youtube-dl

Another place where youtube-dl lives on
git clone git://git.oshgnacknak.de/youtube-dl.git
Log | Files | Refs | README | LICENSE

foxnews.py (5156B)


      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_NAME = 'foxnews'
     11     IE_DESC = 'Fox News and Fox Business Video'
     12     _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
     13     _TESTS = [
     14         {
     15             'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
     16             'md5': '32aaded6ba3ef0d1c04e238d01031e5e',
     17             'info_dict': {
     18                 'id': '3937480',
     19                 'ext': 'flv',
     20                 'title': 'Frozen in Time',
     21                 'description': '16-year-old girl is size of toddler',
     22                 'duration': 265,
     23                 'timestamp': 1304411491,
     24                 'upload_date': '20110503',
     25                 'thumbnail': r're:^https?://.*\.jpg$',
     26             },
     27         },
     28         {
     29             'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips',
     30             'md5': '5846c64a1ea05ec78175421b8323e2df',
     31             'info_dict': {
     32                 'id': '3922535568001',
     33                 'ext': 'mp4',
     34                 'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
     35                 'description': "Congressman discusses president's plan",
     36                 'duration': 292,
     37                 'timestamp': 1417662047,
     38                 'upload_date': '20141204',
     39                 'thumbnail': r're:^https?://.*\.jpg$',
     40             },
     41             'params': {
     42                 # m3u8 download
     43                 'skip_download': True,
     44             },
     45         },
     46         {
     47             'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
     48             'only_matching': True,
     49         },
     50         {
     51             'url': 'http://video.foxbusiness.com/v/4442309889001',
     52             'only_matching': True,
     53         },
     54         {
     55             # From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
     56             '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',
     57             'only_matching': True,
     58         },
     59     ]
     60 
     61     @staticmethod
     62     def _extract_urls(webpage):
     63         return [
     64             mobj.group('url')
     65             for mobj in re.finditer(
     66                 r'<(?:amp-)?iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//video\.foxnews\.com/v/video-embed\.html?.*?\bvideo_id=\d+.*?)\1',
     67                 webpage)]
     68 
     69     def _real_extract(self, url):
     70         host, video_id = re.match(self._VALID_URL, url).groups()
     71 
     72         info = self._extract_feed_info(
     73             'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
     74         info['id'] = video_id
     75         return info
     76 
     77 
     78 class FoxNewsArticleIE(InfoExtractor):
     79     _VALID_URL = r'https?://(?:www\.)?(?:insider\.)?foxnews\.com/(?!v)([^/]+/)+(?P<id>[a-z-]+)'
     80     IE_NAME = 'foxnews:article'
     81 
     82     _TESTS = [{
     83         # data-video-id
     84         'url': 'http://www.foxnews.com/politics/2016/09/08/buzz-about-bud-clinton-camp-denies-claims-wore-earpiece-at-forum.html',
     85         'md5': '83d44e1aff1433e7a29a7b537d1700b5',
     86         'info_dict': {
     87             'id': '5116295019001',
     88             'ext': 'mp4',
     89             'title': 'Trump and Clinton asked to defend positions on Iraq War',
     90             'description': 'Veterans react on \'The Kelly File\'',
     91             'timestamp': 1473301045,
     92             'upload_date': '20160908',
     93         },
     94     }, {
     95         # iframe embed
     96         'url': 'http://www.foxnews.com/us/2018/03/09/parkland-survivor-kyle-kashuv-on-meeting-trump-his-app-to-prevent-another-school-shooting.amp.html?__twitter_impression=true',
     97         'info_dict': {
     98             'id': '5748266721001',
     99             'ext': 'flv',
    100             'title': 'Kyle Kashuv has a positive message for the Trump White House',
    101             'description': 'Marjory Stoneman Douglas student disagrees with classmates.',
    102             'thumbnail': r're:^https?://.*\.jpg$',
    103             'duration': 229,
    104             'timestamp': 1520594670,
    105             'upload_date': '20180309',
    106         },
    107         'params': {
    108             'skip_download': True,
    109         },
    110     }, {
    111         'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
    112         'only_matching': True,
    113     }]
    114 
    115     def _real_extract(self, url):
    116         display_id = self._match_id(url)
    117         webpage = self._download_webpage(url, display_id)
    118 
    119         video_id = self._html_search_regex(
    120             r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
    121             webpage, 'video ID', group='id', default=None)
    122         if video_id:
    123             return self.url_result(
    124                 'http://video.foxnews.com/v/' + video_id, FoxNewsIE.ie_key())
    125 
    126         return self.url_result(
    127             FoxNewsIE._extract_urls(webpage)[0], FoxNewsIE.ie_key())