github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[nbcnews] Simplify

Browse source
This commit is contained in:
Sergey M․ 2015-02-14 17:42:12 +06:00
parent d9aa2b784d
commit a4f3d779db
1 changed files with 7 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

21
youtube_dl/extractor/nbc.py
View file

@ -52,9 +52,9 @@ def _real_extract(self, url):
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 @@ def _real_extract(self, url):
# "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']