diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2015-02-16 04:09:10 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2015-02-16 04:09:10 +0100 |
commit | 5bfd430f81c885decfb3dc7b5ad8478eefbaaaf7 (patch) | |
tree | fc07260fb86a1f1d844718d48203a5bf9f323f2d /youtube_dl/extractor/nbc.py | |
parent | 73fac4e9119bc53d49e646c38529f1b6d8de734d (diff) | |
parent | 8fb474fb17a64ff2aa9f6315ebbc99ae7938c4e1 (diff) |
Merge remote-tracking branch 'origin/master'
Diffstat (limited to 'youtube_dl/extractor/nbc.py')
-rw-r--r-- | youtube_dl/extractor/nbc.py | 25 |
1 files changed, 17 insertions, 8 deletions
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index f840f6532..89a2845fe 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -1,7 +1,6 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..compat import ( @@ -52,9 +51,9 @@ 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 +88,16 @@ 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 +116,13 @@ 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'] |