diff options
Diffstat (limited to 'youtube_dl/extractor')
40 files changed, 818 insertions, 227 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 6bee5b63c..5d2ea39d0 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -241,7 +241,10 @@ from .imdb import ( ImdbIE, ImdbListIE ) -from .imgur import ImgurIE +from .imgur import ( + ImgurIE, + ImgurAlbumIE, +) from .ina import InaIE from .indavideo import ( IndavideoIE, @@ -340,6 +343,7 @@ from .mtv import ( MTVIE, MTVServicesEmbeddedIE, MTVIggyIE, + MTVDEIE, ) from .muenchentv import MuenchenTVIE from .musicplayon import MusicPlayOnIE @@ -454,6 +458,10 @@ from .playfm import PlayFMIE from .playtvak import PlaytvakIE from .playvid import PlayvidIE from .playwire import PlaywireIE +from .pluralsight import ( + PluralsightIE, + PluralsightCourseIE, +) from .podomatic import PodomaticIE from .porn91 import Porn91IE from .pornhd import PornHdIE diff --git a/youtube_dl/extractor/abc.py b/youtube_dl/extractor/abc.py index dc0fb85d6..f9a389f67 100644 --- a/youtube_dl/extractor/abc.py +++ b/youtube_dl/extractor/abc.py @@ -1,16 +1,20 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor +from ..utils import ( + ExtractorError, + js_to_json, + int_or_none, +) class ABCIE(InfoExtractor): IE_NAME = 'abc.net.au' _VALID_URL = r'http://www\.abc\.net\.au/news/[^/]+/[^/]+/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334', 'md5': 'cb3dd03b18455a661071ee1e28344d9f', 'info_dict': { @@ -19,22 +23,47 @@ class ABCIE(InfoExtractor): 'title': 'Australia to help staff Ebola treatment centre in Sierra Leone', 'description': 'md5:809ad29c67a05f54eb41f2a105693a67', }, - } + }, { + 'url': 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326', + 'md5': 'db2a5369238b51f9811ad815b69dc086', + 'info_dict': { + 'id': 'NvqvPeNZsHU', + 'ext': 'mp4', + 'upload_date': '20150816', + 'uploader': 'ABC News (Australia)', + 'description': 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef', + 'uploader_id': 'NewsOnABC', + 'title': 'Marriage Equality: Warren Entsch introduces same sex marriage bill', + }, + 'add_ie': ['Youtube'], + }] def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - urls_info_json = self._search_regex( - r'inlineVideoData\.push\((.*?)\);', webpage, 'video urls', - flags=re.DOTALL) - urls_info = json.loads(urls_info_json.replace('\'', '"')) + mobj = re.search( + r'inline(?P<type>Video|YouTube)Data\.push\((?P<json_data>[^)]+)\);', + webpage) + if mobj is None: + raise ExtractorError('Unable to extract video urls') + + urls_info = self._parse_json( + mobj.group('json_data'), video_id, transform_source=js_to_json) + + if not isinstance(urls_info, list): + urls_info = [urls_info] + + if mobj.group('type') == 'YouTube': + return self.playlist_result([ + self.url_result(url_info['url']) for url_info in urls_info]) + formats = [{ 'url': url_info['url'], - 'width': int(url_info['width']), - 'height': int(url_info['height']), - 'tbr': int(url_info['bitrate']), - 'filesize': int(url_info['filesize']), + 'width': int_or_none(url_info.get('width')), + 'height': int_or_none(url_info.get('height')), + 'tbr': int_or_none(url_info.get('bitrate')), + 'filesize': int_or_none(url_info.get('filesize')), } for url_info in urls_info] self._sort_formats(formats) diff --git a/youtube_dl/extractor/cinemassacre.py b/youtube_dl/extractor/cinemassacre.py index c949a4814..fd1770dac 100644 --- a/youtube_dl/extractor/cinemassacre.py +++ b/youtube_dl/extractor/cinemassacre.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import ExtractorError from .bliptv import BlipTVIE +from .screenwavemedia import ScreenwaveMediaIE class CinemassacreIE(InfoExtractor): @@ -83,10 +84,10 @@ class CinemassacreIE(InfoExtractor): playerdata_url = self._search_regex( [ - r'src="(http://(?:player2\.screenwavemedia\.com|player\.screenwavemedia\.com/play)/[a-zA-Z]+\.php\?[^"]*\bid=.+?)"', - r'<iframe[^>]+src="((?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"', + ScreenwaveMediaIE.EMBED_PATTERN, + r'<iframe[^>]+src="(?P<url>(?:https?:)?//(?:[^.]+\.)?youtube\.com/.+?)"', ], - webpage, 'player data URL', default=None) + webpage, 'player data URL', default=None, group='url') if not playerdata_url: playerdata_url = BlipTVIE._extract_url(webpage) if not playerdata_url: diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index ce2030d28..39cef9c5b 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -510,6 +510,12 @@ class InfoExtractor(object): """Report attempt to log in.""" self.to_screen('Logging in') + @staticmethod + def raise_login_required(msg='This video is only available for registered users'): + raise ExtractorError( + '%s. Use --username and --password or --netrc to provide account credentials.' % msg, + expected=True) + # Methods for following #608 @staticmethod def url_result(url, ie=None, video_id=None, video_title=None): @@ -1151,7 +1157,7 @@ class InfoExtractor(object): } if type_ in SUBTITLES_TYPES: ext = SUBTITLES_TYPES[type_] - lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or subtitles_lang + lang = textstream.get('systemLanguage') or textstream.get('systemLanguageName') or textstream.get('lang') or subtitles_lang subtitles.setdefault(lang, []).append({ 'url': src, 'ext': ext, @@ -1279,6 +1285,23 @@ class InfoExtractor(object): def _get_subtitles(self, *args, **kwargs): raise NotImplementedError("This method must be implemented by subclasses") + @staticmethod + def _merge_subtitle_items(subtitle_list1, subtitle_list2): + """ Merge subtitle items for one language. Items with duplicated URLs + will be dropped. """ + list1_urls = set([item['url'] for item in subtitle_list1]) + ret = list(subtitle_list1) + ret.extend([item for item in subtitle_list2 if item['url'] not in list1_urls]) + return ret + + @classmethod + def _merge_subtitles(cls, subtitle_dict1, subtitle_dict2): + """ Merge two subtitle dictionaries, language by language. """ + ret = dict(subtitle_dict1) + for lang in subtitle_dict2: + ret[lang] = cls._merge_subtitle_items(subtitle_dict1.get(lang, []), subtitle_dict2[lang]) + return ret + def extract_automatic_captions(self, *args, **kwargs): if (self._downloader.params.get('writeautomaticsub', False) or self._downloader.params.get('listsubtitles')): diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 33a033a7f..ce123482e 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -20,9 +20,11 @@ from ..utils import ( ExtractorError, bytes_to_intlist, intlist_to_bytes, + int_or_none, remove_end, unified_strdate, urlencode_postdata, + xpath_text, ) from ..aes import ( aes_cbc_decrypt, @@ -237,7 +239,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text webpage_url = 'http://www.' + mobj.group('url') webpage = self._download_webpage(webpage_url, video_id, 'Downloading webpage') - note_m = self._html_search_regex(r'<div class="showmedia-trailer-notice">(.+?)</div>', webpage, 'trailer-notice', default='') + note_m = self._html_search_regex( + r'<div class="showmedia-trailer-notice">(.+?)</div>', + webpage, 'trailer-notice', default='') if note_m: raise ExtractorError(note_m) @@ -247,6 +251,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text if msg.get('type') == 'error': raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True) + if 'To view this, please log in to verify you are 18 or older.' in webpage: + self.raise_login_required() + video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL) video_title = re.sub(r' {2,}', ' ', video_title) video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='') @@ -281,6 +288,13 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text stream_info = streamdata.find('./{default}preload/stream_info') video_url = stream_info.find('./host').text video_play_path = stream_info.find('./file').text + metadata = stream_info.find('./metadata') + format_info = { + 'format': video_format, + 'format_id': video_format, + 'height': int_or_none(xpath_text(metadata, './height')), + 'width': int_or_none(xpath_text(metadata, './width')), + } if '.fplive.net/' in video_url: video_url = re.sub(r'^rtmpe?://', 'http://', video_url.strip()) @@ -289,19 +303,18 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text netloc='v.lvlt.crcdn.net', path='%s/%s' % (remove_end(parsed_video_url.path, '/'), video_play_path.split(':')[-1]))) if self._is_valid_url(direct_video_url, video_id, video_format): - formats.append({ + format_info.update({ 'url': direct_video_url, - 'format_id': video_format, }) + formats.append(format_info) continue - formats.append({ + format_info.update({ 'url': video_url, 'play_path': video_play_path, 'ext': 'flv', - 'format': video_format, - 'format_id': video_format, }) + formats.append(format_info) subtitles = self.extract_subtitles(video_id, webpage) diff --git a/youtube_dl/extractor/dumpert.py b/youtube_dl/extractor/dumpert.py index 999fb5620..1f00386fe 100644 --- a/youtube_dl/extractor/dumpert.py +++ b/youtube_dl/extractor/dumpert.py @@ -9,8 +9,8 @@ from ..utils import qualities class DumpertIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/mediabase/(?P<id>[0-9]+/[0-9a-zA-Z]+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/(?:mediabase|embed)/(?P<id>[0-9]+/[0-9a-zA-Z]+)' + _TESTS = [{ 'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/', 'md5': '1b9318d7d5054e7dcb9dc7654f21d643', 'info_dict': { @@ -20,11 +20,15 @@ class DumpertIE(InfoExtractor): 'description': 'Niet schrikken hoor', 'thumbnail': 're:^https?://.*\.jpg$', } - } + }, { + 'url': 'http://www.dumpert.nl/embed/6675421/dc440fe7/', + 'only_matching': True, + }] def _real_extract(self, url): video_id = self._match_id(url) + url = 'https://www.dumpert.nl/mediabase/' + video_id req = compat_urllib_request.Request(url) req.add_header('Cookie', 'nsfw=1; cpc=10') webpage = self._download_webpage(req, video_id) diff --git a/youtube_dl/extractor/eroprofile.py b/youtube_dl/extractor/eroprofile.py index 316033cf1..7fcd0151d 100644 --- a/youtube_dl/extractor/eroprofile.py +++ b/youtube_dl/extractor/eroprofile.py @@ -71,8 +71,7 @@ class EroProfileIE(InfoExtractor): m = re.search(r'You must be logged in to view this video\.', webpage) if m: - raise ExtractorError( - 'This video requires login. Please specify a username and password and try again.', expected=True) + self.raise_login_required('This video requires login') video_id = self._search_regex( [r"glbUpdViews\s*\('\d*','(\d+)'", r'p/report/video/(\d+)'], diff --git a/youtube_dl/extractor/fc2.py b/youtube_dl/extractor/fc2.py index e4f7195a8..5c1137e94 100644 --- a/youtube_dl/extractor/fc2.py +++ b/youtube_dl/extractor/fc2.py @@ -15,7 +15,7 @@ from ..utils import ( class FC2IE(InfoExtractor): - _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)?content/(?P<id>[^/]+)' + _VALID_URL = r'^http://video\.fc2\.com/(?:[^/]+/)*content/(?P<id>[^/]+)' IE_NAME = 'fc2' _NETRC_MACHINE = 'fc2' _TESTS = [{ @@ -37,6 +37,9 @@ class FC2IE(InfoExtractor): 'password': '(snip)', 'skip': 'requires actual password' } + }, { + 'url': 'http://video.fc2.com/en/a/content/20130926eZpARwsF', + 'only_matching': True, }] def _login(self): @@ -80,7 +83,7 @@ class FC2IE(InfoExtractor): title = self._og_search_title(webpage) thumbnail = self._og_search_thumbnail(webpage) - refer = url.replace('/content/', '/a/content/') + refer = url.replace('/content/', '/a/content/') if '/a/content/' not in url else url mimi = hashlib.md5((video_id + '_gGddgPfeaf_gzyr').encode('utf-8')).hexdigest() diff --git a/youtube_dl/extractor/folketinget.py b/youtube_dl/extractor/folketinget.py index 0fb29de75..75399fa7d 100644 --- a/youtube_dl/extractor/folketinget.py +++ b/youtube_dl/extractor/folketinget.py @@ -30,6 +30,10 @@ class FolketingetIE(InfoExtractor): 'upload_date': '20141120', 'duration': 3960, }, + 'params': { + # rtmp download + 'skip_download': True, + }, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/foxnews.py b/youtube_dl/extractor/foxnews.py index 917f76b1e..3a4a59135 100644 --- a/youtube_dl/extractor/foxnews.py +++ b/youtube_dl/extractor/foxnews.py @@ -1,5 +1,7 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor from ..utils import ( parse_iso8601, @@ -8,7 +10,8 @@ from ..utils import ( class FoxNewsIE(InfoExtractor): - _VALID_URL = r'https?://video\.foxnews\.com/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)' + IE_DESC = 'Fox News and Fox Business Video' + _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)' _TESTS = [ { 'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips', @@ -42,13 +45,19 @@ class FoxNewsIE(InfoExtractor): 'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com', 'only_matching': True, }, + { + 'url': 'http://video.foxbusiness.com/v/4442309889001', + 'only_matching': True, + }, ] def _real_extract(self, url): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + host = mobj.group('host') video = self._download_json( - 'http://video.foxnews.com/v/feed/video/%s.js?template=fox' % video_id, video_id) + 'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id), video_id) item = video['channel']['item'] title = item['title'] diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py index 75723c00d..129984a5f 100644 --- a/youtube_dl/extractor/francetv.py +++ b/youtube_dl/extractor/francetv.py @@ -78,9 +78,14 @@ class FranceTVBaseInfoExtractor(InfoExtractor): }) self._sort_formats(formats) + title = info['titre'] + subtitle = info.get('sous_titre') + if subtitle: + title += ' - %s' % subtitle + return { 'id': video_id, - 'title': info['titre'], + 'title': title, 'description': clean_html(info['synopsis']), 'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']), 'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']), @@ -214,15 +219,15 @@ class FranceTVIE(FranceTVBaseInfoExtractor): }, # france5 { - 'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968', - 'md5': '78f0f4064f9074438e660785bbf2c5d9', + 'url': 'http://www.france5.fr/emissions/c-a-dire/videos/quels_sont_les_enjeux_de_cette_rentree_politique__31-08-2015_908948?onglet=tous&page=1', + 'md5': 'f6c577df3806e26471b3d21631241fd0', 'info_dict': { - 'id': '108961659', + 'id': '123327454', 'ext': 'flv', - 'title': 'C à dire ?!', - 'description': 'md5:1a4aeab476eb657bf57c4ff122129f81', - 'upload_date': '20140915', - 'timestamp': 1410795000, + 'title': 'C à dire ?! - Quels sont les enjeux de cette rentrée politique ?', + 'description': 'md5:4a0d5cb5dce89d353522a84462bae5a4', + 'upload_date': '20150831', + 'timestamp': 1441035120, }, }, # franceo diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 376feecae..953ec32c3 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -48,6 +48,7 @@ from .vimeo import VimeoIE from .dailymotion import DailymotionCloudIE from .onionstudios import OnionStudiosIE from .snagfilms import SnagFilmsEmbedIE +from .screenwavemedia import ScreenwaveMediaIE class GenericIE(InfoExtractor): @@ -1001,6 +1002,16 @@ class GenericIE(InfoExtractor): 'description': 'New experience with Acrobat DC', 'duration': 248.667, }, + }, + # ScreenwaveMedia embed + { + 'url': 'http://www.thecinemasnob.com/the-cinema-snob/a-nightmare-on-elm-street-2-freddys-revenge1', + 'md5': '24ace5baba0d35d55c6810b51f34e9e0', + 'info_dict': { + 'id': 'cinemasnob-55d26273809dd', + 'ext': 'mp4', + 'title': 'cinemasnob', + }, } ] @@ -1718,6 +1729,11 @@ class GenericIE(InfoExtractor): if snagfilms_url: return self.url_result(snagfilms_url) + # Look for ScreenwaveMedia embeds + mobj = re.search(ScreenwaveMediaIE.EMBED_PATTERN, webpage) + if mobj is not None: + return self.url_result(unescapeHTML(mobj.group('url')), 'ScreenwaveMedia') + # Look for AdobeTVVideo embeds mobj = re.search( r'<iframe[^>]+src=[\'"]((?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]', diff --git a/youtube_dl/extractor/globo.py b/youtube_dl/extractor/globo.py index 8a95793ca..33d6432a6 100644 --- a/youtube_dl/extractor/globo.py +++ b/youtube_dl/extractor/globo.py @@ -13,6 +13,7 @@ from ..compat import ( from ..utils import ( ExtractorError, float_or_none, + int_or_none, ) @@ -359,13 +360,8 @@ class GloboIE(InfoExtractor): self._API_URL_TEMPLATE % video_id, video_id)['videos'][0] title = video['title'] - duration = float_or_none(video['duration'], 1000) - like_count = video['likes'] - uploader = video['channel'] - uploader_id = video['channel_id'] formats = [] - for resource in video['resources']: resource_id = resource.get('_id') if not resource_id: @@ -407,6 +403,11 @@ class GloboIE(InfoExtractor): self._sort_formats(formats) + duration = float_or_none(video.get('duration'), 1000) + like_count = int_or_none(video.get('likes')) + uploader = video.get('channel') + uploader_id = video.get('channel_id') + return { 'id': video_id, 'title': title, diff --git a/youtube_dl/extractor/imgur.py b/youtube_dl/extractor/imgur.py index d692ea79a..70c8ca64e 100644 --- a/youtube_dl/extractor/imgur.py +++ b/youtube_dl/extractor/imgur.py @@ -13,7 +13,7 @@ from ..utils import ( class ImgurIE(InfoExtractor): - _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?P<id>[a-zA-Z0-9]+)' + _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?!gallery)(?P<id>[a-zA-Z0-9]+)' _TESTS = [{ 'url': 'https://i.imgur.com/A61SaA1.gifv', @@ -97,3 +97,28 @@ class ImgurIE(InfoExtractor): 'description': self._og_search_description(webpage), 'title': self._og_search_title(webpage), } + + +class ImgurAlbumIE(InfoExtractor): + _VALID_URL = r'https?://(?:i\.)?imgur\.com/gallery/(?P<id>[a-zA-Z0-9]+)' + + _TEST = { + 'url': 'http://imgur.com/gallery/Q95ko', + 'info_dict': { + 'id': 'Q95ko', + }, + 'playlist_count': 25, + } + + def _real_extract(self, url): + album_id = self._match_id(url) + + album_images = self._download_json( + 'http://imgur.com/gallery/%s/album_images/hit.json?all=true' % album_id, + album_id)['data']['images'] + + entries = [ + self.url_result('http://imgur.com/%s' % image['hash']) + for image in album_images if image.get('hash')] + + return self.playlist_result(entries, album_id) diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py index d28730492..3dca0e566 100644 --- a/youtube_dl/extractor/kaltura.py +++ b/youtube_dl/extractor/kaltura.py @@ -13,12 +13,24 @@ from ..utils import ( class KalturaIE(InfoExtractor): _VALID_URL = r'''(?x) - (?:kaltura:| - https?://(:?(?:www|cdnapisec)\.)?kaltura\.com/index\.php/kwidget/(?:[^/]+/)*?wid/_ - )(?P<partner_id>\d+) - (?::| - /(?:[^/]+/)*?entry_id/ - )(?P<id>[0-9a-z_]+)''' + (?: + kaltura:(?P<partner_id_s>\d+):(?P<id_s>[0-9a-z_]+)| + https?:// + (:?(?:www|cdnapisec)\.)?kaltura\.com/ + (?: + (?: + # flash player + index\.php/kwidget/ + (?:[^/]+/)*?wid/_(?P<partner_id>\d+)/ + (?:[^/]+/)*?entry_id/(?P<id>[0-9a-z_]+)| + # html5 player + html5/html5lib/ + (?:[^/]+/)*?entry_id/(?P<id_html5>[0-9a-z_]+) + .*\?.*\bwid=_(?P<partner_id_html5>\d+) + ) + ) + ) + ''' _API_BASE = 'http://cdnapi.kaltura.com/api_v3/index.php?' _TESTS = [ { @@ -43,6 +55,10 @@ class KalturaIE(InfoExtractor): 'url': 'https://cdnapisec.kaltura.com/index.php/kwidget/wid/_557781/uiconf_id/22845202/entry_id/1_plr1syf3', 'only_matching': True, }, + { + 'url': 'https://cdnapisec.kaltura.com/html5/html5lib/v2.30.2/mwEmbedFrame.php/p/1337/uiconf_id/20540612/entry_id/1_sf5ovm7u?wid=_243342', + 'only_matching': True, + } ] def _kaltura_api_call(self, video_id, actions, *args, **kwargs): @@ -105,9 +121,9 @@ class KalturaIE(InfoExtractor): video_id, actions, note='Downloading video info JSON') def _real_extract(self, url): - video_id = self._match_id(url) mobj = re.match(self._VALID_URL, url) - partner_id, entry_id = mobj.group('partner_id'), mobj.group('id') + partner_id = mobj.group('partner_id_s') or mobj.group('partner_id') or mobj.group('partner_id_html5') + entry_id = mobj.group('id_s') or mobj.group('id') or mobj.group('id_html5') info, source_data = self._get_video_info(entry_id, partner_id) @@ -126,7 +142,7 @@ class KalturaIE(InfoExtractor): self._sort_formats(formats) return { - 'id': video_id, + 'id': entry_id, 'title': info['name'], 'formats': formats, 'description': info.get('description'), diff --git a/youtube_dl/extractor/kontrtube.py b/youtube_dl/extractor/kontrtube.py index 720bc939b..a59c529f4 100644 --- a/youtube_dl/extractor/kontrtube.py +++ b/youtube_dl/extractor/kontrtube.py @@ -4,7 +4,10 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + parse_duration, +) class KontrTubeIE(InfoExtractor): @@ -34,33 +37,28 @@ class KontrTubeIE(InfoExtractor): webpage = self._download_webpage( url, display_id, 'Downloading page') - video_url = self._html_search_regex( + video_url = self._search_regex( r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL') - thumbnail = self._html_search_regex( - r"preview_url\s*:\s*'(.+?)/?',", webpage, 'video thumbnail', fatal=False) + thumbnail = self._search_regex( + r"preview_url\s*:\s*'(.+?)/?',", webpage, 'thumbnail', fatal=False) title = self._html_search_regex( - r'<title>(.+?)</title>', webpage, 'video title') + r'(?s)<h2>(.+?)</h2>', webpage, 'title') description = self._html_search_meta( - 'description', webpage, 'video description') + 'description', webpage, 'description') - mobj = re.search( - r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', - webpage) - duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None + duration = self._search_regex( + r'Длительность: <em>([^<]+)</em>', webpage, 'duration', fatal=False) + if duration: + duration = parse_duration(duration.replace('мин', 'min').replace('сек', 'sec')) - view_count = self._html_search_regex( - r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', + view_count = self._search_regex( + r'Просмотров: <em>([^<]+)</em>', webpage, 'view count', fatal=False) + if view_count: + view_count = int_or_none(view_count.replace(' ', '')) - comment_count = None - comment_str = self._html_search_regex( - r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count', fatal=False) - if comment_str.startswith('комментариев нет'): - comment_count = 0 - else: - mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str) - if mobj: - comment_count = mobj.group('total') + comment_count = int_or_none(self._search_regex( + r'Комментарии \((\d+)\)<', webpage, ' comment count', fatal=False)) return { 'id': video_id, diff --git a/youtube_dl/extractor/krasview.py b/youtube_dl/extractor/krasview.py index 96f95979a..0ae8ebd68 100644 --- a/youtube_dl/extractor/krasview.py +++ b/youtube_dl/extractor/krasview.py @@ -25,6 +25,9 @@ class KrasViewIE(InfoExtractor): 'duration': 27, 'thumbnail': 're:^https?://.*\.jpg', }, + 'params': { + 'skip_download': 'Not accessible from Travis CI server', + }, } def _real_extract(self, url): diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 5b9157ed4..378117270 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -118,9 +118,7 @@ class LyndaIE(LyndaBaseIE): 'lynda returned error: %s' % video_json['Message'], expected=True) if video_json['HasAccess'] is False: - raise ExtractorError( - 'Video %s is only available for members. ' - % video_id + self._ACCOUNT_CREDENTIALS_HINT, expected=True) + self.raise_login_required('Video %s is only available for members' % video_id) video_id = compat_str(video_json['ID']) duration = video_json['DurationInSeconds'] diff --git a/youtube_dl/extractor/mailru.py b/youtube_dl/extractor/mailru.py index 54a14cb94..ab1300185 100644 --- a/youtube_dl/extractor/mailru.py +++ b/youtube_dl/extractor/mailru.py @@ -25,6 +25,7 @@ class MailRuIE(InfoExtractor): 'uploader_id': 'sonypicturesrus@mail.ru', 'duration': 184, }, + 'skip': 'Not accessible from Travis CI server', }, { 'url': 'http://my.mail.ru/corp/hitech/video/news_hi-tech_mail_ru/1263.html', @@ -39,6 +40,7 @@ class MailRuIE(InfoExtractor): 'uploader_id': 'hitech@corp.mail.ru', 'duration': 245, }, + 'skip': 'Not accessible from Travis CI server', }, ] diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index b48fac5e3..a597714e9 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -67,7 +67,7 @@ class MTVServicesInfoExtractor(InfoExtractor): return [{'url': url, 'ext': 'mp4'}] def _extract_video_formats(self, mdoc, mtvn_id): - if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4)$', mdoc.find('.//src').text) is not None: + if re.match(r'.*/(error_country_block\.swf|geoblock\.mp4|copyright_error\.flv(?:\?geo\b.+?)?)$', mdoc.find('.//src').text) is not None: if mtvn_id is not None and self._MOBILE_TEMPLATE is not None: self.to_screen('The normal version is not available from your ' 'country, trying with the mobile version') @@ -114,7 +114,8 @@ class MTVServicesInfoExtractor(InfoExtractor): # Remove the templates, like &device={device} mediagen_url = re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', mediagen_url) if 'acceptMethods' not in mediagen_url: - mediagen_url += '&acceptMethods=fms' + mediagen_url += '&' if '?' in mediagen_url else '?' + mediagen_url += 'acceptMethods=fms' mediagen_doc = self._download_xml(mediagen_url, video_id, 'Downloading video urls') @@ -141,7 +142,7 @@ class MTVServicesInfoExtractor(InfoExtractor): if title_el is None: title_el = itemdoc.find('.//{http://search.yahoo.com/mrss/}title') if title_el is None: - title_el = itemdoc.find('.//title') + title_el = itemdoc.find('.//title') or itemdoc.find('./title') if title_el.text is None: title_el = None @@ -174,8 +175,11 @@ class MTVServicesInfoExtractor(InfoExtractor): if self._LANG: info_url += 'lang=%s&' % self._LANG info_url += data + return self._get_videos_info_from_url(info_url, video_id) + + def _get_videos_info_from_url(self, url, video_id): idoc = self._download_xml( - info_url, video_id, + url, video_id, 'Downloading info', transform_source=fix_xml_ampersands) return self.playlist_result( [self._get_video_info(item) for item in idoc.findall('.//item')]) @@ -288,3 +292,65 @@ class MTVIggyIE(MTVServicesInfoExtractor): } } _FEED_URL = 'http://all.mtvworldverticals.com/feed-xml/' + + +class MTVDEIE(MTVServicesInfoExtractor): + IE_NAME = 'mtv.de' + _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$' + _TESTS = [{ + 'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum', + 'info_dict': { + 'id': 'music_video-a50bc5f0b3aa4b3190aa', + 'ext': 'mp4', + 'title': 'MusicVideo_cro-traum', + 'description': 'Cro - Traum', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97) + 'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen', + 'info_dict': { + 'id': 'local_playlist-f5ae778b9832cc837189', + 'ext': 'mp4', + 'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }, { + # single video in pagePlaylist with different id + 'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3', + 'info_dict': { + 'id': 'local_playlist-4e760566473c4c8c5344', + 'ext': 'mp4', + 'title': 'Article_mtv-movies-spotlight-pixels-teil-3_short-clips_part1', + 'description': 'MTV Movies Supercut', + }, + 'params': { + # rtmp download + 'skip_download': True, + }, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + playlist = self._parse_json( + self._search_regex( + r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'), + video_id) + + # news pages contain single video in playlist with different id + if len(playlist) == 1: + return self._get_videos_info_from_url(playlist[0]['mrss'], video_id) + + for item in playlist: + item_id = item.get('id') + if item_id and compat_str(item_id) == video_id: + return self._get_videos_info_from_url(item['mrss'], video_id) diff --git a/youtube_dl/extractor/nowtv.py b/youtube_dl/extractor/nowtv.py index 66c627bec..c8257719f 100644 --- a/youtube_dl/extractor/nowtv.py +++ b/youtube_dl/extractor/nowtv.py @@ -130,10 +130,16 @@ class NowTVIE(InfoExtractor): }, { 'url': 'http://www.nowtv.at/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit/preview?return=/rtl/bauer-sucht-frau/die-neuen-bauern-und-eine-hochzeit', 'only_matching': True, + }, { + 'url': 'http://www.nowtv.de/rtl2/echtzeit/list/aktuell/schnelles-geld-am-ende-der-welt/player', + 'only_matching': True, }] def _real_extract(self, url): display_id = self._match_id(url) + display_id_split = display_id.split('/') + if len(display_id) > 2: + display_id = '/'.join((display_id_split[0], display_id_split[-1])) info = self._download_json( 'https://api.nowtv.de/v3/movies/%s?fields=id,title,free,geoblocked,articleLong,articleShort,broadcastStartDate,seoUrl,duration,format,files' % display_id, diff --git a/youtube_dl/extractor/nowvideo.py b/youtube_dl/extractor/nowvideo.py index dec09cdfe..17baa9679 100644 --- a/youtube_dl/extractor/nowvideo.py +++ b/youtube_dl/extractor/nowvideo.py @@ -7,7 +7,7 @@ class NowVideoIE(NovaMovIE): IE_NAME = 'nowvideo' IE_DESC = 'NowVideo' - _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|sx|eu|at|ag|co|li)'} + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:ch|ec|sx|eu|at|ag|co|li)'} _HOST = 'www.nowvideo.ch' diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py index 003d27de7..66520c2c5 100644 --- a/youtube_dl/extractor/odnoklassniki.py +++ b/youtube_dl/extractor/odnoklassniki.py @@ -12,7 +12,7 @@ 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?://(?:www\.)?(?:odnoklassniki|ok)\.ru/(?:video|web-api/video/moviePlayer)/(?P<id>[\d-]+)' _TESTS = [{ # metadata in JSON 'url': 'http://ok.ru/video/20079905452', @@ -44,8 +44,26 @@ class OdnoklassnikiIE(InfoExtractor): 'age_limit': 0, }, }, { + # YouTube embed (metadataUrl, provider == USER_YOUTUBE) + 'url': 'http://ok.ru/video/64211978996595-1', + 'md5': '5d7475d428845cd2e13bae6f1a992278', + 'info_dict': { + 'id': '64211978996595-1', + 'ext': 'mp4', + 'title': 'Космическая среда от 26 августа 2015', + 'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0', + 'duration': 440, + 'upload_date': '20150826', + 'uploader_id': '750099571', + 'uploader': 'Алина П', + 'age_limit': 0, + }, + }, { 'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452', 'only_matching': True, + }, { + 'url': 'http://www.ok.ru/video/20648036891', + 'only_matching': True, }] def _real_extract(self, url): @@ -56,7 +74,8 @@ class OdnoklassnikiIE(InfoExtractor): player = self._parse_json( unescapeHTML(self._search_regex( - r'data-attributes="([^"]+)"', webpage, 'player')), + r'data-options=(?P<quote>["\'])(?P<player>{.+?%s.+?})(?P=quote)' % video_id, + webpage, 'player', group='player')), video_id) flashvars = player['flashvars'] @@ -89,16 +108,7 @@ class OdnoklassnikiIE(InfoExtractor): like_count = int_or_none(metadata.get('likeCount')) - quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd')) - - formats = [{ - 'url': f['url'], - 'ext': 'mp4', - 'format_id': f['name'], - 'quality': quality(f['name']), - } for f in metadata['videos']] - - return { + info = { 'id': video_id, 'title': title, 'thumbnail': thumbnail, @@ -108,5 +118,24 @@ class OdnoklassnikiIE(InfoExtractor): 'uploader_id': uploader_id, 'like_count': like_count, 'age_limit': age_limit, - 'formats': formats, } + + if metadata.get('provider') == 'USER_YOUTUBE': + info.update({ + '_type': 'url_transparent', + 'url': movie['contentId'], + }) + return info + + quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd')) + + formats = [{ + 'url': f['url'], + 'ext': 'mp4', + 'format_id': f['name'], + 'quality': quality(f['name']), + } for f in metadata['videos']] + self._sort_formats(formats) + + info['formats'] = formats + return info diff --git a/youtube_dl/extractor/pluralsight.py b/youtube_dl/extractor/pluralsight.py new file mode 100644 index 000000000..fd32836cc --- /dev/null +++ b/youtube_dl/extractor/pluralsight.py @@ -0,0 +1,207 @@ +from __future__ import unicode_literals + +import re +import json + +from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse, + compat_urllib_request, + compat_urlparse, +) +from ..utils import ( + ExtractorError, + int_or_none, + parse_duration, +) + + +class PluralsightIE(InfoExtractor): + IE_NAME = 'pluralsight' + _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/training/player\?author=(?P<author>[^&]+)&name=(?P<name>[^&]+)(?:&mode=live)?&clip=(?P<clip>\d+)&course=(?P<course>[^&]+)' + _LOGIN_URL = 'https://www.pluralsight.com/id/' + _NETRC_MACHINE = 'pluralsight' + + _TEST = { + 'url': 'http://www.pluralsight.com/training/player?author=mike-mckeown&name=hosting-sql-server-windows-azure-iaas-m7-mgmt&mode=live&clip=3&course=hosting-sql-server-windows-azure-iaas', + 'md5': '4d458cf5cf4c593788672419a8dd4cf8', + 'info_dict': { + 'id': 'hosting-sql-server-windows-azure-iaas-m7-mgmt-04', + 'ext': 'mp4', + 'title': 'Management of SQL Server - Demo Monitoring', + 'duration': 338, + }, + 'skip': 'Requires pluralsight account credentials', + } + + def _real_initialize(self): + self._login() + + def _login(self): + (username, password) = self._get_login_info() + if username is None: + self.raise_login_required('Pluralsight account is required') + + login_page = self._download_webpage( + self._LOGIN_URL, None, 'Downloading login page') + + login_form = self._hidden_inputs(login_page) + + login_form.update({ + 'Username': username.encode('utf-8'), + 'Password': password.encode('utf-8'), + }) + + post_url = self._search_regex( + r'<form[^>]+action=(["\'])(?P<url>.+?)\1', login_page, + 'post url', default=self._LOGIN_URL, group='url') + + if not post_url.startswith('http'): + post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url) + + request = compat_urllib_request.Request( + post_url, compat_urllib_parse.urlencode(login_form).encode('utf-8')) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + + response = self._download_webpage( + request, None, 'Logging in as %s' % username) + + error = self._search_regex( + r'<span[^>]+class="field-validation-error"[^>]*>([^<]+)</span>', + response, 'error message', default=None) + if error: + raise ExtractorError('Unable to login: %s' % error, expected=True) + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + author = mobj.group('author') + name = mobj.group('name') + clip_id = mobj.group('clip') + course = mobj.group('course') + + display_id = '%s-%s' % (name, clip_id) + + webpage = self._download_webpage(url, display_id) + + collection = self._parse_json( + self._search_regex( + r'moduleCollection\s*:\s*new\s+ModuleCollection\((\[.+?\])\s*,\s*\$rootScope\)', + webpage, 'modules'), + display_id) + + module, clip = None, None + + for module_ in collection: + if module_.get('moduleName') == name: + module = module_ + for clip_ in module_.get('clips', []): + clip_index = clip_.get('clipIndex') + if clip_index is None: + continue + if compat_str(clip_index) == clip_id: + clip = clip_ + break + + if not clip: + raise ExtractorError('Unable to resolve clip') + + QUALITIES = { + 'low': {'width': 640, 'height': 480}, + 'medium': {'width': 848, 'height': 640}, + 'high': {'width': 1024, 'height': 768}, + } + + ALLOWED_QUALITIES = ( + ('webm', ('high',)), + ('mp4', ('low', 'medium', 'high',)), + ) + + formats = [] + for ext, qualities in ALLOWED_QUALITIES: + for quality in qualities: + f = QUALITIES[quality].copy() + clip_post = { + 'a': author, + 'cap': 'false', + 'cn': clip_id, + 'course': course, + 'lc': 'en', + 'm': name, + 'mt': ext, + 'q': '%dx%d' % (f['width'], f['height']), + } + request = compat_urllib_request.Request( + 'http://www.pluralsight.com/training/Player/ViewClip', + json.dumps(clip_post).encode('utf-8')) + request.add_header('Content-Type', 'application/json;charset=utf-8') + format_id = '%s-%s' % (ext, quality) + clip_url = self._download_webpage( + request, display_id, 'Downloading %s URL' % format_id, fatal=False) + if not clip_url: + continue + f.update({ + 'url': clip_url, + 'ext': ext, + 'format_id': format_id, + }) + formats.append(f) + self._sort_formats(formats) + + # TODO: captions + # http://www.pluralsight.com/training/Player/ViewClip + cap = true + # or + # http://www.pluralsight.com/training/Player/Captions + # { a = author, cn = clip_id, lc = end, m = name } + + return { + 'id': clip['clipName'], + 'title': '%s - %s' % (module['title'], clip['title']), + 'duration': int_or_none(clip.get('duration')) or parse_duration(clip.get('formattedDuration')), + 'creator': author, + 'formats': formats + } + + +class PluralsightCourseIE(InfoExtractor): + IE_NAME = 'pluralsight:course' + _VALID_URL = r'https?://(?:www\.)?pluralsight\.com/courses/(?P<id>[^/]+)' + _TEST = { + # Free course from Pluralsight Starter Subscription for Microsoft TechNet + # https://offers.pluralsight.com/technet?loc=zTS3z&prod=zOTprodz&tech=zOttechz&prog=zOTprogz&type=zSOz&media=zOTmediaz&country=zUSz + 'url': 'http://www.pluralsight.com/courses/hosting-sql-server-windows-azure-iaas', + 'info_dict': { + 'id': 'hosting-sql-server-windows-azure-iaas', + 'title': 'Hosting SQL Server in Microsoft Azure IaaS Fundamentals', + 'description': 'md5:61b37e60f21c4b2f91dc621a977d0986', + }, + 'playlist_count': 31, + } + + def _real_extract(self, url): + course_id = self._match_id(url) + + # TODO: PSM cookie + + course = self._download_json( + 'http://www.pluralsight.com/data/course/%s' % course_id, + course_id, 'Downloading course JSON') + + title = course['title'] + description = course.get('description') or course.get('shortDescription') + + course_data = self._download_json( + 'http://www.pluralsight.com/data/course/content/%s' % course_id, + course_id, 'Downloading course data JSON') + + entries = [] + for module in course_data: + for clip in module.get('clips', []): + player_parameters = clip.get('playerParameters') + if not player_parameters: + continue + entries.append(self.url_result( + 'http://www.pluralsight.com/training/player?%s' % player_parameters, + 'Pluralsight')) + + return self.playlist_result(entries, course_id, title, description) diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py index 72cd80498..25f7faf76 100644 --- a/youtube_dl/extractor/rtl2.py +++ b/youtube_dl/extractor/rtl2.py @@ -1,6 +1,7 @@ # encoding: utf-8 from __future__ import unicode_literals +import re from .common import InfoExtractor @@ -8,22 +9,28 @@ class RTL2IE(InfoExtractor): _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))' _TESTS = [{ 'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0', - 'md5': 'bfcc179030535b08dc2b36b469b5adc7', 'info_dict': { 'id': 'folge-203-0', 'ext': 'f4v', 'title': 'GRIP sucht den Sommerkönig', 'description': 'Matthias, Det und Helge treten gegeneinander an.' }, + 'params': { + # rtmp download + 'skip_download': True, + }, }, { 'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/', - 'md5': 'ffcd517d2805b57ce11a58a2980c2b02', 'info_dict': { 'id': '21040-anna-erwischt-alex', 'ext': 'mp4', 'title': 'Anna erwischt Alex!', 'description': 'Anna ist Alex\' Tochter bei Köln 50667.' }, + 'params': { + # rtmp download + 'skip_download': True, + }, }] def _real_extract(self, url): @@ -34,12 +41,18 @@ class RTL2IE(InfoExtractor): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - vico_id = self._html_search_regex( - r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id') - vivi_id = self._html_search_regex( - r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id') + mobj = re.search( + r'<div[^>]+data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"', + webpage) + if mobj: + vico_id = mobj.group('vico_id') + vivi_id = mobj.group('vivi_id') + else: + vico_id = self._html_search_regex( + r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id') + vivi_id = self._html_search_regex( + r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id') info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id - webpage = self._download_webpage(info_url, '') info = self._download_json(info_url, video_id) video_info = info['video'] diff --git a/youtube_dl/extractor/rtp.py b/youtube_dl/extractor/rtp.py index ecf4939cd..82b323cdd 100644 --- a/youtube_dl/extractor/rtp.py +++ b/youtube_dl/extractor/rtp.py @@ -18,6 +18,10 @@ class RTPIE(InfoExtractor): 'description': 'As paixões musicais de António Cartaxo e António Macedo', 'thumbnail': 're:^https?://.*\.jpg', }, + 'params': { + # rtmp download + 'skip_download': True, + }, }, { 'url': 'http://www.rtp.pt/play/p831/a-quimica-das-coisas', 'only_matching': True, diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py index 82cd98ac7..5b97d33ca 100644 --- a/youtube_dl/extractor/rtve.py +++ b/youtube_dl/extractor/rtve.py @@ -6,7 +6,7 @@ import re import time from .common import InfoExtractor -from ..compat import compat_urlparse +from ..compat import compat_urllib_request, compat_urlparse from ..utils import ( ExtractorError, float_or_none, @@ -102,7 +102,9 @@ class RTVEALaCartaIE(InfoExtractor): if info['state'] == 'DESPU': raise ExtractorError('The video is no longer available', expected=True) png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id) - png = self._download_webpage(png_url, video_id, 'Downloading url information') + png_request = compat_urllib_request.Request(png_url) + png_request.add_header('Referer', url) + png = self._download_webpage(png_request, video_id, 'Downloading url information') video_url = _decrypt_url(png) if not video_url.endswith('.f4m'): auth_url = video_url.replace( diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py index 4e22628d0..c67ad25ce 100644 --- a/youtube_dl/extractor/ruutu.py +++ b/youtube_dl/extractor/ruutu.py @@ -6,19 +6,19 @@ from ..compat import compat_urllib_parse_urlparse from ..utils import ( determine_ext, int_or_none, + xpath_attr, xpath_text, ) class RuutuIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?ruutu\.fi/ohjelmat/(?:[^/?#]+/)*(?P<id>[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?ruutu\.fi/video/(?P<id>\d+)' _TESTS = [ { - 'url': 'http://www.ruutu.fi/ohjelmat/oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi', + 'url': 'http://www.ruutu.fi/video/2058907', 'md5': 'ab2093f39be1ca8581963451b3c0234f', 'info_dict': { 'id': '2058907', - 'display_id': 'oletko-aina-halunnut-tietaa-mita-tapahtuu-vain-hetki-ennen-lahetysta-nyt-se-selvisi', 'ext': 'mp4', 'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!', 'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6', @@ -28,14 +28,13 @@ class RuutuIE(InfoExtractor): }, }, { - 'url': 'http://www.ruutu.fi/ohjelmat/superpesis/superpesis-katso-koko-kausi-ruudussa', + 'url': 'http://www.ruutu.fi/video/2057306', 'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9', 'info_dict': { 'id': '2057306', - 'display_id': 'superpesis-katso-koko-kausi-ruudussa', 'ext': 'mp4', 'title': 'Superpesis: katso koko kausi Ruudussa', - 'description': 'md5:44c44a99fdbe5b380ab74ebd75f0af77', + 'description': 'md5:da2736052fef3b2bd5e0005e63c25eac', 'thumbnail': 're:^https?://.*\.jpg$', 'duration': 40, 'age_limit': 0, @@ -44,29 +43,10 @@ class RuutuIE(InfoExtractor): ] def _real_extract(self, url): - display_id = self._match_id(url) + video_id = self._match_id(url) - webpage = self._download_webpage(url, display_id) - - video_id = self._search_regex( - r'data-media-id="(\d+)"', webpage, 'media id') - - video_xml_url = None - - media_data = self._search_regex( - r'jQuery\.extend\([^,]+,\s*(.+?)\);', webpage, - 'media data', default=None) - if media_data: - media_json = self._parse_json(media_data, display_id, fatal=False) - if media_json: - xml_url = media_json.get('ruutuplayer', {}).get('xmlUrl') - if xml_url: - video_xml_url = xml_url.replace('{ID}', video_id) - - if not video_xml_url: - video_xml_url = 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id - - video_xml = self._download_xml(video_xml_url, video_id) + video_xml = self._download_xml( + 'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id) formats = [] processed_urls = [] @@ -109,10 +89,9 @@ class RuutuIE(InfoExtractor): return { 'id': video_id, - 'display_id': display_id, - 'title': self._og_search_title(webpage), - 'description': self._og_search_description(webpage), - 'thumbnail': self._og_search_thumbnail(webpage), + 'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True), + 'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'), + 'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'), 'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')), 'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')), 'formats': formats, diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py index f3c80708c..a602af692 100644 --- a/youtube_dl/extractor/safari.py +++ b/youtube_dl/extractor/safari.py @@ -20,7 +20,6 @@ from ..utils import ( class SafariBaseIE(InfoExtractor): _LOGIN_URL = 'https://www.safaribooksonline.com/accounts/login/' _SUCCESSFUL_LOGIN_REGEX = r'<a href="/accounts/logout/"[^>]*>Sign Out</a>' - _ACCOUNT_CREDENTIALS_HINT = 'Use --username and --password options to supply credentials for safaribooksonline.com' _NETRC_MACHINE = 'safari' _API_BASE = 'https://www.safaribooksonline.com/api/v1/book' @@ -37,9 +36,7 @@ class SafariBaseIE(InfoExtractor): def _login(self): (username, password) = self._get_login_info() if username is None: - raise ExtractorError( - self._ACCOUNT_CREDENTIALS_HINT, - expected=True) + self.raise_login_required('safaribooksonline.com account is required') headers = std_headers if 'Referer' not in headers: diff --git a/youtube_dl/extractor/screenwavemedia.py b/youtube_dl/extractor/screenwavemedia.py index 220d39078..05f93904c 100644 --- a/youtube_dl/extractor/screenwavemedia.py +++ b/youtube_dl/extractor/screenwavemedia.py @@ -12,8 +12,8 @@ from ..utils import ( class ScreenwaveMediaIE(InfoExtractor): - _VALID_URL = r'http://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?[^"]*\bid=(?P<id>.+)' - + _VALID_URL = r'https?://player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=(?P<id>[A-Za-z0-9-]+)' + EMBED_PATTERN = r'src=(["\'])(?P<url>(?:https?:)?//player\d?\.screenwavemedia\.com/(?:play/)?[a-zA-Z]+\.php\?.*\bid=.+?)\1' _TESTS = [{ 'url': 'http://player.screenwavemedia.com/play/play.php?playerdiv=videoarea&companiondiv=squareAd&id=Cinemassacre-19911', 'only_matching': True, @@ -33,7 +33,7 @@ class ScreenwaveMediaIE(InfoExtractor): 'http://player.screenwavemedia.com/player.js', video_id, 'Downloading playerconfig webpage') - videoserver = self._search_regex(r"\[ipaddress\]\s*=>\s*([\d\.]+)", playerdata, 'videoserver') + videoserver = self._search_regex(r'SWMServer\s*=\s*"([\d\.]+)"', playerdata, 'videoserver') sources = self._parse_json( js_to_json( @@ -56,6 +56,7 @@ class ScreenwaveMediaIE(InfoExtractor): # Fallback to hardcoded sources if JS changes again if not sources: + self.report_warning('Falling back to a hardcoded list of streams') sources = [{ 'file': 'http://%s/vod/%s_%s.mp4' % (videoserver, video_id, format_id), 'type': 'mp4', diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py index a07677686..c5636e8e9 100644 --- a/youtube_dl/extractor/shared.py +++ b/youtube_dl/extractor/shared.py @@ -14,17 +14,28 @@ from ..utils import ( class SharedIE(InfoExtractor): - _VALID_URL = r'http://shared\.sx/(?P<id>[\da-z]{10})' + IE_DESC = 'shared.sx and vivo.sx' + _VALID_URL = r'http://(?:shared|vivo)\.sx/(?P<id>[\da-z]{10})' - _TEST = { + _TESTS = [{ 'url': 'http://shared.sx/0060718775', 'md5': '106fefed92a8a2adb8c98e6a0652f49b', 'info_dict': { 'id': '0060718775', 'ext': 'mp4', 'title': 'Bmp4', + 'filesize': 1720110, }, - } + }, { + 'url': 'http://vivo.sx/d7ddda0e78', + 'md5': '15b3af41be0b4fe01f4df075c2678b2c', + 'info_dict': { + 'id': 'd7ddda0e78', + 'ext': 'mp4', + 'title': 'Chicken', + 'filesize': 528031, + }, + }] def _real_extract(self, url): video_id = self._match_id(url) diff --git a/youtube_dl/extractor/smotri.py b/youtube_dl/extractor/smotri.py index 93a7cfe15..35a81ee87 100644 --- a/youtube_dl/extractor/smotri.py +++ b/youtube_dl/extractor/smotri.py @@ -330,10 +330,7 @@ class SmotriBroadcastIE(InfoExtractor): (username, password) = self._get_login_info() if username is None: - raise ExtractorError( - 'Erotic broadcasts allowed only for registered users, ' - 'use --username and --password options to provide account credentials.', - expected=True) + self.raise_login_required('Erotic broadcasts allowed only for registered users') login_form = { 'login-hint53': '1', diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py index 6ce86cbcd..ed5dcc0d3 100644 --- a/youtube_dl/extractor/soundcloud.py +++ b/youtube_dl/extractor/soundcloud.py @@ -309,7 +309,7 @@ class SoundcloudUserIE(SoundcloudIE): 'id': '114582580', 'title': 'The Akashic Chronicler (All)', }, - 'playlist_mincount': 112, + 'playlist_mincount': 111, }, { 'url': 'https://soundcloud.com/the-akashic-chronicler/tracks', 'info_dict': { @@ -330,14 +330,14 @@ class SoundcloudUserIE(SoundcloudIE): 'id': '114582580', 'title': 'The Akashic Chronicler (Reposts)', }, - 'playlist_mincount': 9, + 'playlist_mincount': 7, }, { 'url': 'https://soundcloud.com/the-akashic-chronicler/likes', 'info_dict': { 'id': '114582580', 'title': 'The Akashic Chronicler (Likes)', }, - 'playlist_mincount': 333, + 'playlist_mincount': 321, }, { 'url': 'https://soundcloud.com/grynpyret/spotlight', 'info_dict': { diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index 5fa6faf18..9e8fb35b2 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -16,8 +16,9 @@ from ..aes import aes_decrypt_text class SpankwireIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<id>[0-9]+)/?)' + _TESTS = [{ + # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/', 'md5': '8bbfde12b101204b39e4b9fe7eb67095', 'info_dict': { @@ -30,14 +31,27 @@ class SpankwireIE(InfoExtractor): 'upload_date': '20070507', 'age_limit': 18, } - } + }, { + # download URL pattern: */mp4_<format_id>_<video_id>.mp4 + 'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/', + 'md5': '09b3c20833308b736ae8902db2f8d7e6', + 'info_dict': { + 'id': '1921551', + 'ext': 'mp4', + 'title': 'Titcums Compiloation I', + 'description': 'cum on tits', + 'uploader': 'dannyh78999', + 'uploader_id': '3056053', + 'upload_date': '20150822', + 'age_limit': 18, + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') - url = 'http://www.' + mobj.group('url') + video_id = mobj.group('id') - req = compat_urllib_request.Request(url) + req = compat_urllib_request.Request('http://www.' + mobj.group('url')) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) @@ -54,7 +68,7 @@ class SpankwireIE(InfoExtractor): r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False) uploader_id = self._html_search_regex( - r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"', + r'by:\s*<a href="/(?:user/viewProfile|Profile\.aspx)\?.*?UserId=(\d+).*?"', webpage, 'uploader id', fatal=False) upload_date = unified_strdate(self._html_search_regex( r'</a> on (.+?) at \d+:\d+', @@ -67,9 +81,10 @@ class SpankwireIE(InfoExtractor): r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>', webpage, 'comment count', fatal=False)) - video_urls = list(map( - compat_urllib_parse_unquote, - re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage))) + videos = re.findall( + r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage) + heights = [int(video[0]) for video in videos] + video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos])) if webpage.find('flashvars\.encrypted = "true"') != -1: password = self._search_regex( r'flashvars\.video_title = "([^"]+)', @@ -79,21 +94,22 @@ class SpankwireIE(InfoExtractor): video_urls)) formats = [] - for video_url in video_urls: + for height, video_url in zip(heights, video_urls): path = compat_urllib_parse_urlparse(video_url).path - format = path.split('/')[4].split('_')[:2] - resolution, bitrate_str = format - format = "-".join(format) - height = int(resolution.rstrip('Pp')) - tbr = int(bitrate_str.rstrip('Kk')) - formats.append({ + _, quality = path.split('/')[4].split('_')[:2] + f = { 'url': video_url, - 'resolution': resolution, - 'format': format, - 'tbr': tbr, 'height': height, - 'format_id': format, - }) + } + tbr = self._search_regex(r'^(\d+)[Kk]$', quality, 'tbr', default=None) + if tbr: + f.update({ + 'tbr': int(tbr), + 'format_id': '%dp' % height, + }) + else: + f['format_id'] = quality + formats.append(f) self._sort_formats(formats) age_limit = self._rta_search(webpage) diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index adaec3375..25edc3100 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -2,7 +2,6 @@ from __future__ import unicode_literals import re -import json import time import hmac import binascii @@ -29,7 +28,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns}) class ThePlatformBaseIE(InfoExtractor): - def _extract_theplatform_smil_formats(self, smil_url, video_id, note='Downloading SMIL data'): + def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'): meta = self._download_xml(smil_url, video_id, note=note) try: error_msg = next( @@ -55,12 +54,13 @@ class ThePlatformBaseIE(InfoExtractor): self._sort_formats(formats) - return formats + subtitles = self._parse_smil_subtitles(meta, default_ns) + + return formats, subtitles def get_metadata(self, path, video_id): info_url = 'http://link.theplatform.com/s/%s?format=preview' % path - info_json = self._download_webpage(info_url, video_id) - info = json.loads(info_json) + info = self._download_json(info_url, video_id) subtitles = {} captions = info.get('captions') @@ -210,12 +210,14 @@ class ThePlatformIE(ThePlatformBaseIE): if sig: smil_url = self._sign_url(smil_url, sig['key'], sig['secret']) - formats = self._extract_theplatform_smil_formats(smil_url, video_id) + formats, subtitles = self._extract_theplatform_smil(smil_url, video_id) ret = self.get_metadata(path, video_id) + combined_subtitles = self._merge_subtitles(ret.get('subtitles', {}), subtitles) ret.update({ 'id': video_id, 'formats': formats, + 'subtitles': combined_subtitles, }) return ret @@ -253,6 +255,7 @@ class ThePlatformFeedIE(ThePlatformBaseIE): entry = feed['entries'][0] formats = [] + subtitles = {} first_video_id = None duration = None for item in entry['media$content']: @@ -261,7 +264,9 @@ class ThePlatformFeedIE(ThePlatformBaseIE): if first_video_id is None: first_video_id = cur_video_id duration = float_or_none(item.get('plfile$duration')) - formats.extend(self._extract_theplatform_smil_formats(smil_url, video_id, 'Downloading SMIL data for %s' % cur_video_id)) + cur_formats, cur_subtitles = self._extract_theplatform_smil(smil_url, video_id, 'Downloading SMIL data for %s' % cur_video_id) + formats.extend(cur_formats) + subtitles = self._merge_subtitles(subtitles, cur_subtitles) self._sort_formats(formats) @@ -275,9 +280,11 @@ class ThePlatformFeedIE(ThePlatformBaseIE): categories = [item['media$name'] for item in entry.get('media$categories', [])] ret = self.get_metadata('%s/%s' % (provider_id, first_video_id), video_id) + subtitles = self._merge_subtitles(subtitles, ret['subtitles']) ret.update({ 'id': video_id, 'formats': formats, + 'subtitles': subtitles, 'thumbnails': thumbnails, 'duration': duration, 'timestamp': timestamp, diff --git a/youtube_dl/extractor/tubitv.py b/youtube_dl/extractor/tubitv.py index 2c4b21807..4f86b3ee9 100644 --- a/youtube_dl/extractor/tubitv.py +++ b/youtube_dl/extractor/tubitv.py @@ -60,9 +60,7 @@ class TubiTvIE(InfoExtractor): 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) + self.raise_login_required('This video requires login') title = self._og_search_title(webpage) description = self._og_search_description(webpage) diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index 4a0eaf65f..365d8b4bf 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -70,9 +70,7 @@ class UdemyIE(InfoExtractor): def _login(self): (username, password) = self._get_login_info() if username is None: - raise ExtractorError( - 'Udemy account is required, use --username and --password options to provide account credentials.', - expected=True) + self.raise_login_required('Udemy account is required') login_popup = self._download_webpage( self._LOGIN_URL, None, 'Downloading login popup') diff --git a/youtube_dl/extractor/yandexmusic.py b/youtube_dl/extractor/yandexmusic.py index f4c0f5702..4098e4629 100644 --- a/youtube_dl/extractor/yandexmusic.py +++ b/youtube_dl/extractor/yandexmusic.py @@ -1,18 +1,38 @@ -# coding=utf-8 +# coding: utf-8 from __future__ import unicode_literals import re import hashlib from .common import InfoExtractor -from ..compat import compat_str +from ..compat import ( + compat_str, + compat_urllib_parse, + compat_urllib_request, +) from ..utils import ( int_or_none, float_or_none, ) -class YandexMusicBaseIE(InfoExtractor): +class YandexMusicTrackIE(InfoExtractor): + IE_NAME = 'yandexmusic:track' + IE_DESC = 'Яндекс.Музыка - Трек' + _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)' + + _TEST = { + 'url': 'http://music.yandex.ru/album/540508/track/4878838', + 'md5': 'f496818aa2f60b6c0062980d2e00dc20', + 'info_dict': { + 'id': '4878838', + 'ext': 'mp3', + 'title': 'Carlo Ambrosio - Gypsy Eyes 1', + 'filesize': 4628061, + 'duration': 193.04, + } + } + def _get_track_url(self, storage_dir, track_id): data = self._download_json( 'http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?action=getTrackSrc&p=download-info/%s' @@ -35,24 +55,6 @@ class YandexMusicBaseIE(InfoExtractor): 'duration': float_or_none(track.get('durationMs'), 1000), } - -class YandexMusicTrackIE(YandexMusicBaseIE): - IE_NAME = 'yandexmusic:track' - IE_DESC = 'Яндекс.Музыка - Трек' - _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<album_id>\d+)/track/(?P<id>\d+)' - - _TEST = { - 'url': 'http://music.yandex.ru/album/540508/track/4878838', - 'md5': 'f496818aa2f60b6c0062980d2e00dc20', - 'info_dict': { - 'id': '4878838', - 'ext': 'mp3', - 'title': 'Carlo Ambrosio - Gypsy Eyes 1', - 'filesize': 4628061, - 'duration': 193.04, - } - } - def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) album_id, track_id = mobj.group('album_id'), mobj.group('id') @@ -64,7 +66,15 @@ class YandexMusicTrackIE(YandexMusicBaseIE): return self._get_track_info(track) -class YandexMusicAlbumIE(YandexMusicBaseIE): +class YandexMusicPlaylistBaseIE(InfoExtractor): + def _build_playlist(self, tracks): + return [ + self.url_result( + 'http://music.yandex.ru/album/%s/track/%s' % (track['albums'][0]['id'], track['id'])) + for track in tracks if track.get('albums') and isinstance(track.get('albums'), list)] + + +class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE): IE_NAME = 'yandexmusic:album' IE_DESC = 'Яндекс.Музыка - Альбом' _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/album/(?P<id>\d+)/?(\?|$)' @@ -85,7 +95,7 @@ class YandexMusicAlbumIE(YandexMusicBaseIE): 'http://music.yandex.ru/handlers/album.jsx?album=%s' % album_id, album_id, 'Downloading album JSON') - entries = [self._get_track_info(track) for track in album['volumes'][0]] + entries = self._build_playlist(album['volumes'][0]) title = '%s - %s' % (album['artists'][0]['name'], album['title']) year = album.get('year') @@ -95,12 +105,12 @@ class YandexMusicAlbumIE(YandexMusicBaseIE): return self.playlist_result(entries, compat_str(album['id']), title) -class YandexMusicPlaylistIE(YandexMusicBaseIE): +class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE): IE_NAME = 'yandexmusic:playlist' IE_DESC = 'Яндекс.Музыка - Плейлист' _VALID_URL = r'https?://music\.yandex\.(?:ru|kz|ua|by)/users/[^/]+/playlists/(?P<id>\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://music.yandex.ru/users/music.partners/playlists/1245', 'info_dict': { 'id': '1245', @@ -108,20 +118,54 @@ class YandexMusicPlaylistIE(YandexMusicBaseIE): 'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9', }, 'playlist_count': 6, - } + }, { + # playlist exceeding the limit of 150 tracks shipped with webpage (see + # https://github.com/rg3/youtube-dl/issues/6666) + 'url': 'https://music.yandex.ru/users/ya.playlist/playlists/1036', + 'info_dict': { + 'id': '1036', + 'title': 'Музыка 90-х', + }, + 'playlist_count': 310, + }] def _real_extract(self, url): playlist_id = self._match_id(url) webpage = self._download_webpage(url, playlist_id) - playlist = self._parse_json( + mu = self._parse_json( self._search_regex( r'var\s+Mu\s*=\s*({.+?});\s*</script>', webpage, 'player'), - playlist_id)['pageData']['playlist'] - - entries = [self._get_track_info(track) for track in playlist['tracks']] + playlist_id) + + playlist = mu['pageData']['playlist'] + tracks, track_ids = playlist['tracks'], playlist['trackIds'] + + # tracks dictionary shipped with webpage is limited to 150 tracks, + # missing tracks should be retrieved manually. + if len(tracks) < len(track_ids): + present_track_ids = set([compat_str(track['id']) for track in tracks if track.get('id')]) + missing_track_ids = set(map(compat_str, track_ids)) - set(present_track_ids) + request = compat_urllib_request.Request( + 'https://music.yandex.ru/handlers/track-entries.jsx', + compat_urllib_parse.urlencode({ + 'entries': ','.join(missing_track_ids), + 'lang': mu.get('settings', {}).get('lang', 'en'), + 'external-domain': 'music.yandex.ru', + 'overembed': 'false', + 'sign': mu.get('authData', {}).get('user', {}).get('sign'), + 'strict': 'true', + }).encode('utf-8')) + request.add_header('Referer', url) + request.add_header('X-Requested-With', 'XMLHttpRequest') + + missing_tracks = self._download_json( + request, playlist_id, 'Downloading missing tracks JSON', fatal=False) + if missing_tracks: + tracks.extend(missing_tracks) return self.playlist_result( - entries, compat_str(playlist_id), + self._build_playlist(tracks), + compat_str(playlist_id), playlist['title'], playlist.get('description')) diff --git a/youtube_dl/extractor/youku.py b/youtube_dl/extractor/youku.py index 78caeb8b3..2e81d9223 100644 --- a/youtube_dl/extractor/youku.py +++ b/youtube_dl/extractor/youku.py @@ -49,6 +49,17 @@ class YoukuIE(InfoExtractor): }, 'playlist_count': 13, 'skip': 'Available in China only', + }, { + 'url': 'http://v.youku.com/v_show/id_XNjA1NzA2Njgw.html', + 'note': 'Video protected with password', + 'info_dict': { + 'id': 'XNjA1NzA2Njgw', + 'title': '邢義田复旦讲座之想象中的胡人—从“左衽孔子”说起', + }, + 'playlist_count': 19, + 'params': { + 'videopassword': '100600', + }, }] def construct_video_urls(self, data1, data2): @@ -185,9 +196,15 @@ class YoukuIE(InfoExtractor): raw_data = self._download_json(req, video_id, note=note) return raw_data['data'][0] + video_password = self._downloader.params.get('videopassword', None) + # request basic data + basic_data_url = 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id + if video_password: + basic_data_url += '?password=%s' % video_password + data1 = retrieve_data( - 'http://v.youku.com/player/getPlayList/VideoIDS/%s' % video_id, + basic_data_url, 'Downloading JSON metadata 1') data2 = retrieve_data( 'http://v.youku.com/player/getPlayList/VideoIDS/%s/Pf/4/ctype/12/ev/1' % video_id, diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 8e2da46e3..030ec70ca 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -660,7 +660,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): def _extract_signature_function(self, video_id, player_url, example_sig): id_m = re.match( - r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', + r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?)?\.(?P<ext>[a-z]+)$', player_url) if not id_m: raise ExtractorError('Cannot identify player %r' % player_url) @@ -1243,7 +1243,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] if 'rtmpe%3Dyes' in encoded_url_map: raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) - url_map = {} + formats = [] for url_data_str in encoded_url_map.split(','): url_data = compat_parse_qs(url_data_str) if 'itag' not in url_data or 'url' not in url_data: @@ -1289,7 +1289,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor): player_desc = 'flash player %s' % player_version else: player_version = self._search_regex( - r'html5player-([^/]+?)(?:/html5player)?\.js', + r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', player_url, 'html5 player', fatal=False) player_desc = 'html5 player %s' % player_version @@ -1303,8 +1303,50 @@ class YoutubeIE(YoutubeBaseInfoExtractor): url += '&signature=' + signature if 'ratebypass' not in url: url += '&ratebypass=yes' - url_map[format_id] = url - formats = _map_to_format_list(url_map) + + # Some itags are not included in DASH manifest thus corresponding formats will + # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993). + # Trying to extract metadata from url_encoded_fmt_stream_map entry. + mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) + width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) + dct = { + 'format_id': format_id, + 'url': url, + 'player_url': player_url, + 'filesize': int_or_none(url_data.get('clen', [None])[0]), + 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000), + 'width': width, + 'height': height, + 'fps': int_or_none(url_data.get('fps', [None])[0]), + 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0], + } + type_ = url_data.get('type', [None])[0] + if type_: + type_split = type_.split(';') + kind_ext = type_split[0].split('/') + if len(kind_ext) == 2: + kind, ext = kind_ext + dct['ext'] = ext + if kind in ('audio', 'video'): + codecs = None + for mobj in re.finditer( + r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_): + if mobj.group('key') == 'codecs': + codecs = mobj.group('val') + break + if codecs: + codecs = codecs.split(',') + if len(codecs) == 2: + acodec, vcodec = codecs[0], codecs[1] + else: + acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0]) + dct.update({ + 'acodec': acodec, + 'vcodec': vcodec, + }) + if format_id in self._formats: + dct.update(self._formats[format_id]) + formats.append(dct) elif video_info.get('hlsvp'): manifest_url = video_info['hlsvp'][0] url_map = self._extract_from_m3u8(manifest_url, video_id) |