aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2015-02-14 17:42:12 +0600
committerSergey M․ <dstftw@gmail.com>2015-02-14 17:42:12 +0600
commita4f3d779db13ec3c8bda67e897de8cd849a7f811 (patch)
treecb3c815f51175a293aa2014a0b5d87eea4375bec
parentd9aa2b784d914ae99c7d9bbaf83d06f1b9dbd04e (diff)
[nbcnews] Simplify
-rw-r--r--youtube_dl/extractor/nbc.py21
1 files changed, 7 insertions, 14 deletions
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
index 3e3de9e2d..52e8595ea 100644
--- a/youtube_dl/extractor/nbc.py
+++ b/youtube_dl/extractor/nbc.py
@@ -52,9 +52,9 @@ class NBCIE(InfoExtractor):
class NBCNewsIE(InfoExtractor):
- _VALID_URL = r'''(?x)https?://www\.nbcnews\.com/
- ((video/.+?/(?P<id>\d+))|
- ((?P<program>feature|nightly-news)/[^/]+/(?P<title>.+)))
+ _VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/
+ (?:video/.+?/(?P<id>\d+)|
+ (?:feature|nightly-news)/[^/]+/(?P<title>.+))
'''
_TESTS = [
@@ -120,17 +120,10 @@ class NBCNewsIE(InfoExtractor):
# "feature" and "nightly-news" pages use theplatform.com
title = mobj.group('title')
webpage = self._download_webpage(url, title)
- 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)
+ bootstrap_json = self._search_regex(
+ r'var\s+(?:bootstrapJson|playlistData)\s*=\s*({.+});?\s*$',
+ webpage, 'bootstrap json', flags=re.MULTILINE)
+ bootstrap = self._parse_json(bootstrap_json, video_id)
info = bootstrap['results'][0]['video']
mpxid = info['mpxId']