diff --git a/AUTHORS b/AUTHORS index 117b9c219..d16d34272 100644 --- a/AUTHORS +++ b/AUTHORS @@ -129,3 +129,11 @@ Mister Hat Peter Ding jackyzy823 George Brighton +Remita Amine +Aurélio A. Heckert +Bernhard Minks +sceext +Zach Bruggeman +Tjark Saul +slangangular +Behrouz Abbasi diff --git a/README.md b/README.md index e3452c9e1..02b9775f9 100644 --- a/README.md +++ b/README.md @@ -75,7 +75,7 @@ which means you can modify it, redistribute it or use it however you like. ## Video Selection: --playlist-start NUMBER Playlist video to start at (default is 1) --playlist-end NUMBER Playlist video to end at (default is last) - --playlist-items ITEM_SPEC Playlist video items to download. Specify indices of the videos in the playlist seperated by commas like: "--playlist-items 1,2,5,8" + --playlist-items ITEM_SPEC Playlist video items to download. Specify indices of the videos in the playlist separated by commas like: "--playlist-items 1,2,5,8" if you want to download videos indexed 1, 2, 5, 8 in the playlist. You can specify range: "--playlist-items 1-3,7,10-13", it will download the videos at index 1, 2, 3, 7, 10, 11, 12 and 13. --match-title REGEX Download only matching titles (regex or caseless sub-string) @@ -108,7 +108,7 @@ which means you can modify it, redistribute it or use it however you like. --playlist-reverse Download playlist videos in reverse order --xattr-set-filesize Set file xattribute ytdl.filesize with expected filesize (experimental) --hls-prefer-native Use the native HLS downloader instead of ffmpeg (experimental) - --external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,curl,wget + --external-downloader COMMAND Use the specified external downloader. Currently supports aria2c,curl,httpie,wget --external-downloader-args ARGS Give these arguments to the external downloader ## Filesystem Options: @@ -190,8 +190,8 @@ which means you can modify it, redistribute it or use it however you like. --all-formats Download all available video formats --prefer-free-formats Prefer free video formats unless a specific one is requested -F, --list-formats List all available formats - --youtube-skip-dash-manifest Do not download the DASH manifest on YouTube videos - --merge-output-format FORMAT If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv.Ignored if no + --youtube-skip-dash-manifest Do not download the DASH manifests and related data on YouTube videos + --merge-output-format FORMAT If a merge is required (e.g. bestvideo+bestaudio), output to given container format. One of mkv, mp4, ogg, webm, flv. Ignored if no merge is required ## Subtitle Options: @@ -214,7 +214,8 @@ which means you can modify it, redistribute it or use it however you like. --audio-format FORMAT Specify audio format: "best", "aac", "vorbis", "mp3", "m4a", "opus", or "wav"; "best" by default --audio-quality QUALITY Specify ffmpeg/avconv audio quality, insert a value between 0 (better) and 9 (worse) for VBR or a specific bitrate like 128K (default 5) - --recode-video FORMAT Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv) + --recode-video FORMAT Encode the video to another format if necessary (currently supported: mp4|flv|ogg|webm|mkv|avi) + --postprocessor-args ARGS Give these arguments to the postprocessor -k, --keep-video Keep the video file on disk after the post-processing; the video is erased by default --no-post-overwrites Do not overwrite post-processed files; the post-processed files are overwritten by default --embed-subs Embed subtitles in the video (only for mkv and mp4 videos) @@ -237,6 +238,26 @@ which means you can modify it, redistribute it or use it however you like. You can configure youtube-dl by placing default arguments (such as `--extract-audio --no-mtime` to always extract the audio and not copy the mtime) into `/etc/youtube-dl.conf` and/or `~/.config/youtube-dl/config`. On Windows, the configuration file locations are `%APPDATA%\youtube-dl\config.txt` and `C:\Users\\youtube-dl.conf`. +### Authentication with `.netrc` file ### + +You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every youtube-dl execution and prevent tracking plain text passwords in shell command history. You can achieve this using [`.netrc` file](http://stackoverflow.com/tags/.netrc/info) on per extractor basis. For that you will need to create `.netrc` file in your `$HOME` and restrict permissions to read/write by you only: +``` +touch $HOME/.netrc +chmod a-rwx,u+rw $HOME/.netrc +``` +After that you can add credentials for extractor in the following format, where *extractor* is the name of extractor in lowercase: +``` +machine login password +``` +For example: +``` +machine youtube login myaccount@gmail.com password my_youtube_password +machine twitch login my_twitch_account_name password my_twitch_password +``` +To activate authentication with `.netrc` file you should pass `--netrc` to youtube-dl or to place it in [configuration file](#configuration). + +On Windows you may also need to setup `%HOME%` environment variable manually. + # OUTPUT TEMPLATE The `-o` option allows users to indicate a template for the output file names. The basic usage is not to set any template arguments when downloading a single file, like in `youtube-dl -o funny_video.flv "http://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences have the format `%(NAME)s`. To clarify, that is a percent symbol followed by a name in parenthesis, followed by a lowercase S. Allowed names are: @@ -268,7 +289,7 @@ youtube-dl_test_video_.mp4 # A simple file name By default youtube-dl tries to download the best quality, but sometimes you may want to download other format. The simplest case is requesting a specific format, for example `-f 22`. You can get the list of available formats using `--list-formats`, you can also use a file extension (currently it supports aac, m4a, mp3, mp4, ogg, wav, webm) or the special names `best`, `bestvideo`, `bestaudio` and `worst`. -If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f +` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. +If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes, as in `-f 22/17/18`. You can also filter the video results by putting a condition in brackets, as in `-f "best[height=720]"` (or `-f "[filesize>10M]"`). This works for filesize, height, width, tbr, abr, vbr, asr, and fps and the comparisons <, <=, >, >=, =, != and for ext, acodec, vcodec, container, and protocol and the comparisons =, != . Formats for which the value is not known are excluded unless you put a question mark (?) after the operator. You can combine format filters, so `-f "[height <=? 720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. Use commas to download multiple formats, such as `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`. You can merge the video and audio of two formats into a single file using `-f +` (requires ffmpeg or avconv), for example `-f bestvideo+bestaudio`. Format selectors can also be grouped using parentheses, for example if you want to download the best mp4 and webm formats with a height lower than 480 you can use `-f '(mp4,webm)[height<480]'`. Since the end of April 2015 and version 2015.04.26 youtube-dl uses `-f bestvideo+bestaudio/best` as default format selection (see #5447, #5456). If ffmpeg or avconv are installed this results in downloading `bestvideo` and `bestaudio` separately and muxing them together into a single file giving the best overall quality available. Otherwise it falls back to `best` and results in downloading best available quality served as a single file. `best` is also needed for videos that don't come from YouTube because they don't provide the audio and video in two different files. If you want to only download some dash formats (for example if you are not interested in getting videos with a resolution higher than 1080p), you can add `-f bestvideo[height<=?1080]+bestaudio/best` to your configuration file. Note that if you use youtube-dl to stream to `stdout` (and most likely to pipe it to your media player then), i.e. you explicitly specify output template as `-o -`, youtube-dl still uses `-f best` format selection in order to start content delivery immediately to your player and not to wait until `bestvideo` and `bestaudio` are downloaded and muxed. @@ -418,6 +439,12 @@ Either prepend `http://www.youtube.com/watch?v=` or separate the ID from the opt youtube-dl -- -wNyEUrxzFU youtube-dl "http://www.youtube.com/watch?v=-wNyEUrxzFU" +### How do I pass cookies to youtube-dl? + +Use the `--cookies` option, for example `--cookies /path/to/cookies/file.txt`. Note that cookies file must be in Mozilla/Netscape format and the first line of 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 cookies file and convert newlines if necessary to correspond your OS, namely `CRLF` (`\r\n`) for Windows, `LF` (`\n`) for Linux and `CR` (`\r`) for Mac OS. `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 particular extractor does not implement it explicitly. + ### Can you add support for this anime video site, or site which shows current movies for free? As a matter of policy (as well as legality), youtube-dl does not include support for services that specialize in infringing copyright. As a rule of thumb, if you cannot easily find a video that the service is quite obviously allowed to distribute (i.e. that has been uploaded by the creator, the creator's distributor, or is published under a free license), the service is probably unfit for inclusion to youtube-dl. diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 9a50fbd1c..657935dc6 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -28,7 +28,8 @@ - **anitube.se** - **AnySex** - **Aparat** - - **AppleDaily** + - **AppleConnect** + - **AppleDaily**: 臺灣蘋果日報 - **AppleTrailers** - **archive.org**: archive.org videos - **ARD** @@ -45,11 +46,12 @@ - **audiomack** - **audiomack:album** - **Azubu** - - **BaiduVideo** + - **BaiduVideo**: 百度视频 - **bambuser** - **bambuser:channel** - **Bandcamp** - **Bandcamp:album** + - **bbc**: BBC - **bbc.co.uk**: BBC iPlayer - **BeatportPro** - **Beeg** @@ -106,7 +108,7 @@ - **Crunchyroll** - **crunchyroll:playlist** - **CSpan**: C-SPAN - - **CtsNews** + - **CtsNews**: 華視新聞 - **culturebox.francetvinfo.fr** - **dailymotion** - **dailymotion:playlist** @@ -121,7 +123,7 @@ - **Discovery** - **divxstage**: DivxStage - **Dotsub** - - **DouyuTV** + - **DouyuTV**: 斗鱼 - **dramafever** - **dramafever:series** - **DRBonanza** @@ -222,7 +224,8 @@ - **instagram:user**: Instagram user profile - **InternetVideoArchive** - **IPrima** - - **iqiyi** + - **iqiyi**: 爱奇艺 + - **Ir90Tv** - **ivi**: ivi.ru - **ivi:compilation**: ivi.ru compilations - **Izlesene** @@ -243,9 +246,16 @@ - **kontrtube**: KontrTube.ru - Труба зовёт - **KrasView**: Красвью - **Ku6** + - **kuwo:album**: 酷我音乐 - 专辑 + - **kuwo:category**: 酷我音乐 - 分类 + - **kuwo:chart**: 酷我音乐 - 排行榜 + - **kuwo:mv**: 酷我音乐 - MV + - **kuwo:singer**: 酷我音乐 - 歌手 + - **kuwo:song**: 酷我音乐 - **la7.tv** - **Laola1Tv** - - **Letv** + - **Lecture2Go** + - **Letv**: 乐视网 - **LetvPlaylist** - **LetvTv** - **Libsyn** @@ -283,6 +293,7 @@ - **Motherless** - **Motorsport**: motorsport.com - **MovieClips** + - **MovieFap** - **Moviezine** - **movshare**: MovShare - **MPORA** @@ -296,6 +307,7 @@ - **MySpace** - **MySpace:album** - **MySpass** + - **Myvi** - **myvideo** - **MyVidster** - **N-JOY** @@ -311,11 +323,18 @@ - **NDTV** - **NerdCubedFeed** - **Nerdist** + - **netease:album**: 网易云音乐 - 专辑 + - **netease:djradio**: 网易云音乐 - 电台 + - **netease:mv**: 网易云音乐 - MV + - **netease:playlist**: 网易云音乐 - 歌单 + - **netease:program**: 网易云音乐 - 电台节目 + - **netease:singer**: 网易云音乐 - 歌手 + - **netease:song**: 网易云音乐 - **Netzkino** - **Newgrounds** - **Newstube** - - **NextMedia** - - **NextMediaActionNews** + - **NextMedia**: 蘋果日報 + - **NextMediaActionNews**: 蘋果日報 - 動新聞 - **nfb**: National Film Board of Canada - **nfl.com** - **nhl.com** @@ -331,13 +350,14 @@ - **Nowness** - **NowTV** - **nowvideo**: NowVideo - - **npo.nl** + - **npo**: npo.nl and ntr.nl + - **npo**: npo.nl and ntr.nl - **npo.nl:live** - **npo.nl:radio** - **npo.nl:radio:fragment** - **NRK** - **NRKPlaylist** - - **NRKTV** + - **NRKTV**: NRK TV and NRK Radio - **ntv.ru** - **Nuvid** - **NYTimes** @@ -381,10 +401,11 @@ - **prosiebensat1**: ProSiebenSat.1 Digital - **Puls4** - **Pyvideo** - - **qqmusic** - - **qqmusic:album** - - **qqmusic:singer** - - **qqmusic:toplist** + - **qqmusic**: QQ音乐 + - **qqmusic:album**: QQ音乐 - 专辑 + - **qqmusic:playlist**: QQ音乐 - 歌单 + - **qqmusic:singer**: QQ音乐 - 歌手 + - **qqmusic:toplist**: QQ音乐 - 排行榜 - **QuickVid** - **R7** - **radio.de** @@ -393,6 +414,7 @@ - **RadioJavan** - **Rai** - **RBMARadio** + - **RDS**: RDS.ca - **RedTube** - **Restudy** - **ReverbNation** @@ -440,6 +462,8 @@ - **smotri:broadcast**: Smotri.com broadcasts - **smotri:community**: Smotri.com community videos - **smotri:user**: Smotri.com user videos + - **SnagFilms** + - **SnagFilmsEmbed** - **Snotr** - **Sohu** - **soompi** @@ -466,6 +490,7 @@ - **SportBox** - **SportBoxEmbed** - **SportDeutschland** + - **Sportschau** - **Srf** - **SRMediathek**: Saarländischer Rundfunk - **SSA** @@ -491,7 +516,6 @@ - **TechTalks** - **techtv.mit.edu** - **ted** - - **tegenlicht.vpro.nl** - **TeleBruxelles** - **telecinco.es** - **TeleMB** @@ -502,6 +526,7 @@ - **TheOnion** - **ThePlatform** - **TheSixtyOne** + - **ThisAmericanLife** - **ThisAV** - **THVideo** - **THVideoPlaylist** @@ -542,10 +567,11 @@ - **twitch:stream** - **twitch:video** - **twitch:vod** + - **TwitterCard** - **Ubu** - **udemy** - **udemy:course** - - **UDNEmbed** + - **UDNEmbed**: 聯合影音 - **Ultimedia** - **Unistra** - **Urort**: NRK P3 Urørt @@ -590,8 +616,8 @@ - **Vimple**: Vimple - one-click video hosting - **Vine** - **vine:user** - - **vk.com** - - **vk.com:user-videos**: vk.com:All of a user's videos + - **vk**: VK + - **vk:uservideos**: VK - User's Videos - **Vodlocker** - **VoiceRepublic** - **Vporn** @@ -607,9 +633,11 @@ - **wdr:mobile** - **WDRMaus**: Sendung mit der Maus - **WebOfStories** + - **WebOfStoriesPlaylist** - **Weibo** - **Wimp** - **Wistia** + - **WNL** - **WorldStarHipHop** - **wrzuta.pl** - **WSJ**: Wall Street Journal @@ -622,18 +650,19 @@ - **Xstream** - **XTube** - **XTubeUser**: XTube user profile - - **Xuite** + - **Xuite**: 隨意窩Xuite影音 - **XVideos** - **XXXYMovies** - **Yahoo**: Yahoo screen and movies - - **Yam** + - **Yam**: 蕃薯藤yam天空部落 - **yandexmusic:album**: Яндекс.Музыка - Альбом - **yandexmusic:playlist**: Яндекс.Музыка - Плейлист - **yandexmusic:track**: Яндекс.Музыка - Трек - **YesJapan** + - **yinyuetai:video**: 音悦Tai - **Ynet** - **YouJizz** - - **youku** + - **youku**: 优酷 - **YouPorn** - **YourUpload** - **youtube**: YouTube.com diff --git a/test/helper.py b/test/helper.py index e1129e58f..c8b34654d 100644 --- a/test/helper.py +++ b/test/helper.py @@ -133,8 +133,8 @@ def expect_info_dict(self, got_dict, expected_dict): elif isinstance(expected, compat_str) and expected.startswith('mincount:'): got = got_dict.get(info_field) self.assertTrue( - isinstance(got, list), - 'Expected field %s to be a list, but it is of type %s' % ( + isinstance(got, (list, dict)), + 'Expected field %s to be a list or a dict, but it is of type %s' % ( info_field, type(got).__name__)) expected_num = int(expected.partition(':')[2]) assertGreaterEqual( diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index a13c09ef4..0388c0bf3 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -15,7 +15,7 @@ from youtube_dl import YoutubeDL from youtube_dl.compat import compat_str from youtube_dl.extractor import YoutubeIE from youtube_dl.postprocessor.common import PostProcessor -from youtube_dl.utils import match_filter_func +from youtube_dl.utils import ExtractorError, match_filter_func TEST_URL = 'http://localhost/sample.mp4' @@ -105,6 +105,7 @@ class TestFormatSelection(unittest.TestCase): def test_format_selection(self): formats = [ {'format_id': '35', 'ext': 'mp4', 'preference': 1, 'url': TEST_URL}, + {'format_id': 'example-with-dashes', 'ext': 'webm', 'preference': 1, 'url': TEST_URL}, {'format_id': '45', 'ext': 'webm', 'preference': 2, 'url': TEST_URL}, {'format_id': '47', 'ext': 'webm', 'preference': 3, 'url': TEST_URL}, {'format_id': '2', 'ext': 'flv', 'preference': 4, 'url': TEST_URL}, @@ -136,6 +137,11 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], '35') + ydl = YDL({'format': 'example-with-dashes'}) + ydl.process_ie_result(info_dict.copy()) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], 'example-with-dashes') + def test_format_selection_audio(self): formats = [ {'format_id': 'audio-low', 'ext': 'webm', 'preference': 1, 'vcodec': 'none', 'url': TEST_URL}, @@ -229,21 +235,70 @@ class TestFormatSelection(unittest.TestCase): '141', '172', '140', '171', '139', ] - for f1id, f2id in zip(order, order[1:]): - f1 = YoutubeIE._formats[f1id].copy() - f1['format_id'] = f1id - f1['url'] = 'url:' + f1id - f2 = YoutubeIE._formats[f2id].copy() - f2['format_id'] = f2id - f2['url'] = 'url:' + f2id + def format_info(f_id): + info = YoutubeIE._formats[f_id].copy() + info['format_id'] = f_id + info['url'] = 'url:' + f_id + return info + formats_order = [format_info(f_id) for f_id in order] + info_dict = _make_result(list(formats_order), extractor='youtube') + ydl = YDL({'format': 'bestvideo+bestaudio'}) + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], '137+141') + self.assertEqual(downloaded['ext'], 'mp4') + + info_dict = _make_result(list(formats_order), extractor='youtube') + ydl = YDL({'format': 'bestvideo[height>=999999]+bestaudio/best'}) + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded = ydl.downloaded_info_dicts[0] + self.assertEqual(downloaded['format_id'], '38') + + info_dict = _make_result(list(formats_order), extractor='youtube') + ydl = YDL({'format': 'bestvideo/best,bestaudio'}) + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] + self.assertEqual(downloaded_ids, ['137', '141']) + + info_dict = _make_result(list(formats_order), extractor='youtube') + ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])+bestaudio'}) + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] + self.assertEqual(downloaded_ids, ['137+141', '248+141']) + + info_dict = _make_result(list(formats_order), extractor='youtube') + ydl = YDL({'format': '(bestvideo[ext=mp4],bestvideo[ext=webm])[height<=720]+bestaudio'}) + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] + self.assertEqual(downloaded_ids, ['136+141', '247+141']) + + info_dict = _make_result(list(formats_order), extractor='youtube') + ydl = YDL({'format': '(bestvideo[ext=none]/bestvideo[ext=webm])+bestaudio'}) + yie = YoutubeIE(ydl) + yie._sort_formats(info_dict['formats']) + ydl.process_ie_result(info_dict) + downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] + self.assertEqual(downloaded_ids, ['248+141']) + + for f1, f2 in zip(formats_order, formats_order[1:]): info_dict = _make_result([f1, f2], extractor='youtube') ydl = YDL({'format': 'best/bestvideo'}) yie = YoutubeIE(ydl) yie._sort_formats(info_dict['formats']) ydl.process_ie_result(info_dict) downloaded = ydl.downloaded_info_dicts[0] - self.assertEqual(downloaded['format_id'], f1id) + self.assertEqual(downloaded['format_id'], f1['format_id']) info_dict = _make_result([f2, f1], extractor='youtube') ydl = YDL({'format': 'best/bestvideo'}) @@ -251,7 +306,18 @@ class TestFormatSelection(unittest.TestCase): yie._sort_formats(info_dict['formats']) ydl.process_ie_result(info_dict) downloaded = ydl.downloaded_info_dicts[0] - self.assertEqual(downloaded['format_id'], f1id) + self.assertEqual(downloaded['format_id'], f1['format_id']) + + def test_invalid_format_specs(self): + def assert_syntax_error(format_spec): + ydl = YDL({'format': format_spec}) + info_dict = _make_result([{'format_id': 'foo', 'url': TEST_URL}]) + self.assertRaises(SyntaxError, ydl.process_ie_result, info_dict) + + assert_syntax_error('bestvideo,,best') + assert_syntax_error('+bestaudio') + assert_syntax_error('bestvideo+') + assert_syntax_error('/') def test_format_filtering(self): formats = [ @@ -308,6 +374,18 @@ class TestFormatSelection(unittest.TestCase): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'G') + ydl = YDL({'format': 'all[width>=400][width<=600]'}) + ydl.process_ie_result(info_dict) + downloaded_ids = [info['format_id'] for info in ydl.downloaded_info_dicts] + self.assertEqual(downloaded_ids, ['B', 'C', 'D']) + + ydl = YDL({'format': 'best[height<40]'}) + try: + ydl.process_ie_result(info_dict) + except ExtractorError: + pass + self.assertEqual(ydl.downloaded_info_dicts, []) + class TestYoutubeDL(unittest.TestCase): def test_subtitles(self): diff --git a/test/test_compat.py b/test/test_compat.py index 1eb454e06..c3ba8ad2e 100644 --- a/test/test_compat.py +++ b/test/test_compat.py @@ -14,6 +14,8 @@ from youtube_dl.utils import get_filesystem_encoding from youtube_dl.compat import ( compat_getenv, compat_expanduser, + compat_urllib_parse_unquote, + compat_urllib_parse_unquote_plus, ) @@ -42,5 +44,28 @@ class TestCompat(unittest.TestCase): dir(youtube_dl.compat))) - set(['unicode_literals']) self.assertEqual(all_names, sorted(present_names)) + def test_compat_urllib_parse_unquote(self): + self.assertEqual(compat_urllib_parse_unquote('abc%20def'), 'abc def') + self.assertEqual(compat_urllib_parse_unquote('%7e/abc+def'), '~/abc+def') + self.assertEqual(compat_urllib_parse_unquote(''), '') + self.assertEqual(compat_urllib_parse_unquote('%'), '%') + self.assertEqual(compat_urllib_parse_unquote('%%'), '%%') + self.assertEqual(compat_urllib_parse_unquote('%%%'), '%%%') + self.assertEqual(compat_urllib_parse_unquote('%2F'), '/') + self.assertEqual(compat_urllib_parse_unquote('%2f'), '/') + self.assertEqual(compat_urllib_parse_unquote('%E6%B4%A5%E6%B3%A2'), '津波') + self.assertEqual( + compat_urllib_parse_unquote(''' +%%a'''), + ''' +%%a''') + self.assertEqual( + compat_urllib_parse_unquote('''%28%5E%E2%97%A3_%E2%97%A2%5E%29%E3%81%A3%EF%B8%BB%E3%83%87%E2%95%90%E4%B8%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%87%80 %E2%86%B6%I%Break%25Things%'''), + '''(^◣_◢^)っ︻デ═一 ⇀ ⇀ ⇀ ⇀ ⇀ ↶%I%Break%Things%''') + + def test_compat_urllib_parse_unquote_plus(self): + self.assertEqual(compat_urllib_parse_unquote_plus('abc%20def'), 'abc def') + self.assertEqual(compat_urllib_parse_unquote_plus('%7e/abc+def'), '~/abc def') + if __name__ == '__main__': unittest.main() diff --git a/test/test_download.py b/test/test_download.py index 1110357a7..284418834 100644 --- a/test/test_download.py +++ b/test/test_download.py @@ -136,7 +136,9 @@ def generator(test_case): # We're not using .download here sine that is just a shim # for outside error handling, and returns the exit code # instead of the result dict. - res_dict = ydl.extract_info(test_case['url']) + res_dict = ydl.extract_info( + test_case['url'], + force_generic_extractor=params.get('force_generic_extractor', False)) except (DownloadError, ExtractorError) as err: # Check if the exception is not a network related one if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError, compat_http_client.BadStatusLine) or (err.exc_info[0] == compat_HTTPError and err.exc_info[1].code == 503): diff --git a/test/test_utils.py b/test/test_utils.py index e13e11b59..a759b2da9 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -235,12 +235,21 @@ class TestUtil(unittest.TestCase): + ''' doc = xml.etree.ElementTree.fromstring(testxml) + self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n'), None) self.assertEqual(find_xpath_attr(doc, './/fourohfour', 'n', 'v'), None) + self.assertEqual(find_xpath_attr(doc, './/node', 'n'), None) + self.assertEqual(find_xpath_attr(doc, './/node', 'n', 'v'), None) + self.assertEqual(find_xpath_attr(doc, './/node', 'x'), doc[1]) self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'a'), doc[1]) + self.assertEqual(find_xpath_attr(doc, './/node', 'x', 'b'), doc[3]) + self.assertEqual(find_xpath_attr(doc, './/node', 'y'), doc[2]) self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'c'), doc[2]) + self.assertEqual(find_xpath_attr(doc, './/node', 'y', 'd'), doc[3]) + self.assertEqual(find_xpath_attr(doc, './/node', 'x', ''), doc[4]) def test_xpath_with_ns(self): testxml = ''' @@ -324,6 +333,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_duration('02:03:04'), 7384) self.assertEqual(parse_duration('01:02:03:04'), 93784) self.assertEqual(parse_duration('1 hour 3 minutes'), 3780) + self.assertEqual(parse_duration('87 Min.'), 5220) def test_fix_xml_ampersands(self): self.assertEqual( diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 411de9ac9..cad6b026e 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -21,24 +21,24 @@ import subprocess import socket import sys import time +import tokenize import traceback if os.name == 'nt': import ctypes from .compat import ( - compat_basestring, compat_cookiejar, compat_expanduser, compat_get_terminal_size, compat_http_client, compat_kwargs, compat_str, + compat_tokenize_tokenize, compat_urllib_error, compat_urllib_request, ) from .utils import ( - escape_url, ContentTooShortError, date_from_str, DateRange, @@ -49,7 +49,6 @@ from .utils import ( ExtractorError, format_bytes, formatSeconds, - HEADRequest, locked_file, make_HTTPS_handler, MaxDownloadsReached, @@ -262,6 +261,8 @@ class YoutubeDL(object): The following options are used by the post processors: prefer_ffmpeg: If True, use ffmpeg instead of avconv if both are available, otherwise prefer avconv. + postprocessor_args: A list of additional command-line arguments for the + postprocessor. """ params = None @@ -851,8 +852,8 @@ class YoutubeDL(object): else: raise Exception('Invalid result type: %s' % result_type) - def _apply_format_filter(self, format_spec, available_formats): - " Returns a tuple of the remaining format_spec and filtered formats " + def _build_format_filter(self, filter_spec): + " Returns a function to filter the formats according to the filter_spec " OPERATORS = { '<': operator.lt, @@ -862,13 +863,13 @@ class YoutubeDL(object): '=': operator.eq, '!=': operator.ne, } - operator_rex = re.compile(r'''(?x)\s*\[ + operator_rex = re.compile(r'''(?x)\s* (?Pwidth|height|tbr|abr|vbr|asr|filesize|fps) \s*(?P%s)(?P\s*\?)?\s* (?P[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?) - \]$ + $ ''' % '|'.join(map(re.escape, OPERATORS.keys()))) - m = operator_rex.search(format_spec) + m = operator_rex.search(filter_spec) if m: try: comparison_value = int(m.group('value')) @@ -879,7 +880,7 @@ class YoutubeDL(object): if comparison_value is None: raise ValueError( 'Invalid value %r in format specification %r' % ( - m.group('value'), format_spec)) + m.group('value'), filter_spec)) op = OPERATORS[m.group('op')] if not m: @@ -887,85 +888,283 @@ class YoutubeDL(object): '=': operator.eq, '!=': operator.ne, } - str_operator_rex = re.compile(r'''(?x)\s*\[ + str_operator_rex = re.compile(r'''(?x) \s*(?Pext|acodec|vcodec|container|protocol) \s*(?P%s)(?P\s*\?)? \s*(?P[a-zA-Z0-9_-]+) - \s*\]$ + \s*$ ''' % '|'.join(map(re.escape, STR_OPERATORS.keys()))) - m = str_operator_rex.search(format_spec) + m = str_operator_rex.search(filter_spec) if m: comparison_value = m.group('value') op = STR_OPERATORS[m.group('op')] if not m: - raise ValueError('Invalid format specification %r' % format_spec) + raise ValueError('Invalid filter specification %r' % filter_spec) def _filter(f): actual_value = f.get(m.group('key')) if actual_value is None: return m.group('none_inclusive') return op(actual_value, comparison_value) - new_formats = [f for f in available_formats if _filter(f)] + return _filter - new_format_spec = format_spec[:-len(m.group(0))] - if not new_format_spec: - new_format_spec = 'best' + def build_format_selector(self, format_spec): + def syntax_error(note, start): + message = ( + 'Invalid format specification: ' + '{0}\n\t{1}\n\t{2}^'.format(note, format_spec, ' ' * start[1])) + return SyntaxError(message) - return (new_format_spec, new_formats) + PICKFIRST = 'PICKFIRST' + MERGE = 'MERGE' + SINGLE = 'SINGLE' + GROUP = 'GROUP' + FormatSelector = collections.namedtuple('FormatSelector', ['type', 'selector', 'filters']) - def select_format(self, format_spec, available_formats): - while format_spec.endswith(']'): - format_spec, available_formats = self._apply_format_filter( - format_spec, available_formats) - if not available_formats: - return None + def _parse_filter(tokens): + filter_parts = [] + for type, string, start, _, _ in tokens: + if type == tokenize.OP and string == ']': + return ''.join(filter_parts) + else: + filter_parts.append(string) - if format_spec in ['best', 'worst', None]: - format_idx = 0 if format_spec == 'worst' else -1 - audiovideo_formats = [ - f for f in available_formats - if f.get('vcodec') != 'none' and f.get('acodec') != 'none'] - if audiovideo_formats: - return audiovideo_formats[format_idx] - # for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format - elif (all(f.get('acodec') != 'none' for f in available_formats) or - all(f.get('vcodec') != 'none' for f in available_formats)): - return available_formats[format_idx] - elif format_spec == 'bestaudio': - audio_formats = [ - f for f in available_formats - if f.get('vcodec') == 'none'] - if audio_formats: - return audio_formats[-1] - elif format_spec == 'worstaudio': - audio_formats = [ - f for f in available_formats - if f.get('vcodec') == 'none'] - if audio_formats: - return audio_formats[0] - elif format_spec == 'bestvideo': - video_formats = [ - f for f in available_formats - if f.get('acodec') == 'none'] - if video_formats: - return video_formats[-1] - elif format_spec == 'worstvideo': - video_formats = [ - f for f in available_formats - if f.get('acodec') == 'none'] - if video_formats: - return video_formats[0] - else: - extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav'] - if format_spec in extensions: - filter_f = lambda f: f['ext'] == format_spec - else: - filter_f = lambda f: f['format_id'] == format_spec - matches = list(filter(filter_f, available_formats)) - if matches: - return matches[-1] - return None + def _remove_unused_ops(tokens): + # Remove operators that we don't use and join them with the sourrounding strings + # for example: 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9' + ALLOWED_OPS = ('/', '+', ',', '(', ')') + last_string, last_start, last_end, last_line = None, None, None, None + for type, string, start, end, line in tokens: + if type == tokenize.OP and string == '[': + if last_string: + yield tokenize.NAME, last_string, last_start, last_end, last_line + last_string = None + yield type, string, start, end, line + # everything inside brackets will be handled by _parse_filter + for type, string, start, end, line in tokens: + yield type, string, start, end, line + if type == tokenize.OP and string == ']': + break + elif type == tokenize.OP and string in ALLOWED_OPS: + if last_string: + yield tokenize.NAME, last_string, last_start, last_end, last_line + last_string = None + yield type, string, start, end, line + elif type in [tokenize.NAME, tokenize.NUMBER, tokenize.OP]: + if not last_string: + last_string = string + last_start = start + last_end = end + else: + last_string += string + if last_string: + yield tokenize.NAME, last_string, last_start, last_end, last_line + + def _parse_format_selection(tokens, inside_merge=False, inside_choice=False, inside_group=False): + selectors = [] + current_selector = None + for type, string, start, _, _ in tokens: + # ENCODING is only defined in python 3.x + if type == getattr(tokenize, 'ENCODING', None): + continue + elif type in [tokenize.NAME, tokenize.NUMBER]: + current_selector = FormatSelector(SINGLE, string, []) + elif type == tokenize.OP: + if string == ')': + if not inside_group: + # ')' will be handled by the parentheses group + tokens.restore_last_token() + break + elif inside_merge and string in ['/', ',']: + tokens.restore_last_token() + break + elif inside_choice and string == ',': + tokens.restore_last_token() + break + elif string == ',': + if not current_selector: + raise syntax_error('"," must follow a format selector', start) + selectors.append(current_selector) + current_selector = None + elif string == '/': + if not current_selector: + raise syntax_error('"/" must follow a format selector', start) + first_choice = current_selector + second_choice = _parse_format_selection(tokens, inside_choice=True) + current_selector = FormatSelector(PICKFIRST, (first_choice, second_choice), []) + elif string == '[': + if not current_selector: + current_selector = FormatSelector(SINGLE, 'best', []) + format_filter = _parse_filter(tokens) + current_selector.filters.append(format_filter) + elif string == '(': + if current_selector: + raise syntax_error('Unexpected "("', start) + group = _parse_format_selection(tokens, inside_group=True) + current_selector = FormatSelector(GROUP, group, []) + elif string == '+': + video_selector = current_selector + audio_selector = _parse_format_selection(tokens, inside_merge=True) + if not video_selector or not audio_selector: + raise syntax_error('"+" must be between two format selectors', start) + current_selector = FormatSelector(MERGE, (video_selector, audio_selector), []) + else: + raise syntax_error('Operator not recognized: "{0}"'.format(string), start) + elif type == tokenize.ENDMARKER: + break + if current_selector: + selectors.append(current_selector) + return selectors + + def _build_selector_function(selector): + if isinstance(selector, list): + fs = [_build_selector_function(s) for s in selector] + + def selector_function(formats): + for f in fs: + for format in f(formats): + yield format + return selector_function + elif selector.type == GROUP: + selector_function = _build_selector_function(selector.selector) + elif selector.type == PICKFIRST: + fs = [_build_selector_function(s) for s in selector.selector] + + def selector_function(formats): + for f in fs: + picked_formats = list(f(formats)) + if picked_formats: + return picked_formats + return [] + elif selector.type == SINGLE: + format_spec = selector.selector + + def selector_function(formats): + formats = list(formats) + if not formats: + return + if format_spec == 'all': + for f in formats: + yield f + elif format_spec in ['best', 'worst', None]: + format_idx = 0 if format_spec == 'worst' else -1 + audiovideo_formats = [ + f for f in formats + if f.get('vcodec') != 'none' and f.get('acodec') != 'none'] + if audiovideo_formats: + yield audiovideo_formats[format_idx] + # for audio only (soundcloud) or video only (imgur) urls, select the best/worst audio format + elif (all(f.get('acodec') != 'none' for f in formats) or + all(f.get('vcodec') != 'none' for f in formats)): + yield formats[format_idx] + elif format_spec == 'bestaudio': + audio_formats = [ + f for f in formats + if f.get('vcodec') == 'none'] + if audio_formats: + yield audio_formats[-1] + elif format_spec == 'worstaudio': + audio_formats = [ + f for f in formats + if f.get('vcodec') == 'none'] + if audio_formats: + yield audio_formats[0] + elif format_spec == 'bestvideo': + video_formats = [ + f for f in formats + if f.get('acodec') == 'none'] + if video_formats: + yield video_formats[-1] + elif format_spec == 'worstvideo': + video_formats = [ + f for f in formats + if f.get('acodec') == 'none'] + if video_formats: + yield video_formats[0] + else: + extensions = ['mp4', 'flv', 'webm', '3gp', 'm4a', 'mp3', 'ogg', 'aac', 'wav'] + if format_spec in extensions: + filter_f = lambda f: f['ext'] == format_spec + else: + filter_f = lambda f: f['format_id'] == format_spec + matches = list(filter(filter_f, formats)) + if matches: + yield matches[-1] + elif selector.type == MERGE: + def _merge(formats_info): + format_1, format_2 = [f['format_id'] for f in formats_info] + # The first format must contain the video and the + # second the audio + if formats_info[0].get('vcodec') == 'none': + self.report_error('The first format must ' + 'contain the video, try using ' + '"-f %s+%s"' % (format_2, format_1)) + return + output_ext = ( + formats_info[0]['ext'] + if self.params.get('merge_output_format') is None + else self.params['merge_output_format']) + return { + 'requested_formats': formats_info, + 'format': '%s+%s' % (formats_info[0].get('format'), + formats_info[1].get('format')), + 'format_id': '%s+%s' % (formats_info[0].get('format_id'), + formats_info[1].get('format_id')), + 'width': formats_info[0].get('width'), + 'height': formats_info[0].get('height'), + 'resolution': formats_info[0].get('resolution'), + 'fps': formats_info[0].get('fps'), + 'vcodec': formats_info[0].get('vcodec'), + 'vbr': formats_info[0].get('vbr'), + 'stretched_ratio': formats_info[0].get('stretched_ratio'), + 'acodec': formats_info[1].get('acodec'), + 'abr': formats_info[1].get('abr'), + 'ext': output_ext, + } + video_selector, audio_selector = map(_build_selector_function, selector.selector) + + def selector_function(formats): + formats = list(formats) + for pair in itertools.product(video_selector(formats), audio_selector(formats)): + yield _merge(pair) + + filters = [self._build_format_filter(f) for f in selector.filters] + + def final_selector(formats): + for _filter in filters: + formats = list(filter(_filter, formats)) + return selector_function(formats) + return final_selector + + stream = io.BytesIO(format_spec.encode('utf-8')) + try: + tokens = list(_remove_unused_ops(compat_tokenize_tokenize(stream.readline))) + except tokenize.TokenError: + raise syntax_error('Missing closing/opening brackets or parenthesis', (0, len(format_spec))) + + class TokenIterator(object): + def __init__(self, tokens): + self.tokens = tokens + self.counter = 0 + + def __iter__(self): + return self + + def __next__(self): + if self.counter >= len(self.tokens): + raise StopIteration() + value = self.tokens[self.counter] + self.counter += 1 + return value + + next = __next__ + + def restore_last_token(self): + self.counter -= 1 + + parsed_selector = _parse_format_selection(iter(TokenIterator(tokens))) + return _build_selector_function(parsed_selector) def _calc_headers(self, info_dict): res = std_headers.copy() @@ -1102,62 +1301,15 @@ class YoutubeDL(object): if req_format is None: req_format_list = [] if (self.params.get('outtmpl', DEFAULT_OUTTMPL) != '-' and - info_dict['extractor'] in ['youtube', 'ted']): + info_dict['extractor'] in ['youtube', 'ted'] and + not info_dict.get('is_live')): merger = FFmpegMergerPP(self) if merger.available and merger.can_merge(): req_format_list.append('bestvideo+bestaudio') req_format_list.append('best') req_format = '/'.join(req_format_list) - formats_to_download = [] - if req_format == 'all': - formats_to_download = formats - else: - for rfstr in req_format.split(','): - # We can accept formats requested in the format: 34/5/best, we pick - # the first that is available, starting from left - req_formats = rfstr.split('/') - for rf in req_formats: - if re.match(r'.+?\+.+?', rf) is not None: - # Two formats have been requested like '137+139' - format_1, format_2 = rf.split('+') - formats_info = (self.select_format(format_1, formats), - self.select_format(format_2, formats)) - if all(formats_info): - # The first format must contain the video and the - # second the audio - if formats_info[0].get('vcodec') == 'none': - self.report_error('The first format must ' - 'contain the video, try using ' - '"-f %s+%s"' % (format_2, format_1)) - return - output_ext = ( - formats_info[0]['ext'] - if self.params.get('merge_output_format') is None - else self.params['merge_output_format']) - selected_format = { - 'requested_formats': formats_info, - 'format': '%s+%s' % (formats_info[0].get('format'), - formats_info[1].get('format')), - 'format_id': '%s+%s' % (formats_info[0].get('format_id'), - formats_info[1].get('format_id')), - 'width': formats_info[0].get('width'), - 'height': formats_info[0].get('height'), - 'resolution': formats_info[0].get('resolution'), - 'fps': formats_info[0].get('fps'), - 'vcodec': formats_info[0].get('vcodec'), - 'vbr': formats_info[0].get('vbr'), - 'stretched_ratio': formats_info[0].get('stretched_ratio'), - 'acodec': formats_info[1].get('acodec'), - 'abr': formats_info[1].get('abr'), - 'ext': output_ext, - } - else: - selected_format = None - else: - selected_format = self.select_format(rf, formats) - if selected_format is not None: - formats_to_download.append(selected_format) - break + format_selector = self.build_format_selector(req_format) + formats_to_download = list(format_selector(formats)) if not formats_to_download: raise ExtractorError('requested format not available', expected=True) @@ -1705,27 +1857,6 @@ class YoutubeDL(object): def urlopen(self, req): """ Start an HTTP download """ - - # According to RFC 3986, URLs can not contain non-ASCII characters, however this is not - # always respected by websites, some tend to give out URLs with non percent-encoded - # non-ASCII characters (see telemb.py, ard.py [#3412]) - # urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991) - # To work around aforementioned issue we will replace request's original URL with - # percent-encoded one - req_is_string = isinstance(req, compat_basestring) - url = req if req_is_string else req.get_full_url() - url_escaped = escape_url(url) - - # Substitute URL if any change after escaping - if url != url_escaped: - if req_is_string: - req = url_escaped - else: - req_type = HEADRequest if req.get_method() == 'HEAD' else compat_urllib_request.Request - req = req_type( - url_escaped, data=req.data, headers=req.headers, - origin_req_host=req.origin_req_host, unverifiable=req.unverifiable) - return self._opener.open(req, timeout=self._socket_timeout) def print_debug_header(self): diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 215b616de..55b22c889 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -169,7 +169,7 @@ def _real_main(argv=None): if not opts.audioquality.isdigit(): parser.error('invalid audio quality specified') if opts.recodevideo is not None: - if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']: + if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv', 'avi']: parser.error('invalid video recode format specified') if opts.convertsubtitles is not None: if opts.convertsubtitles not in ['srt', 'vtt', 'ass']: @@ -263,6 +263,9 @@ def _real_main(argv=None): external_downloader_args = None if opts.external_downloader_args: external_downloader_args = shlex.split(opts.external_downloader_args) + postprocessor_args = None + if opts.postprocessor_args: + postprocessor_args = shlex.split(opts.postprocessor_args) match_filter = ( None if opts.match_filter is None else match_filter_func(opts.match_filter)) @@ -367,6 +370,7 @@ def _real_main(argv=None): 'ffmpeg_location': opts.ffmpeg_location, 'hls_prefer_native': opts.hls_prefer_native, 'external_downloader_args': external_downloader_args, + 'postprocessor_args': postprocessor_args, 'cn_verification_proxy': opts.cn_verification_proxy, } diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index f9529210d..ace5bd716 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -9,6 +9,7 @@ import shutil import socket import subprocess import sys +import itertools try: @@ -41,6 +42,11 @@ try: except ImportError: # Python 2 import cookielib as compat_cookiejar +try: + import http.cookies as compat_cookies +except ImportError: # Python 2 + import Cookie as compat_cookies + try: import html.entities as compat_html_entities except ImportError: # Python 2 @@ -74,42 +80,74 @@ except ImportError: import BaseHTTPServer as compat_http_server try: + from urllib.parse import unquote_to_bytes as compat_urllib_parse_unquote_to_bytes from urllib.parse import unquote as compat_urllib_parse_unquote -except ImportError: - def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'): - if string == '': + from urllib.parse import unquote_plus as compat_urllib_parse_unquote_plus +except ImportError: # Python 2 + _asciire = (compat_urllib_parse._asciire if hasattr(compat_urllib_parse, '_asciire') + else re.compile('([\x00-\x7f]+)')) + + # HACK: The following are the correct unquote_to_bytes, unquote and unquote_plus + # implementations from cpython 3.4.3's stdlib. Python 2's version + # is apparently broken (see https://github.com/rg3/youtube-dl/pull/6244) + + def compat_urllib_parse_unquote_to_bytes(string): + """unquote_to_bytes('abc%20def') -> b'abc def'.""" + # Note: strings are encoded as UTF-8. This is only an issue if it contains + # unescaped non-ASCII characters, which URIs should not. + if not string: + # Is it a string-like object? + string.split + return b'' + if isinstance(string, unicode): + string = string.encode('utf-8') + bits = string.split(b'%') + if len(bits) == 1: return string - res = string.split('%') - if len(res) == 1: + res = [bits[0]] + append = res.append + for item in bits[1:]: + try: + append(compat_urllib_parse._hextochr[item[:2]]) + append(item[2:]) + except KeyError: + append(b'%') + append(item) + return b''.join(res) + + def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'): + """Replace %xx escapes by their single-character equivalent. The optional + encoding and errors parameters specify how to decode percent-encoded + sequences into Unicode characters, as accepted by the bytes.decode() + method. + By default, percent-encoded sequences are decoded with UTF-8, and invalid + sequences are replaced by a placeholder character. + + unquote('abc%20def') -> 'abc def'. + """ + if '%' not in string: + string.split return string if encoding is None: encoding = 'utf-8' if errors is None: errors = 'replace' - # pct_sequence: contiguous sequence of percent-encoded bytes, decoded - pct_sequence = b'' - string = res[0] - for item in res[1:]: - try: - if not item: - raise ValueError - pct_sequence += item[:2].decode('hex') - rest = item[2:] - if not rest: - # This segment was just a single percent-encoded character. - # May be part of a sequence of code units, so delay decoding. - # (Stored in pct_sequence). - continue - except ValueError: - rest = '%' + item - # Encountered non-percent-encoded characters. Flush the current - # pct_sequence. - string += pct_sequence.decode(encoding, errors) + rest - pct_sequence = b'' - if pct_sequence: - # Flush the final pct_sequence - string += pct_sequence.decode(encoding, errors) - return string + bits = _asciire.split(string) + res = [bits[0]] + append = res.append + for i in range(1, len(bits), 2): + append(compat_urllib_parse_unquote_to_bytes(bits[i]).decode(encoding, errors)) + append(bits[i + 1]) + return ''.join(res) + + def compat_urllib_parse_unquote_plus(string, encoding='utf-8', errors='replace'): + """Like unquote(), but also replace plus signs by spaces, as required for + unquoting HTML form values. + + unquote_plus('%7e/abc+def') -> '~/abc def' + """ + string = string.replace('+', ' ') + return compat_urllib_parse_unquote(string, encoding, errors) try: compat_str = unicode # Python 2 @@ -388,12 +426,27 @@ else: pass return _terminal_size(columns, lines) +try: + itertools.count(start=0, step=1) + compat_itertools_count = itertools.count +except TypeError: # Python 2.6 + def compat_itertools_count(start=0, step=1): + n = start + while True: + yield n + n += step + +if sys.version_info >= (3, 0): + from tokenize import tokenize as compat_tokenize_tokenize +else: + from tokenize import generate_tokens as compat_tokenize_tokenize __all__ = [ 'compat_HTTPError', 'compat_basestring', 'compat_chr', 'compat_cookiejar', + 'compat_cookies', 'compat_expanduser', 'compat_get_terminal_size', 'compat_getenv', @@ -401,6 +454,7 @@ __all__ = [ 'compat_html_entities', 'compat_http_client', 'compat_http_server', + 'compat_itertools_count', 'compat_kwargs', 'compat_ord', 'compat_parse_qs', @@ -408,9 +462,12 @@ __all__ = [ 'compat_socket_create_connection', 'compat_str', 'compat_subprocess_get_DEVNULL', + 'compat_tokenize_tokenize', 'compat_urllib_error', 'compat_urllib_parse', 'compat_urllib_parse_unquote', + 'compat_urllib_parse_unquote_plus', + 'compat_urllib_parse_unquote_to_bytes', 'compat_urllib_parse_urlparse', 'compat_urllib_request', 'compat_urlparse', diff --git a/youtube_dl/downloader/__init__.py b/youtube_dl/downloader/__init__.py index f110830c4..dccc59212 100644 --- a/youtube_dl/downloader/__init__.py +++ b/youtube_dl/downloader/__init__.py @@ -8,6 +8,7 @@ from .hls import NativeHlsFD from .http import HttpFD from .rtsp import RtspFD from .rtmp import RtmpFD +from .dash import DashSegmentsFD from ..utils import ( determine_protocol, @@ -20,6 +21,7 @@ PROTOCOL_MAP = { 'mms': RtspFD, 'rtsp': RtspFD, 'f4m': F4mFD, + 'http_dash_segments': DashSegmentsFD, } diff --git a/youtube_dl/downloader/dash.py b/youtube_dl/downloader/dash.py new file mode 100644 index 000000000..8b6fa2753 --- /dev/null +++ b/youtube_dl/downloader/dash.py @@ -0,0 +1,66 @@ +from __future__ import unicode_literals + +import re + +from .common import FileDownloader +from ..compat import compat_urllib_request + + +class DashSegmentsFD(FileDownloader): + """ + Download segments in a DASH manifest + """ + def real_download(self, filename, info_dict): + self.report_destination(filename) + tmpfilename = self.temp_name(filename) + base_url = info_dict['url'] + segment_urls = info_dict['segment_urls'] + + is_test = self.params.get('test', False) + remaining_bytes = self._TEST_FILE_SIZE if is_test else None + byte_counter = 0 + + def append_url_to_file(outf, target_url, target_name, remaining_bytes=None): + self.to_screen('[DashSegments] %s: Downloading %s' % (info_dict['id'], target_name)) + req = compat_urllib_request.Request(target_url) + if remaining_bytes is not None: + req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1)) + + data = self.ydl.urlopen(req).read() + + if remaining_bytes is not None: + data = data[:remaining_bytes] + + outf.write(data) + return len(data) + + def combine_url(base_url, target_url): + if re.match(r'^https?://', target_url): + return target_url + return '%s%s%s' % (base_url, '' if base_url.endswith('/') else '/', target_url) + + with open(tmpfilename, 'wb') as outf: + append_url_to_file( + outf, combine_url(base_url, info_dict['initialization_url']), + 'initialization segment') + for i, segment_url in enumerate(segment_urls): + segment_len = append_url_to_file( + outf, combine_url(base_url, segment_url), + 'segment %d / %d' % (i + 1, len(segment_urls)), + remaining_bytes) + byte_counter += segment_len + if remaining_bytes is not None: + remaining_bytes -= segment_len + if remaining_bytes <= 0: + break + + self.try_rename(tmpfilename, filename) + + self._hook_progress({ + 'downloaded_bytes': byte_counter, + 'total_bytes': byte_counter, + 'filename': filename, + 'status': 'finished', + }) + + return True diff --git a/youtube_dl/downloader/external.py b/youtube_dl/downloader/external.py index 1d5cc9904..07ce59f7d 100644 --- a/youtube_dl/downloader/external.py +++ b/youtube_dl/downloader/external.py @@ -51,6 +51,9 @@ class ExternalFD(FileDownloader): return [] return [command_option, source_address] + def _no_check_certificate(self, command_option): + return [command_option] if self.params.get('nocheckcertificate', False) else [] + def _configuration_args(self, default=[]): ex_args = self.params.get('external_downloader_args') if ex_args is None: @@ -83,12 +86,23 @@ class CurlFD(ExternalFD): return cmd +class AxelFD(ExternalFD): + def _make_cmd(self, tmpfilename, info_dict): + cmd = [self.exe, '-o', tmpfilename] + for key, val in info_dict['http_headers'].items(): + cmd += ['-H', '%s: %s' % (key, val)] + cmd += self._configuration_args() + cmd += ['--', info_dict['url']] + return cmd + + class WgetFD(ExternalFD): def _make_cmd(self, tmpfilename, info_dict): cmd = [self.exe, '-O', tmpfilename, '-nv', '--no-cookies'] for key, val in info_dict['http_headers'].items(): cmd += ['--header', '%s: %s' % (key, val)] cmd += self._source_address('--bind-address') + cmd += self._no_check_certificate('--no-check-certificate') cmd += self._configuration_args() cmd += ['--', info_dict['url']] return cmd diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index b1a858c45..275564b59 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -7,8 +7,7 @@ import os import time import xml.etree.ElementTree as etree -from .common import FileDownloader -from .http import HttpFD +from .fragment import FragmentFD from ..compat import ( compat_urlparse, compat_urllib_error, @@ -16,8 +15,6 @@ from ..compat import ( from ..utils import ( struct_pack, struct_unpack, - encodeFilename, - sanitize_open, xpath_text, ) @@ -226,16 +223,13 @@ def _add_ns(prop): return '{http://ns.adobe.com/f4m/1.0}%s' % prop -class HttpQuietDownloader(HttpFD): - def to_screen(self, *args, **kargs): - pass - - -class F4mFD(FileDownloader): +class F4mFD(FragmentFD): """ A downloader for f4m manifests or AdobeHDS. """ + FD_NAME = 'f4m' + def _get_unencrypted_media(self, doc): media = doc.findall(_add_ns('media')) if not media: @@ -288,7 +282,7 @@ class F4mFD(FileDownloader): def real_download(self, filename, info_dict): man_url = info_dict['url'] requested_bitrate = info_dict.get('tbr') - self.to_screen('[download] Downloading f4m manifest') + self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME) manifest = self.ydl.urlopen(man_url).read() doc = etree.fromstring(manifest) @@ -320,67 +314,20 @@ class F4mFD(FileDownloader): # For some akamai manifests we'll need to add a query to the fragment url akamai_pv = xpath_text(doc, _add_ns('pv-2.0')) - self.report_destination(filename) - http_dl = HttpQuietDownloader( - self.ydl, - { - 'continuedl': True, - 'quiet': True, - 'noprogress': True, - 'ratelimit': self.params.get('ratelimit', None), - 'test': self.params.get('test', False), - } - ) - tmpfilename = self.temp_name(filename) - (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb') + ctx = { + 'filename': filename, + 'total_frags': total_frags, + } + + self._prepare_frag_download(ctx) + + dest_stream = ctx['dest_stream'] write_flv_header(dest_stream) if not live: write_metadata_tag(dest_stream, metadata) - # This dict stores the download progress, it's updated by the progress - # hook - state = { - 'status': 'downloading', - 'downloaded_bytes': 0, - 'frag_index': 0, - 'frag_count': total_frags, - 'filename': filename, - 'tmpfilename': tmpfilename, - } - start = time.time() - - def frag_progress_hook(s): - if s['status'] not in ('downloading', 'finished'): - return - - frag_total_bytes = s.get('total_bytes', 0) - if s['status'] == 'finished': - state['downloaded_bytes'] += frag_total_bytes - state['frag_index'] += 1 - - estimated_size = ( - (state['downloaded_bytes'] + frag_total_bytes) / - (state['frag_index'] + 1) * total_frags) - time_now = time.time() - state['total_bytes_estimate'] = estimated_size - state['elapsed'] = time_now - start - - if s['status'] == 'finished': - progress = self.calc_percent(state['frag_index'], total_frags) - else: - frag_downloaded_bytes = s['downloaded_bytes'] - frag_progress = self.calc_percent(frag_downloaded_bytes, - frag_total_bytes) - progress = self.calc_percent(state['frag_index'], total_frags) - progress += frag_progress / float(total_frags) - - state['eta'] = self.calc_eta( - start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes) - state['speed'] = s.get('speed') - self._hook_progress(state) - - http_dl.add_progress_hook(frag_progress_hook) + self._start_frag_download(ctx) frags_filenames = [] while fragments_list: @@ -391,9 +338,9 @@ class F4mFD(FileDownloader): url += '?' + akamai_pv.strip(';') if info_dict.get('extra_param_to_segment_url'): url += info_dict.get('extra_param_to_segment_url') - frag_filename = '%s-%s' % (tmpfilename, name) + frag_filename = '%s-%s' % (ctx['tmpfilename'], name) try: - success = http_dl.download(frag_filename, {'url': url}) + success = ctx['dl'].download(frag_filename, {'url': url}) if not success: return False with open(frag_filename, 'rb') as down: @@ -425,20 +372,9 @@ class F4mFD(FileDownloader): msg = 'Missed %d fragments' % (fragments_list[0][1] - (frag_i + 1)) self.report_warning(msg) - dest_stream.close() + self._finish_frag_download(ctx) - elapsed = time.time() - start - self.try_rename(tmpfilename, filename) for frag_file in frags_filenames: os.remove(frag_file) - fsize = os.path.getsize(encodeFilename(filename)) - self._hook_progress({ - 'downloaded_bytes': fsize, - 'total_bytes': fsize, - 'filename': filename, - 'status': 'finished', - 'elapsed': elapsed, - }) - return True diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py new file mode 100644 index 000000000..5f9d6796d --- /dev/null +++ b/youtube_dl/downloader/fragment.py @@ -0,0 +1,110 @@ +from __future__ import division, unicode_literals + +import os +import time + +from .common import FileDownloader +from .http import HttpFD +from ..utils import ( + encodeFilename, + sanitize_open, +) + + +class HttpQuietDownloader(HttpFD): + def to_screen(self, *args, **kargs): + pass + + +class FragmentFD(FileDownloader): + """ + A base file downloader class for fragmented media (e.g. f4m/m3u8 manifests). + """ + + def _prepare_and_start_frag_download(self, ctx): + self._prepare_frag_download(ctx) + self._start_frag_download(ctx) + + def _prepare_frag_download(self, ctx): + self.to_screen('[%s] Total fragments: %d' % (self.FD_NAME, ctx['total_frags'])) + self.report_destination(ctx['filename']) + dl = HttpQuietDownloader( + self.ydl, + { + 'continuedl': True, + 'quiet': True, + 'noprogress': True, + 'ratelimit': self.params.get('ratelimit', None), + 'test': self.params.get('test', False), + } + ) + tmpfilename = self.temp_name(ctx['filename']) + dest_stream, tmpfilename = sanitize_open(tmpfilename, 'wb') + ctx.update({ + 'dl': dl, + 'dest_stream': dest_stream, + 'tmpfilename': tmpfilename, + }) + + def _start_frag_download(self, ctx): + total_frags = ctx['total_frags'] + # This dict stores the download progress, it's updated by the progress + # hook + state = { + 'status': 'downloading', + 'downloaded_bytes': 0, + 'frag_index': 0, + 'frag_count': total_frags, + 'filename': ctx['filename'], + 'tmpfilename': ctx['tmpfilename'], + } + start = time.time() + ctx['started'] = start + + def frag_progress_hook(s): + if s['status'] not in ('downloading', 'finished'): + return + + frag_total_bytes = s.get('total_bytes', 0) + if s['status'] == 'finished': + state['downloaded_bytes'] += frag_total_bytes + state['frag_index'] += 1 + + estimated_size = ( + (state['downloaded_bytes'] + frag_total_bytes) / + (state['frag_index'] + 1) * total_frags) + time_now = time.time() + state['total_bytes_estimate'] = estimated_size + state['elapsed'] = time_now - start + + if s['status'] == 'finished': + progress = self.calc_percent(state['frag_index'], total_frags) + else: + frag_downloaded_bytes = s['downloaded_bytes'] + frag_progress = self.calc_percent(frag_downloaded_bytes, + frag_total_bytes) + progress = self.calc_percent(state['frag_index'], total_frags) + progress += frag_progress / float(total_frags) + + state['eta'] = self.calc_eta( + start, time_now, estimated_size, state['downloaded_bytes'] + frag_downloaded_bytes) + state['speed'] = s.get('speed') + self._hook_progress(state) + + ctx['dl'].add_progress_hook(frag_progress_hook) + + return start + + def _finish_frag_download(self, ctx): + ctx['dest_stream'].close() + elapsed = time.time() - ctx['started'] + self.try_rename(ctx['tmpfilename'], ctx['filename']) + fsize = os.path.getsize(encodeFilename(ctx['filename'])) + + self._hook_progress({ + 'downloaded_bytes': fsize, + 'total_bytes': fsize, + 'filename': ctx['filename'], + 'status': 'finished', + 'elapsed': elapsed, + }) diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 8be4f4249..60dca0ab1 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -4,12 +4,11 @@ import os import re import subprocess -from ..postprocessor.ffmpeg import FFmpegPostProcessor from .common import FileDownloader -from ..compat import ( - compat_urlparse, - compat_urllib_request, -) +from .fragment import FragmentFD + +from ..compat import compat_urlparse +from ..postprocessor.ffmpeg import FFmpegPostProcessor from ..utils import ( encodeArgument, encodeFilename, @@ -51,54 +50,50 @@ class HlsFD(FileDownloader): return False -class NativeHlsFD(FileDownloader): +class NativeHlsFD(FragmentFD): """ A more limited implementation that does not require ffmpeg """ - def real_download(self, filename, info_dict): - url = info_dict['url'] - self.report_destination(filename) - tmpfilename = self.temp_name(filename) + FD_NAME = 'hlsnative' - self.to_screen( - '[hlsnative] %s: Downloading m3u8 manifest' % info_dict['id']) - data = self.ydl.urlopen(url).read() - s = data.decode('utf-8', 'ignore') - segment_urls = [] + def real_download(self, filename, info_dict): + man_url = info_dict['url'] + self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME) + manifest = self.ydl.urlopen(man_url).read() + + s = manifest.decode('utf-8', 'ignore') + fragment_urls = [] for line in s.splitlines(): line = line.strip() if line and not line.startswith('#'): segment_url = ( line if re.match(r'^https?://', line) - else compat_urlparse.urljoin(url, line)) - segment_urls.append(segment_url) - - is_test = self.params.get('test', False) - remaining_bytes = self._TEST_FILE_SIZE if is_test else None - byte_counter = 0 - with open(tmpfilename, 'wb') as outf: - for i, segurl in enumerate(segment_urls): - self.to_screen( - '[hlsnative] %s: Downloading segment %d / %d' % - (info_dict['id'], i + 1, len(segment_urls))) - seg_req = compat_urllib_request.Request(segurl) - if remaining_bytes is not None: - seg_req.add_header('Range', 'bytes=0-%d' % (remaining_bytes - 1)) - - segment = self.ydl.urlopen(seg_req).read() - if remaining_bytes is not None: - segment = segment[:remaining_bytes] - remaining_bytes -= len(segment) - outf.write(segment) - byte_counter += len(segment) - if remaining_bytes is not None and remaining_bytes <= 0: + else compat_urlparse.urljoin(man_url, line)) + fragment_urls.append(segment_url) + # We only download the first fragment during the test + if self.params.get('test', False): break - self._hook_progress({ - 'downloaded_bytes': byte_counter, - 'total_bytes': byte_counter, + ctx = { 'filename': filename, - 'status': 'finished', - }) - self.try_rename(tmpfilename, filename) + 'total_frags': len(fragment_urls), + } + + self._prepare_and_start_frag_download(ctx) + + frags_filenames = [] + for i, frag_url in enumerate(fragment_urls): + frag_filename = '%s-Frag%d' % (ctx['tmpfilename'], i) + success = ctx['dl'].download(frag_filename, {'url': frag_url}) + if not success: + return False + with open(frag_filename, 'rb') as down: + ctx['dest_stream'].write(down.read()) + frags_filenames.append(frag_filename) + + self._finish_frag_download(ctx) + + for frag_file in frags_filenames: + os.remove(frag_file) + return True diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index b7f144af9..a29f5cf31 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -4,6 +4,7 @@ import errno import os import socket import time +import re from .common import FileDownloader from ..compat import ( @@ -57,6 +58,24 @@ class HttpFD(FileDownloader): # Establish connection try: data = self.ydl.urlopen(request) + # When trying to resume, Content-Range HTTP header of response has to be checked + # to match the value of requested Range HTTP header. This is due to a webservers + # that don't support resuming and serve a whole file with no Content-Range + # set in response despite of requested Range (see + # https://github.com/rg3/youtube-dl/issues/6057#issuecomment-126129799) + if resume_len > 0: + content_range = data.headers.get('Content-Range') + if content_range: + content_range_m = re.search(r'bytes (\d+)-', content_range) + # Content-Range is present and matches requested Range, resume is possible + if content_range_m and resume_len == int(content_range_m.group(1)): + break + # Content-Range is either not present or invalid. Assuming remote webserver is + # trying to send the whole file, resume is not possible, so wiping the local file + # and performing entire redownload + self.report_unable_to_resume() + resume_len = 0 + open_mode = 'wb' break except (compat_urllib_error.HTTPError, ) as err: if (err.code < 500 or err.code >= 600) and err.code != 416: diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index aba62db53..e38e77a27 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -19,9 +19,14 @@ from .anysex import AnySexIE from .aol import AolIE from .allocine import AllocineIE from .aparat import AparatIE +from .appleconnect import AppleConnectIE from .appletrailers import AppleTrailersIE from .archiveorg import ArchiveOrgIE -from .ard import ARDIE, ARDMediathekIE +from .ard import ( + ARDIE, + ARDMediathekIE, + SportschauIE, +) from .arte import ( ArteTvIE, ArteTVPlus7IE, @@ -38,7 +43,10 @@ from .azubu import AzubuIE from .baidu import BaiduVideoIE from .bambuser import BambuserIE, BambuserChannelIE from .bandcamp import BandcampIE, BandcampAlbumIE -from .bbccouk import BBCCoUkIE +from .bbc import ( + BBCCoUkIE, + BBCIE, +) from .beeg import BeegIE from .behindkink import BehindKinkIE from .beatportpro import BeatportProIE @@ -110,6 +118,7 @@ from .dailymotion import ( ) from .daum import DaumIE from .dbtv import DBTVIE +from .dcn import DCNIE from .dctp import DctpTvIE from .deezer import DeezerPlaylistIE from .dfb import DFBIE @@ -238,6 +247,7 @@ from .instagram import InstagramIE, InstagramUserIE from .internetvideoarchive import InternetVideoArchiveIE from .iprima import IPrimaIE from .iqiyi import IqiyiIE +from .ir90tv import Ir90TvIE from .ivi import ( IviIE, IviCompilationIE @@ -260,8 +270,17 @@ from .keek import KeekIE from .kontrtube import KontrTubeIE from .krasview import KrasViewIE from .ku6 import Ku6IE +from .kuwo import ( + KuwoIE, + KuwoAlbumIE, + KuwoChartIE, + KuwoSingerIE, + KuwoCategoryIE, + KuwoMvIE, +) from .la7 import LA7IE from .laola1tv import Laola1TvIE +from .lecture2go import Lecture2GoIE from .letv import ( LetvIE, LetvTvIE, @@ -323,6 +342,7 @@ from .musicvault import MusicVaultIE from .muzu import MuzuTVIE from .myspace import MySpaceIE, MySpaceAlbumIE from .myspass import MySpassIE +from .myvi import MyviIE from .myvideo import MyVideoIE from .myvidster import MyVidsterIE from .nationalgeographic import NationalGeographicIE @@ -342,6 +362,15 @@ from .ndtv import NDTVIE from .netzkino import NetzkinoIE from .nerdcubed import NerdCubedFeedIE from .nerdist import NerdistIE +from .neteasemusic import ( + NetEaseMusicIE, + NetEaseMusicAlbumIE, + NetEaseMusicSingerIE, + NetEaseMusicListIE, + NetEaseMusicMvIE, + NetEaseMusicProgramIE, + NetEaseMusicDjRadioIE, +) from .newgrounds import NewgroundsIE from .newstube import NewstubeIE from .nextmedia import ( @@ -371,7 +400,8 @@ from .npo import ( NPOLiveIE, NPORadioIE, NPORadioFragmentIE, - TegenlichtVproIE, + VPROIE, + WNLIE ) from .nrk import ( NRKIE, @@ -402,6 +432,10 @@ from .orf import ( from .parliamentliveuk import ParliamentLiveUKIE from .patreon import PatreonIE from .pbs import PBSIE +from .periscope import ( + PeriscopeIE, + QuickscopeIE, +) from .philharmoniedeparis import PhilharmonieDeParisIE from .phoenix import PhoenixIE from .photobucket import PhotobucketIE @@ -432,6 +466,7 @@ from .qqmusic import ( QQMusicSingerIE, QQMusicAlbumIE, QQMusicToplistIE, + QQMusicPlaylistIE, ) from .quickvid import QuickVidIE from .r7 import R7IE @@ -441,6 +476,7 @@ from .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE from .rai import RaiIE from .rbmaradio import RBMARadioIE +from .rds import RDSIE from .redtube import RedTubeIE from .restudy import RestudyIE from .reverbnation import ReverbNationIE @@ -702,7 +738,10 @@ from .wdr import ( WDRMobileIE, WDRMausIE, ) -from .webofstories import WebOfStoriesIE +from .webofstories import ( + WebOfStoriesIE, + WebOfStoriesPlaylistIE, +) from .weibo import WeiboIE from .wimp import WimpIE from .wistia import WistiaIE @@ -733,6 +772,7 @@ from .yandexmusic import ( YandexMusicPlaylistIE, ) from .yesjapan import YesJapanIE +from .yinyuetai import YinYueTaiIE from .ynet import YnetIE from .youjizz import YouJizzIE from .youku import YoukuIE diff --git a/youtube_dl/extractor/appleconnect.py b/youtube_dl/extractor/appleconnect.py new file mode 100644 index 000000000..ea7a70393 --- /dev/null +++ b/youtube_dl/extractor/appleconnect.py @@ -0,0 +1,50 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + str_to_int, + ExtractorError +) + + +class AppleConnectIE(InfoExtractor): + _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/idsa\.(?P[\w-]+)' + _TEST = { + 'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3', + 'md5': '10d0f2799111df4cb1c924520ca78f98', + 'info_dict': { + 'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3', + 'ext': 'm4v', + 'title': 'Energy', + 'uploader': 'Drake', + 'thumbnail': 'http://is5.mzstatic.com/image/thumb/Video5/v4/78/61/c5/7861c5fa-ad6d-294b-1464-cf7605b911d6/source/1920x1080sr.jpg', + 'upload_date': '20150710', + 'timestamp': 1436545535, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + + try: + video_json = self._html_search_regex( + r'class="auc-video-data">(\{.*?\})', webpage, 'json') + except ExtractorError: + raise ExtractorError('This post doesn\'t contain a video', expected=True) + + video_data = self._parse_json(video_json, video_id) + timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp')) + like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count')) + + return { + 'id': video_id, + 'url': video_data['sslSrc'], + 'title': video_data['title'], + 'description': video_data['description'], + 'uploader': video_data['artistName'], + 'thumbnail': video_data['artworkUrl'], + 'timestamp': timestamp, + 'like_count': like_count, + } diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py index 6a35ea463..6f465789b 100644 --- a/youtube_dl/extractor/ard.py +++ b/youtube_dl/extractor/ard.py @@ -8,6 +8,7 @@ from .generic import GenericIE from ..utils import ( determine_ext, ExtractorError, + get_element_by_attribute, qualities, int_or_none, parse_duration, @@ -22,19 +23,125 @@ class ARDMediathekIE(InfoExtractor): _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?' _TESTS = [{ + 'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114', + 'info_dict': { + 'id': '29582122', + 'ext': 'mp4', + 'title': 'Ich liebe das Leben trotzdem', + 'description': 'md5:45e4c225c72b27993314b31a84a5261c', + 'duration': 4557, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916', + 'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e', + 'info_dict': { + 'id': '29522730', + 'ext': 'mp4', + 'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)', + 'description': 'md5:196392e79876d0ac94c94e8cdb2875f1', + 'duration': 5252, + }, + }, { + # audio + 'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086', + 'md5': '219d94d8980b4f538c7fcb0865eb7f2c', + 'info_dict': { + 'id': '28488308', + 'ext': 'mp3', + 'title': 'Tod eines Fußballers', + 'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef', + 'duration': 3240, + }, + }, { 'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht', 'only_matching': True, - }, { - 'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916', - 'info_dict': { - 'id': '22490580', - 'ext': 'mp4', - 'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)', - 'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.', - }, - 'skip': 'Blocked outside of Germany', }] + def _extract_media_info(self, media_info_url, webpage, video_id): + media_info = self._download_json( + media_info_url, video_id, 'Downloading media JSON') + + formats = self._extract_formats(media_info, video_id) + + if not formats: + if '"fsk"' in webpage: + raise ExtractorError( + 'This video is only available after 20:00', expected=True) + elif media_info.get('_geoblocked'): + raise ExtractorError('This video is not available due to geo restriction', expected=True) + + self._sort_formats(formats) + + duration = int_or_none(media_info.get('_duration')) + thumbnail = media_info.get('_previewImage') + + subtitles = {} + subtitle_url = media_info.get('_subtitleUrl') + if subtitle_url: + subtitles['de'] = [{ + 'ext': 'srt', + 'url': subtitle_url, + }] + + return { + 'id': video_id, + 'duration': duration, + 'thumbnail': thumbnail, + 'formats': formats, + 'subtitles': subtitles, + } + + def _extract_formats(self, media_info, video_id): + type_ = media_info.get('_type') + media_array = media_info.get('_mediaArray', []) + formats = [] + for num, media in enumerate(media_array): + for stream in media.get('_mediaStreamArray', []): + stream_urls = stream.get('_stream') + if not stream_urls: + continue + if not isinstance(stream_urls, list): + stream_urls = [stream_urls] + quality = stream.get('_quality') + server = stream.get('_server') + for stream_url in stream_urls: + ext = determine_ext(stream_url) + if ext == 'f4m': + formats.extend(self._extract_f4m_formats( + stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', + video_id, preference=-1, f4m_id='hds')) + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + stream_url, video_id, 'mp4', preference=1, m3u8_id='hls')) + else: + if server and server.startswith('rtmp'): + f = { + 'url': server, + 'play_path': stream_url, + 'format_id': 'a%s-rtmp-%s' % (num, quality), + } + elif stream_url.startswith('http'): + f = { + 'url': stream_url, + 'format_id': 'a%s-%s-%s' % (num, ext, quality) + } + else: + continue + m = re.search(r'_(?P\d+)x(?P\d+)\.mp4$', stream_url) + if m: + f.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) + if type_ == 'audio': + f['vcodec'] = 'none' + formats.append(f) + return formats + def _real_extract(self, url): # determine video id from url m = re.match(self._VALID_URL, url) @@ -92,46 +199,22 @@ class ARDMediathekIE(InfoExtractor): 'format_id': fid, 'url': furl, }) + self._sort_formats(formats) + info = { + 'formats': formats, + } else: # request JSON file - media_info = self._download_json( - 'http://www.ardmediathek.de/play/media/%s' % video_id, video_id) - # The second element of the _mediaArray contains the standard http urls - streams = media_info['_mediaArray'][1]['_mediaStreamArray'] - if not streams: - if '"fsk"' in webpage: - raise ExtractorError('This video is only available after 20:00') + info = self._extract_media_info( + 'http://www.ardmediathek.de/play/media/%s' % video_id, webpage, video_id) - formats = [] - for s in streams: - if type(s['_stream']) == list: - for index, url in enumerate(s['_stream'][::-1]): - quality = s['_quality'] + index - formats.append({ - 'quality': quality, - 'url': url, - 'format_id': '%s-%s' % (determine_ext(url), quality) - }) - continue - - format = { - 'quality': s['_quality'], - 'url': s['_stream'], - } - - format['format_id'] = '%s-%s' % ( - determine_ext(format['url']), format['quality']) - - formats.append(format) - - self._sort_formats(formats) - - return { + info.update({ 'id': video_id, 'title': title, 'description': description, - 'formats': formats, 'thumbnail': thumbnail, - } + }) + + return info class ARDIE(InfoExtractor): @@ -189,3 +272,41 @@ class ARDIE(InfoExtractor): 'upload_date': upload_date, 'thumbnail': thumbnail, } + + +class SportschauIE(ARDMediathekIE): + IE_NAME = 'Sportschau' + _VALID_URL = r'(?Phttps?://(?:www\.)?sportschau\.de/(?:[^/]+/)+video(?P[^/#?]+))\.html' + _TESTS = [{ + 'url': 'http://www.sportschau.de/tourdefrance/videoseppeltkokainhatnichtsmitklassischemdopingzutun100.html', + 'info_dict': { + 'id': 'seppeltkokainhatnichtsmitklassischemdopingzutun100', + 'ext': 'mp4', + 'title': 'Seppelt: "Kokain hat nichts mit klassischem Doping zu tun"', + 'thumbnail': 're:^https?://.*\.jpg$', + 'description': 'Der ARD-Doping Experte Hajo Seppelt gibt seine Einschätzung zum ersten Dopingfall der diesjährigen Tour de France um den Italiener Luca Paolini ab.', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + base_url = mobj.group('baseurl') + + 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_media_info( + base_url + '-mc_defaultQuality-h.json', webpage, video_id) + + info.update({ + 'title': title, + 'description': description, + }) + + return info diff --git a/youtube_dl/extractor/baidu.py b/youtube_dl/extractor/baidu.py index 906895c1e..e37ee4440 100644 --- a/youtube_dl/extractor/baidu.py +++ b/youtube_dl/extractor/baidu.py @@ -8,6 +8,7 @@ from ..compat import compat_urlparse class BaiduVideoIE(InfoExtractor): + IE_DESC = '百度视频' _VALID_URL = r'http://v\.baidu\.com/(?P[a-z]+)/(?P\d+)\.htm' _TESTS = [{ 'url': 'http://v.baidu.com/comic/1069.htm?frp=bdbrand&q=%E4%B8%AD%E5%8D%8E%E5%B0%8F%E5%BD%93%E5%AE%B6', diff --git a/youtube_dl/extractor/bbc.py b/youtube_dl/extractor/bbc.py new file mode 100644 index 000000000..abc5a44a1 --- /dev/null +++ b/youtube_dl/extractor/bbc.py @@ -0,0 +1,780 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + float_or_none, + int_or_none, + parse_duration, + parse_iso8601, +) +from ..compat import compat_HTTPError + + +class BBCCoUkIE(InfoExtractor): + IE_NAME = 'bbc.co.uk' + IE_DESC = 'BBC iPlayer' + _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P[\da-z]{8})' + + _MEDIASELECTOR_URLS = [ + 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s', + ] + + _TESTS = [ + { + 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', + 'info_dict': { + 'id': 'b039d07m', + 'ext': 'flv', + 'title': 'Kaleidoscope, Leonard Cohen', + 'description': 'The Canadian poet and songwriter reflects on his musical career.', + 'duration': 1740, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, + { + 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/', + 'info_dict': { + 'id': 'b00yng1d', + 'ext': 'flv', + 'title': 'The Man in Black: Series 3: The Printed Name', + 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.", + 'duration': 1800, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + 'skip': 'Episode is no longer available on BBC iPlayer Radio', + }, + { + 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/', + 'info_dict': { + 'id': 'b00yng1d', + 'ext': 'flv', + 'title': 'The Voice UK: Series 3: Blind Auditions 5', + 'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.", + 'duration': 5100, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', + }, + { + 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', + 'info_dict': { + 'id': 'b03k3pb7', + 'ext': 'flv', + 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", + 'description': '2. Invasion', + 'duration': 3600, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', + }, { + 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', + 'info_dict': { + 'id': 'b04v209v', + 'ext': 'flv', + 'title': 'Pete Tong, The Essential New Tune Special', + 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", + 'duration': 10800, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', + 'note': 'Audio', + 'info_dict': { + 'id': 'p02frcch', + 'ext': 'flv', + 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', + 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', + 'duration': 3507, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', + 'note': 'Video', + 'info_dict': { + 'id': 'p025c103', + 'ext': 'flv', + 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', + 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', + 'duration': 226, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls', + 'info_dict': { + 'id': 'p02n76xf', + 'ext': 'flv', + 'title': 'Natural World, 2015-2016: 2. Super Powered Owls', + 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d', + 'duration': 3540, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + 'skip': 'geolocation', + }, { + 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition', + 'info_dict': { + 'id': 'b05zmgw1', + 'ext': 'flv', + 'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.', + 'title': 'Royal Academy Summer Exhibition', + 'duration': 3540, + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + 'skip': 'geolocation', + }, { + 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', + 'only_matching': True, + }, { + 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', + 'only_matching': True, + } + ] + + class MediaSelectionError(Exception): + def __init__(self, id): + self.id = id + + def _extract_asx_playlist(self, connection, programme_id): + asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist') + return [ref.get('href') for ref in asx.findall('./Entry/ref')] + + def _extract_connection(self, connection, programme_id): + formats = [] + protocol = connection.get('protocol') + supplier = connection.get('supplier') + if protocol == 'http': + href = connection.get('href') + transfer_format = connection.get('transferFormat') + # ASX playlist + if supplier == 'asx': + for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)): + formats.append({ + 'url': ref, + 'format_id': 'ref%s_%s' % (i, supplier), + }) + # Skip DASH until supported + elif transfer_format == 'dash': + pass + # Direct link + else: + formats.append({ + 'url': href, + 'format_id': supplier, + }) + elif protocol == 'rtmp': + application = connection.get('application', 'ondemand') + auth_string = connection.get('authString') + identifier = connection.get('identifier') + server = connection.get('server') + formats.append({ + 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string), + 'play_path': identifier, + 'app': '%s?%s' % (application, auth_string), + 'page_url': 'http://www.bbc.co.uk', + 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf', + 'rtmp_live': False, + 'ext': 'flv', + 'format_id': supplier, + }) + return formats + + def _extract_items(self, playlist): + return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') + + def _extract_medias(self, media_selection): + error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') + if error is not None: + raise BBCCoUkIE.MediaSelectionError(error.get('id')) + return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') + + def _extract_connections(self, media): + return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection') + + def _extract_video(self, media, programme_id): + formats = [] + vbr = int_or_none(media.get('bitrate')) + vcodec = media.get('encoding') + service = media.get('service') + width = int_or_none(media.get('width')) + height = int_or_none(media.get('height')) + file_size = int_or_none(media.get('media_file_size')) + for connection in self._extract_connections(media): + conn_formats = self._extract_connection(connection, programme_id) + for format in conn_formats: + format.update({ + 'format_id': '%s_%s' % (service, format['format_id']), + 'width': width, + 'height': height, + 'vbr': vbr, + 'vcodec': vcodec, + 'filesize': file_size, + }) + formats.extend(conn_formats) + return formats + + def _extract_audio(self, media, programme_id): + formats = [] + abr = int_or_none(media.get('bitrate')) + acodec = media.get('encoding') + service = media.get('service') + for connection in self._extract_connections(media): + conn_formats = self._extract_connection(connection, programme_id) + for format in conn_formats: + format.update({ + 'format_id': '%s_%s' % (service, format['format_id']), + 'abr': abr, + 'acodec': acodec, + }) + formats.extend(conn_formats) + return formats + + def _get_subtitles(self, media, programme_id): + subtitles = {} + for connection in self._extract_connections(media): + captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') + lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') + subtitles[lang] = [ + { + 'url': connection.get('href'), + 'ext': 'ttml', + }, + ] + return subtitles + + def _raise_extractor_error(self, media_selection_error): + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, media_selection_error.id), + expected=True) + + def _download_media_selector(self, programme_id): + last_exception = None + for mediaselector_url in self._MEDIASELECTOR_URLS: + try: + return self._download_media_selector_url( + mediaselector_url % programme_id, programme_id) + except BBCCoUkIE.MediaSelectionError as e: + if e.id == 'notukerror': + last_exception = e + continue + self._raise_extractor_error(e) + self._raise_extractor_error(last_exception) + + def _download_media_selector_url(self, url, programme_id=None): + try: + media_selection = self._download_xml( + url, programme_id, 'Downloading media selection XML') + except ExtractorError as ee: + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: + media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) + else: + raise + return self._process_media_selector(media_selection, programme_id) + + def _process_media_selector(self, media_selection, programme_id): + formats = [] + subtitles = None + + for media in self._extract_medias(media_selection): + kind = media.get('kind') + if kind == 'audio': + formats.extend(self._extract_audio(media, programme_id)) + elif kind == 'video': + formats.extend(self._extract_video(media, programme_id)) + elif kind == 'captions': + subtitles = self.extract_subtitles(media, programme_id) + return formats, subtitles + + def _download_playlist(self, playlist_id): + try: + playlist = self._download_json( + 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, + playlist_id, 'Downloading playlist JSON') + + version = playlist.get('defaultAvailableVersion') + if version: + smp_config = version['smpConfig'] + title = smp_config['title'] + description = smp_config['summary'] + for item in smp_config['items']: + kind = item['kind'] + if kind != 'programme' and kind != 'radioProgramme': + continue + programme_id = item.get('vpid') + duration = int_or_none(item.get('duration')) + formats, subtitles = self._download_media_selector(programme_id) + return programme_id, title, description, duration, formats, subtitles + except ExtractorError as ee: + if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): + raise + + # fallback to legacy playlist + return self._process_legacy_playlist(playlist_id) + + def _process_legacy_playlist_url(self, url, display_id): + playlist = self._download_legacy_playlist_url(url, display_id) + return self._extract_from_legacy_playlist(playlist, display_id) + + def _process_legacy_playlist(self, playlist_id): + return self._process_legacy_playlist_url( + 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, playlist_id) + + def _download_legacy_playlist_url(self, url, playlist_id=None): + return self._download_xml( + url, playlist_id, 'Downloading legacy playlist XML') + + def _extract_from_legacy_playlist(self, playlist, playlist_id): + no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') + if no_items is not None: + reason = no_items.get('reason') + if reason == 'preAvailability': + msg = 'Episode %s is not yet available' % playlist_id + elif reason == 'postAvailability': + msg = 'Episode %s is no longer available' % playlist_id + elif reason == 'noMedia': + msg = 'Episode %s is not currently available' % playlist_id + else: + msg = 'Episode %s is not available: %s' % (playlist_id, reason) + raise ExtractorError(msg, expected=True) + + for item in self._extract_items(playlist): + kind = item.get('kind') + if kind != 'programme' and kind != 'radioProgramme': + continue + title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text + description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text + + def get_programme_id(item): + def get_from_attributes(item): + for p in('identifier', 'group'): + value = item.get(p) + if value and re.match(r'^[pb][\da-z]{7}$', value): + return value + get_from_attributes(item) + mediator = item.find('./{http://bbc.co.uk/2008/emp/playlist}mediator') + if mediator is not None: + return get_from_attributes(mediator) + + programme_id = get_programme_id(item) + duration = int_or_none(item.get('duration')) + # TODO: programme_id can be None and media items can be incorporated right inside + # playlist's item (e.g. http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) + # as f4m and m3u8 + formats, subtitles = self._download_media_selector(programme_id) + + return programme_id, title, description, duration, formats, subtitles + + def _real_extract(self, url): + group_id = self._match_id(url) + + webpage = self._download_webpage(url, group_id, 'Downloading video page') + + programme_id = None + + tviplayer = self._search_regex( + r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', + webpage, 'player', default=None) + + if tviplayer: + player = self._parse_json(tviplayer, group_id).get('player', {}) + duration = int_or_none(player.get('duration')) + programme_id = player.get('vpid') + + if not programme_id: + programme_id = self._search_regex( + r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) + + if programme_id: + formats, subtitles = self._download_media_selector(programme_id) + title = self._og_search_title(webpage) + description = self._search_regex( + r'

([^<]+)

', + webpage, 'description', fatal=False) + else: + programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) + + self._sort_formats(formats) + + return { + 'id': programme_id, + 'title': title, + 'description': description, + 'thumbnail': self._og_search_thumbnail(webpage, default=None), + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles, + } + + +class BBCIE(BBCCoUkIE): + IE_NAME = 'bbc' + IE_DESC = 'BBC' + _VALID_URL = r'https?://(?:www\.)?bbc\.(?:com|co\.uk)/(?:[^/]+/)+(?P[^/#?]+)' + + _MEDIASELECTOR_URLS = [ + # Provides more formats, namely direct mp4 links, but fails on some videos with + # notukerror for non UK (?) users (e.g. + # http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) + 'http://open.live.bbc.co.uk/mediaselector/4/mtis/stream/%s', + # Provides fewer formats, but works everywhere for everybody (hopefully) + 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/journalism-pc/vpid/%s', + ] + + _TESTS = [{ + # article with multiple videos embedded with data-media-meta containing + # playlist.sxml, externalId and no direct video links + 'url': 'http://www.bbc.com/news/world-europe-32668511', + 'info_dict': { + 'id': 'world-europe-32668511', + 'title': 'Russia stages massive WW2 parade despite Western boycott', + 'description': 'md5:00ff61976f6081841f759a08bf78cc9c', + }, + 'playlist_count': 2, + }, { + # article with multiple videos embedded with data-media-meta (more videos) + 'url': 'http://www.bbc.com/news/business-28299555', + 'info_dict': { + 'id': 'business-28299555', + 'title': 'Farnborough Airshow: Video highlights', + 'description': 'BBC reports and video highlights at the Farnborough Airshow.', + }, + 'playlist_count': 9, + 'skip': 'Save time', + }, { + # article with multiple videos embedded with `new SMP()` + 'url': 'http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460', + 'info_dict': { + 'id': '3662a707-0af9-3149-963f-47bea720b460', + 'title': 'BBC Blogs - Adam Curtis - BUGGER', + }, + 'playlist_count': 18, + }, { + # single video embedded with mediaAssetPage.init() + 'url': 'http://www.bbc.com/news/world-europe-32041533', + 'info_dict': { + 'id': 'p02mprgb', + 'ext': 'mp4', + 'title': 'Aerial footage showed the site of the crash in the Alps - courtesy BFM TV', + 'duration': 47, + 'timestamp': 1427219242, + 'upload_date': '20150324', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + # article with single video embedded with data-media-meta containing + # direct video links (for now these are extracted) and playlist.xml (with + # media items as f4m and m3u8 - currently unsupported) + 'url': 'http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu', + 'info_dict': { + 'id': '150615_telabyad_kentin_cogu', + 'ext': 'mp4', + 'title': "YPG: Tel Abyad'ın tamamı kontrolümüzde", + 'duration': 47, + 'timestamp': 1434397334, + 'upload_date': '20150615', + }, + 'params': { + 'skip_download': True, + } + }, { + # single video embedded with mediaAssetPage.init() (regional section) + 'url': 'http://www.bbc.com/mundo/video_fotos/2015/06/150619_video_honduras_militares_hospitales_corrupcion_aw', + 'info_dict': { + 'id': '150619_video_honduras_militares_hospitales_corrupcion_aw', + 'ext': 'mp4', + 'title': 'Honduras militariza sus hospitales por nuevo escándalo de corrupción', + 'duration': 87, + 'timestamp': 1434713142, + 'upload_date': '20150619', + }, + 'params': { + 'skip_download': True, + } + }, { + # single video from video playlist embedded with vxp-playlist-data JSON + 'url': 'http://www.bbc.com/news/video_and_audio/must_see/33376376', + 'info_dict': { + 'id': 'p02w6qjc', + 'ext': 'mp4', + 'title': '''Judge Mindy Glazer: "I'm sorry to see you here... I always wondered what happened to you"''', + 'duration': 56, + }, + 'params': { + 'skip_download': True, + } + }, { + # single video story with digitalData + 'url': 'http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret', + 'info_dict': { + 'id': 'p02q6gc4', + 'ext': 'flv', + 'title': 'Sri Lanka’s spicy secret', + 'description': 'As a new train line to Jaffna opens up the country’s north, travellers can experience a truly distinct slice of Tamil culture.', + 'timestamp': 1437674293, + 'upload_date': '20150723', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + # single video story without digitalData + 'url': 'http://www.bbc.com/autos/story/20130513-hyundais-rock-star', + 'info_dict': { + 'id': 'p018zqqg', + 'ext': 'mp4', + 'title': 'Hyundai Santa Fe Sport: Rock star', + 'description': 'md5:b042a26142c4154a6e472933cf20793d', + 'timestamp': 1368473503, + 'upload_date': '20130513', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + # single video with playlist.sxml URL + 'url': 'http://www.bbc.com/sport/0/football/33653409', + 'info_dict': { + 'id': 'p02xycnp', + 'ext': 'mp4', + 'title': 'Transfers: Cristiano Ronaldo to Man Utd, Arsenal to spend?', + 'description': 'md5:398fca0e2e701c609d726e034fa1fc89', + 'duration': 140, + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + # single video with playlist URL from weather section + 'url': 'http://www.bbc.com/weather/features/33601775', + 'only_matching': True, + }, { + # custom redirection to www.bbc.com + 'url': 'http://www.bbc.co.uk/news/science-environment-33661876', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if BBCCoUkIE.suitable(url) else super(BBCIE, cls).suitable(url) + + def _extract_from_media_meta(self, media_meta, video_id): + # Direct links to media in media metadata (e.g. + # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu) + # TODO: there are also f4m and m3u8 streams incorporated in playlist.sxml + source_files = media_meta.get('sourceFiles') + if source_files: + return [{ + 'url': f['url'], + 'format_id': format_id, + 'ext': f.get('encoding'), + 'tbr': float_or_none(f.get('bitrate'), 1000), + 'filesize': int_or_none(f.get('filesize')), + } for format_id, f in source_files.items() if f.get('url')], [] + + programme_id = media_meta.get('externalId') + if programme_id: + return self._download_media_selector(programme_id) + + # Process playlist.sxml as legacy playlist + href = media_meta.get('href') + if href: + playlist = self._download_legacy_playlist_url(href) + _, _, _, _, formats, subtitles = self._extract_from_legacy_playlist(playlist, video_id) + return formats, subtitles + + return [], [] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + timestamp = parse_iso8601(self._search_regex( + [r'"datePublished":\s*"([^"]+)', + r']+property="article:published_time"[^>]+content="([^"]+)"', + r'itemprop="datePublished"[^>]+datetime="([^"]+)"'], + webpage, 'date', default=None)) + + # single video with playlist.sxml URL (e.g. http://www.bbc.com/sport/0/football/3365340ng) + playlist = self._search_regex( + r']+name="playlist"[^>]+value="([^"]+)"', + webpage, 'playlist', default=None) + if playlist: + programme_id, title, description, duration, formats, subtitles = \ + self._process_legacy_playlist_url(playlist, playlist_id) + self._sort_formats(formats) + return { + 'id': programme_id, + 'title': title, + 'description': description, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + 'subtitles': subtitles, + } + + # single video story (e.g. http://www.bbc.com/travel/story/20150625-sri-lankas-spicy-secret) + programme_id = self._search_regex( + [r'data-video-player-vpid="([\da-z]{8})"', + r']+name="externalIdentifier"[^>]+value="([\da-z]{8})"'], + webpage, 'vpid', default=None) + if programme_id: + formats, subtitles = self._download_media_selector(programme_id) + self._sort_formats(formats) + # digitalData may be missing (e.g. http://www.bbc.com/autos/story/20130513-hyundais-rock-star) + digital_data = self._parse_json( + self._search_regex( + r'var\s+digitalData\s*=\s*({.+?});?\n', webpage, 'digital data', default='{}'), + programme_id, fatal=False) + page_info = digital_data.get('page', {}).get('pageInfo', {}) + title = page_info.get('pageName') or self._og_search_title(webpage) + description = page_info.get('description') or self._og_search_description(webpage) + timestamp = parse_iso8601(page_info.get('publicationDate')) or timestamp + return { + 'id': programme_id, + 'title': title, + 'description': description, + 'timestamp': timestamp, + 'formats': formats, + 'subtitles': subtitles, + } + + playlist_title = self._html_search_regex( + r'(.*?)(?:\s*-\s*BBC [^ ]+)?', webpage, 'playlist title') + playlist_description = self._og_search_description(webpage, default=None) + + def extract_all(pattern): + return list(filter(None, map( + lambda s: self._parse_json(s, playlist_id, fatal=False), + re.findall(pattern, webpage)))) + + # Multiple video article (e.g. + # http://www.bbc.co.uk/blogs/adamcurtis/entries/3662a707-0af9-3149-963f-47bea720b460) + EMBED_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:[^/]+/)+[\da-z]{8}(?:\b[^"]+)?' + entries = [] + for match in extract_all(r'new\s+SMP\(({.+?})\)'): + embed_url = match.get('playerSettings', {}).get('externalEmbedUrl') + if embed_url and re.match(EMBED_URL, embed_url): + entries.append(embed_url) + entries.extend(re.findall( + r'setPlaylist\("(%s)"\)' % EMBED_URL, webpage)) + if entries: + return self.playlist_result( + [self.url_result(entry, 'BBCCoUk') for entry in entries], + playlist_id, playlist_title, playlist_description) + + # Multiple video article (e.g. http://www.bbc.com/news/world-europe-32668511) + medias = extract_all(r"data-media-meta='({[^']+})'") + + if not medias: + # Single video article (e.g. http://www.bbc.com/news/video_and_audio/international) + media_asset = self._search_regex( + r'mediaAssetPage\.init\(\s*({.+?}), "/', + webpage, 'media asset', default=None) + if media_asset: + media_asset_page = self._parse_json(media_asset, playlist_id, fatal=False) + medias = [] + for video in media_asset_page.get('videos', {}).values(): + medias.extend(video.values()) + + if not medias: + # Multiple video playlist with single `now playing` entry (e.g. + # http://www.bbc.com/news/video_and_audio/must_see/33767813) + vxp_playlist = self._parse_json( + self._search_regex( + r']+class="vxp-playlist-data"[^>]+type="application/json"[^>]*>([^<]+)', + webpage, 'playlist data'), + playlist_id) + playlist_medias = [] + for item in vxp_playlist: + media = item.get('media') + if not media: + continue + playlist_medias.append(media) + # Download single video if found media with asset id matching the video id from URL + if item.get('advert', {}).get('assetId') == playlist_id: + medias = [media] + break + # Fallback to the whole playlist + if not medias: + medias = playlist_medias + + entries = [] + for num, media_meta in enumerate(medias, start=1): + formats, subtitles = self._extract_from_media_meta(media_meta, playlist_id) + if not formats: + continue + self._sort_formats(formats) + + video_id = media_meta.get('externalId') + if not video_id: + video_id = playlist_id if len(medias) == 1 else '%s-%s' % (playlist_id, num) + + title = media_meta.get('caption') + if not title: + title = playlist_title if len(medias) == 1 else '%s - Video %s' % (playlist_title, num) + + duration = int_or_none(media_meta.get('durationInSeconds')) or parse_duration(media_meta.get('duration')) + + images = [] + for image in media_meta.get('images', {}).values(): + images.extend(image.values()) + if 'image' in media_meta: + images.append(media_meta['image']) + + thumbnails = [{ + 'url': image.get('href'), + 'width': int_or_none(image.get('width')), + 'height': int_or_none(image.get('height')), + } for image in images] + + entries.append({ + 'id': video_id, + 'title': title, + 'thumbnails': thumbnails, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + 'subtitles': subtitles, + }) + + return self.playlist_result(entries, playlist_id, playlist_title, playlist_description) diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py deleted file mode 100644 index 5825d2867..000000000 --- a/youtube_dl/extractor/bbccouk.py +++ /dev/null @@ -1,379 +0,0 @@ -from __future__ import unicode_literals - -import xml.etree.ElementTree - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - int_or_none, -) -from ..compat import compat_HTTPError - - -class BBCCoUkIE(InfoExtractor): - IE_NAME = 'bbc.co.uk' - IE_DESC = 'BBC iPlayer' - _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P[\da-z]{8})' - - _TESTS = [ - { - 'url': 'http://www.bbc.co.uk/programmes/b039g8p7', - 'info_dict': { - 'id': 'b039d07m', - 'ext': 'flv', - 'title': 'Kaleidoscope, Leonard Cohen', - 'description': 'The Canadian poet and songwriter reflects on his musical career.', - 'duration': 1740, - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }, - { - 'url': 'http://www.bbc.co.uk/iplayer/episode/b00yng5w/The_Man_in_Black_Series_3_The_Printed_Name/', - 'info_dict': { - 'id': 'b00yng1d', - 'ext': 'flv', - 'title': 'The Man in Black: Series 3: The Printed Name', - 'description': "Mark Gatiss introduces Nicholas Pierpan's chilling tale of a writer's devilish pact with a mysterious man. Stars Ewan Bailey.", - 'duration': 1800, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - 'skip': 'Episode is no longer available on BBC iPlayer Radio', - }, - { - 'url': 'http://www.bbc.co.uk/iplayer/episode/b03vhd1f/The_Voice_UK_Series_3_Blind_Auditions_5/', - 'info_dict': { - 'id': 'b00yng1d', - 'ext': 'flv', - 'title': 'The Voice UK: Series 3: Blind Auditions 5', - 'description': "Emma Willis and Marvin Humes present the fifth set of blind auditions in the singing competition, as the coaches continue to build their teams based on voice alone.", - 'duration': 5100, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', - }, - { - 'url': 'http://www.bbc.co.uk/iplayer/episode/p026c7jt/tomorrows-worlds-the-unearthly-history-of-science-fiction-2-invasion', - 'info_dict': { - 'id': 'b03k3pb7', - 'ext': 'flv', - 'title': "Tomorrow's Worlds: The Unearthly History of Science Fiction", - 'description': '2. Invasion', - 'duration': 3600, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - 'skip': 'Currently BBC iPlayer TV programmes are available to play in the UK only', - }, { - 'url': 'http://www.bbc.co.uk/programmes/b04v20dw', - 'info_dict': { - 'id': 'b04v209v', - 'ext': 'flv', - 'title': 'Pete Tong, The Essential New Tune Special', - 'description': "Pete has a very special mix - all of 2014's Essential New Tunes!", - 'duration': 10800, - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }, { - 'url': 'http://www.bbc.co.uk/music/clips/p02frcc3', - 'note': 'Audio', - 'info_dict': { - 'id': 'p02frcch', - 'ext': 'flv', - 'title': 'Pete Tong, Past, Present and Future Special, Madeon - After Hours mix', - 'description': 'French house superstar Madeon takes us out of the club and onto the after party.', - 'duration': 3507, - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }, { - 'url': 'http://www.bbc.co.uk/music/clips/p025c0zz', - 'note': 'Video', - 'info_dict': { - 'id': 'p025c103', - 'ext': 'flv', - 'title': 'Reading and Leeds Festival, 2014, Rae Morris - Closer (Live on BBC Three)', - 'description': 'Rae Morris performs Closer for BBC Three at Reading 2014', - 'duration': 226, - }, - 'params': { - # rtmp download - 'skip_download': True, - } - }, { - 'url': 'http://www.bbc.co.uk/iplayer/episode/b054fn09/ad/natural-world-20152016-2-super-powered-owls', - 'info_dict': { - 'id': 'p02n76xf', - 'ext': 'flv', - 'title': 'Natural World, 2015-2016: 2. Super Powered Owls', - 'description': 'md5:e4db5c937d0e95a7c6b5e654d429183d', - 'duration': 3540, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - 'skip': 'geolocation', - }, { - 'url': 'http://www.bbc.co.uk/iplayer/episode/b05zmgwn/royal-academy-summer-exhibition', - 'info_dict': { - 'id': 'b05zmgw1', - 'ext': 'flv', - 'description': 'Kirsty Wark and Morgan Quaintance visit the Royal Academy as it prepares for its annual artistic extravaganza, meeting people who have come together to make the show unique.', - 'title': 'Royal Academy Summer Exhibition', - 'duration': 3540, - }, - 'params': { - # rtmp download - 'skip_download': True, - }, - 'skip': 'geolocation', - }, { - 'url': 'http://www.bbc.co.uk/iplayer/playlist/p01dvks4', - 'only_matching': True, - }, { - 'url': 'http://www.bbc.co.uk/music/clips#p02frcc3', - 'only_matching': True, - }, { - 'url': 'http://www.bbc.co.uk/iplayer/cbeebies/episode/b0480276/bing-14-atchoo', - 'only_matching': True, - } - ] - - def _extract_asx_playlist(self, connection, programme_id): - asx = self._download_xml(connection.get('href'), programme_id, 'Downloading ASX playlist') - return [ref.get('href') for ref in asx.findall('./Entry/ref')] - - def _extract_connection(self, connection, programme_id): - formats = [] - protocol = connection.get('protocol') - supplier = connection.get('supplier') - if protocol == 'http': - href = connection.get('href') - # ASX playlist - if supplier == 'asx': - for i, ref in enumerate(self._extract_asx_playlist(connection, programme_id)): - formats.append({ - 'url': ref, - 'format_id': 'ref%s_%s' % (i, supplier), - }) - # Direct link - else: - formats.append({ - 'url': href, - 'format_id': supplier, - }) - elif protocol == 'rtmp': - application = connection.get('application', 'ondemand') - auth_string = connection.get('authString') - identifier = connection.get('identifier') - server = connection.get('server') - formats.append({ - 'url': '%s://%s/%s?%s' % (protocol, server, application, auth_string), - 'play_path': identifier, - 'app': '%s?%s' % (application, auth_string), - 'page_url': 'http://www.bbc.co.uk', - 'player_url': 'http://www.bbc.co.uk/emp/releases/iplayer/revisions/617463_618125_4/617463_618125_4_emp.swf', - 'rtmp_live': False, - 'ext': 'flv', - 'format_id': supplier, - }) - return formats - - def _extract_items(self, playlist): - return playlist.findall('./{http://bbc.co.uk/2008/emp/playlist}item') - - def _extract_medias(self, media_selection): - error = media_selection.find('./{http://bbc.co.uk/2008/mp/mediaselection}error') - if error is not None: - raise ExtractorError( - '%s returned error: %s' % (self.IE_NAME, error.get('id')), expected=True) - return media_selection.findall('./{http://bbc.co.uk/2008/mp/mediaselection}media') - - def _extract_connections(self, media): - return media.findall('./{http://bbc.co.uk/2008/mp/mediaselection}connection') - - def _extract_video(self, media, programme_id): - formats = [] - vbr = int(media.get('bitrate')) - vcodec = media.get('encoding') - service = media.get('service') - width = int(media.get('width')) - height = int(media.get('height')) - file_size = int(media.get('media_file_size')) - for connection in self._extract_connections(media): - conn_formats = self._extract_connection(connection, programme_id) - for format in conn_formats: - format.update({ - 'format_id': '%s_%s' % (service, format['format_id']), - 'width': width, - 'height': height, - 'vbr': vbr, - 'vcodec': vcodec, - 'filesize': file_size, - }) - formats.extend(conn_formats) - return formats - - def _extract_audio(self, media, programme_id): - formats = [] - abr = int(media.get('bitrate')) - acodec = media.get('encoding') - service = media.get('service') - for connection in self._extract_connections(media): - conn_formats = self._extract_connection(connection, programme_id) - for format in conn_formats: - format.update({ - 'format_id': '%s_%s' % (service, format['format_id']), - 'abr': abr, - 'acodec': acodec, - }) - formats.extend(conn_formats) - return formats - - def _get_subtitles(self, media, programme_id): - subtitles = {} - for connection in self._extract_connections(media): - captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') - lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') - subtitles[lang] = [ - { - 'url': connection.get('href'), - 'ext': 'ttml', - }, - ] - return subtitles - - def _download_media_selector(self, programme_id): - try: - media_selection = self._download_xml( - 'http://open.live.bbc.co.uk/mediaselector/5/select/version/2.0/mediaset/pc/vpid/%s' % programme_id, - programme_id, 'Downloading media selection XML') - except ExtractorError as ee: - if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: - media_selection = xml.etree.ElementTree.fromstring(ee.cause.read().decode('utf-8')) - else: - raise - - formats = [] - subtitles = None - - for media in self._extract_medias(media_selection): - kind = media.get('kind') - if kind == 'audio': - formats.extend(self._extract_audio(media, programme_id)) - elif kind == 'video': - formats.extend(self._extract_video(media, programme_id)) - elif kind == 'captions': - subtitles = self.extract_subtitles(media, programme_id) - - return formats, subtitles - - def _download_playlist(self, playlist_id): - try: - playlist = self._download_json( - 'http://www.bbc.co.uk/programmes/%s/playlist.json' % playlist_id, - playlist_id, 'Downloading playlist JSON') - - version = playlist.get('defaultAvailableVersion') - if version: - smp_config = version['smpConfig'] - title = smp_config['title'] - description = smp_config['summary'] - for item in smp_config['items']: - kind = item['kind'] - if kind != 'programme' and kind != 'radioProgramme': - continue - programme_id = item.get('vpid') - duration = int(item.get('duration')) - formats, subtitles = self._download_media_selector(programme_id) - return programme_id, title, description, duration, formats, subtitles - except ExtractorError as ee: - if not (isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404): - raise - - # fallback to legacy playlist - playlist = self._download_xml( - 'http://www.bbc.co.uk/iplayer/playlist/%s' % playlist_id, - playlist_id, 'Downloading legacy playlist XML') - - no_items = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}noItems') - if no_items is not None: - reason = no_items.get('reason') - if reason == 'preAvailability': - msg = 'Episode %s is not yet available' % playlist_id - elif reason == 'postAvailability': - msg = 'Episode %s is no longer available' % playlist_id - elif reason == 'noMedia': - msg = 'Episode %s is not currently available' % playlist_id - else: - msg = 'Episode %s is not available: %s' % (playlist_id, reason) - raise ExtractorError(msg, expected=True) - - for item in self._extract_items(playlist): - kind = item.get('kind') - if kind != 'programme' and kind != 'radioProgramme': - continue - title = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}title').text - description = playlist.find('./{http://bbc.co.uk/2008/emp/playlist}summary').text - programme_id = item.get('identifier') - duration = int(item.get('duration')) - formats, subtitles = self._download_media_selector(programme_id) - - return programme_id, title, description, duration, formats, subtitles - - def _real_extract(self, url): - group_id = self._match_id(url) - - webpage = self._download_webpage(url, group_id, 'Downloading video page') - - programme_id = None - - tviplayer = self._search_regex( - r'mediator\.bind\(({.+?})\s*,\s*document\.getElementById', - webpage, 'player', default=None) - - if tviplayer: - player = self._parse_json(tviplayer, group_id).get('player', {}) - duration = int_or_none(player.get('duration')) - programme_id = player.get('vpid') - - if not programme_id: - programme_id = self._search_regex( - r'"vpid"\s*:\s*"([\da-z]{8})"', webpage, 'vpid', fatal=False, default=None) - - if programme_id: - formats, subtitles = self._download_media_selector(programme_id) - title = self._og_search_title(webpage) - description = self._search_regex( - r'

([^<]+)

', - webpage, 'description', fatal=False) - else: - programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) - - self._sort_formats(formats) - - return { - 'id': programme_id, - 'title': title, - 'description': description, - 'thumbnail': self._og_search_thumbnail(webpage, default=None), - 'duration': duration, - 'formats': formats, - 'subtitles': subtitles, - } diff --git a/youtube_dl/extractor/bet.py b/youtube_dl/extractor/bet.py index 26b934543..03dad4636 100644 --- a/youtube_dl/extractor/bet.py +++ b/youtube_dl/extractor/bet.py @@ -1,7 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urllib_parse +from ..compat import compat_urllib_parse_unquote from ..utils import ( xpath_text, xpath_with_ns, @@ -57,7 +57,7 @@ class BetIE(InfoExtractor): display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) - media_url = compat_urllib_parse.unquote(self._search_regex( + media_url = compat_urllib_parse_unquote(self._search_regex( [r'mediaURL\s*:\s*"([^"]+)"', r"var\s+mrssMediaUrl\s*=\s*'([^']+)'"], webpage, 'media URL')) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index bf60450c2..ecc17ebeb 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -41,8 +41,15 @@ class BiliBiliIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - if self._search_regex(r'(此视频不存在或被删除)', webpage, 'error message', default=None): - raise ExtractorError('The video does not exist or was deleted', expected=True) + if '(此视频不存在或被删除)' in webpage: + raise ExtractorError( + 'The video does not exist or was deleted', expected=True) + + if '>你没有权限浏览！ 由于版权相关问题 我们不对您所在的地区提供服务<' in webpage: + raise ExtractorError( + 'The video is not available in your region due to copyright reasons', + expected=True) + video_code = self._search_regex( r'(?s)
(.*?)
', webpage, 'video code') diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index fb56cd78d..c3296283d 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -5,7 +5,6 @@ import re from .common import InfoExtractor from ..compat import ( - compat_str, compat_urllib_request, compat_urlparse, ) @@ -14,6 +13,8 @@ from ..utils import ( int_or_none, parse_iso8601, unescapeHTML, + xpath_text, + xpath_with_ns, ) @@ -23,10 +24,10 @@ class BlipTVIE(InfoExtractor): _TESTS = [ { 'url': 'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352', - 'md5': 'c6934ad0b6acf2bd920720ec888eb812', + 'md5': '80baf1ec5c3d2019037c1c707d676b9f', 'info_dict': { 'id': '5779306', - 'ext': 'mov', + 'ext': 'm4v', 'title': 'CBR EXCLUSIVE: "Gotham City Imposters" Bats VS Jokerz Short 3', 'description': 'md5:9bc31f227219cde65e47eeec8d2dc596', 'timestamp': 1323138843, @@ -100,6 +101,20 @@ class BlipTVIE(InfoExtractor): 'vcodec': 'none', } }, + { + # missing duration + 'url': 'http://blip.tv/rss/flash/6700880', + 'info_dict': { + 'id': '6684191', + 'ext': 'm4v', + 'title': 'Cowboy Bebop: Gateway Shuffle Review', + 'description': 'md5:3acc480c0f9ae157f5fe88547ecaf3f8', + 'timestamp': 1386639757, + 'upload_date': '20131210', + 'uploader': 'sfdebris', + 'uploader_id': '706520', + } + } ] @staticmethod @@ -128,35 +143,34 @@ class BlipTVIE(InfoExtractor): rss = self._download_xml('http://blip.tv/rss/flash/%s' % video_id, video_id, 'Downloading video RSS') - def blip(s): - return '{http://blip.tv/dtd/blip/1.0}%s' % s - - def media(s): - return '{http://search.yahoo.com/mrss/}%s' % s - - def itunes(s): - return '{http://www.itunes.com/dtds/podcast-1.0.dtd}%s' % s + def _x(p): + return xpath_with_ns(p, { + 'blip': 'http://blip.tv/dtd/blip/1.0', + 'media': 'http://search.yahoo.com/mrss/', + 'itunes': 'http://www.itunes.com/dtds/podcast-1.0.dtd', + }) item = rss.find('channel/item') - video_id = item.find(blip('item_id')).text - title = item.find('./title').text - description = clean_html(compat_str(item.find(blip('puredescription')).text)) - timestamp = parse_iso8601(item.find(blip('datestamp')).text) - uploader = item.find(blip('user')).text - uploader_id = item.find(blip('userid')).text - duration = int(item.find(blip('runtime')).text) - media_thumbnail = item.find(media('thumbnail')) - thumbnail = media_thumbnail.get('url') if media_thumbnail is not None else item.find(itunes('image')).text - categories = [category.text for category in item.findall('category')] + video_id = xpath_text(item, _x('blip:item_id'), 'video id') or lookup_id + title = xpath_text(item, 'title', 'title', fatal=True) + description = clean_html(xpath_text(item, _x('blip:puredescription'), 'description')) + timestamp = parse_iso8601(xpath_text(item, _x('blip:datestamp'), 'timestamp')) + uploader = xpath_text(item, _x('blip:user'), 'uploader') + uploader_id = xpath_text(item, _x('blip:userid'), 'uploader id') + duration = int_or_none(xpath_text(item, _x('blip:runtime'), 'duration')) + media_thumbnail = item.find(_x('media:thumbnail')) + thumbnail = (media_thumbnail.get('url') if media_thumbnail is not None + else xpath_text(item, 'image', 'thumbnail')) + categories = [category.text for category in item.findall('category') if category is not None] formats = [] subtitles_urls = {} - media_group = item.find(media('group')) - for media_content in media_group.findall(media('content')): + media_group = item.find(_x('media:group')) + for media_content in media_group.findall(_x('media:content')): url = media_content.get('url') - role = media_content.get(blip('role')) + role = media_content.get(_x('blip:role')) msg = self._download_webpage( url + '?showplayer=20140425131715&referrer=http://blip.tv&mask=7&skin=flashvars&view=url', video_id, 'Resolving URL for %s' % role) @@ -175,8 +189,8 @@ class BlipTVIE(InfoExtractor): 'url': real_url, 'format_id': role, 'format_note': media_type, - 'vcodec': media_content.get(blip('vcodec')) or 'none', - 'acodec': media_content.get(blip('acodec')), + 'vcodec': media_content.get(_x('blip:vcodec')) or 'none', + 'acodec': media_content.get(_x('blip:acodec')), 'filesize': media_content.get('filesize'), 'width': int_or_none(media_content.get('width')), 'height': int_or_none(media_content.get('height')), diff --git a/youtube_dl/extractor/canalplus.py b/youtube_dl/extractor/canalplus.py index 699b4f7d0..57e0cda2c 100644 --- a/youtube_dl/extractor/canalplus.py +++ b/youtube_dl/extractor/canalplus.py @@ -106,15 +106,11 @@ class CanalplusIE(InfoExtractor): continue format_id = fmt.tag if format_id == 'HLS': - hls_formats = self._extract_m3u8_formats(format_url, video_id, 'flv') - for fmt in hls_formats: - fmt['preference'] = preference(format_id) - formats.extend(hls_formats) + formats.extend(self._extract_m3u8_formats( + format_url, video_id, 'mp4', preference=preference(format_id))) elif format_id == 'HDS': - hds_formats = self._extract_f4m_formats(format_url + '?hdcore=2.11.3', video_id) - for fmt in hds_formats: - fmt['preference'] = preference(format_id) - formats.extend(hds_formats) + formats.extend(self._extract_f4m_formats( + format_url + '?hdcore=2.11.3', video_id, preference=preference(format_id))) else: formats.append({ 'url': format_url, diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index 65f6be623..dda583680 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -7,6 +7,7 @@ from .common import InfoExtractor from ..compat import ( compat_urllib_request, compat_urllib_parse, + compat_urllib_parse_unquote, compat_urllib_parse_urlparse, ) from ..utils import ( @@ -88,7 +89,7 @@ class CeskaTelevizeIE(InfoExtractor): if playlist_url == 'error_region': raise ExtractorError(NOT_AVAILABLE_STRING, expected=True) - req = compat_urllib_request.Request(compat_urllib_parse.unquote(playlist_url)) + req = compat_urllib_request.Request(compat_urllib_parse_unquote(playlist_url)) req.add_header('Referer', url) playlist = self._download_json(req, video_id) diff --git a/youtube_dl/extractor/clipfish.py b/youtube_dl/extractor/clipfish.py index a5c3cb7c6..7af903571 100644 --- a/youtube_dl/extractor/clipfish.py +++ b/youtube_dl/extractor/clipfish.py @@ -1,53 +1,68 @@ from __future__ import unicode_literals import re -import time -import xml.etree.ElementTree from .common import InfoExtractor from ..utils import ( - ExtractorError, - parse_duration, + determine_ext, + int_or_none, + js_to_json, + parse_iso8601, + remove_end, ) class ClipfishIE(InfoExtractor): - IE_NAME = 'clipfish' - - _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P[0-9]+)/' + _VALID_URL = r'https?://(?:www\.)?clipfish\.de/(?:[^/]+/)+video/(?P[0-9]+)' _TEST = { 'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/', - 'md5': '2521cd644e862936cf2e698206e47385', + 'md5': '79bc922f3e8a9097b3d68a93780fd475', 'info_dict': { 'id': '3966754', 'ext': 'mp4', 'title': 'FIFA 14 - E3 2013 Trailer', + 'timestamp': 1370938118, + 'upload_date': '20130611', 'duration': 82, - }, - 'skip': 'Blocked in the US' + } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) - info_url = ('http://www.clipfish.de/devxml/videoinfo/%s?ts=%d' % - (video_id, int(time.time()))) - doc = self._download_xml( - info_url, video_id, note='Downloading info page') - title = doc.find('title').text - video_url = doc.find('filename').text - if video_url is None: - xml_bytes = xml.etree.ElementTree.tostring(doc) - raise ExtractorError('Cannot find video URL in document %r' % - xml_bytes) - thumbnail = doc.find('imageurl').text - duration = parse_duration(doc.find('duration').text) + webpage = self._download_webpage(url, video_id) + + video_info = self._parse_json( + js_to_json(self._html_search_regex( + '(?s)videoObject\s*=\s*({.+?});', webpage, 'video object')), + video_id) + + formats = [] + for video_url in re.findall(r'var\s+videourl\s*=\s*"([^"]+)"', webpage): + ext = determine_ext(video_url) + if ext == 'm3u8': + formats.append({ + 'url': video_url.replace('de.hls.fra.clipfish.de', 'hls.fra.clipfish.de'), + 'ext': 'mp4', + 'format_id': 'hls', + }) + else: + formats.append({ + 'url': video_url, + 'format_id': ext, + }) + self._sort_formats(formats) + + title = remove_end(self._og_search_title(webpage), ' - Video') + thumbnail = self._og_search_thumbnail(webpage) + duration = int_or_none(video_info.get('length')) + timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, 'upload date')) return { 'id': video_id, 'title': title, - 'url': video_url, + 'formats': formats, 'thumbnail': thumbnail, 'duration': duration, + 'timestamp': timestamp, } diff --git a/youtube_dl/extractor/clipsyndicate.py b/youtube_dl/extractor/clipsyndicate.py index d07d544ea..8306d6fb7 100644 --- a/youtube_dl/extractor/clipsyndicate.py +++ b/youtube_dl/extractor/clipsyndicate.py @@ -1,7 +1,5 @@ from __future__ import unicode_literals -import re - from .common import InfoExtractor from ..utils import ( find_xpath_attr, @@ -10,9 +8,9 @@ from ..utils import ( class ClipsyndicateIE(InfoExtractor): - _VALID_URL = r'http://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P\d+)' + _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe', 'md5': '4d7d549451bad625e0ff3d7bd56d776c', 'info_dict': { @@ -22,11 +20,13 @@ class ClipsyndicateIE(InfoExtractor): 'duration': 612, 'thumbnail': 're:^https?://.+\.jpg', }, - } + }, { + 'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack', + 'only_matching': True, + }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) js_player = self._download_webpage( 'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id, video_id, 'Downlaoding player') diff --git a/youtube_dl/extractor/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py index 9c25b2223..81f3d7697 100644 --- a/youtube_dl/extractor/comcarcoff.py +++ b/youtube_dl/extractor/comcarcoff.py @@ -36,7 +36,7 @@ class ComCarCoffIE(InfoExtractor): webpage, 'full data json')) video_id = full_data['activeVideo']['video'] - video_data = full_data['videos'][video_id] + video_data = full_data.get('videos', {}).get(video_id) or full_data['singleshots'][video_id] thumbnails = [{ 'url': video_data['images']['thumb'], }, { diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 81623bfe3..def6caa0d 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -14,10 +14,13 @@ import xml.etree.ElementTree from ..compat import ( compat_cookiejar, + compat_cookies, compat_HTTPError, compat_http_client, compat_urllib_error, + compat_urllib_parse, compat_urllib_parse_urlparse, + compat_urllib_request, compat_urlparse, compat_str, ) @@ -27,12 +30,15 @@ from ..utils import ( bug_reports_message, clean_html, compiled_regex_type, + determine_ext, ExtractorError, + fix_xml_ampersands, float_or_none, int_or_none, RegexNotFoundError, sanitize_filename, unescapeHTML, + url_basename, ) @@ -63,7 +69,7 @@ class InfoExtractor(object): Potential fields: * url Mandatory. The URL of the video file - * ext Will be calculated from url if missing + * ext Will be calculated from URL if missing * format A human-readable description of the format ("mp4 container with h264/opus"). Calculated from the format_id, width, height. @@ -153,7 +159,7 @@ class InfoExtractor(object): lower to higher preference, each element is a dictionary with the "ext" entry and one of: * "data": The subtitles file contents - * "url": A url pointing to the subtitles file + * "url": A URL pointing to the subtitles file automatic_captions: Like 'subtitles', used by the YoutubeIE for automatically generated captions duration: Length of the video in seconds, as an integer. @@ -174,13 +180,18 @@ class InfoExtractor(object): Set to "root" to indicate that this is a comment to the original video. age_limit: Age restriction for the video, as an integer (years) - webpage_url: The url to the video webpage, if given to youtube-dl it + webpage_url: The URL to the video webpage, if given to youtube-dl it should allow to get the same result again. (It will be set by YoutubeDL if it's missing) categories: A list of categories that the video falls in, for example ["Sports", "Berlin"] + tags: A list of tags assigned to the video, e.g. ["sweden", "pop music"] is_live: True, False, or None (=unknown). Whether this video is a live stream that goes on instead of a fixed-length video. + start_time: Time in seconds where the reproduction should start, as + specified in the URL. + end_time: Time in seconds where the reproduction should end, as + specified in the URL. Unless mentioned otherwise, the fields should be Unicode strings. @@ -499,7 +510,7 @@ class InfoExtractor(object): # Methods for following #608 @staticmethod def url_result(url, ie=None, video_id=None, video_title=None): - """Returns a url that points to a page that should be processed""" + """Returns a URL that points to a page that should be processed""" # TODO: ie should be the class used for getting the info video_info = {'_type': 'url', 'url': url, @@ -624,6 +635,12 @@ class InfoExtractor(object): template % (content_re, property_re), ] + @staticmethod + def _meta_regex(prop): + return r'''(?isx)]+(?:itemprop|name|property|id)=(["\']?)%s\1) + [^>]+?content=(["\'])(?P.*?)\2''' % re.escape(prop) + def _og_search_property(self, prop, html, name=None, **kargs): if name is None: name = 'OpenGraph %s' % prop @@ -633,7 +650,7 @@ class InfoExtractor(object): return unescapeHTML(escaped) def _og_search_thumbnail(self, html, **kargs): - return self._og_search_property('image', html, 'thumbnail url', fatal=False, **kargs) + return self._og_search_property('image', html, 'thumbnail URL', fatal=False, **kargs) def _og_search_description(self, html, **kargs): return self._og_search_property('description', html, fatal=False, **kargs) @@ -654,9 +671,7 @@ class InfoExtractor(object): if display_name is None: display_name = name return self._html_search_regex( - r'''(?isx)]+(?:itemprop|name|property)=(["\']?)%s\1) - [^>]+?content=(["\'])(?P.*?)\2''' % re.escape(name), + self._meta_regex(name), html, display_name, fatal=fatal, group='content', **kwargs) def _dc_search_uploader(self, html): @@ -705,6 +720,25 @@ class InfoExtractor(object): return self._html_search_meta('twitter:player', html, 'twitter card player') + @staticmethod + def _hidden_inputs(html): + return dict([ + (input.group('name'), input.group('value')) for input in re.finditer( + r'''(?x) + ["\'])hidden(?P=q_hidden)\s+ + name=(?P["\'])(?P.+?)(?P=q_name)\s+ + (?:id=(?P["\']).+?(?P=q_id)\s+)? + value=(?P["\'])(?P.*?)(?P=q_value) + ''', html) + ]) + + def _form_hidden_inputs(self, form_id, html): + form = self._search_regex( + r'(?s)]+?id=(["\'])%s\1[^>]*>(?P
.+?)
' % form_id, + html, '%s form' % form_id, group='form') + return self._hidden_inputs(form) + def _sort_formats(self, formats, field_preference=None): if not formats: raise ExtractorError('No video formats found') @@ -815,10 +849,14 @@ class InfoExtractor(object): self.to_screen(msg) time.sleep(timeout) - def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None): + def _extract_f4m_formats(self, manifest_url, video_id, preference=None, f4m_id=None, + transform_source=lambda s: fix_xml_ampersands(s).strip()): manifest = self._download_xml( manifest_url, video_id, 'Downloading f4m manifest', - 'Unable to download f4m manifest') + 'Unable to download f4m manifest', + # Some manifests may be malformed, e.g. prosiebensat1 generated manifests + # (see https://github.com/rg3/youtube-dl/issues/6215#issuecomment-121704244) + transform_source=transform_source) formats = [] manifest_version = '1.0' @@ -828,8 +866,19 @@ class InfoExtractor(object): media_nodes = manifest.findall('{http://ns.adobe.com/f4m/2.0}media') for i, media_el in enumerate(media_nodes): if manifest_version == '2.0': - manifest_url = ('/'.join(manifest_url.split('/')[:-1]) + '/' + - (media_el.attrib.get('href') or media_el.attrib.get('url'))) + media_url = media_el.attrib.get('href') or media_el.attrib.get('url') + if not media_url: + continue + manifest_url = ( + media_url if media_url.startswith('http://') or media_url.startswith('https://') + else ('/'.join(manifest_url.split('/')[:-1]) + '/' + media_url)) + # If media_url is itself a f4m manifest do the recursive extraction + # since bitrates in parent manifest (this one) and media_url manifest + # may differ leading to inability to resolve the format by requested + # bitrate in f4m downloader + if determine_ext(manifest_url) == 'f4m': + formats.extend(self._extract_f4m_formats(manifest_url, video_id, preference, f4m_id)) + continue tbr = int_or_none(media_el.attrib.get('bitrate')) formats.append({ 'format_id': '-'.join(filter(None, [f4m_id, compat_str(i if tbr is None else tbr)])), @@ -846,7 +895,8 @@ class InfoExtractor(object): def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None, entry_protocol='m3u8', preference=None, - m3u8_id=None, note=None, errnote=None): + m3u8_id=None, note=None, errnote=None, + fatal=True): formats = [{ 'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])), @@ -866,7 +916,10 @@ class InfoExtractor(object): m3u8_doc = self._download_webpage( m3u8_url, video_id, note=note or 'Downloading m3u8 information', - errnote=errnote or 'Failed to download m3u8 information') + errnote=errnote or 'Failed to download m3u8 information', + fatal=fatal) + if m3u8_doc is False: + return m3u8_doc last_info = None last_media = None kv_rex = re.compile( @@ -927,69 +980,167 @@ class InfoExtractor(object): self._sort_formats(formats) return formats - # TODO: improve extraction - def _extract_smil_formats(self, smil_url, video_id, fatal=True): - smil = self._download_xml( - smil_url, video_id, 'Downloading SMIL file', - 'Unable to download SMIL file', fatal=fatal) + @staticmethod + def _xpath_ns(path, namespace=None): + if not namespace: + return path + out = [] + for c in path.split('/'): + if not c or c == '.': + out.append(c) + else: + out.append('{%s}%s' % (namespace, c)) + return '/'.join(out) + + def _extract_smil_formats(self, smil_url, video_id, fatal=True, f4m_params=None): + smil = self._download_smil(smil_url, video_id, fatal=fatal) + if smil is False: assert not fatal return [] - base = smil.find('./head/meta').get('base') + namespace = self._parse_smil_namespace(smil) + + return self._parse_smil_formats( + smil, smil_url, video_id, namespace=namespace, f4m_params=f4m_params) + + def _extract_smil_info(self, smil_url, video_id, fatal=True, f4m_params=None): + smil = self._download_smil(smil_url, video_id, fatal=fatal) + if smil is False: + return {} + return self._parse_smil(smil, smil_url, video_id, f4m_params=f4m_params) + + def _download_smil(self, smil_url, video_id, fatal=True): + return self._download_xml( + smil_url, video_id, 'Downloading SMIL file', + 'Unable to download SMIL file', fatal=fatal) + + def _parse_smil(self, smil, smil_url, video_id, f4m_params=None): + namespace = self._parse_smil_namespace(smil) + + formats = self._parse_smil_formats( + smil, smil_url, video_id, namespace=namespace, f4m_params=f4m_params) + subtitles = self._parse_smil_subtitles(smil, namespace=namespace) + + video_id = os.path.splitext(url_basename(smil_url))[0] + title = None + description = None + for meta in smil.findall(self._xpath_ns('./head/meta', namespace)): + name = meta.attrib.get('name') + content = meta.attrib.get('content') + if not name or not content: + continue + if not title and name == 'title': + title = content + elif not description and name in ('description', 'abstract'): + description = content + + return { + 'id': video_id, + 'title': title or video_id, + 'description': description, + 'formats': formats, + 'subtitles': subtitles, + } + + def _parse_smil_namespace(self, smil): + return self._search_regex( + r'(?i)^{([^}]+)?}smil$', smil.tag, 'namespace', default=None) + + def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None): + base = smil_url + for meta in smil.findall(self._xpath_ns('./head/meta', namespace)): + b = meta.get('base') or meta.get('httpBase') + if b: + base = b + break formats = [] rtmp_count = 0 - if smil.findall('./body/seq/video'): - video = smil.findall('./body/seq/video')[0] - fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count) - formats.extend(fmts) - else: - for video in smil.findall('./body/switch/video'): - fmts, rtmp_count = self._parse_smil_video(video, video_id, base, rtmp_count) - formats.extend(fmts) + http_count = 0 + + videos = smil.findall(self._xpath_ns('.//video', namespace)) + for video in videos: + src = video.get('src') + if not src: + continue + + bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) + filesize = int_or_none(video.get('size') or video.get('fileSize')) + width = int_or_none(video.get('width')) + height = int_or_none(video.get('height')) + proto = video.get('proto') + ext = video.get('ext') + src_ext = determine_ext(src) + streamer = video.get('streamer') or base + + if proto == 'rtmp' or streamer.startswith('rtmp'): + rtmp_count += 1 + formats.append({ + 'url': streamer, + 'play_path': src, + 'ext': 'flv', + 'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate), + 'tbr': bitrate, + 'filesize': filesize, + 'width': width, + 'height': height, + }) + continue + + src_url = src if src.startswith('http') else compat_urlparse.urljoin(base, src) + + if proto == 'm3u8' or src_ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + src_url, video_id, ext or 'mp4', m3u8_id='hls')) + continue + + if src_ext == 'f4m': + f4m_url = src_url + if not f4m_params: + f4m_params = { + 'hdcore': '3.2.0', + 'plugin': 'flowplayer-3.2.0.1', + } + f4m_url += '&' if '?' in f4m_url else '?' + f4m_url += compat_urllib_parse.urlencode(f4m_params) + formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds')) + continue + + if src_url.startswith('http'): + http_count += 1 + formats.append({ + 'url': src_url, + 'ext': ext or src_ext or 'flv', + 'format_id': 'http-%d' % (bitrate or http_count), + 'tbr': bitrate, + 'filesize': filesize, + 'width': width, + 'height': height, + }) + continue self._sort_formats(formats) return formats - def _parse_smil_video(self, video, video_id, base, rtmp_count): - src = video.get('src') - if not src: - return ([], rtmp_count) - bitrate = int_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000) - width = int_or_none(video.get('width')) - height = int_or_none(video.get('height')) - proto = video.get('proto') - if not proto: - if base: - if base.startswith('rtmp'): - proto = 'rtmp' - elif base.startswith('http'): - proto = 'http' - ext = video.get('ext') - if proto == 'm3u8': - return (self._extract_m3u8_formats(src, video_id, ext), rtmp_count) - elif proto == 'rtmp': - rtmp_count += 1 - streamer = video.get('streamer') or base - return ([{ - 'url': streamer, - 'play_path': src, - 'ext': 'flv', - 'format_id': 'rtmp-%d' % (rtmp_count if bitrate is None else bitrate), - 'tbr': bitrate, - 'width': width, - 'height': height, - }], rtmp_count) - elif proto.startswith('http'): - return ([{ - 'url': base + src, - 'ext': ext or 'flv', - 'tbr': bitrate, - 'width': width, - 'height': height, - }], rtmp_count) + def _parse_smil_subtitles(self, smil, namespace=None): + subtitles = {} + for num, textstream in enumerate(smil.findall(self._xpath_ns('.//textstream', namespace))): + src = textstream.get('src') + if not src: + continue + ext = textstream.get('ext') or determine_ext(src) + if not ext: + type_ = textstream.get('type') + if type_ == 'text/srt': + ext = 'srt' + lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') + subtitles.setdefault(lang, []).append({ + 'url': src, + 'ext': ext, + }) + return subtitles def _live_title(self, name): """ Generate the title for a live video """ @@ -1025,6 +1176,12 @@ class InfoExtractor(object): None, '/', True, False, expire_time, '', None, None, None) self._downloader.cookiejar.set_cookie(cookie) + def _get_cookies(self, url): + """ Return a compat_cookies.SimpleCookie with the cookies for the url """ + req = compat_urllib_request.Request(url) + self._downloader.cookiejar.add_cookie_header(req) + return compat_cookies.SimpleCookie(req.get_header('Cookie')) + def get_testcases(self, include_onlymatching=False): t = getattr(self, '_TEST', None) if t: @@ -1076,7 +1233,7 @@ class InfoExtractor(object): class SearchInfoExtractor(InfoExtractor): """ Base class for paged search queries extractors. - They accept urls in the format _SEARCH_KEY(|all|[0-9]):{query} + They accept URLs in the format _SEARCH_KEY(|all|[0-9]):{query} Instances should define _SEARCH_KEY and _MAX_RESULTS. """ diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 41f0c736d..d1b6d7366 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -12,6 +12,7 @@ from math import pow, sqrt, floor from .common import InfoExtractor from ..compat import ( compat_urllib_parse, + compat_urllib_parse_unquote, compat_urllib_request, ) from ..utils import ( @@ -27,7 +28,7 @@ from ..aes import ( class CrunchyrollIE(InfoExtractor): - _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:media(?:-|/\?id=)|[^/]*/[^/?&]*?)(?P[0-9]+))(?:[/?&]|$)' _NETRC_MACHINE = 'crunchyroll' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', @@ -45,6 +46,22 @@ class CrunchyrollIE(InfoExtractor): # rtmp 'skip_download': True, }, + }, { + 'url': 'http://www.crunchyroll.com/media-589804/culture-japan-1', + 'info_dict': { + 'id': '589804', + 'ext': 'flv', + 'title': 'Culture Japan Episode 1 – Rebuilding Japan after the 3.11', + 'description': 'md5:fe2743efedb49d279552926d0bd0cd9e', + 'thumbnail': 're:^https?://.*\.jpg$', + 'uploader': 'Danny Choo Network', + 'upload_date': '20120213', + }, + 'params': { + # rtmp + 'skip_download': True, + }, + }, { 'url': 'http://www.crunchyroll.fr/girl-friend-beta/episode-11-goodbye-la-mode-661697', 'only_matching': True, @@ -238,7 +255,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text video_upload_date = unified_strdate(video_upload_date) video_uploader = self._html_search_regex(r'
\s*Publisher:(.+?)
', webpage, 'video_uploader', fatal=False, flags=re.DOTALL) - playerdata_url = compat_urllib_parse.unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url')) + playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url')) playerdata_req = compat_urllib_request.Request(playerdata_url) playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url}) playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') @@ -251,16 +268,17 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage): stream_quality, stream_format = self._FORMAT_IDS[fmt] video_format = fmt + 'p' - streamdata_req = compat_urllib_request.Request('http://www.crunchyroll.com/xml/') - # urlencode doesn't work! - streamdata_req.data = 'req=RpcApiVideoEncode%5FGetStreamInfo&video%5Fencode%5Fquality=' + stream_quality + '&media%5Fid=' + stream_id + '&video%5Fformat=' + stream_format + streamdata_req = compat_urllib_request.Request( + 'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s' + % (stream_id, stream_format, stream_quality), + compat_urllib_parse.urlencode({'current_page': url}).encode('utf-8')) streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded') - streamdata_req.add_header('Content-Length', str(len(streamdata_req.data))) streamdata = self._download_xml( streamdata_req, video_id, note='Downloading media info for %s' % video_format) - video_url = streamdata.find('./host').text - video_play_path = streamdata.find('./file').text + stream_info = streamdata.find('./{default}preload/stream_info') + video_url = stream_info.find('./host').text + video_play_path = stream_info.find('./file').text formats.append({ 'url': video_url, 'play_path': video_play_path, diff --git a/youtube_dl/extractor/ctsnews.py b/youtube_dl/extractor/ctsnews.py index 0226f8036..45049bf37 100644 --- a/youtube_dl/extractor/ctsnews.py +++ b/youtube_dl/extractor/ctsnews.py @@ -6,6 +6,7 @@ from ..utils import parse_iso8601, ExtractorError class CtsNewsIE(InfoExtractor): + IE_DESC = '華視新聞' # https connection failed (Connection reset) _VALID_URL = r'http://news\.cts\.com\.tw/[a-z]+/[a-z]+/\d+/(?P\d+)\.html' _TESTS = [{ diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index 8852f0add..2d90b2224 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -13,8 +13,9 @@ from ..compat import ( ) from ..utils import ( ExtractorError, + determine_ext, int_or_none, - orderedSet, + parse_iso8601, str_to_int, unescapeHTML, ) @@ -28,10 +29,16 @@ class DailymotionBaseInfoExtractor(InfoExtractor): request.add_header('Cookie', 'family_filter=off; ff=off') return request + def _download_webpage_handle_no_ff(self, url, *args, **kwargs): + request = self._build_request(url) + return self._download_webpage_handle(request, *args, **kwargs) + + def _download_webpage_no_ff(self, url, *args, **kwargs): + request = self._build_request(url) + return self._download_webpage(request, *args, **kwargs) + class DailymotionIE(DailymotionBaseInfoExtractor): - """Information Extractor for Dailymotion""" - _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P[^/?_]+)' IE_NAME = 'dailymotion' @@ -50,9 +57,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'info_dict': { 'id': 'x2iuewm', 'ext': 'mp4', - 'uploader': 'IGN', 'title': 'Steam Machine Models, Pricing Listed on Steam Store - IGN News', + 'description': 'Several come bundled with the Steam Controller.', + 'thumbnail': 're:^https?:.*\.(?:jpg|png)$', + 'duration': 74, + 'timestamp': 1425657362, 'upload_date': '20150306', + 'uploader': 'IGN', + 'uploader_id': 'xijv66', + 'age_limit': 0, + 'view_count': int, + 'comment_count': int, } }, # Vevo video @@ -86,38 +101,106 @@ class DailymotionIE(DailymotionBaseInfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - url = 'https://www.dailymotion.com/video/%s' % video_id - # Retrieve video webpage to extract further information - request = self._build_request(url) - webpage = self._download_webpage(request, video_id) - - # Extract URL, uploader and title from webpage - self.report_extraction(video_id) - - # It may just embed a vevo video: - m_vevo = re.search( - r'[\w]*)', - webpage) - if m_vevo is not None: - vevo_id = m_vevo.group('id') - self.to_screen('Vevo video detected: %s' % vevo_id) - return self.url_result('vevo:%s' % vevo_id, ie='Vevo') + webpage = self._download_webpage_no_ff( + 'https://www.dailymotion.com/video/%s' % video_id, video_id) age_limit = self._rta_search(webpage) - video_upload_date = None - mobj = re.search(r'', webpage) - if mobj is not None: - video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3) + description = self._og_search_description(webpage) or self._html_search_meta( + 'description', webpage, 'description') + + view_count = str_to_int(self._search_regex( + [r']+itemprop="interactionCount"[^>]+content="UserPlays:(\d+)"', + r'video_views_count[^>]+>\s+([\d\.,]+)'], + webpage, 'view count', fatal=False)) + comment_count = int_or_none(self._search_regex( + r']+itemprop="interactionCount"[^>]+content="UserComments:(\d+)"', + webpage, 'comment count', fatal=False)) + + player_v5 = self._search_regex( + r'playerV5\s*=\s*dmp\.create\([^,]+?,\s*({.+?})\);', + webpage, 'player v5', default=None) + if player_v5: + player = self._parse_json(player_v5, video_id) + metadata = player['metadata'] + formats = [] + for quality, media_list in metadata['qualities'].items(): + for media in media_list: + media_url = media.get('url') + if not media_url: + continue + type_ = media.get('type') + if type_ == 'application/vnd.lumberjack.manifest': + continue + if type_ == 'application/x-mpegURL' or determine_ext(media_url) == 'm3u8': + formats.extend(self._extract_m3u8_formats( + media_url, video_id, 'mp4', m3u8_id='hls')) + else: + f = { + 'url': media_url, + 'format_id': quality, + } + m = re.search(r'H264-(?P\d+)x(?P\d+)', media_url) + if m: + f.update({ + 'width': int(m.group('width')), + 'height': int(m.group('height')), + }) + formats.append(f) + self._sort_formats(formats) + + title = metadata['title'] + duration = int_or_none(metadata.get('duration')) + timestamp = int_or_none(metadata.get('created_time')) + thumbnail = metadata.get('poster_url') + uploader = metadata.get('owner', {}).get('screenname') + uploader_id = metadata.get('owner', {}).get('id') + + subtitles = {} + for subtitle_lang, subtitle in metadata.get('subtitles', {}).get('data', {}).items(): + subtitles[subtitle_lang] = [{ + 'ext': determine_ext(subtitle_url), + 'url': subtitle_url, + } for subtitle_url in subtitle.get('urls', [])] + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'age_limit': age_limit, + 'view_count': view_count, + 'comment_count': comment_count, + 'formats': formats, + 'subtitles': subtitles, + } + + # vevo embed + vevo_id = self._search_regex( + r'[\w]*)', + webpage, 'vevo embed', default=None) + if vevo_id: + return self.url_result('vevo:%s' % vevo_id, 'Vevo') + + # fallback old player + embed_page = self._download_webpage_no_ff( + 'https://www.dailymotion.com/embed/video/%s' % video_id, + video_id, 'Downloading embed page') + + timestamp = parse_iso8601(self._html_search_meta( + 'video:release_date', webpage, 'upload date')) + + info = self._parse_json( + self._search_regex( + r'var info = ({.*?}),$', embed_page, + 'video info', flags=re.MULTILINE), + video_id) - embed_url = 'https://www.dailymotion.com/embed/video/%s' % video_id - embed_request = self._build_request(embed_url) - embed_page = self._download_webpage( - embed_request, video_id, 'Downloading embed page') - info = self._search_regex(r'var info = ({.*?}),$', embed_page, - 'video info', flags=re.MULTILINE) - info = json.loads(info) if info.get('error') is not None: msg = 'Couldn\'t get video, Dailymotion says: %s' % info['error']['title'] raise ExtractorError(msg, expected=True) @@ -138,16 +221,11 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'width': width, 'height': height, }) - if not formats: - raise ExtractorError('Unable to extract video URL') + self._sort_formats(formats) # subtitles video_subtitles = self.extract_subtitles(video_id, webpage) - view_count = str_to_int(self._search_regex( - r'video_views_count[^>]+>\s+([\d\.,]+)', - webpage, 'view count', fatal=False)) - title = self._og_search_title(webpage, default=None) if title is None: title = self._html_search_regex( @@ -158,12 +236,14 @@ class DailymotionIE(DailymotionBaseInfoExtractor): 'id': video_id, 'formats': formats, 'uploader': info['owner.screenname'], - 'upload_date': video_upload_date, + 'timestamp': timestamp, 'title': title, + 'description': description, 'subtitles': video_subtitles, 'thumbnail': info['thumbnail_url'], 'age_limit': age_limit, 'view_count': view_count, + 'duration': info['duration'] } def _get_subtitles(self, video_id, webpage): @@ -197,18 +277,26 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): }] def _extract_entries(self, id): - video_ids = [] + video_ids = set() + processed_urls = set() for pagenum in itertools.count(1): - request = self._build_request(self._PAGE_TEMPLATE % (id, pagenum)) - webpage = self._download_webpage(request, - id, 'Downloading page %s' % pagenum) + page_url = self._PAGE_TEMPLATE % (id, pagenum) + webpage, urlh = self._download_webpage_handle_no_ff( + page_url, id, 'Downloading page %s' % pagenum) + if urlh.geturl() in processed_urls: + self.report_warning('Stopped at duplicated page %s, which is the same as %s' % ( + page_url, urlh.geturl()), id) + break - video_ids.extend(re.findall(r'data-xid="(.+?)"', webpage)) + processed_urls.add(urlh.geturl()) + + for video_id in re.findall(r'data-xid="(.+?)"', webpage): + if video_id not in video_ids: + yield self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') + video_ids.add(video_id) if re.search(self._MORE_PAGES_INDICATOR, webpage) is None: break - return [self.url_result('http://www.dailymotion.com/video/%s' % video_id, 'Dailymotion') - for video_id in orderedSet(video_ids)] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -225,7 +313,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): class DailymotionUserIE(DailymotionPlaylistIE): IE_NAME = 'dailymotion:user' - _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:(?:old/)?user/)?(?P[^/]+)$' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?!(?:embed|#|video|playlist)/)(?:(?:old/)?user/)?(?P[^/]+)' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' _TESTS = [{ 'url': 'https://www.dailymotion.com/user/nqtv', @@ -234,6 +322,17 @@ class DailymotionUserIE(DailymotionPlaylistIE): 'title': 'Rémi Gaillard', }, 'playlist_mincount': 100, + }, { + 'url': 'http://www.dailymotion.com/user/UnderProject', + 'info_dict': { + 'id': 'UnderProject', + 'title': 'UnderProject', + }, + 'playlist_mincount': 1800, + 'expected_warnings': [ + 'Stopped at duplicated page', + ], + 'skip': 'Takes too long time', }] def _real_extract(self, url): @@ -284,8 +383,7 @@ class DailymotionCloudIE(DailymotionBaseInfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - request = self._build_request(url) - webpage = self._download_webpage(request, video_id) + webpage = self._download_webpage_no_ff(url, video_id) title = self._html_search_regex(r'([^>]+)', webpage, 'title') diff --git a/youtube_dl/extractor/dcn.py b/youtube_dl/extractor/dcn.py new file mode 100644 index 000000000..82261e25c --- /dev/null +++ b/youtube_dl/extractor/dcn.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request, +) +from ..utils import ( + int_or_none, + parse_iso8601, +) + + +class DCNIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?dcndigital\.ae/(?:#/)?(?:video/.+|show/\d+/.+?)/(?P\d+)' + _TEST = { + 'url': 'http://www.dcndigital.ae/#/show/199074/%D8%B1%D8%AD%D9%84%D8%A9-%D8%A7%D9%84%D8%B9%D9%85%D8%B1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/17375/6887', + 'info_dict': + { + 'id': '17375', + 'ext': 'mp4', + 'title': 'رحلة العمر : الحلقة 1', + 'description': 'md5:0156e935d870acb8ef0a66d24070c6d6', + 'thumbnail': 're:^https?://.*\.jpg$', + 'duration': 2041, + 'timestamp': 1227504126, + 'upload_date': '20081124', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + request = compat_urllib_request.Request( + 'http://admin.mangomolo.com/analytics/index.php/plus/video?id=%s' % video_id, + headers={'Origin': 'http://www.dcndigital.ae'}) + + video = self._download_json(request, video_id) + title = video.get('title_en') or video['title_ar'] + + webpage = self._download_webpage( + 'http://admin.mangomolo.com/analytics/index.php/customers/embed/video?' + + compat_urllib_parse.urlencode({ + 'id': video['id'], + 'user_id': video['user_id'], + 'signature': video['signature'], + 'countries': 'Q0M=', + 'filter': 'DENY', + }), video_id) + + m3u8_url = self._html_search_regex(r'file:\s*"([^"]+)', webpage, 'm3u8 url') + formats = self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native', m3u8_id='hls') + + rtsp_url = self._search_regex( + r']+href="(rtsp://[^"]+)"', webpage, 'rtsp url', fatal=False) + if rtsp_url: + formats.append({ + 'url': rtsp_url, + 'format_id': 'rtsp', + }) + + self._sort_formats(formats) + + img = video.get('img') + thumbnail = 'http://admin.mangomolo.com/analytics/%s' % img if img else None + duration = int_or_none(video.get('duration')) + description = video.get('description_en') or video.get('description_ar') + timestamp = parse_iso8601(video.get('create_time') or video.get('update_time'), ' ') + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'duration': duration, + 'timestamp': timestamp, + 'formats': formats, + } diff --git a/youtube_dl/extractor/dfb.py b/youtube_dl/extractor/dfb.py index 8049779b0..263532cc6 100644 --- a/youtube_dl/extractor/dfb.py +++ b/youtube_dl/extractor/dfb.py @@ -3,42 +3,47 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import unified_strdate class DFBIE(InfoExtractor): IE_NAME = 'tv.dfb.de' - _VALID_URL = r'https?://tv\.dfb\.de/video/[^/]+/(?P\d+)' + _VALID_URL = r'https?://tv\.dfb\.de/video/(?P[^/]+)/(?P\d+)' _TEST = { - 'url': 'http://tv.dfb.de/video/highlights-des-empfangs-in-berlin/9070/', + 'url': 'http://tv.dfb.de/video/u-19-em-stimmen-zum-spiel-gegen-russland/11633/', # The md5 is different each time 'info_dict': { - 'id': '9070', + 'id': '11633', + 'display_id': 'u-19-em-stimmen-zum-spiel-gegen-russland', 'ext': 'flv', - 'title': 'Highlights des Empfangs in Berlin', - 'upload_date': '20140716', + 'title': 'U 19-EM: Stimmen zum Spiel gegen Russland', + 'upload_date': '20150714', }, } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + display_id = mobj.group('display_id') - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage(url, display_id) player_info = self._download_xml( 'http://tv.dfb.de/server/hd_video.php?play=%s' % video_id, - video_id) + display_id) video_info = player_info.find('video') - f4m_info = self._download_xml(self._proto_relative_url(video_info.find('url').text.strip()), video_id) + f4m_info = self._download_xml( + self._proto_relative_url(video_info.find('url').text.strip()), display_id) token_el = f4m_info.find('token') manifest_url = token_el.attrib['url'] + '?' + 'hdnea=' + token_el.attrib['auth'] + '&hdcore=3.2.0' + formats = self._extract_f4m_formats(manifest_url, display_id) return { 'id': video_id, + 'display_id': display_id, 'title': video_info.find('title').text, - 'url': manifest_url, - 'ext': 'flv', 'thumbnail': self._og_search_thumbnail(webpage), - 'upload_date': ''.join(video_info.find('time_date').text.split('.')[::-1]), + 'upload_date': unified_strdate(video_info.find('time_date').text), + 'formats': formats, } diff --git a/youtube_dl/extractor/douyutv.py b/youtube_dl/extractor/douyutv.py index 479430c51..373b3b4b4 100644 --- a/youtube_dl/extractor/douyutv.py +++ b/youtube_dl/extractor/douyutv.py @@ -9,6 +9,7 @@ from ..compat import (compat_str, compat_basestring) class DouyuTVIE(InfoExtractor): + IE_DESC = '斗鱼' _VALID_URL = r'http://(?:www\.)?douyutv\.com/(?P[A-Za-z0-9]+)' _TESTS = [{ 'url': 'http://www.douyutv.com/iseven', diff --git a/youtube_dl/extractor/dramafever.py b/youtube_dl/extractor/dramafever.py index ca41a3abf..38e6597c8 100644 --- a/youtube_dl/extractor/dramafever.py +++ b/youtube_dl/extractor/dramafever.py @@ -23,8 +23,23 @@ class DramaFeverBaseIE(InfoExtractor): _LOGIN_URL = 'https://www.dramafever.com/accounts/login/' _NETRC_MACHINE = 'dramafever' + _CONSUMER_SECRET = 'DA59dtVXYLxajktV' + + _consumer_secret = None + + def _get_consumer_secret(self): + mainjs = self._download_webpage( + 'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js', + None, 'Downloading main.js', fatal=False) + if not mainjs: + return self._CONSUMER_SECRET + return self._search_regex( + r"var\s+cs\s*=\s*'([^']+)'", mainjs, + 'consumer secret', default=self._CONSUMER_SECRET) + def _real_initialize(self): self._login() + self._consumer_secret = self._get_consumer_secret() def _login(self): (username, password) = self._get_login_info() @@ -119,6 +134,23 @@ class DramaFeverIE(DramaFeverBaseIE): 'url': href, }] + series_id, episode_number = video_id.split('.') + episode_info = self._download_json( + # We only need a single episode info, so restricting page size to one episode + # and dealing with page number as with episode number + r'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_number=%s&page_size=1' + % (self._consumer_secret, series_id, episode_number), + video_id, 'Downloading episode info JSON', fatal=False) + if episode_info: + value = episode_info.get('value') + if value: + subfile = value[0].get('subfile') or value[0].get('new_subfile') + if subfile and subfile != 'http://www.dramafever.com/st/': + subtitles.setdefault('English', []).append({ + 'ext': 'srt', + 'url': subfile, + }) + return { 'id': video_id, 'title': title, @@ -152,27 +184,14 @@ class DramaFeverSeriesIE(DramaFeverBaseIE): 'playlist_count': 20, }] - _CONSUMER_SECRET = 'DA59dtVXYLxajktV' _PAGE_SIZE = 60 # max is 60 (see http://api.drama9.com/#get--api-4-episode-series-) - def _get_consumer_secret(self, video_id): - mainjs = self._download_webpage( - 'http://www.dramafever.com/static/51afe95/df2014/scripts/main.js', - video_id, 'Downloading main.js', fatal=False) - if not mainjs: - return self._CONSUMER_SECRET - return self._search_regex( - r"var\s+cs\s*=\s*'([^']+)'", mainjs, - 'consumer secret', default=self._CONSUMER_SECRET) - def _real_extract(self, url): series_id = self._match_id(url) - consumer_secret = self._get_consumer_secret(series_id) - series = self._download_json( 'http://www.dramafever.com/api/4/series/query/?cs=%s&series_id=%s' - % (consumer_secret, series_id), + % (self._consumer_secret, series_id), series_id, 'Downloading series JSON')['series'][series_id] title = clean_html(series['name']) @@ -182,7 +201,7 @@ class DramaFeverSeriesIE(DramaFeverBaseIE): for page_num in itertools.count(1): episodes = self._download_json( 'http://www.dramafever.com/api/4/episode/series/?cs=%s&series_id=%s&page_size=%d&page_number=%d' - % (consumer_secret, series_id, self._PAGE_SIZE, page_num), + % (self._consumer_secret, series_id, self._PAGE_SIZE, page_num), series_id, 'Downloading episodes JSON page #%d' % page_num) for episode in episodes.get('value', []): episode_url = episode.get('episode_url') diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index 9cb1bf301..b1cd4f5d4 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,9 +1,7 @@ from __future__ import unicode_literals -from ..compat import ( - compat_urllib_parse, -) from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote class EHowIE(InfoExtractor): @@ -26,7 +24,7 @@ class EHowIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = self._search_regex( r'(?:file|source)=(http[^\'"&]*)', webpage, 'video URL') - final_url = compat_urllib_parse.unquote(video_url) + final_url = compat_urllib_parse_unquote(video_url) uploader = self._html_search_meta('uploader', webpage) title = self._og_search_title(webpage).replace(' | eHow', '') diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 82dc27bc6..178a7ca4c 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -9,7 +9,7 @@ from ..compat import ( compat_http_client, compat_str, compat_urllib_error, - compat_urllib_parse, + compat_urllib_parse_unquote, compat_urllib_request, ) from ..utils import ( @@ -17,6 +17,8 @@ from ..utils import ( int_or_none, limit_length, urlencode_postdata, + get_element_by_id, + clean_html, ) @@ -42,6 +44,7 @@ class FacebookIE(InfoExtractor): 'id': '637842556329505', 'ext': 'mp4', 'title': 're:Did you know Kei Nishikori is the first Asian man to ever reach a Grand Slam', + 'uploader': 'Tennis on Facebook', } }, { 'note': 'Video without discernible title', @@ -50,6 +53,7 @@ class FacebookIE(InfoExtractor): 'id': '274175099429670', 'ext': 'mp4', 'title': 'Facebook video #274175099429670', + 'uploader': 'Asif Nawab Butt', }, 'expected_warnings': [ 'title' @@ -136,7 +140,7 @@ class FacebookIE(InfoExtractor): else: raise ExtractorError('Cannot parse data') data = dict(json.loads(m.group(1))) - params_raw = compat_urllib_parse.unquote(data['params']) + params_raw = compat_urllib_parse_unquote(data['params']) params = json.loads(params_raw) video_data = params['video_data'][0] @@ -161,6 +165,7 @@ class FacebookIE(InfoExtractor): video_title = limit_length(video_title, 80) if not video_title: video_title = 'Facebook video #%s' % video_id + uploader = clean_html(get_element_by_id('fbPhotoPageAuthorName', webpage)) return { 'id': video_id, @@ -168,4 +173,5 @@ class FacebookIE(InfoExtractor): 'formats': formats, 'duration': int_or_none(video_data.get('video_duration')), 'thumbnail': video_data.get('thumbnail_src'), + 'uploader': uploader, } diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index b2c984bf2..75723c00d 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -6,15 +6,11 @@ import re import json from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse_urlparse, - compat_urlparse, -) +from ..compat import compat_urlparse from ..utils import ( clean_html, ExtractorError, int_or_none, - float_or_none, parse_duration, determine_ext, ) @@ -59,12 +55,12 @@ class FranceTVBaseInfoExtractor(InfoExtractor): # See https://github.com/rg3/youtube-dl/issues/3963 # m3u8 urls work fine continue - video_url_parsed = compat_urllib_parse_urlparse(video_url) f4m_url = self._download_webpage( - 'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url_parsed.path, + 'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url, video_id, 'Downloading f4m manifest token', fatal=False) if f4m_url: - formats.extend(self._extract_f4m_formats(f4m_url, video_id, 1, format_id)) + formats.extend(self._extract_f4m_formats( + f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, 1, format_id)) elif ext == 'm3u8': formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id)) elif video_url.startswith('rtmp'): @@ -87,7 +83,7 @@ class FranceTVBaseInfoExtractor(InfoExtractor): 'title': info['titre'], 'description': clean_html(info['synopsis']), 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']), - 'duration': float_or_none(info.get('real_duration'), 1000) or parse_duration(info['duree']), + 'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']), 'timestamp': int_or_none(info['diffusion']['timestamp']), 'formats': formats, } @@ -160,11 +156,21 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor): class FranceTVIE(FranceTVBaseInfoExtractor): IE_NAME = 'francetv' IE_DESC = 'France 2, 3, 4, 5 and Ô' - _VALID_URL = r'''(?x)https?://www\.france[2345o]\.fr/ - (?: - emissions/.*?/(videos|emissions)/(?P[^/?]+) - | (emissions?|jt)/(?P[^/?]+) - )''' + _VALID_URL = r'''(?x) + https?:// + (?: + (?:www\.)?france[2345o]\.fr/ + (?: + emissions/[^/]+/(?:videos|diffusions)| + emission/[^/]+| + videos| + jt + ) + /| + embed\.francetv\.fr/\?ue= + ) + (?P[^/?]+) + ''' _TESTS = [ # france2 @@ -221,24 +227,46 @@ class FranceTVIE(FranceTVBaseInfoExtractor): }, # franceo { - 'url': 'http://www.franceo.fr/jt/info-afrique/04-12-2013', - 'md5': '52f0bfe202848b15915a2f39aaa8981b', + 'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015', + 'md5': '47d5816d3b24351cdce512ad7ab31da8', 'info_dict': { - 'id': '108634970', + 'id': '125377621', 'ext': 'flv', - 'title': 'Infô Afrique', - 'description': 'md5:ebf346da789428841bee0fd2a935ea55', - 'upload_date': '20140915', - 'timestamp': 1410822000, + 'title': 'Infô soir', + 'description': 'md5:01b8c6915a3d93d8bbbd692651714309', + 'upload_date': '20150718', + 'timestamp': 1437241200, + 'duration': 414, }, }, + { + # francetv embed + 'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87', + 'info_dict': { + 'id': 'EV_30231', + 'ext': 'flv', + 'title': 'Alcaline, le concert avec Calogero', + 'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff', + 'upload_date': '20150226', + 'timestamp': 1424989860, + 'duration': 5400, + }, + }, + { + 'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05', + 'only_matching': True, + }, + { + 'url': 'http://www.franceo.fr/videos/125377617', + 'only_matching': True, + } ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - webpage = self._download_webpage(url, mobj.group('key') or mobj.group('id')) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) video_id, catalogue = self._html_search_regex( - r'href="http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', + r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video ID').split('@') return self._extract_video(video_id, catalogue) diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 2d33fa7f5..b3f1bafcc 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -5,7 +5,7 @@ import json from .common import InfoExtractor from ..compat import ( - compat_urllib_parse, + compat_urllib_parse_unquote, compat_urlparse, ) from ..utils import ( @@ -75,7 +75,7 @@ class GameSpotIE(InfoExtractor): return { 'id': data_video['guid'], 'display_id': page_id, - 'title': compat_urllib_parse.unquote(data_video['title']), + 'title': compat_urllib_parse_unquote(data_video['title']), 'formats': formats, 'description': self._html_search_meta('description', webpage), 'thumbnail': self._og_search_thumbnail(webpage), diff --git a/youtube_dl/extractor/gdcvault.py b/youtube_dl/extractor/gdcvault.py index 43f916412..a6834db43 100644 --- a/youtube_dl/extractor/gdcvault.py +++ b/youtube_dl/extractor/gdcvault.py @@ -7,7 +7,10 @@ from ..compat import ( compat_urllib_parse, compat_urllib_request, ) -from ..utils import remove_end +from ..utils import ( + remove_end, + HEADRequest, +) class GDCVaultIE(InfoExtractor): @@ -73,10 +76,20 @@ class GDCVaultIE(InfoExtractor): return video_formats def _parse_flv(self, xml_description): - video_formats = [] + formats = [] akamai_url = xml_description.find('./metadata/akamaiHost').text + audios = xml_description.find('./metadata/audios') + if audios is not None: + for audio in audios: + formats.append({ + 'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url, + 'play_path': remove_end(audio.get('url'), '.flv'), + 'ext': 'flv', + 'vcodec': 'none', + 'format_id': audio.get('code'), + }) slide_video_path = xml_description.find('./metadata/slideVideo').text - video_formats.append({ + formats.append({ 'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url, 'play_path': remove_end(slide_video_path, '.flv'), 'ext': 'flv', @@ -86,7 +99,7 @@ class GDCVaultIE(InfoExtractor): 'format_id': 'slides', }) speaker_video_path = xml_description.find('./metadata/speakerVideo').text - video_formats.append({ + formats.append({ 'url': 'rtmp://%s/ondemand?ovpfv=1.1' % akamai_url, 'play_path': remove_end(speaker_video_path, '.flv'), 'ext': 'flv', @@ -95,7 +108,7 @@ class GDCVaultIE(InfoExtractor): 'preference': -1, 'format_id': 'speaker', }) - return video_formats + return formats def _login(self, webpage_url, display_id): (username, password) = self._get_login_info() @@ -133,16 +146,18 @@ class GDCVaultIE(InfoExtractor): r's1\.addVariable\("file",\s*encodeURIComponent\("(/[^"]+)"\)\);', start_page, 'url', default=None) if direct_url: - video_url = 'http://www.gdcvault.com/' + direct_url title = self._html_search_regex( r'Session Name\s*(.*?)', start_page, 'title') + video_url = 'http://www.gdcvault.com' + direct_url + # resolve the url so that we can detect the correct extension + head = self._request_webpage(HEADRequest(video_url), video_id) + video_url = head.geturl() return { 'id': video_id, 'display_id': display_id, 'url': video_url, - 'ext': 'flv', 'title': title, } @@ -168,8 +183,8 @@ class GDCVaultIE(InfoExtractor): # Fallback to the older format xml_name = self._html_search_regex(r'