From d9aa2b784d914ae99c7d9bbaf83d06f1b9dbd04e Mon Sep 17 00:00:00 2001 From: Ryan Schmidt Date: Sat, 14 Feb 2015 04:10:23 -0600 Subject: [PATCH 1/2] Support NBC Nightly News broadcasts --- youtube_dl/extractor/nbc.py | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index f840f6532..3e3de9e2d 100644 --- 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\d+))| - (feature/[^/]+/(?P.+))) + ((?P<program>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): @@ -107,12 +117,19 @@ 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*$', webpage, 'bootstrap json', - flags=re.MULTILINE) + program = mobj.group('program') + if program == 'feature': + bootstrap_json = self._search_regex( + r'var bootstrapJson = ({.+})\s*$', webpage, 'bootstrap json', + flags=re.MULTILINE) + else: + # nightly-news + bootstrap_json = self._search_regex( + r'var playlistData = ({.+});\s*$', webpage, 'playlist data', + flags=re.MULTILINE) bootstrap = json.loads(bootstrap_json) info = bootstrap['results'][0]['video'] mpxid = info['mpxId'] From a4f3d779db13ec3c8bda67e897de8cd849a7f811 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com> Date: Sat, 14 Feb 2015 17:42:12 +0600 Subject: [PATCH 2/2] [nbcnews] Simplify --- youtube_dl/extractor/nbc.py | 21 +++++++-------------- 1 file changed, 7 insertions(+), 14 deletions(-) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 3e3de9e2d..52e8595ea 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -52,9 +52,9 @@ class NBCIE(InfoExtractor): class NBCNewsIE(InfoExtractor): - _VALID_URL = r'''(?x)https?://www\.nbcnews\.com/ - ((video/.+?/(?P<id>\d+))| - ((?P<program>feature|nightly-news)/[^/]+/(?P<title>.+))) + _VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/ + (?:video/.+?/(?P<id>\d+)| + (?:feature|nightly-news)/[^/]+/(?P<title>.+)) ''' _TESTS = [ @@ -120,17 +120,10 @@ class NBCNewsIE(InfoExtractor): # "feature" and "nightly-news" pages use theplatform.com title = mobj.group('title') webpage = self._download_webpage(url, title) - program = mobj.group('program') - if program == 'feature': - bootstrap_json = self._search_regex( - r'var bootstrapJson = ({.+})\s*$', 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']