_ Git - youtube-dl/blob - youtube_dl/extractor/cbsnews.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .cbs import CBSBaseIE
   6 from ..utils import (
   7     parse_duration,
   8 )
   9
  10
  11 class CBSNewsIE(CBSBaseIE):
  12     IE_DESC = 'CBS News'
  13     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
  14
  15     _TESTS = [
  16         {
  17             'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
  18             'info_dict': {
  19                 'id': 'tesla-and-spacex-elon-musks-industrial-empire',
  20                 'ext': 'flv',
  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',
  23                 'duration': 791,
  24             },
  25             'params': {
  26                 # rtmp download
  27                 'skip_download': True,
  28             },
  29         },
  30         {
  31             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
  32             'info_dict': {
  33                 'id': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
  34                 'ext': 'mp4',
  35                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
  36                 'thumbnail': 're:^https?://.*\.jpg$',
  37                 'duration': 205,
  38                 'subtitles': {
  39                     'en': [{
  40                         'ext': 'ttml',
  41                     }],
  42                 },
  43             },
  44             'params': {
  45                 # m3u8 download
  46                 'skip_download': True,
  47             },
  48         },
  49     ]
  50
  51     def _real_extract(self, url):
  52         video_id = self._match_id(url)
  53
  54         webpage = self._download_webpage(url, video_id)
  55
  56         video_info = self._parse_json(self._html_search_regex(
  57             r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
  58             webpage, 'video JSON info'), video_id)
  59
  60         item = video_info['item'] if 'item' in video_info else video_info
  61         title = item.get('articleTitle') or item.get('hed')
  62         duration = item.get('duration')
  63         thumbnail = item.get('mediaImage') or item.get('thumbnail')
  64
  65         subtitles = {}
  66         formats = []
  67         for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
  68             pid = item.get('media' + format_id)
  69             if not pid:
  70                 continue
  71             release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' % pid
  72             tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
  73             formats.extend(tp_formats)
  74             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
  75         self._sort_formats(formats)
  76
  77         return {
  78             'id': video_id,
  79             'title': title,
  80             'thumbnail': thumbnail,
  81             'duration': duration,
  82             'formats': formats,
  83             'subtitles': subtitles,
  84         }
  85
  86
  87 class CBSNewsLiveVideoIE(InfoExtractor):
  88     IE_DESC = 'CBS News Live Videos'
  89     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
  90
  91     _TEST = {
  92         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
  93         'info_dict': {
  94             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
  95             'ext': 'flv',
  96             'title': 'Clinton, Sanders Prepare To Face Off In NH',
  97             'duration': 334,
  98         },
  99     }
 100
 101     def _real_extract(self, url):
 102         video_id = self._match_id(url)
 103
 104         webpage = self._download_webpage(url, video_id)
 105
 106         video_info = self._parse_json(self._html_search_regex(
 107             r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
 108
 109         hdcore_sign = 'hdcore=3.3.1'
 110         f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
 111         if f4m_formats:
 112             for entry in f4m_formats:
 113                 # URLs without the extra param induce an 404 error
 114                 entry.update({'extra_param_to_segment_url': hdcore_sign})
 115         self._sort_formats(f4m_formats)
 116
 117         return {
 118             'id': video_id,
 119             'title': video_info['headline'],
 120             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
 121             'duration': parse_duration(video_info.get('segmentDur')),
 122             'formats': f4m_formats,
 123         }