diff options
91 files changed, 2314 insertions, 1075 deletions
@@ -124,3 +124,6 @@ Mohammad Teimori Pabandi Roman Le Négrate Matthias Küch Julian Richen +Ping O. +Mister Hat +Peter Ding @@ -17,12 +17,12 @@ youtube-dl - download videos from youtube.com or other video platforms To install it right away for all UNIX users (Linux, OS X, etc.), type: sudo curl https://yt-dl.org/latest/youtube-dl -o /usr/local/bin/youtube-dl - sudo chmod a+x /usr/local/bin/youtube-dl + sudo chmod a+rx /usr/local/bin/youtube-dl If you do not have curl, you can alternatively use a recent wget: sudo wget https://yt-dl.org/downloads/latest/youtube-dl -O /usr/local/bin/youtube-dl - sudo chmod a+x /usr/local/bin/youtube-dl + sudo chmod a+rx /usr/local/bin/youtube-dl Windows users can [download a .exe file](https://yt-dl.org/latest/youtube-dl.exe) and place it in their home directory or any other location on their [PATH](http://en.wikipedia.org/wiki/PATH_%28variable%29). @@ -168,7 +168,7 @@ which means you can modify it, redistribute it or use it however you like. --no-progress Do not print progress bar --console-title Display progress in console titlebar -v, --verbose Print various debugging information - --dump-pages Print downloaded pages to debug problems (very verbose) + --dump-pages Print downloaded pages encoded using base64 to debug problems (very verbose) --write-pages Write downloaded intermediary pages to files in the current directory to debug problems --print-traffic Display sent and read HTTP traffic -C, --call-home Contact the youtube-dl server for debugging @@ -220,7 +220,7 @@ which means you can modify it, redistribute it or use it however you like. --embed-thumbnail Embed thumbnail in the audio as cover art --add-metadata Write metadata to the video file --metadata-from-title FORMAT Parse additional metadata like song title / artist from the video title. The format syntax is the same as --output, the parsed - parameters replace existing values. Additional templates: %(album), %(artist). Example: --metadata-from-title "%(artist)s - + parameters replace existing values. Additional templates: %(album)s, %(artist)s. Example: --metadata-from-title "%(artist)s - %(title)s" matches a title like "Coldplay - Paradise" --xattrs Write metadata to the video file's xattrs (using dublin core and xdg standards) --fixup POLICY Automatically correct known faults of the file. One of never (do nothing), warn (only emit a warning), detect_or_warn(the default; diff --git a/docs/supportedsites.md b/docs/supportedsites.md index 43fbe8b1d..d147b53fe 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -10,6 +10,7 @@ - **56.com** - **5min** - **8tracks** + - **91porn** - **9gag** - **abc.net.au** - **Abc7News** @@ -26,8 +27,7 @@ - **anitube.se** - **AnySex** - **Aparat** - - **AppleDailyAnimationNews** - - **AppleDailyRealtimeNews** + - **AppleDaily** - **AppleTrailers** - **archive.org**: archive.org videos - **ARD** @@ -142,6 +142,7 @@ - **Eporner** - **EroProfile** - **Escapist** + - **ESPN** (Currently broken) - **EveryonesMixtape** - **exfm**: ex.fm - **ExpoTV** @@ -151,7 +152,6 @@ - **fc2** - **fernsehkritik.tv** - **fernsehkritik.tv:postecke** - - **Firedrive** - **Firstpost** - **Flickr** - **Folketinget**: Folketinget (ft.dk; Danish parliament) @@ -229,6 +229,7 @@ - **KanalPlay**: Kanal 5/9/11 Play - **Kankan** - **Karaoketv** + - **KarriereVideos** - **keek** - **KeezMovies** - **KhanAcademy** @@ -319,8 +320,10 @@ - **Noco** - **Normalboots** - **NosVideo** + - **Nova**: TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz - **novamov**: NovaMov - **Nowness** + - **NowTV** - **nowvideo**: NowVideo - **npo.nl** - **npo.nl:live** @@ -338,6 +341,7 @@ - **OktoberfestTV** - **on.aol.com** - **Ooyala** + - **OoyalaExternal** - **OpenFilm** - **orf:fm4**: radio FM4 - **orf:iptv**: iptv.ORF.at @@ -391,7 +395,6 @@ - **Rte** - **rtl.nl**: rtl.nl and rtlxl.nl - **RTL2** - - **RTLnow** - **RTP** - **RTS**: RTS.ch - **rtve.es:alacarta**: RTVE a la carta @@ -429,8 +432,9 @@ - **smotri:community**: Smotri.com community videos - **smotri:user**: Smotri.com user videos - **Snotr** - - **Sockshare** - **Sohu** + - **soompi** + - **soompi:show** - **soundcloud** - **soundcloud:playlist** - **soundcloud:set** @@ -451,6 +455,7 @@ - **Spike** - **Sport5** - **SportBox** + - **SportBoxEmbed** - **SportDeutschland** - **Srf** - **SRMediathek**: Saarländischer Rundfunk @@ -504,12 +509,15 @@ - **Trilulilu** - **TruTube** - **Tube8** + - **TubiTv** - **Tudou** - **Tumblr** - **TuneIn** - **Turbo** - **Tutv** - **tv.dfb.de** + - **TV2** + - **TV2Article** - **TV4**: tv4.se and tv4play.se - **tvigle**: Интернет-телевидение Tvigle.ru - **tvp.pl** @@ -559,6 +567,7 @@ - **vier:videos** - **Viewster** - **viki** + - **viki:channel** - **vimeo** - **vimeo:album** - **vimeo:channel** diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index 82b827536..a13c09ef4 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -12,6 +12,7 @@ import copy from test.helper import FakeYDL, assertRegexpMatches 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 @@ -507,6 +508,51 @@ class TestYoutubeDL(unittest.TestCase): res = get_videos(f) self.assertEqual(res, ['1']) + def test_playlist_items_selection(self): + entries = [{ + 'id': compat_str(i), + 'title': compat_str(i), + 'url': TEST_URL, + } for i in range(1, 5)] + playlist = { + '_type': 'playlist', + 'id': 'test', + 'entries': entries, + 'extractor': 'test:playlist', + 'extractor_key': 'test:playlist', + 'webpage_url': 'http://example.com', + } + + def get_ids(params): + ydl = YDL(params) + # make a copy because the dictionary can be modified + ydl.process_ie_result(playlist.copy()) + return [int(v['id']) for v in ydl.downloaded_info_dicts] + + result = get_ids({}) + self.assertEqual(result, [1, 2, 3, 4]) + + result = get_ids({'playlistend': 10}) + self.assertEqual(result, [1, 2, 3, 4]) + + result = get_ids({'playlistend': 2}) + self.assertEqual(result, [1, 2]) + + result = get_ids({'playliststart': 10}) + self.assertEqual(result, []) + + result = get_ids({'playliststart': 2}) + self.assertEqual(result, [2, 3, 4]) + + result = get_ids({'playlist_items': '2-4'}) + self.assertEqual(result, [2, 3, 4]) + + result = get_ids({'playlist_items': '2,4'}) + self.assertEqual(result, [2, 4]) + + result = get_ids({'playlist_items': '10'}) + self.assertEqual(result, []) + if __name__ == '__main__': unittest.main() diff --git a/test/test_aes.py b/test/test_aes.py index 4dc7de7b5..315a3f5ae 100644 --- a/test/test_aes.py +++ b/test/test_aes.py @@ -39,7 +39,7 @@ class TestAES(unittest.TestCase): encrypted = base64.b64encode( intlist_to_bytes(self.iv[:8]) + b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae' - ) + ).decode('utf-8') decrypted = (aes_decrypt_text(encrypted, password, 16)) self.assertEqual(decrypted, self.secret_msg) @@ -47,7 +47,7 @@ class TestAES(unittest.TestCase): encrypted = base64.b64encode( intlist_to_bytes(self.iv[:8]) + b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83' - ) + ).decode('utf-8') decrypted = (aes_decrypt_text(encrypted, password, 32)) self.assertEqual(decrypted, self.secret_msg) diff --git a/test/test_subtitles.py b/test/test_subtitles.py index 891ee620b..c4e3adb67 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -266,7 +266,7 @@ class TestNRKSubtitles(BaseTestSubtitles): self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() self.assertEqual(set(subtitles.keys()), set(['no'])) - self.assertEqual(md5(subtitles['no']), '1d221e6458c95c5494dcd38e6a1f129a') + self.assertEqual(md5(subtitles['no']), '544fa917d3197fcbee64634559221cc2') class TestRaiSubtitles(BaseTestSubtitles): diff --git a/test/test_utils.py b/test/test_utils.py index b40107037..e13e11b59 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -621,6 +621,21 @@ Line ''' self.assertEqual(dfxp2srt(dfxp_data), srt_data) + dfxp_data_no_default_namespace = '''<?xml version="1.0" encoding="UTF-8"?> + <tt xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter"> + <body> + <div xml:lang="en"> + <p begin="0" end="1">The first line</p> + </div> + </body> + </tt>''' + srt_data = '''1 +00:00:00,000 --> 00:00:01,000 +The first line + +''' + self.assertEqual(dfxp2srt(dfxp_data_no_default_namespace), srt_data) + if __name__ == '__main__': unittest.main() @@ -4,6 +4,8 @@ envlist = py26,py27,py33,py34 deps = nose coverage +# We need a valid $HOME for test_compat_expanduser +passenv = HOME defaultargs = test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 691f3e09f..aa6ec9d9a 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -49,6 +49,7 @@ from .utils import ( ExtractorError, format_bytes, formatSeconds, + HEADRequest, locked_file, make_HTTPS_handler, MaxDownloadsReached, @@ -759,7 +760,9 @@ class YoutubeDL(object): if isinstance(ie_entries, list): n_all_entries = len(ie_entries) if playlistitems: - entries = [ie_entries[i - 1] for i in playlistitems] + entries = [ + ie_entries[i - 1] for i in playlistitems + if -n_all_entries <= i - 1 < n_all_entries] else: entries = ie_entries[playliststart:playlistend] n_entries = len(entries) @@ -921,8 +924,9 @@ class YoutubeDL(object): if f.get('vcodec') != 'none' and f.get('acodec') != 'none'] if audiovideo_formats: return audiovideo_formats[format_idx] - # for audio only urls, select the best/worst audio format - elif all(f.get('acodec') != 'none' for f in available_formats): + # 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 = [ @@ -1045,6 +1049,8 @@ class YoutubeDL(object): if not formats: raise ExtractorError('No video formats found!') + formats_dict = {} + # We check that all the formats have the format and format_id fields for i, format in enumerate(formats): if 'url' not in format: @@ -1052,6 +1058,18 @@ class YoutubeDL(object): if format.get('format_id') is None: format['format_id'] = compat_str(i) + format_id = format['format_id'] + if format_id not in formats_dict: + formats_dict[format_id] = [] + formats_dict[format_id].append(format) + + # Make sure all formats have unique format_id + for format_id, ambiguous_formats in formats_dict.items(): + if len(ambiguous_formats) > 1: + for i, format in enumerate(ambiguous_formats): + format['format_id'] = '%s-%d' % (format_id, i) + + for i, format in enumerate(formats): if format.get('format') is None: format['format'] = '{id} - {res}{note}'.format( id=format['format_id'], @@ -1366,7 +1384,7 @@ class YoutubeDL(object): postprocessors = [] self.report_warning('You have requested multiple ' 'formats but ffmpeg or avconv are not installed.' - ' The formats won\'t be merged') + ' The formats won\'t be merged.') else: postprocessors = [merger] @@ -1393,8 +1411,8 @@ class YoutubeDL(object): requested_formats = info_dict['requested_formats'] if self.params.get('merge_output_format') is None and not compatible_formats(requested_formats): info_dict['ext'] = 'mkv' - self.report_warning('You have requested formats incompatible for merge. ' - 'The formats will be merged into mkv') + self.report_warning( + 'Requested formats are incompatible for merge and will be merged into mkv.') # Ensure filename always has a correct extension for successful merge filename = '%s.%s' % (filename_wo_ext, info_dict['ext']) if os.path.exists(encodeFilename(filename)): @@ -1525,6 +1543,7 @@ class YoutubeDL(object): pps_chain.extend(ie_info['__postprocessors']) pps_chain.extend(self._pps) for pp in pps_chain: + files_to_delete = [] try: files_to_delete, info = pp.run(info) except PostProcessingError as e: @@ -1703,7 +1722,8 @@ class YoutubeDL(object): if req_is_string: req = url_escaped else: - req = compat_urllib_request.Request( + 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) diff --git a/youtube_dl/aes.py b/youtube_dl/aes.py index 07224d508..7817adcfd 100644 --- a/youtube_dl/aes.py +++ b/youtube_dl/aes.py @@ -152,7 +152,7 @@ def aes_decrypt_text(data, password, key_size_bytes): """ NONCE_LENGTH_BYTES = 8 - data = bytes_to_intlist(base64.b64decode(data)) + data = bytes_to_intlist(base64.b64decode(data.encode('utf-8'))) password = bytes_to_intlist(password.encode('utf-8')) key = password[:key_size_bytes] + [0] * (key_size_bytes - len(password)) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 860023d14..631381eea 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -141,6 +141,7 @@ from .engadget import EngadgetIE from .eporner import EpornerIE from .eroprofile import EroProfileIE from .escapist import EscapistIE +from .espn import ESPNIE from .everyonesmixtape import EveryonesMixtapeIE from .exfm import ExfmIE from .expotv import ExpoTVIE @@ -148,7 +149,6 @@ from .extremetube import ExtremeTubeIE from .facebook import FacebookIE from .faz import FazIE from .fc2 import FC2IE -from .firedrive import FiredriveIE from .firstpost import FirstpostIE from .firsttv import FirstTVIE from .fivemin import FiveMinIE @@ -243,6 +243,7 @@ from .kaltura import KalturaIE from .kanalplay import KanalPlayIE from .kankan import KankanIE from .karaoketv import KaraoketvIE +from .karrierevideos import KarriereVideosIE from .keezmovies import KeezMoviesIE from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE @@ -337,8 +338,7 @@ from .newstube import NewstubeIE from .nextmedia import ( NextMediaIE, NextMediaActionNewsIE, - AppleDailyRealtimeNewsIE, - AppleDailyAnimationNewsIE + AppleDailyIE, ) from .nfb import NFBIE from .nfl import NFLIE @@ -352,8 +352,10 @@ from .ninegag import NineGagIE from .noco import NocoIE from .normalboots import NormalbootsIE from .nosvideo import NosVideoIE +from .nova import NovaIE from .novamov import NovaMovIE from .nowness import NownessIE +from .nowtv import NowTVIE from .nowvideo import NowVideoIE from .npo import ( NPOIE, @@ -376,7 +378,10 @@ from .nytimes import ( from .nuvid import NuvidIE from .odnoklassniki import OdnoklassnikiIE from .oktoberfesttv import OktoberfestTVIE -from .ooyala import OoyalaIE +from .ooyala import ( + OoyalaIE, + OoyalaExternalIE, +) from .openfilm import OpenFilmIE from .orf import ( ORFTVthekIE, @@ -397,6 +402,7 @@ from .playfm import PlayFMIE from .playvid import PlayvidIE from .playwire import PlaywireIE from .podomatic import PodomaticIE +from .porn91 import Porn91IE from .pornhd import PornHdIE from .pornhub import ( PornHubIE, @@ -434,7 +440,6 @@ from .roxwel import RoxwelIE from .rtbf import RTBFIE from .rte import RteIE from .rtlnl import RtlNlIE -from .rtlnow import RTLnowIE from .rtl2 import RTL2IE from .rtp import RTPIE from .rts import RTSIE @@ -477,8 +482,11 @@ from .smotri import ( SmotriBroadcastIE, ) from .snotr import SnotrIE -from .sockshare import SockshareIE from .sohu import SohuIE +from .soompi import ( + SoompiIE, + SoompiShowIE, +) from .soundcloud import ( SoundcloudIE, SoundcloudSetIE, @@ -503,7 +511,10 @@ from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE from .spike import SpikeIE from .sport5 import Sport5IE -from .sportbox import SportBoxIE +from .sportbox import ( + SportBoxIE, + SportBoxEmbedIE, +) from .sportdeutschland import SportDeutschlandIE from .srf import SrfIE from .srmediathek import SRMediathekIE @@ -561,11 +572,16 @@ from .traileraddict import TrailerAddictIE from .trilulilu import TriluliluIE from .trutube import TruTubeIE from .tube8 import Tube8IE +from .tubitv import TubiTvIE from .tudou import TudouIE from .tumblr import TumblrIE from .tunein import TuneInIE from .turbo import TurboIE from .tutv import TutvIE +from .tv2 import ( + TV2IE, + TV2ArticleIE, +) from .tv4 import TV4IE from .tvigle import TvigleIE from .tvp import TvpIE, TvpSeriesIE @@ -637,7 +653,10 @@ from .vine import ( VineIE, VineUserIE, ) -from .viki import VikiIE +from .viki import ( + VikiIE, + VikiChannelIE, +) from .vk import ( VKIE, VKUserVideosIE, diff --git a/youtube_dl/extractor/aftonbladet.py b/youtube_dl/extractor/aftonbladet.py index a117502bc..e0518cf26 100644 --- a/youtube_dl/extractor/aftonbladet.py +++ b/youtube_dl/extractor/aftonbladet.py @@ -6,11 +6,11 @@ from ..utils import int_or_none class AftonbladetIE(InfoExtractor): - _VALID_URL = r'http://tv\.aftonbladet\.se/webbtv.+?(?P<id>article[0-9]+)\.ab(?:$|[?#])' + _VALID_URL = r'http://tv\.aftonbladet\.se/abtv/articles/(?P<id>[0-9]+)' _TEST = { - 'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab', + 'url': 'http://tv.aftonbladet.se/abtv/articles/36015', 'info_dict': { - 'id': 'article36015', + 'id': '36015', 'ext': 'mp4', 'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna', 'description': 'Jupiters måne mest aktiv av alla himlakroppar', @@ -25,8 +25,9 @@ class AftonbladetIE(InfoExtractor): # find internal video meta data meta_url = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json' - internal_meta_id = self._html_search_regex( - r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id') + player_config = self._parse_json(self._html_search_regex( + r'data-player-config="([^"]+)"', webpage, 'player config'), video_id) + internal_meta_id = player_config['videoId'] internal_meta_url = meta_url % internal_meta_id internal_meta_json = self._download_json( internal_meta_url, video_id, 'Downloading video meta data') diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py index 8273bd6c9..76de24477 100644 --- a/youtube_dl/extractor/arte.py +++ b/youtube_dl/extractor/arte.py @@ -7,7 +7,6 @@ from .common import InfoExtractor from ..utils import ( find_xpath_attr, unified_strdate, - get_element_by_id, get_element_by_attribute, int_or_none, qualities, @@ -195,7 +194,9 @@ class ArteTVFutureIE(ArteTVPlus7IE): def _real_extract(self, url): anchor_id, lang = self._extract_url_info(url) webpage = self._download_webpage(url, anchor_id) - row = get_element_by_id(anchor_id, webpage) + row = self._search_regex( + r'(?s)id="%s"[^>]*>.+?(<div[^>]*arte_vp_url[^>]*>)' % anchor_id, + webpage, 'row') return self._extract_from_webpage(row, anchor_id, lang) diff --git a/youtube_dl/extractor/bilibili.py b/youtube_dl/extractor/bilibili.py index 7ca835e31..2103ed73a 100644 --- a/youtube_dl/extractor/bilibili.py +++ b/youtube_dl/extractor/bilibili.py @@ -3,6 +3,8 @@ from __future__ import unicode_literals import re import itertools +import json +import xml.etree.ElementTree as ET from .common import InfoExtractor from ..utils import ( @@ -67,11 +69,19 @@ class BiliBiliIE(InfoExtractor): entries = [] - lq_doc = self._download_xml( + lq_page = self._download_webpage( 'http://interface.bilibili.com/v_cdn_play?appkey=1&cid=%s' % cid, video_id, note='Downloading LQ video info' ) + try: + err_info = json.loads(lq_page) + raise ExtractorError( + 'BiliBili said: ' + err_info['error_text'], expected=True) + except ValueError: + pass + + lq_doc = ET.fromstring(lq_page) lq_durls = lq_doc.findall('./durl') hq_doc = self._download_xml( @@ -80,9 +90,11 @@ class BiliBiliIE(InfoExtractor): note='Downloading HQ video info', fatal=False, ) - hq_durls = hq_doc.findall('./durl') if hq_doc is not False else itertools.repeat(None) - - assert len(lq_durls) == len(hq_durls) + if hq_doc is not False: + hq_durls = hq_doc.findall('./durl') + assert len(lq_durls) == len(hq_durls) + else: + hq_durls = itertools.repeat(None) i = 1 for lq_durl, hq_durl in zip(lq_durls, hq_durls): diff --git a/youtube_dl/extractor/cbsnews.py b/youtube_dl/extractor/cbsnews.py index 7e47960ab..52e61d85b 100644 --- a/youtube_dl/extractor/cbsnews.py +++ b/youtube_dl/extractor/cbsnews.py @@ -32,7 +32,7 @@ class CBSNewsIE(InfoExtractor): 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack', 'ext': 'flv', 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack', - 'thumbnail': 'http://cbsnews2.cbsistatic.com/hub/i/r/2014/04/04/0c9fbc66-576b-41ca-8069-02d122060dd2/thumbnail/140x90/6dad7a502f88875ceac38202984b6d58/en-0404-werner-replace-640x360.jpg', + 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 205, }, 'params': { diff --git a/youtube_dl/extractor/ccc.py b/youtube_dl/extractor/ccc.py index 2a5d4be18..6924eac70 100644 --- a/youtube_dl/extractor/ccc.py +++ b/youtube_dl/extractor/ccc.py @@ -16,7 +16,7 @@ class CCCIE(InfoExtractor): _TEST = { 'url': 'http://media.ccc.de/browse/congress/2013/30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor.html#video', - 'md5': '205a365d0d57c0b1e43a12c9ffe8f9be', + 'md5': '3a1eda8f3a29515d27f5adb967d7e740', 'info_dict': { 'id': '20131228183', 'ext': 'mp4', @@ -51,7 +51,7 @@ class CCCIE(InfoExtractor): matches = re.finditer(r'''(?xs) <(?:span|div)\s+class='label\s+filetype'>(?P<format>.*?)</(?:span|div)>\s* - <a\s+href='(?P<http_url>[^']+)'>\s* + <a\s+download\s+href='(?P<http_url>[^']+)'>\s* (?: .*? <a\s+href='(?P<torrent_url>[^']+\.torrent)' diff --git a/youtube_dl/extractor/chilloutzone.py b/youtube_dl/extractor/chilloutzone.py index c922f6959..0206d96db 100644 --- a/youtube_dl/extractor/chilloutzone.py +++ b/youtube_dl/extractor/chilloutzone.py @@ -57,7 +57,7 @@ class ChilloutzoneIE(InfoExtractor): base64_video_info = self._html_search_regex( r'var cozVidData = "(.+?)";', webpage, 'video data') - decoded_video_info = base64.b64decode(base64_video_info).decode("utf-8") + decoded_video_info = base64.b64decode(base64_video_info.encode('utf-8')).decode('utf-8') video_info_dict = json.loads(decoded_video_info) # get video information from dict diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index cf0a7551b..c949a4814 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -60,6 +60,17 @@ class CinemassacreIE(InfoExtractor): 'uploader_id': 'Cinemassacre', 'title': 'AVGN: McKids', } + }, + { + 'url': 'http://cinemassacre.com/2015/05/25/mario-kart-64-nintendo-64-james-mike-mondays/', + 'md5': '1376908e49572389e7b06251a53cdd08', + 'info_dict': { + 'id': 'Cinemassacre-555779690c440', + 'ext': 'mp4', + 'description': 'Let’s Play Mario Kart 64 !! Mario Kart 64 is a classic go-kart racing game released for the Nintendo 64 (N64). Today James & Mike do 4 player Battle Mode with Kyle and Bootsy!', + 'title': 'Mario Kart 64 (Nintendo 64) James & Mike Mondays', + 'upload_date': '20150525', + } } ] @@ -72,7 +83,7 @@ class CinemassacreIE(InfoExtractor): playerdata_url = self._search_regex( [ - r'src="(http://player\.screenwavemedia\.com/play/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', + r'src="(http://(?:player2\.screenwavemedia\.com|player\.screenwavemedia\.com/play)/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"', ], webpage, 'player data URL', default=None) diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index 5efc5f4fe..3b1bd4033 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -12,7 +12,7 @@ from ..utils import ( class CNNIE(InfoExtractor): _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/ - (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z]{3,5})(?:-ap)?|(?=&)))''' + (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:[a-z\-]+)|(?=&)))''' _TESTS = [{ 'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 65bb77086..cecf917ff 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -786,8 +786,8 @@ class InfoExtractor(object): return True except ExtractorError as e: if isinstance(e.cause, compat_HTTPError): - self.report_warning( - '%s URL is invalid, skipping' % item, video_id) + self.to_screen( + '%s: %s URL is invalid, skipping' % (video_id, item)) return False raise diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 1c77df47e..41f0c736d 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -76,8 +76,8 @@ class CrunchyrollIE(InfoExtractor): self._login() def _decrypt_subtitles(self, data, iv, id): - data = bytes_to_intlist(data) - iv = bytes_to_intlist(iv) + data = bytes_to_intlist(base64.b64decode(data.encode('utf-8'))) + iv = bytes_to_intlist(base64.b64decode(iv.encode('utf-8'))) id = int(id) def obfuscate_key_aux(count, modulo, start): @@ -179,6 +179,16 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text return output + def _extract_subtitles(self, subtitle): + sub_root = xml.etree.ElementTree.fromstring(subtitle) + return [{ + 'ext': 'srt', + 'data': self._convert_subtitles_to_srt(sub_root), + }, { + 'ext': 'ass', + 'data': self._convert_subtitles_to_ass(sub_root), + }] + def _get_subtitles(self, video_id, webpage): subtitles = {} for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): @@ -190,25 +200,11 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text data = self._search_regex(r'<data>([^<]+)', sub_page, 'subtitle_data', fatal=False) if not id or not iv or not data: continue - id = int(id) - iv = base64.b64decode(iv) - data = base64.b64decode(data) - subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8') lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) if not lang_code: continue - sub_root = xml.etree.ElementTree.fromstring(subtitle) - subtitles[lang_code] = [ - { - 'ext': 'srt', - 'data': self._convert_subtitles_to_srt(sub_root), - }, - { - 'ext': 'ass', - 'data': self._convert_subtitles_to_ass(sub_root), - }, - ] + subtitles[lang_code] = self._extract_subtitles(subtitle) return subtitles def _real_extract(self, url): diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index db10b8d00..70aa4333c 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -225,7 +225,7 @@ class DailymotionPlaylistIE(DailymotionBaseInfoExtractor): class DailymotionUserIE(DailymotionPlaylistIE): IE_NAME = 'dailymotion:user' - _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:old/)?user/(?P<user>[^/]+)' + _VALID_URL = r'https?://(?:www\.)?dailymotion\.[a-z]{2,3}/(?:(?:old/)?user/)?(?P<user>[^/]+)$' _PAGE_TEMPLATE = 'http://www.dailymotion.com/user/%s/%s' _TESTS = [{ 'url': 'https://www.dailymotion.com/user/nqtv', @@ -239,7 +239,8 @@ class DailymotionUserIE(DailymotionPlaylistIE): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user = mobj.group('user') - webpage = self._download_webpage(url, user) + webpage = self._download_webpage( + 'https://www.dailymotion.com/user/%s' % user, user) full_user = unescapeHTML(self._html_search_regex( r'<a class="nav-image" title="([^"]+)" href="/%s">' % re.escape(user), webpage, 'user')) diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index f25ab319e..baa24c6d1 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,8 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -from .common import InfoExtractor, ExtractorError -from ..utils import parse_iso8601 +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_iso8601, +) class DRTVIE(InfoExtractor): @@ -60,19 +63,31 @@ class DRTVIE(InfoExtractor): restricted_to_denmark = asset['RestrictedToDenmark'] spoken_subtitles = asset['Target'] == 'SpokenSubtitles' for link in asset['Links']: - target = link['Target'] uri = link['Uri'] + target = link['Target'] format_id = target - preference = -1 if target == 'HDS' else -2 + preference = None if spoken_subtitles: - preference -= 2 + preference = -1 format_id += '-spoken-subtitles' - formats.append({ - 'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri, - 'format_id': format_id, - 'ext': link['FileFormat'], - 'preference': preference, - }) + if target == 'HDS': + formats.extend(self._extract_f4m_formats( + uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43', + video_id, preference, f4m_id=format_id)) + elif target == 'HLS': + formats.extend(self._extract_m3u8_formats( + uri, video_id, 'mp4', preference=preference, + m3u8_id=format_id)) + else: + bitrate = link.get('Bitrate') + if bitrate: + format_id += '-%s' % bitrate + formats.append({ + 'url': uri, + 'format_id': format_id, + 'tbr': bitrate, + 'ext': link.get('FileFormat'), + }) subtitles_list = asset.get('SubtitlesList') if isinstance(subtitles_list, list): LANGS = { diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py index 70f8efe27..4827022e0 100644 --- a/youtube_dl/extractor/empflix.py +++ b/youtube_dl/extractor/empflix.py @@ -4,22 +4,28 @@ from .tnaflix import TNAFlixIE class EMPFlixIE(TNAFlixIE): - _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<display_id>[0-9a-zA-Z-]+)-(?P<id>[0-9]+)\.html' + _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html' _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"' _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"' _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' - _TEST = { - 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', - 'md5': 'b1bc15b6412d33902d6e5952035fcabc', - 'info_dict': { - 'id': '33051', - 'display_id': 'Amateur-Finger-Fuck', - 'ext': 'mp4', - 'title': 'Amateur Finger Fuck', - 'description': 'Amateur solo finger fucking.', - 'thumbnail': 're:https?://.*\.jpg$', - 'age_limit': 18, + _TESTS = [ + { + 'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html', + 'md5': 'b1bc15b6412d33902d6e5952035fcabc', + 'info_dict': { + 'id': '33051', + 'display_id': 'Amateur-Finger-Fuck', + 'ext': 'mp4', + 'title': 'Amateur Finger Fuck', + 'description': 'Amateur solo finger fucking.', + 'thumbnail': 're:https?://.*\.jpg$', + 'age_limit': 18, + } + }, + { + 'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html', + 'only_matching': True, } - } + ] diff --git a/youtube_dl/extractor/espn.py b/youtube_dl/extractor/espn.py new file mode 100644 index 000000000..e6f8f0337 --- /dev/null +++ b/youtube_dl/extractor/espn.py @@ -0,0 +1,55 @@ +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class ESPNIE(InfoExtractor): + _VALID_URL = r'https?://espn\.go\.com/(?:[^/]+/)*(?P<id>[^/]+)' + _WORKING = False + _TESTS = [{ + 'url': 'http://espn.go.com/video/clip?id=10365079', + 'info_dict': { + 'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG', + 'ext': 'mp4', + 'title': 'dm_140128_30for30Shorts___JudgingJewellv2', + 'description': '', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'https://espn.go.com/video/iframe/twitter/?cms=espn&id=10365079', + 'only_matching': True, + }, { + 'url': 'http://espn.go.com/nba/recap?gameId=400793786', + 'only_matching': True, + }, { + 'url': 'http://espn.go.com/blog/golden-state-warriors/post/_/id/593/how-warriors-rapidly-regained-a-winning-edge', + 'only_matching': True, + }, { + 'url': 'http://espn.go.com/sports/endurance/story/_/id/12893522/dzhokhar-tsarnaev-sentenced-role-boston-marathon-bombings', + 'only_matching': True, + }, { + 'url': 'http://espn.go.com/nba/playoffs/2015/story/_/id/12887571/john-wall-washington-wizards-no-swelling-left-hand-wrist-game-5-return', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + video_id = self._search_regex( + r'class="video-play-button"[^>]+data-id="(\d+)', + webpage, 'video id') + + player = self._download_webpage( + 'https://espn.go.com/video/iframe/twitter/?id=%s' % video_id, video_id) + + pcode = self._search_regex( + r'["\']pcode=([^"\']+)["\']', player, 'pcode') + + return self.url_result( + 'ooyalaexternal:espn:%s:%s' % (video_id, pcode), + 'OoyalaExternal') diff --git a/youtube_dl/extractor/facebook.py b/youtube_dl/extractor/facebook.py index 937b28fcc..82dc27bc6 100644 --- a/youtube_dl/extractor/facebook.py +++ b/youtube_dl/extractor/facebook.py @@ -50,7 +50,10 @@ class FacebookIE(InfoExtractor): 'id': '274175099429670', 'ext': 'mp4', 'title': 'Facebook video #274175099429670', - } + }, + 'expected_warnings': [ + 'title' + ] }, { 'url': 'https://www.facebook.com/video.php?v=10204634152394104', 'only_matching': True, @@ -149,12 +152,12 @@ class FacebookIE(InfoExtractor): raise ExtractorError('Cannot find video formats') video_title = self._html_search_regex( - r'<h2 class="uiHeaderTitle">([^<]*)</h2>', webpage, 'title', - fatal=False) + r'<h2\s+[^>]*class="uiHeaderTitle"[^>]*>([^<]*)</h2>', webpage, 'title', + default=None) if not video_title: video_title = self._html_search_regex( r'(?s)<span class="fbPhotosPhotoCaption".*?id="fbPhotoPageCaption"><span class="hasCaption">(.*?)</span>', - webpage, 'alternative title', default=None) + webpage, 'alternative title', fatal=False) video_title = limit_length(video_title, 80) if not video_title: video_title = 'Facebook video #%s' % video_id diff --git a/youtube_dl/extractor/firedrive.py b/youtube_dl/extractor/firedrive.py deleted file mode 100644 index 3191116d9..000000000 --- a/youtube_dl/extractor/firedrive.py +++ /dev/null @@ -1,80 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) -from ..utils import ( - ExtractorError, -) - - -class FiredriveIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?firedrive\.com/' + \ - '(?:file|embed)/(?P<id>[0-9a-zA-Z]+)' - _FILE_DELETED_REGEX = r'<div class="removed_file_image">' - - _TESTS = [{ - 'url': 'https://www.firedrive.com/file/FEB892FA160EBD01', - 'md5': 'd5d4252f80ebeab4dc2d5ceaed1b7970', - 'info_dict': { - 'id': 'FEB892FA160EBD01', - 'ext': 'flv', - 'title': 'bbb_theora_486kbit.flv', - 'thumbnail': 're:^http://.*\.jpg$', - }, - }] - - def _real_extract(self, url): - video_id = self._match_id(url) - url = 'http://firedrive.com/file/%s' % video_id - webpage = self._download_webpage(url, video_id) - - if re.search(self._FILE_DELETED_REGEX, webpage) is not None: - raise ExtractorError('Video %s does not exist' % video_id, - expected=True) - - fields = dict(re.findall(r'''(?x)<input\s+ - type="hidden"\s+ - name="([^"]+)"\s+ - value="([^"]*)" - ''', webpage)) - - post = compat_urllib_parse.urlencode(fields) - req = compat_urllib_request.Request(url, post) - req.add_header('Content-type', 'application/x-www-form-urlencoded') - - # Apparently, this header is required for confirmation to work. - req.add_header('Host', 'www.firedrive.com') - - webpage = self._download_webpage(req, video_id, - 'Downloading video page') - - title = self._search_regex(r'class="external_title_left">(.+)</div>', - webpage, 'title') - thumbnail = self._search_regex(r'image:\s?"(//[^\"]+)', webpage, - 'thumbnail', fatal=False) - if thumbnail is not None: - thumbnail = 'http:' + thumbnail - - ext = self._search_regex(r'type:\s?\'([^\']+)\',', - webpage, 'extension', fatal=False) - video_url = self._search_regex( - r'file:\s?loadURL\(\'(http[^\']+)\'\),', webpage, 'file url') - - formats = [{ - 'format_id': 'sd', - 'url': video_url, - 'ext': ext, - }] - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'formats': formats, - } diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py index 47373e215..2d33fa7f5 100644 --- a/youtube_dl/extractor/gamespot.py +++ b/youtube_dl/extractor/gamespot.py @@ -14,8 +14,8 @@ from ..utils import ( class GameSpotIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?' - _TEST = { + _VALID_URL = r'http://(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?' + _TESTS = [{ 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825', 'info_dict': { @@ -23,8 +23,16 @@ class GameSpotIE(InfoExtractor): 'ext': 'mp4', 'title': 'Arma 3 - Community Guide: SITREP I', 'description': 'Check out this video where some of the basics of Arma 3 is explained.', - } - } + }, + }, { + 'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/', + 'info_dict': { + 'id': 'gs-2300-6424837', + 'ext': 'flv', + 'title': 'The Witcher 3: Wild Hunt [Xbox ONE] - Now Playing', + 'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.', + }, + }] def _real_extract(self, url): page_id = self._match_id(url) @@ -32,25 +40,37 @@ class GameSpotIE(InfoExtractor): data_video_json = self._search_regex( r'data-video=["\'](.*?)["\']', webpage, 'data video') data_video = json.loads(unescapeHTML(data_video_json)) + streams = data_video['videoStreams'] - # Transform the manifest url to a link to the mp4 files - # they are used in mobile devices. - f4m_url = data_video['videoStreams']['f4m_stream'] - f4m_path = compat_urlparse.urlparse(f4m_url).path - QUALITIES_RE = r'((,\d+)+,?)' - qualities = self._search_regex(QUALITIES_RE, f4m_path, 'qualities').strip(',').split(',') - http_path = f4m_path[1:].split('/', 1)[1] - http_template = re.sub(QUALITIES_RE, r'%s', http_path) - http_template = http_template.replace('.csmil/manifest.f4m', '') - http_template = compat_urlparse.urljoin( - 'http://video.gamespotcdn.com/', http_template) formats = [] - for q in qualities: - formats.append({ - 'url': http_template % q, - 'ext': 'mp4', - 'format_id': q, - }) + f4m_url = streams.get('f4m_stream') + if f4m_url is not None: + # Transform the manifest url to a link to the mp4 files + # they are used in mobile devices. + f4m_path = compat_urlparse.urlparse(f4m_url).path + QUALITIES_RE = r'((,\d+)+,?)' + qualities = self._search_regex(QUALITIES_RE, f4m_path, 'qualities').strip(',').split(',') + http_path = f4m_path[1:].split('/', 1)[1] + http_template = re.sub(QUALITIES_RE, r'%s', http_path) + http_template = http_template.replace('.csmil/manifest.f4m', '') + http_template = compat_urlparse.urljoin( + 'http://video.gamespotcdn.com/', http_template) + for q in qualities: + formats.append({ + 'url': http_template % q, + 'ext': 'mp4', + 'format_id': q, + }) + else: + for quality in ['sd', 'hd']: + # It's actually a link to a flv file + flv_url = streams.get('f4m_{0}'.format(quality)) + if flv_url is not None: + formats.append({ + 'url': flv_url, + 'ext': 'flv', + 'format_id': quality, + }) return { 'id': data_video['guid'], diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 3d756e848..96ca398de 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -9,6 +9,8 @@ from .common import InfoExtractor from .youtube import YoutubeIE from ..compat import ( compat_urllib_parse, + compat_urllib_parse_unquote, + compat_urllib_request, compat_urlparse, compat_xml_parse_error, ) @@ -32,6 +34,7 @@ from .brightcove import BrightcoveIE from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE +from .sportbox import SportBoxEmbedIE from .smotri import SmotriIE from .condenast import CondeNastIE from .udn import UDNEmbedIE @@ -45,6 +48,97 @@ class GenericIE(InfoExtractor): _VALID_URL = r'.*' IE_NAME = 'generic' _TESTS = [ + # Direct link to a video + { + 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', + 'md5': '67d406c2bcb6af27fa886f31aa934bbe', + 'info_dict': { + 'id': 'trailer', + 'ext': 'mp4', + 'title': 'trailer', + 'upload_date': '20100513', + } + }, + # Direct link to media delivered compressed (until Accept-Encoding is *) + { + 'url': 'http://calimero.tk/muzik/FictionJunction-Parallel_Hearts.flac', + 'md5': '128c42e68b13950268b648275386fc74', + 'info_dict': { + 'id': 'FictionJunction-Parallel_Hearts', + 'ext': 'flac', + 'title': 'FictionJunction-Parallel_Hearts', + 'upload_date': '20140522', + }, + 'expected_warnings': [ + 'URL could be a direct video link, returning it as such.' + ] + }, + # Direct download with broken HEAD + { + 'url': 'http://ai-radio.org:8000/radio.opus', + 'info_dict': { + 'id': 'radio', + 'ext': 'opus', + 'title': 'radio', + }, + 'params': { + 'skip_download': True, # infinite live stream + }, + 'expected_warnings': [ + r'501.*Not Implemented' + ], + }, + # Direct link with incorrect MIME type + { + 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', + 'md5': '4ccbebe5f36706d85221f204d7eb5913', + 'info_dict': { + 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', + 'id': '5_Lennart_Poettering_-_Systemd', + 'ext': 'webm', + 'title': '5_Lennart_Poettering_-_Systemd', + 'upload_date': '20141120', + }, + 'expected_warnings': [ + 'URL could be a direct video link, returning it as such.' + ] + }, + # RSS feed + { + 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'info_dict': { + 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', + 'title': 'Zero Punctuation', + 'description': 're:.*groundbreaking video review series.*' + }, + 'playlist_mincount': 11, + }, + # RSS feed with enclosure + { + 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml', + 'info_dict': { + 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624', + 'ext': 'm4v', + 'upload_date': '20150228', + 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624', + } + }, + # google redirect + { + 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE', + 'info_dict': { + 'id': 'cmQHVoWB5FY', + 'ext': 'mp4', + 'upload_date': '20130224', + 'uploader_id': 'TheVerge', + 'description': 're:^Chris Ziegler takes a look at the\.*', + 'uploader': 'The Verge', + 'title': 'First Firefox OS phones side-by-side', + }, + 'params': { + 'skip_download': False, + } + }, { 'url': 'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html', 'md5': '85b90ccc9d73b4acd9138d3af4c27f89', @@ -124,17 +218,6 @@ class GenericIE(InfoExtractor): 'skip_download': True, # m3u8 download }, }, - # Direct link to a video - { - 'url': 'http://media.w3.org/2010/05/sintel/trailer.mp4', - 'md5': '67d406c2bcb6af27fa886f31aa934bbe', - 'info_dict': { - 'id': 'trailer', - 'ext': 'mp4', - 'title': 'trailer', - 'upload_date': '20100513', - } - }, # ooyala video { 'url': 'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', @@ -159,22 +242,6 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Ooyala'], }, - # google redirect - { - 'url': 'http://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&ved=0CCUQtwIwAA&url=http%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DcmQHVoWB5FY&ei=F-sNU-LLCaXk4QT52ICQBQ&usg=AFQjCNEw4hL29zgOohLXvpJ-Bdh2bils1Q&bvm=bv.61965928,d.bGE', - 'info_dict': { - 'id': 'cmQHVoWB5FY', - 'ext': 'mp4', - 'upload_date': '20130224', - 'uploader_id': 'TheVerge', - 'description': 're:^Chris Ziegler takes a look at the\.*', - 'uploader': 'The Verge', - 'title': 'First Firefox OS phones side-by-side', - }, - 'params': { - 'skip_download': False, - } - }, # embed.ly video { 'url': 'http://www.tested.com/science/weird/460206-tested-grinding-coffee-2000-frames-second/', @@ -224,6 +291,37 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, + # SportBox embed + { + 'url': 'http://www.vestifinance.ru/articles/25753', + 'info_dict': { + 'id': '25753', + 'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"', + }, + 'playlist': [{ + 'info_dict': { + 'id': '370908', + 'title': 'Госзаказ. День 3', + 'ext': 'mp4', + } + }, { + 'info_dict': { + 'id': '370905', + 'title': 'Госзаказ. День 2', + 'ext': 'mp4', + } + }, { + 'info_dict': { + 'id': '370902', + 'title': 'Госзаказ. День 1', + 'ext': 'mp4', + } + }], + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, # Embedded TED video { 'url': 'http://en.support.wordpress.com/videos/ted-talks/', @@ -375,16 +473,6 @@ class GenericIE(InfoExtractor): 'title': 'Busty Blonde Siri Tit Fuck While Wank at HandjobHub.com', } }, - # RSS feed - { - 'url': 'http://phihag.de/2014/youtube-dl/rss2.xml', - 'info_dict': { - 'id': 'http://phihag.de/2014/youtube-dl/rss2.xml', - 'title': 'Zero Punctuation', - 'description': 're:.*groundbreaking video review series.*' - }, - 'playlist_mincount': 11, - }, # Multiple brightcove videos # https://github.com/rg3/youtube-dl/issues/2283 { @@ -438,21 +526,6 @@ class GenericIE(InfoExtractor): 'uploader': 'thoughtworks.wistia.com', }, }, - # Direct download with broken HEAD - { - 'url': 'http://ai-radio.org:8000/radio.opus', - 'info_dict': { - 'id': 'radio', - 'ext': 'opus', - 'title': 'radio', - }, - 'params': { - 'skip_download': True, # infinite live stream - }, - 'expected_warnings': [ - r'501.*Not Implemented' - ], - }, # Soundcloud embed { 'url': 'http://nakedsecurity.sophos.com/2014/10/29/sscc-171-are-you-sure-that-1234-is-a-bad-password-podcast/', @@ -484,21 +557,6 @@ class GenericIE(InfoExtractor): }, 'playlist_mincount': 2, }, - # Direct link with incorrect MIME type - { - 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', - 'md5': '4ccbebe5f36706d85221f204d7eb5913', - 'info_dict': { - 'url': 'http://ftp.nluug.nl/video/nluug/2014-11-20_nj14/zaal-2/5_Lennart_Poettering_-_Systemd.webm', - 'id': '5_Lennart_Poettering_-_Systemd', - 'ext': 'webm', - 'title': '5_Lennart_Poettering_-_Systemd', - 'upload_date': '20141120', - }, - 'expected_warnings': [ - 'URL could be a direct video link, returning it as such.' - ] - }, # Cinchcast embed { 'url': 'http://undergroundwellness.com/podcasts/306-5-steps-to-permanent-gut-healing/', @@ -657,16 +715,6 @@ class GenericIE(InfoExtractor): 'age_limit': 0, }, }, - # RSS feed with enclosure - { - 'url': 'http://podcastfeeds.nbcnews.com/audio/podcast/MSNBC-MADDOW-NETCAST-M4V.xml', - 'info_dict': { - 'id': 'pdv_maddow_netcast_m4v-02-27-2015-201624', - 'ext': 'm4v', - 'upload_date': '20150228', - 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624', - } - }, # Crooks and Liars embed { 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists', @@ -862,7 +910,7 @@ class GenericIE(InfoExtractor): force_videoid = smuggled_data['force_videoid'] video_id = force_videoid else: - video_id = os.path.splitext(url.rstrip('/').split('/')[-1])[0] + video_id = compat_urllib_parse_unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0]) self.to_screen('%s: Requesting header' % video_id) @@ -884,7 +932,9 @@ class GenericIE(InfoExtractor): full_response = None if head_response is False: - full_response = self._request_webpage(url, video_id) + request = compat_urllib_request.Request(url) + request.add_header('Accept-Encoding', '*') + full_response = self._request_webpage(request, video_id) head_response = full_response # Check for direct link to a video @@ -895,7 +945,7 @@ class GenericIE(InfoExtractor): head_response.headers.get('Last-Modified')) return { 'id': video_id, - 'title': os.path.splitext(url_basename(url))[0], + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), 'direct': True, 'formats': [{ 'format_id': m.group('format_id'), @@ -909,7 +959,17 @@ class GenericIE(InfoExtractor): self._downloader.report_warning('Falling back on generic information extractor.') if not full_response: - full_response = self._request_webpage(url, video_id) + request = compat_urllib_request.Request(url) + # Some webservers may serve compressed content of rather big size (e.g. gzipped flac) + # making it impossible to download only chunk of the file (yet we need only 512kB to + # test whether it's HTML or not). According to youtube-dl default Accept-Encoding + # that will always result in downloading the whole file that is not desirable. + # Therefore for extraction pass we have to override Accept-Encoding to any in order + # to accept raw bytes and being able to download only a chunk. + # It may probably better to solve this by checking Content-Type for application/octet-stream + # after HEAD request finishes, but not sure if we can rely on this. + request.add_header('Accept-Encoding', '*') + full_response = self._request_webpage(request, video_id) # Maybe it's a direct link to a video? # Be careful not to download the whole thing! @@ -921,7 +981,7 @@ class GenericIE(InfoExtractor): head_response.headers.get('Last-Modified')) return { 'id': video_id, - 'title': os.path.splitext(url_basename(url))[0], + 'title': compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0]), 'direct': True, 'url': url, 'upload_date': upload_date, @@ -1229,6 +1289,11 @@ class GenericIE(InfoExtractor): if rutv_url: return self.url_result(rutv_url, 'RUTV') + # Look for embedded SportBox player + sportbox_urls = SportBoxEmbedIE._extract_urls(webpage) + if sportbox_urls: + return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed') + # Look for embedded TED player mobj = re.search( r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage) @@ -1388,7 +1453,7 @@ class GenericIE(InfoExtractor): # Look for Senate ISVP iframe senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) if senate_isvp_url: - return self.url_result(surl, 'SenateISVP') + return self.url_result(senate_isvp_url, 'SenateISVP') def check_video(vurl): if YoutubeIE.suitable(vurl): diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index fe5d95e2c..d692ea79a 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -3,6 +3,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( int_or_none, js_to_json, @@ -12,7 +13,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P<id>[a-zA-Z0-9]+)(?:\.mp4|\.gifv)?' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P<id>[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -34,7 +35,8 @@ class ImgurIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + compat_urlparse.urljoin(url, video_id), video_id) width = int_or_none(self._search_regex( r'<param name="width" value="([0-9]+)"', diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py index 65f6ca103..b10755788 100644 --- a/youtube_dl/extractor/instagram.py +++ b/youtube_dl/extractor/instagram.py @@ -7,9 +7,9 @@ from ..utils import int_or_none class InstagramIE(InfoExtractor): - _VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)' + _VALID_URL = r'https://instagram\.com/p/(?P<id>[\da-zA-Z]+)' _TEST = { - 'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc', + 'url': 'https://instagram.com/p/aye83DjauH/?foo=bar#abc', 'md5': '0d2da106a9d2631273e192b372806516', 'info_dict': { 'id': 'aye83DjauH', @@ -41,11 +41,11 @@ class InstagramIE(InfoExtractor): class InstagramUserIE(InfoExtractor): - _VALID_URL = r'http://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])' + _VALID_URL = r'https://instagram\.com/(?P<username>[^/]{2,})/?(?:$|[?#])' IE_DESC = 'Instagram user profile' IE_NAME = 'instagram:user' _TEST = { - 'url': 'http://instagram.com/porsche', + 'url': 'https://instagram.com/porsche', 'info_dict': { 'id': 'porsche', 'title': 'porsche', diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py index 8529bedfc..821c8ec10 100644 --- a/youtube_dl/extractor/iprima.py +++ b/youtube_dl/extractor/iprima.py @@ -11,11 +11,12 @@ from ..compat import ( ) from ..utils import ( ExtractorError, + remove_end, ) class IPrimaIE(InfoExtractor): - _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)' + _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)' _TESTS = [{ 'url': 'http://play.iprima.cz/particka/particka-92', @@ -23,7 +24,7 @@ class IPrimaIE(InfoExtractor): 'id': '39152', 'ext': 'flv', 'title': 'Partička (92)', - 'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6', + 'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45', 'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg', }, 'params': { @@ -35,13 +36,14 @@ class IPrimaIE(InfoExtractor): 'id': '9718337', 'ext': 'flv', 'title': 'Tchibo Partička - Jarní móda', - 'description': 'md5:589f8f59f414220621ff8882eb3ce7be', 'thumbnail': 're:^http:.*\.jpg$', }, 'params': { 'skip_download': True, # requires rtmpdump }, - 'skip': 'Do not have permission to access this page', + }, { + 'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015', + 'only_matching': True, }] def _real_extract(self, url): @@ -102,8 +104,10 @@ class IPrimaIE(InfoExtractor): return { 'id': real_id, - 'title': self._og_search_title(webpage), + 'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'), 'thumbnail': self._og_search_thumbnail(webpage), 'formats': formats, - 'description': self._og_search_description(webpage), + 'description': self._search_regex( + r'<p[^>]+itemprop="description"[^>]*>([^<]+)', + webpage, 'description', default=None), } diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py index 99a1361f8..bc226fa67 100644 --- a/youtube_dl/extractor/izlesene.py +++ b/youtube_dl/extractor/izlesene.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote from ..utils import ( determine_ext, float_or_none, @@ -30,7 +31,7 @@ class IzleseneIE(InfoExtractor): 'description': 'md5:253753e2655dde93f59f74b572454f6d', 'thumbnail': 're:^http://.*\.jpg', 'uploader_id': 'pelikzzle', - 'timestamp': 1404302298, + 'timestamp': int, 'upload_date': '20140702', 'duration': 95.395, 'age_limit': 0, @@ -46,7 +47,7 @@ class IzleseneIE(InfoExtractor): 'description': 'Tarkan Dortmund 2006 Konseri', 'thumbnail': 're:^http://.*\.jpg', 'uploader_id': 'parlayankiz', - 'timestamp': 1163322193, + 'timestamp': int, 'upload_date': '20061112', 'duration': 253.666, 'age_limit': 0, @@ -67,9 +68,9 @@ class IzleseneIE(InfoExtractor): uploader = self._html_search_regex( r"adduserUsername\s*=\s*'([^']+)';", - webpage, 'uploader', fatal=False, default='') + webpage, 'uploader', fatal=False) timestamp = parse_iso8601(self._html_search_meta( - 'uploadDate', webpage, 'upload date', fatal=False)) + 'uploadDate', webpage, 'upload date')) duration = float_or_none(self._html_search_regex( r'"videoduration"\s*:\s*"([^"]+)"', @@ -86,8 +87,7 @@ class IzleseneIE(InfoExtractor): # Might be empty for some videos. streams = self._html_search_regex( - r'"qualitylevel"\s*:\s*"([^"]+)"', - webpage, 'streams', fatal=False, default='') + r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='') formats = [] if streams: @@ -95,15 +95,15 @@ class IzleseneIE(InfoExtractor): quality, url = re.search(r'\[(\w+)\](.+)', stream).groups() formats.append({ 'format_id': '%sp' % quality if quality else 'sd', - 'url': url, + 'url': compat_urllib_parse_unquote(url), 'ext': ext, }) else: stream_url = self._search_regex( - r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL') + r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL') formats.append({ 'format_id': 'sd', - 'url': stream_url, + 'url': compat_urllib_parse_unquote(stream_url), 'ext': ext, }) diff --git a/youtube_dl/extractor/karrierevideos.py b/youtube_dl/extractor/karrierevideos.py new file mode 100644 index 000000000..bed94bc93 --- /dev/null +++ b/youtube_dl/extractor/karrierevideos.py @@ -0,0 +1,96 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..compat import compat_urlparse +from ..utils import ( + fix_xml_ampersands, + float_or_none, + xpath_with_ns, + xpath_text, +) + + +class KarriereVideosIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?karrierevideos\.at(?:/[^/]+)+/(?P<id>[^/]+)' + _TESTS = [{ + 'url': 'http://www.karrierevideos.at/berufsvideos/mittlere-hoehere-schulen/altenpflegerin', + 'info_dict': { + 'id': '32c91', + 'ext': 'flv', + 'title': 'AltenpflegerIn', + 'description': 'md5:dbadd1259fde2159a9b28667cb664ae2', + 'thumbnail': 're:^http://.*\.png', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + # broken ampersands + 'url': 'http://www.karrierevideos.at/orientierung/vaeterkarenz-und-neue-chancen-fuer-muetter-baby-was-nun', + 'info_dict': { + 'id': '5sniu', + 'ext': 'flv', + 'title': 'Väterkarenz und neue Chancen für Mütter - "Baby - was nun?"', + 'description': 'md5:97092c6ad1fd7d38e9d6a5fdeb2bcc33', + 'thumbnail': 're:^http://.*\.png', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + title = (self._html_search_meta('title', webpage, default=None) or + self._search_regex(r'<h1 class="title">([^<]+)</h1>')) + + video_id = self._search_regex( + r'/config/video/(.+?)\.xml', webpage, 'video id') + playlist = self._download_xml( + 'http://www.karrierevideos.at/player-playlist.xml.php?p=%s' % video_id, + video_id, transform_source=fix_xml_ampersands) + + NS_MAP = { + 'jwplayer': 'http://developer.longtailvideo.com/trac/wiki/FlashFormats' + } + + def ns(path): + return xpath_with_ns(path, NS_MAP) + + item = playlist.find('./tracklist/item') + video_file = xpath_text( + item, ns('./jwplayer:file'), 'video url', fatal=True) + streamer = xpath_text( + item, ns('./jwplayer:streamer'), 'streamer', fatal=True) + + uploader = xpath_text( + item, ns('./jwplayer:author'), 'uploader') + duration = float_or_none( + xpath_text(item, ns('./jwplayer:duration'), 'duration')) + + description = self._html_search_regex( + r'(?s)<div class="leadtext">(.+?)</div>', + webpage, 'description') + + thumbnail = self._html_search_meta( + 'thumbnail', webpage, 'thumbnail') + if thumbnail: + thumbnail = compat_urlparse.urljoin(url, thumbnail) + + return { + 'id': video_id, + 'url': streamer.replace('rtmpt', 'rtmp'), + 'play_path': 'mp4:%s' % video_file, + 'ext': 'flv', + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'duration': duration, + } diff --git a/youtube_dl/extractor/letv.py b/youtube_dl/extractor/letv.py index 1484ac0d2..da896caf1 100644 --- a/youtube_dl/extractor/letv.py +++ b/youtube_dl/extractor/letv.py @@ -50,9 +50,7 @@ class LetvIE(InfoExtractor): 'title': '与龙共舞 完整版', 'description': 'md5:7506a5eeb1722bb9d4068f85024e3986', }, - 'params': { - 'cn_verification_proxy': 'http://proxy.uku.im:8888' - }, + 'skip': 'Only available in China', }] @staticmethod diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py index d8897eb90..7091f3335 100644 --- a/youtube_dl/extractor/mitele.py +++ b/youtube_dl/extractor/mitele.py @@ -20,7 +20,6 @@ class MiTeleIE(InfoExtractor): _TESTS = [{ 'url': 'http://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144/', - 'md5': '6a75fe9d0d3275bead0cb683c616fddb', 'info_dict': { 'id': '0fce117d', 'ext': 'mp4', @@ -29,6 +28,10 @@ class MiTeleIE(InfoExtractor): 'display_id': 'programa-144', 'duration': 2913, }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -56,12 +59,14 @@ class MiTeleIE(InfoExtractor): episode, transform_source=strip_jsonp ) + formats = self._extract_m3u8_formats( + token_info['tokenizedUrl'], episode, ext='mp4') return { 'id': embed_data['videoId'], 'display_id': episode, 'title': info_el.find('title').text, - 'url': token_info['tokenizedUrl'], + 'formats': formats, 'description': get_element_by_attribute('class', 'text', webpage), 'thumbnail': info_el.find('thumb').text, 'duration': parse_duration(info_el.find('duration').text), diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py index c10405f04..925967753 100644 --- a/youtube_dl/extractor/naver.py +++ b/youtube_dl/extractor/naver.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..compat import ( compat_urllib_parse, + compat_urlparse, ) from ..utils import ( ExtractorError, @@ -16,7 +17,7 @@ from ..utils import ( class NaverIE(InfoExtractor): _VALID_URL = r'https?://(?:m\.)?tvcast\.naver\.com/v/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://tvcast.naver.com/v/81652', 'info_dict': { 'id': '81652', @@ -25,7 +26,18 @@ class NaverIE(InfoExtractor): 'description': '합격불변의 법칙 메가스터디 | 메가스터디 수학 김상희 선생님이 9월 모의고사 수학A형 16번에서 20번까지 해설강의를 공개합니다.', 'upload_date': '20130903', }, - } + }, { + 'url': 'http://tvcast.naver.com/v/395837', + 'md5': '638ed4c12012c458fefcddfd01f173cd', + 'info_dict': { + 'id': '395837', + 'ext': 'mp4', + 'title': '9년이 지나도 아픈 기억, 전효성의 아버지', + 'description': 'md5:5bf200dcbf4b66eb1b350d1eb9c753f7', + 'upload_date': '20150519', + }, + 'skip': 'Georestricted', + }] def _real_extract(self, url): video_id = self._match_id(url) @@ -35,7 +47,7 @@ class NaverIE(InfoExtractor): webpage) if m_id is None: m_error = re.search( - r'(?s)<div class="nation_error">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>', + r'(?s)<div class="(?:nation_error|nation_box)">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>', webpage) if m_error: raise ExtractorError(clean_html(m_error.group('msg')), expected=True) @@ -58,14 +70,18 @@ class NaverIE(InfoExtractor): formats = [] for format_el in urls.findall('EncodingOptions/EncodingOption'): domain = format_el.find('Domain').text + uri = format_el.find('uri').text f = { - 'url': domain + format_el.find('uri').text, + 'url': compat_urlparse.urljoin(domain, uri), 'ext': 'mp4', 'width': int(format_el.find('width').text), 'height': int(format_el.find('height').text), } if domain.startswith('rtmp'): + # urlparse does not support custom schemes + # https://bugs.python.org/issue18828 f.update({ + 'url': domain + uri, 'ext': 'flv', 'rtmp_protocol': '1', # rtmpt }) diff --git a/youtube_dl/extractor/nba.py b/youtube_dl/extractor/nba.py index 862b706bf..944096e1c 100644 --- a/youtube_dl/extractor/nba.py +++ b/youtube_dl/extractor/nba.py @@ -22,6 +22,18 @@ class NBAIE(InfoExtractor): }, { 'url': 'http://www.nba.com/video/games/hornets/2014/12/05/0021400276-nyk-cha-play5.nba/', 'only_matching': True, + }, { + 'url': 'http://watch.nba.com/nba/video/channels/playoffs/2015/05/20/0041400301-cle-atl-recap.nba', + 'info_dict': { + 'id': '0041400301-cle-atl-recap.nba', + 'ext': 'mp4', + 'title': 'NBA GAME TIME | Video: Hawks vs. Cavaliers Game 1', + 'description': 'md5:8094c3498d35a9bd6b1a8c396a071b4d', + 'duration': 228, + }, + 'params': { + 'skip_download': True, + } }] def _real_extract(self, url): @@ -35,8 +47,12 @@ class NBAIE(InfoExtractor): self._og_search_title(webpage, default=shortened_video_id), ' : NBA.com') description = self._og_search_description(webpage) - duration = parse_duration( - self._html_search_meta('duration', webpage, 'duration')) + duration_str = self._html_search_meta( + 'duration', webpage, 'duration', default=None) + if not duration_str: + duration_str = self._html_search_regex( + r'Duration:</b>\s*(\d+:\d+)', webpage, 'duration', fatal=False) + duration = parse_duration(duration_str) return { 'id': shortened_video_id, diff --git a/youtube_dl/extractor/nextmedia.py b/youtube_dl/extractor/nextmedia.py index 02dba4ef6..d1b7cff4c 100644 --- a/youtube_dl/extractor/nextmedia.py +++ b/youtube_dl/extractor/nextmedia.py @@ -89,8 +89,8 @@ class NextMediaActionNewsIE(NextMediaIE): return self._extract_from_nextmedia_page(news_id, url, article_page) -class AppleDailyRealtimeNewsIE(NextMediaIE): - _VALID_URL = r'http://(www|ent).appledaily.com.tw/(realtimenews|enews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?' +class AppleDailyIE(NextMediaIE): + _VALID_URL = r'http://(www|ent).appledaily.com.tw/(?:animation|appledaily|enews|realtimenews)/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?' _TESTS = [{ 'url': 'http://ent.appledaily.com.tw/enews/article/entertainment/20150128/36354694', 'md5': 'a843ab23d150977cc55ef94f1e2c1e4d', @@ -99,7 +99,7 @@ class AppleDailyRealtimeNewsIE(NextMediaIE): 'ext': 'mp4', 'title': '周亭羽走過摩鐵陰霾2男陪吃 九把刀孤寒看醫生', 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'md5:b23787119933404ce515c6356a8c355c', + 'description': 'md5:2acd430e59956dc47cd7f67cb3c003f4', 'upload_date': '20150128', } }, { @@ -110,26 +110,10 @@ class AppleDailyRealtimeNewsIE(NextMediaIE): 'ext': 'mp4', 'title': '不滿被踩腳 山東兩大媽一路打下車', 'thumbnail': 're:^https?://.*\.jpg$', - 'description': 'md5:2648aaf6fc4f401f6de35a91d111aa1d', + 'description': 'md5:175b4260c1d7c085993474217e4ab1b4', 'upload_date': '20150128', } - }] - - _URL_PATTERN = r'\{url: \'(.+)\'\}' - - def _fetch_title(self, page): - return self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title') - - def _fetch_thumbnail(self, page): - return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False) - - def _fetch_timestamp(self, page): - return None - - -class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE): - _VALID_URL = 'http://www.appledaily.com.tw/animation/[^/]+/[^/]+/(?P<date>\d+)/(?P<id>\d+)(/.*)?' - _TESTS = [{ + }, { 'url': 'http://www.appledaily.com.tw/animation/realtimenews/new/20150128/5003671', 'md5': '03df296d95dedc2d5886debbb80cb43f', 'info_dict': { @@ -154,10 +138,22 @@ class AppleDailyAnimationNewsIE(AppleDailyRealtimeNewsIE): 'expected_warnings': [ 'video thumbnail', ] + }, { + 'url': 'http://www.appledaily.com.tw/appledaily/article/supplement/20140417/35770334/', + 'only_matching': True, }] + _URL_PATTERN = r'\{url: \'(.+)\'\}' + def _fetch_title(self, page): - return self._html_search_meta('description', page, 'news title') + return (self._html_search_regex(r'<h1 id="h1">([^<>]+)</h1>', page, 'news title', default=None) or + self._html_search_meta('description', page, 'news title')) + + def _fetch_thumbnail(self, page): + return self._html_search_regex(r"setInitialImage\(\'([^']+)'\)", page, 'video thumbnail', fatal=False) + + def _fetch_timestamp(self, page): + return None def _fetch_description(self, page): return self._html_search_meta('description', page, 'news description') diff --git a/youtube_dl/extractor/nova.py b/youtube_dl/extractor/nova.py new file mode 100644 index 000000000..3f9c776ef --- /dev/null +++ b/youtube_dl/extractor/nova.py @@ -0,0 +1,179 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + clean_html, + unified_strdate, +) + + +class NovaIE(InfoExtractor): + IE_DESC = 'TN.cz, Prásk.tv, Nova.cz, Novaplus.cz, FANDA.tv, Krásná.cz and Doma.cz' + _VALID_URL = 'http://(?:[^.]+\.)?(?P<site>tv(?:noviny)?|tn|novaplus|vymena|fanda|krasna|doma|prask)\.nova\.cz/(?:[^/]+/)+(?P<id>[^/]+?)(?:\.html|/|$)' + _TESTS = [{ + 'url': 'http://tvnoviny.nova.cz/clanek/novinky/co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou.html?utm_source=tvnoviny&utm_medium=cpfooter&utm_campaign=novaplus', + 'info_dict': { + 'id': '1608920', + 'display_id': 'co-na-sebe-sportaci-praskli-vime-jestli-pujde-hrdlicka-na-materskou', + 'ext': 'flv', + 'title': 'Duel: Michal Hrdlička a Petr Suchoň', + 'description': 'md5:d0cc509858eee1b1374111c588c6f5d5', + 'thumbnail': 're:^https?://.*\.(?:jpg)', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://tn.nova.cz/clanek/tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci.html#player_13260', + 'md5': '1dd7b9d5ea27bc361f110cd855a19bd3', + 'info_dict': { + 'id': '1757139', + 'display_id': 'tajemstvi-ukryte-v-podzemi-specialni-nemocnice-v-prazske-krci', + 'ext': 'mp4', + 'title': 'Podzemní nemocnice v pražské Krči', + 'description': 'md5:f0a42dd239c26f61c28f19e62d20ef53', + 'thumbnail': 're:^https?://.*\.(?:jpg)', + } + }, { + 'url': 'http://novaplus.nova.cz/porad/policie-modrava/video/5591-policie-modrava-15-dil-blondynka-na-hrbitove', + 'info_dict': { + 'id': '1756825', + 'display_id': '5591-policie-modrava-15-dil-blondynka-na-hrbitove', + 'ext': 'flv', + 'title': 'Policie Modrava - 15. díl - Blondýnka na hřbitově', + 'description': 'md5:dc24e50be5908df83348e50d1431295e', # Make sure this description is clean of html tags + 'thumbnail': 're:^https?://.*\.(?:jpg)', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://novaplus.nova.cz/porad/televizni-noviny/video/5585-televizni-noviny-30-5-2015/', + 'info_dict': { + 'id': '1756858', + 'ext': 'flv', + 'title': 'Televizní noviny - 30. 5. 2015', + 'thumbnail': 're:^https?://.*\.(?:jpg)', + 'upload_date': '20150530', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html', + 'info_dict': { + 'id': '1753621', + 'ext': 'mp4', + 'title': 'Zaklínač 3: Divoký hon', + 'description': 're:.*Pokud se stejně jako my nemůžete.*', + 'thumbnail': 're:https?://.*\.jpg(\?.*)?', + 'upload_date': '20150521', + }, + 'params': { + # rtmp download + 'skip_download': True, + } + }, { + 'url': 'http://sport.tn.nova.cz/clanek/sport/hokej/nhl/zivot-jde-dal-hodnotil-po-vyrazeni-z-playoff-jiri-sekac.html', + 'only_matching': True, + }, { + 'url': 'http://fanda.nova.cz/clanek/fun-and-games/krvavy-epos-zaklinac-3-divoky-hon-vychazi-vyhrajte-ho-pro-sebe.html', + 'only_matching': True, + }, { + 'url': 'http://doma.nova.cz/clanek/zdravi/prijdte-se-zapsat-do-registru-kostni-drene-jiz-ve-stredu-3-cervna.html', + 'only_matching': True, + }, { + 'url': 'http://prask.nova.cz/clanek/novinky/co-si-na-sobe-nase-hvezdy-nechaly-pojistit.html', + 'only_matching': True, + }, { + 'url': 'http://tv.nova.cz/clanek/novinky/zivot-je-zivot-bondovsky-trailer.html', + 'only_matching': True, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + site = mobj.group('site') + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + [r"(?:media|video_id)\s*:\s*'(\d+)'", + r'media=(\d+)', + r'id="article_video_(\d+)"', + r'id="player_(\d+)"'], + webpage, 'video id') + + config_url = self._search_regex( + r'src="(http://tn\.nova\.cz/bin/player/videojs/config\.php\?[^"]+)"', + webpage, 'config url', default=None) + + if not config_url: + DEFAULT_SITE_ID = '23000' + SITES = { + 'tvnoviny': DEFAULT_SITE_ID, + 'novaplus': DEFAULT_SITE_ID, + 'vymena': DEFAULT_SITE_ID, + 'krasna': DEFAULT_SITE_ID, + 'fanda': '30', + 'tn': '30', + 'doma': '30', + } + + site_id = self._search_regex( + r'site=(\d+)', webpage, 'site id', default=None) or SITES.get(site, DEFAULT_SITE_ID) + + config_url = ('http://tn.nova.cz/bin/player/videojs/config.php?site=%s&media=%s&jsVar=vjsconfig' + % (site_id, video_id)) + + config = self._download_json( + config_url, display_id, + 'Downloading config JSON', + transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1]) + + mediafile = config['mediafile'] + video_url = mediafile['src'] + + m = re.search(r'^(?P<url>rtmpe?://[^/]+/(?P<app>[^/]+?))/&*(?P<playpath>.+)$', video_url) + if m: + formats = [{ + 'url': m.group('url'), + 'app': m.group('app'), + 'play_path': m.group('playpath'), + 'player_path': 'http://tvnoviny.nova.cz/static/shared/app/videojs/video-js.swf', + 'ext': 'flv', + }] + else: + formats = [{ + 'url': video_url, + }] + self._sort_formats(formats) + + title = mediafile.get('meta', {}).get('title') or self._og_search_title(webpage) + description = clean_html(self._og_search_description(webpage, default=None)) + thumbnail = config.get('poster') + + if site == 'novaplus': + upload_date = unified_strdate(self._search_regex( + r'(\d{1,2}-\d{1,2}-\d{4})$', display_id, 'upload date', default=None)) + elif site == 'fanda': + upload_date = unified_strdate(self._search_regex( + r'<span class="date_time">(\d{1,2}\.\d{1,2}\.\d{4})', webpage, 'upload date', default=None)) + else: + upload_date = None + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'upload_date': upload_date, + 'thumbnail': thumbnail, + 'formats': formats, + } diff --git a/youtube_dl/extractor/nowtv.py b/youtube_dl/extractor/nowtv.py new file mode 100644 index 000000000..173e46cd8 --- /dev/null +++ b/youtube_dl/extractor/nowtv.py @@ -0,0 +1,192 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + ExtractorError, + int_or_none, + parse_iso8601, + parse_duration, + remove_start, +) + + +class NowTVIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?nowtv\.de/(?P<station>rtl|rtl2|rtlnitro|superrtl|ntv|vox)/(?P<id>.+?)/player' + + _TESTS = [{ + # rtl + 'url': 'http://www.nowtv.de/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/player', + 'info_dict': { + 'id': '203519', + 'display_id': 'bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', + 'ext': 'mp4', + 'title': 'Die neuen Bauern und eine Hochzeit', + 'description': 'md5:e234e1ed6d63cf06be5c070442612e7e', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1432580700, + 'upload_date': '20150525', + 'duration': 2786, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + # rtl2 + 'url': 'http://www.nowtv.de/rtl2/berlin-tag-nacht/berlin-tag-nacht-folge-934/player', + 'info_dict': { + 'id': '203481', + 'display_id': 'berlin-tag-nacht/berlin-tag-nacht-folge-934', + 'ext': 'mp4', + 'title': 'Berlin - Tag & Nacht (Folge 934)', + 'description': 'md5:c85e88c2e36c552dfe63433bc9506dd0', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1432666800, + 'upload_date': '20150526', + 'duration': 2641, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + # rtlnitro + 'url': 'http://www.nowtv.de/rtlnitro/alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00/player', + 'info_dict': { + 'id': '165780', + 'display_id': 'alarm-fuer-cobra-11-die-autobahnpolizei/hals-und-beinbruch-2014-08-23-21-10-00', + 'ext': 'mp4', + 'title': 'Hals- und Beinbruch', + 'description': 'md5:b50d248efffe244e6f56737f0911ca57', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1432415400, + 'upload_date': '20150523', + 'duration': 2742, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + # superrtl + 'url': 'http://www.nowtv.de/superrtl/medicopter-117/angst/player', + 'info_dict': { + 'id': '99205', + 'display_id': 'medicopter-117/angst', + 'ext': 'mp4', + 'title': 'Angst!', + 'description': 'md5:30cbc4c0b73ec98bcd73c9f2a8c17c4e', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1222632900, + 'upload_date': '20080928', + 'duration': 3025, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + # ntv + 'url': 'http://www.nowtv.de/ntv/ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch/player', + 'info_dict': { + 'id': '203521', + 'display_id': 'ratgeber-geld/thema-ua-der-erste-blick-die-apple-watch', + 'ext': 'mp4', + 'title': 'Thema u.a.: Der erste Blick: Die Apple Watch', + 'description': 'md5:4312b6c9d839ffe7d8caf03865a531af', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1432751700, + 'upload_date': '20150527', + 'duration': 1083, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + # vox + 'url': 'http://www.nowtv.de/vox/der-hundeprofi/buero-fall-chihuahua-joel/player', + 'info_dict': { + 'id': '128953', + 'display_id': 'der-hundeprofi/buero-fall-chihuahua-joel', + 'ext': 'mp4', + 'title': "Büro-Fall / Chihuahua 'Joel'", + 'description': 'md5:e62cb6bf7c3cc669179d4f1eb279ad8d', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1432408200, + 'upload_date': '20150523', + 'duration': 3092, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('id') + station = mobj.group('station') + + info = self._download_json( + 'https://api.nowtv.de/v3/movies/%s?fields=*,format,files' % display_id, + display_id) + + video_id = compat_str(info['id']) + + files = info['files'] + if not files: + if info.get('geoblocked', False): + raise ExtractorError( + 'Video %s is not available from your location due to geo restriction' % video_id, + expected=True) + if not info.get('free', True): + raise ExtractorError( + 'Video %s is not available for free' % video_id, expected=True) + + f = info.get('format', {}) + station = f.get('station') or station + + STATIONS = { + 'rtl': 'rtlnow', + 'rtl2': 'rtl2now', + 'vox': 'voxnow', + 'nitro': 'rtlnitronow', + 'ntv': 'n-tvnow', + 'superrtl': 'superrtlnow' + } + + formats = [] + for item in files['items']: + item_path = remove_start(item['path'], '/') + tbr = int_or_none(item['bitrate']) + m3u8_url = 'http://hls.fra.%s.de/hls-vod-enc/%s.m3u8' % (STATIONS[station], item_path) + m3u8_url = m3u8_url.replace('now/', 'now/videos/') + formats.append({ + 'url': m3u8_url, + 'format_id': '%s-%sk' % (item['id'], tbr), + 'ext': 'mp4', + 'tbr': tbr, + }) + self._sort_formats(formats) + + title = info['title'] + description = info.get('articleLong') or info.get('articleShort') + timestamp = parse_iso8601(info.get('broadcastStartDate'), ' ') + duration = parse_duration(info.get('duration')) + thumbnail = f.get('defaultImage169Format') or f.get('defaultImage169Logo') + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'formats': formats, + } diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index fbc521d1a..6c7149fe3 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..compat import compat_urllib_parse from ..utils import ( unified_strdate, int_or_none, @@ -11,8 +12,9 @@ from ..utils import ( class OdnoklassnikiIE(InfoExtractor): - _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>\d+)' + _VALID_URL = r'https?://(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)' _TESTS = [{ + # metadata in JSON 'url': 'http://ok.ru/video/20079905452', 'md5': '8e24ad2da6f387948e7a7d44eb8668fe', 'info_dict': { @@ -20,11 +22,22 @@ class OdnoklassnikiIE(InfoExtractor): 'ext': 'mp4', 'title': 'Культура меняет нас (прекрасный ролик!))', 'duration': 100, - 'upload_date': '20141207', 'uploader_id': '330537914540', 'uploader': 'Виталий Добровольский', 'like_count': int, - 'age_limit': 0, + }, + }, { + # metadataUrl + 'url': 'http://ok.ru/video/63567059965189-0', + 'md5': '9676cf86eff5391d35dea675d224e131', + 'info_dict': { + 'id': '63567059965189-0', + 'ext': 'mp4', + 'title': 'Девушка без комплексов ...', + 'duration': 191, + 'uploader_id': '534380003155', + 'uploader': 'Андрей Мещанинов', + 'like_count': int, }, }, { 'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452', @@ -34,14 +47,23 @@ class OdnoklassnikiIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) + webpage = self._download_webpage( + 'http://ok.ru/video/%s' % video_id, video_id) player = self._parse_json( unescapeHTML(self._search_regex( r'data-attributes="([^"]+)"', webpage, 'player')), video_id) - metadata = self._parse_json(player['flashvars']['metadata'], video_id) + flashvars = player['flashvars'] + + metadata = flashvars.get('metadata') + if metadata: + metadata = self._parse_json(metadata, video_id) + else: + metadata = self._download_json( + compat_urllib_parse.unquote(flashvars['metadataUrl']), + video_id, 'Downloading metadata JSON') movie = metadata['movie'] title = movie['title'] @@ -53,11 +75,11 @@ class OdnoklassnikiIE(InfoExtractor): uploader = author.get('name') upload_date = unified_strdate(self._html_search_meta( - 'ya:ovs:upload_date', webpage, 'upload date')) + 'ya:ovs:upload_date', webpage, 'upload date', default=None)) age_limit = None adult = self._html_search_meta( - 'ya:ovs:adult', webpage, 'age limit') + 'ya:ovs:adult', webpage, 'age limit', default=None) if adult: age_limit = 18 if adult == 'true' else 0 diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py index c0e6d643d..a262a9f6d 100644 --- a/youtube_dl/extractor/ooyala.py +++ b/youtube_dl/extractor/ooyala.py @@ -12,50 +12,7 @@ from ..utils import ( ) -class OoyalaIE(InfoExtractor): - _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)' - - _TESTS = [ - { - # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video - 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'info_dict': { - 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', - 'ext': 'mp4', - 'title': 'Explaining Data Recovery from Hard Drives and SSDs', - 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', - }, - }, { - # Only available for ipad - 'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', - 'info_dict': { - 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', - 'ext': 'mp4', - 'title': 'Simulation Overview - Levels of Simulation', - 'description': '', - }, - }, - { - # Information available only through SAS api - # From http://community.plm.automation.siemens.com/t5/News-NX-Manufacturing/Tool-Path-Divide/ba-p/4187 - 'url': 'http://player.ooyala.com/player.js?embedCode=FiOG81ZTrvckcchQxmalf4aQj590qTEx', - 'md5': 'a84001441b35ea492bc03736e59e7935', - 'info_dict': { - 'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx', - 'ext': 'mp4', - 'title': 'Ooyala video', - } - } - ] - - @staticmethod - def _url_for_embed_code(embed_code): - return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code - - @classmethod - def _build_url_result(cls, embed_code): - return cls.url_result(cls._url_for_embed_code(embed_code), - ie=cls.ie_key()) +class OoyalaBaseIE(InfoExtractor): def _extract_result(self, info, more_info): embedCode = info['embedCode'] @@ -77,11 +34,8 @@ class OoyalaIE(InfoExtractor): 'thumbnail': more_info['promo'], } - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - embedCode = mobj.group('id') - player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embedCode - player = self._download_webpage(player_url, embedCode) + def _extract(self, player_url, video_id): + player = self._download_webpage(player_url, video_id) mobile_url = self._search_regex(r'mobile_player_url="(.+?)&device="', player, 'mobile player url') # Looks like some videos are only available for particular devices @@ -94,7 +48,7 @@ class OoyalaIE(InfoExtractor): devices.insert(0, 'unknown') for device in devices: mobile_player = self._download_webpage( - '%s&device=%s' % (mobile_url, device), embedCode, + '%s&device=%s' % (mobile_url, device), video_id, 'Downloading mobile player JS for %s device' % device) videos_info = self._search_regex( r'var streams=window.oo_testEnv\?\[\]:eval\("\((\[{.*?}\])\)"\);', @@ -105,10 +59,10 @@ class OoyalaIE(InfoExtractor): if not videos_info: formats = [] auth_data = self._download_json( - 'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (embedCode, embedCode), - embedCode) + 'http://player.ooyala.com/sas/player_api/v1/authorization/embed_code/%s/%s?domain=www.example.org&supportedFormats=mp4,webm' % (video_id, video_id), + video_id) - cur_auth_data = auth_data['authorization_data'][embedCode] + cur_auth_data = auth_data['authorization_data'][video_id] for stream in cur_auth_data['streams']: formats.append({ @@ -123,7 +77,7 @@ class OoyalaIE(InfoExtractor): }) if formats: return { - 'id': embedCode, + 'id': video_id, 'formats': formats, 'title': 'Ooyala video', } @@ -143,9 +97,100 @@ class OoyalaIE(InfoExtractor): videos = [self._extract_result(info, more_info) for (info, more_info) in zip(videos_info, videos_more_info['lineup'])] return { '_type': 'playlist', - 'id': embedCode, + 'id': video_id, 'title': unescapeHTML(videos_more_info['title']), 'entries': videos, } else: return self._extract_result(videos_info[0], videos_more_info) + + +class OoyalaIE(OoyalaBaseIE): + _VALID_URL = r'(?:ooyala:|https?://.+?\.ooyala\.com/.*?(?:embedCode|ec)=)(?P<id>.+?)(&|$)' + + _TESTS = [ + { + # From http://it.slashdot.org/story/13/04/25/178216/recovering-data-from-broken-hard-drives-and-ssds-video + 'url': 'http://player.ooyala.com/player.js?embedCode=pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'info_dict': { + 'id': 'pxczE2YjpfHfn1f3M-ykG_AmJRRn0PD8', + 'ext': 'mp4', + 'title': 'Explaining Data Recovery from Hard Drives and SSDs', + 'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.', + }, + }, { + # Only available for ipad + 'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'info_dict': { + 'id': 'x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0', + 'ext': 'mp4', + 'title': 'Simulation Overview - Levels of Simulation', + 'description': '', + }, + }, + { + # Information available only through SAS api + # From http://community.plm.automation.siemens.com/t5/News-NX-Manufacturing/Tool-Path-Divide/ba-p/4187 + 'url': 'http://player.ooyala.com/player.js?embedCode=FiOG81ZTrvckcchQxmalf4aQj590qTEx', + 'md5': 'a84001441b35ea492bc03736e59e7935', + 'info_dict': { + 'id': 'FiOG81ZTrvckcchQxmalf4aQj590qTEx', + 'ext': 'mp4', + 'title': 'Ooyala video', + } + } + ] + + @staticmethod + def _url_for_embed_code(embed_code): + return 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code + + @classmethod + def _build_url_result(cls, embed_code): + return cls.url_result(cls._url_for_embed_code(embed_code), + ie=cls.ie_key()) + + def _real_extract(self, url): + embed_code = self._match_id(url) + player_url = 'http://player.ooyala.com/player.js?embedCode=%s' % embed_code + return self._extract(player_url, embed_code) + + +class OoyalaExternalIE(OoyalaBaseIE): + _VALID_URL = r'''(?x) + (?: + ooyalaexternal:| + https?://.+?\.ooyala\.com/.*?\bexternalId= + ) + (?P<partner_id>[^:]+) + : + (?P<id>.+) + (?: + :| + .*?&pcode= + ) + (?P<pcode>.+?) + (&|$) + ''' + + _TEST = { + 'url': 'https://player.ooyala.com/player.js?externalId=espn:10365079&pcode=1kNG061cgaoolOncv54OAO1ceO-I&adSetCode=91cDU6NuXTGKz3OdjOxFdAgJVtQcKJnI&callback=handleEvents&hasModuleParams=1&height=968&playerBrandingId=7af3bd04449c444c964f347f11873075&targetReplaceId=videoPlayer&width=1656&wmode=opaque&allowScriptAccess=always', + 'info_dict': { + 'id': 'FkYWtmazr6Ed8xmvILvKLWjd4QvYZpzG', + 'ext': 'mp4', + 'title': 'dm_140128_30for30Shorts___JudgingJewellv2', + 'description': '', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + partner_id = mobj.group('partner_id') + video_id = mobj.group('id') + pcode = mobj.group('pcode') + player_url = 'http://player.ooyala.com/player.js?externalId=%s:%s&pcode=%s' % (partner_id, video_id, pcode) + return self._extract(player_url, video_id) diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py index f179ea200..6cdc2638b 100644 --- a/youtube_dl/extractor/patreon.py +++ b/youtube_dl/extractor/patreon.py @@ -87,7 +87,7 @@ class PatreonIE(InfoExtractor): r'<div class="attach"><a target="_blank" href="([^"]+)">', webpage, 'attachment URL', default=None) embed = self._html_search_regex( - r'<div id="watchCreation">\s*<iframe class="embedly-embed" src="([^"]+)"', + r'<div[^>]+id="watchCreation"[^>]*>\s*<iframe[^>]+src="([^"]+)"', webpage, 'embedded URL', default=None) if attach_fn is not None: diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py new file mode 100644 index 000000000..72d1b2718 --- /dev/null +++ b/youtube_dl/extractor/porn91.py @@ -0,0 +1,71 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +from ..compat import compat_urllib_parse +from .common import InfoExtractor +from ..utils import ( + parse_duration, + int_or_none, + ExtractorError, +) + + +class Porn91IE(InfoExtractor): + IE_NAME = '91porn' + _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)' + + _TEST = { + 'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134', + 'md5': '6df8f6d028bc8b14f5dbd73af742fb20', + 'info_dict': { + 'id': '7e42283b4f5ab36da134', + 'title': '18岁大一漂亮学妹，水嫩性感，再爽一次！', + 'ext': 'mp4', + 'duration': 431, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id + self._set_cookie('91porn.com', 'language', 'cn_CN') + webpage = self._download_webpage(url, video_id, 'get HTML content') + + if '作为游客，你每天只可观看10个视频' in webpage: + raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True) + + title = self._search_regex( + r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title') + title = title.replace('\n', '') + + # get real url + file_id = self._search_regex( + r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id') + sec_code = self._search_regex( + r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code') + max_vid = self._search_regex( + r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid') + url_params = compat_urllib_parse.urlencode({ + 'VID': file_id, + 'mp4': '1', + 'seccode': sec_code, + 'max_vid': max_vid, + }) + info_cn = self._download_webpage( + 'http://91porn.com/getfile.php?' + url_params, video_id, + 'get real video url') + video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url') + + duration = parse_duration(self._search_regex( + r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False)) + + comment_count = int_or_none(self._search_regex( + r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False)) + + return { + 'id': video_id, + 'title': title, + 'url': video_url, + 'duration': duration, + 'comment_count': comment_count, + } diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 0c8b731cf..daa284ea2 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -71,7 +71,8 @@ class PornHubIE(InfoExtractor): video_urls = list(map(compat_urllib_parse.unquote, re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) if webpage.find('"encrypted":true') != -1: - password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password')) + password = compat_urllib_parse.unquote_plus( + self._search_regex(r'"video_title":"([^"]+)', webpage, 'password')) video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) formats = [] diff --git a/youtube_dl/extractor/pornovoisines.py b/youtube_dl/extractor/pornovoisines.py index 9688ed948..eba4dfbb3 100644 --- a/youtube_dl/extractor/pornovoisines.py +++ b/youtube_dl/extractor/pornovoisines.py @@ -34,7 +34,7 @@ class PornoVoisinesIE(InfoExtractor): 'duration': 120, 'view_count': int, 'average_rating': float, - 'categories': ['Débutante', 'Scénario', 'Sodomie'], + 'categories': ['Débutantes', 'Scénario', 'Sodomie'], 'age_limit': 18, } } @@ -71,7 +71,7 @@ class PornoVoisinesIE(InfoExtractor): view_count = int_or_none(self._search_regex( r'(\d+) vues', webpage, 'view count', fatal=False)) average_rating = self._search_regex( - r'Note : (\d+,\d+)', webpage, 'average rating', fatal=False) + r'Note\s*:\s*(\d+(?:,\d+)?)', webpage, 'average rating', fatal=False) if average_rating: average_rating = float_or_none(average_rating.replace(',', '.')) diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py index 7cc799664..255d4abc1 100644 --- a/youtube_dl/extractor/prosiebensat1.py +++ b/youtube_dl/extractor/prosiebensat1.py @@ -17,7 +17,7 @@ from ..utils import ( class ProSiebenSat1IE(InfoExtractor): IE_NAME = 'prosiebensat1' IE_DESC = 'ProSiebenSat.1 Digital' - _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|ran|the-voice-of-germany)\.de|fem\.com)/(?P<id>.+)' + _VALID_URL = r'https?://(?:www\.)?(?:(?:prosieben|prosiebenmaxx|sixx|sat1|kabeleins|the-voice-of-germany)\.(?:de|at)|ran\.de|fem\.com)/(?P<id>.+)' _TESTS = [ { diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py index 13113820b..bafa81c21 100644 --- a/youtube_dl/extractor/qqmusic.py +++ b/youtube_dl/extractor/qqmusic.py @@ -9,7 +9,6 @@ from .common import InfoExtractor from ..utils import ( strip_jsonp, unescapeHTML, - js_to_json, ) from ..compat import compat_urllib_request @@ -19,17 +18,23 @@ class QQMusicIE(InfoExtractor): _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)' _TESTS = [{ 'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD', - 'md5': 'bed90b6db2a7a7a7e11bc585f471f63a', + 'md5': '9ce1c1c8445f561506d2e3cfb0255705', 'info_dict': { 'id': '004295Et37taLD', - 'ext': 'm4a', + 'ext': 'mp3', 'title': '可惜没如果', 'upload_date': '20141227', 'creator': '林俊杰', - 'description': 'md5:4348ff1dd24036906baa7b6f973f8d30', + 'description': 'md5:d327722d0361576fde558f1ac68a7065', } }] + _FORMATS = { + 'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320}, + 'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128}, + 'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10} + } + # Reference: m_r_GetRUin() in top_player.js # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js @staticmethod @@ -60,6 +65,8 @@ class QQMusicIE(InfoExtractor): lrc_content = self._html_search_regex( r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>', detail_info_page, 'LRC lyrics', default=None) + if lrc_content: + lrc_content = lrc_content.replace('\\n', '\n') guid = self.m_r_get_ruin() @@ -67,11 +74,22 @@ class QQMusicIE(InfoExtractor): 'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid, mid, note='Retrieve vkey', errnote='Unable to get vkey', transform_source=strip_jsonp)['key'] - song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid) + + formats = [] + for format_id, details in self._FORMATS.items(): + formats.append({ + 'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0' + % (details['prefix'], mid, details['ext'], vkey, guid), + 'format': format_id, + 'format_id': format_id, + 'preference': details['preference'], + 'abr': details.get('abr'), + }) + self._sort_formats(formats) return { 'id': mid, - 'url': song_url, + 'formats': formats, 'title': song_name, 'upload_date': publish_time, 'creator': singer, @@ -179,60 +197,49 @@ class QQMusicToplistIE(QQPlaylistBaseIE): _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)' _TESTS = [{ - 'url': 'http://y.qq.com/#type=toplist&p=global_12', + 'url': 'http://y.qq.com/#type=toplist&p=global_123', 'info_dict': { - 'id': 'global_12', - 'title': 'itunes榜', + 'id': 'global_123', + 'title': '美国iTunes榜', }, 'playlist_count': 10, }, { - 'url': 'http://y.qq.com/#type=toplist&p=top_6', + 'url': 'http://y.qq.com/#type=toplist&p=top_3', 'info_dict': { - 'id': 'top_6', + 'id': 'top_3', 'title': 'QQ音乐巅峰榜·欧美', + 'description': 'QQ音乐巅峰榜·欧美根据用户收听行为自动生成，集结当下最流行的欧美新歌！:更新时间：每周四22点|统' + '计周期：一周（上周四至本周三）|统计对象：三个月内发行的欧美歌曲|统计数量：100首|统计算法：根据' + '歌曲在一周内的有效播放次数，由高到低取前100名（同一歌手最多允许5首歌曲同时上榜）|有效播放次数：' + '登录用户完整播放一首歌曲，记为一次有效播放；同一用户收听同一首歌曲，每天记录为1次有效播放' }, 'playlist_count': 100, }, { - 'url': 'http://y.qq.com/#type=toplist&p=global_5', + 'url': 'http://y.qq.com/#type=toplist&p=global_106', 'info_dict': { - 'id': 'global_5', - 'title': '韩国mnet排行榜', + 'id': 'global_106', + 'title': '韩国Mnet榜', }, 'playlist_count': 50, }] - @staticmethod - def strip_qq_jsonp(code): - return js_to_json(re.sub(r'^MusicJsonCallback\((.*?)\)/\*.+?\*/$', r'\1', code)) - def _real_extract(self, url): list_id = self._match_id(url) list_type, num_id = list_id.split("_") - list_page = self._download_webpage( - "http://y.qq.com/y/static/toplist/index/%s.html" % list_id, - list_id, 'Download toplist page') - - entries = [] - if list_type == 'top': - jsonp_url = "http://y.qq.com/y/static/toplist/json/top/%s/1.js" % num_id - else: - jsonp_url = "http://y.qq.com/y/static/toplist/json/global/%s/1_1.js" % num_id - toplist_json = self._download_json( - jsonp_url, list_id, note='Retrieve toplist json', - errnote='Unable to get toplist json', transform_source=self.strip_qq_jsonp) - - for song in toplist_json['l']: - s = song['s'] - song_mid = s.split("|")[20] - entries.append(self.url_result( - 'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic', - song_mid)) + 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg?type=%s&topid=%s&format=json' + % (list_type, num_id), + list_id, 'Download toplist page') - list_name = self._html_search_regex( - r'<h2 id="top_name">([^\']+)</h2>', list_page, 'top list name', - default=None) + entries = [ + self.url_result( + 'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid'] + ) for song in toplist_json['songlist'] + ] - return self.playlist_result(entries, list_id, list_name) + topinfo = toplist_json.get('topinfo', {}) + list_name = topinfo.get('ListName') + list_description = topinfo.get('info') + return self.playlist_result(entries, list_id, list_name, list_description) diff --git a/youtube_dl/extractor/rtbf.py b/youtube_dl/extractor/rtbf.py index dce64e151..5a381d9ce 100644 --- a/youtube_dl/extractor/rtbf.py +++ b/youtube_dl/extractor/rtbf.py @@ -1,10 +1,11 @@ # coding: utf-8 from __future__ import unicode_literals -import re -import json - from .common import InfoExtractor +from ..utils import ( + int_or_none, + unescapeHTML, +) class RTBFIE(InfoExtractor): @@ -16,25 +17,24 @@ class RTBFIE(InfoExtractor): 'id': '1921274', 'ext': 'mp4', 'title': 'Les Diables au coeur (épisode 2)', - 'description': 'Football - Diables Rouges', 'duration': 3099, - 'timestamp': 1398456336, - 'upload_date': '20140425', } } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) - page = self._download_webpage('https://www.rtbf.be/video/embed?id=%s' % video_id, video_id) + webpage = self._download_webpage( + 'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id) - data = json.loads(self._html_search_regex( - r'<div class="js-player-embed(?: player-embed)?" data-video="([^"]+)"', page, 'data video'))['data'] + data = self._parse_json( + unescapeHTML(self._search_regex( + r'data-video="([^"]+)"', webpage, 'data video')), + video_id) video_url = data.get('downloadUrl') or data.get('url') - if data['provider'].lower() == 'youtube': + if data.get('provider').lower() == 'youtube': return self.url_result(video_url, 'Youtube') return { @@ -42,8 +42,8 @@ class RTBFIE(InfoExtractor): 'url': video_url, 'title': data['title'], 'description': data.get('description') or data.get('subtitle'), - 'thumbnail': data['thumbnail']['large'], + 'thumbnail': data.get('thumbnail'), 'duration': data.get('duration') or data.get('realDuration'), - 'timestamp': data['created'], - 'view_count': data['viewCount'], + 'timestamp': int_or_none(data.get('created')), + 'view_count': int_or_none(data.get('viewCount')), } diff --git a/youtube_dl/extractor/rtlnow.py b/youtube_dl/extractor/rtlnow.py deleted file mode 100644 index 785a8045e..000000000 --- a/youtube_dl/extractor/rtlnow.py +++ /dev/null @@ -1,174 +0,0 @@ -# encoding: utf-8 -from __future__ import unicode_literals - -import re - -from .common import InfoExtractor -from ..utils import ( - ExtractorError, - clean_html, - unified_strdate, - int_or_none, -) - - -class RTLnowIE(InfoExtractor): - """Information Extractor for RTL NOW, RTL2 NOW, RTL NITRO, SUPER RTL NOW, VOX NOW and n-tv NOW""" - _VALID_URL = r'''(?x) - (?:https?://)? - (?P<url> - (?P<domain> - rtl-now\.rtl\.de| - rtl2now\.rtl2\.de| - (?:www\.)?voxnow\.de| - (?:www\.)?rtlnitronow\.de| - (?:www\.)?superrtlnow\.de| - (?:www\.)?n-tvnow\.de) - /+[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\? - (?:container_id|film_id)=(?P<video_id>[0-9]+)& - player=1(?:&season=[0-9]+)?(?:&.*)? - )''' - - _TESTS = [ - { - 'url': 'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1', - 'info_dict': { - 'id': '90419', - 'ext': 'flv', - 'title': 'Ahornallee - Folge 1 - Der Einzug', - 'description': 'md5:ce843b6b5901d9a7f7d04d1bbcdb12de', - 'upload_date': '20070416', - 'duration': 1685, - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Only works from Germany', - }, - { - 'url': 'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5', - 'info_dict': { - 'id': '69756', - 'ext': 'flv', - 'title': 'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.', - 'description': 'md5:3fb247005ed21a935ffc82b7dfa70cf0', - 'thumbnail': 'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg', - 'upload_date': '20120519', - 'duration': 1245, - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Only works from Germany', - }, - { - 'url': 'http://www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17', - 'info_dict': { - 'id': '13883', - 'ext': 'flv', - 'title': 'Voxtours - Südafrika-Reporter II', - 'description': 'md5:de7f8d56be6fd4fed10f10f57786db00', - 'upload_date': '20090627', - 'duration': 1800, - }, - 'params': { - 'skip_download': True, - }, - }, - { - 'url': 'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1', - 'info_dict': { - 'id': '99205', - 'ext': 'flv', - 'title': 'Medicopter 117 - Angst!', - 'description': 're:^Im Therapiezentrum \'Sonnalm\' kommen durch eine Unachtsamkeit die für die B.handlung mit Phobikern gehaltenen Voglespinnen frei\. Eine Ausreißerin', - 'thumbnail': 'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg', - 'upload_date': '20080928', - 'duration': 2691, - }, - 'params': { - 'skip_download': True, - }, - }, - { - 'url': 'http://rtl-now.rtl.de/der-bachelor/folge-4.php?film_id=188729&player=1&season=5', - 'info_dict': { - 'id': '188729', - 'ext': 'flv', - 'upload_date': '20150204', - 'description': 'md5:5e1ce23095e61a79c166d134b683cecc', - 'title': 'Der Bachelor - Folge 4', - } - }, { - 'url': 'http://www.n-tvnow.de/deluxe-alles-was-spass-macht/thema-ua-luxushotel-fuer-vierbeiner.php?container_id=153819&player=1&season=0', - 'only_matching': True, - }, - ] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_page_url = 'http://%s/' % mobj.group('domain') - video_id = mobj.group('video_id') - - webpage = self._download_webpage('http://' + mobj.group('url'), video_id) - - mobj = re.search(r'(?s)<div style="margin-left: 20px; font-size: 13px;">(.*?)<div id="playerteaser">', webpage) - if mobj: - raise ExtractorError(clean_html(mobj.group(1)), expected=True) - - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage, default=None) - - upload_date = unified_strdate(self._html_search_meta('uploadDate', webpage, 'upload date')) - - mobj = re.search(r'<meta itemprop="duration" content="PT(?P<seconds>\d+)S" />', webpage) - duration = int(mobj.group('seconds')) if mobj else None - - playerdata_url = self._html_search_regex( - r"'playerdata': '(?P<playerdata_url>[^']+)'", webpage, 'playerdata_url') - - playerdata = self._download_xml(playerdata_url, video_id, 'Downloading player data XML') - - videoinfo = playerdata.find('./playlist/videoinfo') - - formats = [] - for filename in videoinfo.findall('filename'): - mobj = re.search(r'(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>.+)', filename.text) - if mobj: - fmt = { - 'url': mobj.group('url'), - 'play_path': 'mp4:' + mobj.group('play_path'), - 'page_url': video_page_url, - 'player_url': video_page_url + 'includes/vodplayer.swf', - } - else: - mobj = re.search(r'.*/(?P<hoster>[^/]+)/videos/(?P<play_path>.+)\.f4m', filename.text) - if mobj: - fmt = { - 'url': 'rtmpe://fms.rtl.de/' + mobj.group('hoster'), - 'play_path': 'mp4:' + mobj.group('play_path'), - 'page_url': url, - 'player_url': video_page_url + 'includes/vodplayer.swf', - } - else: - fmt = { - 'url': filename.text, - } - fmt.update({ - 'width': int_or_none(filename.get('width')), - 'height': int_or_none(filename.get('height')), - 'vbr': int_or_none(filename.get('bitrate')), - 'ext': 'flv', - }) - formats.append(fmt) - - return { - 'id': video_id, - 'title': title, - 'description': description, - 'thumbnail': thumbnail, - 'upload_date': upload_date, - 'duration': duration, - 'formats': formats, - } diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py index d0981115d..9fbe239d8 100644 --- a/youtube_dl/extractor/rts.py +++ b/youtube_dl/extractor/rts.py @@ -190,6 +190,7 @@ class RTSIE(InfoExtractor): 'tbr': media['rate'] or extract_bitrate(media['url']), } for media in info['media'] if media.get('rate')]) + self._check_formats(formats, video_id) self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 849300140..82cd98ac7 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -17,7 +17,7 @@ from ..utils import ( def _decrypt_url(png): - encrypted_data = base64.b64decode(png) + encrypted_data = base64.b64decode(png.encode('utf-8')) text_index = encrypted_data.find(b'tEXt') text_chunk = encrypted_data[text_index - 4:] length = struct_unpack('!I', text_chunk[:4])[0] diff --git a/youtube_dl/extractor/rutv.py b/youtube_dl/extractor/rutv.py index 55604637d..d9df06861 100644 --- a/youtube_dl/extractor/rutv.py +++ b/youtube_dl/extractor/rutv.py @@ -104,7 +104,7 @@ class RUTVIE(InfoExtractor): @classmethod def _extract_url(cls, webpage): mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.rutv\.ru/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage) + r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.(?:rutv\.ru|vgtrk\.com)/(?:iframe/(?:swf|video|live)/id|index/iframe/cast_id)/.+?)\1', webpage) if mobj: return mobj.group('url') diff --git a/youtube_dl/extractor/sbs.py b/youtube_dl/extractor/sbs.py index b8775c2f9..d4bd1a0d7 100644 --- a/youtube_dl/extractor/sbs.py +++ b/youtube_dl/extractor/sbs.py @@ -1,7 +1,6 @@ # -*- coding: utf-8 -*- from __future__ import unicode_literals -import json import re from .common import InfoExtractor from ..utils import ( @@ -33,16 +32,18 @@ class SBSIE(InfoExtractor): }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - release_urls_json = js_to_json(self._search_regex( + player = self._search_regex( r'(?s)playerParams\.releaseUrls\s*=\s*(\{.*?\n\});\n', - webpage, '')) - release_urls = json.loads(release_urls_json) - theplatform_url = ( - release_urls.get('progressive') or release_urls.get('standard')) + webpage, 'player') + player = re.sub(r"'\s*\+\s*[\da-zA-Z_]+\s*\+\s*'", '', player) + + release_urls = self._parse_json(js_to_json(player), video_id) + + theplatform_url = release_urls.get('progressive') or release_urls['standard'] title = remove_end(self._og_search_title(webpage), ' (The Feed)') description = self._html_search_meta('description', webpage) @@ -52,7 +53,6 @@ class SBSIE(InfoExtractor): '_type': 'url_transparent', 'id': video_id, 'url': theplatform_url, - 'title': title, 'description': description, 'thumbnail': thumbnail, diff --git a/youtube_dl/extractor/senateisvp.py b/youtube_dl/extractor/senateisvp.py index d3b8a1be4..9c53704ea 100644 --- a/youtube_dl/extractor/senateisvp.py +++ b/youtube_dl/extractor/senateisvp.py @@ -48,7 +48,7 @@ class SenateISVPIE(InfoExtractor): ["arch", "", "http://ussenate-f.akamaihd.net/"] ] _IE_NAME = 'senate.gov' - _VALID_URL = r'http://www\.senate\.gov/isvp/\?(?P<qs>.+)' + _VALID_URL = r'http://www\.senate\.gov/isvp/?\?(?P<qs>.+)' _TESTS = [{ 'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png', 'info_dict': { @@ -72,12 +72,16 @@ class SenateISVPIE(InfoExtractor): 'ext': 'mp4', 'title': 'Integrated Senate Video Player' } + }, { + # From http://www.c-span.org/video/?96791-1 + 'url': 'http://www.senate.gov/isvp?type=live&comm=banking&filename=banking012715', + 'only_matching': True, }] @staticmethod def _search_iframe_url(webpage): mobj = re.search( - r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/\?[^'\"]+)['\"]", + r"<iframe[^>]+src=['\"](?P<url>http://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]", webpage) if mobj: return mobj.group('url') diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index 26ced716e..9f3e944e7 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -47,7 +47,7 @@ class SharedIE(InfoExtractor): video_url = self._html_search_regex( r'data-url="([^"]+)"', video_page, 'video URL') title = base64.b64decode(self._html_search_meta( - 'full:title', webpage, 'title')).decode('utf-8') + 'full:title', webpage, 'title').encode('utf-8')).decode('utf-8') filesize = int_or_none(self._html_search_meta( 'full:size', webpage, 'file size', fatal=False)) thumbnail = self._html_search_regex( diff --git a/youtube_dl/extractor/sockshare.py b/youtube_dl/extractor/sockshare.py deleted file mode 100644 index b5fa6f1da..000000000 --- a/youtube_dl/extractor/sockshare.py +++ /dev/null @@ -1,83 +0,0 @@ -# coding: utf-8 -from __future__ import unicode_literals - -import re - -from ..compat import ( - compat_urllib_parse, - compat_urllib_request, -) -from ..utils import ( - determine_ext, - ExtractorError, -) - -from .common import InfoExtractor - - -class SockshareIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?sockshare\.com/file/(?P<id>[0-9A-Za-z]+)' - _FILE_DELETED_REGEX = r'This file doesn\'t exist, or has been removed\.</div>' - _TEST = { - 'url': 'http://www.sockshare.com/file/437BE28B89D799D7', - 'md5': '9d0bf1cfb6dbeaa8d562f6c97506c5bd', - 'info_dict': { - 'id': '437BE28B89D799D7', - 'title': 'big_buck_bunny_720p_surround.avi', - 'ext': 'avi', - } - } - - def _real_extract(self, url): - video_id = self._match_id(url) - url = 'http://sockshare.com/file/%s' % video_id - webpage = self._download_webpage(url, video_id) - - if re.search(self._FILE_DELETED_REGEX, webpage) is not None: - raise ExtractorError('Video %s does not exist' % video_id, - expected=True) - - confirm_hash = self._html_search_regex(r'''(?x)<input\s+ - type="hidden"\s+ - value="([^"]*)"\s+ - name="hash" - ''', webpage, 'hash') - - fields = { - "hash": confirm_hash.encode('utf-8'), - "confirm": "Continue as Free User" - } - - post = compat_urllib_parse.urlencode(fields) - req = compat_urllib_request.Request(url, post) - # Apparently, this header is required for confirmation to work. - req.add_header('Host', 'www.sockshare.com') - req.add_header('Content-type', 'application/x-www-form-urlencoded') - - webpage = self._download_webpage( - req, video_id, 'Downloading video page') - - video_url = self._html_search_regex( - r'<a href="([^"]*)".+class="download_file_link"', - webpage, 'file url') - video_url = "http://www.sockshare.com" + video_url - title = self._html_search_regex(( - r'<h1>(.+)<strong>', - r'var name = "([^"]+)";'), - webpage, 'title', default=None) - thumbnail = self._html_search_regex( - r'<img\s+src="([^"]*)".+?name="bg"', - webpage, 'thumbnail', default=None) - - formats = [{ - 'format_id': 'sd', - 'url': video_url, - 'ext': determine_ext(title), - }] - - return { - 'id': video_id, - 'title': title, - 'thumbnail': thumbnail, - 'formats': formats, - } diff --git a/youtube_dl/extractor/sohu.py b/youtube_dl/extractor/sohu.py index eab4adfca..29bd9ce6f 100644 --- a/youtube_dl/extractor/sohu.py +++ b/youtube_dl/extractor/sohu.py @@ -23,9 +23,7 @@ class SohuIE(InfoExtractor): 'ext': 'mp4', 'title': 'MV：Far East Movement《The Illest》', }, - 'params': { - 'cn_verification_proxy': 'proxy.uku.im:8888' - } + 'skip': 'On available in China', }, { 'url': 'http://tv.sohu.com/20150305/n409385080.shtml', 'md5': 'ac9a5d322b4bf9ae184d53e4711e4f1a', diff --git a/youtube_dl/extractor/soompi.py b/youtube_dl/extractor/soompi.py new file mode 100644 index 000000000..5da66ca9e --- /dev/null +++ b/youtube_dl/extractor/soompi.py @@ -0,0 +1,146 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .crunchyroll import CrunchyrollIE + +from .common import InfoExtractor +from ..compat import compat_HTTPError +from ..utils import ( + ExtractorError, + int_or_none, + remove_start, + xpath_text, +) + + +class SoompiBaseIE(InfoExtractor): + def _get_episodes(self, webpage, episode_filter=None): + episodes = self._parse_json( + self._search_regex( + r'VIDEOS\s*=\s*(\[.+?\]);', webpage, 'episodes JSON'), + None) + return list(filter(episode_filter, episodes)) + + +class SoompiIE(SoompiBaseIE, CrunchyrollIE): + IE_NAME = 'soompi' + _VALID_URL = r'https?://tv\.soompi\.com/(?:en/)?watch/(?P<id>[0-9]+)' + _TESTS = [{ + 'url': 'http://tv.soompi.com/en/watch/29235', + 'info_dict': { + 'id': '29235', + 'ext': 'mp4', + 'title': 'Episode 1096', + 'description': '2015-05-20' + }, + 'params': { + 'skip_download': True, + }, + }] + + def _get_episode(self, webpage, video_id): + return self._get_episodes(webpage, lambda x: x['id'] == video_id)[0] + + def _get_subtitles(self, config, video_id): + sub_langs = {} + for subtitle in config.findall('./{default}preload/subtitles/subtitle'): + sub_langs[subtitle.attrib['id']] = subtitle.attrib['title'] + + subtitles = {} + for s in config.findall('./{default}preload/subtitle'): + lang_code = sub_langs.get(s.attrib['id']) + if not lang_code: + continue + sub_id = s.get('id') + data = xpath_text(s, './data', 'data') + iv = xpath_text(s, './iv', 'iv') + if not id or not iv or not data: + continue + subtitle = self._decrypt_subtitles(data, iv, sub_id).decode('utf-8') + subtitles[lang_code] = self._extract_subtitles(subtitle) + return subtitles + + def _real_extract(self, url): + video_id = self._match_id(url) + + try: + webpage = self._download_webpage( + url, video_id, 'Downloading episode page') + except ExtractorError as ee: + if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: + webpage = ee.cause.read() + block_message = self._html_search_regex( + r'(?s)<div class="block-message">(.+?)</div>', webpage, + 'block message', default=None) + if block_message: + raise ExtractorError(block_message, expected=True) + raise + + formats = [] + config = None + for format_id in re.findall(r'\?quality=([0-9a-zA-Z]+)', webpage): + config = self._download_xml( + 'http://tv.soompi.com/en/show/_/%s-config.xml?mode=hls&quality=%s' % (video_id, format_id), + video_id, 'Downloading %s XML' % format_id) + m3u8_url = xpath_text( + config, './{default}preload/stream_info/file', + '%s m3u8 URL' % format_id) + if not m3u8_url: + continue + formats.extend(self._extract_m3u8_formats( + m3u8_url, video_id, 'mp4', m3u8_id=format_id)) + self._sort_formats(formats) + + episode = self._get_episode(webpage, video_id) + + title = episode['name'] + description = episode.get('description') + duration = int_or_none(episode.get('duration')) + + thumbnails = [{ + 'id': thumbnail_id, + 'url': thumbnail_url, + } for thumbnail_id, thumbnail_url in episode.get('img_url', {}).items()] + + subtitles = self.extract_subtitles(config, video_id) + + return { + 'id': video_id, + 'title': title, + 'description': description, + 'thumbnails': thumbnails, + 'duration': duration, + 'formats': formats, + 'subtitles': subtitles + } + + +class SoompiShowIE(SoompiBaseIE): + IE_NAME = 'soompi:show' + _VALID_URL = r'https?://tv\.soompi\.com/en/shows/(?P<id>[0-9a-zA-Z\-_]+)' + _TESTS = [{ + 'url': 'http://tv.soompi.com/en/shows/liar-game', + 'info_dict': { + 'id': 'liar-game', + 'title': 'Liar Game', + 'description': 'md5:52c02bce0c1a622a95823591d0589b66', + }, + 'playlist_count': 14, + }] + + def _real_extract(self, url): + show_id = self._match_id(url) + + webpage = self._download_webpage( + url, show_id, 'Downloading show page') + + title = remove_start(self._og_search_title(webpage), 'SoompiTV | ') + description = self._og_search_description(webpage) + + entries = [ + self.url_result('http://tv.soompi.com/en/watch/%s' % episode['id'], 'Soompi') + for episode in self._get_episodes(webpage)] + + return self.playlist_result(entries, show_id, title, description) diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index b936202f6..06d6e6640 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -71,7 +71,7 @@ class SpankwireIE(InfoExtractor): compat_urllib_parse.unquote, re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage))) if webpage.find('flashvars\.encrypted = "true"') != -1: - password = self._html_search_regex( + password = self._search_regex( r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ') video_urls = list(map( diff --git a/youtube_dl/extractor/spiegeltv.py b/youtube_dl/extractor/spiegeltv.py index 98cf92d89..359722ad6 100644 --- a/youtube_dl/extractor/spiegeltv.py +++ b/youtube_dl/extractor/spiegeltv.py @@ -51,9 +51,9 @@ class SpiegeltvIE(InfoExtractor): is_wide = media_json['is_wide'] server_json = self._download_json( - 'http://www.spiegel.tv/streaming_servers/', video_id, - note='Downloading server information') - server = server_json[0]['endpoint'] + 'http://spiegeltv-prod-static.s3.amazonaws.com/projectConfigs/projectConfig.json', + video_id, note='Downloading server information') + server = server_json['streamingserver'][0]['endpoint'] thumbnails = [] for image in media_json['images']: @@ -76,5 +76,6 @@ class SpiegeltvIE(InfoExtractor): 'ext': 'm4v', 'description': description, 'duration': duration, - 'thumbnails': thumbnails + 'thumbnails': thumbnails, + 'rtmp_live': True, } diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py index becdf658f..86d509ae5 100644 --- a/youtube_dl/extractor/sportbox.py +++ b/youtube_dl/extractor/sportbox.py @@ -4,37 +4,36 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( - parse_duration, - parse_iso8601, + unified_strdate, ) class SportBoxIE(InfoExtractor): - _VALID_URL = r'https?://news\.sportbox\.ru/Vidy_sporta/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)' - _TESTS = [ - { - 'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S', - 'md5': 'ff56a598c2cf411a9a38a69709e97079', - 'info_dict': { - 'id': '80822', - 'ext': 'mp4', - 'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн', - 'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed', - 'thumbnail': 're:^https?://.*\.jpg$', - 'timestamp': 1411896237, - 'upload_date': '20140928', - 'duration': 4846, - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, { - 'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4', - 'only_matching': True, - } - ] + _VALID_URL = r'https?://news\.sportbox\.ru/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)' + _TESTS = [{ + 'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S', + 'md5': 'ff56a598c2cf411a9a38a69709e97079', + 'info_dict': { + 'id': '80822', + 'ext': 'mp4', + 'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн', + 'description': 'md5:3d72dc4a006ab6805d82f037fdc637ad', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20140928', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4', + 'only_matching': True, + }, { + 'url': 'http://news.sportbox.ru/video/no_ads/spbvideo_NI536574_V_Novorossijske_proshel_detskij_turnir_Pole_slavy_bojevoj?ci=211355', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -42,35 +41,75 @@ class SportBoxIE(InfoExtractor): webpage = self._download_webpage(url, display_id) - video_id = self._search_regex( - r'src="/vdl/player/media/(\d+)"', webpage, 'video id') + player = self._search_regex( + r'src="/?(vdl/player/[^"]+)"', webpage, 'player') + + title = self._html_search_regex( + [r'"nodetitle"\s*:\s*"([^"]+)"', r'class="node-header_{1,2}title">([^<]+)'], + webpage, 'title') + description = self._og_search_description(webpage) or self._html_search_meta( + 'description', webpage, 'description') + thumbnail = self._og_search_thumbnail(webpage) + upload_date = unified_strdate(self._html_search_meta( + 'dateCreated', webpage, 'upload date')) + + return { + '_type': 'url_transparent', + 'url': compat_urlparse.urljoin(url, '/%s' % player), + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'upload_date': upload_date, + } - player = self._download_webpage( - 'http://news.sportbox.ru/vdl/player/media/%s' % video_id, - display_id, 'Downloading player webpage') + +class SportBoxEmbedIE(InfoExtractor): + _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://news.sportbox.ru/vdl/player/ci/211355', + 'info_dict': { + 'id': '211355', + 'ext': 'mp4', + 'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<iframe[^>]+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"', + webpage) + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) hls = self._search_regex( - r"var\s+original_hls_file\s*=\s*'([^']+)'", player, 'hls file') + r"sportboxPlayer\.jwplayer_common_params\.file\s*=\s*['\"]([^'\"]+)['\"]", + webpage, 'hls file') - formats = self._extract_m3u8_formats(hls, display_id, 'mp4') + formats = self._extract_m3u8_formats(hls, video_id, 'mp4') - title = self._html_search_regex( - r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title') - description = self._html_search_regex( - r'(?s)<div itemprop="description">(.+?)</div>', webpage, 'description', fatal=False) - thumbnail = self._og_search_thumbnail(webpage) - timestamp = parse_iso8601(self._search_regex( - r'<span itemprop="uploadDate">([^<]+)</span>', webpage, 'timestamp', fatal=False)) - duration = parse_duration(self._html_search_regex( - r'<meta itemprop="duration" content="PT([^"]+)">', webpage, 'duration', fatal=False)) + title = self._search_regex( + r'sportboxPlayer\.node_title\s*=\s*"([^"]+)"', webpage, 'title') + + thumbnail = self._search_regex( + r'sportboxPlayer\.jwplayer_common_params\.image\s*=\s*"([^"]+)"', + webpage, 'thumbnail', default=None) return { 'id': video_id, - 'display_id': display_id, 'title': title, - 'description': description, 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, 'formats': formats, } diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py index 56be52638..d1b7264b4 100644 --- a/youtube_dl/extractor/teamcoco.py +++ b/youtube_dl/extractor/teamcoco.py @@ -10,6 +10,7 @@ from .common import InfoExtractor from ..utils import ( ExtractorError, qualities, + determine_ext, ) from ..compat import compat_ord @@ -50,6 +51,17 @@ class TeamcocoIE(InfoExtractor): 'params': { 'skip_download': True, # m3u8 downloads } + }, { + 'url': 'http://teamcoco.com/video/full-episode-mon-6-1-joel-mchale-jake-tapper-and-musical-guest-courtney-barnett?playlist=x;eyJ0eXBlIjoidGFnIiwiaWQiOjl9', + 'info_dict': { + 'id': '89341', + 'ext': 'mp4', + 'title': 'Full Episode - Mon. 6/1 - Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett', + 'description': 'Guests: Joel McHale, Jake Tapper, And Musical Guest Courtney Barnett', + }, + 'params': { + 'skip_download': True, # m3u8 downloads + } } ] _VIDEO_ID_REGEXES = ( @@ -108,10 +120,24 @@ class TeamcocoIE(InfoExtractor): formats = [] get_quality = qualities(['500k', '480p', '1000k', '720p', '1080p']) for filed in data['files']: - if filed['type'] == 'hls': - formats.extend(self._extract_m3u8_formats( - filed['url'], video_id, ext='mp4')) + if determine_ext(filed['url']) == 'm3u8': + # compat_urllib_parse.urljoin does not work here + if filed['url'].startswith('/'): + m3u8_url = 'http://ht.cdn.turner.com/tbs/big/teamcoco' + filed['url'] + else: + m3u8_url = filed['url'] + m3u8_formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4') + for m3u8_format in m3u8_formats: + if m3u8_format not in formats: + formats.append(m3u8_format) + elif determine_ext(filed['url']) == 'f4m': + # TODO Correct f4m extraction + continue else: + if filed['url'].startswith('/mp4:protected/'): + # TODO Correct extraction for these files + continue m_format = re.search(r'(\d+(k|p))\.mp4', filed['url']) if m_format is not None: format_id = m_format.group(1) diff --git a/youtube_dl/extractor/telecinco.py b/youtube_dl/extractor/telecinco.py index 251a68680..a0c744fd1 100644 --- a/youtube_dl/extractor/telecinco.py +++ b/youtube_dl/extractor/telecinco.py @@ -16,6 +16,10 @@ class TelecincoIE(MiTeleIE): 'title': 'Con Martín Berasategui, hacer un bacalao al ...', 'duration': 662, }, + 'params': { + # m3u8 download + 'skip_download': True, + }, }, { 'url': 'http://www.telecinco.es/informativos/nacional/Pablo_Iglesias-Informativos_Telecinco-entrevista-Pedro_Piqueras_2_1945155182.html', 'only_matching': True, diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py index 466155ef8..f6694149b 100644 --- a/youtube_dl/extractor/tenplay.py +++ b/youtube_dl/extractor/tenplay.py @@ -2,6 +2,10 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import ( + int_or_none, + float_or_none, +) class TenPlayIE(InfoExtractor): @@ -49,18 +53,23 @@ class TenPlayIE(InfoExtractor): if protocol == 'rtmp': url = url.replace('&mp4:', '') + tbr = int_or_none(rendition.get('encodingRate'), 1000) + formats.append({ - 'format_id': '_'.join(['rtmp', rendition['videoContainer'].lower(), rendition['videoCodec'].lower()]), - 'width': rendition['frameWidth'], - 'height': rendition['frameHeight'], - 'tbr': rendition['encodingRate'] / 1024, - 'filesize': rendition['size'], + 'format_id': '_'.join( + ['rtmp', rendition['videoContainer'].lower(), + rendition['videoCodec'].lower(), '%sk' % tbr]), + 'width': int_or_none(rendition['frameWidth']), + 'height': int_or_none(rendition['frameHeight']), + 'tbr': tbr, + 'filesize': int_or_none(rendition['size']), 'protocol': protocol, 'ext': ext, 'vcodec': rendition['videoCodec'].lower(), 'container': rendition['videoContainer'].lower(), 'url': url, }) + self._sort_formats(formats) return { 'id': video_id, @@ -74,8 +83,8 @@ class TenPlayIE(InfoExtractor): 'url': json['thumbnailURL'] }], 'thumbnail': json['videoStillURL'], - 'duration': json['length'] / 1000, - 'timestamp': float(json['creationDate']) / 1000, - 'uploader': json['customFields']['production_company_distributor'] if 'production_company_distributor' in json['customFields'] else 'TENplay', - 'view_count': json['playsTotal'] + 'duration': float_or_none(json.get('length'), 1000), + 'timestamp': float_or_none(json.get('creationDate'), 1000), + 'uploader': json.get('customFields', {}).get('production_company_distributor') or 'TENplay', + 'view_count': int_or_none(json.get('playsTotal')), } diff --git a/youtube_dl/extractor/tf1.py b/youtube_dl/extractor/tf1.py index 025d0877c..3a68eaa80 100644 --- a/youtube_dl/extractor/tf1.py +++ b/youtube_dl/extractor/tf1.py @@ -6,8 +6,8 @@ from .common import InfoExtractor class TF1IE(InfoExtractor): """TF1 uses the wat.tv player.""" - _VALID_URL = r'http://(?:videos\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html' - _TESTS = { + _VALID_URL = r'http://(?:(?:videos|www|lci)\.tf1|www\.tfou)\.fr/.*?-(?P<id>\d+)(?:-\d+)?\.html' + _TESTS = [{ 'url': 'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html', 'info_dict': { 'id': '10635995', @@ -32,7 +32,13 @@ class TF1IE(InfoExtractor): # Sometimes wat serves the whole file with the --test option 'skip_download': True, }, - } + }, { + 'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html', + 'only_matching': True, + }, { + 'url': 'http://lci.tf1.fr/sept-a-huit/videos/sept-a-huit-du-24-mai-2015-8611550.html', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/tnaflix.py b/youtube_dl/extractor/tnaflix.py index d48cbbf14..c282865b2 100644 --- a/youtube_dl/extractor/tnaflix.py +++ b/youtube_dl/extractor/tnaflix.py @@ -10,26 +10,32 @@ from ..utils import ( class TNAFlixIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/(?P<cat_id>[\w-]+)/(?P<display_id>[\w-]+)/video(?P<id>\d+)' + _VALID_URL = r'https?://(?:www\.)?tnaflix\.com/[^/]+/(?P<display_id>[^/]+)/video(?P<id>\d+)' _TITLE_REGEX = r'<title>(.+?) - TNAFlix Porn Videos</title>' _DESCRIPTION_REGEX = r'<h3 itemprop="description">([^<]+)</h3>' _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"' - _TEST = { - 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', - 'md5': 'ecf3498417d09216374fc5907f9c6ec0', - 'info_dict': { - 'id': '553878', - 'display_id': 'Carmella-Decesare-striptease', - 'ext': 'mp4', - 'title': 'Carmella Decesare - striptease', - 'description': '', - 'thumbnail': 're:https?://.*\.jpg$', - 'duration': 91, - 'age_limit': 18, + _TESTS = [ + { + 'url': 'http://www.tnaflix.com/porn-stars/Carmella-Decesare-striptease/video553878', + 'md5': 'ecf3498417d09216374fc5907f9c6ec0', + 'info_dict': { + 'id': '553878', + 'display_id': 'Carmella-Decesare-striptease', + 'ext': 'mp4', + 'title': 'Carmella Decesare - striptease', + 'description': '', + 'thumbnail': 're:https?://.*\.jpg$', + 'duration': 91, + 'age_limit': 18, + } + }, + { + 'url': 'https://www.tnaflix.com/amateur-porn/bunzHD-Ms.Donk/video358632', + 'only_matching': True, } - } + ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -45,9 +51,8 @@ class TNAFlixIE(InfoExtractor): age_limit = self._rta_search(webpage) - duration = self._html_search_meta('duration', webpage, 'duration', default=None) - if duration: - duration = parse_duration(duration[1:]) + duration = parse_duration(self._html_search_meta( + 'duration', webpage, 'duration', default=None)) cfg_url = self._proto_relative_url(self._html_search_regex( self._CONFIG_REGEX, webpage, 'flashvars.config'), 'http:') @@ -56,14 +61,15 @@ class TNAFlixIE(InfoExtractor): cfg_url, display_id, note='Downloading metadata', transform_source=fix_xml_ampersands) - thumbnail = cfg_xml.find('./startThumb').text + thumbnail = self._proto_relative_url( + cfg_xml.find('./startThumb').text, 'http:') formats = [] for item in cfg_xml.findall('./quality/item'): video_url = re.sub('speed=\d+', 'speed=', item.find('videoLink').text) format_id = item.find('res').text fmt = { - 'url': video_url, + 'url': self._proto_relative_url(video_url, 'http:'), 'format_id': format_id, } m = re.search(r'^(\d+)', format_id) diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py index d73ad3762..6ca8840b0 100644 --- a/youtube_dl/extractor/tube8.py +++ b/youtube_dl/extractor/tube8.py @@ -47,7 +47,7 @@ class Tube8IE(InfoExtractor): webpage = self._download_webpage(req, display_id) flashvars = json.loads(self._html_search_regex( - r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars')) + r'flashvars\s*=\s*({.+?})', webpage, 'flashvars')) video_url = flashvars['video_url'] if flashvars.get('encrypted') is True: @@ -58,19 +58,19 @@ class Tube8IE(InfoExtractor): thumbnail = flashvars.get('image_url') title = self._html_search_regex( - r'videotitle\s*=\s*"([^"]+)', webpage, 'title') + r'videoTitle\s*=\s*"([^"]+)', webpage, 'title') description = self._html_search_regex( - r'>Description:</strong>(.+?)<', webpage, 'description', fatal=False) + r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False) uploader = self._html_search_regex( - r'<strong class="video-username">(?:<a href="[^"]+">)?([^<]+)(?:</a>)?</strong>', + r'<span class="username">\s*(.+?)\s*<', webpage, 'uploader', fatal=False) like_count = int_or_none(self._html_search_regex( - r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False)) + r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False)) dislike_count = int_or_none(self._html_search_regex( - r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False)) + r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False)) view_count = self._html_search_regex( - r'<strong>Views: </strong>([\d,\.]+)</li>', webpage, 'view count', fatal=False) + r'<strong>Views: </strong>([\d,\.]+)\s*</li>', webpage, 'view count', fatal=False) if view_count: view_count = str_to_int(view_count) comment_count = self._html_search_regex( diff --git a/youtube_dl/extractor/tubitv.py b/youtube_dl/extractor/tubitv.py new file mode 100644 index 000000000..2c4b21807 --- /dev/null +++ b/youtube_dl/extractor/tubitv.py @@ -0,0 +1,84 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import codecs +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, + compat_urllib_request +) +from ..utils import ( + ExtractorError, + int_or_none, +) + + +class TubiTvIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?tubitv\.com/video\?id=(?P<id>[0-9]+)' + _LOGIN_URL = 'http://tubitv.com/login' + _NETRC_MACHINE = 'tubitv' + _TEST = { + 'url': 'http://tubitv.com/video?id=54411&title=The_Kitchen_Musical_-_EP01', + 'info_dict': { + 'id': '54411', + 'ext': 'mp4', + 'title': 'The Kitchen Musical - EP01', + 'thumbnail': 're:^https?://.*\.png$', + 'description': 'md5:37532716166069b353e8866e71fefae7', + 'duration': 2407, + }, + 'params': { + 'skip_download': 'HLS download', + }, + } + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + return + self.report_login() + form_data = { + 'username': username, + 'password': password, + } + payload = compat_urllib_parse.urlencode(form_data).encode('utf-8') + request = compat_urllib_request.Request(self._LOGIN_URL, payload) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + login_page = self._download_webpage( + request, None, False, 'Wrong login info') + if not re.search(r'id="tubi-logout"', login_page): + raise ExtractorError( + 'Login failed (invalid username/password)', expected=True) + + def _real_initialize(self): + self._login() + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + if re.search(r"<(?:DIV|div) class='login-required-screen'>", webpage): + raise ExtractorError( + 'This video requires login, use --username and --password ' + 'options to provide account credentials.', expected=True) + + title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) + duration = int_or_none(self._html_search_meta( + 'video:duration', webpage, 'duration')) + + apu = self._search_regex(r"apu='([^']+)'", webpage, 'apu') + m3u8_url = codecs.decode(apu, 'rot_13')[::-1] + formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'thumbnail': thumbnail, + 'description': description, + 'duration': duration, + } diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py index 828c808a6..e6218808f 100644 --- a/youtube_dl/extractor/tumblr.py +++ b/youtube_dl/extractor/tumblr.py @@ -28,6 +28,17 @@ class TumblrIE(InfoExtractor): 'description': 'md5:dba62ac8639482759c8eb10ce474586a', 'thumbnail': 're:http://.*\.jpg', } + }, { + 'url': 'http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching', + 'md5': 'de07e5211d60d4f3a2c3df757ea9f6ab', + 'info_dict': { + 'id': 'Wmur', + 'ext': 'mp4', + 'title': 'naked smoking & stretching', + 'upload_date': '20150506', + 'timestamp': 1430931613, + }, + 'add_ie': ['Vidme'], }] def _real_extract(self, url): @@ -38,6 +49,12 @@ class TumblrIE(InfoExtractor): url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id) webpage = self._download_webpage(url, video_id) + vid_me_embed_url = self._search_regex( + r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]', + webpage, 'vid.me embed', default=None) + if vid_me_embed_url is not None: + return self.url_result(vid_me_embed_url, 'Vidme') + iframe_url = self._search_regex( r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'', webpage, 'iframe url') diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py index 4de0aac52..fad720b68 100644 --- a/youtube_dl/extractor/tutv.py +++ b/youtube_dl/extractor/tutv.py @@ -26,7 +26,7 @@ class TutvIE(InfoExtractor): data_content = self._download_webpage( 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info') - video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8') + video_url = base64.b64decode(compat_parse_qs(data_content)['kpt'][0].encode('utf-8')).decode('utf-8') return { 'id': internal_id, diff --git a/youtube_dl/extractor/tv2.py b/youtube_dl/extractor/tv2.py new file mode 100644 index 000000000..fa338b936 --- /dev/null +++ b/youtube_dl/extractor/tv2.py @@ -0,0 +1,126 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + determine_ext, + int_or_none, + float_or_none, + parse_iso8601, + remove_end, +) + + +class TV2IE(InfoExtractor): + _VALID_URL = 'http://(?:www\.)?tv2\.no/v/(?P<id>\d+)' + _TEST = { + 'url': 'http://www.tv2.no/v/916509/', + 'md5': '9cb9e3410b18b515d71892f27856e9b1', + 'info_dict': { + 'id': '916509', + 'ext': 'flv', + 'title': 'Se Gryttens hyllest av Steven Gerrard', + 'description': 'TV 2 Sportens huspoet tar avskjed med Liverpools kaptein Steven Gerrard.', + 'timestamp': 1431715610, + 'upload_date': '20150515', + 'duration': 156.967, + 'view_count': int, + 'categories': list, + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + formats = [] + format_urls = [] + for protocol in ('HDS', 'HLS'): + data = self._download_json( + 'http://sumo.tv2.no/api/web/asset/%s/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % (video_id, protocol), + video_id, 'Downloading play JSON')['playback'] + for item in data['items']['item']: + video_url = item.get('url') + if not video_url or video_url in format_urls: + continue + format_id = '%s-%s' % (protocol.lower(), item.get('mediaFormat')) + if not self._is_valid_url(video_url, video_id, format_id): + continue + format_urls.append(video_url) + ext = determine_ext(video_url) + if ext == 'f4m': + formats.extend(self._extract_f4m_formats( + video_url, video_id, f4m_id=format_id)) + elif ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', m3u8_id=format_id)) + elif ext == 'ism' or video_url.endswith('.ism/Manifest'): + pass + else: + formats.append({ + 'url': video_url, + 'format_id': format_id, + 'tbr': int_or_none(item.get('bitrate')), + 'filesize': int_or_none(item.get('fileSize')), + }) + self._sort_formats(formats) + + asset = self._download_json( + 'http://sumo.tv2.no/api/web/asset/%s.json' % video_id, + video_id, 'Downloading metadata JSON')['asset'] + + title = asset['title'] + description = asset.get('description') + timestamp = parse_iso8601(asset.get('createTime')) + duration = float_or_none(asset.get('accurateDuration') or asset.get('duration')) + view_count = int_or_none(asset.get('views')) + categories = asset.get('keywords', '').split(',') + + thumbnails = [{ + 'id': thumbnail.get('@type'), + 'url': thumbnail.get('url'), + } for _, thumbnail in asset.get('imageVersions', {}).items()] + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description, + 'thumbnails': thumbnails, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': view_count, + 'categories': categories, + 'formats': formats, + } + + +class TV2ArticleIE(InfoExtractor): + _VALID_URL = 'http://(?:www\.)?tv2\.no/(?:a|\d{4}/\d{2}/\d{2}(/[^/]+)+)/(?P<id>\d+)' + _TESTS = [{ + 'url': 'http://www.tv2.no/2015/05/16/nyheter/alesund/krim/pingvin/6930542', + 'info_dict': { + 'id': '6930542', + 'title': 'Russen hetses etter pingvintyveri – innrømmer å ha åpnet luken på buret', + 'description': 'md5:339573779d3eea3542ffe12006190954', + }, + 'playlist_count': 2, + }, { + 'url': 'http://www.tv2.no/a/6930542', + 'only_matching': True, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('http://www.tv2.no/v/%s' % video_id, 'TV2') + for video_id in re.findall(r'data-assetid="(\d+)"', webpage)] + + title = remove_end(self._og_search_title(webpage), ' - TV2.no') + description = remove_end(self._og_search_description(webpage), ' - TV2.no') + + return self.playlist_result(entries, playlist_id, title, description) diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py index 102362b29..dc3a8334a 100644 --- a/youtube_dl/extractor/tvigle.py +++ b/youtube_dl/extractor/tvigle.py @@ -5,7 +5,9 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, float_or_none, + int_or_none, parse_age_limit, ) @@ -24,22 +26,24 @@ class TvigleIE(InfoExtractor): 'display_id': 'sokrat', 'ext': 'flv', 'title': 'Сократ', - 'description': 'md5:a05bd01be310074d5833efc6743be95e', + 'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17', 'duration': 6586, - 'age_limit': 0, + 'age_limit': 12, }, + 'skip': 'georestricted', }, { 'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/', - 'md5': 'd9012d7c7c598fe7a11d7fb46dc1f574', + 'md5': 'e7efe5350dd5011d0de6550b53c3ba7b', 'info_dict': { 'id': '5142516', - 'ext': 'mp4', + 'ext': 'flv', 'title': 'Ведущий телепрограммы «60 минут» (США) о Владимире Высоцком', 'description': 'md5:027f7dc872948f14c96d19b4178428a4', 'duration': 186.080, 'age_limit': 0, }, + 'skip': 'georestricted', }, { 'url': 'https://cloud.tvigle.ru/video/5267604/', 'only_matching': True, @@ -54,7 +58,7 @@ class TvigleIE(InfoExtractor): if not video_id: webpage = self._download_webpage(url, display_id) video_id = self._html_search_regex( - r'<li class="video-preview current_playing" id="(\d+)">', + r'class="video-preview current_playing" id="(\d+)">', webpage, 'video id') video_data = self._download_json( @@ -62,21 +66,34 @@ class TvigleIE(InfoExtractor): item = video_data['playlist']['items'][0] + videos = item.get('videos') + + error_message = item.get('errorMessage') + if not videos and error_message: + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error_message), expected=True) + title = item['title'] - description = item['description'] - thumbnail = item['thumbnail'] + description = item.get('description') + thumbnail = item.get('thumbnail') duration = float_or_none(item.get('durationMilliseconds'), 1000) age_limit = parse_age_limit(item.get('ageRestrictions')) formats = [] for vcodec, fmts in item['videos'].items(): - for quality, video_url in fmts.items(): + for format_id, video_url in fmts.items(): + if format_id == 'm3u8': + formats.extend(self._extract_m3u8_formats( + video_url, video_id, 'mp4', m3u8_id=vcodec)) + continue + height = self._search_regex( + r'^(\d+)[pP]$', format_id, 'height', default=None) formats.append({ 'url': video_url, - 'format_id': '%s-%s' % (vcodec, quality), + 'format_id': '%s-%s' % (vcodec, format_id), 'vcodec': vcodec, - 'height': int(quality[:-1]), - 'filesize': item['video_files_size'][vcodec][quality], + 'height': int_or_none(height), + 'filesize': int_or_none(item.get('video_files_size', {}).get(vcodec, {}).get(format_id)), }) self._sort_formats(formats) diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py index 67e8bfea0..c1ee1decc 100644 --- a/youtube_dl/extractor/twentyfourvideo.py +++ b/youtube_dl/extractor/twentyfourvideo.py @@ -15,7 +15,7 @@ class TwentyFourVideoIE(InfoExtractor): _TESTS = [ { 'url': 'http://www.24video.net/video/view/1044982', - 'md5': '48dd7646775690a80447a8dca6a2df76', + 'md5': 'd041af8b5b4246ea466226a0d6693345', 'info_dict': { 'id': '1044982', 'ext': 'mp4', @@ -54,7 +54,7 @@ class TwentyFourVideoIE(InfoExtractor): webpage, 'upload date')) uploader = self._html_search_regex( - r'Загрузил\s*<a href="/jsecUser/movies/[^"]+" class="link">([^<]+)</a>', + r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>', webpage, 'uploader', fatal=False) view_count = int_or_none(self._html_search_regex( diff --git a/youtube_dl/extractor/ultimedia.py b/youtube_dl/extractor/ultimedia.py index 96c809eaf..c4751050e 100644 --- a/youtube_dl/extractor/ultimedia.py +++ b/youtube_dl/extractor/ultimedia.py @@ -4,6 +4,7 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_urlparse from ..utils import ( ExtractorError, qualities, @@ -44,9 +45,9 @@ class UltimediaIE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - deliver_url = self._search_regex( - r'<iframe[^>]+src="(https?://(?:www\.)?ultimedia\.com/deliver/[^"]+)"', - webpage, 'deliver URL') + deliver_url = self._proto_relative_url(self._search_regex( + r'<iframe[^>]+src="((?:https?:)?//(?:www\.)?ultimedia\.com/deliver/[^"]+)"', + webpage, 'deliver URL'), compat_urllib_parse_urlparse(url).scheme + ':') deliver_page = self._download_webpage( deliver_url, video_id, 'Downloading iframe page') @@ -57,7 +58,8 @@ class UltimediaIE(InfoExtractor): player = self._parse_json( self._search_regex( - r"jwplayer\('player(?:_temp)?'\)\.setup\(({.+?})\)\.on", deliver_page, 'player'), + r"jwplayer\('player(?:_temp)?'\)\.setup\(({.+?})\)\.on", + deliver_page, 'player'), video_id) quality = qualities(['flash', 'html5']) diff --git a/youtube_dl/extractor/vgtv.py b/youtube_dl/extractor/vgtv.py index e6ee1e471..f38a72fde 100644 --- a/youtube_dl/extractor/vgtv.py +++ b/youtube_dl/extractor/vgtv.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import float_or_none +from ..utils import ( + ExtractorError, + float_or_none, +) class VGTVIE(InfoExtractor): @@ -59,16 +62,16 @@ class VGTVIE(InfoExtractor): }, { # streamType: live - 'url': 'http://www.vgtv.no/#!/live/100015/direkte-her-kan-du-se-laksen-live-fra-suldalslaagen', + 'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla', 'info_dict': { - 'id': '100015', + 'id': '113063', 'ext': 'flv', - 'title': 'DIREKTE: Her kan du se laksen live fra Suldalslågen!', - 'description': 'md5:9a60cc23fa349f761628924e56eeec2d', + 'title': 're:^DIREKTE: V75 fra Solvalla [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', + 'description': 'md5:b3743425765355855f88e096acc93231', 'thumbnail': 're:^https?://.*\.jpg', 'duration': 0, - 'timestamp': 1407423348, - 'upload_date': '20140807', + 'timestamp': 1432975582, + 'upload_date': '20150530', 'view_count': int, }, 'params': { @@ -97,7 +100,12 @@ class VGTVIE(InfoExtractor): % (host, video_id, HOST_WEBSITES[host]), video_id, 'Downloading media JSON') + if data.get('status') == 'inactive': + raise ExtractorError( + 'Video %s is no longer available' % video_id, expected=True) + streams = data['streamUrls'] + stream_type = data.get('streamType') formats = [] @@ -107,7 +115,8 @@ class VGTVIE(InfoExtractor): hls_url, video_id, 'mp4', m3u8_id='hls')) hds_url = streams.get('hds') - if hds_url: + # wasLive hds are always 404 + if hds_url and stream_type != 'wasLive': formats.extend(self._extract_f4m_formats( hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', video_id, f4m_id='hds')) @@ -135,13 +144,14 @@ class VGTVIE(InfoExtractor): return { 'id': video_id, - 'title': data['title'], + 'title': self._live_title(data['title']), 'description': data['description'], 'thumbnail': data['images']['main'] + '?t[]=900x506q80', 'timestamp': data['published'], 'duration': float_or_none(data['duration'], 1000), 'view_count': data['displays'], 'formats': formats, + 'is_live': True if stream_type == 'live' else False, } diff --git a/youtube_dl/extractor/videott.py b/youtube_dl/extractor/videott.py index ececc7ee0..591024ead 100644 --- a/youtube_dl/extractor/videott.py +++ b/youtube_dl/extractor/videott.py @@ -43,7 +43,7 @@ class VideoTtIE(InfoExtractor): formats = [ { - 'url': base64.b64decode(res['u']).decode('utf-8'), + 'url': base64.b64decode(res['u'].encode('utf-8')).decode('utf-8'), 'ext': 'flv', 'format_id': res['l'], } for res in settings['res'] if res['u'] diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py index bd953fb4c..e0b55078b 100644 --- a/youtube_dl/extractor/vidme.py +++ b/youtube_dl/extractor/vidme.py @@ -10,7 +10,7 @@ from ..utils import ( class VidmeIE(InfoExtractor): _VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)' - _TEST = { + _TESTS = [{ 'url': 'https://vid.me/QNB', 'md5': 'f42d05e7149aeaec5c037b17e5d3dc82', 'info_dict': { @@ -23,9 +23,14 @@ class VidmeIE(InfoExtractor): 'upload_date': '20140725', 'thumbnail': 're:^https?://.*\.jpg', }, - } + }, { + # From http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching + 'url': 'https://vid.me/e/Wmur', + 'only_matching': True, + }] def _real_extract(self, url): + url = url.replace('vid.me/e/', 'vid.me/') video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py index 619039e51..15377097e 100644 --- a/youtube_dl/extractor/vier.py +++ b/youtube_dl/extractor/vier.py @@ -38,11 +38,14 @@ class VierIE(InfoExtractor): webpage = self._download_webpage(url, display_id) video_id = self._search_regex( - r'"nid"\s*:\s*"(\d+)"', webpage, 'video id') + [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'], + webpage, 'video id') application = self._search_regex( - r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod') + [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'], + webpage, 'application', default='vier_vod') filename = self._search_regex( - r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename') + [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'], + webpage, 'filename') playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename) formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4') diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index cf6af1e5c..7f2fb1ca8 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -1,29 +1,65 @@ from __future__ import unicode_literals -import re +import time +import hmac +import hashlib +import itertools -from ..compat import ( - compat_urlparse, - compat_urllib_request, -) from ..utils import ( ExtractorError, - unescapeHTML, - unified_strdate, - US_RATINGS, - determine_ext, - mimetype2ext, + int_or_none, + parse_age_limit, + parse_iso8601, ) from .common import InfoExtractor -class VikiIE(InfoExtractor): - IE_NAME = 'viki' +class VikiBaseIE(InfoExtractor): + _VALID_URL_BASE = r'https?://(?:www\.)?viki\.(?:com|net|mx|jp|fr)/' + _API_QUERY_TEMPLATE = '/v4/%sapp=%s&t=%s&site=www.viki.com' + _API_URL_TEMPLATE = 'http://api.viki.io%s&sig=%s' + + _APP = '65535a' + _APP_VERSION = '2.2.5.1428709186' + _APP_SECRET = '-$iJ}@p7!G@SyU/je1bEyWg}upLu-6V6-Lg9VD(]siH,r.,m-r|ulZ,U4LC/SeR)' + + def _prepare_call(self, path, timestamp=None): + path += '?' if '?' not in path else '&' + if not timestamp: + timestamp = int(time.time()) + query = self._API_QUERY_TEMPLATE % (path, self._APP, timestamp) + sig = hmac.new( + self._APP_SECRET.encode('ascii'), + query.encode('ascii'), + hashlib.sha1 + ).hexdigest() + return self._API_URL_TEMPLATE % (query, sig) + + def _call_api(self, path, video_id, note, timestamp=None): + resp = self._download_json( + self._prepare_call(path, timestamp), video_id, note) + + error = resp.get('error') + if error: + if error == 'invalid timestamp': + resp = self._download_json( + self._prepare_call(path, int(resp['current_timestamp'])), + video_id, '%s (retry)' % note) + error = resp.get('error') + if error: + self._raise_error(resp['error']) + + return resp - # iPad2 - _USER_AGENT = 'Mozilla/5.0(iPad; U; CPU OS 4_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8F191 Safari/6533.18.5' + def _raise_error(self, error): + raise ExtractorError( + '%s returned error: %s' % (self.IE_NAME, error), + expected=True) - _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)' + +class VikiIE(VikiBaseIE): + IE_NAME = 'viki' + _VALID_URL = r'%s(?:videos|player)/(?P<id>[0-9]+v)' % VikiBaseIE._VALID_URL_BASE _TESTS = [{ 'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14', 'info_dict': { @@ -37,111 +73,218 @@ class VikiIE(InfoExtractor): }, 'skip': 'Blocked in the US', }, { + # clip 'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference', - 'md5': 'ca6493e6f0a6ec07da9aa8d6304b4b2c', + 'md5': '86c0b5dbd4d83a6611a79987cc7a1989', 'info_dict': { 'id': '1067139v', 'ext': 'mp4', + 'title': "'The Avengers: Age of Ultron' Press Conference", 'description': 'md5:d70b2f9428f5488321bfe1db10d612ea', + 'duration': 352, + 'timestamp': 1430380829, 'upload_date': '20150430', - 'title': '\'The Avengers: Age of Ultron\' Press Conference', + 'uploader': 'Arirang TV', + 'like_count': int, + 'age_limit': 0, } }, { 'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi', 'info_dict': { 'id': '1048879v', 'ext': 'mp4', - 'upload_date': '20140820', - 'description': 'md5:54ff56d51bdfc7a30441ec967394e91c', 'title': 'Ankhon Dekhi', + 'duration': 6512, + 'timestamp': 1408532356, + 'upload_date': '20140820', + 'uploader': 'Spuul', + 'like_count': int, + 'age_limit': 13, }, 'params': { - # requires ffmpeg + # m3u8 download 'skip_download': True, } + }, { + # episode + 'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1', + 'md5': '190f3ef426005ba3a080a63325955bc3', + 'info_dict': { + 'id': '44699v', + 'ext': 'mp4', + 'title': 'Boys Over Flowers - Episode 1', + 'description': 'md5:52617e4f729c7d03bfd4bcbbb6e946f2', + 'duration': 4155, + 'timestamp': 1270496524, + 'upload_date': '20100405', + 'uploader': 'group8', + 'like_count': int, + 'age_limit': 13, + } + }, { + # youtube external + 'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1', + 'md5': '216d1afdc0c64d1febc1e9f2bd4b864b', + 'info_dict': { + 'id': '50562v', + 'ext': 'mp4', + 'title': 'Poor Nastya [COMPLETE] - Episode 1', + 'description': '', + 'duration': 607, + 'timestamp': 1274949505, + 'upload_date': '20101213', + 'uploader': 'ad14065n', + 'uploader_id': 'ad14065n', + 'like_count': int, + 'age_limit': 13, + } + }, { + 'url': 'http://www.viki.com/player/44699v', + 'only_matching': True, }] def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - - uploader_m = re.search( - r'<strong>Broadcast Network: </strong>\s*([^<]*)<', webpage) - if uploader_m is None: - uploader = None - else: - uploader = uploader_m.group(1).strip() - - rating_str = self._html_search_regex( - r'<strong>Rating: </strong>\s*([^<]*)<', webpage, - 'rating information', default='').strip() - age_limit = US_RATINGS.get(rating_str) - - req = compat_urllib_request.Request( - 'http://www.viki.com/player5_fragment/%s?action=show&controller=videos' % video_id) - req.add_header('User-Agent', self._USER_AGENT) - info_webpage = self._download_webpage( - req, video_id, note='Downloading info page') - err_msg = self._html_search_regex(r'<div[^>]+class="video-error[^>]+>(.+)</div>', info_webpage, 'error message', default=None) - if err_msg: - if 'not available in your region' in err_msg: - raise ExtractorError( - 'Video %s is blocked from your location.' % video_id, - expected=True) - else: - raise ExtractorError('Viki said: ' + err_msg) - mobj = re.search( - r'<source[^>]+type="(?P<mime_type>[^"]+)"[^>]+src="(?P<url>[^"]+)"', info_webpage) - if not mobj: - raise ExtractorError('Unable to find video URL') - video_url = unescapeHTML(mobj.group('url')) - video_ext = mimetype2ext(mobj.group('mime_type')) - - if determine_ext(video_url) == 'm3u8': - formats = self._extract_m3u8_formats( - video_url, video_id, ext=video_ext) - else: - formats = [{ - 'url': video_url, - 'ext': video_ext, - }] - - upload_date_str = self._html_search_regex( - r'"created_at":"([^"]+)"', info_webpage, 'upload date') - upload_date = ( - unified_strdate(upload_date_str) - if upload_date_str is not None - else None - ) - - # subtitles - video_subtitles = self.extract_subtitles(video_id, info_webpage) - - return { + video = self._call_api( + 'videos/%s.json' % video_id, video_id, 'Downloading video JSON') + + title = None + titles = video.get('titles') + if titles: + title = titles.get('en') or titles[titles.keys()[0]] + if not title: + title = 'Episode %d' % video.get('number') if video.get('type') == 'episode' else video.get('id') or video_id + container_titles = video.get('container', {}).get('titles') + if container_titles: + container_title = container_titles.get('en') or container_titles[container_titles.keys()[0]] + title = '%s - %s' % (container_title, title) + + descriptions = video.get('descriptions') + description = descriptions.get('en') or descriptions[titles.keys()[0]] if descriptions else None + + duration = int_or_none(video.get('duration')) + timestamp = parse_iso8601(video.get('created_at')) + uploader = video.get('author') + like_count = int_or_none(video.get('likes', {}).get('count')) + age_limit = parse_age_limit(video.get('rating')) + + thumbnails = [] + for thumbnail_id, thumbnail in video.get('images', {}).items(): + thumbnails.append({ + 'id': thumbnail_id, + 'url': thumbnail.get('url'), + }) + + subtitles = {} + for subtitle_lang, _ in video.get('subtitle_completions', {}).items(): + subtitles[subtitle_lang] = [{ + 'ext': subtitles_format, + 'url': self._prepare_call( + 'videos/%s/subtitles/%s.%s' % (video_id, subtitle_lang, subtitles_format)), + } for subtitles_format in ('srt', 'vtt')] + + result = { 'id': video_id, 'title': title, - 'formats': formats, 'description': description, - 'thumbnail': thumbnail, - 'age_limit': age_limit, + 'duration': duration, + 'timestamp': timestamp, 'uploader': uploader, - 'subtitles': video_subtitles, - 'upload_date': upload_date, + 'like_count': like_count, + 'age_limit': age_limit, + 'thumbnails': thumbnails, + 'subtitles': subtitles, } - def _get_subtitles(self, video_id, info_webpage): - res = {} - for sturl_html in re.findall(r'<track src="([^"]+)"', info_webpage): - sturl = unescapeHTML(sturl_html) - m = re.search(r'/(?P<lang>[a-z]+)\.vtt', sturl) - if not m: - continue - res[m.group('lang')] = [{ - 'url': compat_urlparse.urljoin('http://www.viki.com', sturl), - 'ext': 'vtt', - }] - return res + streams = self._call_api( + 'videos/%s/streams.json' % video_id, video_id, + 'Downloading video streams JSON') + + if 'external' in streams: + result.update({ + '_type': 'url_transparent', + 'url': streams['external']['url'], + }) + return result + + formats = [] + for format_id, stream_dict in streams.items(): + height = self._search_regex( + r'^(\d+)[pP]$', format_id, 'height', default=None) + for protocol, format_dict in stream_dict.items(): + if format_id == 'm3u8': + formats = self._extract_m3u8_formats( + format_dict['url'], video_id, 'mp4', m3u8_id='m3u8-%s' % protocol) + else: + formats.append({ + 'url': format_dict['url'], + 'format_id': '%s-%s' % (format_id, protocol), + 'height': height, + }) + self._sort_formats(formats) + + result['formats'] = formats + return result + + +class VikiChannelIE(VikiBaseIE): + IE_NAME = 'viki:channel' + _VALID_URL = r'%s(?:tv|news|movies|artists)/(?P<id>[0-9]+c)' % VikiBaseIE._VALID_URL_BASE + _TESTS = [{ + 'url': 'http://www.viki.com/tv/50c-boys-over-flowers', + 'info_dict': { + 'id': '50c', + 'title': 'Boys Over Flowers', + 'description': 'md5:ecd3cff47967fe193cff37c0bec52790', + }, + 'playlist_count': 70, + }, { + 'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete', + 'info_dict': { + 'id': '1354c', + 'title': 'Poor Nastya [COMPLETE]', + 'description': 'md5:05bf5471385aa8b21c18ad450e350525', + }, + 'playlist_count': 127, + }, { + 'url': 'http://www.viki.com/news/24569c-showbiz-korea', + 'only_matching': True, + }, { + 'url': 'http://www.viki.com/movies/22047c-pride-and-prejudice-2005', + 'only_matching': True, + }, { + 'url': 'http://www.viki.com/artists/2141c-shinee', + 'only_matching': True, + }] + + _PER_PAGE = 25 + + def _real_extract(self, url): + channel_id = self._match_id(url) + + channel = self._call_api( + 'containers/%s.json' % channel_id, channel_id, + 'Downloading channel JSON') + + titles = channel['titles'] + title = titles.get('en') or titles[titles.keys()[0]] + + descriptions = channel['descriptions'] + description = descriptions.get('en') or descriptions[descriptions.keys()[0]] + + entries = [] + for video_type in ('episodes', 'clips', 'movies'): + for page_num in itertools.count(1): + page = self._call_api( + 'containers/%s/%s.json?per_page=%d&sort=number&direction=asc&with_paging=true&page=%d' + % (channel_id, video_type, self._PER_PAGE, page_num), channel_id, + 'Downloading %s JSON page #%d' % (video_type, page_num)) + for video in page['response']: + video_id = video['id'] + entries.append(self.url_result( + 'http://www.viki.com/videos/%s' % video_id, 'Viki')) + if not page['pagination']['next']: + break + + return self.playlist_result(entries, channel_id, title, description) diff --git a/youtube_dl/extractor/vuclip.py b/youtube_dl/extractor/vuclip.py index c3fde53f5..a6d9b5fee 100644 --- a/youtube_dl/extractor/vuclip.py +++ b/youtube_dl/extractor/vuclip.py @@ -49,7 +49,7 @@ class VuClipIE(InfoExtractor): links_code = self._search_regex( r'''(?xs) (?: - <img\s+src="/im/play.gif".*?>| + <img\s+src="[^"]*/play.gif".*?>| <!--\ player\ end\ -->\s*</div><!--\ thumb\ end--> ) (.*?) diff --git a/youtube_dl/extractor/vulture.py b/youtube_dl/extractor/vulture.py index 1eb24a3d6..faa167e65 100644 --- a/youtube_dl/extractor/vulture.py +++ b/youtube_dl/extractor/vulture.py @@ -44,7 +44,7 @@ class VultureIE(InfoExtractor): query_webpage = self._download_webpage( query_url, display_id, note='Downloading query page') params_json = self._search_regex( - r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n,\n', + r'(?sm)new MagnifyEmbeddablePlayer\({.*?contentItem:\s*(\{.*?\})\n?,\n', query_webpage, 'player params') params = json.loads(params_json) diff --git a/youtube_dl/extractor/wimp.py b/youtube_dl/extractor/wimp.py index d6dec25ca..f69d46a28 100644 --- a/youtube_dl/extractor/wimp.py +++ b/youtube_dl/extractor/wimp.py @@ -37,7 +37,8 @@ class WimpIE(InfoExtractor): video_id = mobj.group(1) webpage = self._download_webpage(url, video_id) video_url = self._search_regex( - r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", webpage, 'video URL') + [r"[\"']file[\"']\s*[:,]\s*[\"'](.+?)[\"']", r"videoId\s*:\s*[\"']([^\"']+)[\"']"], + webpage, 'video URL') if YoutubeIE.suitable(video_url): self.to_screen('Found YouTube video') return { diff --git a/youtube_dl/extractor/xminus.py b/youtube_dl/extractor/xminus.py index 8c6241aed..7c9d8af6f 100644 --- a/youtube_dl/extractor/xminus.py +++ b/youtube_dl/extractor/xminus.py @@ -43,7 +43,7 @@ class XMinusIE(InfoExtractor): r'minus_track\.dur_sec=\'([0-9]*?)\'', webpage, 'duration', fatal=False)) filesize_approx = parse_filesize(self._html_search_regex( - r'<div class="filesize[^"]*"></div>\s*([0-9.]+\s*[a-zA-Z][bB])', + r'<div id="finfo"[^>]*>\s*↓\s*([0-9.]+\s*[a-zA-Z][bB])', webpage, 'approximate filesize', fatal=False)) tbr = int_or_none(self._html_search_regex( r'<div class="quality[^"]*"></div>\s*([0-9]+)\s*kbps', @@ -58,7 +58,7 @@ class XMinusIE(InfoExtractor): description = re.sub(' *\r *', '\n', description) enc_token = self._html_search_regex( - r'minus_track\.tkn="(.+?)"', webpage, 'enc_token') + r'minus_track\.s?tkn="(.+?)"', webpage, 'enc_token') token = ''.join( c if pos == 3 else compat_chr(compat_ord(c) - 1) for pos, c in enumerate(reversed(enc_token))) diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index bf4e659ac..f9afbdbab 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,6 +15,7 @@ from ..utils import ( unescapeHTML, ExtractorError, int_or_none, + mimetype2ext, ) from .nbc import NBCSportsVPlayerIE @@ -236,6 +237,22 @@ class YahooIE(InfoExtractor): self._sort_formats(formats) + closed_captions = self._html_search_regex( + r'"closedcaptions":(\[[^\]]+\])', webpage, 'closed captions', + default='[]') + + cc_json = self._parse_json(closed_captions, video_id, fatal=False) + subtitles = {} + if cc_json: + for closed_caption in cc_json: + lang = closed_caption['lang'] + if lang not in subtitles: + subtitles[lang] = [] + subtitles[lang].append({ + 'url': closed_caption['url'], + 'ext': mimetype2ext(closed_caption['content_type']), + }) + return { 'id': video_id, 'display_id': display_id, @@ -244,6 +261,7 @@ class YahooIE(InfoExtractor): 'description': clean_html(meta['description']), 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), 'duration': int_or_none(meta.get('duration')), + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index e58184adc..419f7b019 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -49,6 +49,11 @@ class YoutubeBaseInfoExtractor(InfoExtractor): # YouTube sets the expire time to about two months expire_time=time.time() + 2 * 30 * 24 * 3600) + def _ids_to_results(self, ids): + return [ + self.url_result(vid_id, 'Youtube', video_id=vid_id) + for vid_id in ids] + def _login(self): """ Attempt to log in to YouTube. @@ -1121,12 +1126,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor): self.report_warning( 'Skipping DASH manifest: %r' % e, video_id) else: - # Hide the formats we found through non-DASH + # Remove the formats we found through non-DASH, they + # contain less info and it can be wrong, because we use + # fixed values (for example the resolution). See + # https://github.com/rg3/youtube-dl/issues/5774 for an + # example. dash_keys = set(df['format_id'] for df in dash_formats) - for f in formats: - if f['format_id'] in dash_keys: - f['format_id'] = 'nondash-%s' % f['format_id'] - f['preference'] = f.get('preference', 0) - 10000 + formats = [f for f in formats if f['format_id'] not in dash_keys] formats.extend(dash_formats) # Check for malformed aspect ratio @@ -1261,11 +1267,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): def _real_initialize(self): self._login() - def _ids_to_results(self, ids): - return [ - self.url_result(vid_id, 'Youtube', video_id=vid_id) - for vid_id in ids] - def _extract_mix(self, playlist_id): # The mixes are generated from a single video # the id of the playlist is just 'RD' + video_id @@ -1398,6 +1399,24 @@ class YoutubeChannelIE(InfoExtractor): channel_id = self._match_id(url) url = self._TEMPLATE_URL % channel_id + + # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) + # Workaround by extracting as a playlist if managed to obtain channel playlist URL + # otherwise fallback on channel by page extraction + channel_page = self._download_webpage( + url + '?view=57', channel_id, + 'Downloading channel page', fatal=False) + channel_playlist_id = self._html_search_meta( + 'channelId', channel_page, 'channel id', default=None) + if not channel_playlist_id: + channel_playlist_id = self._search_regex( + r'data-channel-external-id="([^"]+)"', + channel_page, 'channel id', default=None) + if channel_playlist_id and channel_playlist_id.startswith('UC'): + playlist_id = 'UU' + channel_playlist_id[2:] + return self.url_result( + compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') + channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') autogenerated = re.search(r'''(?x) class="[^"]*?(?: @@ -1601,20 +1620,10 @@ class YoutubeShowIE(InfoExtractor): class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): """ - Base class for extractors that fetch info from - http://www.youtube.com/feed_ajax + Base class for feed extractors Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. """ _LOGIN_REQUIRED = True - # use action_load_personal_feed instead of action_load_system_feed - _PERSONAL_FEED = False - - @property - def _FEED_TEMPLATE(self): - action = 'action_load_system_feed' - if self._PERSONAL_FEED: - action = 'action_load_personal_feed' - return 'https://www.youtube.com/feed_ajax?%s=1&feed_name=%s&paging=%%s' % (action, self._FEED_NAME) @property def IE_NAME(self): @@ -1624,67 +1633,23 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): self._login() def _real_extract(self, url): - feed_entries = [] - paging = 0 - for i in itertools.count(1): - info = self._download_json( - self._FEED_TEMPLATE % paging, - '%s feed' % self._FEED_NAME, - 'Downloading page %s' % i, - transform_source=uppercase_escape) - feed_html = info.get('feed_html') or info.get('content_html') - load_more_widget_html = info.get('load_more_widget_html') or feed_html - m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) - ids = orderedSet(m.group(1) for m in m_ids) - feed_entries.extend( - self.url_result(video_id, 'Youtube', video_id=video_id) - for video_id in ids) - mobj = re.search( - r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)', - load_more_widget_html) - if mobj is None: - break - paging = mobj.group('paging') - return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) - - -class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): - IE_NAME = 'youtube:recommended' - IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' - _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' - _FEED_NAME = 'recommended' - _PLAYLIST_TITLE = 'Youtube Recommended videos' - - -class YoutubeWatchLaterIE(YoutubePlaylistIE): - IE_NAME = 'youtube:watchlater' - IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' - _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|playlist\?list=WL)|:ytwatchlater' - - _TESTS = [] # override PlaylistIE tests - - def _real_extract(self, url): - return self._extract_playlist('WL') - - -class YoutubeHistoryIE(YoutubePlaylistIE): - IE_NAME = 'youtube:history' - IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' - _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' - _TESTS = [] - - def _real_extract(self, url): - title = 'Youtube History' - page = self._download_webpage('https://www.youtube.com/feed/history', title) + page = self._download_webpage( + 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE) # The extraction process is the same as for playlists, but the regex # for the video ids doesn't contain an index ids = [] more_widget_html = content_html = page - for page_num in itertools.count(1): matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) - new_ids = orderedSet(matches) + + # 'recommended' feed has infinite 'load more' and each new portion spins + # the same videos in (sometimes) slightly different order, so we'll check + # for unicity and break when portion has no new videos + new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches)) + if not new_ids: + break + ids.extend(new_ids) mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) @@ -1692,17 +1657,25 @@ class YoutubeHistoryIE(YoutubePlaylistIE): break more = self._download_json( - 'https://youtube.com/%s' % mobj.group('more'), title, + 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, 'Downloading page #%s' % page_num, transform_source=uppercase_escape) content_html = more['content_html'] more_widget_html = more['load_more_widget_html'] - return { - '_type': 'playlist', - 'title': title, - 'entries': self._ids_to_results(ids), - } + return self.playlist_result( + self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE) + + +class YoutubeWatchLaterIE(YoutubePlaylistIE): + IE_NAME = 'youtube:watchlater' + IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' + _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|playlist\?list=WL)|:ytwatchlater' + + _TESTS = [] # override PlaylistIE tests + + def _real_extract(self, url): + return self._extract_playlist('WL') class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): @@ -1717,42 +1690,25 @@ class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): return self.url_result(playlist_id, 'YoutubePlaylist') -class YoutubeSubscriptionsIE(YoutubePlaylistIE): - IE_NAME = 'youtube:subscriptions' - IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' - _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' - _TESTS = [] - - def _real_extract(self, url): - title = 'Youtube Subscriptions' - page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title) - - # The extraction process is the same as for playlists, but the regex - # for the video ids doesn't contain an index - ids = [] - more_widget_html = content_html = page +class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): + IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' + _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' + _FEED_NAME = 'recommended' + _PLAYLIST_TITLE = 'Youtube Recommended videos' - for page_num in itertools.count(1): - matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) - new_ids = orderedSet(matches) - ids.extend(new_ids) - mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) - if not mobj: - break +class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): + IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' + _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' + _FEED_NAME = 'subscriptions' + _PLAYLIST_TITLE = 'Youtube Subscriptions' - more = self._download_json( - 'https://youtube.com/%s' % mobj.group('more'), title, - 'Downloading page #%s' % page_num, - transform_source=uppercase_escape) - content_html = more['content_html'] - more_widget_html = more['load_more_widget_html'] - return { - '_type': 'playlist', - 'title': title, - 'entries': self._ids_to_results(ids), - } +class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): + IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' + _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' + _FEED_NAME = 'history' + _PLAYLIST_TITLE = 'Youtube History' class YoutubeTruncatedURLIE(InfoExtractor): diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 22dbc3aec..5a2315bd9 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -537,7 +537,7 @@ def parseOpts(overrideArguments=None): verbosity.add_option( '--dump-pages', '--dump-intermediate-pages', action='store_true', dest='dump_intermediate_pages', default=False, - help='Print downloaded pages to debug problems (very verbose)') + help='Print downloaded pages encoded using base64 to debug problems (very verbose)') verbosity.add_option( '--write-pages', action='store_true', dest='write_pages', default=False, @@ -713,7 +713,7 @@ def parseOpts(overrideArguments=None): help='Parse additional metadata like song title / artist from the video title. ' 'The format syntax is the same as --output, ' 'the parsed parameters replace existing values. ' - 'Additional templates: %(album), %(artist). ' + 'Additional templates: %(album)s, %(artist)s. ' 'Example: --metadata-from-title "%(artist)s - %(title)s" matches a title like ' '"Coldplay - Paradise"') postproc.add_option( diff --git a/youtube_dl/postprocessor/embedthumbnail.py b/youtube_dl/postprocessor/embedthumbnail.py index 8f825f785..774494efd 100644 --- a/youtube_dl/postprocessor/embedthumbnail.py +++ b/youtube_dl/postprocessor/embedthumbnail.py @@ -49,7 +49,7 @@ class EmbedThumbnailPP(FFmpegPostProcessor): os.remove(encodeFilename(filename)) os.rename(encodeFilename(temp_filename), encodeFilename(filename)) - elif info['ext'] == 'm4a': + elif info['ext'] in ['m4a', 'mp4']: if not check_executable('AtomicParsley', ['-v']): raise EmbedThumbnailPPError('AtomicParsley was not found. Please install.') @@ -82,6 +82,6 @@ class EmbedThumbnailPP(FFmpegPostProcessor): os.remove(encodeFilename(filename)) os.rename(encodeFilename(temp_filename), encodeFilename(filename)) else: - raise EmbedThumbnailPPError('Only mp3 and m4a are supported for thumbnail embedding for now.') + raise EmbedThumbnailPPError('Only mp3 and m4a/mp4 are supported for thumbnail embedding for now.') return [], info diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py index ed9ed9ed6..52d198fa3 100644 --- a/youtube_dl/utils.py +++ b/youtube_dl/utils.py @@ -1665,6 +1665,7 @@ def mimetype2ext(mt): return { 'x-ms-wmv': 'wmv', 'x-mp4-fragmented': 'mp4', + 'ttml+xml': 'ttml', }.get(res, res) @@ -1848,9 +1849,9 @@ def dfxp2srt(dfxp_data): out = str_or_empty(node.text) for child in node: - if child.tag == _x('ttml:br'): + if child.tag in (_x('ttml:br'), 'br'): out += '\n' + str_or_empty(child.tail) - elif child.tag == _x('ttml:span'): + elif child.tag in (_x('ttml:span'), 'span'): out += str_or_empty(parse_node(child)) else: out += str_or_empty(xml.etree.ElementTree.tostring(child)) @@ -1859,7 +1860,10 @@ def dfxp2srt(dfxp_data): dfxp = xml.etree.ElementTree.fromstring(dfxp_data.encode('utf-8')) out = [] - paras = dfxp.findall(_x('.//ttml:p')) + paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p') + + if not paras: + raise ValueError('Invalid dfxp/TTML subtitle') for para, index in zip(paras, itertools.count(1)): begin_time = parse_dfxp_time_expr(para.attrib['begin']) diff --git a/youtube_dl/version.py b/youtube_dl/version.py index 38f00bc9b..9cf84ff71 100644 --- a/youtube_dl/version.py +++ b/youtube_dl/version.py @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2015.05.15' +__version__ = '2015.06.04.1' |