projects
/
youtube-dl
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
cffcbc0
)
Support NBC Nightly News broadcasts
author
Ryan Schmidt
<github@ryandesign.com>
Sat, 14 Feb 2015 10:10:23 +0000
(
04:10
-0600)
committer
Ryan Schmidt
<github@ryandesign.com>
Sat, 14 Feb 2015 10:10:23 +0000
(
04:10
-0600)
youtube_dl/extractor/nbc.py
patch
|
blob
|
history
diff --git
a/youtube_dl/extractor/nbc.py
b/youtube_dl/extractor/nbc.py
index f840f65321997078859ab5f74682969ec4499359..3e3de9e2d8c7ffea00415bfd378df43ca1d33135 100644
(file)
--- a/
youtube_dl/extractor/nbc.py
+++ b/
youtube_dl/extractor/nbc.py
@@
-54,7
+54,7
@@
class NBCIE(InfoExtractor):
class NBCNewsIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://www\.nbcnews\.com/
((video/.+?/(?P<id>\d+))|
class NBCNewsIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://www\.nbcnews\.com/
((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,
}
else:
'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
}
else:
- # "feature" pages use theplatform.com
+ # "feature"
and "nightly-news"
pages use theplatform.com
title = mobj.group('title')
webpage = self._download_webpage(url, title)
title = mobj.group('title')
webpage = self._download_webpage(url, title)
- bootstrap_json = self._search_regex(
- r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json',
- flags=re.MULTILINE)
+ program = mobj.group('program')
+ if program == 'feature':
+ bootstrap_json = self._search_regex(
+ r'var bootstrapJson = ({.+})\s*$', 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)
info = bootstrap['results'][0]['video']
mpxid = info['mpxId']
bootstrap = json.loads(bootstrap_json)
info = bootstrap['results'][0]['video']
mpxid = info['mpxId']