Support NBC Nightly News broadcasts

This commit is contained in:
Ryan Schmidt 2015-02-14 04:10:23 -06:00
parent cffcbc02de
commit d9aa2b784d
1 changed files with 22 additions and 5 deletions

View File

@ -54,7 +54,7 @@ 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>.+))) ((?P<program>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):
@ -107,12 +117,19 @@ 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( program = mobj.group('program')
r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json', if program == 'feature':
flags=re.MULTILINE) bootstrap_json = self._search_regex(
r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json',
flags=re.MULTILINE)
else:
# nightly-news
bootstrap_json = self._search_regex(
r'var playlistData = ({.+});\s*$', webpage, 'playlist data',
flags=re.MULTILINE)
bootstrap = json.loads(bootstrap_json) bootstrap = json.loads(bootstrap_json)
info = bootstrap['results'][0]['video'] info = bootstrap['results'][0]['video']
mpxid = info['mpxId'] mpxid = info['mpxId']