_ 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     find_xpath_attr,
   9 )
  10
  11
  12 class CBSNewsIE(CBSBaseIE):
  13     IE_DESC = 'CBS News'
  14     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/(?:news|videos)/(?P<id>[\da-z_-]+)'
  15
  16     _TESTS = [
  17         {
  18             'url': 'http://www.cbsnews.com/news/tesla-and-spacex-elon-musks-industrial-empire/',
  19             'info_dict': {
  20                 'id': 'tesla-and-spacex-elon-musks-industrial-empire',
  21                 'ext': 'flv',
  22                 'title': 'Tesla and SpaceX: Elon Musk\'s industrial empire',
  23                 'thumbnail': 'http://beta.img.cbsnews.com/i/2014/03/30/60147937-2f53-4565-ad64-1bdd6eb64679/60-0330-pelley-640x360.jpg',
  24                 'duration': 791,
  25             },
  26             'params': {
  27                 # rtmp download
  28                 'skip_download': True,
  29             },
  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': 'fort-hood-shooting-army-downplays-mental-illness-as-cause-of-attack',
  35                 'ext': 'mp4',
  36                 'title': 'Fort Hood shooting: Army downplays mental illness as cause of attack',
  37                 'thumbnail': 're:^https?://.*\.jpg$',
  38                 'duration': 205,
  39                 'subtitles': {
  40                     'en': [{
  41                         'ext': 'ttml',
  42                     }],
  43                 },
  44             },
  45             'params': {
  46                 # m3u8 download
  47                 'skip_download': True,
  48             },
  49         },
  50     ]
  51
  52     def _real_extract(self, url):
  53         video_id = self._match_id(url)
  54
  55         webpage = self._download_webpage(url, video_id)
  56
  57         video_info = self._parse_json(self._html_search_regex(
  58             r'(?:<ul class="media-list items" id="media-related-items"><li data-video-info|<div id="cbsNewsVideoPlayer" data-video-player-options)=\'({.+?})\'',
  59             webpage, 'video JSON info'), video_id)
  60
  61         item = video_info['item'] if 'item' in video_info else video_info
  62         title = item.get('articleTitle') or item.get('hed')
  63         duration = item.get('duration')
  64         thumbnail = item.get('mediaImage') or item.get('thumbnail')
  65
  66         subtitles = {}
  67         formats = []
  68         for format_id in ['RtmpMobileLow', 'RtmpMobileHigh', 'Hls', 'RtmpDesktop']:
  69             pid = item.get('media' + format_id)
  70             if not pid:
  71                 continue
  72             release_url = 'http://link.theplatform.com/s/dJ5BDC/%s?mbr=true' % pid
  73             tp_formats, tp_subtitles = self._extract_theplatform_smil(release_url, video_id, 'Downloading %s SMIL data' % pid)
  74             formats.extend(tp_formats)
  75             subtitles = self._merge_subtitles(subtitles, tp_subtitles)
  76         self._sort_formats(formats)
  77
  78         return {
  79             'id': video_id,
  80             'title': title,
  81             'thumbnail': thumbnail,
  82             'duration': duration,
  83             'formats': formats,
  84             'subtitles': subtitles,
  85         }
  86
  87
  88 class CBSNewsLiveVideoIE(InfoExtractor):
  89     IE_DESC = 'CBS News Live Videos'
  90     _VALID_URL = r'https?://(?:www\.)?cbsnews\.com/live/video/(?P<id>[\da-z_-]+)'
  91
  92     _TEST = {
  93         'url': 'http://www.cbsnews.com/live/video/clinton-sanders-prepare-to-face-off-in-nh/',
  94         'info_dict': {
  95             'id': 'clinton-sanders-prepare-to-face-off-in-nh',
  96             'ext': 'flv',
  97             'title': 'Clinton, Sanders Prepare To Face Off In NH',
  98             'duration': 334,
  99         },
 100     }
 101
 102     def _real_extract(self, url):
 103         video_id = self._match_id(url)
 104
 105         webpage = self._download_webpage(url, video_id)
 106
 107         video_info = self._parse_json(self._html_search_regex(
 108             r'data-story-obj=\'({.+?})\'', webpage, 'video JSON info'), video_id)['story']
 109
 110         hdcore_sign = 'hdcore=3.3.1'
 111         f4m_formats = self._extract_f4m_formats(video_info['url'] + '&' + hdcore_sign, video_id)
 112         if f4m_formats:
 113             for entry in f4m_formats:
 114                 # URLs without the extra param induce an 404 error
 115                 entry.update({'extra_param_to_segment_url': hdcore_sign})
 116         self._sort_formats(f4m_formats)
 117
 118         return {
 119             'id': video_id,
 120             'title': video_info['headline'],
 121             'thumbnail': video_info.get('thumbnail_url_hd') or video_info.get('thumbnail_url_sd'),
 122             'duration': parse_duration(video_info.get('segmentDur')),
 123             'formats': f4m_formats,
 124         }