class CNNIE(InfoExtractor):
- _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
- (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn(-ap)?|(?=&)))'''
+ _VALID_URL = r'''(?x)https?://(?:(?:edition|www)\.)?cnn\.com/video/(?:data/.+?|\?)/
+ (?P<path>.+?/(?P<title>[^/]+?)(?:\.(?:cnn|hln)(?:-ap)?|(?=&)))'''
_TESTS = [{
'url': 'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
'md5': '3e6121ea48df7e2259fe73a0628605c4',
'info_dict': {
- 'id': 'sports_2013_06_09_nadal-1-on-1.cnn',
+ 'id': 'sports/2013/06/09/nadal-1-on-1.cnn',
'ext': 'mp4',
'title': 'Nadal wins 8th French Open title',
'description': 'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"",
"upload_date": "20130821",
}
+ }, {
+ 'url': 'http://www.cnn.com/video/data/2.0/video/living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln.html',
+ 'md5': 'f14d02ebd264df951feb2400e2c25a1b',
+ 'info_dict': {
+ 'id': 'living/2014/12/22/growing-america-nashville-salemtown-board-episode-1.hln',
+ 'ext': 'mp4',
+ 'title': 'Nashville Ep. 1: Hand crafted skateboards',
+ 'description': 'md5:e7223a503315c9f150acac52e76de086',
+ 'upload_date': '20141222',
+ }
}]
def _real_extract(self, url):
'url': cnn_url,
'ie_key': CNNIE.ie_key(),
}
+
+
+class CNNArticleIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:(?:edition|www)\.)?cnn\.com/(?!video/)'
+ _TEST = {
+ 'url': 'http://www.cnn.com/2014/12/21/politics/obama-north-koreas-hack-not-war-but-cyber-vandalism/',
+ 'md5': '275b326f85d80dff7592a9820f5dc887',
+ 'info_dict': {
+ 'id': 'bestoftv/2014/12/21/sotu-crowley-president-obama-north-korea-not-going-to-be-intimidated.cnn',
+ 'ext': 'mp4',
+ 'title': 'Obama: We\'re not going to be intimidated',
+ 'description': 'md5:e735586f3dc936075fa654a4d91b21f9',
+ 'upload_date': '20141220',
+ },
+ 'add_ie': ['CNN'],
+ }
+
+ def _real_extract(self, url):
+ webpage = self._download_webpage(url, url_basename(url))
+ cnn_url = self._html_search_regex(r"video:\s*'([^']+)'", webpage, 'cnn url')
+ return {
+ '_type': 'url',
+ 'url': 'http://cnn.com/video/?/video/' + cnn_url,
+ 'ie_key': CNNIE.ie_key(),
+ }