|
|
@ -52,9 +52,9 @@ class NBCIE(InfoExtractor):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class NBCNewsIE(InfoExtractor):
|
|
|
|
class NBCNewsIE(InfoExtractor):
|
|
|
|
_VALID_URL = r'''(?x)https?://www\.nbcnews\.com/
|
|
|
|
_VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/
|
|
|
|
((video/.+?/(?P<id>\d+))|
|
|
|
|
(?:video/.+?/(?P<id>\d+)|
|
|
|
|
(feature/[^/]+/(?P<title>.+)))
|
|
|
|
(?:feature|nightly-news)/[^/]+/(?P<title>.+))
|
|
|
|
'''
|
|
|
|
'''
|
|
|
|
|
|
|
|
|
|
|
|
_TESTS = [
|
|
|
|
_TESTS = [
|
|
|
@ -89,6 +89,16 @@ class NBCNewsIE(InfoExtractor):
|
|
|
|
'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
|
|
|
|
'description': 'md5:757988edbaae9d7be1d585eb5d55cc04',
|
|
|
|
},
|
|
|
|
},
|
|
|
|
},
|
|
|
|
},
|
|
|
|
|
|
|
|
{
|
|
|
|
|
|
|
|
'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
|
|
|
|
|
|
|
|
'md5': 'b5dda8cddd8650baa0dcb616dd2cf60d',
|
|
|
|
|
|
|
|
'info_dict': {
|
|
|
|
|
|
|
|
'id': 'sekXqyTVnmN3',
|
|
|
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
|
|
|
'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
|
|
|
|
|
|
|
|
'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
|
|
|
|
|
|
|
|
},
|
|
|
|
|
|
|
|
},
|
|
|
|
]
|
|
|
|
]
|
|
|
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
def _real_extract(self, url):
|
|
|
@ -107,13 +117,13 @@ class NBCNewsIE(InfoExtractor):
|
|
|
|
'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
|
|
|
|
'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
|
|
|
|
}
|
|
|
|
}
|
|
|
|
else:
|
|
|
|
else:
|
|
|
|
# "feature" pages use theplatform.com
|
|
|
|
# "feature" and "nightly-news" pages use theplatform.com
|
|
|
|
title = mobj.group('title')
|
|
|
|
title = mobj.group('title')
|
|
|
|
webpage = self._download_webpage(url, title)
|
|
|
|
webpage = self._download_webpage(url, title)
|
|
|
|
bootstrap_json = self._search_regex(
|
|
|
|
bootstrap_json = self._search_regex(
|
|
|
|
r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json',
|
|
|
|
r'var\s+(?:bootstrapJson|playlistData)\s*=\s*({.+});?\s*$',
|
|
|
|
flags=re.MULTILINE)
|
|
|
|
webpage, 'bootstrap json', flags=re.MULTILINE)
|
|
|
|
bootstrap = json.loads(bootstrap_json)
|
|
|
|
bootstrap = self._parse_json(bootstrap_json, video_id)
|
|
|
|
info = bootstrap['results'][0]['video']
|
|
|
|
info = bootstrap['results'][0]['video']
|
|
|
|
mpxid = info['mpxId']
|
|
|
|
mpxid = info['mpxId']
|
|
|
|
|
|
|
|
|
|
|
|