2 from __future__ import unicode_literals
7 from .common import InfoExtractor
8 from ..utils import remove_start
11 class CBSNewsIE(InfoExtractor):
13 _VALID_URL = r'http://(?:www\.)?cbsnews\.com/(?:[^/]+/)+(?P<id>[\da-z_-]+)'
17 'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
19 'id': 'tesla-and-spacex-elon-musks-industrial-empire',
21 'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire',
22 'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg',
27 'skip_download': True,
31 'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
33 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
35 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
36 'thumbnail': 're:^https?://.*\.jpg$',
41 'skip_download': True,
45 'url': 'http://www.cbsnews.com/videos/mountain-lions-of-l-a/',
47 'id': 'Mountain Lions of L.A.',
49 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
50 'thumbnail': 're:^http?://.*\.jpg$',
51 'subtitles': 're:^http?://.*\.xml$',
56 'skip_download': True,
61 def _real_extract(self, url):
62 mobj = re.match(self._VALID_URL, url)
63 video_id = mobj.group('id')
65 webpage = self._download_webpage(url, video_id)
67 video_info = json.loads(self._html_search_regex(
68 r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
69 webpage, 'video JSON info'))
71 item = video_info['item'] if 'item' in video_info else video_info
72 title = item.get('articleTitle') or item.get('hed')
73 duration = item.get('duration')
74 thumbnail = item.get('mediaImage') or item.get('thumbnail')
77 for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
78 uri = item.get('media' + format_id + 'URI')
81 uri = remove_start(uri, '{manifest:none}')
84 'format_id': format_id,
86 if uri.startswith('rtmp'):
88 r'{slistFilePath}', '',
89 uri.split('<break>')[-1].split('{break}')[-1])
91 r'{manifest:.+}.*$', '', play_path)
93 'app': 'ondemand?auth=cbs',
94 'play_path': 'mp4:' + play_path,
95 'player_url': 'http://www.cbsnews.com/[[IMPORT]]/vidtech.cbsinteractive.com/player/3_3_0/CBSI_PLAYER_HD.swf',
96 'page_url': 'http://www.cbsnews.com',
99 elif uri.endswith('.m3u8'):
103 if 'mpxRefId' in video_info:
104 cap_url = 'http://www.cbsnews.com/videos/captions/%s.adb_xml' % video_info['mpxRefId']
116 'thumbnail': thumbnail,
117 'duration': duration,
119 'subtitles': subtitles,