From: Philipp Hagemeister Date: Thu, 27 Sep 2012 18:18:29 +0000 (+0200) Subject: Merge remote-tracking branch 'FiloSottille/vbr' X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=commitdiff_plain;h=234e230c8781ed46013a6a26d56c4b1dcbe57e69;hp=3a68d7b467d59e6df4d8473989dcd9edb460dd75;p=youtube-dl Merge remote-tracking branch 'FiloSottille/vbr' Conflicts: youtube-dl youtube-dl.exe --- diff --git a/LATEST_VERSION b/LATEST_VERSION index 0c8dc502a..88c5427e0 100644 --- a/LATEST_VERSION +++ b/LATEST_VERSION @@ -1 +1 @@ -2012.02.27 +2012.09.27 diff --git a/Makefile b/Makefile index e2da02e96..625948211 100644 --- a/Makefile +++ b/Makefile @@ -1,26 +1,48 @@ -default: update +all: youtube-dl README.md youtube-dl.1 youtube-dl.bash-completion LATEST_VERSION -update: compile update-readme update-latest +# TODO: re-add youtube-dl.exe, and make sure it's 1. safe and 2. doesn't need sudo -update-latest: - ./youtube-dl.dev --version > LATEST_VERSION +clean: + rm -f youtube-dl youtube-dl.exe youtube-dl.1 LATEST_VERSION -update-readme: - @options=$$(COLUMNS=80 ./youtube-dl.dev --help | sed -e '1,/.*General Options.*/ d' -e 's/^\W\{2\}\(\w\)/### \1/') && \ - header=$$(sed -e '/.*## OPTIONS/,$$ d' README.md) && \ - footer=$$(sed -e '1,/.*## FAQ/ d' README.md) && \ +PREFIX=/usr/local +install: youtube-dl youtube-dl.1 youtube-dl.bash-completion + install -m 755 --owner root --group root youtube-dl $(PREFIX)/bin/ + install -m 644 --owner root --group root youtube-dl.1 $(PREFIX)/man/man1 + install -m 644 --owner root --group root youtube-dl.bash-completion /etc/bash_completion.d/youtube-dl + +.PHONY: all clean install README.md youtube-dl.bash-completion +# TODO un-phone README.md and youtube-dl.bash_completion by reading from .in files and generating from them + +youtube-dl: youtube_dl/*.py + zip --quiet --junk-paths youtube-dl youtube_dl/*.py + echo '#!/usr/bin/env python' > youtube-dl + cat youtube-dl.zip >> youtube-dl + rm youtube-dl.zip + chmod a+x youtube-dl + +youtube-dl.exe: youtube_dl/*.py + bash devscripts/wine-py2exe.sh build_exe.py + +README.md: youtube-dl + @options=$$(COLUMNS=80 ./youtube-dl --help | sed -e '1,/.*General Options.*/ d' -e 's/^\W\{2\}\(\w\)/## \1/') && \ + header=$$(sed -e '/.*# OPTIONS/,$$ d' README.md) && \ + footer=$$(sed -e '1,/.*# FAQ/ d' README.md) && \ echo "$${header}" > README.md && \ echo >> README.md && \ - echo '## OPTIONS' >> README.md && \ + echo '# OPTIONS' >> README.md && \ echo "$${options}" >> README.md&& \ echo >> README.md && \ - echo '## FAQ' >> README.md && \ + echo '# FAQ' >> README.md && \ echo "$${footer}" >> README.md -compile: - zip --quiet --junk-paths youtube-dl youtube_dl/*.py - echo '#!/usr/bin/env python' > youtube-dl - cat youtube-dl.zip >> youtube-dl - rm youtube-dl.zip +youtube-dl.1: README.md + pandoc -s -w man README.md -o youtube-dl.1 + +youtube-dl.bash-completion: README.md + @options=`egrep -o '(--[a-z-]+) ' README.md | sort -u | xargs echo` && \ + content=`sed "s/opts=\"[^\"]*\"/opts=\"$${options}\"/g" youtube-dl.bash-completion` && \ + echo "$${content}" > youtube-dl.bash-completion -.PHONY: default compile update update-latest update-readme +LATEST_VERSION: youtube-dl + ./youtube-dl --version > LATEST_VERSION diff --git a/README.md b/README.md index 8a6742d94..51501684b 100644 --- a/README.md +++ b/README.md @@ -1,16 +1,19 @@ -# youtube-dl +% youtube-dl(1) -## USAGE -youtube-dl [options] url [url...] +# NAME +youtube-dl -## DESCRIPTION +# SYNOPSIS +**youtube-dl** [OPTIONS] URL [URL...] + +# 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.x (x being at least 6), and it is not platform specific. It should work in your Unix box, in Windows or in Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. -## OPTIONS +# OPTIONS -h, --help print this help text and exit --version print program version and exit -U, --update update this program to latest version @@ -18,10 +21,11 @@ which means you can modify it, redistribute it or use it however you like. -r, --rate-limit LIMIT download rate limit (e.g. 50k or 44.6m) -R, --retries RETRIES number of retries (default is 10) --dump-user-agent display the current browser identification + --user-agent None specify a custom user agent --list-extractors List all supported extractors and the URLs they would handle -### Video Selection: +## Video Selection: --playlist-start NUMBER playlist video to start at (default is 1) --playlist-end NUMBER playlist video to end at (default is last) --match-title REGEX download only matching titles (regex or caseless @@ -30,7 +34,7 @@ which means you can modify it, redistribute it or use it however you like. caseless sub-string) --max-downloads NUMBER Abort after downloading NUMBER files -### Filesystem Options: +## Filesystem Options: -t, --title use title in file name -l, --literal use literal title in file name -A, --auto-number number downloaded files starting from 00000 @@ -53,7 +57,7 @@ which means you can modify it, redistribute it or use it however you like. --write-description write video description to a .description file --write-info-json write video metadata to a .info.json file -### Verbosity / Simulation Options: +## Verbosity / Simulation Options: -q, --quiet activates quiet mode -s, --simulate do not download the video and do not write anything to disk @@ -68,7 +72,7 @@ which means you can modify it, redistribute it or use it however you like. --console-title display progress in console titlebar -v, --verbose print various debugging information -### Video Format Options: +## Video Format Options: -f, --format FORMAT video format code --all-formats download all available video formats --prefer-free-formats prefer free video formats unless a specific one is @@ -80,12 +84,12 @@ which means you can modify it, redistribute it or use it however you like. --srt-lang LANG language of the closed captions to download (optional) use IETF language tags like 'en' -### Authentication Options: +## Authentication Options: -u, --username USERNAME account username -p, --password PASSWORD account password -n, --netrc use .netrc authentication data -### Post-processing Options: +## Post-processing Options: --extract-audio convert video files to audio-only files (requires ffmpeg or avconv and ffprobe or avprobe) --audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", or "wav"; @@ -96,7 +100,7 @@ which means you can modify it, redistribute it or use it however you like. -k, --keep-video keeps the video file on disk after the post- processing; the video is erased by default -## FAQ +# FAQ ### Can you please put the -b option back? @@ -118,13 +122,13 @@ The URLs youtube-dl outputs require the downloader to have the correct cookies. youtube has switched to a new video info format in July 2011 which is not supported by old versions of youtube-dl. You can update youtube-dl with `sudo youtube-dl --update`. -## COPYRIGHT +# COPYRIGHT youtube-dl is released into the public domain by the copyright holders. This README file was originally written by Daniel Bolton () and is likewise released into the public domain. -## BUGS +# BUGS Bugs and suggestions should be reported at: diff --git a/devscripts/posix-locale.sh b/devscripts/posix-locale.sh old mode 100644 new mode 100755 diff --git a/devscripts/release.sh b/devscripts/release.sh new file mode 100755 index 000000000..75f8ec8eb --- /dev/null +++ b/devscripts/release.sh @@ -0,0 +1,11 @@ +#! /bin/bash + +if [ -z "$1" ]; then echo "ERROR: specify version number like this: $0 1994.09.06"; exit 1; fi +version="$1" +if [ ! -z "`git tag | grep "$version"`" ]; then echo 'ERROR: version already present'; exit 1; fi +if [ ! -z "`git status --porcelain`" ]; then echo 'ERROR: the working directory is not clean; commit or stash changes'; exit 1; fi +sed -i "s/__version__ = '.*'/__version__ = '$version'/" youtube_dl/__init__.py +make all +git add -A +git commit -m "release $version" +git tag -m "Release $version" "$version" \ No newline at end of file diff --git a/devscripts/wine-py2exe.sh b/devscripts/wine-py2exe.sh old mode 100644 new mode 100755 diff --git a/test/testvideo-original.mp4 b/test/testvideo-original.mp4 new file mode 100644 index 000000000..2d25af712 Binary files /dev/null and b/test/testvideo-original.mp4 differ diff --git a/youtube-dl b/youtube-dl index 913619d6d..9c78766ff 100755 Binary files a/youtube-dl and b/youtube-dl differ diff --git a/youtube-dl.1 b/youtube-dl.1 new file mode 100644 index 000000000..1220a3a57 --- /dev/null +++ b/youtube-dl.1 @@ -0,0 +1,194 @@ +.TH youtube-dl 1 "" +.SH NAME +.PP +youtube-dl +.SH SYNOPSIS +.PP +\f[B]youtube-dl\f[] [OPTIONS] URL [URL...] +.SH DESCRIPTION +.PP +\f[B]youtube-dl\f[] is a small command-line program to download videos +from YouTube.com and a few more sites. +It requires the Python interpreter, version 2.x (x being at least 6), +and it is not platform specific. +It should work in your Unix box, in Windows or in Mac OS X. +It is released to the public domain, which means you can modify it, +redistribute it or use it however you like. +.SH OPTIONS +.IP +.nf +\f[C] +-h,\ --help\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ print\ this\ help\ text\ and\ exit +--version\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ print\ program\ version\ and\ exit +-U,\ --update\ \ \ \ \ \ \ \ \ \ \ \ \ update\ this\ program\ to\ latest\ version +-i,\ --ignore-errors\ \ \ \ \ \ continue\ on\ download\ errors +-r,\ --rate-limit\ LIMIT\ \ \ download\ rate\ limit\ (e.g.\ 50k\ or\ 44.6m) +-R,\ --retries\ RETRIES\ \ \ \ number\ of\ retries\ (default\ is\ 10) +--dump-user-agent\ \ \ \ \ \ \ \ display\ the\ current\ browser\ identification +--user-agent\ None\ \ \ \ \ \ \ \ specify\ a\ custom\ user\ agent +--list-extractors\ \ \ \ \ \ \ \ List\ all\ supported\ extractors\ and\ the\ URLs\ they +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ would\ handle +\f[] +.fi +.SS Video Selection: +.IP +.nf +\f[C] +--playlist-start\ NUMBER\ \ playlist\ video\ to\ start\ at\ (default\ is\ 1) +--playlist-end\ NUMBER\ \ \ \ playlist\ video\ to\ end\ at\ (default\ is\ last) +--match-title\ REGEX\ \ \ \ \ \ download\ only\ matching\ titles\ (regex\ or\ caseless +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ sub-string) +--reject-title\ REGEX\ \ \ \ \ skip\ download\ for\ matching\ titles\ (regex\ or +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ caseless\ sub-string) +--max-downloads\ NUMBER\ \ \ Abort\ after\ downloading\ NUMBER\ files +\f[] +.fi +.SS Filesystem Options: +.IP +.nf +\f[C] +-t,\ --title\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ title\ in\ file\ name +-l,\ --literal\ \ \ \ \ \ \ \ \ \ \ \ use\ literal\ title\ in\ file\ name +-A,\ --auto-number\ \ \ \ \ \ \ \ number\ downloaded\ files\ starting\ from\ 00000 +-o,\ --output\ TEMPLATE\ \ \ \ output\ filename\ template.\ Use\ %(stitle)s\ to\ get\ the +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ title,\ %(uploader)s\ for\ the\ uploader\ name, +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(autonumber)s\ to\ get\ an\ automatically\ incremented +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ number,\ %(ext)s\ for\ the\ filename\ extension, +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(upload_date)s\ for\ the\ upload\ date\ (YYYYMMDD),\ and +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %%\ for\ a\ literal\ percent.\ Use\ -\ to\ output\ to +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ stdout. +-a,\ --batch-file\ FILE\ \ \ \ file\ containing\ URLs\ to\ download\ (\[aq]-\[aq]\ for\ stdin) +-w,\ --no-overwrites\ \ \ \ \ \ do\ not\ overwrite\ files +-c,\ --continue\ \ \ \ \ \ \ \ \ \ \ resume\ partially\ downloaded\ files +--no-continue\ \ \ \ \ \ \ \ \ \ \ \ do\ not\ resume\ partially\ downloaded\ files\ (restart +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ from\ beginning) +--cookies\ FILE\ \ \ \ \ \ \ \ \ \ \ file\ to\ read\ cookies\ from\ and\ dump\ cookie\ jar\ in +--no-part\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ use\ .part\ files +--no-mtime\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ use\ the\ Last-modified\ header\ to\ set\ the\ file +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ modification\ time +--write-description\ \ \ \ \ \ write\ video\ description\ to\ a\ .description\ file +--write-info-json\ \ \ \ \ \ \ \ write\ video\ metadata\ to\ a\ .info.json\ file +\f[] +.fi +.SS Verbosity / Simulation Options: +.IP +.nf +\f[C] +-q,\ --quiet\ \ \ \ \ \ \ \ \ \ \ \ \ \ activates\ quiet\ mode +-s,\ --simulate\ \ \ \ \ \ \ \ \ \ \ do\ not\ download\ the\ video\ and\ do\ not\ write\ anything +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ to\ disk +--skip-download\ \ \ \ \ \ \ \ \ \ do\ not\ download\ the\ video +-g,\ --get-url\ \ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ URL +-e,\ --get-title\ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ title +--get-thumbnail\ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ thumbnail\ URL +--get-description\ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ video\ description +--get-filename\ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ output\ filename +--get-format\ \ \ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ output\ format +--no-progress\ \ \ \ \ \ \ \ \ \ \ \ do\ not\ print\ progress\ bar +--console-title\ \ \ \ \ \ \ \ \ \ display\ progress\ in\ console\ titlebar +-v,\ --verbose\ \ \ \ \ \ \ \ \ \ \ \ print\ various\ debugging\ information +\f[] +.fi +.SS Video Format Options: +.IP +.nf +\f[C] +-f,\ --format\ FORMAT\ \ \ \ \ \ video\ format\ code +--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\ (currently\ youtube\ only) +--write-srt\ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ video\ closed\ captions\ to\ a\ .srt\ file +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (currently\ youtube\ only) +--srt-lang\ LANG\ \ \ \ \ \ \ \ \ \ language\ of\ the\ closed\ captions\ to\ download +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (optional)\ use\ IETF\ language\ tags\ like\ \[aq]en\[aq] +\f[] +.fi +.SS Authentication Options: +.IP +.nf +\f[C] +-u,\ --username\ USERNAME\ \ account\ username +-p,\ --password\ PASSWORD\ \ account\ password +-n,\ --netrc\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ .netrc\ authentication\ data +\f[] +.fi +.SS Post-processing Options: +.IP +.nf +\f[C] +--extract-audio\ \ \ \ \ \ \ \ \ \ convert\ video\ files\ to\ audio-only\ files\ (requires +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ ffmpeg\ or\ avconv\ and\ ffprobe\ or\ avprobe) +--audio-format\ FORMAT\ \ \ \ "best",\ "aac",\ "vorbis",\ "mp3",\ "m4a",\ 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\ 128K\ (default\ 5) +-k,\ --keep-video\ \ \ \ \ \ \ \ \ keeps\ the\ video\ file\ on\ disk\ after\ the\ post- +\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ processing;\ the\ video\ is\ erased\ by\ default +\f[] +.fi +.SH FAQ +.SS Can you please put the -b option back? +.PP +Most people asking this question are not aware that youtube-dl now +defaults to downloading the highest available quality as reported by +YouTube, which will be 1080p or 720p in some cases, so you no longer +need the -b option. +For some specific videos, maybe YouTube does not report them to be +available in a specific high quality format you\[aq]\[aq]re interested +in. +In that case, simply request it with the -f option and youtube-dl will +try to download it. +.SS I get HTTP error 402 when trying to download a video. What\[aq]s +this? +.PP +Apparently YouTube requires you to pass a CAPTCHA test if you download +too much. +We\[aq]\[aq]re considering to provide a way to let you solve the +CAPTCHA (https://github.com/rg3/youtube-dl/issues/154), but at the +moment, your best course of action is pointing a webbrowser to the +youtube URL, solving the CAPTCHA, and restart youtube-dl. +.SS I have downloaded a video but how can I play it? +.PP +Once the video is fully downloaded, use any video player, such as +vlc (http://www.videolan.org) or mplayer (http://www.mplayerhq.hu/). +.SS The links provided by youtube-dl -g are not working anymore +.PP +The URLs youtube-dl outputs require the downloader to have the correct +cookies. +Use the \f[C]--cookies\f[] option to write the required cookies into a +file, and advise your downloader to read cookies from that file. +Some sites also require a common user agent to be used, use +\f[C]--dump-user-agent\f[] to see the one in use by youtube-dl. +.SS ERROR: no fmt_url_map or conn information found in video info +.PP +youtube has switched to a new video info format in July 2011 which is +not supported by old versions of youtube-dl. +You can update youtube-dl with \f[C]sudo\ youtube-dl\ --update\f[]. +.SH COPYRIGHT +.PP +youtube-dl is released into the public domain by the copyright holders. +.PP +This README file was originally written by Daniel Bolton +() and is likewise released into the public +domain. +.SH BUGS +.PP +Bugs and suggestions should be reported at: + +.PP +Please include: +.IP \[bu] 2 +Your exact command line, like +\f[C]youtube-dl\ -t\ "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"\f[]. +A common mistake is not to escape the \f[C]&\f[]. +Putting URLs in quotes should solve this problem. +.IP \[bu] 2 +The output of \f[C]youtube-dl\ --version\f[] +.IP \[bu] 2 +The output of \f[C]python\ --version\f[] +.IP \[bu] 2 +The name and version of your Operating System ("Ubuntu 11.04 x64" or +"Windows 7 x64" is usually enough). diff --git a/youtube-dl.bash-completion b/youtube-dl.bash-completion new file mode 100644 index 000000000..1eca2adf3 --- /dev/null +++ b/youtube-dl.bash-completion @@ -0,0 +1,14 @@ +__youtube-dl() +{ + local cur prev opts + COMPREPLY=() + cur="${COMP_WORDS[COMP_CWORD]}" + opts="--all-formats --audio-format --audio-quality --auto-number --batch-file --console-title --continue --cookies --dump-user-agent --extract-audio --format --get-description --get-filename --get-format --get-thumbnail --get-title --get-url --help --ignore-errors --keep-video --list-extractors --list-formats --literal --match-title --max-downloads --max-quality --netrc --no-continue --no-mtime --no-overwrites --no-part --no-progress --output --password --playlist-end --playlist-start --prefer-free-formats --quiet --rate-limit --reject-title --retries --simulate --skip-download --srt-lang --title --update --user-agent --username --verbose --version --write-description --write-info-json --write-srt" + + if [[ ${cur} == * ]] ; then + COMPREPLY=( $(compgen -W "${opts}" -- ${cur}) ) + return 0 + fi +} + +complete -F __youtube-dl youtube-dl diff --git a/youtube-dl.dev b/youtube-dl.dev deleted file mode 100755 index 473b7f42d..000000000 --- a/youtube-dl.dev +++ /dev/null @@ -1,6 +0,0 @@ -#!/usr/bin/env python -# -*- coding: utf-8 -*- - -import youtube_dl - -youtube_dl.main() diff --git a/youtube-dl.exe b/youtube-dl.exe index bf8ed478b..2aa052ccf 100755 Binary files a/youtube-dl.exe and b/youtube-dl.exe differ diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py index baf859ea8..ff5c47726 100644 --- a/youtube_dl/InfoExtractors.py +++ b/youtube_dl/InfoExtractors.py @@ -13,6 +13,8 @@ import urllib import urllib2 import email.utils import xml.etree.ElementTree +import random +import math from urlparse import parse_qs try: @@ -95,7 +97,7 @@ class InfoExtractor(object): class YoutubeIE(InfoExtractor): """Information extractor for youtube.com.""" - _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' + _VALID_URL = r'^((?:https?://)?(?:youtu\.be/|(?:\w+\.)?youtube(?:-nocookie)?\.com/|tube\.majestyc\.net/)(?!view_play_list|my_playlists|artist|playlist)(?:(?:(?:v|embed|e)/)|(?:(?:watch(?:_popup)?(?:\.php)?)?(?:\?|#!?)(?:.+&)?v=))?)?([0-9A-Za-z_-]+)(?(1).+)?$' _LANG_URL = r'http://www.youtube.com/?hl=en&persist_hl=1&gl=US&persist_gl=1&opt_out_ackd=1' _LOGIN_URL = 'https://www.youtube.com/signup?next=/&gl=US&hl=en' _AGE_URL = 'http://www.youtube.com/verify_age?next_url=/&gl=US&hl=en' @@ -366,7 +368,8 @@ class YoutubeIE(InfoExtractor): srt_list = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) - srt_lang_list = re.findall(r'lang_code="([\w\-]+)"', srt_list) + srt_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', srt_list) + srt_lang_list = dict((l[1], l[0]) for l in srt_lang_list) if not srt_lang_list: raise Trouble(u'WARNING: video has no closed captions') if self._downloader.params.get('subtitleslang', False): @@ -374,14 +377,16 @@ class YoutubeIE(InfoExtractor): elif 'en' in srt_lang_list: srt_lang = 'en' else: - srt_lang = srt_lang_list[0] + srt_lang = srt_lang_list.keys()[0] if not srt_lang in srt_lang_list: raise Trouble(u'WARNING: no closed captions found in the specified language') - request = urllib2.Request('http://video.google.com/timedtext?hl=en&lang=%s&v=%s' % (srt_lang, video_id)) + request = urllib2.Request('http://www.youtube.com/api/timedtext?lang=%s&name=%s&v=%s' % (srt_lang, srt_lang_list[srt_lang], video_id)) try: srt_xml = urllib2.urlopen(request).read() except (urllib2.URLError, httplib.HTTPException, socket.error), err: raise Trouble(u'WARNING: unable to download video subtitles: %s' % str(err)) + if not srt_xml: + raise Trouble(u'WARNING: unable to download video subtitles') video_subtitles = self._closed_captions_xml_to_srt(srt_xml.decode('utf-8')) except Trouble as trouble: self._downloader.trouble(trouble[0]) @@ -399,7 +404,7 @@ class YoutubeIE(InfoExtractor): url_data_strs = video_info['url_encoded_fmt_stream_map'][0].split(',') url_data = [parse_qs(uds) for uds in url_data_strs] url_data = filter(lambda ud: 'itag' in ud and 'url' in ud, url_data) - url_map = dict((ud['itag'][0], ud['url'][0]) for ud in url_data) + url_map = dict((ud['itag'][0], ud['url'][0] + '&signature=' + ud['sig'][0]) for ud in url_data) format_limit = self._downloader.params.get('format_limit', None) available_formats = self._available_formats_prefer_free if self._downloader.params.get('prefer_free_formats', False) else self._available_formats @@ -1619,6 +1624,98 @@ class YoutubeUserIE(InfoExtractor): self._downloader.download(['http://www.youtube.com/watch?v=%s' % video_id]) +class BlipTVUserIE(InfoExtractor): + """Information Extractor for blip.tv users.""" + + _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?blip\.tv/)|bliptvuser:)([^/]+)/*$' + _PAGE_SIZE = 12 + IE_NAME = u'blip.tv:user' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_page(self, username, pagenum): + """Report attempt to download user page.""" + self._downloader.to_screen(u'[%s] user %s: Downloading video ids from page %d' % + (self.IE_NAME, username, pagenum)) + + def _real_extract(self, url): + # Extract username + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid url: %s' % url) + return + + username = mobj.group(1) + + page_base = 'http://m.blip.tv/pr/show_get_full_episode_list?users_id=%s&lite=0&esi=1' + + request = urllib2.Request(url) + + try: + page = urllib2.urlopen(request).read().decode('utf-8') + mobj = re.search(r'data-users-id="([^"]+)"', page) + page_base = page_base % mobj.group(1) + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + + # Download video ids using BlipTV Ajax calls. Result size per + # query is limited (currently to 12 videos) so we need to query + # page by page until there are no video ids - it means we got + # all of them. + + video_ids = [] + pagenum = 1 + + while True: + self.report_download_page(username, pagenum) + + request = urllib2.Request( page_base + "&page=" + str(pagenum) ) + + try: + page = urllib2.urlopen(request).read().decode('utf-8') + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download webpage: %s' % str(err)) + return + + # Extract video identifiers + ids_in_page = [] + + for mobj in re.finditer(r'href="/([^"]+)"', page): + if mobj.group(1) not in ids_in_page: + ids_in_page.append(unescapeHTML(mobj.group(1))) + + video_ids.extend(ids_in_page) + + # A little optimization - if current page is not + # "full", ie. does not contain PAGE_SIZE video ids then + # we can assume that this page is the last one - there + # are no more ids on further pages - no need to query + # again. + + if len(ids_in_page) < self._PAGE_SIZE: + break + + pagenum += 1 + + all_ids_count = len(video_ids) + playliststart = self._downloader.params.get('playliststart', 1) - 1 + playlistend = self._downloader.params.get('playlistend', -1) + + if playlistend == -1: + video_ids = video_ids[playliststart:] + else: + video_ids = video_ids[playliststart:playlistend] + + self._downloader.to_screen(u"[%s] user %s: Collected %d video ids (downloading %d of them)" % + (self.IE_NAME, username, all_ids_count, len(video_ids))) + + for video_id in video_ids: + self._downloader.download([u'http://blip.tv/'+video_id]) + + class DepositFilesIE(InfoExtractor): """Information extractor for depositfiles.com""" @@ -1917,7 +2014,7 @@ class BlipTVIE(InfoExtractor): else: cchar = '?' json_url = url + cchar + 'skin=json&version=2&no_wrap=1' - request = urllib2.Request(json_url) + request = urllib2.Request(json_url.encode('utf-8')) self.report_extraction(mobj.group(1)) info = None try: @@ -1975,6 +2072,7 @@ class BlipTVIE(InfoExtractor): self._downloader.trouble(u'ERROR: unable to parse video information: %s' % repr(err)) return + std_headers['User-Agent'] = 'iTunes/10.6.1' return [info] @@ -2193,12 +2291,14 @@ class EscapistIE(InfoExtractor): self.report_extraction(showName) try: - webPageBytes = urllib2.urlopen(url).read() + webPage = urllib2.urlopen(url) + webPageBytes = webPage.read() + m = re.match(r'text/html; charset="?([^"]+)"?', webPage.headers['Content-Type']) + webPage = webPageBytes.decode(m.group(1) if m else 'utf-8') except (urllib2.URLError, httplib.HTTPException, socket.error), err: self._downloader.trouble(u'ERROR: unable to download webpage: ' + unicode(err)) return - webPage = webPageBytes.decode('utf-8') descMatch = re.search('[A-Za-z0-9]+)\.html' + IE_NAME = u'Youku' + + def __init__(self, downloader=None): + InfoExtractor.__init__(self, downloader) + + def report_download_webpage(self, file_id): + """Report webpage download.""" + self._downloader.to_screen(u'[Youku] %s: Downloading webpage' % file_id) + + def report_extraction(self, file_id): + """Report information extraction.""" + self._downloader.to_screen(u'[Youku] %s: Extracting information' % file_id) + + def _gen_sid(self): + nowTime = int(time.time() * 1000) + random1 = random.randint(1000,1998) + random2 = random.randint(1000,9999) + + 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) ) + mixed.append(source[int(index)]) + source.remove(source[int(index)]) + #return ''.join(mixed) + return mixed + + def _get_file_id(self, fileId, seed): + mixed = self._get_file_ID_mix_string(seed) + ids = fileId.split('*') + realId = [] + for ch in ids: + if ch: + realId.append(mixed[int(ch)]) + return ''.join(realId) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group('ID') + + info_url = 'http://v.youku.com/player/getPlayList/VideoIDS/' + video_id + + request = urllib2.Request(info_url, None, std_headers) + try: + self.report_download_webpage(video_id) + jsondata = urllib2.urlopen(request).read() + except (urllib2.URLError, httplib.HTTPException, socket.error) as err: + self._downloader.trouble(u'ERROR: Unable to retrieve video webpage: %s' % str(err)) + return + + self.report_extraction(video_id) + try: + config = json.loads(jsondata) + + video_title = config['data'][0]['title'] + seed = config['data'][0]['seed'] + + format = self._downloader.params.get('format', None) + supported_format = 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' + else: + format = 'flv' + ext = u'flv' + + + fileid = config['data'][0]['streamfileids'][format] + seg_number = len(config['data'][0]['segs'][format]) + + keys=[] + for i in xrange(seg_number): + keys.append(config['data'][0]['segs'][format][i]['k']) + + #TODO check error + #youku only could be viewed from mainland china + except: + self._downloader.trouble(u'ERROR: unable to extract info section') + return + + 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 + 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) + + info = { + 'id': '%s_part%02d' % (video_id, index), + 'url': download_url, + 'uploader': None, + 'title': video_title, + 'ext': ext, + 'format': u'NA' + } + files_info.append(info) + + return files_info + + +class XNXXIE(InfoExtractor): + """Information extractor for xnxx.com""" + + _VALID_URL = r'^http://video\.xnxx\.com/video([0-9]+)/(.*)' + IE_NAME = u'xnxx' + VIDEO_URL_RE = r'flv_url=(.*?)&' + VIDEO_TITLE_RE = r'(.*?)\s+-\s+XNXX.COM' + VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&' + + def report_webpage(self, video_id): + """Report information extraction""" + self._downloader.to_screen(u'[%s] %s: Downloading webpage' % (self.IE_NAME, video_id)) + + def report_extraction(self, video_id): + """Report information extraction""" + self._downloader.to_screen(u'[%s] %s: Extracting information' % (self.IE_NAME, video_id)) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + if mobj is None: + self._downloader.trouble(u'ERROR: invalid URL: %s' % url) + return + video_id = mobj.group(1).decode('utf-8') + + self.report_webpage(video_id) + + # Get webpage content + try: + webpage = urllib2.urlopen(url).read() + except (urllib2.URLError, httplib.HTTPException, socket.error), err: + self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err) + return + + result = re.search(self.VIDEO_URL_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video url') + return + video_url = urllib.unquote(result.group(1).decode('utf-8')) + + result = re.search(self.VIDEO_TITLE_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video title') + return + video_title = result.group(1).decode('utf-8') + + result = re.search(self.VIDEO_THUMB_RE, webpage) + if result is None: + self._downloader.trouble(u'ERROR: unable to extract video thumbnail') + return + video_thumbnail = result.group(1).decode('utf-8') + + info = {'id': video_id, + 'url': video_url, + 'uploader': None, + 'upload_date': None, + 'title': video_title, + 'ext': 'flv', + 'format': 'flv', + 'thumbnail': video_thumbnail, + 'description': None, + 'player_url': None} + + return [info] diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 8817228f3..3b3a9a4f4 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -19,7 +19,7 @@ __authors__ = ( ) __license__ = 'Public Domain' -__version__ = '2012.02.27' +__version__ = '2012.09.27' UPDATE_URL = 'https://raw.github.com/rg3/youtube-dl/master/youtube-dl' UPDATE_URL_VERSION = 'https://raw.github.com/rg3/youtube-dl/master/LATEST_VERSION' @@ -190,6 +190,8 @@ def parseOpts(): general.add_option('--dump-user-agent', action='store_true', dest='dump_user_agent', help='display the current browser identification', default=False) + general.add_option('--user-agent', + action='store', dest='useragent', help='specify a custom user agent') general.add_option('--list-extractors', action='store_true', dest='list_extractors', help='List all supported extractors and the URLs they would handle', default=False) @@ -338,6 +340,7 @@ def gen_extractors(): YahooSearchIE(), DepositFilesIE(), FacebookIE(), + BlipTVUserIE(), BlipTVIE(), VimeoIE(), MyVideoIE(), @@ -350,6 +353,8 @@ def gen_extractors(): MixcloudIE(), StanfordOpenClassroomIE(), MTVIE(), + YoukuIE(), + XNXXIE(), GenericIE() ] @@ -367,7 +372,10 @@ def _real_main(): jar.load() except (IOError, OSError), err: sys.exit(u'ERROR: unable to open cookie file') - + # Set user agent + if opts.useragent is not None: + std_headers['User-Agent'] = opts.useragent + # Dump user agent if opts.dump_user_agent: print std_headers['User-Agent'] diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 2853ba50f..922e17ecc 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -223,7 +223,7 @@ def encodeFilename(s): assert type(s) == type(u'') - if sys.platform == 'win32' and sys.getwindowsversion().major >= 5: + if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5: # Pass u'' 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.)