]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/sendtonews.py
3 from . common
import InfoExtractor
14 class SendtoNewsIE ( InfoExtractor
):
16 _VALID_URL
= r
'https?://embed\.sendtonews\.com/player2/embedplayer\.php\?.*\bSC=(?P<id>[0-9A-Za-z-]+)'
19 # From http://cleveland.cbslocal.com/2016/05/16/indians-score-season-high-15-runs-in-blowout-win-over-reds-rapid-reaction/
20 'url' : 'http://embed.sendtonews.com/player2/embedplayer.php?SC=GxfCe0Zo7D-175909-5588&type=single&autoplay=on&sound=YES' ,
22 'id' : 'GxfCe0Zo7D-175909-5588'
25 # test the first video only to prevent lengthy tests
30 'title' : 'Indians introduce Encarnacion' ,
31 'description' : 'Indians president of baseball operations Chris Antonetti and Edwin Encarnacion discuss the slugger \' s three-year contract with Cleveland' ,
33 'thumbnail' : r
're:https?://.*\.jpg$' ,
34 'upload_date' : '20170105' ,
35 'timestamp' : 1483649762 ,
40 'skip_download' : True ,
44 _URL_TEMPLATE
= '//embed.sendtonews.com/player2/embedplayer.php?SC= %s '
47 def _extract_embed_urls ( cls
, url
, webpage
):
48 mobj
= re
. search ( r
'''(?x)<script[^>]+src=([\' "])
49 (?:https?:)?//embed\.sendtonews\.com/player/responsiveembed\.php \?
50 .* \b SC=(?P<SC>[0-9a-zA-Z-]+).*
54 yield cls._URL_TEMPLATE % sc
56 def _real_extract(self, url):
57 playlist_id = self._match_id(url)
59 data_url = update_url_query(
60 url.replace('embedplayer.php', 'data_read.php'),
61 {'cmd': 'loadInitial'} )
62 playlist_data = self._download_json(data_url, playlist_id)
65 for video in playlist_data['playlistData'][0]:
66 info_dict = self._parse_jwplayer_data(
67 video['jwconfiguration'],
68 require_title=False, m3u8_id='hls', rtmp_params= {'no_resume': True} )
70 for f in info_dict['formats']:
73 tbr = int_or_none(self._search_regex(
74 r'/(\d+)k/', f['url'], 'bitrate', default=None))
78 'format_id': ' %s-%d ' % (determine_protocol(f), tbr),
83 if video.get('thumbnailUrl'):
86 'url': video['thumbnailUrl'],
88 if video.get('smThumbnailUrl'):
91 'url': video['smThumbnailUrl'],
94 'title': video['S_headLine'].strip(),
95 'description': unescapeHTML(video.get('S_fullStory')),
96 'thumbnails': thumbnails,
97 'duration': float_or_none(video.get('SM_length')),
98 'timestamp': parse_iso8601(video.get('S_sysDate'), delimiter=' '),
99 # 'tbr' was explicitly set to be preferred over 'height' originally,
100 # So this is being kept unless someone can confirm this is unnecessary
101 '_format_sort_fields': ('tbr', 'res')
103 entries.append(info_dict)
105 return self.playlist_result(entries, playlist_id)