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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .amp import AMPIE
   6 from .common import InfoExtractor
   7
   8
   9 class FoxNewsIE(AMPIE):
  10     IE_DESC = 'Fox News and Fox Business Video'
  11     _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
  12     _TESTS = [
  13         {
  14             'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
  15             'md5': '32aaded6ba3ef0d1c04e238d01031e5e',
  16             'info_dict': {
  17                 'id': '3937480',
  18                 'ext': 'flv',
  19                 'title': 'Frozen in Time',
  20                 'description': '16-year-old girl is size of toddler',
  21                 'duration': 265,
  22                 'timestamp': 1304411491,
  23                 'upload_date': '20110503',
  24                 'thumbnail': 're:^https?://.*\.jpg$',
  25             },
  26         },
  27         {
  28             'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips',
  29             'md5': '5846c64a1ea05ec78175421b8323e2df',
  30             'info_dict': {
  31                 'id': '3922535568001',
  32                 'ext': 'mp4',
  33                 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
  34                 'description': "Congressman discusses president's plan",
  35                 'duration': 292,
  36                 'timestamp': 1417662047,
  37                 'upload_date': '20141204',
  38                 'thumbnail': 're:^https?://.*\.jpg$',
  39             },
  40             'params': {
  41                 # m3u8 download
  42                 'skip_download': True,
  43             },
  44         },
  45         {
  46             'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
  47             'only_matching': True,
  48         },
  49         {
  50             'url': 'http://video.foxbusiness.com/v/4442309889001',
  51             'only_matching': True,
  52         },
  53         {
  54             # From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
  55             'url': 'http://video.insider.foxnews.com/v/video-embed.html?video_id=5099377331001&autoplay=true&share_url=http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words&share_title=Student%20Group:%20Saying%20%27Politically%20Correct,%27%20%27Trash%27%20and%20%27Lame%27%20Is%20Offensive&share=true',
  56             'only_matching': True,
  57         },
  58     ]
  59
  60     def _real_extract(self, url):
  61         host, video_id = re.match(self._VALID_URL, url).groups()
  62
  63         info = self._extract_feed_info(
  64             'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
  65         info['id'] = video_id
  66         return info
  67
  68
  69 class FoxNewsInsiderIE(InfoExtractor):
  70     _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
  71     IE_NAME = 'foxnews:insider'
  72
  73     _TEST = {
  74         'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
  75         'md5': 'a10c755e582d28120c62749b4feb4c0c',
  76         'info_dict': {
  77             'id': '5099377331001',
  78             'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words',
  79             'ext': 'mp4',
  80             'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive',
  81             'description': 'Is campus censorship getting out of control?',
  82             'timestamp': 1472168725,
  83             'upload_date': '20160825',
  84             'thumbnail': 're:^https?://.*\.jpg$',
  85         },
  86         'add_ie': [FoxNewsIE.ie_key()],
  87     }
  88
  89     def _real_extract(self, url):
  90         display_id = self._match_id(url)
  91
  92         webpage = self._download_webpage(url, display_id)
  93
  94         embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL')
  95
  96         title = self._og_search_title(webpage)
  97         description = self._og_search_description(webpage)
  98
  99         return {
 100             '_type': 'url_transparent',
 101             'ie_key': FoxNewsIE.ie_key(),
 102             'url': embed_url,
 103             'display_id': display_id,
 104             'title': title,
 105             'description': description,
 106         }