diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md index f37d8aa42..145c3ff83 100644 --- a/.github/ISSUE_TEMPLATE.md +++ b/.github/ISSUE_TEMPLATE.md @@ -6,8 +6,8 @@ --- -### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2017.12.14*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. -- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2017.12.14** +### Make sure you are using the *latest* version: run `youtube-dl --version` and ensure your version is *2018.01.21*. If it's not, read [this FAQ entry](https://github.com/rg3/youtube-dl/blob/master/README.md#how-do-i-update-youtube-dl) and update. Issues with outdated version will be rejected. +- [ ] I've **verified** and **I assure** that I'm running youtube-dl **2018.01.21** ### Before submitting an *issue* make sure you have: - [ ] At least skimmed through the [README](https://github.com/rg3/youtube-dl/blob/master/README.md), **most notably** the [FAQ](https://github.com/rg3/youtube-dl#faq) and [BUGS](https://github.com/rg3/youtube-dl#bugs) sections @@ -35,7 +35,7 @@ Add the `-v` flag to **your command line** you run youtube-dl with (`youtube-dl [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 -[debug] youtube-dl version 2017.12.14 +[debug] youtube-dl version 2018.01.21 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.travis.yml b/.travis.yml index 5f4f3922b..92f326860 100644 --- a/.travis.yml +++ b/.travis.yml @@ -7,16 +7,21 @@ python: - "3.4" - "3.5" - "3.6" + - "pypy" + - "pypy3" sudo: false env: - YTDL_TEST_SET=core - YTDL_TEST_SET=download matrix: + include: + - env: JYTHON=true; YTDL_TEST_SET=core + - env: JYTHON=true; YTDL_TEST_SET=download fast_finish: true allow_failures: - env: YTDL_TEST_SET=download + - env: JYTHON=true; YTDL_TEST_SET=core + - env: JYTHON=true; YTDL_TEST_SET=download +before_install: + - if [ "$JYTHON" == "true" ]; then ./devscripts/install_jython.sh; export PATH="$HOME/jython/bin:$PATH"; fi script: ./devscripts/run_tests.sh -notifications: - email: - - filippo.valsorda@gmail.com - - yasoob.khld@gmail.com diff --git a/AUTHORS b/AUTHORS index 7e012247c..40215a5cf 100644 --- a/AUTHORS +++ b/AUTHORS @@ -231,3 +231,5 @@ John Dong Tatsuyuki Ishi Daniel Weber Kay Bouché +Yang Hongbo +Lei Wang diff --git a/ChangeLog b/ChangeLog index 03d2defb7..65a01fcc7 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,144 @@ +version 2018.01.21 + +Core +* [extractor/common] Improve jwplayer DASH formats extraction (#9242, #15187) +* [utils] Improve scientific notation handling in js_to_json (#14789) + +Extractors ++ [southparkdk] Add support for southparkstudios.nu ++ [southpark] Add support for collections (#14803) +* [franceinter] Fix upload date extraction (#14996) ++ [rtvs] Add support for rtvs.sk (#9242, #15187) +* [restudy] Fix extraction and extend URL regular expression (#15347) +* [youtube:live] Improve live detection (#15365) ++ [springboardplatform] Add support for springboardplatform.com +* [prosiebensat1] Add another clip id regular expression (#15290) +- [ringtv] Remove extractor (#15345) + + +version 2018.01.18 + +Extractors +* [soundcloud] Update client id (#15306) +- [kamcord] Remove extractor (#15322) ++ [spiegel] Add support for nexx videos (#15285) +* [twitch] Fix authentication and error capture (#14090, #15264) +* [vk] Detect more errors due to copyright complaints (#15259) + + +version 2018.01.14 + +Extractors +* [youtube] Fix live streams extraction (#15202) +* [wdr] Bypass geo restriction +* [wdr] Rework extractors (#14598) ++ [wdr] Add support for wdrmaus.de/elefantenseite (#14598) ++ [gamestar] Add support for gamepro.de (#3384) +* [viafree] Skip rtmp formats (#15232) ++ [pandoratv] Add support for mobile URLs (#12441) ++ [pandoratv] Add support for new URL format (#15131) ++ [ximalaya] Add support for ximalaya.com (#14687) ++ [digg] Add support for digg.com (#15214) +* [limelight] Tolerate empty pc formats (#15150, #15151, #15207) +* [ndr:embed:base] Make separate formats extraction non fatal (#15203) ++ [weibo] Add extractor (#15079) ++ [ok] Add support for live streams +* [canalplus] Fix extraction (#15072) +* [bilibili] Fix extraction (#15188) + + +version 2018.01.07 + +Core +* [utils] Fix youtube-dl under PyPy3 on Windows +* [YoutubeDL] Output python implementation in debug header + +Extractors ++ [jwplatform] Add support for multiple embeds (#15192) +* [mitele] Fix extraction (#15186) ++ [motherless] Add support for groups (#15124) +* [lynda] Relax URL regular expression (#15185) +* [soundcloud] Fallback to avatar picture for thumbnail (#12878) +* [youku] Fix list extraction (#15135) +* [openload] Fix extraction (#15166) +* [lynda] Skip invalid subtitles (#15159) +* [twitch] Pass video id to url_result when extracting playlist (#15139) +* [rtve.es:alacarta] Fix extraction of some new URLs +* [acast] Fix extraction (#15147) + + +version 2017.12.31 + +Core ++ [extractor/common] Add container meta field for formats extracted + in _parse_mpd_formats (#13616) ++ [downloader/hls] Use HTTP headers for key request +* [common] Use AACL as the default fourcc when AudioTag is 255 +* [extractor/common] Fix extraction of DASH formats with the same + representation id (#15111) + +Extractors ++ [slutload] Add support for mobile URLs (#14806) +* [abc:iview] Bypass geo restriction +* [abc:iview] Fix extraction (#14711, #14782, #14838, #14917, #14963, #14985, + #15035, #15057, #15061, #15071, #15095, #15106) +* [openload] Fix extraction (#15118) +- [sandia] Remove extractor +- [collegerama] Remove extractor ++ [mediasite] Add support for sites based on Mediasite Video Platform (#5428, + #11185, #14343) ++ [ufctv] Add support for ufc.tv (#14520) +* [pluralsight] Fix missing first line of subtitles (#11118) +* [openload] Fallback on f-page extraction (#14665, #14879) +* [vimeo] Improve password protected videos extraction (#15114) +* [aws] Fix canonical/signed headers generation on python 2 (#15102) + + +version 2017.12.28 + +Extractors ++ [internazionale] Add support for internazionale.it (#14973) +* [playtvak] Relax video regular expression and make description optional + (#15037) ++ [filmweb] Add support for filmweb.no (#8773, #10368) ++ [23video] Add support for 23video.com ++ [espn] Add support for fivethirtyeight.com (#6864) ++ [umg:de] Add support for universal-music.de (#11582, #11584) ++ [espn] Add support for espnfc and extract more formats (#8053) +* [youku] Update ccode (#14880) ++ [openload] Add support for oload.stream (#15070) +* [youku] Fix list extraction (#15065) + + +version 2017.12.23 + +Core +* [extractor/common] Move X-Forwarded-For setup code into _request_webpage ++ [YoutubeDL] Add support for playlist_uploader and playlist_uploader_id in + output template (#11427, #15018) ++ [extractor/common] Introduce uploader, uploader_id and uploader_url + meta fields for playlists (#11427, #15018) +* [downloader/fragment] Encode filename of fragment being removed (#15020) ++ [utils] Add another date format pattern (#14999) + +Extractors ++ [kaltura] Add another embed pattern for entry_id ++ [7plus] Add support for 7plus.com.au (#15043) +* [animeondemand] Relax login error regular expression ++ [shahid] Add support for show pages (#7401) ++ [youtube] Extract uploader, uploader_id and uploader_url for playlists + (#11427, #15018) +* [afreecatv] Improve format extraction (#15019) ++ [cspan] Add support for audio only pages and catch page errors (#14995) ++ [mailru] Add support for embed URLs (#14904) +* [crunchyroll] Future-proof XML element checks (#15013) +* [cbslocal] Fix timestamp extraction (#14999, #15000) +* [discoverygo] Correct TTML subtitle extension +* [vk] Make view count optional (#14979) +* [disney] Skip Apple FairPlay formats (#14982) +* [voot] Fix format extraction (#14758) + + version 2017.12.14 Core @@ -148,8 +289,8 @@ Extractors + [fxnetworks] Extract series metadata (#14603) + [younow] Add support for younow.com (#9255, #9432, #12436) * [dctptv] Fix extraction (#14599) -* [youtube] Restrict embed regex (#14600) -* [vimeo] Restrict iframe embed regex (#14600) +* [youtube] Restrict embed regular expression (#14600) +* [vimeo] Restrict iframe embed regular expression (#14600) * [soundgasm] Improve extraction (#14588) - [myvideo] Remove extractor (#8557) + [nbc] Add support for classic-tv videos (#14575) diff --git a/MANIFEST.in b/MANIFEST.in index 5743f605a..4e43e99f3 100644 --- a/MANIFEST.in +++ b/MANIFEST.in @@ -1,7 +1,9 @@ include README.md -include test/*.py -include test/*.json +include LICENSE +include AUTHORS +include ChangeLog include youtube-dl.bash-completion include youtube-dl.fish include youtube-dl.1 recursive-include docs Makefile conf.py *.rst +recursive-include test * diff --git a/Makefile b/Makefile index 1c760bef8..fe247810f 100644 --- a/Makefile +++ b/Makefile @@ -110,7 +110,7 @@ _EXTRACTOR_FILES = $(shell find youtube_dl/extractor -iname '*.py' -and -not -in youtube_dl/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES) $(PYTHON) devscripts/make_lazy_extractors.py $@ -youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog +youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash-completion youtube-dl.zsh youtube-dl.fish ChangeLog AUTHORS @tar -czf youtube-dl.tar.gz --transform "s|^|youtube-dl/|" --owner 0 --group 0 \ --exclude '*.DS_Store' \ --exclude '*.kate-swp' \ @@ -122,7 +122,7 @@ youtube-dl.tar.gz: youtube-dl README.md README.txt youtube-dl.1 youtube-dl.bash- --exclude 'docs/_build' \ -- \ bin devscripts test youtube_dl docs \ - ChangeLog LICENSE README.md README.txt \ + ChangeLog AUTHORS LICENSE README.md README.txt \ Makefile MANIFEST.in youtube-dl.1 youtube-dl.bash-completion \ youtube-dl.zsh youtube-dl.fish setup.py setup.cfg \ youtube-dl diff --git a/README.md b/README.md index 47b0640ab..eb05f848f 100644 --- a/README.md +++ b/README.md @@ -46,7 +46,7 @@ Or with [MacPorts](https://www.macports.org/): Alternatively, refer to the [developer instructions](#developer-instructions) for how to check out and work with the git repository. For further options, including PGP signatures, see the [youtube-dl Download Page](https://rg3.github.io/youtube-dl/download.html). # DESCRIPTION -**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on Mac OS X. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. +**youtube-dl** is a command-line program to download videos from YouTube.com and a few more sites. It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like. youtube-dl [OPTIONS] URL [URL...] @@ -863,7 +863,7 @@ Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. In order to extract cookies from browser use any conforming browser extension for exporting cookies. For example, [cookies.txt](https://chrome.google.com/webstore/detail/cookiestxt/njabckikapfpffapmjgojcnbfjonfjfg) (for Chrome) or [Export Cookies](https://addons.mozilla.org/en-US/firefox/addon/export-cookies/) (for Firefox). -Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, Mac OS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format. +Note that the cookies file must be in Mozilla/Netscape format and the first line of the cookies file must be either `# HTTP Cookie File` or `# Netscape HTTP Cookie File`. Make sure you have correct [newline format](https://en.wikipedia.org/wiki/Newline) in the cookies file and convert newlines if necessary to correspond with your OS, namely `CRLF` (`\r\n`) for Windows and `LF` (`\n`) for Unix and Unix-like systems (Linux, macOS, etc.). `HTTP Error 400: Bad Request` when using `--cookies` is a good sign of invalid newline format. Passing cookies to youtube-dl is a good way to workaround login when a particular extractor does not implement it explicitly. Another use case is working around [CAPTCHA](https://en.wikipedia.org/wiki/CAPTCHA) some websites require you to solve in particular cases in order to get access (e.g. YouTube, CloudFlare). diff --git a/devscripts/install_jython.sh b/devscripts/install_jython.sh new file mode 100755 index 000000000..bafca4da4 --- /dev/null +++ b/devscripts/install_jython.sh @@ -0,0 +1,5 @@ +#!/bin/bash + +wget http://central.maven.org/maven2/org/python/jython-installer/2.7.1/jython-installer-2.7.1.jar +java -jar jython-installer-2.7.1.jar -s -d "$HOME/jython" +$HOME/jython/bin/jython -m pip install nose diff --git a/docs/supportedsites.md b/docs/supportedsites.md index ebddd5b9d..b0825c58b 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -3,6 +3,7 @@ - **1up.com** - **20min** - **220.ro** + - **23video** - **24video** - **3qsdn**: 3Q SDN - **3sat** @@ -10,6 +11,7 @@ - **56.com** - **5min** - **6play** + - **7plus** - **8tracks** - **91porn** - **9c9media** @@ -126,7 +128,7 @@ - **CamdemyFolder** - **CamWithHer** - **canalc2.tv** - - **Canalplus**: canalplus.fr, piwiplus.fr and d8.tv + - **Canalplus**: mycanal.fr and piwiplus.fr - **Canvas** - **CanvasEen**: canvas.be and een.be - **CarambaTV** @@ -169,7 +171,6 @@ - **CNN** - **CNNArticle** - **CNNBlogs** - - **CollegeRama** - **ComCarCoff** - **ComedyCentral** - **ComedyCentralFullEpisodes** @@ -209,6 +210,7 @@ - **defense.gouv.fr** - **democracynow** - **DHM**: Filmarchiv - Deutsches Historisches Museum + - **Digg** - **DigitallySpeaking** - **Digiteka** - **Discovery** @@ -268,6 +270,8 @@ - **Fczenit** - **filmon** - **filmon:channel** + - **Filmweb** + - **FiveThirtyEight** - **FiveTV** - **Flickr** - **Flipagram** @@ -358,6 +362,7 @@ - **InfoQ** - **Instagram** - **instagram:user**: Instagram user profile + - **Internazionale** - **InternetVideoArchive** - **IPrima** - **iqiyi**: 爱奇艺 @@ -378,7 +383,6 @@ - **JWPlatform** - **Kakao** - **Kaltura** - - **Kamcord** - **KanalPlay**: Kanal 5/9/11 Play - **Kankan** - **Karaoketv** @@ -444,6 +448,7 @@ - **media.ccc.de** - **Medialaan** - **Mediaset** + - **Mediasite** - **Medici** - **megaphone.fm**: megaphone.fm embedded players - **Meipai**: 美拍 @@ -473,6 +478,7 @@ - **Moniker**: allmyvideos.net and vidspot.net - **Morningstar**: morningstar.com - **Motherless** + - **MotherlessGroup** - **Motorsport**: motorsport.com - **MovieClips** - **MovieFap** @@ -676,7 +682,6 @@ - **revision** - **revision3:embed** - **RICE** - - **RingTV** - **RMCDecouverte** - **RockstarGames** - **RoosterTeeth** @@ -697,6 +702,7 @@ - **rtve.es:live**: RTVE.es live streams - **rtve.es:television** - **RTVNH** + - **RTVS** - **Rudo** - **RUHD** - **RulePorn** @@ -712,7 +718,6 @@ - **safari**: safaribooksonline.com online video - **safari:api** - **safari:course**: safaribooksonline.com online courses - - **Sandia**: Sandia National Laboratories - **Sapo**: SAPO Vídeos - **savefrom.net** - **SBS**: sbs.com.au @@ -728,6 +733,7 @@ - **Servus** - **Sexu** - **Shahid** + - **ShahidShow** - **Shared**: shared.sx - **ShowRoomLive** - **Sina** @@ -767,7 +773,7 @@ - **Sport5** - **SportBoxEmbed** - **SportDeutschland** - - **Sportschau** + - **SpringboardPlatform** - **Sprout** - **sr:mediathek**: Saarländischer Rundfunk - **SRGSSR** @@ -886,7 +892,9 @@ - **udemy** - **udemy:course** - **UDNEmbed**: 聯合影音 + - **UFCTV** - **UKTVPlay** + - **umg:de**: Universal Music Deutschland - **Unistra** - **Unity** - **uol.com.br** @@ -994,10 +1002,14 @@ - **WatchIndianPorn**: Watch Indian Porn - **WDR** - **wdr:mobile** + - **WDRElefant** + - **WDRPage** - **Webcaster** - **WebcasterFeed** - **WebOfStories** - **WebOfStoriesPlaylist** + - **Weibo** + - **WeiboMobile** - **WeiqiTV**: WQTV - **wholecloud**: WholeCloud - **Wimp** @@ -1017,6 +1029,8 @@ - **xiami:artist**: 虾米音乐 - 歌手 - **xiami:collection**: 虾米音乐 - 精选集 - **xiami:song**: 虾米音乐 + - **ximalaya**: 喜马拉雅FM + - **ximalaya:album**: 喜马拉雅FM 专辑 - **XMinus** - **XNXX** - **Xstream** diff --git a/setup.py b/setup.py index 67d6633ed..7dbb5805f 100644 --- a/setup.py +++ b/setup.py @@ -109,6 +109,7 @@ setup( author_email='ytdl@yt-dl.org', maintainer='Sergey M.', maintainer_email='dstftw@gmail.com', + license='Unlicense', packages=[ 'youtube_dl', 'youtube_dl.extractor', 'youtube_dl.downloader', diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py index 8a372d2c9..7b31d5198 100644 --- a/test/test_InfoExtractor.py +++ b/test/test_InfoExtractor.py @@ -493,9 +493,20 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/ _TEST_CASES = [ ( # https://github.com/rg3/youtube-dl/issues/13919 + # Also tests duplicate representation ids, see + # https://github.com/rg3/youtube-dl/issues/15111 'float_duration', 'http://unknown/manifest.mpd', [{ + 'manifest_url': 'http://unknown/manifest.mpd', + 'ext': 'm4a', + 'format_id': '318597', + 'format_note': 'DASH audio', + 'protocol': 'http_dash_segments', + 'acodec': 'mp4a.40.2', + 'vcodec': 'none', + 'tbr': 61.587, + }, { 'manifest_url': 'http://unknown/manifest.mpd', 'ext': 'mp4', 'format_id': '318597', diff --git a/test/test_download.py b/test/test_download.py index 209f5f6d6..ebe820dfc 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -92,8 +92,8 @@ class TestDownload(unittest.TestCase): def generator(test_case, tname): def test_template(self): - ie = youtube_dl.extractor.get_info_extractor(test_case['name']) - other_ies = [get_info_extractor(ie_key) for ie_key in test_case.get('add_ie', [])] + ie = youtube_dl.extractor.get_info_extractor(test_case['name'])() + other_ies = [get_info_extractor(ie_key)() for ie_key in test_case.get('add_ie', [])] is_playlist = any(k.startswith('playlist') for k in test_case) test_cases = test_case.get( 'playlist', [] if is_playlist else [test_case]) diff --git a/test/test_utils.py b/test/test_utils.py index 0857c0fc0..fdf6031f7 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -814,6 +814,9 @@ class TestUtil(unittest.TestCase): inp = '''{"duration": "00:01:07"}''' self.assertEqual(js_to_json(inp), '''{"duration": "00:01:07"}''') + inp = '''{segments: [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''' + self.assertEqual(js_to_json(inp), '''{"segments": [{"offset":-3.885780586188048e-16,"duration":39.75000000000001}]}''') + def test_js_to_json_edgecases(self): on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}") self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"}) @@ -885,6 +888,13 @@ class TestUtil(unittest.TestCase): on = js_to_json('{/*comment\n*/42/*comment\n*/:/*comment\n*/42/*comment\n*/}') self.assertEqual(json.loads(on), {'42': 42}) + on = js_to_json('{42:4.2e1}') + self.assertEqual(json.loads(on), {'42': 42.0}) + + def test_js_to_json_malformed(self): + self.assertEqual(js_to_json('42a1'), '42"a1"') + self.assertEqual(js_to_json('42a-1'), '42"a"-1') + def test_extract_attributes(self): self.assertEqual(extract_attributes(''), {'x': 'y'}) self.assertEqual(extract_attributes(""), {'x': 'y'}) diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index ace80f14b..97bd9c526 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -2233,8 +2233,16 @@ class YoutubeDL(object): sys.exc_clear() except Exception: pass - self._write_string('[debug] Python version %s - %s\n' % ( - platform.python_version(), platform_name())) + + def python_implementation(): + impl_name = platform.python_implementation() + if impl_name == 'PyPy' and hasattr(sys, 'pypy_version_info'): + return impl_name + ' version %d.%d.%d' % sys.pypy_version_info[:3] + return impl_name + + self._write_string('[debug] Python version %s (%s) - %s\n' % ( + platform.python_version(), python_implementation(), + platform_name())) exe_versions = FFmpegPostProcessor.get_versions(self) exe_versions['rtmpdump'] = rtmpdump_version() diff --git a/youtube_dl/aes.py b/youtube_dl/aes.py index c5bb3c4ef..461bb6d41 100644 --- a/youtube_dl/aes.py +++ b/youtube_dl/aes.py @@ -1,8 +1,8 @@ from __future__ import unicode_literals -import base64 from math import ceil +from .compat import compat_b64decode from .utils import bytes_to_intlist, intlist_to_bytes BLOCK_SIZE_BYTES = 16 @@ -180,7 +180,7 @@ def aes_decrypt_text(data, password, key_size_bytes): """ NONCE_LENGTH_BYTES = 8 - data = bytes_to_intlist(base64.b64decode(data.encode('utf-8'))) + data = bytes_to_intlist(compat_b64decode(data)) password = bytes_to_intlist(password.encode('utf-8')) key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password)) diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 2a62248ef..646c9d79c 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -1,14 +1,17 @@ # coding: utf-8 from __future__ import unicode_literals +import base64 import binascii import collections +import ctypes import email import getpass import io import itertools import optparse import os +import platform import re import shlex import shutil @@ -2906,14 +2909,44 @@ except ImportError: # not 2.6+ or is 3.x except ImportError: compat_zip = zip + +if sys.version_info < (3, 3): + def compat_b64decode(s, *args, **kwargs): + if isinstance(s, compat_str): + s = s.encode('ascii') + return base64.b64decode(s, *args, **kwargs) +else: + compat_b64decode = base64.b64decode + + +if platform.python_implementation() == 'PyPy' and sys.pypy_version_info < (5, 4, 0): + # PyPy2 prior to version 5.4.0 expects byte strings as Windows function + # names, see the original PyPy issue [1] and the youtube-dl one [2]. + # 1. https://bitbucket.org/pypy/pypy/issues/2360/windows-ctypescdll-typeerror-function-name + # 2. https://github.com/rg3/youtube-dl/pull/4392 + def compat_ctypes_WINFUNCTYPE(*args, **kwargs): + real = ctypes.WINFUNCTYPE(*args, **kwargs) + + def resf(tpl, *args, **kwargs): + funcname, dll = tpl + return real((str(funcname), dll), *args, **kwargs) + + return resf +else: + def compat_ctypes_WINFUNCTYPE(*args, **kwargs): + return ctypes.WINFUNCTYPE(*args, **kwargs) + + __all__ = [ 'compat_HTMLParseError', 'compat_HTMLParser', 'compat_HTTPError', + 'compat_b64decode', 'compat_basestring', 'compat_chr', 'compat_cookiejar', 'compat_cookies', + 'compat_ctypes_WINFUNCTYPE', 'compat_etree_fromstring', 'compat_etree_register_namespace', 'compat_expanduser', diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index fdb80f42a..15e71be9a 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -1,12 +1,12 @@ from __future__ import division, unicode_literals -import base64 import io import itertools import time from .fragment import FragmentFD from ..compat import ( + compat_b64decode, compat_etree_fromstring, compat_urlparse, compat_urllib_error, @@ -312,7 +312,7 @@ class F4mFD(FragmentFD): boot_info = self._get_bootstrap_from_url(bootstrap_url) else: bootstrap_url = None - bootstrap = base64.b64decode(node.text.encode('ascii')) + bootstrap = compat_b64decode(node.text) boot_info = read_bootstrap_info(bootstrap) return boot_info, bootstrap_url @@ -349,7 +349,7 @@ class F4mFD(FragmentFD): live = boot_info['live'] metadata_node = media.find(_add_ns('metadata')) if metadata_node is not None: - metadata = base64.b64decode(metadata_node.text.encode('ascii')) + metadata = compat_b64decode(metadata_node.text) else: metadata = None diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 1a6e226c8..4dc3ab46a 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -163,7 +163,8 @@ class HlsFD(FragmentFD): return False if decrypt_info['METHOD'] == 'AES-128': iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence) - decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(decrypt_info['URI']).read() + decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen( + self._prepare_url(info_dict, decrypt_info['URI'])).read() frag_content = AES.new( decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content) self._append_fragment(ctx, frag_content) diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index 60f753b95..87017ed39 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -1,6 +1,9 @@ from __future__ import unicode_literals +import hashlib +import hmac import re +import time from .common import InfoExtractor from ..compat import compat_str @@ -10,6 +13,7 @@ from ..utils import ( int_or_none, parse_iso8601, try_get, + update_url_query, ) @@ -101,21 +105,24 @@ class ABCIE(InfoExtractor): class ABCIViewIE(InfoExtractor): IE_NAME = 'abc.net.au:iview' _VALID_URL = r'https?://iview\.abc\.net\.au/programs/[^/]+/(?P[^/?#]+)' + _GEO_COUNTRIES = ['AU'] # ABC iview programs are normally available for 14 days only. _TESTS = [{ - 'url': 'http://iview.abc.net.au/programs/diaries-of-a-broken-mind/ZX9735A001S00', + 'url': 'http://iview.abc.net.au/programs/call-the-midwife/ZW0898A003S00', 'md5': 'cde42d728b3b7c2b32b1b94b4a548afc', 'info_dict': { - 'id': 'ZX9735A001S00', + 'id': 'ZW0898A003S00', 'ext': 'mp4', - 'title': 'Diaries Of A Broken Mind', - 'description': 'md5:7de3903874b7a1be279fe6b68718fc9e', - 'upload_date': '20161010', - 'uploader_id': 'abc2', - 'timestamp': 1476064920, + 'title': 'Series 5 Ep 3', + 'description': 'md5:e0ef7d4f92055b86c4f33611f180ed79', + 'upload_date': '20171228', + 'uploader_id': 'abc1', + 'timestamp': 1514499187, + }, + 'params': { + 'skip_download': True, }, - 'skip': 'Video gone', }] def _real_extract(self, url): @@ -126,20 +133,30 @@ class ABCIViewIE(InfoExtractor): title = video_params.get('title') or video_params['seriesTitle'] stream = next(s for s in video_params['playlist'] if s.get('type') == 'program') - format_urls = [ - try_get(stream, lambda x: x['hds-unmetered'], compat_str)] + house_number = video_params.get('episodeHouseNumber') + path = '/auth/hls/sign?ts={0}&hn={1}&d=android-mobile'.format( + int(time.time()), house_number) + sig = hmac.new( + 'android.content.res.Resources'.encode('utf-8'), + path.encode('utf-8'), hashlib.sha256).hexdigest() + token = self._download_webpage( + 'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id) - # May have higher quality video - sd_url = try_get( - stream, lambda x: x['streams']['hds']['sd'], compat_str) - if sd_url: - format_urls.append(sd_url.replace('metered', 'um')) + def tokenize_url(url, token): + return update_url_query(url, { + 'hdnea': token, + }) - formats = [] - for format_url in format_urls: - if format_url: - formats.extend( - self._extract_akamai_formats(format_url, video_id)) + for sd in ('sd', 'sd-low'): + sd_url = try_get( + stream, lambda x: x['streams']['hls'][sd], compat_str) + if not sd_url: + continue + formats = self._extract_m3u8_formats( + tokenize_url(sd_url, token), video_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) + if formats: + break self._sort_formats(formats) subtitles = {} diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py index 6dace3051..5871e72dc 100644 --- a/youtube_dl/extractor/acast.py +++ b/youtube_dl/extractor/acast.py @@ -8,7 +8,7 @@ from .common import InfoExtractor from ..compat import compat_str from ..utils import ( int_or_none, - parse_iso8601, + unified_timestamp, OnDemandPagedList, ) @@ -32,7 +32,7 @@ class ACastIE(InfoExtractor): }, { # test with multiple blings 'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna', - 'md5': '55c0097badd7095f494c99a172f86501', + 'md5': 'e87d5b8516cd04c0d81b6ee1caca28d0', 'info_dict': { 'id': '2a92b283-1a75-4ad8-8396-499c641de0d9', 'ext': 'mp3', @@ -40,23 +40,24 @@ class ACastIE(InfoExtractor): 'timestamp': 1477346700, 'upload_date': '20161024', 'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4', - 'duration': 2797, + 'duration': 2766, } }] def _real_extract(self, url): channel, display_id = re.match(self._VALID_URL, url).groups() cast_data = self._download_json( - 'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id) + 'https://play-api.acast.com/splash/%s/%s' % (channel, display_id), display_id) + e = cast_data['result']['episode'] return { - 'id': compat_str(cast_data['id']), + 'id': compat_str(e['id']), 'display_id': display_id, - 'url': [b['audio'] for b in cast_data['blings'] if b['type'] == 'BlingAudio'][0], - 'title': cast_data['name'], - 'description': cast_data.get('description'), - 'thumbnail': cast_data.get('image'), - 'timestamp': parse_iso8601(cast_data.get('publishingDate')), - 'duration': int_or_none(cast_data.get('duration')), + 'url': e['mediaUrl'], + 'title': e['name'], + 'description': e.get('description'), + 'thumbnail': e.get('image'), + 'timestamp': unified_timestamp(e.get('publishingDate')), + 'duration': int_or_none(e.get('duration')), } diff --git a/youtube_dl/extractor/adn.py b/youtube_dl/extractor/adn.py index cffdab6ca..64fb755da 100644 --- a/youtube_dl/extractor/adn.py +++ b/youtube_dl/extractor/adn.py @@ -1,13 +1,15 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import json import os from .common import InfoExtractor from ..aes import aes_cbc_decrypt -from ..compat import compat_ord +from ..compat import ( + compat_b64decode, + compat_ord, +) from ..utils import ( bytes_to_intlist, ExtractorError, @@ -48,9 +50,9 @@ class ADNIE(InfoExtractor): # http://animedigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js dec_subtitles = intlist_to_bytes(aes_cbc_decrypt( - bytes_to_intlist(base64.b64decode(enc_subtitles[24:])), + bytes_to_intlist(compat_b64decode(enc_subtitles[24:])), bytes_to_intlist(b'\x1b\xe0\x29\x61\x38\x94\x24\x00\x12\xbd\xc5\x80\xac\xce\xbe\xb0'), - bytes_to_intlist(base64.b64decode(enc_subtitles[:24])) + bytes_to_intlist(compat_b64decode(enc_subtitles[:24])) )) subtitles_json = self._parse_json( dec_subtitles[:-compat_ord(dec_subtitles[-1])].decode(), diff --git a/youtube_dl/extractor/animeondemand.py b/youtube_dl/extractor/animeondemand.py index 34c2b363e..e4fa72f46 100644 --- a/youtube_dl/extractor/animeondemand.py +++ b/youtube_dl/extractor/animeondemand.py @@ -85,8 +85,8 @@ class AnimeOnDemandIE(InfoExtractor): if all(p not in response for p in ('>Logout<', 'href="/users/sign_out"')): error = self._search_regex( - r'

(.+?)

', - response, 'error', default=None) + r']+\bclass=(["\'])(?:(?!\1).)*\balert\b(?:(?!\1).)*\1[^>]*>(?P.+?)

', + response, 'error', default=None, group='error') if error: raise ExtractorError('Unable to login: %s' % error, expected=True) raise ExtractorError('Unable to log in') diff --git a/youtube_dl/extractor/aws.py b/youtube_dl/extractor/aws.py index 670abce0c..dccfeaf73 100644 --- a/youtube_dl/extractor/aws.py +++ b/youtube_dl/extractor/aws.py @@ -21,11 +21,11 @@ class AWSIE(InfoExtractor): 'Accept': 'application/json', 'Host': self._AWS_PROXY_HOST, 'X-Amz-Date': amz_date, + 'X-Api-Key': self._AWS_API_KEY } session_token = aws_dict.get('session_token') if session_token: headers['X-Amz-Security-Token'] = session_token - headers['X-Api-Key'] = self._AWS_API_KEY def aws_hash(s): return hashlib.sha256(s.encode('utf-8')).hexdigest() @@ -33,9 +33,9 @@ class AWSIE(InfoExtractor): # Task 1: http://docs.aws.amazon.com/general/latest/gr/sigv4-create-canonical-request.html canonical_querystring = compat_urllib_parse_urlencode(query) canonical_headers = '' - for header_name, header_value in headers.items(): + for header_name, header_value in sorted(headers.items()): canonical_headers += '%s:%s\n' % (header_name.lower(), header_value) - signed_headers = ';'.join([header.lower() for header in headers.keys()]) + signed_headers = ';'.join([header.lower() for header in sorted(headers.keys())]) canonical_request = '\n'.join([ 'GET', aws_dict['uri'], diff --git a/youtube_dl/extractor/bigflix.py b/youtube_dl/extractor/bigflix.py index b4ce767af..28e3e59f6 100644 --- a/youtube_dl/extractor/bigflix.py +++ b/youtube_dl/extractor/bigflix.py @@ -1,11 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote +from ..compat import ( + compat_b64decode, + compat_urllib_parse_unquote, +) class BigflixIE(InfoExtractor): @@ -39,8 +41,8 @@ class BigflixIE(InfoExtractor): webpage, 'title') def decode_url(quoted_b64_url): - return base64.b64decode(compat_urllib_parse_unquote( - quoted_b64_url).encode('ascii')).decode('utf-8') + return compat_b64decode(compat_urllib_parse_unquote( + quoted_b64_url)).decode('utf-8') formats = [] for height, encoded_url in re.findall( diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 1e57310d6..beffcecd0 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -102,6 +102,7 @@ class BiliBiliIE(InfoExtractor): video_id, anime_id, compat_urlparse.urljoin(url, '//bangumi.bilibili.com/anime/%s' % anime_id))) headers = { 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + 'Referer': url } headers.update(self.geo_verification_headers()) @@ -116,10 +117,15 @@ class BiliBiliIE(InfoExtractor): payload = 'appkey=%s&cid=%s&otype=json&quality=2&type=mp4' % (self._APP_KEY, cid) sign = hashlib.md5((payload + self._BILIBILI_KEY).encode('utf-8')).hexdigest() + headers = { + 'Referer': url + } + headers.update(self.geo_verification_headers()) + video_info = self._download_json( 'http://interface.bilibili.com/playurl?%s&sign=%s' % (payload, sign), video_id, note='Downloading video info page', - headers=self.geo_verification_headers()) + headers=headers) if 'durl' not in video_info: self._report_error(video_info) diff --git a/youtube_dl/extractor/brightcove.py b/youtube_dl/extractor/brightcove.py index 0ed59bcbc..f04505011 100644 --- a/youtube_dl/extractor/brightcove.py +++ b/youtube_dl/extractor/brightcove.py @@ -464,7 +464,7 @@ class BrightcoveNewIE(AdobePassIE): 'timestamp': 1441391203, 'upload_date': '20150904', 'uploader_id': '929656772001', - 'formats': 'mincount:22', + 'formats': 'mincount:20', }, }, { # with rtmp streams @@ -478,7 +478,7 @@ class BrightcoveNewIE(AdobePassIE): 'timestamp': 1433556729, 'upload_date': '20150606', 'uploader_id': '4036320279001', - 'formats': 'mincount:41', + 'formats': 'mincount:39', }, 'params': { # m3u8 download @@ -564,59 +564,7 @@ class BrightcoveNewIE(AdobePassIE): return entries - def _real_extract(self, url): - url, smuggled_data = unsmuggle_url(url, {}) - self._initialize_geo_bypass(smuggled_data.get('geo_countries')) - - account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups() - - webpage = self._download_webpage( - 'http://players.brightcove.net/%s/%s_%s/index.min.js' - % (account_id, player_id, embed), video_id) - - policy_key = None - - catalog = self._search_regex( - r'catalog\(({.+?})\);', webpage, 'catalog', default=None) - if catalog: - catalog = self._parse_json( - js_to_json(catalog), video_id, fatal=False) - if catalog: - policy_key = catalog.get('policyKey') - - if not policy_key: - policy_key = self._search_regex( - r'policyKey\s*:\s*(["\'])(?P.+?)\1', - webpage, 'policy key', group='pk') - - api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id) - try: - json_data = self._download_json(api_url, video_id, headers={ - 'Accept': 'application/json;pk=%s' % policy_key - }) - except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - json_data = self._parse_json(e.cause.read().decode(), video_id)[0] - message = json_data.get('message') or json_data['error_code'] - if json_data.get('error_subcode') == 'CLIENT_GEO': - self.raise_geo_restricted(msg=message) - raise ExtractorError(message, expected=True) - raise - - errors = json_data.get('errors') - if errors and errors[0].get('error_subcode') == 'TVE_AUTH': - custom_fields = json_data['custom_fields'] - tve_token = self._extract_mvpd_auth( - smuggled_data['source_url'], video_id, - custom_fields['bcadobepassrequestorid'], - custom_fields['bcadobepassresourceid']) - json_data = self._download_json( - api_url, video_id, headers={ - 'Accept': 'application/json;pk=%s' % policy_key - }, query={ - 'tveToken': tve_token, - }) - + def _parse_brightcove_metadata(self, json_data, video_id): title = json_data['name'].strip() formats = [] @@ -682,6 +630,7 @@ class BrightcoveNewIE(AdobePassIE): }) formats.append(f) + errors = json_data.get('errors') if not formats and errors: error = errors[0] raise ExtractorError( @@ -708,9 +657,64 @@ class BrightcoveNewIE(AdobePassIE): 'thumbnail': json_data.get('thumbnail') or json_data.get('poster'), 'duration': duration, 'timestamp': parse_iso8601(json_data.get('published_at')), - 'uploader_id': account_id, + 'uploader_id': json_data.get('account_id'), 'formats': formats, 'subtitles': subtitles, 'tags': json_data.get('tags', []), 'is_live': is_live, } + + def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + self._initialize_geo_bypass(smuggled_data.get('geo_countries')) + + account_id, player_id, embed, video_id = re.match(self._VALID_URL, url).groups() + + webpage = self._download_webpage( + 'http://players.brightcove.net/%s/%s_%s/index.min.js' + % (account_id, player_id, embed), video_id) + + policy_key = None + + catalog = self._search_regex( + r'catalog\(({.+?})\);', webpage, 'catalog', default=None) + if catalog: + catalog = self._parse_json( + js_to_json(catalog), video_id, fatal=False) + if catalog: + policy_key = catalog.get('policyKey') + + if not policy_key: + policy_key = self._search_regex( + r'policyKey\s*:\s*(["\'])(?P.+?)\1', + webpage, 'policy key', group='pk') + + api_url = 'https://edge.api.brightcove.com/playback/v1/accounts/%s/videos/%s' % (account_id, video_id) + try: + json_data = self._download_json(api_url, video_id, headers={ + 'Accept': 'application/json;pk=%s' % policy_key + }) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: + json_data = self._parse_json(e.cause.read().decode(), video_id)[0] + message = json_data.get('message') or json_data['error_code'] + if json_data.get('error_subcode') == 'CLIENT_GEO': + self.raise_geo_restricted(msg=message) + raise ExtractorError(message, expected=True) + raise + + errors = json_data.get('errors') + if errors and errors[0].get('error_subcode') == 'TVE_AUTH': + custom_fields = json_data['custom_fields'] + tve_token = self._extract_mvpd_auth( + smuggled_data['source_url'], video_id, + custom_fields['bcadobepassrequestorid'], + custom_fields['bcadobepassresourceid']) + json_data = self._download_json( + api_url, video_id, headers={ + 'Accept': 'application/json;pk=%s' % policy_key + }, query={ + 'tveToken': tve_token, + }) + + return self._parse_brightcove_metadata(json_data, video_id) diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index d8bf073f4..51c11cb7e 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -4,59 +4,36 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_urlparse from ..utils import ( - dict_get, # ExtractorError, # HEADRequest, int_or_none, qualities, - remove_end, unified_strdate, ) class CanalplusIE(InfoExtractor): - IE_DESC = 'canalplus.fr, piwiplus.fr and d8.tv' - _VALID_URL = r'''(?x) - https?:// - (?: - (?: - (?:(?:www|m)\.)?canalplus\.fr| - (?:www\.)?piwiplus\.fr| - (?:www\.)?d8\.tv| - (?:www\.)?c8\.fr| - (?:www\.)?d17\.tv| - (?:(?:football|www)\.)?cstar\.fr| - (?:www\.)?itele\.fr - )/(?:(?:[^/]+/)*(?P[^/?#&]+))?(?:\?.*\bvid=(?P\d+))?| - player\.canalplus\.fr/#/(?P\d+) - ) - - ''' + IE_DESC = 'mycanal.fr and piwiplus.fr' + _VALID_URL = r'https?://(?:www\.)?(?Pmycanal|piwiplus)\.fr/(?:[^/]+/)*(?P[^?/]+)(?:\.html\?.*\bvid=|/p/)(?P\d+)' _VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/%s/%s?format=json' _SITE_ID_MAP = { - 'canalplus': 'cplus', + 'mycanal': 'cplus', 'piwiplus': 'teletoon', - 'd8': 'd8', - 'c8': 'd8', - 'd17': 'd17', - 'cstar': 'd17', - 'itele': 'itele', } # Only works for direct mp4 URLs _GEO_COUNTRIES = ['FR'] _TESTS = [{ - 'url': 'http://www.canalplus.fr/c-emissions/pid1830-c-zapping.html?vid=1192814', + 'url': 'https://www.mycanal.fr/d17-emissions/lolywood/p/1397061', 'info_dict': { - 'id': '1405510', - 'display_id': 'pid1830-c-zapping', + 'id': '1397061', + 'display_id': 'lolywood', 'ext': 'mp4', - 'title': 'Zapping - 02/07/2016', - 'description': 'Le meilleur de toutes les chaînes, tous les jours', - 'upload_date': '20160702', + 'title': 'Euro 2016 : Je préfère te prévenir - Lolywood - Episode 34', + 'description': 'md5:7d97039d455cb29cdba0d652a0efaa5e', + 'upload_date': '20160602', }, }, { # geo restricted, bypassed @@ -70,64 +47,12 @@ class CanalplusIE(InfoExtractor): 'upload_date': '20140724', }, 'expected_warnings': ['HTTP Error 403: Forbidden'], - }, { - # geo restricted, bypassed - 'url': 'http://www.c8.fr/c8-divertissement/ms-touche-pas-a-mon-poste/pid6318-videos-integrales.html?vid=1443684', - 'md5': 'bb6f9f343296ab7ebd88c97b660ecf8d', - 'info_dict': { - 'id': '1443684', - 'display_id': 'pid6318-videos-integrales', - 'ext': 'mp4', - 'title': 'Guess my iep ! - TPMP - 07/04/2017', - 'description': 'md5:6f005933f6e06760a9236d9b3b5f17fa', - 'upload_date': '20170407', - }, - 'expected_warnings': ['HTTP Error 403: Forbidden'], - }, { - 'url': 'http://www.itele.fr/chroniques/invite-michael-darmon/rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510', - 'info_dict': { - 'id': '1420176', - 'display_id': 'rachida-dati-nicolas-sarkozy-est-le-plus-en-phase-avec-les-inquietudes-des-francais-171510', - 'ext': 'mp4', - 'title': 'L\'invité de Michaël Darmon du 14/10/2016 - ', - 'description': 'Chaque matin du lundi au vendredi, Michaël Darmon reçoit un invité politique à 8h25.', - 'upload_date': '20161014', - }, - }, { - 'url': 'http://football.cstar.fr/cstar-minisite-foot/pid7566-feminines-videos.html?vid=1416769', - 'info_dict': { - 'id': '1416769', - 'display_id': 'pid7566-feminines-videos', - 'ext': 'mp4', - 'title': 'France - Albanie : les temps forts de la soirée - 20/09/2016', - 'description': 'md5:c3f30f2aaac294c1c969b3294de6904e', - 'upload_date': '20160921', - }, - 'params': { - 'skip_download': True, - }, - }, { - 'url': 'http://m.canalplus.fr/?vid=1398231', - 'only_matching': True, - }, { - 'url': 'http://www.d17.tv/emissions/pid8303-lolywood.html?vid=1397061', - 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) + site, display_id, video_id = re.match(self._VALID_URL, url).groups() - site_id = self._SITE_ID_MAP[compat_urllib_parse_urlparse(url).netloc.rsplit('.', 2)[-2]] - - # Beware, some subclasses do not define an id group - display_id = remove_end(dict_get(mobj.groupdict(), ('display_id', 'id', 'vid')), '.html') - - webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - [r']+?videoId=(["\'])(?P\d+)', - r'id=["\']canal_video_player(?P\d+)', - r'data-video=["\'](?P\d+)'], - webpage, 'video id', default=mobj.group('vid'), group='id') + site_id = self._SITE_ID_MAP[site] info_url = self._VIDEO_INFO_TEMPLATE % (site_id, video_id) video_data = self._download_json(info_url, video_id, 'Downloading video JSON') @@ -161,7 +86,7 @@ class CanalplusIE(InfoExtractor): format_url + '?hdcore=2.11.3', video_id, f4m_id=format_id, fatal=False)) else: formats.append({ - # the secret extracted ya function in http://player.canalplus.fr/common/js/canalPlayer.js + # the secret extracted from ya function in http://player.canalplus.fr/common/js/canalPlayer.js 'url': format_url + '?secret=pqzerjlsmdkjfoiuerhsdlfknaes', 'format_id': format_id, 'preference': preference(format_id), diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py index d4769da75..5aac21299 100644 --- a/youtube_dl/extractor/chilloutzone.py +++ b/youtube_dl/extractor/chilloutzone.py @@ -1,11 +1,11 @@ from __future__ import unicode_literals import re -import base64 import json from .common import InfoExtractor from .youtube import YoutubeIE +from ..compat import compat_b64decode from ..utils import ( clean_html, ExtractorError @@ -58,7 +58,7 @@ class ChilloutzoneIE(InfoExtractor): base64_video_info = self._html_search_regex( r'var cozVidData = "(.+?)";', webpage, 'video data') - decoded_video_info = base64.b64decode(base64_video_info.encode('utf-8')).decode('utf-8') + decoded_video_info = compat_b64decode(base64_video_info).decode('utf-8') video_info_dict = json.loads(decoded_video_info) # get video information from dict diff --git a/youtube_dl/extractor/chirbit.py b/youtube_dl/extractor/chirbit.py index 4815b34be..8d75cdf19 100644 --- a/youtube_dl/extractor/chirbit.py +++ b/youtube_dl/extractor/chirbit.py @@ -1,10 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import re from .common import InfoExtractor +from ..compat import compat_b64decode from ..utils import parse_duration @@ -44,8 +44,7 @@ class ChirbitIE(InfoExtractor): # Reverse engineered from https://chirb.it/js/chirbit.player.js (look # for soundURL) - audio_url = base64.b64decode( - data_fd[::-1].encode('ascii')).decode('utf-8') + audio_url = compat_b64decode(data_fd[::-1]).decode('utf-8') title = self._search_regex( r'class=["\']chirbit-title["\'][^>]*>([^<]+)', webpage, 'title') diff --git a/youtube_dl/extractor/collegerama.py b/youtube_dl/extractor/collegerama.py deleted file mode 100644 index 6a41db87c..000000000 --- a/youtube_dl/extractor/collegerama.py +++ /dev/null @@ -1,93 +0,0 @@ -from __future__ import unicode_literals - -import json - -from .common import InfoExtractor -from ..utils import ( - float_or_none, - int_or_none, - sanitized_Request, -) - - -class CollegeRamaIE(InfoExtractor): - _VALID_URL = r'https?://collegerama\.tudelft\.nl/Mediasite/Play/(?P[\da-f]+)' - _TESTS = [ - { - 'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d', - 'md5': '481fda1c11f67588c0d9d8fbdced4e39', - 'info_dict': { - 'id': '585a43626e544bdd97aeb71a0ec907a01d', - 'ext': 'mp4', - 'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.', - 'description': '', - 'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$', - 'duration': 7713.088, - 'timestamp': 1413309600, - 'upload_date': '20141014', - }, - }, - { - 'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4', - 'md5': 'ef1fdded95bdf19b12c5999949419c92', - 'info_dict': { - 'id': '86a9ea9f53e149079fbdb4202b521ed21d', - 'ext': 'wmv', - 'title': '64ste Vakantiecursus: Afvalwater', - 'description': 'md5:7fd774865cc69d972f542b157c328305', - 'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$', - 'duration': 10853, - 'timestamp': 1326446400, - 'upload_date': '20120113', - }, - }, - ] - - def _real_extract(self, url): - video_id = self._match_id(url) - - player_options_request = { - 'getPlayerOptionsRequest': { - 'ResourceId': video_id, - 'QueryString': '', - } - } - - request = sanitized_Request( - 'http://collegerama.tudelft.nl/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions', - json.dumps(player_options_request)) - request.add_header('Content-Type', 'application/json') - - player_options = self._download_json(request, video_id) - - presentation = player_options['d']['Presentation'] - title = presentation['Title'] - description = presentation.get('Description') - thumbnail = None - duration = float_or_none(presentation.get('Duration'), 1000) - timestamp = int_or_none(presentation.get('UnixTime'), 1000) - - formats = [] - for stream in presentation['Streams']: - for video in stream['VideoUrls']: - thumbnail_url = stream.get('ThumbnailUrl') - if thumbnail_url: - thumbnail = 'http://collegerama.tudelft.nl' + thumbnail_url - format_id = video['MediaType'] - if format_id == 'SS': - continue - formats.append({ - 'url': video['Location'], - 'format_id': format_id, - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'duration': duration, - 'timestamp': timestamp, - 'formats': formats, - } diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index e5ef5e490..a072e9bc9 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -495,6 +495,16 @@ class InfoExtractor(object): self.to_screen('%s' % (note,)) else: self.to_screen('%s: %s' % (video_id, note)) + + # Some sites check X-Forwarded-For HTTP header in order to figure out + # the origin of the client behind proxy. This allows bypassing geo + # restriction by faking this header's value to IP that belongs to some + # geo unrestricted country. We will do so once we encounter any + # geo restriction error. + if self._x_forwarded_for_ip: + if 'X-Forwarded-For' not in headers: + headers['X-Forwarded-For'] = self._x_forwarded_for_ip + if isinstance(url_or_request, compat_urllib_request.Request): url_or_request = update_Request( url_or_request, data=data, headers=headers, query=query) @@ -524,15 +534,6 @@ class InfoExtractor(object): if isinstance(url_or_request, (compat_str, str)): url_or_request = url_or_request.partition('#')[0] - # Some sites check X-Forwarded-For HTTP header in order to figure out - # the origin of the client behind proxy. This allows bypassing geo - # restriction by faking this header's value to IP that belongs to some - # geo unrestricted country. We will do so once we encounter any - # geo restriction error. - if self._x_forwarded_for_ip: - if 'X-Forwarded-For' not in headers: - headers['X-Forwarded-For'] = self._x_forwarded_for_ip - urlh = self._request_webpage(url_or_request, video_id, note, errnote, fatal, data=data, headers=headers, query=query) if urlh is False: assert not fatal @@ -1879,6 +1880,7 @@ class InfoExtractor(object): 'language': lang if lang not in ('mul', 'und', 'zxx', 'mis') else None, 'format_note': 'DASH %s' % content_type, 'filesize': filesize, + 'container': mimetype2ext(mime_type) + '_dash', } f.update(parse_codecs(representation_attrib.get('codecs'))) representation_ms_info = extract_multisegment_info(representation, adaption_set_ms_info) @@ -2006,16 +2008,14 @@ class InfoExtractor(object): f['url'] = initialization_url f['fragments'].append({location_key(initialization_url): initialization_url}) f['fragments'].extend(representation_ms_info['fragments']) - try: - existing_format = next( - fo for fo in formats - if fo['format_id'] == representation_id) - except StopIteration: - full_info = formats_dict.get(representation_id, {}).copy() - full_info.update(f) - formats.append(full_info) - else: - existing_format.update(f) + # According to [1, 5.3.5.2, Table 7, page 35] @id of Representation + # is not necessarily unique within a Period thus formats with + # the same `format_id` are quite possible. There are numerous examples + # of such manifests (see https://github.com/rg3/youtube-dl/issues/15111, + # https://github.com/rg3/youtube-dl/issues/13919) + full_info = formats_dict.get(representation_id, {}).copy() + full_info.update(f) + formats.append(full_info) else: self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) return formats @@ -2055,7 +2055,7 @@ class InfoExtractor(object): stream_timescale = int_or_none(stream.get('TimeScale')) or timescale stream_name = stream.get('Name') for track in stream.findall('QualityLevel'): - fourcc = track.get('FourCC') + fourcc = track.get('FourCC', 'AACL' if track.get('AudioTag') == '255' else None) # TODO: add support for WVC1 and WMAP if fourcc not in ('H264', 'AVC1', 'AACL'): self.report_warning('%s is not a supported codec' % fourcc) @@ -2404,7 +2404,7 @@ class InfoExtractor(object): formats.extend(self._extract_m3u8_formats( source_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id=m3u8_id, fatal=False)) - elif ext == 'mpd': + elif source_type == 'dash' or ext == 'mpd': formats.extend(self._extract_mpd_formats( source_url, video_id, mpd_id=mpd_id, fatal=False)) elif ext == 'smil': diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index b92f25447..3efdc8c21 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -3,13 +3,13 @@ from __future__ import unicode_literals import re import json -import base64 import zlib from hashlib import sha1 from math import pow, sqrt, floor from .common import InfoExtractor from ..compat import ( + compat_b64decode, compat_etree_fromstring, compat_urllib_parse_urlencode, compat_urllib_request, @@ -272,8 +272,8 @@ class CrunchyrollIE(CrunchyrollBaseIE): } def _decrypt_subtitles(self, data, iv, id): - data = bytes_to_intlist(base64.b64decode(data.encode('utf-8'))) - iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8'))) + data = bytes_to_intlist(compat_b64decode(data)) + iv = bytes_to_intlist(compat_b64decode(iv)) id = int(id) def obfuscate_key_aux(count, modulo, start): diff --git a/youtube_dl/extractor/daisuki.py b/youtube_dl/extractor/daisuki.py index 5c9ac68a0..dbc1aa5d4 100644 --- a/youtube_dl/extractor/daisuki.py +++ b/youtube_dl/extractor/daisuki.py @@ -10,6 +10,7 @@ from ..aes import ( aes_cbc_decrypt, aes_cbc_encrypt, ) +from ..compat import compat_b64decode from ..utils import ( bytes_to_intlist, bytes_to_long, @@ -93,7 +94,7 @@ class DaisukiMottoIE(InfoExtractor): rtn = self._parse_json( intlist_to_bytes(aes_cbc_decrypt(bytes_to_intlist( - base64.b64decode(encrypted_rtn)), + compat_b64decode(encrypted_rtn)), aes_key, iv)).decode('utf-8').rstrip('\0'), video_id) diff --git a/youtube_dl/extractor/digg.py b/youtube_dl/extractor/digg.py new file mode 100644 index 000000000..913c1750f --- /dev/null +++ b/youtube_dl/extractor/digg.py @@ -0,0 +1,56 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import js_to_json + + +class DiggIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?digg\.com/video/(?P[^/?#&]+)' + _TESTS = [{ + # JWPlatform via provider + 'url': 'http://digg.com/video/sci-fi-short-jonah-daniel-kaluuya-get-out', + 'info_dict': { + 'id': 'LcqvmS0b', + 'ext': 'mp4', + 'title': "'Get Out' Star Daniel Kaluuya Goes On 'Moby Dick'-Like Journey In Sci-Fi Short 'Jonah'", + 'description': 'md5:541bb847648b6ee3d6514bc84b82efda', + 'upload_date': '20180109', + 'timestamp': 1515530551, + }, + 'params': { + 'skip_download': True, + }, + }, { + # Youtube via provider + 'url': 'http://digg.com/video/dog-boat-seal-play', + 'only_matching': True, + }, { + # vimeo as regular embed + 'url': 'http://digg.com/video/dream-girl-short-film', + 'only_matching': True, + }] + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + info = self._parse_json( + self._search_regex( + r'(?s)video_info\s*=\s*({.+?});\n', webpage, 'video info', + default='{}'), display_id, transform_source=js_to_json, + fatal=False) + + video_id = info.get('video_id') + + if video_id: + provider = info.get('provider_name') + if provider == 'youtube': + return self.url_result( + video_id, ie='Youtube', video_id=video_id) + elif provider == 'jwplayer': + return self.url_result( + 'jwplatform:%s' % video_id, ie='JWPlatform', + video_id=video_id) + + return self.url_result(url, 'Generic') diff --git a/youtube_dl/extractor/dumpert.py b/youtube_dl/extractor/dumpert.py index c9fc9b5a9..be2e3d378 100644 --- a/youtube_dl/extractor/dumpert.py +++ b/youtube_dl/extractor/dumpert.py @@ -1,10 +1,10 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import re from .common import InfoExtractor +from ..compat import compat_b64decode from ..utils import ( qualities, sanitized_Request, @@ -42,7 +42,7 @@ class DumpertIE(InfoExtractor): r'data-files="([^"]+)"', webpage, 'data files') files = self._parse_json( - base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'), + compat_b64decode(files_base64).decode('utf-8'), video_id) quality = qualities(['flv', 'mobile', 'tablet', '720p']) diff --git a/youtube_dl/extractor/einthusan.py b/youtube_dl/extractor/einthusan.py index 3f6268637..4485bf8c1 100644 --- a/youtube_dl/extractor/einthusan.py +++ b/youtube_dl/extractor/einthusan.py @@ -1,13 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import json from .common import InfoExtractor from ..compat import ( - compat_urlparse, + compat_b64decode, compat_str, + compat_urlparse, ) from ..utils import ( extract_attributes, @@ -36,9 +36,9 @@ class EinthusanIE(InfoExtractor): # reversed from jsoncrypto.prototype.decrypt() in einthusan-PGMovieWatcher.js def _decrypt(self, encrypted_data, video_id): - return self._parse_json(base64.b64decode(( + return self._parse_json(compat_b64decode(( encrypted_data[:10] + encrypted_data[-1] + encrypted_data[12:-1] - ).encode('ascii')).decode('utf-8'), video_id) + )).decode('utf-8'), video_id) def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py index 7a7436068..127c69b2e 100644 --- a/youtube_dl/extractor/espn.py +++ b/youtube_dl/extractor/espn.py @@ -1,6 +1,9 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor +from .once import OnceIE from ..compat import compat_str from ..utils import ( determine_ext, @@ -9,22 +12,27 @@ from ..utils import ( ) -class ESPNIE(InfoExtractor): +class ESPNIE(OnceIE): _VALID_URL = r'''(?x) https?:// - (?: - (?:(?:\w+\.)+)?espn\.go| - (?:www\.)?espn - )\.com/ (?: (?: - video/clip| - watch/player - ) - (?: - \?.*?\bid=| - /_/id/ - ) + (?: + (?:(?:\w+\.)+)?espn\.go| + (?:www\.)?espn + )\.com/ + (?: + (?: + video/(?:clip|iframe/twitter)| + watch/player + ) + (?: + .*?\?.*?\bid=| + /_/id/ + ) + ) + )| + (?:www\.)espnfc\.(?:com|us)/(?:video/)?[^/]+/\d+/video/ ) (?P\d+) ''' @@ -77,6 +85,15 @@ class ESPNIE(InfoExtractor): }, { 'url': 'http://www.espn.com/video/clip/_/id/17989860', 'only_matching': True, + }, { + 'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079', + 'only_matching': True, + }, { + 'url': 'http://www.espnfc.us/video/espn-fc-tv/86/video/3319154/nashville-unveiled-as-the-newest-club-in-mls', + 'only_matching': True, + }, { + 'url': 'http://www.espnfc.com/english-premier-league/23/video/3324163/premier-league-in-90-seconds-golden-tweets', + 'only_matching': True, }] def _real_extract(self, url): @@ -93,7 +110,9 @@ class ESPNIE(InfoExtractor): def traverse_source(source, base_source_id=None): for source_id, source in source.items(): - if isinstance(source, compat_str): + if source_id == 'alert': + continue + elif isinstance(source, compat_str): extract_source(source, base_source_id) elif isinstance(source, dict): traverse_source( @@ -106,7 +125,9 @@ class ESPNIE(InfoExtractor): return format_urls.add(source_url) ext = determine_ext(source_url) - if ext == 'smil': + if OnceIE.suitable(source_url): + formats.extend(self._extract_once_formats(source_url)) + elif ext == 'smil': formats.extend(self._extract_smil_formats( source_url, video_id, fatal=False)) elif ext == 'f4m': @@ -117,12 +138,24 @@ class ESPNIE(InfoExtractor): source_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id=source_id, fatal=False)) else: - formats.append({ + f = { 'url': source_url, 'format_id': source_id, - }) + } + mobj = re.search(r'(\d+)p(\d+)_(\d+)k\.', source_url) + if mobj: + f.update({ + 'height': int(mobj.group(1)), + 'fps': int(mobj.group(2)), + 'tbr': int(mobj.group(3)), + }) + if source_id == 'mezzanine': + f['preference'] = 1 + formats.append(f) - traverse_source(clip['links']['source']) + links = clip.get('links', {}) + traverse_source(links.get('source', {})) + traverse_source(links.get('mobile', {})) self._sort_formats(formats) description = clip.get('caption') or clip.get('description') @@ -144,9 +177,6 @@ class ESPNIE(InfoExtractor): class ESPNArticleIE(InfoExtractor): _VALID_URL = r'https?://(?:espn\.go|(?:www\.)?espn)\.com/(?:[^/]+/)*(?P[^/]+)' _TESTS = [{ - 'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079', - 'only_matching': True, - }, { 'url': 'http://espn.go.com/nba/recap?gameId=400793786', 'only_matching': True, }, { @@ -175,3 +205,34 @@ class ESPNArticleIE(InfoExtractor): return self.url_result( 'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key()) + + +class FiveThirtyEightIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?fivethirtyeight\.com/features/(?P[^/?#]+)' + _TEST = { + 'url': 'http://fivethirtyeight.com/features/how-the-6-8-raiders-can-still-make-the-playoffs/', + 'info_dict': { + 'id': '21846851', + 'ext': 'mp4', + 'title': 'FiveThirtyEight: The Raiders can still make the playoffs', + 'description': 'Neil Paine breaks down the simplest scenario that will put the Raiders into the playoffs at 8-8.', + 'timestamp': 1513960621, + 'upload_date': '20171222', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Unable to download f4m manifest'], + } + + 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=["\'](?P\d+)', + webpage, 'video id', group='id') + + return self.url_result( + 'http://espn.go.com/video/clip?id=%s' % video_id, ESPNIE.ie_key()) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e90ab4415..b442256fe 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -205,7 +205,6 @@ from .cnn import ( CNNArticleIE, ) from .coub import CoubIE -from .collegerama import CollegeRamaIE from .comedycentral import ( ComedyCentralFullEpisodesIE, ComedyCentralIE, @@ -260,6 +259,7 @@ from .deezer import DeezerPlaylistIE from .democracynow import DemocracynowIE from .dfb import DFBIE from .dhm import DHMIE +from .digg import DiggIE from .dotsub import DotsubIE from .douyutv import ( DouyuShowIE, @@ -322,6 +322,7 @@ from .escapist import EscapistIE from .espn import ( ESPNIE, ESPNArticleIE, + FiveThirtyEightIE, ) from .esri import EsriVideoIE from .etonline import ETOnlineIE @@ -344,6 +345,7 @@ from .filmon import ( FilmOnIE, FilmOnChannelIE, ) +from .filmweb import FilmwebIE from .firsttv import FirstTVIE from .fivemin import FiveMinIE from .fivetv import FiveTVIE @@ -464,6 +466,7 @@ from .indavideo import ( ) from .infoq import InfoQIE from .instagram import InstagramIE, InstagramUserIE +from .internazionale import InternazionaleIE from .internetvideoarchive import InternetVideoArchiveIE from .iprima import IPrimaIE from .iqiyi import IqiyiIE @@ -487,7 +490,6 @@ from .jwplatform import JWPlatformIE from .jpopsukitv import JpopsukiIE from .kakao import KakaoIE from .kaltura import KalturaIE -from .kamcord import KamcordIE from .kanalplay import KanalPlayIE from .kankan import KankanIE from .karaoketv import KaraoketvIE @@ -573,6 +575,7 @@ from .massengeschmacktv import MassengeschmackTVIE from .matchtv import MatchTVIE from .mdr import MDRIE from .mediaset import MediasetIE +from .mediasite import MediasiteIE from .medici import MediciIE from .megaphone import MegaphoneIE from .meipai import MeipaiIE @@ -606,7 +609,10 @@ from .mofosex import MofosexIE from .mojvideo import MojvideoIE from .moniker import MonikerIE from .morningstar import MorningstarIE -from .motherless import MotherlessIE +from .motherless import ( + MotherlessIE, + MotherlessGroupIE +) from .motorsport import MotorsportIE from .movieclips import MovieClipsIE from .moviezine import MoviezineIE @@ -875,7 +881,6 @@ from .revision3 import ( Revision3IE, ) from .rice import RICEIE -from .ringtv import RingTVIE from .rmcdecouverte import RMCDecouverteIE from .ro220 import Ro220IE from .rockstargames import RockstarGamesIE @@ -895,6 +900,7 @@ from .rtp import RTPIE from .rts import RTSIE from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE from .rtvnh import RTVNHIE +from .rtvs import RTVSIE from .rudo import RudoIE from .ruhd import RUHDIE from .ruleporn import RulePornIE @@ -909,7 +915,6 @@ from .rutube import ( from .rutv import RUTVIE from .ruutu import RuutuIE from .ruv import RuvIE -from .sandia import SandiaIE from .safari import ( SafariIE, SafariApiIE, @@ -926,6 +931,7 @@ from .senateisvp import SenateISVPIE from .sendtonews import SendtoNewsIE from .servingsys import ServingSysIE from .servus import ServusIE +from .sevenplus import SevenPlusIE from .sexu import SexuIE from .seznamzpravy import ( SeznamZpravyIE, @@ -988,7 +994,7 @@ from .stitcher import StitcherIE from .sport5 import Sport5IE from .sportbox import SportBoxEmbedIE from .sportdeutschland import SportDeutschlandIE -from .sportschau import SportschauIE +from .springboardplatform import SpringboardPlatformIE from .sprout import SproutIE from .srgssr import ( SRGSSRIE, @@ -1044,7 +1050,6 @@ from .theplatform import ( ThePlatformFeedIE, ) from .thescene import TheSceneIE -from .thesixtyone import TheSixtyOneIE from .thestar import TheStarIE from .thesun import TheSunIE from .theweatherchannel import TheWeatherChannelIE @@ -1122,6 +1127,7 @@ from .tvplayer import TVPlayerIE from .tweakers import TweakersIE from .twentyfourvideo import TwentyFourVideoIE from .twentymin import TwentyMinutenIE +from .twentythreevideo import TwentyThreeVideoIE from .twitch import ( TwitchVideoIE, TwitchChapterIE, @@ -1144,8 +1150,10 @@ from .udemy import ( UdemyCourseIE ) from .udn import UDNEmbedIE +from .ufctv import UFCTVIE from .uktvplay import UKTVPlayIE from .digiteka import DigitekaIE +from .umg import UMGDeIE from .unistra import UnistraIE from .unity import UnityIE from .uol import UOLIE @@ -1283,6 +1291,8 @@ from .watchbox import WatchBoxIE from .watchindianporn import WatchIndianPornIE from .wdr import ( WDRIE, + WDRPageIE, + WDRElefantIE, WDRMobileIE, ) from .webcaster import ( @@ -1293,6 +1303,10 @@ from .webofstories import ( WebOfStoriesIE, WebOfStoriesPlaylistIE, ) +from .weibo import ( + WeiboIE, + WeiboMobileIE +) from .weiqitv import WeiqiTVIE from .wimp import WimpIE from .wistia import WistiaIE @@ -1318,6 +1332,10 @@ from .xiami import ( XiamiArtistIE, XiamiCollectionIE ) +from .ximalaya import ( + XimalayaIE, + XimalayaAlbumIE +) from .xminus import XMinusIE from .xnxx import XNXXIE from .xstream import XstreamIE diff --git a/youtube_dl/extractor/filmweb.py b/youtube_dl/extractor/filmweb.py new file mode 100644 index 000000000..56000bc5b --- /dev/null +++ b/youtube_dl/extractor/filmweb.py @@ -0,0 +1,42 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class FilmwebIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?filmweb\.no/(?Ptrailere|filmnytt)/article(?P\d+)\.ece' + _TEST = { + 'url': 'http://www.filmweb.no/trailere/article1264921.ece', + 'md5': 'e353f47df98e557d67edaceda9dece89', + 'info_dict': { + 'id': '13033574', + 'ext': 'mp4', + 'title': 'Det som en gang var', + 'upload_date': '20160316', + 'timestamp': 1458140101, + 'uploader_id': '12639966', + 'uploader': 'Live Roaldset', + } + } + + def _real_extract(self, url): + article_type, article_id = re.match(self._VALID_URL, url).groups() + if article_type == 'filmnytt': + webpage = self._download_webpage(url, article_id) + article_id = self._search_regex(r'data-videoid="(\d+)"', webpage, 'article id') + embed_code = self._download_json( + 'https://www.filmweb.no/template_v2/ajax/json_trailerEmbed.jsp', + article_id, query={ + 'articleId': article_id, + })['embedCode'] + iframe_url = self._proto_relative_url(self._search_regex( + r']+src="([^"]+)', embed_code, 'iframe url')) + + return { + '_type': 'url_transparent', + 'id': article_id, + 'url': iframe_url, + 'ie_key': 'TwentyThreeVideo', + } diff --git a/youtube_dl/extractor/franceinter.py b/youtube_dl/extractor/franceinter.py index 707b9e00d..05806895c 100644 --- a/youtube_dl/extractor/franceinter.py +++ b/youtube_dl/extractor/franceinter.py @@ -33,7 +33,7 @@ class FranceInterIE(InfoExtractor): description = self._og_search_description(webpage) upload_date_str = self._search_regex( - r'class=["\']cover-emission-period["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<', + r'class=["\']\s*cover-emission-period\s*["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<', webpage, 'upload date', fatal=False) if upload_date_str: upload_date_list = upload_date_str.split() diff --git a/youtube_dl/extractor/gamestar.py b/youtube_dl/extractor/gamestar.py index e607d6ab8..f00dab2f3 100644 --- a/youtube_dl/extractor/gamestar.py +++ b/youtube_dl/extractor/gamestar.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( int_or_none, @@ -9,27 +11,34 @@ from ..utils import ( class GameStarIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?gamestar\.de/videos/.*,(?P[0-9]+)\.html' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?game(?Ppro|star)\.de/videos/.*,(?P[0-9]+)\.html' + _TESTS = [{ 'url': 'http://www.gamestar.de/videos/trailer,3/hobbit-3-die-schlacht-der-fuenf-heere,76110.html', - 'md5': '96974ecbb7fd8d0d20fca5a00810cea7', + 'md5': 'ee782f1f8050448c95c5cacd63bc851c', 'info_dict': { 'id': '76110', 'ext': 'mp4', 'title': 'Hobbit 3: Die Schlacht der Fünf Heere - Teaser-Trailer zum dritten Teil', 'description': 'Der Teaser-Trailer zu Hobbit 3: Die Schlacht der Fünf Heere zeigt einige Szenen aus dem dritten Teil der Saga und kündigt den...', 'thumbnail': r're:^https?://.*\.jpg$', - 'timestamp': 1406542020, + 'timestamp': 1406542380, 'upload_date': '20140728', - 'duration': 17 + 'duration': 17, } - } + }, { + 'url': 'http://www.gamepro.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html', + 'only_matching': True, + }, { + 'url': 'http://www.gamestar.de/videos/top-10-indie-spiele-fuer-nintendo-switch-video-tolle-nindies-games-zum-download,95316.html', + 'only_matching': True, + }] def _real_extract(self, url): - video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + mobj = re.match(self._VALID_URL, url) + site = mobj.group('site') + video_id = mobj.group('id') - url = 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id + webpage = self._download_webpage(url, video_id) # TODO: there are multiple ld+json objects in the webpage, # while _search_json_ld finds only the first one @@ -37,16 +46,17 @@ class GameStarIE(InfoExtractor): r'(?s)]+type=(["\'])application/ld\+json\1[^>]*>(?P[^<]+VideoObject[^<]+)', webpage, 'JSON-LD', group='json_ld'), video_id) info_dict = self._json_ld(json_ld, video_id) - info_dict['title'] = remove_end(info_dict['title'], ' - GameStar') + info_dict['title'] = remove_end( + info_dict['title'], ' - Game%s' % site.title()) - view_count = json_ld.get('interactionCount') + view_count = int_or_none(json_ld.get('interactionCount')) comment_count = int_or_none(self._html_search_regex( - r'([0-9]+) Kommentare', webpage, 'comment_count', - fatal=False)) + r'Kommentare\s*]+class=["\']count[^>]+>\s*\(\s*([0-9]+)', + webpage, 'comment count', fatal=False)) info_dict.update({ 'id': video_id, - 'url': url, + 'url': 'http://gamestar.de/_misc/videos/portal/getVideoUrl.cfm?premium=0&videoId=' + video_id, 'ext': 'mp4', 'view_count': view_count, 'comment_count': comment_count diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index c7b609215..1d9da8115 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -100,6 +100,8 @@ from .megaphone import MegaphoneIE from .vzaar import VzaarIE from .channel9 import Channel9IE from .vshare import VShareIE +from .mediasite import MediasiteIE +from .springboardplatform import SpringboardPlatformIE class GenericIE(InfoExtractor): @@ -1925,6 +1927,33 @@ class GenericIE(InfoExtractor): 'title': 'vl14062007715967', 'ext': 'mp4', } + }, + { + 'url': 'http://www.heidelberg-laureate-forum.org/blog/video/lecture-friday-september-23-2016-sir-c-antony-r-hoare/', + 'md5': 'aecd089f55b1cb5a59032cb049d3a356', + 'info_dict': { + 'id': '90227f51a80c4d8f86c345a7fa62bd9a1d', + 'ext': 'mp4', + 'title': 'Lecture: Friday, September 23, 2016 - Sir Tony Hoare', + 'description': 'md5:5a51db84a62def7b7054df2ade403c6c', + 'timestamp': 1474354800, + 'upload_date': '20160920', + } + }, + { + 'url': 'http://www.kidzworld.com/article/30935-trolls-the-beat-goes-on-interview-skylar-astin-and-amanda-leighton', + 'info_dict': { + 'id': '1731611', + 'ext': 'mp4', + 'title': 'Official Trailer | TROLLS: THE BEAT GOES ON!', + 'description': 'md5:eb5f23826a027ba95277d105f248b825', + 'timestamp': 1516100691, + 'upload_date': '20180116', + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': [SpringboardPlatformIE.ie_key()], } # { # # TODO: find another test @@ -2695,9 +2724,9 @@ class GenericIE(InfoExtractor): return self.url_result(viewlift_url) # Look for JWPlatform embeds - jwplatform_url = JWPlatformIE._extract_url(webpage) - if jwplatform_url: - return self.url_result(jwplatform_url, 'JWPlatform') + jwplatform_urls = JWPlatformIE._extract_urls(webpage) + if jwplatform_urls: + return self.playlist_from_matches(jwplatform_urls, video_id, video_title, ie=JWPlatformIE.ie_key()) # Look for Digiteka embeds digiteka_url = DigitekaIE._extract_url(webpage) @@ -2883,6 +2912,22 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( vshare_urls, video_id, video_title, ie=VShareIE.ie_key()) + # Look for Mediasite embeds + mediasite_urls = MediasiteIE._extract_urls(webpage) + if mediasite_urls: + entries = [ + self.url_result(smuggle_url( + compat_urlparse.urljoin(url, mediasite_url), + {'UrlReferrer': url}), ie=MediasiteIE.ie_key()) + for mediasite_url in mediasite_urls] + return self.playlist_result(entries, video_id, video_title) + + springboardplatform_urls = SpringboardPlatformIE._extract_urls(webpage) + if springboardplatform_urls: + return self.playlist_from_matches( + springboardplatform_urls, video_id, video_title, + ie=SpringboardPlatformIE.ie_key()) + def merge_dicts(dict1, dict2): merged = {} for k, v in dict1.items(): diff --git a/youtube_dl/extractor/hotnewhiphop.py b/youtube_dl/extractor/hotnewhiphop.py index 34163725f..4703e1894 100644 --- a/youtube_dl/extractor/hotnewhiphop.py +++ b/youtube_dl/extractor/hotnewhiphop.py @@ -1,8 +1,7 @@ from __future__ import unicode_literals -import base64 - from .common import InfoExtractor +from ..compat import compat_b64decode from ..utils import ( ExtractorError, HEADRequest, @@ -48,7 +47,7 @@ class HotNewHipHopIE(InfoExtractor): if 'mediaKey' not in mkd: raise ExtractorError('Did not get a media key') - redirect_url = base64.b64decode(video_url_base64).decode('utf-8') + redirect_url = compat_b64decode(video_url_base64).decode('utf-8') redirect_req = HEADRequest(redirect_url) req = self._request_webpage( redirect_req, video_id, diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py index c3e892feb..391c2f5d0 100644 --- a/youtube_dl/extractor/infoq.py +++ b/youtube_dl/extractor/infoq.py @@ -2,9 +2,8 @@ from __future__ import unicode_literals -import base64 - from ..compat import ( + compat_b64decode, compat_urllib_parse_unquote, compat_urlparse, ) @@ -61,7 +60,7 @@ class InfoQIE(BokeCCBaseIE): encoded_id = self._search_regex( r"jsclassref\s*=\s*'([^']*)'", webpage, 'encoded id', default=None) - real_id = compat_urllib_parse_unquote(base64.b64decode(encoded_id.encode('ascii')).decode('utf-8')) + real_id = compat_urllib_parse_unquote(compat_b64decode(encoded_id).decode('utf-8')) playpath = 'mp4:' + real_id return [{ diff --git a/youtube_dl/extractor/internazionale.py b/youtube_dl/extractor/internazionale.py new file mode 100644 index 000000000..10ba1f6cf --- /dev/null +++ b/youtube_dl/extractor/internazionale.py @@ -0,0 +1,64 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import unified_timestamp + + +class InternazionaleIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?internazionale\.it/video/(?:[^/]+/)*(?P[^/?#&]+)' + _TEST = { + 'url': 'https://www.internazionale.it/video/2015/02/19/richard-linklater-racconta-una-scena-di-boyhood', + 'md5': '3e39d32b66882c1218e305acbf8348ca', + 'info_dict': { + 'id': '265968', + 'display_id': 'richard-linklater-racconta-una-scena-di-boyhood', + 'ext': 'mp4', + 'title': 'Richard Linklater racconta una scena di Boyhood', + 'description': 'md5:efb7e5bbfb1a54ae2ed5a4a015f0e665', + 'timestamp': 1424354635, + 'upload_date': '20150219', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'format': 'bestvideo', + }, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + + webpage = self._download_webpage(url, display_id) + + DATA_RE = r'data-%s=(["\'])(?P(?:(?!\1).)+)\1' + + title = self._search_regex( + DATA_RE % 'video-title', webpage, 'title', default=None, + group='value') or self._og_search_title(webpage) + + video_id = self._search_regex( + DATA_RE % 'job-id', webpage, 'video id', group='value') + video_path = self._search_regex( + DATA_RE % 'video-path', webpage, 'video path', group='value') + + video_base = 'https://video.internazionale.it/%s/%s.' % (video_path, video_id) + + formats = self._extract_m3u8_formats( + video_base + 'm3u8', display_id, 'mp4', + entry_protocol='m3u8_native', m3u8_id='hls', fatal=False) + formats.extend(self._extract_mpd_formats( + video_base + 'mpd', display_id, mpd_id='dash', fatal=False)) + self._sort_formats(formats) + + timestamp = unified_timestamp(self._html_search_meta( + 'article:published_time', webpage, 'timestamp')) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'thumbnail': self._og_search_thumbnail(webpage), + 'description': self._og_search_description(webpage), + 'timestamp': timestamp, + 'formats': formats, + } diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index c9bcbb08f..63d0dc998 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -23,11 +23,14 @@ class JWPlatformIE(InfoExtractor): @staticmethod def _extract_url(webpage): - mobj = re.search( - r'<(?:script|iframe)[^>]+?src=["\'](?P(?:https?:)?//content.jwplatform.com/players/[a-zA-Z0-9]{8})', + urls = JWPlatformIE._extract_urls(webpage) + return urls[0] if urls else None + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//content\.jwplatform\.com/players/[a-zA-Z0-9]{8})', webpage) - if mobj: - return mobj.group('url') def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index bdac2df3e..562e25f6d 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -125,9 +125,12 @@ class KalturaIE(InfoExtractor): (?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P\d+)(?:(?!(?P=q1)).)* (?P=q1).*? (?: - entry_?[Ii]d| - (?P["'])entry_?[Ii]d(?P=q2) - )\s*:\s* + (?: + entry_?[Ii]d| + (?P["'])entry_?[Ii]d(?P=q2) + )\s*:\s*| + \[\s*(?P["'])entry_?[Ii]d(?P=q2_1)\s*\]\s*=\s* + ) (?P["'])(?P(?:(?!(?P=q3)).)+)(?P=q3) ''', webpage) or re.search( diff --git a/youtube_dl/extractor/kamcord.py b/youtube_dl/extractor/kamcord.py deleted file mode 100644 index b50120d98..000000000 --- a/youtube_dl/extractor/kamcord.py +++ /dev/null @@ -1,71 +0,0 @@ -from __future__ import unicode_literals - -from .common import InfoExtractor -from ..compat import compat_str -from ..utils import ( - int_or_none, - qualities, -) - - -class KamcordIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?kamcord\.com/v/(?P[^/?#&]+)' - _TEST = { - 'url': 'https://www.kamcord.com/v/hNYRduDgWb4', - 'md5': 'c3180e8a9cfac2e86e1b88cb8751b54c', - 'info_dict': { - 'id': 'hNYRduDgWb4', - 'ext': 'mp4', - 'title': 'Drinking Madness', - 'uploader': 'jacksfilms', - 'uploader_id': '3044562', - 'view_count': int, - 'like_count': int, - 'comment_count': int, - }, - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video = self._parse_json( - self._search_regex( - r'window\.__props\s*=\s*({.+?});?(?:\n|\s*\d+)|player/embed)/(?P\d+)' + _VALID_URL = r'''(?x) + https?:// + (?:www\.)?(?:lynda\.com|educourse\.ga)/ + (?: + (?:[^/]+/){2,3}(?P\d+)| + player/embed + )/ + (?P\d+) + ''' _TIMECODE_REGEX = r'\[(?P\d+:\d+:\d+[\.,]\d+)\]' @@ -113,6 +121,9 @@ class LyndaIE(LyndaBaseIE): }, { 'url': 'https://educourse.ga/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html', 'only_matching': True, + }, { + 'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Willkommen-Grundlagen-guten-Gestaltung/393570/393572-4.html', + 'only_matching': True, }] def _raise_unavailable(self, video_id): @@ -244,8 +255,9 @@ class LyndaIE(LyndaBaseIE): def _get_subtitles(self, video_id): url = 'https://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id subs = self._download_json(url, None, False) - if subs: - return {'en': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]} + fixed_subs = self._fix_subtitles(subs) + if fixed_subs: + return {'en': [{'ext': 'srt', 'data': fixed_subs}]} else: return {} @@ -256,7 +268,15 @@ class LyndaCourseIE(LyndaBaseIE): # Course link equals to welcome/introduction video link of same course # We will recognize it as course link - _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P[^/]+/[^/]+/(?P\d+))-\d\.html' + _VALID_URL = r'https?://(?:www|m)\.(?:lynda\.com|educourse\.ga)/(?P(?:[^/]+/){2,3}(?P\d+))-2\.html' + + _TESTS = [{ + 'url': 'https://www.lynda.com/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html', + 'only_matching': True, + }, { + 'url': 'https://www.lynda.com/de/Graphic-Design-tutorials/Grundlagen-guten-Gestaltung/393570-2.html', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) diff --git a/youtube_dl/extractor/mangomolo.py b/youtube_dl/extractor/mangomolo.py index dbd761a67..482175a34 100644 --- a/youtube_dl/extractor/mangomolo.py +++ b/youtube_dl/extractor/mangomolo.py @@ -1,13 +1,12 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 - from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote -from ..utils import ( - int_or_none, +from ..compat import ( + compat_b64decode, + compat_urllib_parse_unquote, ) +from ..utils import int_or_none class MangomoloBaseIE(InfoExtractor): @@ -51,4 +50,4 @@ class MangomoloLiveIE(MangomoloBaseIE): _IS_LIVE = True def _get_real_id(self, page_id): - return base64.b64decode(compat_urllib_parse_unquote(page_id).encode()).decode() + return compat_b64decode(compat_urllib_parse_unquote(page_id)).decode() diff --git a/youtube_dl/extractor/mediasite.py b/youtube_dl/extractor/mediasite.py new file mode 100644 index 000000000..0e2645c55 --- /dev/null +++ b/youtube_dl/extractor/mediasite.py @@ -0,0 +1,214 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urlparse, +) +from ..utils import ( + ExtractorError, + float_or_none, + mimetype2ext, + unescapeHTML, + unsmuggle_url, + urljoin, +) + + +class MediasiteIE(InfoExtractor): + _VALID_URL = r'(?xi)https?://[^/]+/Mediasite/Play/(?P[0-9a-f]{32,34})(?P\?[^#]+|)' + _TESTS = [ + { + 'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d', + 'info_dict': { + 'id': '2db6c271681e4f199af3c60d1f82869b1d', + 'ext': 'mp4', + 'title': 'Lecture: Tuesday, September 20, 2016 - Sir Andrew Wiles', + 'description': 'Sir Andrew Wiles: “Equations in arithmetic”\\n\\nI will describe some of the interactions between modern number theory and the problem of solving equations in rational numbers or integers\\u0027.', + 'timestamp': 1474268400.0, + 'upload_date': '20160919', + }, + }, + { + 'url': 'http://mediasite.uib.no/Mediasite/Play/90bb363295d945d6b548c867d01181361d?catalog=a452b7df-9ae1-46b7-a3ba-aceeb285f3eb', + 'info_dict': { + 'id': '90bb363295d945d6b548c867d01181361d', + 'ext': 'mp4', + 'upload_date': '20150429', + 'title': '5) IT-forum 2015-Dag 1 - Dungbeetle - How and why Rain created a tiny bug tracker for Unity', + 'timestamp': 1430311380.0, + }, + }, + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Play/585a43626e544bdd97aeb71a0ec907a01d', + 'md5': '481fda1c11f67588c0d9d8fbdced4e39', + 'info_dict': { + 'id': '585a43626e544bdd97aeb71a0ec907a01d', + 'ext': 'mp4', + 'title': 'Een nieuwe wereld: waarden, bewustzijn en techniek van de mensheid 2.0.', + 'description': '', + 'thumbnail': r're:^https?://.*\.jpg(?:\?.*)?$', + 'duration': 7713.088, + 'timestamp': 1413309600, + 'upload_date': '20141014', + }, + }, + { + 'url': 'https://collegerama.tudelft.nl/Mediasite/Play/86a9ea9f53e149079fbdb4202b521ed21d?catalog=fd32fd35-6c99-466c-89d4-cd3c431bc8a4', + 'md5': 'ef1fdded95bdf19b12c5999949419c92', + 'info_dict': { + 'id': '86a9ea9f53e149079fbdb4202b521ed21d', + 'ext': 'wmv', + 'title': '64ste Vakantiecursus: Afvalwater', + 'description': 'md5:7fd774865cc69d972f542b157c328305', + 'thumbnail': r're:^https?://.*\.jpg(?:\?.*?)?$', + 'duration': 10853, + 'timestamp': 1326446400, + 'upload_date': '20120113', + }, + }, + { + 'url': 'http://digitalops.sandia.gov/Mediasite/Play/24aace4429fc450fb5b38cdbf424a66e1d', + 'md5': '9422edc9b9a60151727e4b6d8bef393d', + 'info_dict': { + 'id': '24aace4429fc450fb5b38cdbf424a66e1d', + 'ext': 'mp4', + 'title': 'Xyce Software Training - Section 1', + 'description': r're:(?s)SAND Number: SAND 2013-7800.{200,}', + 'upload_date': '20120409', + 'timestamp': 1333983600, + 'duration': 7794, + } + } + ] + + # look in Mediasite.Core.js (Mediasite.ContentStreamType[*]) + _STREAM_TYPES = { + 0: 'video1', # the main video + 2: 'slide', + 3: 'presentation', + 4: 'video2', # screencast? + 5: 'video3', + } + + @staticmethod + def _extract_urls(webpage): + return [ + unescapeHTML(mobj.group('url')) + for mobj in re.finditer( + r'(?xi)]+\bsrc=(["\'])(?P(?:(?:https?:)?//[^/]+)?/Mediasite/Play/[0-9a-f]{32,34}(?:\?.*?)?)\1', + webpage)] + + def _real_extract(self, url): + url, data = unsmuggle_url(url, {}) + mobj = re.match(self._VALID_URL, url) + resource_id = mobj.group('id') + query = mobj.group('query') + + webpage, urlh = self._download_webpage_handle(url, resource_id) # XXX: add UrlReferrer? + redirect_url = compat_str(urlh.geturl()) + + # XXX: might have also extracted UrlReferrer and QueryString from the html + service_path = compat_urlparse.urljoin(redirect_url, self._html_search_regex( + r']+\bid=["\']ServicePath[^>]+>(.+?)', webpage, resource_id, + default='/Mediasite/PlayerService/PlayerService.svc/json')) + + player_options = self._download_json( + '%s/GetPlayerOptions' % service_path, resource_id, + headers={ + 'Content-type': 'application/json; charset=utf-8', + 'X-Requested-With': 'XMLHttpRequest', + }, + data=json.dumps({ + 'getPlayerOptionsRequest': { + 'ResourceId': resource_id, + 'QueryString': query, + 'UrlReferrer': data.get('UrlReferrer', ''), + 'UseScreenReader': False, + } + }).encode('utf-8'))['d'] + + presentation = player_options['Presentation'] + title = presentation['Title'] + + if presentation is None: + raise ExtractorError( + 'Mediasite says: %s' % player_options['PlayerPresentationStatusMessage'], + expected=True) + + thumbnails = [] + formats = [] + for snum, Stream in enumerate(presentation['Streams']): + stream_type = Stream.get('StreamType') + if stream_type is None: + continue + + video_urls = Stream.get('VideoUrls') + if not isinstance(video_urls, list): + video_urls = [] + + stream_id = self._STREAM_TYPES.get( + stream_type, 'type%u' % stream_type) + + stream_formats = [] + for unum, VideoUrl in enumerate(video_urls): + video_url = VideoUrl.get('Location') + if not video_url or not isinstance(video_url, compat_str): + continue + # XXX: if Stream.get('CanChangeScheme', False), switch scheme to HTTP/HTTPS + + media_type = VideoUrl.get('MediaType') + if media_type == 'SS': + stream_formats.extend(self._extract_ism_formats( + video_url, resource_id, + ism_id='%s-%u.%u' % (stream_id, snum, unum), + fatal=False)) + elif media_type == 'Dash': + stream_formats.extend(self._extract_mpd_formats( + video_url, resource_id, + mpd_id='%s-%u.%u' % (stream_id, snum, unum), + fatal=False)) + else: + stream_formats.append({ + 'format_id': '%s-%u.%u' % (stream_id, snum, unum), + 'url': video_url, + 'ext': mimetype2ext(VideoUrl.get('MimeType')), + }) + + # TODO: if Stream['HasSlideContent']: + # synthesise an MJPEG video stream '%s-%u.slides' % (stream_type, snum) + # from Stream['Slides'] + # this will require writing a custom downloader... + + # disprefer 'secondary' streams + if stream_type != 0: + for fmt in stream_formats: + fmt['preference'] = -1 + + thumbnail_url = Stream.get('ThumbnailUrl') + if thumbnail_url: + thumbnails.append({ + 'id': '%s-%u' % (stream_id, snum), + 'url': urljoin(redirect_url, thumbnail_url), + 'preference': -1 if stream_type != 0 else 0, + }) + formats.extend(stream_formats) + + self._sort_formats(formats) + + # XXX: Presentation['Presenters'] + # XXX: Presentation['Transcript'] + + return { + 'id': resource_id, + 'title': title, + 'description': presentation.get('Description'), + 'duration': float_or_none(presentation.get('Duration'), 1000), + 'timestamp': float_or_none(presentation.get('UnixTime'), 1000), + 'formats': formats, + 'thumbnails': thumbnails, + } diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index 964dc542c..42759eae8 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -1,13 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals +import json import uuid from .common import InfoExtractor from .ooyala import OoyalaIE from ..compat import ( compat_str, - compat_urllib_parse_urlencode, compat_urlparse, ) from ..utils import ( @@ -42,31 +42,33 @@ class MiTeleBaseIE(InfoExtractor): duration = int_or_none(mmc.get('duration')) for location in mmc['locations']: gat = self._proto_relative_url(location.get('gat'), 'http:') - bas = location.get('bas') - loc = location.get('loc') + gcp = location.get('gcp') ogn = location.get('ogn') - if None in (gat, bas, loc, ogn): + if None in (gat, gcp, ogn): continue token_data = { - 'bas': bas, - 'icd': loc, + 'gcp': gcp, 'ogn': ogn, - 'sta': '0', + 'sta': 0, } media = self._download_json( - '%s/?%s' % (gat, compat_urllib_parse_urlencode(token_data)), - video_id, 'Downloading %s JSON' % location['loc']) - file_ = media.get('file') - if not file_: + gat, video_id, data=json.dumps(token_data).encode('utf-8'), + headers={ + 'Content-Type': 'application/json;charset=utf-8', + 'Referer': url, + }) + stream = media.get('stream') or media.get('file') + if not stream: continue - ext = determine_ext(file_) + ext = determine_ext(stream) if ext == 'f4m': formats.extend(self._extract_f4m_formats( - file_ + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18', + stream + '&hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id, f4m_id='hds', fatal=False)) elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - file_, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) + stream, video_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 7b2bb6e20..a56b7690f 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,12 +1,12 @@ from __future__ import unicode_literals -import base64 import functools import itertools import re from .common import InfoExtractor from ..compat import ( + compat_b64decode, compat_chr, compat_ord, compat_str, @@ -79,7 +79,7 @@ class MixcloudIE(InfoExtractor): if encrypted_play_info is not None: # Decode - encrypted_play_info = base64.b64decode(encrypted_play_info) + encrypted_play_info = compat_b64decode(encrypted_play_info) else: # New path full_info_json = self._parse_json(self._html_search_regex( @@ -109,7 +109,7 @@ class MixcloudIE(InfoExtractor): kpa_target = encrypted_play_info else: kps = ['https://', 'http://'] - kpa_target = base64.b64decode(info_json['streamInfo']['url']) + kpa_target = compat_b64decode(info_json['streamInfo']['url']) for kp in kps: partial_key = self._decrypt_xor_cipher(kpa_target, kp) for quote in ["'", '"']: @@ -165,7 +165,7 @@ class MixcloudIE(InfoExtractor): format_url = stream_info.get(url_key) if not format_url: continue - decrypted = self._decrypt_xor_cipher(key, base64.b64decode(format_url)) + decrypted = self._decrypt_xor_cipher(key, compat_b64decode(format_url)) if not decrypted: continue if url_key == 'hlsUrl': diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py index 6fe3b6049..e24396e79 100644 --- a/youtube_dl/extractor/motherless.py +++ b/youtube_dl/extractor/motherless.py @@ -4,8 +4,11 @@ import datetime import re from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( ExtractorError, + InAdvancePagedList, + orderedSet, str_to_int, unified_strdate, ) @@ -114,3 +117,86 @@ class MotherlessIE(InfoExtractor): 'age_limit': age_limit, 'url': video_url, } + + +class MotherlessGroupIE(InfoExtractor): + _VALID_URL = 'https?://(?:www\.)?motherless\.com/gv?/(?P[a-z0-9_]+)' + _TESTS = [{ + 'url': 'http://motherless.com/g/movie_scenes', + 'info_dict': { + 'id': 'movie_scenes', + 'title': 'Movie Scenes', + 'description': 'Hot and sexy scenes from "regular" movies... ' + 'Beautiful actresses fully nude... A looot of ' + 'skin! :)Enjoy!', + }, + 'playlist_mincount': 662, + }, { + 'url': 'http://motherless.com/gv/sex_must_be_funny', + 'info_dict': { + 'id': 'sex_must_be_funny', + 'title': 'Sex must be funny', + 'description': 'Sex can be funny. Wide smiles,laugh, games, fun of ' + 'any kind!' + }, + 'playlist_mincount': 9, + }] + + @classmethod + def suitable(cls, url): + return (False if MotherlessIE.suitable(url) + else super(MotherlessGroupIE, cls).suitable(url)) + + def _extract_entries(self, webpage, base): + entries = [] + for mobj in re.finditer( + r'href="(?P/[^"]+)"[^>]*>(?:\s*]+alt="[^-]+-\s(?P[^"]+)")?', + webpage): + video_url = compat_urlparse.urljoin(base, mobj.group('href')) + if not MotherlessIE.suitable(video_url): + continue + video_id = MotherlessIE._match_id(video_url) + title = mobj.group('title') + entries.append(self.url_result( + video_url, ie=MotherlessIE.ie_key(), video_id=video_id, + video_title=title)) + # Alternative fallback + if not entries: + entries = [ + self.url_result( + compat_urlparse.urljoin(base, '/' + video_id), + ie=MotherlessIE.ie_key(), video_id=video_id) + for video_id in orderedSet(re.findall( + r'data-codename=["\']([A-Z0-9]+)', webpage))] + return entries + + def _real_extract(self, url): + group_id = self._match_id(url) + page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id) + webpage = self._download_webpage(page_url, group_id) + title = self._search_regex( + r'<title>([\w\s]+\w)\s+-', webpage, 'title', fatal=False) + description = self._html_search_meta( + 'description', webpage, fatal=False) + page_count = self._int(self._search_regex( + r'(\d+)</(?:a|span)><(?:a|span)[^>]+>\s*NEXT', + webpage, 'page_count'), 'page_count') + PAGE_SIZE = 80 + + def _get_page(idx): + webpage = self._download_webpage( + page_url, group_id, query={'page': idx + 1}, + note='Downloading page %d/%d' % (idx + 1, page_count) + ) + for entry in self._extract_entries(webpage, url): + yield entry + + playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE) + + return { + '_type': 'playlist', + 'id': group_id, + 'title': title, + 'description': description, + 'entries': playlist + } diff --git a/youtube_dl/extractor/ndr.py b/youtube_dl/extractor/ndr.py index 07528d140..aec2ea133 100644 --- a/youtube_dl/extractor/ndr.py +++ b/youtube_dl/extractor/ndr.py @@ -190,10 +190,12 @@ class NDREmbedBaseIE(InfoExtractor): ext = determine_ext(src, None) if ext == 'f4m': formats.extend(self._extract_f4m_formats( - src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, f4m_id='hds')) + src + '?hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, + f4m_id='hds', fatal=False)) elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - src, video_id, 'mp4', m3u8_id='hls', entry_protocol='m3u8_native')) + src, video_id, 'mp4', m3u8_id='hls', + entry_protocol='m3u8_native', fatal=False)) else: quality = f.get('quality') ff = { diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index 8e13bcf1f..5c8b37e18 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -19,11 +19,11 @@ from ..utils import ( class OdnoklassnikiIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?:www|m|mobile)\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)' + _VALID_URL = r'https?://(?:(?:www|m|mobile)\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer|live)/(?P<id>[\d-]+)' _TESTS = [{ # metadata in JSON 'url': 'http://ok.ru/video/20079905452', - 'md5': '6ba728d85d60aa2e6dd37c9e70fdc6bc', + 'md5': '0b62089b479e06681abaaca9d204f152', 'info_dict': { 'id': '20079905452', 'ext': 'mp4', @@ -35,7 +35,6 @@ class OdnoklassnikiIE(InfoExtractor): 'like_count': int, 'age_limit': 0, }, - 'skip': 'Video has been blocked', }, { # metadataUrl 'url': 'http://ok.ru/video/63567059965189-0?fromTime=5', @@ -99,6 +98,9 @@ class OdnoklassnikiIE(InfoExtractor): }, { 'url': 'http://mobile.ok.ru/video/20079905452', 'only_matching': True, + }, { + 'url': 'https://www.ok.ru/live/484531969818', + 'only_matching': True, }] def _real_extract(self, url): @@ -184,6 +186,10 @@ class OdnoklassnikiIE(InfoExtractor): }) return info + assert title + if provider == 'LIVE_TV_APP': + info['title'] = self._live_title(title) + quality = qualities(('4', '0', '1', '2', '3', '5')) formats = [{ @@ -210,6 +216,20 @@ class OdnoklassnikiIE(InfoExtractor): if fmt_type: fmt['quality'] = quality(fmt_type) + # Live formats + m3u8_url = metadata.get('hlsMasterPlaylistUrl') + if m3u8_url: + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8', + m3u8_id='hls', fatal=False)) + rtmp_url = metadata.get('rtmpUrl') + if rtmp_url: + formats.append({ + 'url': rtmp_url, + 'format_id': 'rtmp', + 'ext': 'flv', + }) + self._sort_formats(formats) info['formats'] = formats diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index 52580baed..ad8bf03f8 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -1,9 +1,13 @@ from __future__ import unicode_literals + import re -import base64 from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_b64decode, + compat_str, + compat_urllib_parse_urlencode, +) from ..utils import ( determine_ext, ExtractorError, @@ -12,7 +16,6 @@ from ..utils import ( try_get, unsmuggle_url, ) -from ..compat import compat_urllib_parse_urlencode class OoyalaBaseIE(InfoExtractor): @@ -44,7 +47,7 @@ class OoyalaBaseIE(InfoExtractor): url_data = try_get(stream, lambda x: x['url']['data'], compat_str) if not url_data: continue - s_url = base64.b64decode(url_data.encode('ascii')).decode('utf-8') + s_url = compat_b64decode(url_data).decode('utf-8') if not s_url or s_url in urls: continue urls.append(s_url) diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py index a99af12a4..eaaaf8a08 100644 --- a/youtube_dl/extractor/openload.py +++ b/youtube_dl/extractor/openload.py @@ -112,6 +112,8 @@ class PhantomJSwrapper(object): return get_exe_version('phantomjs', version_re=r'([0-9.]+)') def __init__(self, extractor, required_version=None, timeout=10000): + self._TMP_FILES = {} + self.exe = check_executable('phantomjs', ['-v']) if not self.exe: raise ExtractorError('PhantomJS executable not found in PATH, ' @@ -130,7 +132,6 @@ class PhantomJSwrapper(object): self.options = { 'timeout': timeout, } - self._TMP_FILES = {} for name in self._TMP_FILE_NAMES: tmp = tempfile.NamedTemporaryFile(delete=False) tmp.close() @@ -140,7 +141,7 @@ class PhantomJSwrapper(object): for name in self._TMP_FILE_NAMES: try: os.remove(self._TMP_FILES[name].name) - except (IOError, OSError): + except (IOError, OSError, KeyError): pass def _save_cookies(self, url): @@ -242,7 +243,7 @@ class PhantomJSwrapper(object): class OpenloadIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' + _VALID_URL = r'https?://(?:www\.)?(?:openload\.(?:co|io|link)|oload\.(?:tv|stream))/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)' _TESTS = [{ 'url': 'https://openload.co/f/kUEfGclsU9o', @@ -283,12 +284,20 @@ class OpenloadIE(InfoExtractor): # for title and ext 'url': 'https://openload.co/embed/Sxz5sADo82g/', 'only_matching': True, + }, { + # unavailable via https://openload.co/embed/e-Ixz9ZR5L0/ but available + # via https://openload.co/f/e-Ixz9ZR5L0/ + 'url': 'https://openload.co/f/e-Ixz9ZR5L0/', + 'only_matching': True, }, { 'url': 'https://oload.tv/embed/KnG-kKZdcfY/', 'only_matching': True, }, { 'url': 'http://www.openload.link/f/KnG-kKZdcfY', 'only_matching': True, + }, { + 'url': 'https://oload.stream/f/KnG-kKZdcfY', + 'only_matching': True, }] _USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36' @@ -301,20 +310,34 @@ class OpenloadIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - url = 'https://openload.co/embed/%s/' % video_id + url_pattern = 'https://openload.co/%%s/%s/' % video_id headers = { 'User-Agent': self._USER_AGENT, } - webpage = self._download_webpage(url, video_id, headers=headers) - - if 'File not found' in webpage or 'deleted by the owner' in webpage: - raise ExtractorError('File not found', expected=True, video_id=video_id) + for path in ('embed', 'f'): + page_url = url_pattern % path + last = path == 'f' + webpage = self._download_webpage( + page_url, video_id, 'Downloading %s webpage' % path, + headers=headers, fatal=last) + if not webpage: + continue + if 'File not found' in webpage or 'deleted by the owner' in webpage: + if not last: + continue + raise ExtractorError('File not found', expected=True, video_id=video_id) + break phantom = PhantomJSwrapper(self, required_version='2.0') - webpage, _ = phantom.get(url, html=webpage, video_id=video_id, headers=headers) + webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id, headers=headers) - decoded_id = get_element_by_id('streamurl', webpage) + decoded_id = (get_element_by_id('streamurl', webpage) or + get_element_by_id('streamuri', webpage) or + get_element_by_id('streamurj', webpage)) + + if not decoded_id: + raise ExtractorError('Can\'t find stream URL', video_id=video_id) video_url = 'https://openload.co/stream/%s?mime=true' % decoded_id @@ -323,7 +346,7 @@ class OpenloadIE(InfoExtractor): 'title', default=None) or self._html_search_meta( 'description', webpage, 'title', fatal=True) - entries = self._parse_html5_media_entries(url, webpage, video_id) + entries = self._parse_html5_media_entries(page_url, webpage, video_id) entry = entries[0] if entries else {} subtitles = entry.get('subtitles') diff --git a/youtube_dl/extractor/pandoratv.py b/youtube_dl/extractor/pandoratv.py index fc7bd3411..538738c09 100644 --- a/youtube_dl/extractor/pandoratv.py +++ b/youtube_dl/extractor/pandoratv.py @@ -1,6 +1,8 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..compat import ( compat_str, @@ -18,7 +20,14 @@ from ..utils import ( class PandoraTVIE(InfoExtractor): IE_NAME = 'pandora.tv' IE_DESC = '판도라TV' - _VALID_URL = r'https?://(?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?pandora\.tv/view/(?P<user_id>[^/]+)/(?P<id>\d+)| # new format + (?:.+?\.)?channel\.pandora\.tv/channel/video\.ptv\?| # old format + m\.pandora\.tv/?\? # mobile + ) + ''' _TESTS = [{ 'url': 'http://jp.channel.pandora.tv/channel/video.ptv?c1=&prgid=53294230&ch_userid=mikakim&ref=main&lot=cate_01_2', 'info_dict': { @@ -53,14 +62,25 @@ class PandoraTVIE(InfoExtractor): # Test metadata only 'skip_download': True, }, + }, { + 'url': 'http://www.pandora.tv/view/mikakim/53294230#36797454_new', + 'only_matching': True, + }, { + 'url': 'http://m.pandora.tv/?c=view&ch_userid=mikakim&prgid=54600346', + 'only_matching': True, }] def _real_extract(self, url): - qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - video_id = qs.get('prgid', [None])[0] - user_id = qs.get('ch_userid', [None])[0] - if any(not f for f in (video_id, user_id,)): - raise ExtractorError('Invalid URL', expected=True) + mobj = re.match(self._VALID_URL, url) + user_id = mobj.group('user_id') + video_id = mobj.group('id') + + if not user_id or not video_id: + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + video_id = qs.get('prgid', [None])[0] + user_id = qs.get('ch_userid', [None])[0] + if any(not f for f in (video_id, user_id,)): + raise ExtractorError('Invalid URL', expected=True) data = self._download_json( 'http://m.pandora.tv/?c=view&m=viewJsonApi&ch_userid=%s&prgid=%s' diff --git a/youtube_dl/extractor/playtvak.py b/youtube_dl/extractor/playtvak.py index 391e1bd09..4c5f57919 100644 --- a/youtube_dl/extractor/playtvak.py +++ b/youtube_dl/extractor/playtvak.py @@ -24,7 +24,7 @@ class PlaytvakIE(InfoExtractor): 'id': 'A150730_150323_hodinovy-manzel_kuko', 'ext': 'mp4', 'title': 'Vyžeňte vosy a sršně ze zahrady', - 'description': 'md5:f93d398691044d303bc4a3de62f3e976', + 'description': 'md5:4436e61b7df227a093778efb7e373571', 'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$', 'duration': 279, 'timestamp': 1438732860, @@ -36,9 +36,19 @@ class PlaytvakIE(InfoExtractor): 'info_dict': { 'id': 'A150624_164934_planespotting_cat', 'ext': 'flv', - 'title': 're:^Přímý přenos iDNES.cz [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'title': 're:^Planespotting [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'description': 'Sledujte provoz na ranveji Letiště Václava Havla v Praze', - 'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$', + 'is_live': True, + }, + 'params': { + 'skip_download': True, # requires rtmpdump + }, + }, { # another live stream, this one without Misc.videoFLV + 'url': 'https://slowtv.playtvak.cz/zive-sledujte-vlaky-v-primem-prenosu-dwi-/hlavni-nadrazi.aspx?c=A151218_145728_hlavni-nadrazi_plap', + 'info_dict': { + 'id': 'A151218_145728_hlavni-nadrazi_plap', + 'ext': 'flv', + 'title': 're:^Hlavní nádraží [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'is_live': True, }, 'params': { @@ -95,7 +105,7 @@ class PlaytvakIE(InfoExtractor): webpage = self._download_webpage(url, video_id) info_url = self._html_search_regex( - r'Misc\.videoFLV\(\s*{\s*data\s*:\s*"([^"]+)"', webpage, 'info url') + r'Misc\.video(?:FLV)?\(\s*{\s*data\s*:\s*"([^"]+)"', webpage, 'info url') parsed_url = compat_urlparse.urlparse(info_url) @@ -160,7 +170,7 @@ class PlaytvakIE(InfoExtractor): if is_live: title = self._live_title(title) description = self._og_search_description(webpage, default=None) or self._html_search_meta( - 'description', webpage, 'description') + 'description', webpage, 'description', default=None) timestamp = None duration = None if not is_live: diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py index 597b11218..aacc5d4bb 100644 --- a/youtube_dl/extractor/pluralsight.py +++ b/youtube_dl/extractor/pluralsight.py @@ -171,12 +171,12 @@ class PluralsightIE(PluralsightBaseIE): for num, current in enumerate(subs): current = subs[num] start, text = ( - float_or_none(dict_get(current, TIME_OFFSET_KEYS)), + float_or_none(dict_get(current, TIME_OFFSET_KEYS, skip_false_values=False)), dict_get(current, TEXT_KEYS)) if start is None or text is None: continue end = duration if num == len(subs) - 1 else float_or_none( - dict_get(subs[num + 1], TIME_OFFSET_KEYS)) + dict_get(subs[num + 1], TIME_OFFSET_KEYS, skip_false_values=False)) if end is None: continue srt += os.linesep.join( diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index d8a4bd244..48757fd4f 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -344,6 +344,8 @@ class ProSiebenSat1IE(ProSiebenSat1BaseIE): r'clip[iI]d=(\d+)', r'clip[iI]d\s*=\s*["\'](\d+)', r"'itemImageUrl'\s*:\s*'/dynamic/thumbnails/full/\d+/(\d+)", + r'proMamsId"\s*:\s*"(\d+)', + r'proMamsId"\s*:\s*"(\d+)', ] _TITLE_REGEXES = [ r'<h2 class="subtitle" itemprop="name">\s*(.+?)</h2>', diff --git a/youtube_dl/extractor/restudy.py b/youtube_dl/extractor/restudy.py index fd50065d4..d47fb45ca 100644 --- a/youtube_dl/extractor/restudy.py +++ b/youtube_dl/extractor/restudy.py @@ -5,8 +5,8 @@ from .common import InfoExtractor class RestudyIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?restudy\.dk/video/play/id/(?P<id>[0-9]+)' - _TEST = { + _VALID_URL = r'https?://(?:(?:www|portal)\.)?restudy\.dk/video/[^/]+/id/(?P<id>[0-9]+)' + _TESTS = [{ 'url': 'https://www.restudy.dk/video/play/id/1637', 'info_dict': { 'id': '1637', @@ -18,7 +18,10 @@ class RestudyIE(InfoExtractor): # rtmp download 'skip_download': True, } - } + }, { + 'url': 'https://portal.restudy.dk/video/leiden-frosteffekt/id/1637', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -29,7 +32,7 @@ class RestudyIE(InfoExtractor): description = self._og_search_description(webpage).strip() formats = self._extract_smil_formats( - 'https://www.restudy.dk/awsmedia/SmilDirectory/video_%s.xml' % video_id, + 'https://cdn.portal.restudy.dk/dynamic/themes/front/awsmedia/SmilDirectory/video_%s.xml' % video_id, video_id) self._sort_formats(formats) diff --git a/youtube_dl/extractor/ringtv.py b/youtube_dl/extractor/ringtv.py deleted file mode 100644 index 2c2c707bd..000000000 --- a/youtube_dl/extractor/ringtv.py +++ /dev/null @@ -1,44 +0,0 @@ -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor - - -class RingTVIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?ringtv\.craveonline\.com/(?P<type>news|videos/video)/(?P<id>[^/?#]+)' - _TEST = { - 'url': 'http://ringtv.craveonline.com/news/310833-luis-collazo-says-victor-ortiz-better-not-quit-on-jan-30', - 'md5': 'd25945f5df41cdca2d2587165ac28720', - 'info_dict': { - 'id': '857645', - 'ext': 'mp4', - 'title': 'Video: Luis Collazo says Victor Ortiz "better not quit on Jan. 30" - Ring TV', - 'description': 'Luis Collazo is excited about his Jan. 30 showdown with fellow former welterweight titleholder Victor Ortiz at Barclays Center in his hometown of Brooklyn. The SuperBowl week fight headlines a Golden Boy Live! card on Fox Sports 1.', - } - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id').split('-')[0] - webpage = self._download_webpage(url, video_id) - - if mobj.group('type') == 'news': - video_id = self._search_regex( - r'''(?x)<iframe[^>]+src="http://cms\.springboardplatform\.com/ - embed_iframe/[0-9]+/video/([0-9]+)/''', - webpage, 'real video ID') - title = self._og_search_title(webpage) - description = self._html_search_regex( - r'addthis:description="([^"]+)"', - webpage, 'description', fatal=False) - final_url = 'http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4' % video_id - thumbnail_url = 'http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg' % video_id - - return { - 'id': video_id, - 'url': final_url, - 'title': title, - 'thumbnail': thumbnail_url, - 'description': description, - } diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py index 666e90e90..18a327d81 100644 --- a/youtube_dl/extractor/rtl2.py +++ b/youtube_dl/extractor/rtl2.py @@ -1,12 +1,12 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import re from .common import InfoExtractor from ..aes import aes_cbc_decrypt from ..compat import ( + compat_b64decode, compat_ord, compat_str, ) @@ -142,11 +142,11 @@ class RTL2YouIE(RTL2YouBaseIE): stream_data = self._download_json( self._BACKWERK_BASE_URL + 'stream/video/' + video_id, video_id) - data, iv = base64.b64decode(stream_data['streamUrl']).decode().split(':') + data, iv = compat_b64decode(stream_data['streamUrl']).decode().split(':') stream_url = intlist_to_bytes(aes_cbc_decrypt( - bytes_to_intlist(base64.b64decode(data)), + bytes_to_intlist(compat_b64decode(data)), bytes_to_intlist(self._AES_KEY), - bytes_to_intlist(base64.b64decode(iv)) + bytes_to_intlist(compat_b64decode(iv)) )) if b'rtl2_you_video_not_found' in stream_url: raise ExtractorError('video not found', expected=True) diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index d9edf9da2..ce9db0629 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -7,6 +7,7 @@ import time from .common import InfoExtractor from ..compat import ( + compat_b64decode, compat_struct_unpack, ) from ..utils import ( @@ -21,7 +22,7 @@ from ..utils import ( def _decrypt_url(png): - encrypted_data = base64.b64decode(png.encode('utf-8')) + encrypted_data = compat_b64decode(png) text_index = encrypted_data.find(b'tEXt') text_chunk = encrypted_data[text_index - 4:] length = compat_struct_unpack('!I', text_chunk[:4])[0] @@ -31,6 +32,9 @@ def _decrypt_url(png): hash_index = data.index('#') alphabet_data = data[:hash_index] url_data = data[hash_index + 1:] + if url_data[0] == 'H' and url_data[3] == '%': + # remove useless HQ%% at the start + url_data = url_data[4:] alphabet = [] e = 0 diff --git a/youtube_dl/extractor/rtvs.py b/youtube_dl/extractor/rtvs.py new file mode 100644 index 000000000..6573b260d --- /dev/null +++ b/youtube_dl/extractor/rtvs.py @@ -0,0 +1,47 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class RTVSIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv/\d+/(?P<id>\d+)' + _TESTS = [{ + # radio archive + 'url': 'http://www.rtvs.sk/radio/archiv/11224/414872', + 'md5': '134d5d6debdeddf8a5d761cbc9edacb8', + 'info_dict': { + 'id': '414872', + 'ext': 'mp3', + 'title': 'Ostrov pokladov 1 časť.mp3' + }, + 'params': { + 'skip_download': True, + } + }, { + # tv archive + 'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118', + 'md5': '85e2c55cf988403b70cac24f5c086dc6', + 'info_dict': { + 'id': '63118', + 'ext': 'mp4', + 'title': 'Amaro Džives - Náš deň', + 'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.' + }, + 'params': { + 'skip_download': True, + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + playlist_url = self._search_regex( + r'playlist["\']?\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, + 'playlist url', group='url') + + data = self._download_json( + playlist_url, video_id, 'Downloading playlist')[0] + return self._parse_jwplayer_data(data, video_id=video_id) diff --git a/youtube_dl/extractor/sandia.py b/youtube_dl/extractor/sandia.py deleted file mode 100644 index 96e43af84..000000000 --- a/youtube_dl/extractor/sandia.py +++ /dev/null @@ -1,65 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import json - -from .common import InfoExtractor -from ..utils import ( - int_or_none, - mimetype2ext, -) - - -class SandiaIE(InfoExtractor): - IE_DESC = 'Sandia National Laboratories' - _VALID_URL = r'https?://digitalops\.sandia\.gov/Mediasite/Play/(?P<id>[0-9a-f]+)' - _TEST = { - 'url': 'http://digitalops.sandia.gov/Mediasite/Play/24aace4429fc450fb5b38cdbf424a66e1d', - 'md5': '9422edc9b9a60151727e4b6d8bef393d', - 'info_dict': { - 'id': '24aace4429fc450fb5b38cdbf424a66e1d', - 'ext': 'mp4', - 'title': 'Xyce Software Training - Section 1', - 'description': 're:(?s)SAND Number: SAND 2013-7800.{200,}', - 'upload_date': '20120409', - 'timestamp': 1333983600, - 'duration': 7794, - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - presentation_data = self._download_json( - 'http://digitalops.sandia.gov/Mediasite/PlayerService/PlayerService.svc/json/GetPlayerOptions', - video_id, data=json.dumps({ - 'getPlayerOptionsRequest': { - 'ResourceId': video_id, - 'QueryString': '', - } - }), headers={ - 'Content-Type': 'application/json; charset=utf-8', - })['d']['Presentation'] - - title = presentation_data['Title'] - - formats = [] - for stream in presentation_data.get('Streams', []): - for fd in stream.get('VideoUrls', []): - formats.append({ - 'format_id': fd['MediaType'], - 'format_note': fd['MimeType'].partition('/')[2], - 'ext': mimetype2ext(fd['MimeType']), - 'url': fd['Location'], - 'protocol': 'f4m' if fd['MimeType'] == 'video/x-mp4-fragmented' else None, - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': title, - 'description': presentation_data.get('Description'), - 'formats': formats, - 'timestamp': int_or_none(presentation_data.get('UnixTime'), 1000), - 'duration': int_or_none(presentation_data.get('Duration'), 1000), - } diff --git a/youtube_dl/extractor/sevenplus.py b/youtube_dl/extractor/sevenplus.py new file mode 100644 index 000000000..9792f820a --- /dev/null +++ b/youtube_dl/extractor/sevenplus.py @@ -0,0 +1,67 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .brightcove import BrightcoveNewIE +from ..utils import update_url_query + + +class SevenPlusIE(BrightcoveNewIE): + IE_NAME = '7plus' + _VALID_URL = r'https?://(?:www\.)?7plus\.com\.au/(?P<path>[^?]+\?.*?\bepisode-id=(?P<id>[^&#]+))' + _TESTS = [{ + 'url': 'https://7plus.com.au/BEAT?episode-id=BEAT-001', + 'info_dict': { + 'id': 'BEAT-001', + 'ext': 'mp4', + 'title': 'S1 E1 - Help / Lucy In The Sky With Diamonds', + 'description': 'md5:37718bea20a8eedaca7f7361af566131', + 'uploader_id': '5303576322001', + 'upload_date': '20171031', + 'timestamp': 1509440068, + }, + 'params': { + 'format': 'bestvideo', + 'skip_download': True, + } + }, { + 'url': 'https://7plus.com.au/UUUU?episode-id=AUMS43-001', + 'only_matching': True, + }] + + def _real_extract(self, url): + path, episode_id = re.match(self._VALID_URL, url).groups() + + media = self._download_json( + 'https://videoservice.swm.digital/playback', episode_id, query={ + 'appId': '7plus', + 'deviceType': 'web', + 'platformType': 'web', + 'accountId': 5303576322001, + 'referenceId': 'ref:' + episode_id, + 'deliveryId': 'csai', + 'videoType': 'vod', + })['media'] + + for source in media.get('sources', {}): + src = source.get('src') + if not src: + continue + source['src'] = update_url_query(src, {'rule': ''}) + + info = self._parse_brightcove_metadata(media, episode_id) + + content = self._download_json( + 'https://component-cdn.swm.digital/content/' + path, + episode_id, headers={ + 'market-id': 4, + }, fatal=False) or {} + for item in content.get('items', {}): + if item.get('componentData', {}).get('componentType') == 'infoPanel': + for src_key, dst_key in [('title', 'title'), ('shortSynopsis', 'description')]: + value = item.get(src_key) + if value: + info[dst_key] = value + + return info diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 89e19e927..b2250afdd 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -1,8 +1,7 @@ from __future__ import unicode_literals -import base64 - from .common import InfoExtractor +from ..compat import compat_b64decode from ..utils import ( ExtractorError, int_or_none, @@ -22,8 +21,8 @@ class SharedBaseIE(InfoExtractor): video_url = self._extract_video_url(webpage, video_id, url) - title = base64.b64decode(self._html_search_meta( - 'full:title', webpage, 'title').encode('utf-8')).decode('utf-8') + title = compat_b64decode(self._html_search_meta( + 'full:title', webpage, 'title')).decode('utf-8') filesize = int_or_none(self._html_search_meta( 'full:size', webpage, 'file size', fatal=False)) @@ -92,5 +91,4 @@ class VivoIE(SharedBaseIE): r'InitializeStream\s*\(\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, 'stream', group='url'), video_id, - transform_source=lambda x: base64.b64decode( - x.encode('ascii')).decode('utf-8'))[0] + transform_source=lambda x: compat_b64decode(x).decode('utf-8'))[0] diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py index 7145d285a..6fc2ff60d 100644 --- a/youtube_dl/extractor/slutload.py +++ b/youtube_dl/extractor/slutload.py @@ -1,11 +1,13 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor class SlutloadIE(InfoExtractor): _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$' - _TEST = { + _TESTS = [{ 'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/', 'md5': '868309628ba00fd488cf516a113fd717', 'info_dict': { @@ -15,11 +17,17 @@ class SlutloadIE(InfoExtractor): 'age_limit': 18, 'thumbnail': r're:https?://.*?\.jpg' } - } + }, { + # mobile site + 'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + + desktop_url = re.sub(r'^(https?://)mobile\.', r'\1', url) + webpage = self._download_webpage(desktop_url, video_id) video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>', webpage, 'title').strip() diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 8894f4b0c..97ff422f0 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -136,9 +136,28 @@ class SoundcloudIE(InfoExtractor): 'license': 'all-rights-reserved', }, }, + # no album art, use avatar pic for thumbnail + { + 'url': 'https://soundcloud.com/garyvee/sideways-prod-mad-real', + 'md5': '59c7872bc44e5d99b7211891664760c2', + 'info_dict': { + 'id': '309699954', + 'ext': 'mp3', + 'title': 'Sideways (Prod. Mad Real)', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'uploader': 'garyvee', + 'upload_date': '20170226', + 'duration': 207, + 'thumbnail': r're:https?://.*\.jpg', + 'license': 'all-rights-reserved', + }, + 'params': { + 'skip_download': True, + }, + }, ] - _CLIENT_ID = 'c6CU49JDMapyrQo06UxU9xouB9ZVzqCn' + _CLIENT_ID = 'DQskPX1pntALRzMp4HSxya3Mc0AO66Ro' _IPHONE_CLIENT_ID = '376f225bf427445fc4bfb6b99b72e0bf' @staticmethod @@ -160,7 +179,7 @@ class SoundcloudIE(InfoExtractor): name = full_title or track_id if quiet: self.report_extraction(name) - thumbnail = info.get('artwork_url') + thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url') if isinstance(thumbnail, compat_str): thumbnail = thumbnail.replace('-large', '-t500x500') ext = 'mp3' diff --git a/youtube_dl/extractor/southpark.py b/youtube_dl/extractor/southpark.py index d8ce416fc..da75a43a7 100644 --- a/youtube_dl/extractor/southpark.py +++ b/youtube_dl/extractor/southpark.py @@ -6,7 +6,7 @@ from .mtv import MTVServicesInfoExtractor class SouthParkIE(MTVServicesInfoExtractor): IE_NAME = 'southpark.cc.com' - _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))' + _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))' _FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss' @@ -20,6 +20,9 @@ class SouthParkIE(MTVServicesInfoExtractor): 'timestamp': 1112760000, 'upload_date': '20050406', }, + }, { + 'url': 'http://southpark.cc.com/collections/7758/fan-favorites/1', + 'only_matching': True, }] @@ -41,7 +44,7 @@ class SouthParkEsIE(SouthParkIE): class SouthParkDeIE(SouthParkIE): IE_NAME = 'southpark.de' - _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden)/(?P<id>.+?)(\?|#|$))' + _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden|collections)/(?P<id>.+?)(\?|#|$))' _FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/' _TESTS = [{ @@ -70,12 +73,15 @@ class SouthParkDeIE(SouthParkIE): 'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.', }, 'playlist_count': 3, + }, { + 'url': 'http://www.southpark.de/collections/2476/superhero-showdown/1', + 'only_matching': True, }] class SouthParkNlIE(SouthParkIE): IE_NAME = 'southpark.nl' - _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|(?:full-)?episodes)/(?P<id>.+?)(\?|#|$))' + _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.nl/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))' _FEED_URL = 'http://www.southpark.nl/feeds/video-player/mrss/' _TESTS = [{ @@ -90,7 +96,7 @@ class SouthParkNlIE(SouthParkIE): class SouthParkDkIE(SouthParkIE): IE_NAME = 'southparkstudios.dk' - _VALID_URL = r'https?://(?:www\.)?(?P<url>southparkstudios\.dk/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))' + _VALID_URL = r'https?://(?:www\.)?(?P<url>southparkstudios\.(?:dk|nu)/(?:clips|full-episodes|collections)/(?P<id>.+?)(\?|#|$))' _FEED_URL = 'http://www.southparkstudios.dk/feeds/video-player/mrss/' _TESTS = [{ @@ -100,4 +106,10 @@ class SouthParkDkIE(SouthParkIE): 'description': 'Butters is convinced he\'s living in a virtual reality.', }, 'playlist_mincount': 3, + }, { + 'url': 'http://www.southparkstudios.dk/collections/2476/superhero-showdown/1', + 'only_matching': True, + }, { + 'url': 'http://www.southparkstudios.nu/collections/2476/superhero-showdown/1', + 'only_matching': True, }] diff --git a/youtube_dl/extractor/spiegel.py b/youtube_dl/extractor/spiegel.py index 84298fee4..fc995e8c1 100644 --- a/youtube_dl/extractor/spiegel.py +++ b/youtube_dl/extractor/spiegel.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from .nexx import NexxEmbedIE +from .nexx import ( + NexxIE, + NexxEmbedIE, +) from .spiegeltv import SpiegeltvIE from ..compat import compat_urlparse from ..utils import ( @@ -51,6 +54,10 @@ class SpiegelIE(InfoExtractor): }, { 'url': 'http://www.spiegel.de/video/astronaut-alexander-gerst-von-der-iss-station-beantwortet-fragen-video-1519126-iframe.html', 'only_matching': True, + }, { + # nexx video + 'url': 'http://www.spiegel.de/video/spiegel-tv-magazin-ueber-guellekrise-in-schleswig-holstein-video-99012776.html', + 'only_matching': True, }] def _real_extract(self, url): @@ -61,6 +68,14 @@ class SpiegelIE(InfoExtractor): if SpiegeltvIE.suitable(handle.geturl()): return self.url_result(handle.geturl(), 'Spiegeltv') + nexx_id = self._search_regex( + r'nexxOmniaId\s*:\s*(\d+)', webpage, 'nexx id', default=None) + if nexx_id: + domain_id = NexxIE._extract_domain_id(webpage) or '748' + return self.url_result( + 'nexx:%s:%s' % (domain_id, nexx_id), ie=NexxIE.ie_key(), + video_id=nexx_id) + video_data = extract_attributes(self._search_regex(r'(<div[^>]+id="spVideoElements"[^>]+>)', webpage, 'video element', default='')) title = video_data.get('data-video-title') or get_element_by_attribute('class', 'module-title', webpage) diff --git a/youtube_dl/extractor/sportschau.py b/youtube_dl/extractor/sportschau.py deleted file mode 100644 index 0d7925a08..000000000 --- a/youtube_dl/extractor/sportschau.py +++ /dev/null @@ -1,38 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -from .wdr import WDRBaseIE -from ..utils import get_element_by_attribute - - -class SportschauIE(WDRBaseIE): - IE_NAME = 'Sportschau' - _VALID_URL = r'https?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video-?(?P<id>[^/#?]+)\.html' - _TEST = { - 'url': 'http://www.sportschau.de/uefaeuro2016/videos/video-dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100.html', - 'info_dict': { - 'id': 'mdb-1140188', - 'display_id': 'dfb-team-geht-gut-gelaunt-ins-spiel-gegen-polen-100', - 'ext': 'mp4', - 'title': 'DFB-Team geht gut gelaunt ins Spiel gegen Polen', - 'description': 'Vor dem zweiten Gruppenspiel gegen Polen herrscht gute Stimmung im deutschen Team. Insbesondere Bastian Schweinsteiger strotzt vor Optimismus nach seinem Tor gegen die Ukraine.', - 'upload_date': '20160615', - }, - 'skip': 'Geo-restricted to Germany', - } - - def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - title = get_element_by_attribute('class', 'headline', webpage) - description = self._html_search_meta('description', webpage, 'description') - - info = self._extract_wdr_video(webpage, video_id) - - info.update({ - 'title': title, - 'description': description, - }) - - return info diff --git a/youtube_dl/extractor/springboardplatform.py b/youtube_dl/extractor/springboardplatform.py new file mode 100644 index 000000000..07d99b579 --- /dev/null +++ b/youtube_dl/extractor/springboardplatform.py @@ -0,0 +1,125 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + int_or_none, + xpath_attr, + xpath_text, + xpath_element, + unescapeHTML, + unified_timestamp, +) + + +class SpringboardPlatformIE(InfoExtractor): + _VALID_URL = r'''(?x) + https?:// + cms\.springboardplatform\.com/ + (?: + (?:previews|embed_iframe)/(?P<index>\d+)/video/(?P<id>\d+)| + xml_feeds_advanced/index/(?P<index_2>\d+)/rss3/(?P<id_2>\d+) + ) + ''' + _TESTS = [{ + 'url': 'http://cms.springboardplatform.com/previews/159/video/981017/0/0/1', + 'md5': '5c3cb7b5c55740d482561099e920f192', + 'info_dict': { + 'id': '981017', + 'ext': 'mp4', + 'title': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX', + 'description': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX', + 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1409132328, + 'upload_date': '20140827', + 'duration': 193, + }, + }, { + 'url': 'http://cms.springboardplatform.com/embed_iframe/159/video/981017/rab007/rapbasement.com/1/1', + 'only_matching': True, + }, { + 'url': 'http://cms.springboardplatform.com/embed_iframe/20/video/1731611/ki055/kidzworld.com/10', + 'only_matching': True, + }, { + 'url': 'http://cms.springboardplatform.com/xml_feeds_advanced/index/159/rss3/981017/0/0/1/', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return [ + mobj.group('url') + for mobj in re.finditer( + r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cms\.springboardplatform\.com/embed_iframe/\d+/video/\d+.*?)\1', + webpage)] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') or mobj.group('id_2') + index = mobj.group('index') or mobj.group('index_2') + + video = self._download_xml( + 'http://cms.springboardplatform.com/xml_feeds_advanced/index/%s/rss3/%s' + % (index, video_id), video_id) + + item = xpath_element(video, './/item', 'item', fatal=True) + + content = xpath_element( + item, './{http://search.yahoo.com/mrss/}content', 'content', + fatal=True) + title = unescapeHTML(xpath_text(item, './title', 'title', fatal=True)) + + video_url = content.attrib['url'] + + if 'error_video.mp4' in video_url: + raise ExtractorError( + 'Video %s no longer exists' % video_id, expected=True) + + duration = int_or_none(content.get('duration')) + tbr = int_or_none(content.get('bitrate')) + filesize = int_or_none(content.get('fileSize')) + width = int_or_none(content.get('width')) + height = int_or_none(content.get('height')) + + description = unescapeHTML(xpath_text( + item, './description', 'description')) + thumbnail = xpath_attr( + item, './{http://search.yahoo.com/mrss/}thumbnail', 'url', + 'thumbnail') + + timestamp = unified_timestamp(xpath_text( + item, './{http://cms.springboardplatform.com/namespaces.html}created', + 'timestamp')) + + formats = [{ + 'url': video_url, + 'format_id': 'http', + 'tbr': tbr, + 'filesize': filesize, + 'width': width, + 'height': height, + }] + + m3u8_format = formats[0].copy() + m3u8_format.update({ + 'url': re.sub(r'(https?://)cdn\.', r'\1hls.', video_url) + '.m3u8', + 'ext': 'mp4', + 'format_id': 'hls', + 'protocol': 'm3u8_native', + }) + formats.append(m3u8_format) + + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/tbs.py b/youtube_dl/extractor/tbs.py index eab22c38f..edc31729d 100644 --- a/youtube_dl/extractor/tbs.py +++ b/youtube_dl/extractor/tbs.py @@ -58,7 +58,7 @@ class TBSIE(TurnerBaseIE): continue if stream_data.get('playlistProtection') == 'spe': m3u8_url = self._add_akamai_spe_token( - 'http://www.%s.com/service/token_spe' % site, + 'http://token.vgtf.net/token/token_spe', m3u8_url, media_id, { 'url': url, 'site_name': site[:3].upper(), diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index 75346393b..9056c8cbc 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -1,18 +1,20 @@ # coding: utf-8 from __future__ import unicode_literals -import base64 import binascii import re import json from .common import InfoExtractor +from ..compat import ( + compat_b64decode, + compat_ord, +) from ..utils import ( ExtractorError, qualities, determine_ext, ) -from ..compat import compat_ord class TeamcocoIE(InfoExtractor): @@ -97,7 +99,7 @@ class TeamcocoIE(InfoExtractor): for i in range(len(cur_fragments)): cur_sequence = (''.join(cur_fragments[i:] + cur_fragments[:i])).encode('ascii') try: - raw_data = base64.b64decode(cur_sequence) + raw_data = compat_b64decode(cur_sequence) if compat_ord(raw_data[0]) == compat_ord('{'): return json.loads(raw_data.decode('utf-8')) except (TypeError, binascii.Error, UnicodeDecodeError, ValueError): diff --git a/youtube_dl/extractor/thesixtyone.py b/youtube_dl/extractor/thesixtyone.py deleted file mode 100644 index d63aef5de..000000000 --- a/youtube_dl/extractor/thesixtyone.py +++ /dev/null @@ -1,106 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -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]+)/?$''' - _SONG_URL_TEMPLATE = 'http://thesixtyone.com/s/{0:}' - _SONG_FILE_URL_TEMPLATE = 'http://{audio_server:}/thesixtyone_production/audio/{0:}_stream' - _THUMBNAIL_URL_TEMPLATE = '{photo_base_url:}_desktop' - _TESTS = [ - { - 'url': 'http://www.thesixtyone.com/s/SrE3zD7s1jt/', - 'md5': '821cc43b0530d3222e3e2b70bb4622ea', - 'info_dict': { - 'id': 'SrE3zD7s1jt', - 'ext': 'mp3', - 'title': 'CASIO - Unicorn War Mixtape', - 'thumbnail': 're:^https?://.*_desktop$', - '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, - }, - { - 'url': 'http://www.thesixtyone.com/maryatmidnight/song/StrawberriesandCream/yvWtLp0c4GQ/', - '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): - song_id = self._match_id(url) - - webpage = self._download_webpage( - self._SONG_URL_TEMPLATE.format(song_id), song_id) - - song_data = self._parse_json(self._search_regex( - r'"%s":\s(\{.*?\})' % song_id, webpage, 'song_data'), song_id) - - if self._search_regex(r'(t61\.s3_audio_load\s*=\s*1\.0;)', webpage, 's3_audio_load marker', default=None): - song_data['audio_server'] = 's3.amazonaws.com' - else: - song_data['audio_server'] = song_data['audio_server'] + '.thesixtyone.com' - - 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/tutv.py b/youtube_dl/extractor/tutv.py index 822372ea1..362318b24 100644 --- a/youtube_dl/extractor/tutv.py +++ b/youtube_dl/extractor/tutv.py @@ -1,9 +1,10 @@ from __future__ import unicode_literals -import base64 - from .common import InfoExtractor -from ..compat import compat_parse_qs +from ..compat import ( + compat_b64decode, + compat_parse_qs, +) class TutvIE(InfoExtractor): @@ -26,7 +27,7 @@ class TutvIE(InfoExtractor): data_content = self._download_webpage( 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info') - video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0].encode('utf-8')).decode('utf-8') + video_url = compat_b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8') return { 'id': internal_id, diff --git a/youtube_dl/extractor/tvplay.py b/youtube_dl/extractor/tvplay.py index 46132eda1..84597b55e 100644 --- a/youtube_dl/extractor/tvplay.py +++ b/youtube_dl/extractor/tvplay.py @@ -273,6 +273,8 @@ class TVPlayIE(InfoExtractor): 'ext': ext, } if video_url.startswith('rtmp'): + if smuggled_data.get('skip_rtmp'): + continue m = re.search( r'^(?P<url>rtmp://[^/]+/(?P<app>[^/]+))/(?P<playpath>.+)$', video_url) if not m: @@ -434,6 +436,10 @@ class ViafreeIE(InfoExtractor): return self.url_result( smuggle_url( 'mtg:%s' % video_id, - {'geo_countries': [ - compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]]}), + { + 'geo_countries': [ + compat_urlparse.urlparse(url).netloc.rsplit('.', 1)[-1]], + # rtmp host mtgfs.fplive.net for viafree is unresolvable + 'skip_rtmp': True, + }), ie=TVPlayIE.ie_key(), video_id=video_id) diff --git a/youtube_dl/extractor/twentythreevideo.py b/youtube_dl/extractor/twentythreevideo.py new file mode 100644 index 000000000..aa0c6e90f --- /dev/null +++ b/youtube_dl/extractor/twentythreevideo.py @@ -0,0 +1,77 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import int_or_none + + +class TwentyThreeVideoIE(InfoExtractor): + IE_NAME = '23video' + _VALID_URL = r'https?://video\.(?P<domain>twentythree\.net|23video\.com|filmweb\.no)/v\.ihtml/player\.html\?(?P<query>.*?\bphoto(?:_|%5f)id=(?P<id>\d+).*)' + _TEST = { + 'url': 'https://video.twentythree.net/v.ihtml/player.html?showDescriptions=0&source=site&photo%5fid=20448876&autoPlay=1', + 'md5': '75fcf216303eb1dae9920d651f85ced4', + 'info_dict': { + 'id': '20448876', + 'ext': 'mp4', + 'title': 'Video Marketing Minute: Personalized Video', + 'timestamp': 1513855354, + 'upload_date': '20171221', + 'uploader_id': '12258964', + 'uploader': 'Rasmus Bysted', + } + } + + def _real_extract(self, url): + domain, query, photo_id = re.match(self._VALID_URL, url).groups() + base_url = 'https://video.%s' % domain + photo_data = self._download_json( + base_url + '/api/photo/list?' + query, photo_id, query={ + 'format': 'json', + }, transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'photo data'))['photo'] + title = photo_data['title'] + + formats = [] + + audio_path = photo_data.get('audio_download') + if audio_path: + formats.append({ + 'format_id': 'audio', + 'url': base_url + audio_path, + 'filesize': int_or_none(photo_data.get('audio_size')), + 'vcodec': 'none', + }) + + def add_common_info_to_list(l, template, id_field, id_value): + f_base = template % id_value + f_path = photo_data.get(f_base + 'download') + if not f_path: + return + l.append({ + id_field: id_value, + 'url': base_url + f_path, + 'width': int_or_none(photo_data.get(f_base + 'width')), + 'height': int_or_none(photo_data.get(f_base + 'height')), + 'filesize': int_or_none(photo_data.get(f_base + 'size')), + }) + + for f in ('mobile_high', 'medium', 'hd', '1080p', '4k'): + add_common_info_to_list(formats, 'video_%s_', 'format_id', f) + + thumbnails = [] + for t in ('quad16', 'quad50', 'quad75', 'quad100', 'small', 'portrait', 'standard', 'medium', 'large', 'original'): + add_common_info_to_list(thumbnails, '%s_', 'id', t) + + return { + 'id': photo_id, + 'title': title, + 'timestamp': int_or_none(photo_data.get('creation_date_epoch')), + 'duration': int_or_none(photo_data.get('video_length')), + 'view_count': int_or_none(photo_data.get('view_count')), + 'comment_count': int_or_none(photo_data.get('number_of_comments')), + 'uploader_id': photo_data.get('user_id'), + 'uploader': photo_data.get('display_name'), + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py index bf57eac01..1981b4d4a 100644 --- a/youtube_dl/extractor/twitch.py +++ b/youtube_dl/extractor/twitch.py @@ -85,10 +85,15 @@ class TwitchBaseIE(InfoExtractor): if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: response = self._parse_json( e.cause.read().decode('utf-8'), None) - fail(response['message']) + fail(response.get('message') or response['errors'][0]) raise - redirect_url = urljoin(post_url, response['redirect']) + if 'Authenticated successfully' in response.get('message', ''): + return None, None + + redirect_url = urljoin( + post_url, + response.get('redirect') or response['redirect_path']) return self._download_webpage_handle( redirect_url, None, 'Downloading login redirect page', headers=headers) @@ -106,6 +111,10 @@ class TwitchBaseIE(InfoExtractor): 'password': password, }) + # Successful login + if not redirect_page: + return + if re.search(r'(?i)<form[^>]+id="two-factor-submit"', redirect_page) is not None: # TODO: Add mechanism to request an SMS or phone call tfa_token = self._get_tfa_info('two-factor authentication token') @@ -358,9 +367,16 @@ class TwitchPlaylistBaseIE(TwitchBaseIE): break offset += limit return self.playlist_result( - [self.url_result(entry) for entry in orderedSet(entries)], + [self._make_url_result(entry) for entry in orderedSet(entries)], channel_id, channel_name) + def _make_url_result(self, url): + try: + video_id = 'v%s' % TwitchVodIE._match_id(url) + return self.url_result(url, TwitchVodIE.ie_key(), video_id=video_id) + except AssertionError: + return self.url_result(url) + def _extract_playlist_page(self, response): videos = response.get('videos') return [video['url'] for video in videos] if videos else [] diff --git a/youtube_dl/extractor/ufctv.py b/youtube_dl/extractor/ufctv.py new file mode 100644 index 000000000..ab823814b --- /dev/null +++ b/youtube_dl/extractor/ufctv.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, +) + + +class UFCTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?ufc\.tv/video/(?P<id>[^/]+)' + _TEST = { + 'url': 'https://www.ufc.tv/video/ufc-219-countdown-full-episode', + 'info_dict': { + 'id': '34167', + 'ext': 'mp4', + 'title': 'UFC 219 Countdown: Full Episode', + 'description': 'md5:26d4e8bf4665ae5878842d7050c3c646', + 'timestamp': 1513962360, + 'upload_date': '20171222', + }, + 'params': { + # m3u8 download + 'skip_download': True, + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + video_data = self._download_json(url, display_id, query={ + 'format': 'json', + }) + video_id = str(video_data['id']) + title = video_data['name'] + m3u8_url = self._download_json( + 'https://www.ufc.tv/service/publishpoint', video_id, query={ + 'type': 'video', + 'format': 'json', + 'id': video_id, + }, headers={ + 'User-Agent': 'Mozilla/5.0 (iPhone; CPU iPhone OS 11_0_1 like Mac OS X) AppleWebKit/604.1.38 (KHTML, like Gecko) Version/11.0 Mobile/15A402 Safari/604.1', + })['path'] + m3u8_url = m3u8_url.replace('_iphone.', '.') + formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4') + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'description': video_data.get('description'), + 'duration': parse_duration(video_data.get('runtime')), + 'timestamp': parse_iso8601(video_data.get('releaseDate')), + 'formats': formats, + } diff --git a/youtube_dl/extractor/umg.py b/youtube_dl/extractor/umg.py new file mode 100644 index 000000000..d815cd9a6 --- /dev/null +++ b/youtube_dl/extractor/umg.py @@ -0,0 +1,103 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_filesize, + parse_iso8601, +) + + +class UMGDeIE(InfoExtractor): + IE_NAME = 'umg:de' + IE_DESC = 'Universal Music Deutschland' + _VALID_URL = r'https?://(?:www\.)?universal-music\.de/[^/]+/videos/[^/?#]+-(?P<id>\d+)' + _TEST = { + 'url': 'https://www.universal-music.de/sido/videos/jedes-wort-ist-gold-wert-457803', + 'md5': 'ebd90f48c80dcc82f77251eb1902634f', + 'info_dict': { + 'id': '457803', + 'ext': 'mp4', + 'title': 'Jedes Wort ist Gold wert', + 'timestamp': 1513591800, + 'upload_date': '20171218', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + video_data = self._download_json( + 'https://api.universal-music.de/graphql', + video_id, query={ + 'query': '''{ + universalMusic(channel:16) { + video(id:%s) { + headline + formats { + formatId + url + type + width + height + mimeType + fileSize + } + duration + createdDate + } + } +}''' % video_id})['data']['universalMusic']['video'] + + title = video_data['headline'] + hls_url_template = 'http://mediadelivery.universal-music-services.de/vod/mp4:autofill/storage/' + '/'.join(list(video_id)) + '/content/%s/file/playlist.m3u8' + + thumbnails = [] + formats = [] + + def add_m3u8_format(format_id): + m3u8_formats = self._extract_m3u8_formats( + hls_url_template % format_id, video_id, 'mp4', + 'm3u8_native', m3u8_id='hls', fatal='False') + if m3u8_formats and m3u8_formats[0].get('height'): + formats.extend(m3u8_formats) + + for f in video_data.get('formats', []): + f_url = f.get('url') + mime_type = f.get('mimeType') + if not f_url or mime_type == 'application/mxf': + continue + fmt = { + 'url': f_url, + 'width': int_or_none(f.get('width')), + 'height': int_or_none(f.get('height')), + 'filesize': parse_filesize(f.get('fileSize')), + } + f_type = f.get('type') + if f_type == 'Image': + thumbnails.append(fmt) + elif f_type == 'Video': + format_id = f.get('formatId') + if format_id: + fmt['format_id'] = format_id + if mime_type == 'video/mp4': + add_m3u8_format(format_id) + urlh = self._request_webpage(f_url, video_id, fatal=False) + if urlh: + first_byte = urlh.read(1) + if first_byte not in (b'F', b'\x00'): + continue + formats.append(fmt) + if not formats: + for format_id in (867, 836, 940): + add_m3u8_format(format_id) + self._sort_formats(formats, ('width', 'height', 'filesize', 'tbr')) + + return { + 'id': video_id, + 'title': title, + 'duration': int_or_none(video_data.get('duration')), + 'timestamp': parse_iso8601(video_data.get('createdDate'), ' '), + 'thumbnails': thumbnails, + 'formats': formats, + } diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index cedb54876..6af705657 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -468,11 +468,12 @@ class VimeoIE(VimeoBaseInfoExtractor): request = sanitized_Request(url, headers=headers) try: webpage, urlh = self._download_webpage_handle(request, video_id) + redirect_url = compat_str(urlh.geturl()) # Some URLs redirect to ondemand can't be extracted with # this extractor right away thus should be passed through # ondemand extractor (e.g. https://vimeo.com/73445910) - if VimeoOndemandIE.suitable(urlh.geturl()): - return self.url_result(urlh.geturl(), VimeoOndemandIE.ie_key()) + if VimeoOndemandIE.suitable(redirect_url): + return self.url_result(redirect_url, VimeoOndemandIE.ie_key()) except ExtractorError as ee: if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: errmsg = ee.cause.read() @@ -541,15 +542,15 @@ class VimeoIE(VimeoBaseInfoExtractor): if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None: if '_video_password_verified' in data: raise ExtractorError('video password verification failed!') - self._verify_video_password(url, video_id, webpage) + self._verify_video_password(redirect_url, video_id, webpage) return self._real_extract( - smuggle_url(url, {'_video_password_verified': 'verified'})) + smuggle_url(redirect_url, {'_video_password_verified': 'verified'})) else: raise ExtractorError('Unable to extract info section', cause=e) else: if config.get('view') == 4: - config = self._verify_player_video_password(url, video_id) + config = self._verify_player_video_password(redirect_url, video_id) def is_rented(): if '>You rented this title.<' in webpage: diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index d4838b3e5..b8ea50362 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -318,9 +318,14 @@ class VKIE(VKBaseIE): 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.', expected=True) + ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.' + 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.', + ERROR_COPYRIGHT, + + r'>The video .*? was removed from public access by request of the copyright holder.<': + ERROR_COPYRIGHT, r'<!>Please log in or <': 'Video %s is only available for registered users, ' diff --git a/youtube_dl/extractor/voot.py b/youtube_dl/extractor/voot.py index 426754489..751b21ee5 100644 --- a/youtube_dl/extractor/voot.py +++ b/youtube_dl/extractor/voot.py @@ -16,7 +16,7 @@ class VootIE(InfoExtractor): _TESTS = [{ 'url': 'https://www.voot.com/shows/ishq-ka-rang-safed/1/360558/is-this-the-end-of-kamini-/441353', 'info_dict': { - 'id': '441353', + 'id': '0_8ledb18o', 'ext': 'mp4', 'title': 'Ishq Ka Rang Safed - Season 01 - Episode 340', 'description': 'md5:06291fbbbc4dcbe21235c40c262507c1', @@ -59,9 +59,10 @@ class VootIE(InfoExtractor): media = media_info['assets'] + entry_id = media['EntryId'] title = media['MediaName'] formats = self._extract_m3u8_formats( - 'https://cdnapisec.kaltura.com/p/1982551/playManifest/pt/https/f/applehttp/t/web/e/' + media['EntryId'], + 'https://cdnapisec.kaltura.com/p/1982551/playManifest/pt/https/f/applehttp/t/web/e/' + entry_id, video_id, 'mp4', m3u8_id='hls') self._sort_formats(formats) @@ -83,7 +84,8 @@ class VootIE(InfoExtractor): episode_number = int_or_none(value) return { - 'id': video_id, + 'extractor_key': 'Kaltura', + 'id': entry_id, 'title': title, 'description': description, 'series': series, diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py index 621de1e1e..cf6f7c7ed 100644 --- a/youtube_dl/extractor/wdr.py +++ b/youtube_dl/extractor/wdr.py @@ -4,49 +4,50 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urlparse, +) from ..utils import ( determine_ext, ExtractorError, js_to_json, strip_jsonp, + try_get, unified_strdate, update_url_query, urlhandle_detect_ext, ) -class WDRBaseIE(InfoExtractor): - def _extract_wdr_video(self, webpage, display_id): - # for wdr.de the data-extension is in a tag with the class "mediaLink" - # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn" - # for wdrmaus, in a tag with the class "videoButton" (previously a link - # to the page in a multiline "videoLink"-tag) - json_metadata = self._html_search_regex( - r'''(?sx)class= - (?: - (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+| - (["\'])videoLink\b.*?\2[\s]*>\n[^\n]* - )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3 - ''', - webpage, 'media link', default=None, group='data') +class WDRIE(InfoExtractor): + _VALID_URL = r'https?://deviceids-medp\.wdr\.de/ondemand/\d+/(?P<id>\d+)\.js' + _GEO_COUNTRIES = ['DE'] + _TEST = { + 'url': 'http://deviceids-medp.wdr.de/ondemand/155/1557833.js', + 'info_dict': { + 'id': 'mdb-1557833', + 'ext': 'mp4', + 'title': 'Biathlon-Staffel verpasst Podest bei Olympia-Generalprobe', + 'upload_date': '20180112', + }, + } - if not json_metadata: - return - - media_link_obj = self._parse_json(json_metadata, display_id, - transform_source=js_to_json) - jsonp_url = media_link_obj['mediaObj']['url'] + def _real_extract(self, url): + video_id = self._match_id(url) metadata = self._download_json( - jsonp_url, display_id, transform_source=strip_jsonp) + url, video_id, transform_source=strip_jsonp) - metadata_tracker_data = metadata['trackerData'] - metadata_media_resource = metadata['mediaResource'] + is_live = metadata.get('mediaType') == 'live' + + tracker_data = metadata['trackerData'] + media_resource = metadata['mediaResource'] formats = [] # check if the metadata contains a direct URL to a file - for kind, media_resource in metadata_media_resource.items(): + for kind, media_resource in media_resource.items(): if kind not in ('dflt', 'alt'): continue @@ -57,13 +58,13 @@ class WDRBaseIE(InfoExtractor): ext = determine_ext(medium_url) if ext == 'm3u8': formats.extend(self._extract_m3u8_formats( - medium_url, display_id, 'mp4', 'm3u8_native', + medium_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls')) elif ext == 'f4m': manifest_url = update_url_query( medium_url, {'hdcore': '3.2.0', 'plugin': 'aasp-3.2.0.77.18'}) formats.extend(self._extract_f4m_formats( - manifest_url, display_id, f4m_id='hds', fatal=False)) + manifest_url, video_id, f4m_id='hds', fatal=False)) elif ext == 'smil': formats.extend(self._extract_smil_formats( medium_url, 'stream', fatal=False)) @@ -73,7 +74,7 @@ class WDRBaseIE(InfoExtractor): } if ext == 'unknown_video': urlh = self._request_webpage( - medium_url, display_id, note='Determining extension') + medium_url, video_id, note='Determining extension') ext = urlhandle_detect_ext(urlh) a_format['ext'] = ext formats.append(a_format) @@ -81,30 +82,30 @@ class WDRBaseIE(InfoExtractor): self._sort_formats(formats) subtitles = {} - caption_url = metadata_media_resource.get('captionURL') + caption_url = media_resource.get('captionURL') if caption_url: subtitles['de'] = [{ 'url': caption_url, 'ext': 'ttml', }] - title = metadata_tracker_data['trackerClipTitle'] + title = tracker_data['trackerClipTitle'] return { - 'id': metadata_tracker_data.get('trackerClipId', display_id), - 'display_id': display_id, - 'title': title, - 'alt_title': metadata_tracker_data.get('trackerClipSubcategory'), + 'id': tracker_data.get('trackerClipId', video_id), + 'title': self._live_title(title) if is_live else title, + 'alt_title': tracker_data.get('trackerClipSubcategory'), 'formats': formats, 'subtitles': subtitles, - 'upload_date': unified_strdate(metadata_tracker_data.get('trackerClipAirTime')), + 'upload_date': unified_strdate(tracker_data.get('trackerClipAirTime')), + 'is_live': is_live, } -class WDRIE(WDRBaseIE): +class WDRPageIE(InfoExtractor): _CURRENT_MAUS_URL = r'https?://(?:www\.)wdrmaus.de/(?:[^/]+/){1,2}[^/?#]+\.php5' - _PAGE_REGEX = r'/(?:mediathek/)?[^/]+/(?P<type>[^/]+)/(?P<display_id>.+)\.html' - _VALID_URL = r'(?P<page_url>https?://(?:www\d\.)?wdr\d?\.de)' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL + _PAGE_REGEX = r'/(?:mediathek/)?(?:[^/]+/)*(?P<display_id>[^/]+)\.html' + _VALID_URL = r'https?://(?:www\d?\.)?(?:wdr\d?|sportschau)\.de' + _PAGE_REGEX + '|' + _CURRENT_MAUS_URL _TESTS = [ { @@ -124,6 +125,7 @@ class WDRIE(WDRBaseIE): 'ext': 'ttml', }]}, }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://www1.wdr.de/mediathek/audio/wdr3/wdr3-gespraech-am-samstag/audio-schriftstellerin-juli-zeh-100.html', @@ -139,19 +141,17 @@ class WDRIE(WDRBaseIE): 'is_live': False, 'subtitles': {} }, + 'skip': 'HTTP Error 404: Not Found', }, { 'url': 'http://www1.wdr.de/mediathek/video/live/index.html', 'info_dict': { - 'id': 'mdb-103364', + 'id': 'mdb-1406149', 'ext': 'mp4', - 'display_id': 'index', - 'title': r're:^WDR Fernsehen im Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'title': r're:^WDR Fernsehen im Livestream \(nur in Deutschland erreichbar\) [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'alt_title': 'WDR Fernsehen Live', - 'upload_date': None, - 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9', + 'upload_date': '20150101', 'is_live': True, - 'subtitles': {} }, 'params': { 'skip_download': True, # m3u8 download @@ -159,19 +159,18 @@ class WDRIE(WDRBaseIE): }, { 'url': 'http://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html', - 'playlist_mincount': 8, + 'playlist_mincount': 7, 'info_dict': { - 'id': 'aktuelle-stunde/aktuelle-stunde-120', + 'id': 'aktuelle-stunde-120', }, }, { 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5', 'info_dict': { - 'id': 'mdb-1323501', + 'id': 'mdb-1552552', 'ext': 'mp4', 'upload_date': 're:^[0-9]{8}$', 'title': 're:^Die Sendung mit der Maus vom [0-9.]{10}$', - 'description': 'Die Seite mit der Maus -', }, 'skip': 'The id changes from week to week because of the new episode' }, @@ -183,7 +182,6 @@ class WDRIE(WDRBaseIE): 'ext': 'mp4', 'upload_date': '20130919', 'title': 'Sachgeschichte - Achterbahn ', - 'description': 'Die Seite mit der Maus -', }, }, { @@ -191,52 +189,114 @@ class WDRIE(WDRBaseIE): # Live stream, MD5 unstable 'info_dict': { 'id': 'mdb-869971', - 'ext': 'flv', - 'title': 'COSMO Livestream', - 'description': 'md5:2309992a6716c347891c045be50992e4', + 'ext': 'mp4', + 'title': r're:^COSMO Livestream [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'upload_date': '20160101', }, + 'params': { + 'skip_download': True, # m3u8 download + } + }, + { + 'url': 'http://www.sportschau.de/handballem2018/handball-nationalmannschaft-em-stolperstein-vorrunde-100.html', + 'info_dict': { + 'id': 'mdb-1556012', + 'ext': 'mp4', + 'title': 'DHB-Vizepräsident Bob Hanning - "Die Weltspitze ist extrem breit"', + 'upload_date': '20180111', + }, + 'params': { + 'skip_download': True, + }, + }, + { + 'url': 'http://www.sportschau.de/handballem2018/audio-vorschau---die-handball-em-startet-mit-grossem-favoritenfeld-100.html', + 'only_matching': True, } ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - url_type = mobj.group('type') - page_url = mobj.group('page_url') display_id = mobj.group('display_id') webpage = self._download_webpage(url, display_id) - info_dict = self._extract_wdr_video(webpage, display_id) + entries = [] - if not info_dict: + # Article with several videos + + # for wdr.de the data-extension is in a tag with the class "mediaLink" + # for wdr.de radio players, in a tag with the class "wdrrPlayerPlayBtn" + # for wdrmaus, in a tag with the class "videoButton" (previously a link + # to the page in a multiline "videoLink"-tag) + for mobj in re.finditer( + r'''(?sx)class= + (?: + (["\'])(?:mediaLink|wdrrPlayerPlayBtn|videoButton)\b.*?\1[^>]+| + (["\'])videoLink\b.*?\2[\s]*>\n[^\n]* + )data-extension=(["\'])(?P<data>(?:(?!\3).)+)\3 + ''', webpage): + media_link_obj = self._parse_json( + mobj.group('data'), display_id, transform_source=js_to_json, + fatal=False) + if not media_link_obj: + continue + jsonp_url = try_get( + media_link_obj, lambda x: x['mediaObj']['url'], compat_str) + if jsonp_url: + entries.append(self.url_result(jsonp_url, ie=WDRIE.ie_key())) + + # Playlist (e.g. https://www1.wdr.de/mediathek/video/sendungen/aktuelle-stunde/aktuelle-stunde-120.html) + if not entries: entries = [ - self.url_result(page_url + href[0], 'WDR') - for href in re.findall( - r'<a href="(%s)"[^>]+data-extension=' % self._PAGE_REGEX, - webpage) + self.url_result( + compat_urlparse.urljoin(url, mobj.group('href')), + ie=WDRPageIE.ie_key()) + for mobj in re.finditer( + r'<a[^>]+\bhref=(["\'])(?P<href>(?:(?!\1).)+)\1[^>]+\bdata-extension=', + webpage) if re.match(self._PAGE_REGEX, mobj.group('href')) ] - if entries: # Playlist page - return self.playlist_result(entries, playlist_id=display_id) + return self.playlist_result(entries, playlist_id=display_id) - raise ExtractorError('No downloadable streams found', expected=True) - is_live = url_type == 'live' +class WDRElefantIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)wdrmaus\.de/elefantenseite/#(?P<id>.+)' + _TEST = { + 'url': 'http://www.wdrmaus.de/elefantenseite/#folge_ostern_2015', + 'info_dict': { + 'title': 'Folge Oster-Spezial 2015', + 'id': 'mdb-1088195', + 'ext': 'mp4', + 'age_limit': None, + 'upload_date': '20150406' + }, + 'params': { + 'skip_download': True, + }, + } - if is_live: - info_dict.update({ - 'title': self._live_title(info_dict['title']), - 'upload_date': None, - }) - elif 'upload_date' not in info_dict: - info_dict['upload_date'] = unified_strdate(self._html_search_meta('DC.Date', webpage, 'upload date')) + def _real_extract(self, url): + display_id = self._match_id(url) - info_dict.update({ - 'description': self._html_search_meta('Description', webpage), - 'is_live': is_live, - }) - - return info_dict + # Table of Contents seems to always be at this address, so fetch it directly. + # The website fetches configurationJS.php5, which links to tableOfContentsJS.php5. + table_of_contents = self._download_json( + 'https://www.wdrmaus.de/elefantenseite/data/tableOfContentsJS.php5', + display_id) + if display_id not in table_of_contents: + raise ExtractorError( + 'No entry in site\'s table of contents for this URL. ' + 'Is the fragment part of the URL (after the #) correct?', + expected=True) + xml_metadata_path = table_of_contents[display_id]['xmlPath'] + xml_metadata = self._download_xml( + 'https://www.wdrmaus.de/elefantenseite/' + xml_metadata_path, + display_id) + zmdb_url_element = xml_metadata.find('./movie/zmdb_url') + if zmdb_url_element is None: + raise ExtractorError( + '%s is not a video' % display_id, expected=True) + return self.url_result(zmdb_url_element.text, ie=WDRIE.ie_key()) class WDRMobileIE(InfoExtractor): diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py new file mode 100644 index 000000000..3cb4d71a6 --- /dev/null +++ b/youtube_dl/extractor/weibo.py @@ -0,0 +1,140 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + +import json +import random +import re + +from ..compat import ( + compat_parse_qs, + compat_str, +) +from ..utils import ( + js_to_json, + strip_jsonp, + urlencode_postdata, +) + + +class WeiboIE(InfoExtractor): + _VALID_URL = r'https?://weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)' + _TEST = { + 'url': 'https://weibo.com/6275294458/Fp6RGfbff?type=comment', + 'info_dict': { + 'id': 'Fp6RGfbff', + 'ext': 'mp4', + 'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + # to get Referer url for genvisitor + webpage, urlh = self._download_webpage_handle(url, video_id) + + visitor_url = urlh.geturl() + + if 'passport.weibo.com' in visitor_url: + # first visit + visitor_data = self._download_json( + 'https://passport.weibo.com/visitor/genvisitor', video_id, + note='Generating first-visit data', + transform_source=strip_jsonp, + headers={'Referer': visitor_url}, + data=urlencode_postdata({ + 'cb': 'gen_callback', + 'fp': json.dumps({ + 'os': '2', + 'browser': 'Gecko57,0,0,0', + 'fonts': 'undefined', + 'screenInfo': '1440*900*24', + 'plugins': '', + }), + })) + + tid = visitor_data['data']['tid'] + cnfd = '%03d' % visitor_data['data']['confidence'] + + self._download_webpage( + 'https://passport.weibo.com/visitor/visitor', video_id, + note='Running first-visit callback', + query={ + 'a': 'incarnate', + 't': tid, + 'w': 2, + 'c': cnfd, + 'cb': 'cross_domain', + 'from': 'weibo', + '_rand': random.random(), + }) + + webpage = self._download_webpage( + url, video_id, note='Revisiting webpage') + + title = self._html_search_regex( + r'<title>(.+?)', webpage, 'title') + + video_formats = compat_parse_qs(self._search_regex( + r'video-sources=\\\"(.+?)\"', webpage, 'video_sources')) + + formats = [] + supported_resolutions = (480, 720) + for res in supported_resolutions: + vid_urls = video_formats.get(compat_str(res)) + if not vid_urls or not isinstance(vid_urls, list): + continue + + vid_url = vid_urls[0] + formats.append({ + 'url': vid_url, + 'height': res, + }) + + self._sort_formats(formats) + + uploader = self._og_search_property( + 'nick-name', webpage, 'uploader', default=None) + + return { + 'id': video_id, + 'title': title, + 'uploader': uploader, + 'formats': formats + } + + +class WeiboMobileIE(InfoExtractor): + _VALID_URL = r'https?://m\.weibo\.cn/status/(?P[0-9]+)(\?.+)?' + _TEST = { + 'url': 'https://m.weibo.cn/status/4189191225395228?wm=3333_2001&sourcetype=weixin&featurecode=newtitle&from=singlemessage&isappinstalled=0', + 'info_dict': { + 'id': '4189191225395228', + 'ext': 'mp4', + 'title': '午睡当然是要甜甜蜜蜜的啦', + 'uploader': '柴犬柴犬' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + # to get Referer url for genvisitor + webpage = self._download_webpage(url, video_id, note='visit the page') + + weibo_info = self._parse_json(self._search_regex( + r'var\s+\$render_data\s*=\s*\[({.*})\]\[0\]\s*\|\|\s*{};', + webpage, 'js_code', flags=re.DOTALL), + video_id, transform_source=js_to_json) + + status_data = weibo_info.get('status', {}) + page_info = status_data.get('page_info') + title = status_data['status_title'] + uploader = status_data.get('user', {}).get('screen_name') + + return { + 'id': video_id, + 'title': title, + 'uploader': uploader, + 'url': page_info['media_info']['stream_url'] + } diff --git a/youtube_dl/extractor/ximalaya.py b/youtube_dl/extractor/ximalaya.py new file mode 100644 index 000000000..a912e54b8 --- /dev/null +++ b/youtube_dl/extractor/ximalaya.py @@ -0,0 +1,233 @@ +# coding: utf-8 + +from __future__ import unicode_literals + +import itertools +import re + +from .common import InfoExtractor + + +class XimalayaBaseIE(InfoExtractor): + _GEO_COUNTRIES = ['CN'] + + +class XimalayaIE(XimalayaBaseIE): + IE_NAME = 'ximalaya' + IE_DESC = '喜马拉雅FM' + _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?P[0-9]+)/sound/(?P[0-9]+)' + _USER_URL_FORMAT = '%s://www.ximalaya.com/zhubo/%i/' + _TESTS = [ + { + 'url': 'http://www.ximalaya.com/61425525/sound/47740352/', + 'info_dict': { + 'id': '47740352', + 'ext': 'm4a', + 'uploader': '小彬彬爱听书', + 'uploader_id': 61425525, + 'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/', + 'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白', + 'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。", + 'thumbnails': [ + { + 'name': 'cover_url', + 'url': r're:^https?://.*\.jpg$', + }, + { + 'name': 'cover_url_142', + 'url': r're:^https?://.*\.jpg$', + 'width': 180, + 'height': 180 + } + ], + 'categories': ['renwen', '人文'], + 'duration': 93, + 'view_count': int, + 'like_count': int, + } + }, + { + 'url': 'http://m.ximalaya.com/61425525/sound/47740352/', + 'info_dict': { + 'id': '47740352', + 'ext': 'm4a', + 'uploader': '小彬彬爱听书', + 'uploader_id': 61425525, + 'uploader_url': 'http://www.ximalaya.com/zhubo/61425525/', + 'title': '261.唐诗三百首.卷八.送孟浩然之广陵.李白', + 'description': "contains:《送孟浩然之广陵》\n作者：李白\n故人西辞黄鹤楼，烟花三月下扬州。\n孤帆远影碧空尽，惟见长江天际流。", + 'thumbnails': [ + { + 'name': 'cover_url', + 'url': r're:^https?://.*\.jpg$', + }, + { + 'name': 'cover_url_142', + 'url': r're:^https?://.*\.jpg$', + 'width': 180, + 'height': 180 + } + ], + 'categories': ['renwen', '人文'], + 'duration': 93, + 'view_count': int, + 'like_count': int, + } + }, + { + 'url': 'https://www.ximalaya.com/11045267/sound/15705996/', + 'info_dict': { + 'id': '15705996', + 'ext': 'm4a', + 'uploader': '李延隆老师', + 'uploader_id': 11045267, + 'uploader_url': 'https://www.ximalaya.com/zhubo/11045267/', + 'title': 'Lesson 1 Excuse me!', + 'description': "contains:Listen to the tape then answer\xa0this question. Whose handbag is it?\n" + "听录音，然后回答问题，这是谁的手袋？", + 'thumbnails': [ + { + 'name': 'cover_url', + 'url': r're:^https?://.*\.jpg$', + }, + { + 'name': 'cover_url_142', + 'url': r're:^https?://.*\.jpg$', + 'width': 180, + 'height': 180 + } + ], + 'categories': ['train', '外语'], + 'duration': 40, + 'view_count': int, + 'like_count': int, + } + }, + ] + + def _real_extract(self, url): + + is_m = 'm.ximalaya' in url + scheme = 'https' if url.startswith('https') else 'http' + + audio_id = self._match_id(url) + webpage = self._download_webpage(url, audio_id, + note='Download sound page for %s' % audio_id, + errnote='Unable to get sound page') + + audio_info_file = '%s://m.ximalaya.com/tracks/%s.json' % (scheme, audio_id) + audio_info = self._download_json(audio_info_file, audio_id, + 'Downloading info json %s' % audio_info_file, + 'Unable to download info file') + + formats = [] + for bps, k in (('24k', 'play_path_32'), ('64k', 'play_path_64')): + if audio_info.get(k): + formats.append({ + 'format_id': bps, + 'url': audio_info[k], + }) + + thumbnails = [] + for k in audio_info.keys(): + # cover pics kyes like: cover_url', 'cover_url_142' + if k.startswith('cover_url'): + thumbnail = {'name': k, 'url': audio_info[k]} + if k == 'cover_url_142': + thumbnail['width'] = 180 + thumbnail['height'] = 180 + thumbnails.append(thumbnail) + + audio_uploader_id = audio_info.get('uid') + + if is_m: + audio_description = self._html_search_regex(r'(?s)]+>(.+?)', + webpage, 'audio_description', fatal=False) + else: + audio_description = self._html_search_regex(r'(?s)]*>(.+?)', + webpage, 'audio_description', fatal=False) + + if not audio_description: + audio_description_file = '%s://www.ximalaya.com/sounds/%s/rich_intro' % (scheme, audio_id) + audio_description = self._download_webpage(audio_description_file, audio_id, + note='Downloading description file %s' % audio_description_file, + errnote='Unable to download descrip file', + fatal=False) + audio_description = audio_description.strip() if audio_description else None + + return { + 'id': audio_id, + 'uploader': audio_info.get('nickname'), + 'uploader_id': audio_uploader_id, + 'uploader_url': self._USER_URL_FORMAT % (scheme, audio_uploader_id) if audio_uploader_id else None, + 'title': audio_info['title'], + 'thumbnails': thumbnails, + 'description': audio_description, + 'categories': list(filter(None, (audio_info.get('category_name'), audio_info.get('category_title')))), + 'duration': audio_info.get('duration'), + 'view_count': audio_info.get('play_count'), + 'like_count': audio_info.get('favorites_count'), + 'formats': formats, + } + + +class XimalayaAlbumIE(XimalayaBaseIE): + IE_NAME = 'ximalaya:album' + IE_DESC = '喜马拉雅FM 专辑' + _VALID_URL = r'https?://(?:www\.|m\.)?ximalaya\.com/(?P[0-9]+)/album/(?P[0-9]+)' + _TEMPLATE_URL = '%s://www.ximalaya.com/%s/album/%s/' + _BASE_URL_TEMPL = '%s://www.ximalaya.com%s' + _LIST_VIDEO_RE = r']+?href="(?P/%s/sound/(?P\d+)/?)"[^>]+?title="(?P[^>]+)">' + _TESTS = [{ + 'url': 'http://www.ximalaya.com/61425525/album/5534601/', + 'info_dict': { + 'title': '唐诗三百首（含赏析）', + 'id': '5534601', + }, + 'playlist_count': 312, + }, { + 'url': 'http://m.ximalaya.com/61425525/album/5534601', + 'info_dict': { + 'title': '唐诗三百首（含赏析）', + 'id': '5534601', + }, + 'playlist_count': 312, + }, + ] + + def _real_extract(self, url): + self.scheme = scheme = 'https' if url.startswith('https') else 'http' + + mobj = re.match(self._VALID_URL, url) + uid, playlist_id = mobj.group('uid'), mobj.group('id') + + webpage = self._download_webpage(self._TEMPLATE_URL % (scheme, uid, playlist_id), playlist_id, + note='Download album page for %s' % playlist_id, + errnote='Unable to get album info') + + title = self._html_search_regex(r'detailContent_title[^>]*><h1(?:[^>]+)?>([^<]+)</h1>', + webpage, 'title', fatal=False) + + return self.playlist_result(self._entries(webpage, playlist_id, uid), playlist_id, title) + + def _entries(self, page, playlist_id, uid): + html = page + for page_num in itertools.count(1): + for entry in self._process_page(html, uid): + yield entry + + next_url = self._search_regex(r'<a\s+href=(["\'])(?P<more>[\S]+)\1[^>]+rel=(["\'])next\3', + html, 'list_next_url', default=None, group='more') + if not next_url: + break + + next_full_url = self._BASE_URL_TEMPL % (self.scheme, next_url) + html = self._download_webpage(next_full_url, playlist_id) + + def _process_page(self, html, uid): + find_from = html.index('album_soundlist') + for mobj in re.finditer(self._LIST_VIDEO_RE % uid, html[find_from:]): + yield self.url_result(self._BASE_URL_TEMPL % (self.scheme, mobj.group('url')), + XimalayaIE.ie_key(), + mobj.group('id'), + mobj.group('title')) diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index f0ba01197..5b0b248cd 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -154,7 +154,7 @@ class YoukuIE(InfoExtractor): # request basic data basic_data_params = { 'vid': video_id, - 'ccode': '0501', + 'ccode': '0507', 'client_ip': '192.168.1.1', 'utid': cna, 'client_ts': time.time() / 1000, @@ -241,13 +241,23 @@ class YoukuShowIE(InfoExtractor): # Ongoing playlist. The initial page is the last one 'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html', 'only_matching': True, + }, { + # No data-id value. + 'url': 'http://list.youku.com/show/id_zefbfbd61237fefbfbdef.html', + 'only_matching': True, + }, { + # Wrong number of reload_id. + 'url': 'http://list.youku.com/show/id_z20eb4acaf5c211e3b2ad.html', + 'only_matching': True, }] def _extract_entries(self, playlist_data_url, show_id, note, query): query['callback'] = 'cb' playlist_data = self._download_json( playlist_data_url, show_id, query=query, note=note, - transform_source=lambda s: js_to_json(strip_jsonp(s)))['html'] + transform_source=lambda s: js_to_json(strip_jsonp(s))).get('html') + if playlist_data is None: + return [None, None] drama_list = (get_element_by_class('p-drama-grid', playlist_data) or get_element_by_class('p-drama-half-row', playlist_data)) if drama_list is None: @@ -276,9 +286,9 @@ class YoukuShowIE(InfoExtractor): r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id') # The first reload_id has the same items as first_page reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page) + entries.extend(initial_entries) for idx, reload_id in enumerate(reload_ids): if reload_id == first_page_reload_id: - entries.extend(initial_entries) continue _, new_entries = self._extract_entries( 'http://list.youku.com/show/episode', show_id, @@ -287,8 +297,8 @@ class YoukuShowIE(InfoExtractor): 'id': page_config['showid'], 'stage': reload_id, }) - entries.extend(new_entries) - + if new_entries is not None: + entries.extend(new_entries) desc = self._html_search_meta('description', webpage, fatal=False) playlist_title = desc.split(',')[0] if desc else None detail_li = get_element_by_class('p-intro', webpage) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 0919bef0e..f698a5627 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1810,7 +1810,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): 'url': video_info['conn'][0], 'player_url': player_url, }] - elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: + elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): 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) @@ -2530,10 +2530,11 @@ class YoutubeLiveIE(YoutubeBaseInfoExtractor): webpage = self._download_webpage(url, channel_id, fatal=False) if webpage: page_type = self._og_search_property( - 'type', webpage, 'page type', default=None) + 'type', webpage, 'page type', default='') video_id = self._html_search_meta( 'videoId', webpage, 'video id', default=None) - if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id): + if page_type.startswith('video') and video_id and re.match( + r'^[0-9A-Za-z_-]{11}$', video_id): return self.url_result(video_id, YoutubeIE.ie_key()) return self.url_result(base_url) diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index 2843a3dc0..2fe9cf585 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -39,6 +39,7 @@ from .compat import ( compat_HTMLParser, compat_basestring, compat_chr, + compat_ctypes_WINFUNCTYPE, compat_etree_fromstring, compat_expanduser, compat_html_entities, @@ -1330,24 +1331,24 @@ def _windows_write_string(s, out): if fileno not in WIN_OUTPUT_IDS: return False - GetStdHandle = ctypes.WINFUNCTYPE( + GetStdHandle = compat_ctypes_WINFUNCTYPE( ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)( - (b'GetStdHandle', ctypes.windll.kernel32)) + ('GetStdHandle', ctypes.windll.kernel32)) h = GetStdHandle(WIN_OUTPUT_IDS[fileno]) - WriteConsoleW = ctypes.WINFUNCTYPE( + WriteConsoleW = compat_ctypes_WINFUNCTYPE( ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR, ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD), - ctypes.wintypes.LPVOID)((b'WriteConsoleW', ctypes.windll.kernel32)) + ctypes.wintypes.LPVOID)(('WriteConsoleW', ctypes.windll.kernel32)) written = ctypes.wintypes.DWORD(0) - GetFileType = ctypes.WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)((b'GetFileType', ctypes.windll.kernel32)) + GetFileType = compat_ctypes_WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)(('GetFileType', ctypes.windll.kernel32)) FILE_TYPE_CHAR = 0x0002 FILE_TYPE_REMOTE = 0x8000 - GetConsoleMode = ctypes.WINFUNCTYPE( + GetConsoleMode = compat_ctypes_WINFUNCTYPE( ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.POINTER(ctypes.wintypes.DWORD))( - (b'GetConsoleMode', ctypes.windll.kernel32)) + ('GetConsoleMode', ctypes.windll.kernel32)) INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value def not_a_console(handle): @@ -2266,7 +2267,7 @@ def js_to_json(code): "(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"| '(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'| {comment}|,(?={skip}[\]}}])| - [a-zA-Z_][.a-zA-Z_0-9]*| + (?:(?<![0-9])[eE]|[a-df-zA-DF-Z_])[.a-zA-Z_0-9]*| \b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?| [0-9]+(?={skip}:) '''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 2b5a63464..11e82f433 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2017.12.14' +__version__ = '2018.01.21'