover art') + postproc.add_option( + '--add-metadata', + action='store_true', dest='addmetadata', default=False, + help='write metadata to the video file') + postproc.add_option( + '--xattrs', + action='store_true', dest='xattrs', default=False, + help='write metadata to the video file\'s xattrs (using dublin core and xdg standards)') + postproc.add_option( + '--prefer-avconv', + action='store_false', dest='prefer_ffmpeg', help='Prefer avconv over ffmpeg for running the postprocessors (default)') - postproc.add_option('--prefer-ffmpeg', action='store_true', dest='prefer_ffmpeg', + postproc.add_option( + '--prefer-ffmpeg', + action='store_true', dest='prefer_ffmpeg', help='Prefer ffmpeg over avconv for running the postprocessors') postproc.add_option( - '--exec', metavar='CMD', dest='exec_cmd', - help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'' ) + '--exec', + metavar='CMD', dest='exec_cmd', + help='Execute a command on the file after downloading, similar to find\'s -exec syntax. Example: --exec \'adb push {} /sdcard/Music/ && rm {}\'') parser.add_option_group(general) parser.add_option_group(selection) @@ -460,7 +642,7 @@ def parseOpts(overrideArguments=None): if overrideArguments is not None: opts, args = parser.parse_args(overrideArguments) if opts.verbose: - write_string(u'[debug] Override config: ' + repr(overrideArguments) + '\n') + write_string('[debug] Override config: ' + repr(overrideArguments) + '\n') else: commandLineConf = sys.argv[1:] if '--ignore-config' in commandLineConf: @@ -476,8 +658,8 @@ def parseOpts(overrideArguments=None): opts, args = parser.parse_args(argv) if opts.verbose: - write_string(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n') - write_string(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n') - write_string(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n') + write_string('[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n') + write_string('[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n') + write_string('[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n') return parser, opts, args diff --git a/youtube_dl/postprocessor/__init__.py b/youtube_dl/postprocessor/__init__.py index ee88f7483..06efd497b 100644 --- a/youtube_dl/postprocessor/__init__.py +++ b/youtube_dl/postprocessor/__init__.py @@ -1,7 +1,11 @@ +from __future__ import unicode_literals from .atomicparsley import AtomicParsleyPP from .ffmpeg import ( + FFmpegPostProcessor, FFmpegAudioFixPP, + FFmpegEmbedSubtitlePP, + FFmpegExtractAudioPP, FFmpegMergerPP, FFmpegMetadataPP, FFmpegVideoConvertor, @@ -14,13 +18,16 @@ from .execafterdownload import ExecAfterDownloadPP __all__ = [ 'AtomicParsleyPP', + 'ExecAfterDownloadPP', 'FFmpegAudioFixPP', + 'FFmpegEmbedSubtitlePP', + 'FFmpegExtractAudioPP', 'FFmpegMergerPP', 'FFmpegMetadataPP', + 'FFmpegPostProcessor', 'FFmpegVideoConvertor', 'FFmpegExtractAudioPP', 'FFmpegEmbedSubtitlePP', 'FFmpegJoinVideosPP', 'XAttrMetadataPP', - 'ExecAfterDownloadPP', ] diff --git a/youtube_dl/postprocessor/atomicparsley.py b/youtube_dl/postprocessor/atomicparsley.py index 765b2d9ee..448ccc5f3 100644 --- a/youtube_dl/postprocessor/atomicparsley.py +++ b/youtube_dl/postprocessor/atomicparsley.py @@ -6,10 +6,11 @@ import os import subprocess from .common import PostProcessor - +from ..compat import ( + compat_urlretrieve, +) from ..utils import ( check_executable, - compat_urlretrieve, encodeFilename, PostProcessingError, prepend_extension, diff --git a/youtube_dl/postprocessor/common.py b/youtube_dl/postprocessor/common.py index 788f94d02..e54ae678d 100644 --- a/youtube_dl/postprocessor/common.py +++ b/youtube_dl/postprocessor/common.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + from ..utils import PostProcessingError diff --git a/youtube_dl/postprocessor/execafterdownload.py b/youtube_dl/postprocessor/execafterdownload.py index 08419a3d4..09db43611 100644 --- a/youtube_dl/postprocessor/execafterdownload.py +++ b/youtube_dl/postprocessor/execafterdownload.py @@ -3,10 +3,8 @@ from __future__ import unicode_literals import subprocess from .common import PostProcessor -from ..utils import ( - shlex_quote, - PostProcessingError, -) +from ..compat import shlex_quote +from ..utils import PostProcessingError class ExecAfterDownloadPP(PostProcessor): @@ -28,4 +26,3 @@ class ExecAfterDownloadPP(PostProcessor): 'Command returned error code %d' % retCode) return None, information # by default, keep file and do nothing - diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 1362a8986..2f3246d89 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import subprocess import sys @@ -7,11 +9,14 @@ import io from .common import AudioConversionError, PostProcessor -from ..utils import ( - check_executable, +from ..compat import ( compat_subprocess_get_DEVNULL, +) +from ..utils import ( encodeArgument, encodeFilename, + get_exe_version, + is_outdated_version, PostProcessingError, prepend_extension, shell_quote, @@ -27,29 +32,56 @@ class FFmpegPostProcessorError(PostProcessingError): class FFmpegPostProcessor(PostProcessor): def __init__(self, downloader=None, deletetempfiles=False): PostProcessor.__init__(self, downloader) - self._exes = self.detect_executables() + self._versions = self.get_versions() self._deletetempfiles = deletetempfiles - @staticmethod - def detect_executables(): - programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] - return dict((program, check_executable(program, ['-version'])) for program in programs) + def check_version(self): + if not self._executable: + raise FFmpegPostProcessorError('ffmpeg or avconv not found. Please install one.') - def _get_executable(self): + REQUIRED_VERSION = '1.0' + if is_outdated_version( + self._versions[self._executable], REQUIRED_VERSION): + warning = 'Your copy of %s is outdated, update %s to version %s or newer if you encounter any errors.' % ( + self._executable, self._executable, REQUIRED_VERSION) + if self._downloader: + self._downloader.report_warning(warning) + + @staticmethod + def get_versions(): + programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe'] + return dict((p, get_exe_version(p, args=['-version'])) for p in programs) + + @property + def _executable(self): if self._downloader.params.get('prefer_ffmpeg', False): - return self._exes['ffmpeg'] or self._exes['avconv'] + prefs = ('ffmpeg', 'avconv') else: - return self._exes['avconv'] or self._exes['ffmpeg'] + prefs = ('avconv', 'ffmpeg') + for p in prefs: + if self._versions[p]: + return p + return None + + @property + def _probe_executable(self): + if self._downloader.params.get('prefer_ffmpeg', False): + prefs = ('ffprobe', 'avprobe') + else: + prefs = ('avprobe', 'ffprobe') + for p in prefs: + if self._versions[p]: + return p + return None def _uses_avconv(self): - return self._get_executable() == self._exes['avconv'] + return self._executable == 'avconv' def _encode_opts(self, opts): return [encodeArgument(o) for o in opts] def run_ffmpeg_multiple_files(self, input_paths, out_path, opts, input_opts=[]): - if not self._get_executable(): - raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.') + self.check_version() files_cmd = [] for path in input_paths: @@ -59,7 +91,7 @@ class FFmpegPostProcessor(PostProcessor): [encodeFilename(self._ffmpeg_filename_argument(out_path), True)]) if self._downloader.params.get('verbose', False): - self._downloader.to_screen(u'[debug] ffmpeg command line: %s' % shell_quote(cmd)) + self._downloader.to_screen('[debug] ffmpeg command line: %s' % shell_quote(cmd)) p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE) stdout, stderr = p.communicate() if p.returncode != 0: @@ -75,8 +107,8 @@ class FFmpegPostProcessor(PostProcessor): def _ffmpeg_filename_argument(self, fn): # ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details - if fn.startswith(u'-'): - return u'./' + fn + if fn.startswith('-'): + return './' + fn return fn @@ -90,11 +122,12 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): self._nopostoverwrites = nopostoverwrites def get_audio_codec(self, path): - if not self._exes['ffprobe'] and not self._exes['avprobe']: - raise PostProcessingError(u'ffprobe or avprobe not found. Please install one.') + + if not self._probe_executable: + raise PostProcessingError('ffprobe or avprobe not found. Please install one.') try: cmd = [ - self._exes['avprobe'] or self._exes['ffprobe'], + self._probe_executable, '-show_streams', encodeFilename(self._ffmpeg_filename_argument(path), True)] handle = subprocess.Popen(cmd, stderr=compat_subprocess_get_DEVNULL(), stdout=subprocess.PIPE) @@ -127,7 +160,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): filecodec = self.get_audio_codec(path) if filecodec is None: - raise PostProcessingError(u'WARNING: unable to obtain file audio codec with ffprobe') + raise PostProcessingError('WARNING: unable to obtain file audio codec with ffprobe') uses_avconv = self._uses_avconv() more_opts = [] @@ -176,7 +209,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): extension = 'wav' more_opts += ['-f', 'wav'] - prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups + prefix, sep, ext = path.rpartition('.') # not os.path.splitext, since the latter does not work on unicode in all setups new_path = prefix + sep + extension # If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly. @@ -185,16 +218,16 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): try: if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)): - self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path) + self._downloader.to_screen('[youtube] Post-process file %s exists, skipping' % new_path) else: - self._downloader.to_screen(u'[' + self._get_executable() + '] Destination: ' + new_path) + self._downloader.to_screen('[' + self._executable + '] Destination: ' + new_path) self.run_ffmpeg(path, new_path, acodec, more_opts) except: - etype,e,tb = sys.exc_info() + etype, e, tb = sys.exc_info() if isinstance(e, AudioConversionError): - msg = u'audio conversion failed: ' + e.msg + msg = 'audio conversion failed: ' + e.msg else: - msg = u'error running ' + self._get_executable() + msg = 'error running ' + self._executable raise PostProcessingError(msg) # Try to update the date time for extracted audio file. @@ -202,30 +235,30 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor): try: os.utime(encodeFilename(new_path), (time.time(), information['filetime'])) except: - self._downloader.report_warning(u'Cannot update utime of audio file') + self._downloader.report_warning('Cannot update utime of audio file') information['filepath'] = new_path - return self._nopostoverwrites,information + return self._nopostoverwrites, information class FFmpegVideoConvertor(FFmpegPostProcessor): - def __init__(self, downloader=None,preferedformat=None): + def __init__(self, downloader=None, preferedformat=None): super(FFmpegVideoConvertor, self).__init__(downloader) - self._preferedformat=preferedformat + self._preferedformat = preferedformat def run(self, information): path = information['filepath'] - prefix, sep, ext = path.rpartition(u'.') + prefix, sep, ext = path.rpartition('.') outpath = prefix + sep + self._preferedformat if information['ext'] == self._preferedformat: - self._downloader.to_screen(u'[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat)) - return True,information - self._downloader.to_screen(u'['+'ffmpeg'+'] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) +outpath) + self._downloader.to_screen('[ffmpeg] Not converting video file %s - already is in target format %s' % (path, self._preferedformat)) + return True, information + self._downloader.to_screen('[' + 'ffmpeg' + '] Converting video from %s to %s, Destination: ' % (information['ext'], self._preferedformat) + outpath) self.run_ffmpeg(path, outpath, []) information['filepath'] = outpath information['format'] = self._preferedformat information['ext'] = self._preferedformat - return False,information + return False, information class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): @@ -427,11 +460,11 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): return cls._lang_map.get(code[:2]) def run(self, information): - if information['ext'] != u'mp4': - self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files') + if information['ext'] != 'mp4': + self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4 files') return True, information if not information.get('subtitles'): - self._downloader.to_screen(u'[ffmpeg] There aren\'t any subtitles to embed') + self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to embed') return True, information sub_langs = [key for key in information['subtitles']] @@ -440,14 +473,14 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy'] for (i, lang) in enumerate(sub_langs): - opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text']) + opts.extend(['-map', '%d:0' % (i + 1), '-c:s:%d' % i, 'mov_text']) lang_code = self._conver_lang_code(lang) if lang_code is not None: opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code]) opts.extend(['-f', 'mp4']) - temp_filename = filename + u'.temp' - self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename) + temp_filename = filename + '.temp' + self._downloader.to_screen('[ffmpeg] Embedding subtitles in \'%s\'' % filename) self.run_ffmpeg_multiple_files(input_files, temp_filename, opts) os.remove(encodeFilename(filename)) os.rename(encodeFilename(temp_filename), encodeFilename(filename)) @@ -468,13 +501,13 @@ class FFmpegMetadataPP(FFmpegPostProcessor): metadata['artist'] = info['uploader_id'] if not metadata: - self._downloader.to_screen(u'[ffmpeg] There isn\'t any metadata to add') + self._downloader.to_screen('[ffmpeg] There isn\'t any metadata to add') return True, info filename = info['filepath'] temp_filename = prepend_extension(filename, 'temp') - if info['ext'] == u'm4a': + if info['ext'] == 'm4a': options = ['-vn', '-acodec', 'copy'] else: options = ['-c', 'copy'] @@ -482,7 +515,7 @@ class FFmpegMetadataPP(FFmpegPostProcessor): for (name, value) in metadata.items(): options.extend(['-metadata', '%s=%s' % (name, value)]) - self._downloader.to_screen(u'[ffmpeg] Adding metadata to \'%s\'' % filename) + self._downloader.to_screen('[ffmpeg] Adding metadata to \'%s\'' % filename) self.run_ffmpeg(filename, temp_filename, options) os.remove(encodeFilename(filename)) os.rename(encodeFilename(temp_filename), encodeFilename(filename)) @@ -492,8 +525,8 @@ class FFmpegMetadataPP(FFmpegPostProcessor): class FFmpegMergerPP(FFmpegPostProcessor): def run(self, info): filename = info['filepath'] - args = ['-c', 'copy'] - self._downloader.to_screen(u'[ffmpeg] Merging formats into "%s"' % filename) + args = ['-c', 'copy', '-map', '0:v:0', '-map', '1:a:0', '-shortest'] + self._downloader.to_screen('[ffmpeg] Merging formats into "%s"' % filename) self.run_ffmpeg_multiple_files(info['__files_to_merge'], filename, args) return True, info @@ -504,7 +537,7 @@ class FFmpegAudioFixPP(FFmpegPostProcessor): temp_filename = prepend_extension(filename, 'temp') options = ['-vn', '-acodec', 'copy'] - self._downloader.to_screen(u'[ffmpeg] Fixing audio file "%s"' % filename) + self._downloader.to_screen('[ffmpeg] Fixing audio file "%s"' % filename) self.run_ffmpeg(filename, temp_filename, options) os.remove(encodeFilename(filename)) diff --git a/youtube_dl/postprocessor/xattrpp.py b/youtube_dl/postprocessor/xattrpp.py index f6940940b..f6c63fe97 100644 --- a/youtube_dl/postprocessor/xattrpp.py +++ b/youtube_dl/postprocessor/xattrpp.py @@ -1,12 +1,16 @@ +from __future__ import unicode_literals + import os import subprocess import sys from .common import PostProcessor +from ..compat import ( + subprocess_check_output +) from ..utils import ( check_executable, hyphenate_date, - subprocess_check_output ) @@ -106,4 +110,3 @@ class XAttrMetadataPP(PostProcessor): except (subprocess.CalledProcessError, OSError): self._downloader.report_error("This filesystem doesn't support extended attributes. (You may have to enable them in your /etc/fstab)") return False, info - diff --git a/youtube_dl/swfinterp.py b/youtube_dl/swfinterp.py index b63c65b20..2bd264b30 100644 --- a/youtube_dl/swfinterp.py +++ b/youtube_dl/swfinterp.py @@ -62,15 +62,17 @@ class _ScopeDict(dict): class _AVMClass(object): - def __init__(self, name_idx, name): + def __init__(self, name_idx, name, static_properties=None): self.name_idx = name_idx self.name = name self.method_names = {} self.method_idxs = {} self.methods = {} self.method_pyfunctions = {} + self.static_properties = static_properties if static_properties else {} self.variables = _ScopeDict(self) + self.constants = {} def make_object(self): return _AVMClass_Object(self) @@ -148,8 +150,38 @@ def _read_byte(reader): return res +StringClass = _AVMClass('(no name idx)', 'String') +ByteArrayClass = _AVMClass('(no name idx)', 'ByteArray') +TimerClass = _AVMClass('(no name idx)', 'Timer') +TimerEventClass = _AVMClass('(no name idx)', 'TimerEvent', {'TIMER': 'timer'}) +_builtin_classes = { + StringClass.name: StringClass, + ByteArrayClass.name: ByteArrayClass, + TimerClass.name: TimerClass, + TimerEventClass.name: TimerEventClass, +} + + +class _Undefined(object): + def __bool__(self): + return False + __nonzero__ = __bool__ + + def __hash__(self): + return 0 + + def __str__(self): + return 'undefined' + __repr__ = __str__ + +undefined = _Undefined() + + class SWFInterpreter(object): def __init__(self, file_contents): + self._patched_functions = { + (TimerClass, 'addEventListener'): lambda params: undefined, + } code_tag = next(tag for tag_code, tag in _extract_tags(file_contents) if tag_code == 82) @@ -170,11 +202,13 @@ class SWFInterpreter(object): # Constant pool int_count = u30() + self.constant_ints = [0] for _c in range(1, int_count): - s32() + self.constant_ints.append(s32()) + self.constant_uints = [0] uint_count = u30() for _c in range(1, uint_count): - u32() + self.constant_uints.append(u32()) double_count = u30() read_bytes(max(0, (double_count - 1)) * 8) string_count = u30() @@ -212,6 +246,10 @@ class SWFInterpreter(object): u30() # namespace_idx name_idx = u30() self.multinames.append(self.constant_strings[name_idx]) + elif kind == 0x09: + name_idx = u30() + u30() + self.multinames.append(self.constant_strings[name_idx]) else: self.multinames.append(_Multiname(kind)) for _c2 in range(MULTINAME_SIZES[kind]): @@ -258,13 +296,28 @@ class SWFInterpreter(object): kind = kind_full & 0x0f attrs = kind_full >> 4 methods = {} - if kind in [0x00, 0x06]: # Slot or Const + constants = None + if kind == 0x00: # Slot u30() # Slot id u30() # type_name_idx vindex = u30() if vindex != 0: read_byte() # vkind - elif kind in [0x01, 0x02, 0x03]: # Method / Getter / Setter + elif kind == 0x06: # Const + u30() # Slot id + u30() # type_name_idx + vindex = u30() + vkind = 'any' + if vindex != 0: + vkind = read_byte() + if vkind == 0x03: # Constant_Int + value = self.constant_ints[vindex] + elif vkind == 0x04: # Constant_UInt + value = self.constant_uints[vindex] + else: + return {}, None # Ignore silently for now + constants = {self.multinames[trait_name_idx]: value} + elif kind in (0x01, 0x02, 0x03): # Method / Getter / Setter u30() # disp_id method_idx = u30() methods[self.multinames[trait_name_idx]] = method_idx @@ -283,7 +336,7 @@ class SWFInterpreter(object): for _c3 in range(metadata_count): u30() # metadata index - return methods + return methods, constants # Classes class_count = u30() @@ -305,18 +358,22 @@ class SWFInterpreter(object): u30() # iinit trait_count = u30() for _c2 in range(trait_count): - trait_methods = parse_traits_info() + trait_methods, trait_constants = parse_traits_info() avm_class.register_methods(trait_methods) + if trait_constants: + avm_class.constants.update(trait_constants) assert len(classes) == class_count self._classes_by_name = dict((c.name, c) for c in classes) for avm_class in classes: - u30() # cinit + avm_class.cinit_idx = u30() trait_count = u30() for _c2 in range(trait_count): - trait_methods = parse_traits_info() + trait_methods, trait_constants = parse_traits_info() avm_class.register_methods(trait_methods) + if trait_constants: + avm_class.constants.update(trait_constants) # Scripts script_count = u30() @@ -329,6 +386,7 @@ class SWFInterpreter(object): # Method bodies method_body_count = u30() Method = collections.namedtuple('Method', ['code', 'local_count']) + self._all_methods = [] for _c in range(method_body_count): method_idx = u30() u30() # max_stack @@ -337,9 +395,10 @@ class SWFInterpreter(object): u30() # max_scope_depth code_length = u30() code = read_bytes(code_length) + m = Method(code, local_count) + self._all_methods.append(m) for avm_class in classes: if method_idx in avm_class.method_idxs: - m = Method(code, local_count) avm_class.methods[avm_class.method_idxs[method_idx]] = m exception_count = u30() for _c2 in range(exception_count): @@ -354,13 +413,27 @@ class SWFInterpreter(object): assert p + code_reader.tell() == len(code_tag) - def extract_class(self, class_name): + def patch_function(self, avm_class, func_name, f): + self._patched_functions[(avm_class, func_name)] = f + + def extract_class(self, class_name, call_cinit=True): try: - return self._classes_by_name[class_name] + res = self._classes_by_name[class_name] except KeyError: raise ExtractorError('Class %r not found' % class_name) + if call_cinit and hasattr(res, 'cinit_idx'): + res.register_methods({'$cinit': res.cinit_idx}) + res.methods['$cinit'] = self._all_methods[res.cinit_idx] + cinit = self.extract_function(res, '$cinit') + cinit([]) + + return res + def extract_function(self, avm_class, func_name): + p = self._patched_functions.get((avm_class, func_name)) + if p: + return p if func_name in avm_class.method_pyfunctions: return avm_class.method_pyfunctions[func_name] if func_name in self._classes_by_name: @@ -379,10 +452,15 @@ class SWFInterpreter(object): registers = [avm_class.variables] + list(args) + [None] * m.local_count stack = [] scopes = collections.deque([ - self._classes_by_name, avm_class.variables]) + self._classes_by_name, avm_class.constants, avm_class.variables]) while True: opcode = _read_byte(coder) - if opcode == 17: # iftrue + if opcode == 9: # label + pass # Spec says: "Do nothing." + elif opcode == 16: # jump + offset = s24() + coder.seek(coder.tell() + offset) + elif opcode == 17: # iftrue offset = s24() value = stack.pop() if value: @@ -392,9 +470,40 @@ class SWFInterpreter(object): value = stack.pop() if not value: coder.seek(coder.tell() + offset) + elif opcode == 19: # ifeq + offset = s24() + value2 = stack.pop() + value1 = stack.pop() + if value2 == value1: + coder.seek(coder.tell() + offset) + elif opcode == 20: # ifne + offset = s24() + value2 = stack.pop() + value1 = stack.pop() + if value2 != value1: + coder.seek(coder.tell() + offset) + elif opcode == 21: # iflt + offset = s24() + value2 = stack.pop() + value1 = stack.pop() + if value1 < value2: + coder.seek(coder.tell() + offset) + elif opcode == 32: # pushnull + stack.append(None) + elif opcode == 33: # pushundefined + stack.append(undefined) elif opcode == 36: # pushbyte v = _read_byte(coder) stack.append(v) + elif opcode == 37: # pushshort + v = u30() + stack.append(v) + elif opcode == 38: # pushtrue + stack.append(True) + elif opcode == 39: # pushfalse + stack.append(False) + elif opcode == 40: # pushnan + stack.append(float('NaN')) elif opcode == 42: # dup value = stack[-1] stack.append(value) @@ -419,11 +528,31 @@ class SWFInterpreter(object): [stack.pop() for _ in range(arg_count)])) obj = stack.pop() - if isinstance(obj, _AVMClass_Object): + if obj == StringClass: + if mname == 'String': + assert len(args) == 1 + assert isinstance(args[0], ( + int, compat_str, _Undefined)) + if args[0] == undefined: + res = 'undefined' + else: + res = compat_str(args[0]) + stack.append(res) + continue + else: + raise NotImplementedError( + 'Function String.%s is not yet implemented' + % mname) + elif isinstance(obj, _AVMClass_Object): func = self.extract_function(obj.avm_class, mname) res = func(args) stack.append(res) continue + elif isinstance(obj, _AVMClass): + func = self.extract_function(obj, mname) + res = func(args) + stack.append(res) + continue elif isinstance(obj, _ScopeDict): if mname in obj.avm_class.method_names: func = self.extract_function(obj.avm_class, mname) @@ -442,6 +571,13 @@ class SWFInterpreter(object): res = obj.split(args[0]) stack.append(res) continue + elif mname == 'charCodeAt': + assert len(args) <= 1 + idx = 0 if len(args) == 0 else args[0] + assert isinstance(idx, int) + res = ord(obj[idx]) + stack.append(res) + continue elif isinstance(obj, list): if mname == 'slice': assert len(args) == 1 @@ -458,9 +594,18 @@ class SWFInterpreter(object): raise NotImplementedError( 'Unsupported property %r on %r' % (mname, obj)) + elif opcode == 71: # returnvoid + res = undefined + return res elif opcode == 72: # returnvalue res = stack.pop() return res + elif opcode == 73: # constructsuper + # Not yet implemented, just hope it works without it + arg_count = u30() + args = list(reversed( + [stack.pop() for _ in range(arg_count)])) + obj = stack.pop() elif opcode == 74: # constructproperty index = u30() arg_count = u30() @@ -481,6 +626,17 @@ class SWFInterpreter(object): args = list(reversed( [stack.pop() for _ in range(arg_count)])) obj = stack.pop() + if isinstance(obj, _AVMClass_Object): + func = self.extract_function(obj.avm_class, mname) + res = func(args) + assert res is undefined + continue + if isinstance(obj, _ScopeDict): + assert mname in obj.avm_class.method_names + func = self.extract_function(obj.avm_class, mname) + res = func(args) + assert res is undefined + continue if mname == 'reverse': assert isinstance(obj, list) obj.reverse() @@ -504,7 +660,10 @@ class SWFInterpreter(object): break else: res = scopes[0] - stack.append(res[mname]) + if mname not in res and mname in _builtin_classes: + stack.append(_builtin_classes[mname]) + else: + stack.append(res[mname]) elif opcode == 94: # findproperty index = u30() mname = self.multinames[index] @@ -524,9 +683,15 @@ class SWFInterpreter(object): break else: scope = avm_class.variables - # I cannot find where static variables are initialized - # so let's just return None - res = scope.get(mname) + + if mname in scope: + res = scope[mname] + elif mname in _builtin_classes: + res = _builtin_classes[mname] + else: + # Assume unitialized + # TODO warn here + res = undefined stack.append(res) elif opcode == 97: # setproperty index = u30() @@ -548,22 +713,57 @@ class SWFInterpreter(object): pname = self.multinames[index] if pname == 'length': obj = stack.pop() - assert isinstance(obj, list) + assert isinstance(obj, (compat_str, list)) stack.append(len(obj)) + elif isinstance(pname, compat_str): # Member access + obj = stack.pop() + if isinstance(obj, _AVMClass): + res = obj.static_properties[pname] + stack.append(res) + continue + + assert isinstance(obj, (dict, _ScopeDict)),\ + 'Accessing member %r on %r' % (pname, obj) + res = obj.get(pname, undefined) + stack.append(res) else: # Assume attribute access idx = stack.pop() assert isinstance(idx, int) obj = stack.pop() assert isinstance(obj, list) stack.append(obj[idx]) + elif opcode == 104: # initproperty + index = u30() + value = stack.pop() + idx = self.multinames[index] + if isinstance(idx, _Multiname): + idx = stack.pop() + obj = stack.pop() + obj[idx] = value elif opcode == 115: # convert_ value = stack.pop() intvalue = int(value) stack.append(intvalue) elif opcode == 128: # coerce u30() + elif opcode == 130: # coerce_a + value = stack.pop() + # um, yes, it's any value + stack.append(value) elif opcode == 133: # coerce_s assert isinstance(stack[-1], (type(None), compat_str)) + elif opcode == 147: # decrement + value = stack.pop() + assert isinstance(value, int) + stack.append(value - 1) + elif opcode == 149: # typeof + value = stack.pop() + return { + _Undefined: 'undefined', + compat_str: 'String', + int: 'Number', + float: 'Number', + }[type(value)] elif opcode == 160: # add value2 = stack.pop() value1 = stack.pop() @@ -574,16 +774,37 @@ class SWFInterpreter(object): value1 = stack.pop() res = value1 - value2 stack.append(res) + elif opcode == 162: # multiply + value2 = stack.pop() + value1 = stack.pop() + res = value1 * value2 + stack.append(res) elif opcode == 164: # modulo value2 = stack.pop() value1 = stack.pop() res = value1 % value2 stack.append(res) + elif opcode == 168: # bitand + value2 = stack.pop() + value1 = stack.pop() + assert isinstance(value1, int) + assert isinstance(value2, int) + res = value1 & value2 + stack.append(res) + elif opcode == 171: # equals + value2 = stack.pop() + value1 = stack.pop() + result = value1 == value2 + stack.append(result) elif opcode == 175: # greaterequals value2 = stack.pop() value1 = stack.pop() result = value1 >= value2 stack.append(result) + elif opcode == 192: # increment_i + value = stack.pop() + assert isinstance(value, int) + stack.append(value + 1) elif opcode == 208: # getlocal_0 stack.append(registers[0]) elif opcode == 209: # getlocal_1 @@ -606,4 +827,3 @@ class SWFInterpreter(object): avm_class.method_pyfunctions[func_name] = resfunc return resfunc - diff --git a/youtube_dl/update.py b/youtube_dl/update.py index 273083761..4c07a558e 100644 --- a/youtube_dl/update.py +++ b/youtube_dl/update.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import io import json import traceback @@ -7,20 +9,18 @@ import subprocess import sys from zipimport import zipimporter -from .utils import ( +from .compat import ( compat_str, compat_urllib_request, ) from .version import __version__ + 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(''))) + + assert isinstance(message, bytes) block_size = 0 n = key[0] while n: @@ -31,14 +31,18 @@ def rsa_verify(message, signature, key): 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 = (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 + if b'\x00' not 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 + if signature != sha256(message).digest(): + return False return True @@ -51,18 +55,19 @@ def update_self(to_screen, verbose): UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537) if not isinstance(globals().get('__loader__'), zipimporter) and not hasattr(sys, "frozen"): - to_screen(u'It looks like you installed youtube-dl with a package manager, pip, setup.py or a tarball. Please use that to update.') + to_screen('It looks like you installed youtube-dl with a package manager, pip, setup.py or a tarball. Please use that to update.') return # Check if there is a new version try: newversion = compat_urllib_request.urlopen(VERSION_URL).read().decode('utf-8').strip() except: - if verbose: to_screen(compat_str(traceback.format_exc())) - to_screen(u'ERROR: can\'t find the current version. Please try again later.') + if verbose: + to_screen(compat_str(traceback.format_exc())) + to_screen('ERROR: can\'t find the current version. Please try again later.') return if newversion == __version__: - to_screen(u'youtube-dl is up-to-date (' + __version__ + ')') + to_screen('youtube-dl is up-to-date (' + __version__ + ')') return # Download and check versions info @@ -70,16 +75,17 @@ def update_self(to_screen, verbose): versions_info = compat_urllib_request.urlopen(JSON_URL).read().decode('utf-8') versions_info = json.loads(versions_info) except: - if verbose: to_screen(compat_str(traceback.format_exc())) - to_screen(u'ERROR: can\'t obtain versions info. Please try again later.') + if verbose: + to_screen(compat_str(traceback.format_exc())) + to_screen('ERROR: can\'t obtain versions info. Please try again later.') return if not 'signature' in versions_info: - to_screen(u'ERROR: the versions file is not signed or corrupted. Aborting.') + to_screen('ERROR: the versions file is not signed or corrupted. Aborting.') return signature = versions_info['signature'] del versions_info['signature'] if not rsa_verify(json.dumps(versions_info, sort_keys=True).encode('utf-8'), signature, UPDATES_RSA_KEY): - to_screen(u'ERROR: the versions file signature is invalid. Aborting.') + to_screen('ERROR: the versions file signature is invalid. Aborting.') return version_id = versions_info['latest'] @@ -87,10 +93,10 @@ def update_self(to_screen, verbose): def version_tuple(version_str): return tuple(map(int, version_str.split('.'))) if version_tuple(__version__) >= version_tuple(version_id): - to_screen(u'youtube-dl is up to date (%s)' % __version__) + to_screen('youtube-dl is up to date (%s)' % __version__) return - to_screen(u'Updating to version ' + version_id + ' ...') + to_screen('Updating to version ' + version_id + ' ...') version = versions_info['versions'][version_id] print_notes(to_screen, versions_info['versions']) @@ -98,11 +104,11 @@ def update_self(to_screen, verbose): filename = sys.argv[0] # Py2EXE: Filename could be different if hasattr(sys, "frozen") and not os.path.isfile(filename): - if os.path.isfile(filename + u'.exe'): - filename += u'.exe' + if os.path.isfile(filename + '.exe'): + filename += '.exe' if not os.access(filename, os.W_OK): - to_screen(u'ERROR: no write permissions on %s' % filename) + to_screen('ERROR: no write permissions on %s' % filename) return # Py2EXE @@ -110,7 +116,7 @@ def update_self(to_screen, verbose): exe = os.path.abspath(filename) directory = os.path.dirname(exe) if not os.access(directory, os.W_OK): - to_screen(u'ERROR: no write permissions on %s' % directory) + to_screen('ERROR: no write permissions on %s' % directory) return try: @@ -118,40 +124,43 @@ def update_self(to_screen, verbose): newcontent = urlh.read() urlh.close() except (IOError, OSError): - if verbose: to_screen(compat_str(traceback.format_exc())) - to_screen(u'ERROR: unable to download latest version') + if verbose: + to_screen(compat_str(traceback.format_exc())) + to_screen('ERROR: unable to download latest version') return newcontent_hash = hashlib.sha256(newcontent).hexdigest() if newcontent_hash != version['exe'][1]: - to_screen(u'ERROR: the downloaded file hash does not match. Aborting.') + to_screen('ERROR: the downloaded file hash does not match. Aborting.') return try: with open(exe + '.new', 'wb') as outf: outf.write(newcontent) except (IOError, OSError): - if verbose: to_screen(compat_str(traceback.format_exc())) - to_screen(u'ERROR: unable to write the new version') + if verbose: + to_screen(compat_str(traceback.format_exc())) + to_screen('ERROR: unable to write the new version') return try: bat = os.path.join(directory, 'youtube-dl-updater.bat') with io.open(bat, 'w') as batfile: - batfile.write(u""" + batfile.write(''' @echo off echo Waiting for file handle to be closed ... ping 127.0.0.1 -n 5 -w 1000 > NUL move /Y "%s.new" "%s" > NUL echo Updated youtube-dl to version %s. start /b "" cmd /c del "%%~f0"&exit /b" - \n""" % (exe, exe, version_id)) + \n''' % (exe, exe, version_id)) subprocess.Popen([bat]) # Continues to run in the background return # Do not show premature success messages except (IOError, OSError): - if verbose: to_screen(compat_str(traceback.format_exc())) - to_screen(u'ERROR: unable to overwrite current version') + if verbose: + to_screen(compat_str(traceback.format_exc())) + to_screen('ERROR: unable to overwrite current version') return # Zip unix package @@ -161,35 +170,39 @@ start /b "" cmd /c del "%%~f0"&exit /b" newcontent = urlh.read() urlh.close() except (IOError, OSError): - if verbose: to_screen(compat_str(traceback.format_exc())) - to_screen(u'ERROR: unable to download latest version') + if verbose: + to_screen(compat_str(traceback.format_exc())) + to_screen('ERROR: unable to download latest version') return newcontent_hash = hashlib.sha256(newcontent).hexdigest() if newcontent_hash != version['bin'][1]: - to_screen(u'ERROR: the downloaded file hash does not match. Aborting.') + to_screen('ERROR: the downloaded file hash does not match. Aborting.') return try: with open(filename, 'wb') as outf: outf.write(newcontent) except (IOError, OSError): - if verbose: to_screen(compat_str(traceback.format_exc())) - to_screen(u'ERROR: unable to overwrite current version') + if verbose: + to_screen(compat_str(traceback.format_exc())) + to_screen('ERROR: unable to overwrite current version') return - to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.') + to_screen('Updated youtube-dl. Restart youtube-dl to use the new version.') + def get_notes(versions, fromVersion): notes = [] - for v,vdata in sorted(versions.items()): + for v, vdata in sorted(versions.items()): if v > fromVersion: notes.extend(vdata.get('notes', [])) return notes + def print_notes(to_screen, versions, fromVersion=__version__): notes = get_notes(versions, fromVersion) if notes: - to_screen(u'PLEASE NOTE:') + to_screen('PLEASE NOTE:') for note in notes: to_screen(note) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 34bc432ab..bbad10a4c 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1,6 +1,8 @@ #!/usr/bin/env python # -*- coding: utf-8 -*- +from __future__ import unicode_literals + import calendar import codecs import contextlib @@ -8,7 +10,6 @@ import ctypes import datetime import email.utils import errno -import getpass import gzip import itertools import io @@ -29,179 +30,20 @@ import traceback import xml.etree.ElementTree import zlib -try: - import urllib.request as compat_urllib_request -except ImportError: # Python 2 - import urllib2 as compat_urllib_request +from .compat import ( + compat_chr, + compat_getenv, + compat_html_entities, + compat_parse_qs, + compat_str, + compat_urllib_error, + compat_urllib_parse, + compat_urllib_parse_urlparse, + compat_urllib_request, + compat_urlparse, + shlex_quote, +) -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: - 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: - 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, unicode - 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: - compat_str = unicode # Python 2 -except NameError: - compat_str = 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 shlex import quote as shlex_quote -except ImportError: # Python < 3.3 - def shlex_quote(s): - return "'" + s.replace("'", "'\"'\"'") + "'" - - -def compat_ord(c): - if type(c) is int: return c - else: return ord(c) # This is not clearly defined otherwise compiled_regex_type = type(re.compile('')) @@ -214,6 +56,7 @@ std_headers = { 'Accept-Language': 'en-us,en;q=0.5', } + def preferredencoding(): """Get preferred encoding. @@ -222,28 +65,33 @@ def preferredencoding(): """ try: pref = locale.getpreferredencoding() - u'TEST'.encode(pref) + 'TEST'.encode(pref) except: pref = 'UTF-8' return pref -if sys.version_info < (3,0): - def compat_print(s): - print(s.encode(preferredencoding(), 'xmlcharrefreplace')) -else: - def compat_print(s): - assert type(s) == type(u'') - print(s) - def write_json_file(obj, fn): - """ Encode obj as JSON and write it to fn, atomically """ + """ Encode obj as JSON and write it to fn, atomically if possible """ + + fn = encodeFilename(fn) + if sys.version_info < (3, 0) and sys.platform != 'win32': + encoding = get_filesystem_encoding() + # os.path.basename returns a bytes object, but NamedTemporaryFile + # will fail if the filename contains non ascii characters unless we + # use a unicode object + path_basename = lambda f: os.path.basename(fn).decode(encoding) + # the same for os.path.dirname + path_dirname = lambda f: os.path.dirname(fn).decode(encoding) + else: + path_basename = os.path.basename + path_dirname = os.path.dirname args = { 'suffix': '.tmp', - 'prefix': os.path.basename(fn) + '.', - 'dir': os.path.dirname(fn), + 'prefix': path_basename(fn) + '.', + 'dir': path_dirname(fn), 'delete': False, } @@ -262,6 +110,13 @@ def write_json_file(obj, fn): try: with tf: json.dump(obj, tf) + if sys.platform == 'win32': + # Need to remove existing file on Windows, else os.rename raises + # WindowsError or FileExistsError. + try: + os.unlink(fn) + except OSError: + pass os.rename(tf.name, fn) except: try: @@ -276,7 +131,7 @@ if sys.version_info >= (2, 7): """ Find the xpath xpath[@key=val] """ assert re.match(r'^[a-zA-Z-]+$', key) assert re.match(r'^[a-zA-Z0-9@\s:._-]*$', val) - expr = xpath + u"[@%s='%s']" % (key, val) + expr = xpath + "[@%s='%s']" % (key, val) return node.find(expr) else: def find_xpath_attr(node, xpath, key, val): @@ -292,6 +147,8 @@ else: # On python2.6 the xml.etree.ElementTree.Element methods don't support # the namespace parameter + + def xpath_with_ns(path, ns_map): components = [c.split(':') for c in path.split('/')] replaced = [] @@ -318,127 +175,32 @@ def xpath_text(node, xpath, name=None, fatal=False): return n.text -compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix -class BaseHTMLParser(compat_html_parser.HTMLParser): - def __init(self): - compat_html_parser.HTMLParser.__init__(self) - self.html = None - - def loads(self, html): - self.html = html - self.feed(html) - self.close() - -class AttrParser(BaseHTMLParser): - """Modified HTMLParser that isolates a tag with the specified attribute""" - def __init__(self, attribute, value): - self.attribute = attribute - self.value = value - self.result = None - self.started = False - self.depth = {} - self.watch_startpos = False - self.error_count = 0 - BaseHTMLParser.__init__(self) - - def error(self, message): - if self.error_count > 10 or self.started: - raise compat_html_parser.HTMLParseError(message, self.getpos()) - self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line - self.error_count += 1 - self.goahead(1) - - def handle_starttag(self, tag, attrs): - attrs = dict(attrs) - if self.started: - self.find_startpos(None) - if self.attribute in attrs and attrs[self.attribute] == self.value: - self.result = [tag] - self.started = True - self.watch_startpos = True - if self.started: - if not tag in self.depth: self.depth[tag] = 0 - self.depth[tag] += 1 - - def handle_endtag(self, tag): - if self.started: - if tag in self.depth: self.depth[tag] -= 1 - if self.depth[self.result[0]] == 0: - self.started = False - self.result.append(self.getpos()) - - def find_startpos(self, x): - """Needed to put the start position of the result (self.result[1]) - after the opening tag with the requested id""" - if self.watch_startpos: - self.watch_startpos = False - self.result.append(self.getpos()) - handle_entityref = handle_charref = handle_data = handle_comment = \ - handle_decl = handle_pi = unknown_decl = find_startpos - - def get_result(self): - if self.result is None: - return None - if len(self.result) != 3: - return None - lines = self.html.split('\n') - lines = lines[self.result[1][0]-1:self.result[2][0]] - lines[0] = lines[0][self.result[1][1]:] - if len(lines) == 1: - lines[-1] = lines[-1][:self.result[2][1]-self.result[1][1]] - lines[-1] = lines[-1][:self.result[2][1]] - return '\n'.join(lines).strip() -# Hack for https://github.com/rg3/youtube-dl/issues/662 -if sys.version_info < (2, 7, 3): - AttrParser.parse_endtag = (lambda self, i: - i + len("</scr'+'ipt>") - if self.rawdata[i:].startswith("</scr'+'ipt>") - else compat_html_parser.HTMLParser.parse_endtag(self, i)) - def get_element_by_id(id, html): """Return the content of the tag with the specified ID in the passed HTML document""" return get_element_by_attribute("id", id, html) + def get_element_by_attribute(attribute, value, html): """Return the content of the tag with the specified attribute in the passed HTML document""" - parser = AttrParser(attribute, value) - try: - parser.loads(html) - except compat_html_parser.HTMLParseError: - pass - return parser.get_result() -class MetaParser(BaseHTMLParser): - """ - Modified HTMLParser that isolates a meta tag with the specified name - attribute. - """ - def __init__(self, name): - BaseHTMLParser.__init__(self) - self.name = name - self.content = None - self.result = None + m = re.search(r'''(?xs) + <([a-zA-Z0-9:._-]+) + (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]+|="[^"]+"|='[^']+'))*? + \s+%s=['"]?%s['"]? + (?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]+|="[^"]+"|='[^']+'))*? + \s*> + (?P<content>.*?) + </\1> + ''' % (re.escape(attribute), re.escape(value)), html) - def handle_starttag(self, tag, attrs): - if tag != 'meta': - return - attrs = dict(attrs) - if attrs.get('name') == self.name: - self.result = attrs.get('content') + if not m: + return None + res = m.group('content') - def get_result(self): - return self.result + if res.startswith('"') or res.startswith("'"): + res = res[1:-1] -def get_meta_content(name, html): - """ - Return the content attribute from the meta tag with the given name attribute. - """ - parser = MetaParser(name) - try: - parser.loads(html) - except compat_html_parser.HTMLParseError: - pass - return parser.get_result() + return unescapeHTML(res) def clean_html(html): @@ -465,7 +227,7 @@ def sanitize_open(filename, open_mode): It returns the tuple (stream, definitive_file_name). """ try: - if filename == u'-': + if filename == '-': if sys.platform == 'win32': import msvcrt msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY) @@ -478,9 +240,9 @@ def sanitize_open(filename, open_mode): # In case of error, try to remove win32 forbidden chars alt_filename = os.path.join( - re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', path_part) - for path_part in os.path.split(filename) - ) + re.sub('[/<>:"\\|\\\\?\\*]', '#', path_part) + for path_part in os.path.split(filename) + ) if alt_filename == filename: raise else: @@ -497,6 +259,7 @@ def timeconvert(timestr): timestamp = email.utils.mktime_tz(timetuple) return timestamp + def sanitize_filename(s, restricted=False, is_id=False): """Sanitizes a string so it could be used as part of a filename. If restricted is set, use a stricter subset of allowed characters. @@ -517,7 +280,7 @@ def sanitize_filename(s, restricted=False, is_id=False): return '_' return char - result = u''.join(map(replace_insane, s)) + result = ''.join(map(replace_insane, s)) if not is_id: while '__' in result: result = result.replace('__', '_') @@ -529,6 +292,7 @@ def sanitize_filename(s, restricted=False, is_id=False): result = '_' return result + def orderedSet(iterable): """ Remove all duplicates from the input iterable """ res = [] @@ -547,15 +311,15 @@ def _htmlentity_transform(entity): mobj = re.match(r'#(x?[0-9]+)', entity) if mobj is not None: numstr = mobj.group(1) - if numstr.startswith(u'x'): + if numstr.startswith('x'): base = 16 - numstr = u'0%s' % numstr + numstr = '0%s' % numstr else: base = 10 return compat_chr(int(numstr, base)) # Unknown entity in name, return its literal representation - return (u'&%s;' % entity) + return ('&%s;' % entity) def unescapeHTML(s): @@ -579,7 +343,7 @@ def encodeFilename(s, for_subprocess=False): return s if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: - # Pass u'' directly to use Unicode APIs on Windows 2000 and up + # Pass '' directly to use Unicode APIs on Windows 2000 and up # (Detecting Windows NT 4 is tricky because 'major >= 4' would # match Windows 9x series as well. Besides, NT 4 is obsolete.) if not for_subprocess: @@ -613,6 +377,7 @@ def decodeOption(optval): assert isinstance(optval, compat_str) return optval + def formatSeconds(secs): if secs > 3600: return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60) @@ -662,8 +427,10 @@ def make_HTTPS_handler(opts_no_check_certificate, **kwargs): pass # Python < 3.4 return compat_urllib_request.HTTPSHandler(context=context, **kwargs) + class ExtractorError(Exception): """Error during info extraction.""" + def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None): """ tb, if given, is the original traceback (so that it can be printed out). If expected is set, this is a normal error message and most likely not a bug in youtube-dl. @@ -673,8 +440,16 @@ class ExtractorError(Exception): expected = True if video_id is not None: msg = video_id + ': ' + msg + if cause: + msg += ' (caused by %r)' % cause if not expected: - msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output. Make sure you are using the latest version; type youtube-dl -U to update.' + if ytdl_is_updateable(): + update_cmd = 'type youtube-dl -U to update' + else: + update_cmd = 'see https://yt-dl.org/update on how to update' + msg += '; please report this issue on https://yt-dl.org/bug .' + msg += ' Make sure you are using the latest version; %s.' % update_cmd + msg += ' Be sure to call youtube-dl with the --verbose flag and include its complete output.' super(ExtractorError, self).__init__(msg) self.traceback = tb @@ -685,7 +460,7 @@ class ExtractorError(Exception): def format_traceback(self): if self.traceback is None: return None - return u''.join(traceback.format_tb(self.traceback)) + return ''.join(traceback.format_tb(self.traceback)) class RegexNotFoundError(ExtractorError): @@ -700,6 +475,7 @@ class DownloadError(Exception): configured to continue on errors. They will contain the appropriate error message. """ + def __init__(self, msg, exc_info=None): """ exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """ super(DownloadError, self).__init__(msg) @@ -721,9 +497,11 @@ class PostProcessingError(Exception): This exception may be raised by PostProcessor's .run() method to indicate an error in the postprocessing task. """ + def __init__(self, msg): self.msg = msg + class MaxDownloadsReached(Exception): """ --max-downloads limit has been reached. """ pass @@ -753,6 +531,7 @@ class ContentTooShortError(Exception): self.downloaded = downloaded self.expected = expected + class YoutubeDLHandler(compat_urllib_request.HTTPHandler): """Handler for HTTP requests and responses. @@ -799,6 +578,12 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler): del req.headers['User-agent'] req.headers['User-agent'] = req.headers['Youtubedl-user-agent'] del req.headers['Youtubedl-user-agent'] + + if sys.version_info < (2, 7) and '#' in req.get_full_url(): + # Python 2.6 is brain-dead when it comes to fragments + req._Request__original = req._Request__original.partition('#')[0] + req._Request__r_type = req._Request__r_type.partition('#')[0] + return req def http_response(self, req, resp): @@ -841,7 +626,7 @@ def parse_iso8601(date_str, delimiter='T'): return None m = re.search( - r'Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$', + r'(\.[0-9]+)?(?:Z$| ?(?P<sign>\+|-)(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2})$)', date_str) if not m: timezone = datetime.timedelta() @@ -854,7 +639,7 @@ def parse_iso8601(date_str, delimiter='T'): timezone = datetime.timedelta( hours=sign * int(m.group('hours')), minutes=sign * int(m.group('minutes'))) - date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter) + date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter) dt = datetime.datetime.strptime(date_str, date_format) - timezone return calendar.timegm(dt.timetuple()) @@ -866,7 +651,7 @@ def unified_strdate(date_str): return None upload_date = None - #Replace commas + # Replace commas date_str = date_str.replace(',', ' ') # %z (UTC offset) is only supported in python>=3.2 date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str) @@ -884,7 +669,9 @@ def unified_strdate(date_str): '%d/%m/%Y', '%d/%m/%y', '%Y/%m/%d %H:%M:%S', + '%d/%m/%Y %H:%M:%S', '%Y-%m-%d %H:%M:%S', + '%Y-%m-%d %H:%M:%S.%f', '%d.%m.%Y %H:%M', '%d.%m.%Y %H.%M', '%Y-%m-%dT%H:%M:%SZ', @@ -905,17 +692,20 @@ def unified_strdate(date_str): upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d') return upload_date -def determine_ext(url, default_ext=u'unknown_video'): + +def determine_ext(url, default_ext='unknown_video'): if url is None: return default_ext - guess = url.partition(u'?')[0].rpartition(u'.')[2] + guess = url.partition('?')[0].rpartition('.')[2] if re.match(r'^[A-Za-z0-9]+$', guess): return guess else: return default_ext + def subtitles_filename(filename, sub_lang, sub_format): - return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format + return filename.rsplit('.', 1)[0] + '.' + sub_lang + '.' + sub_format + def build_part_filename(final_filename, part_index): (name, ext) = os.path.splitext(final_filename) @@ -935,7 +725,7 @@ def date_from_str(date_str): if sign == '-': time = -time unit = match.group('unit') - #A bad aproximation? + # A bad aproximation? if unit == 'month': unit = 'day' time *= 30 @@ -946,7 +736,8 @@ def date_from_str(date_str): delta = datetime.timedelta(**{unit: time}) return today + delta return datetime.datetime.strptime(date_str, "%Y%m%d").date() - + + def hyphenate_date(date_str): """ Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format""" @@ -956,8 +747,10 @@ def hyphenate_date(date_str): else: return date_str + class DateRange(object): """Represents a time interval between two dates""" + def __init__(self, start=None, end=None): """start and end must be strings in the format accepted by date""" if start is not None: @@ -970,17 +763,20 @@ class DateRange(object): self.end = datetime.datetime.max.date() if self.start > self.end: raise ValueError('Date range: "%s" , the start date must be before the end date' % self) + @classmethod def day(cls, day): """Returns a range that only contains the given day""" - return cls(day,day) + return cls(day, day) + def __contains__(self, date): """Check if the date is in the range""" if not isinstance(date, datetime.date): date = date_from_str(date) return self.start <= date <= self.end + def __str__(self): - return '%s - %s' % ( self.start.isoformat(), self.end.isoformat()) + return '%s - %s' % (self.start.isoformat(), self.end.isoformat()) def platform_name(): @@ -1099,10 +895,7 @@ def bytes_to_intlist(bs): def intlist_to_bytes(xs): if not xs: return b'' - if isinstance(chr(0), bytes): # Python 2 - return ''.join([chr(x) for x in xs]) - else: - return bytes(xs) + return struct_pack('%dB' % len(xs), *xs) # Cross-platform file locking @@ -1201,17 +994,20 @@ class locked_file(object): return self.f.read(*args) +def get_filesystem_encoding(): + encoding = sys.getfilesystemencoding() + return encoding if encoding is not None else 'utf-8' + + def shell_quote(args): quoted_args = [] - encoding = sys.getfilesystemencoding() - if encoding is None: - encoding = 'utf-8' + encoding = get_filesystem_encoding() for a in args: if isinstance(a, bytes): # We may get a filename encoded with 'encodeFilename' a = a.decode(encoding) quoted_args.append(pipes.quote(a)) - return u' '.join(quoted_args) + return ' '.join(quoted_args) def takewhile_inclusive(pred, seq): @@ -1227,35 +1023,86 @@ def smuggle_url(url, data): """ Pass additional data in a URL for internal use. """ sdata = compat_urllib_parse.urlencode( - {u'__youtubedl_smuggle': json.dumps(data)}) - return url + u'#' + sdata + {'__youtubedl_smuggle': json.dumps(data)}) + return url + '#' + sdata def unsmuggle_url(smug_url, default=None): if not '#__youtubedl_smuggle' in smug_url: return smug_url, default - url, _, sdata = smug_url.rpartition(u'#') - jsond = compat_parse_qs(sdata)[u'__youtubedl_smuggle'][0] + url, _, sdata = smug_url.rpartition('#') + jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0] data = json.loads(jsond) return url, data def format_bytes(bytes): if bytes is None: - return u'N/A' + return 'N/A' if type(bytes) is str: bytes = float(bytes) if bytes == 0.0: exponent = 0 else: exponent = int(math.log(bytes, 1024.0)) - suffix = [u'B', u'KiB', u'MiB', u'GiB', u'TiB', u'PiB', u'EiB', u'ZiB', u'YiB'][exponent] + suffix = ['B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB', 'EiB', 'ZiB', 'YiB'][exponent] converted = float(bytes) / float(1024 ** exponent) - return u'%.2f%s' % (converted, suffix) + return '%.2f%s' % (converted, suffix) + + +def parse_filesize(s): + if s is None: + return None + + # The lower-case forms are of course incorrect and inofficial, + # but we support those too + _UNIT_TABLE = { + 'B': 1, + 'b': 1, + 'KiB': 1024, + 'KB': 1000, + 'kB': 1024, + 'Kb': 1000, + 'MiB': 1024 ** 2, + 'MB': 1000 ** 2, + 'mB': 1024 ** 2, + 'Mb': 1000 ** 2, + 'GiB': 1024 ** 3, + 'GB': 1000 ** 3, + 'gB': 1024 ** 3, + 'Gb': 1000 ** 3, + 'TiB': 1024 ** 4, + 'TB': 1000 ** 4, + 'tB': 1024 ** 4, + 'Tb': 1000 ** 4, + 'PiB': 1024 ** 5, + 'PB': 1000 ** 5, + 'pB': 1024 ** 5, + 'Pb': 1000 ** 5, + 'EiB': 1024 ** 6, + 'EB': 1000 ** 6, + 'eB': 1024 ** 6, + 'Eb': 1000 ** 6, + 'ZiB': 1024 ** 7, + 'ZB': 1000 ** 7, + 'zB': 1024 ** 7, + 'Zb': 1000 ** 7, + 'YiB': 1024 ** 8, + 'YB': 1000 ** 8, + 'yB': 1024 ** 8, + 'Yb': 1000 ** 8, + } + + units_re = '|'.join(re.escape(u) for u in _UNIT_TABLE) + m = re.match(r'(?P<num>[0-9]+(?:\.[0-9]*)?)\s*(?P<unit>%s)' % units_re, s) + if not m: + return None + + return int(float(m.group('num')) * _UNIT_TABLE[m.group('unit')]) def get_term_width(): - columns = os.environ.get('COLUMNS', None) + columns = compat_getenv('COLUMNS', None) if columns: return int(columns) @@ -1274,8 +1121,8 @@ def month_by_name(name): """ Return the number of a month by (locale-independently) English name """ ENGLISH_NAMES = [ - u'January', u'February', u'March', u'April', u'May', u'June', - u'July', u'August', u'September', u'October', u'November', u'December'] + 'January', 'February', 'March', 'April', 'May', 'June', + 'July', 'August', 'September', 'October', 'November', 'December'] try: return ENGLISH_NAMES.index(name) + 1 except ValueError: @@ -1286,7 +1133,7 @@ def fix_xml_ampersands(xml_str): """Replace all the '&' by '&' in XML""" return re.sub( r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)', - u'&', + '&', xml_str) @@ -1319,7 +1166,7 @@ def remove_end(s, end): def url_basename(url): path = compat_urlparse.urlparse(url).path - return path.strip(u'/').split(u'/')[-1] + return path.strip('/').split('/')[-1] class HEADRequest(compat_urllib_request.Request): @@ -1344,7 +1191,7 @@ def str_to_int(int_str): """ A more relaxed version of int_or_none """ if int_str is None: return None - int_str = re.sub(r'[,\.\+]', u'', int_str) + int_str = re.sub(r'[,\.\+]', '', int_str) return int(int_str) @@ -1359,7 +1206,12 @@ def parse_duration(s): s = s.strip() m = re.match( - r'(?i)(?:(?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)?(?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s*)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$', s) + r'''(?ix)T? + (?: + (?:(?P<hours>[0-9]+)\s*(?:[:h]|hours?)\s*)? + (?P<mins>[0-9]+)\s*(?:[:m]|mins?|minutes?)\s* + )? + (?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*(?:s|secs?|seconds?)?$''', s) if not m: return None res = int(m.group('secs')) @@ -1373,8 +1225,8 @@ def parse_duration(s): def prepend_extension(filename, ext): - name, real_ext = os.path.splitext(filename) - return u'{0}.{1}{2}'.format(name, ext, real_ext) + name, real_ext = os.path.splitext(filename) + return '{0}.{1}{2}'.format(name, ext, real_ext) def check_executable(exe, args=[]): @@ -1387,15 +1239,36 @@ def check_executable(exe, args=[]): return exe -class PagedList(object): - def __init__(self, pagefunc, pagesize): - self._pagefunc = pagefunc - self._pagesize = pagesize +def get_exe_version(exe, args=['--version'], + version_re=r'version\s+([0-9._-a-zA-Z]+)', + unrecognized='present'): + """ Returns the version of the specified executable, + or False if the executable is not present """ + try: + out, err = subprocess.Popen( + [exe] + args, + stdout=subprocess.PIPE, stderr=subprocess.STDOUT).communicate() + except OSError: + return False + firstline = out.partition(b'\n')[0].decode('ascii', 'ignore') + m = re.search(version_re, firstline) + if m: + return m.group(1) + else: + return unrecognized + +class PagedList(object): def __len__(self): # This is only useful for tests return len(self.getslice()) + +class OnDemandPagedList(PagedList): + def __init__(self, pagefunc, pagesize): + self._pagefunc = pagefunc + self._pagesize = pagesize + def getslice(self, start=0, end=None): res = [] for pagenum in itertools.count(start // self._pagesize): @@ -1434,6 +1307,35 @@ class PagedList(object): return res +class InAdvancePagedList(PagedList): + def __init__(self, pagefunc, pagecount, pagesize): + self._pagefunc = pagefunc + self._pagecount = pagecount + self._pagesize = pagesize + + def getslice(self, start=0, end=None): + res = [] + start_page = start // self._pagesize + end_page = ( + self._pagecount if end is None else (end // self._pagesize + 1)) + skip_elems = start - start_page * self._pagesize + only_more = None if end is None else end - start + for pagenum in range(start_page, end_page): + page = list(self._pagefunc(pagenum)) + if skip_elems: + page = page[skip_elems:] + skip_elems = None + if only_more is not None: + if len(page) < only_more: + only_more -= len(page) + else: + page = page[:only_more] + res.extend(page) + break + res.extend(page) + return res + + def uppercase_escape(s): unicode_escape = codecs.getdecoder('unicode_escape') return re.sub( @@ -1446,7 +1348,7 @@ def escape_rfc3986(s): """Escape non-ASCII characters as suggested by RFC 3986""" if sys.version_info < (3, 0) and isinstance(s, unicode): s = s.encode('utf-8') - return compat_urllib_parse.quote(s, "%/;:@&=+$,!~*'()?#[]") + return compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]") def escape_url(url): @@ -1460,7 +1362,7 @@ def escape_url(url): ).geturl() try: - struct.pack(u'!I', 0) + struct.pack('!I', 0) except TypeError: # In Python 2.6 (and some 2.7 versions), struct requires a bytes argument def struct_pack(spec, *args): @@ -1481,7 +1383,7 @@ def read_batch_urls(batch_fd): def fixup(url): if not isinstance(url, compat_str): url = url.decode('utf-8', 'replace') - BOM_UTF8 = u'\xef\xbb\xbf' + BOM_UTF8 = '\xef\xbb\xbf' if url.startswith(BOM_UTF8): url = url[len(BOM_UTF8):] url = url.strip() @@ -1520,15 +1422,6 @@ def parse_xml(s): return tree -if sys.version_info < (3, 0) and sys.platform == 'win32': - def compat_getpass(prompt, *args, **kwargs): - if isinstance(prompt, compat_str): - prompt = prompt.encode(preferredencoding()) - return getpass.getpass(prompt, *args, **kwargs) -else: - compat_getpass = getpass.getpass - - US_RATINGS = { 'G': 0, 'PG': 10, @@ -1538,33 +1431,38 @@ US_RATINGS = { } +def parse_age_limit(s): + if s is None: + return None + m = re.match(r'^(?P<age>\d{1,2})\+?$', s) + return int(m.group('age')) if m else US_RATINGS.get(s, None) + + def strip_jsonp(code): - return re.sub(r'(?s)^[a-zA-Z0-9_]+\s*\(\s*(.*)\);?\s*?\s*$', r'\1', code) + return re.sub( + r'(?s)^[a-zA-Z0-9_]+\s*\(\s*(.*)\);?\s*?(?://[^\n]*)*$', r'\1', code) def js_to_json(code): def fix_kv(m): - key = m.group(2) - if key.startswith("'"): - assert key.endswith("'") - assert '"' not in key - key = '"%s"' % key[1:-1] - elif not key.startswith('"'): - key = '"%s"' % key - - value = m.group(4) - if value.startswith("'"): - assert value.endswith("'") - assert '"' not in value - value = '"%s"' % value[1:-1] - - return m.group(1) + key + m.group(3) + value + v = m.group(0) + if v in ('true', 'false', 'null'): + return v + if v.startswith('"'): + return v + if v.startswith("'"): + v = v[1:-1] + v = re.sub(r"\\\\|\\'|\"", lambda m: { + '\\\\': '\\\\', + "\\'": "'", + '"': '\\"', + }[m.group(0)], v) + return '"%s"' % v res = re.sub(r'''(?x) - ([{,]\s*) - ("[^"]*"|\'[^\']*\'|[a-z0-9A-Z]+) - (:\s*) - ([0-9.]+|true|false|"[^"]*"|\'[^\']*\'|\[|\{) + "(?:[^"\\]*(?:\\\\|\\")?)*"| + '(?:[^'\\]*(?:\\\\|\\')?)*'| + [a-zA-Z_][a-zA-Z_0-9]* ''', fix_kv, code) res = re.sub(r',(\s*\])', lambda m: m.group(1), res) return res @@ -1582,18 +1480,6 @@ def qualities(quality_ids): DEFAULT_OUTTMPL = '%(title)s-%(id)s.%(ext)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 - def limit_length(s, length): """ Add ellipses to overly long strings """ @@ -1603,3 +1489,28 @@ def limit_length(s, length): if len(s) > length: return s[:length - len(ELLIPSES)] + ELLIPSES return s + + +def version_tuple(v): + return [int(e) for e in v.split('.')] + + +def is_outdated_version(version, limit, assume_new=True): + if not version: + return not assume_new + try: + return version_tuple(version) < version_tuple(limit) + except ValueError: + return not assume_new + + +def ytdl_is_updateable(): + """ Returns if youtube-dl can be updated with -U """ + from zipimport import zipimporter + + return isinstance(globals().get('__loader__'), zipimporter) or hasattr(sys, 'frozen') + + +def args_to_str(args): + # Get a short string representation for a subprocess command + return ' '.join(shlex_quote(a) for a in args) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index a59cbf879..9476bedfa 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,2 +1,3 @@ +from __future__ import unicode_literals -__version__ = '2014.09.16' +__version__ = '2014.11.27'