X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/99a6f8745584b59fe0fa1f5e81f6c3667bd3fb2b..c39143087e10ba3fe3c3a309b847354b82d6125e:/youtube_dl/extractor/generic.py?ds=sidebyside diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index 1d9da81..067de28 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -23,6 +23,7 @@ from ..utils import ( is_html, js_to_json, KNOWN_EXTENSIONS, + merge_dicts, mimetype2ext, orderedSet, sanitized_Request, @@ -46,7 +47,7 @@ from .nbc import NBCSportsVPlayerIE from .ooyala import OoyalaIE from .rutv import RUTVIE from .tvc import TVCIE -from .sportbox import SportBoxEmbedIE +from .sportbox import SportBoxIE from .smotri import SmotriIE from .myvi import MyviIE from .condenast import CondeNastIE @@ -58,6 +59,7 @@ from .xhamster import XHamsterEmbedIE from .tnaflix import TNAFlixNetworkEmbedIE from .drtuber import DrTuberIE from .redtube import RedTubeIE +from .tube8 import Tube8IE from .vimeo import VimeoIE from .dailymotion import DailymotionIE from .dailymail import DailyMailIE @@ -102,6 +104,18 @@ from .channel9 import Channel9IE from .vshare import VShareIE from .mediasite import MediasiteIE from .springboardplatform import SpringboardPlatformIE +from .yapfiles import YapFilesIE +from .vice import ViceIE +from .xfileshare import XFileShareIE +from .cloudflarestream import CloudflareStreamIE +from .peertube import PeerTubeIE +from .teachable import TeachableIE +from .indavideo import IndavideoEmbedIE +from .apa import APAIE +from .foxnews import FoxNewsIE +from .viqeo import ViqeoIE +from .expressen import ExpressenIE +from .zype import ZypeIE class GenericIE(InfoExtractor): @@ -186,6 +200,16 @@ class GenericIE(InfoExtractor): 'title': 'pdv_maddow_netcast_m4v-02-27-2015-201624', } }, + # RSS feed with enclosures and unsupported link URLs + { + 'url': 'http://www.hellointernet.fm/podcast?format=rss', + 'info_dict': { + 'id': 'http://www.hellointernet.fm/podcast?format=rss', + 'description': 'CGP Grey and Brady Haran talk about YouTube, life, work, whatever.', + 'title': 'Hello Internet', + }, + 'playlist_mincount': 100, + }, # SMIL from http://videolectures.net/promogram_igor_mekjavic_eng { 'url': 'http://videolectures.net/promogram_igor_mekjavic_eng/video/1/smil.xml', @@ -1216,7 +1240,7 @@ class GenericIE(InfoExtractor): 'title': '35871', 'timestamp': 1355743100, 'upload_date': '20121217', - 'uploader_id': 'batchUser', + 'uploader_id': 'cplapp@learn360.com', }, 'add_ie': ['Kaltura'], }, @@ -1267,23 +1291,38 @@ class GenericIE(InfoExtractor): }, 'add_ie': ['Kaltura'], }, - # EaglePlatform embed (generic URL) { - 'url': 'http://lenta.ru/news/2015/03/06/navalny/', - # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used + # Kaltura iframe embed, more sophisticated + 'url': 'http://www.cns.nyu.edu/~eero/math-tools/Videos/lecture-05sep2017.html', 'info_dict': { - 'id': '227304', + 'id': '1_9gzouybz', 'ext': 'mp4', - 'title': 'Навальный вышел на свободу', - 'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5', - 'thumbnail': r're:^https?://.*\.jpg$', - 'duration': 87, - 'view_count': int, - 'age_limit': 0, + 'title': 'lecture-05sep2017', + 'description': 'md5:40f347d91fd4ba047e511c5321064b49', + 'upload_date': '20170913', + 'uploader_id': 'eps2', + 'timestamp': 1505340777, }, 'params': { 'skip_download': True, }, + 'add_ie': ['Kaltura'], + }, + { + # meta twitter:player + 'url': 'http://thechive.com/2017/12/08/all-i-want-for-christmas-is-more-twerk/', + 'info_dict': { + 'id': '0_01b42zps', + 'ext': 'mp4', + 'title': 'Main Twerk (Video)', + 'upload_date': '20171208', + 'uploader_id': 'sebastian.salinas@thechive.com', + 'timestamp': 1512713057, + }, + 'params': { + 'skip_download': True, + }, + 'add_ie': ['Kaltura'], }, # referrer protected EaglePlatform embed { @@ -1360,17 +1399,6 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, }, - # SVT embed - { - 'url': 'http://www.svt.se/sport/ishockey/jagr-tacklar-giroux-under-intervjun', - 'info_dict': { - 'id': '2900353', - 'ext': 'flv', - 'title': 'Här trycker Jagr till Giroux (under SVT-intervjun)', - 'duration': 27, - 'age_limit': 0, - }, - }, # Crooks and Liars embed { 'url': 'http://crooksandliars.com/2015/04/fox-friends-says-protecting-atheists', @@ -1441,21 +1469,6 @@ class GenericIE(InfoExtractor): }, 'expected_warnings': ['Failed to parse JSON Expecting value'], }, - # Ooyala embed - { - 'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T', - 'info_dict': { - 'id': '50YnY4czr4ms1vJ7yz3xzq0excz_pUMs', - 'ext': 'mp4', - 'description': 'Index/Match versus VLOOKUP.', - 'title': 'This is what separates the Excel masters from the wannabes', - 'duration': 191.933, - }, - 'params': { - # m3u8 downloads - 'skip_download': True, - } - }, # Brightcove URL in single quotes { 'url': 'http://www.sportsnet.ca/baseball/mlb/sn-presents-russell-martin-world-citizen/', @@ -1954,7 +1967,140 @@ class GenericIE(InfoExtractor): 'skip_download': True, }, 'add_ie': [SpringboardPlatformIE.ie_key()], - } + }, + { + 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU', + 'info_dict': { + 'id': 'uPDB5I9wfp8', + 'ext': 'webm', + 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3', + 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d', + 'upload_date': '20160219', + 'uploader': 'Pocoyo - Português (BR)', + 'uploader_id': 'PocoyoBrazil', + }, + 'add_ie': [YoutubeIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + 'url': 'https://www.yapfiles.ru/show/1872528/690b05d3054d2dbe1e69523aa21bb3b1.mp4.html', + 'info_dict': { + 'id': 'vMDE4NzI1Mjgt690b', + 'ext': 'mp4', + 'title': 'Котята', + }, + 'add_ie': [YapFilesIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # CloudflareStream embed + 'url': 'https://www.cloudflare.com/products/cloudflare-stream/', + 'info_dict': { + 'id': '31c9291ab41fac05471db4e73aa11717', + 'ext': 'mp4', + 'title': '31c9291ab41fac05471db4e73aa11717', + }, + 'add_ie': [CloudflareStreamIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # PeerTube embed + 'url': 'https://joinpeertube.org/fr/home/', + 'info_dict': { + 'id': 'home', + 'title': 'Reprenez le contrôle de vos vidéos ! #JoinPeertube', + }, + 'playlist_count': 2, + }, + { + # Indavideo embed + 'url': 'https://streetkitchen.hu/receptek/igy_kell_otthon_hamburgert_sutni/', + 'info_dict': { + 'id': '1693903', + 'ext': 'mp4', + 'title': 'Így kell otthon hamburgert sütni', + 'description': 'md5:f5a730ecf900a5c852e1e00540bbb0f7', + 'timestamp': 1426330212, + 'upload_date': '20150314', + 'uploader': 'StreetKitchen', + 'uploader_id': '546363', + }, + 'add_ie': [IndavideoEmbedIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # APA embed via JWPlatform embed + 'url': 'http://www.vol.at/blue-man-group/5593454', + 'info_dict': { + 'id': 'jjv85FdZ', + 'ext': 'mp4', + 'title': '"Blau ist mysteriös": Die Blue Man Group im Interview', + 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', + 'thumbnail': r're:^https?://.*\.jpg$', + 'duration': 254, + 'timestamp': 1519211149, + 'upload_date': '20180221', + }, + 'params': { + 'skip_download': True, + }, + }, + { + 'url': 'http://share-videos.se/auto/video/83645793?uid=13', + 'md5': 'b68d276de422ab07ee1d49388103f457', + 'info_dict': { + 'id': '83645793', + 'title': 'Lock up and get excited', + 'ext': 'mp4' + }, + 'skip': 'TODO: fix nested playlists processing in tests', + }, + { + # Viqeo embeds + 'url': 'https://viqeo.tv/', + 'info_dict': { + 'id': 'viqeo', + 'title': 'All-new video platform', + }, + 'playlist_count': 6, + }, + { + # Zype embed + 'url': 'https://www.cookscountry.com/episode/554-smoky-barbecue-favorites', + 'info_dict': { + 'id': '5b400b834b32992a310622b9', + 'ext': 'mp4', + 'title': 'Smoky Barbecue Favorites', + 'thumbnail': r're:^https?://.*\.jpe?g', + }, + 'add_ie': [ZypeIE.ie_key()], + 'params': { + 'skip_download': True, + }, + }, + { + # videojs embed + 'url': 'https://video.sibnet.ru/shell.php?videoid=3422904', + 'info_dict': { + 'id': 'shell', + 'ext': 'mp4', + 'title': 'Доставщик пиццы спросил разрешения сыграть на фортепиано', + 'description': 'md5:89209cdc587dab1e4a090453dbaa2cb1', + 'thumbnail': r're:^https?://.*\.jpg$', + }, + 'params': { + 'skip_download': True, + }, + 'expected_warnings': ['Failed to download MPD manifest'], + }, # { # # TODO: find another test # # http://schema.org/VideoObject @@ -1985,13 +2131,15 @@ class GenericIE(InfoExtractor): entries = [] for it in doc.findall('./channel/item'): - next_url = xpath_text(it, 'link', fatal=False) + next_url = None + enclosure_nodes = it.findall('./enclosure') + for e in enclosure_nodes: + next_url = e.attrib.get('url') + if next_url: + break + if not next_url: - enclosure_nodes = it.findall('./enclosure') - for e in enclosure_nodes: - next_url = e.attrib.get('url') - if next_url: - break + next_url = xpath_text(it, 'link', fatal=False) if not next_url: continue @@ -2049,10 +2197,7 @@ class GenericIE(InfoExtractor): def _real_extract(self, url): if url.startswith('//'): - return { - '_type': 'url', - 'url': self.http_scheme() + url, - } + return self.url_result(self.http_scheme() + url) parsed_url = compat_urlparse.urlparse(url) if not parsed_url.scheme: @@ -2201,7 +2346,11 @@ class GenericIE(InfoExtractor): self._sort_formats(smil['formats']) return smil elif doc.tag == '{http://xspf.org/ns/0/}playlist': - return self.playlist_result(self._parse_xspf(doc, video_id), video_id) + return self.playlist_result( + self._parse_xspf( + doc, video_id, xspf_url=url, + xspf_base_url=compat_str(full_response.geturl())), + video_id) elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag): info_dict['formats'] = self._parse_mpd_formats( doc, @@ -2280,7 +2429,10 @@ class GenericIE(InfoExtractor): # Look for Brightcove New Studio embeds bc_urls = BrightcoveNewIE._extract_urls(self, webpage) if bc_urls: - return self.playlist_from_matches(bc_urls, video_id, video_title, ie='BrightcoveNew') + return self.playlist_from_matches( + bc_urls, video_id, video_title, + getter=lambda x: smuggle_url(x, {'referrer': url}), + ie='BrightcoveNew') # Look for Nexx embeds nexx_urls = NexxIE._extract_urls(webpage) @@ -2497,9 +2649,9 @@ class GenericIE(InfoExtractor): return self.url_result(tvc_url, 'TVC') # Look for embedded SportBox player - sportbox_urls = SportBoxEmbedIE._extract_urls(webpage) + sportbox_urls = SportBoxIE._extract_urls(webpage) if sportbox_urls: - return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie='SportBoxEmbed') + return self.playlist_from_matches(sportbox_urls, video_id, video_title, ie=SportBoxIE.ie_key()) # Look for embedded XHamster player xhamster_urls = XHamsterEmbedIE._extract_urls(webpage) @@ -2526,6 +2678,11 @@ class GenericIE(InfoExtractor): if redtube_urls: return self.playlist_from_matches(redtube_urls, video_id, video_title, ie=RedTubeIE.ie_key()) + # Look for embedded Tube8 player + tube8_urls = Tube8IE._extract_urls(webpage) + if tube8_urls: + return self.playlist_from_matches(tube8_urls, video_id, video_title, ie=Tube8IE.ie_key()) + # Look for embedded Tvigle player mobj = re.search( r']+?src=(["\'])(?P(?:https?:)?//cloud\.tvigle\.ru/video/.+?)\1', webpage) @@ -2879,7 +3036,7 @@ class GenericIE(InfoExtractor): wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key()) # Look for Mediaset embeds - mediaset_urls = MediasetIE._extract_urls(webpage) + mediaset_urls = MediasetIE._extract_urls(self, webpage) if mediaset_urls: return self.playlist_from_matches( mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key()) @@ -2928,20 +3085,71 @@ class GenericIE(InfoExtractor): springboardplatform_urls, video_id, video_title, ie=SpringboardPlatformIE.ie_key()) - def merge_dicts(dict1, dict2): - merged = {} - for k, v in dict1.items(): - if v is not None: - merged[k] = v - for k, v in dict2.items(): - if v is None: - continue - if (k not in merged or - (isinstance(v, compat_str) and v and - isinstance(merged[k], compat_str) and - not merged[k])): - merged[k] = v - return merged + yapfiles_urls = YapFilesIE._extract_urls(webpage) + if yapfiles_urls: + return self.playlist_from_matches( + yapfiles_urls, video_id, video_title, ie=YapFilesIE.ie_key()) + + vice_urls = ViceIE._extract_urls(webpage) + if vice_urls: + return self.playlist_from_matches( + vice_urls, video_id, video_title, ie=ViceIE.ie_key()) + + xfileshare_urls = XFileShareIE._extract_urls(webpage) + if xfileshare_urls: + return self.playlist_from_matches( + xfileshare_urls, video_id, video_title, ie=XFileShareIE.ie_key()) + + cloudflarestream_urls = CloudflareStreamIE._extract_urls(webpage) + if cloudflarestream_urls: + return self.playlist_from_matches( + cloudflarestream_urls, video_id, video_title, ie=CloudflareStreamIE.ie_key()) + + peertube_urls = PeerTubeIE._extract_urls(webpage, url) + if peertube_urls: + return self.playlist_from_matches( + peertube_urls, video_id, video_title, ie=PeerTubeIE.ie_key()) + + teachable_url = TeachableIE._extract_url(webpage, url) + if teachable_url: + return self.url_result(teachable_url) + + indavideo_urls = IndavideoEmbedIE._extract_urls(webpage) + if indavideo_urls: + return self.playlist_from_matches( + indavideo_urls, video_id, video_title, ie=IndavideoEmbedIE.ie_key()) + + apa_urls = APAIE._extract_urls(webpage) + if apa_urls: + return self.playlist_from_matches( + apa_urls, video_id, video_title, ie=APAIE.ie_key()) + + foxnews_urls = FoxNewsIE._extract_urls(webpage) + if foxnews_urls: + return self.playlist_from_matches( + foxnews_urls, video_id, video_title, ie=FoxNewsIE.ie_key()) + + sharevideos_urls = [sharevideos_mobj.group('url') for sharevideos_mobj in re.finditer( + r']+?\bsrc\s*=\s*(["\'])(?P(?:https?:)?//embed\.share-videos\.se/auto/embed/\d+\?.*?\buid=\d+.*?)\1', + webpage)] + if sharevideos_urls: + return self.playlist_from_matches( + sharevideos_urls, video_id, video_title) + + viqeo_urls = ViqeoIE._extract_urls(webpage) + if viqeo_urls: + return self.playlist_from_matches( + viqeo_urls, video_id, video_title, ie=ViqeoIE.ie_key()) + + expressen_urls = ExpressenIE._extract_urls(webpage) + if expressen_urls: + return self.playlist_from_matches( + expressen_urls, video_id, video_title, ie=ExpressenIE.ie_key()) + + zype_urls = ZypeIE._extract_urls(webpage) + if zype_urls: + return self.playlist_from_matches( + zype_urls, video_id, video_title, ie=ZypeIE.ie_key()) # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') @@ -2964,9 +3172,13 @@ class GenericIE(InfoExtractor): jwplayer_data = self._find_jwplayer_data( webpage, video_id, transform_source=js_to_json) if jwplayer_data: - info = self._parse_jwplayer_data( - jwplayer_data, video_id, require_title=False, base_url=url) - return merge_dicts(info, info_dict) + try: + info = self._parse_jwplayer_data( + jwplayer_data, video_id, require_title=False, base_url=url) + return merge_dicts(info, info_dict) + except ExtractorError: + # See https://github.com/rg3/youtube-dl/pull/16735 + pass # Video.js embed mobj = re.search(