diff options
Diffstat (limited to 'yt_dlp/extractor/generic.py')
| -rw-r--r-- | yt_dlp/extractor/generic.py | 197 |
1 files changed, 177 insertions, 20 deletions
diff --git a/yt_dlp/extractor/generic.py b/yt_dlp/extractor/generic.py index 5dafef283..2b59d076f 100644 --- a/yt_dlp/extractor/generic.py +++ b/yt_dlp/extractor/generic.py @@ -28,6 +28,7 @@ from ..utils import ( mimetype2ext, orderedSet, parse_duration, + parse_resolution, sanitized_Request, smuggle_url, unescapeHTML, @@ -100,6 +101,8 @@ from .ustream import UstreamIE from .arte import ArteTVEmbedIE from .videopress import VideoPressIE from .rutube import RutubeIE +from .glomex import GlomexEmbedIE +from .megatvcom import MegaTVComEmbedIE from .limelight import LimelightBaseIE from .anvato import AnvatoIE from .washingtonpost import WashingtonPostIE @@ -112,6 +115,7 @@ from .channel9 import Channel9IE from .vshare import VShareIE from .mediasite import MediasiteIE from .springboardplatform import SpringboardPlatformIE +from .ted import TedEmbedIE from .yapfiles import YapFilesIE from .vice import ViceIE from .xfileshare import XFileShareIE @@ -135,8 +139,12 @@ from .arcpublishing import ArcPublishingIE from .medialaan import MedialaanIE from .simplecast import SimplecastIE from .wimtv import WimTVIE +from .tvopengr import TVOpenGrEmbedIE +from .ertgr import ERTWebtvEmbedIE from .tvp import TVPEmbedIE from .blogger import BloggerIE +from .mainstreaming import MainStreamingIE +from .gfycat import GfycatIE class GenericIE(InfoExtractor): @@ -1870,6 +1878,62 @@ class GenericIE(InfoExtractor): 'add_ie': [RutubeIE.ie_key()], }, { + # glomex:embed + 'url': 'https://www.skai.gr/news/world/iatrikos-syllogos-tourkias-to-turkovac-aplo-dialyma-erntogan-eiste-apateones-kai-pseytes', + 'info_dict': { + 'id': 'v-ch2nkhcirwc9-sf', + 'ext': 'mp4', + 'title': 'md5:786e1e24e06c55993cee965ef853a0c1', + 'description': 'md5:8b517a61d577efe7e36fde72fd535995', + 'timestamp': 1641885019, + 'upload_date': '20220111', + 'duration': 460000, + 'thumbnail': 'https://i3thumbs.glomex.com/dC1idjJwdndiMjRzeGwvMjAyMi8wMS8xMS8wNy8xMF8zNV82MWRkMmQ2YmU5ZTgyLmpwZw==/profile:player-960x540', + }, + }, + { + # megatvcom:embed + 'url': 'https://www.in.gr/2021/12/18/greece/apokalypsi-mega-poios-parelave-tin-ereyna-tsiodra-ek-merous-tis-kyvernisis-o-prothypourgos-telika-gnorize/', + 'info_dict': { + 'id': 'apokalypsi-mega-poios-parelave-tin-ereyna-tsiodra-ek-merous-tis-kyvernisis-o-prothypourgos-telika-gnorize', + 'title': 'md5:5e569cf996ec111057c2764ec272848f', + }, + 'playlist': [{ + 'md5': '1afa26064ff00ccb91617957dbc73dc1', + 'info_dict': { + 'ext': 'mp4', + 'id': '564916', + 'display_id': 'md5:6cdf22d3a2e7bacb274b7295089a1770', + 'title': 'md5:33b9dd39584685b62873043670eb52a6', + 'description': 'md5:c1db7310f390518ac36dd69d947ef1a1', + 'timestamp': 1639753145, + 'upload_date': '20211217', + 'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/12/prezerakos-1024x597.jpg', + }, + }, { + 'md5': '4a1c220695f1ef865a8b7966a53e2474', + 'info_dict': { + 'ext': 'mp4', + 'id': '564905', + 'display_id': 'md5:ead15695e485e649aed2b81ebd699b88', + 'title': 'md5:2b71fd54249a3ca34609fe39ae31c47b', + 'description': 'md5:c42e12f638d0a97d6de4508e2c4df982', + 'timestamp': 1639753047, + 'upload_date': '20211217', + 'thumbnail': 'https://www.megatv.com/wp-content/uploads/2021/12/tsiodras-mitsotakis-1024x545.jpg', + }, + }] + }, + { + 'url': 'https://www.ertnews.gr/video/manolis-goyalles-o-anthropos-piso-apo-ti-diadiktyaki-vasilopita/', + 'info_dict': { + 'id': '2022/tv/news-themata-ianouarios/20220114-apotis6-gouales-pita.mp4', + 'ext': 'mp4', + 'title': 'md5:df64f5b61c06d0e9556c0cdd5cf14464', + 'thumbnail': 'https://www.ert.gr/themata/photos/2021/20220114-apotis6-gouales-pita.jpg', + }, + }, + { # ThePlatform embedded with whitespaces in URLs 'url': 'http://www.golfchannel.com/topics/shows/golftalkcentral.htm', 'only_matching': True, @@ -2175,6 +2239,22 @@ class GenericIE(InfoExtractor): }, }, { + # tvopengr:embed + 'url': 'https://www.ethnos.gr/World/article/190604/hparosiaxekinoynoisynomiliessthgeneyhmethskiatoypolemoypanoapothnoykrania', + 'md5': 'eb0c3995d0a6f18f6538c8e057865d7d', + 'info_dict': { + 'id': '101119', + 'ext': 'mp4', + 'display_id': 'oikarpoitondiapragmateyseonhparosias', + 'title': 'md5:b979f4d640c568617d6547035528a149', + 'description': 'md5:e54fc1977c7159b01cc11cd7d9d85550', + 'timestamp': 1641772800, + 'upload_date': '20220110', + 'thumbnail': 'https://opentv-static.siliconweb.com/imgHandler/1920/70bc39fa-895b-4918-a364-c39d2135fc6d.jpg', + + } + }, + { # blogger embed 'url': 'https://blog.tomeuvizoso.net/2019/01/a-panfrost-milestone.html', 'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac', @@ -2382,8 +2462,47 @@ class GenericIE(InfoExtractor): 'timestamp': 1636788683.0, 'upload_date': '20211113' } + }, + { + # MainStreaming player + 'url': 'https://www.lactv.it/2021/10/03/lac-news24-la-settimana-03-10-2021/', + 'info_dict': { + 'id': 'EUlZfGWkGpOd', + 'title': 'La Settimana ', + 'description': '03 Ottobre ore 02:00', + 'ext': 'mp4', + 'live_status': 'not_live', + 'thumbnail': r're:https?://[A-Za-z0-9-]*\.msvdn.net/image/\w+/poster', + 'duration': 1512 + } + }, + { + # Multiple gfycat iframe embeds + 'url': 'https://www.gezip.net/bbs/board.php?bo_table=entertaine&wr_id=613422', + 'info_dict': { + 'title': '재이, 윤, 세은 황금 드레스를 입고 빛난다', + 'id': 'board' + }, + 'playlist_count': 8, + }, + { + # Multiple gfycat gifs (direct links) + 'url': 'https://www.gezip.net/bbs/board.php?bo_table=entertaine&wr_id=612199', + 'info_dict': { + 'title': '옳게 된 크롭 니트 스테이씨 아이사', + 'id': 'board' + }, + 'playlist_count': 6 + }, + { + # Multiple gfycat embeds, with uppercase "IFR" in urls + 'url': 'https://kkzz.kr/?vid=2295', + 'info_dict': { + 'title': '지방시 앰버서더 에스파 카리나 움짤', + 'id': '?vid=2295' + }, + 'playlist_count': 9 } - # ] def report_following_redirect(self, new_url): @@ -3083,10 +3202,9 @@ class GenericIE(InfoExtractor): return self.url_result(mobj.group('url'), 'Tvigle') # Look for embedded TED player - mobj = re.search( - r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage) - if mobj is not None: - return self.url_result(mobj.group('url'), 'TED') + ted_urls = TedEmbedIE._extract_urls(webpage) + if ted_urls: + return self.playlist_from_matches(ted_urls, video_id, video_title, ie=TedEmbedIE.ie_key()) # Look for embedded Ustream videos ustream_url = UstreamIE._extract_url(webpage) @@ -3422,6 +3540,18 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( rutube_urls, video_id, video_title, ie=RutubeIE.ie_key()) + # Look for Glomex embeds + glomex_urls = list(GlomexEmbedIE._extract_urls(webpage, url)) + if glomex_urls: + return self.playlist_from_matches( + glomex_urls, video_id, video_title, ie=GlomexEmbedIE.ie_key()) + + # Look for megatv.com embeds + megatvcom_urls = list(MegaTVComEmbedIE._extract_urls(webpage)) + if megatvcom_urls: + return self.playlist_from_matches( + megatvcom_urls, video_id, video_title, ie=MegaTVComEmbedIE.ie_key()) + # Look for WashingtonPost embeds wapo_urls = WashingtonPostIE._extract_urls(webpage) if wapo_urls: @@ -3568,10 +3698,32 @@ class GenericIE(InfoExtractor): return self.playlist_from_matches( rumble_urls, video_id, video_title, ie=RumbleEmbedIE.ie_key()) + # Look for (tvopen|ethnos).gr embeds + tvopengr_urls = list(TVOpenGrEmbedIE._extract_urls(webpage)) + if tvopengr_urls: + return self.playlist_from_matches(tvopengr_urls, video_id, video_title, ie=TVOpenGrEmbedIE.ie_key()) + + # Look for ert.gr webtv embeds + ertwebtv_urls = list(ERTWebtvEmbedIE._extract_urls(webpage)) + if len(ertwebtv_urls) == 1: + return self.url_result(self._proto_relative_url(ertwebtv_urls[0]), video_title=video_title, url_transparent=True) + elif ertwebtv_urls: + return self.playlist_from_matches(ertwebtv_urls, video_id, video_title, ie=ERTWebtvEmbedIE.ie_key()) + tvp_urls = TVPEmbedIE._extract_urls(webpage) if tvp_urls: return self.playlist_from_matches(tvp_urls, video_id, video_title, ie=TVPEmbedIE.ie_key()) + # Look for MainStreaming embeds + mainstreaming_urls = MainStreamingIE._extract_urls(webpage) + if mainstreaming_urls: + return self.playlist_from_matches(mainstreaming_urls, video_id, video_title, ie=MainStreamingIE.ie_key()) + + # Look for Gfycat Embeds + gfycat_urls = GfycatIE._extract_urls(webpage) + if gfycat_urls: + return self.playlist_from_matches(gfycat_urls, video_id, video_title, ie=GfycatIE.ie_key()) + # Look for HTML5 media entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') if entries: @@ -3663,12 +3815,16 @@ class GenericIE(InfoExtractor): # Looking for http://schema.org/VideoObject json_ld = self._search_json_ld(webpage, video_id, default={}) - if json_ld.get('url'): + if json_ld.get('url') not in (url, None): self.report_detected('JSON LD') - if determine_ext(json_ld.get('url')) == 'm3u8': + if determine_ext(json_ld['url']) == 'm3u8': json_ld['formats'], json_ld['subtitles'] = self._extract_m3u8_formats_and_subtitles( json_ld['url'], video_id, 'mp4') json_ld.pop('url') + self._sort_formats(json_ld['formats']) + else: + json_ld['_type'] = 'url_transparent' + json_ld['url'] = smuggle_url(json_ld['url'], {'force_videoid': video_id, 'to_generic': True}) return merge_dicts(json_ld, info_dict) def check_video(vurl): @@ -3723,20 +3879,21 @@ class GenericIE(InfoExtractor): protocol, _, _ = url.partition('/') thumbnail = protocol + thumbnail + url_keys = list(filter(re.compile(r'video_url|video_alt_url\d*').fullmatch, flashvars.keys())) formats = [] - for key in ('video_url', 'video_alt_url', 'video_alt_url2'): - if key in flashvars and '/get_file/' in flashvars[key]: - next_format = { - 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']), - 'format_id': flashvars.get(key + '_text', key), - 'ext': 'mp4', - } - height = re.search(r'%s_(\d+)p\.mp4(?:/[?].*)?$' % flashvars['video_id'], flashvars[key]) - if height: - next_format['height'] = int(height.group(1)) - else: - next_format['quality'] = 1 - formats.append(next_format) + for key in url_keys: + if '/get_file/' not in flashvars[key]: + continue + format_id = flashvars.get(f'{key}_text', key) + formats.append({ + 'url': self._kvs_getrealurl(flashvars[key], flashvars['license_code']), + 'format_id': format_id, + 'ext': 'mp4', + **(parse_resolution(format_id) or parse_resolution(flashvars[key])) + }) + if not formats[-1].get('height'): + formats[-1]['quality'] = 1 + self._sort_formats(formats) return { |