import re
from .amp import AMPIE
+from .common import InfoExtractor
class FoxNewsIE(AMPIE):
IE_DESC = 'Fox News and Fox Business Video'
- _VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
+ _VALID_URL = r'https?://(?P<host>video\.(?:insider\.)?fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_TESTS = [
{
'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
'url': 'http://video.foxbusiness.com/v/4442309889001',
'only_matching': True,
},
+ {
+ # From http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words
+ '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',
+ 'only_matching': True,
+ },
]
def _real_extract(self, url):
'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
info['id'] = video_id
return info
+
+
+class FoxNewsInsiderIE(InfoExtractor):
+ _VALID_URL = r'https?://insider\.foxnews\.com/([^/]+/)+(?P<id>[a-z-]+)'
+ IE_NAME = 'foxnews:insider'
+
+ _TEST = {
+ 'url': 'http://insider.foxnews.com/2016/08/25/univ-wisconsin-student-group-pushing-silence-certain-words',
+ 'md5': 'a10c755e582d28120c62749b4feb4c0c',
+ 'info_dict': {
+ 'id': '5099377331001',
+ 'display_id': 'univ-wisconsin-student-group-pushing-silence-certain-words',
+ 'ext': 'mp4',
+ 'title': 'Student Group: Saying \'Politically Correct,\' \'Trash\' and \'Lame\' Is Offensive',
+ 'description': 'Is campus censorship getting out of control?',
+ 'timestamp': 1472168725,
+ 'upload_date': '20160825',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ },
+ 'add_ie': [FoxNewsIE.ie_key()],
+ }
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, display_id)
+
+ embed_url = self._html_search_meta('embedUrl', webpage, 'embed URL')
+
+ title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage)
+
+ return {
+ '_type': 'url_transparent',
+ 'ie_key': FoxNewsIE.ie_key(),
+ 'url': embed_url,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': description,
+ }