Raphaël G. Git Repositories - youtubedl/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             'skip': 'Subscribers only',
  30         },
  31         {
  32             'url': 'http://www.cbsnews.com/videos/fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack/',
  33             'info_dict': {
  34                 'id': 'SNJBOYzXiWBOvaLsdzwH8fmtP1SCd91Y',
  35                 'ext': 'mp4',
  36                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
  37                 'description': 'md5:4a6983e480542d8b333a947bfc64ddc7',
  38                 'upload_date': '19700101',
  39                 'uploader': 'CBSI-NEW',
  40                 'thumbnail': 're:^https?://.*\.jpg$',
  41                 'duration': 205,
  42                 'subtitles': {
  43                     'en': [{
  44                         'ext': 'ttml',
  45                     }],
  46                 },
  47             },
  48             'params': {
  49                 # m3u8 download
  50                 'skip_download': True,
  51             },
  52         },
  53     ]
  54
  55     def _real_extract(self, url):
  56         video_id = self._match_id(url)
  57
  58         webpage = self._download_webpage(url, video_id)
  59
  60         video_info = self._parse_json(self._html_search_regex(
  61             r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
  62             webpage, 'video JSON info'), video_id)
  63
  64         item = video_info['item'] if 'item' in video_info else video_info
  65         guid = item['mpxRefId']
  66         return self._extract_video_info('byGuid=%s' % guid, guid)
  67
  68
  69 class CBSNewsLiveVideoIE(InfoExtractor):
  70     IE_DESC = 'CBS News Live Videos'
  71     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
  72
  73     # Live videos get deleted soon. See http://www.cbsnews.com/live/ for the latest examples
  74     _TEST = {
  75         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
  76         'info_dict': {
  77             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
  78             'ext': 'flv',
  79             'title': 'Clinton, Sanders Prepare To Face Off In NH',
  80             'duration': 334,
  81         },
  82         'skip': 'Video gone',
  83     }
  84
  85     def _real_extract(self, url):
  86         video_id = self._match_id(url)
  87
  88         webpage = self._download_webpage(url, video_id)
  89
  90         video_info = self._parse_json(self._html_search_regex(
  91             r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
  92
  93         hdcore_sign = 'hdcore=3.3.1'
  94         f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
  95         if f4m_formats:
  96             for entry in f4m_formats:
  97                 # URLs without the extra param induce an 404 error
  98                 entry.update({'extra_param_to_segment_url': hdcore_sign})
  99         self._sort_formats(f4m_formats)
 100
 101         return {
 102             'id': video_id,
 103             'title': video_info['headline'],
 104             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
 105             'duration': parse_duration(video_info.get('segmentDur')),
 106             'formats': f4m_formats,
 107         }