diff options
| author | Sergey M․ <dstftw@gmail.com> | 2015-02-14 17:42:32 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2015-02-14 17:42:32 +0600 |
| commit | 36f73e8044f3f34c8a0af86f867d4a3e2f5d5ba4 (patch) | |
| tree | cb3c815f51175a293aa2014a0b5d87eea4375bec | |
| parent | cffcbc02de504d84e1c2677bb525c00b03e04f53 (diff) | |
| parent | a4f3d779db13ec3c8bda67e897de8cd849a7f811 (diff) | |
| download | youtube-dl-36f73e8044f3f34c8a0af86f867d4a3e2f5d5ba4.tar.xz | |
Merge branch 'ryandesign-nbc-nightly-news'
| -rw-r--r-- | youtube_dl/extractor/nbc.py | 24 |
1 files changed, 17 insertions, 7 deletions
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index f840f6532..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+))| - (feature/[^/]+/(?P<title>.+))) + _VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/ + (?:video/.+?/(?P<id>\d+)| + (?:feature|nightly-news)/[^/]+/(?P<title>.+)) ''' _TESTS = [ @@ -89,6 +89,16 @@ class NBCNewsIE(InfoExtractor): '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): @@ -107,13 +117,13 @@ class NBCNewsIE(InfoExtractor): '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) bootstrap_json = self._search_regex( - r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json', - flags=re.MULTILINE) - bootstrap = json.loads(bootstrap_json) + r'var\s+(?:bootstrapJson|playlistData)\s*=\s*({.+});?\s*$', + webpage, 'bootstrap json', flags=re.MULTILINE) + bootstrap = self._parse_json(bootstrap_json, video_id) info = bootstrap['results'][0]['video'] mpxid = info['mpxId'] |