From a2a4d5fa313d5244d24fa70d5db91971a7583d79 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Tue, 31 Mar 2015 02:47:18 +0800 Subject: [PATCH] [Yahoo/NBCSports] Generalize NBC sports info extractor --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/nbc.py | 31 ++++++++++++++++++++++++++++++- youtube_dl/extractor/yahoo.py | 10 ++++++---- 3 files changed, 37 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 5d0d2a9bc..b113aaec6 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -310,6 +310,7 @@ from .nba import NBAIE from .nbc import ( NBCIE, + NBCSportsVPlayerIE, NBCSportsIE, NBCNewsIE, ) diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py index 033bf71f0..c8dd72ab4 100644 --- a/youtube_dl/extractor/nbc.py +++ b/youtube_dl/extractor/nbc.py @@ -50,7 +50,7 @@ def _real_extract(self, url): return self.url_result(theplatform_url) -class NBCSportsIE(InfoExtractor): +class NBCSportsVPlayerIE(InfoExtractor): _VALID_URL = r'https?://vplayer\.nbcsports\.com/(?:[^/]+/)+(?P[0-9a-zA-Z]+)' _TEST = { @@ -64,6 +64,13 @@ class NBCSportsIE(InfoExtractor): } } + @staticmethod + def _extract_url(webpage): + iframe_m = re.search( + r']+src="(?Phttps?://vplayer\.nbcsports\.com/[^"]+)"', webpage) + if iframe_m: + return iframe_m.group('url') + def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) @@ -71,6 +78,28 @@ def _real_extract(self, url): return self.url_result(theplatform_url, 'ThePlatform') +class NBCSportsIE(InfoExtractor): + # Does not include https becuase its certificate is invalid + _VALID_URL = r'http://www\.nbcsports\.com//?(?:[^/]+/)+(?P[0-9a-z-]+)' + + _TEST = { + 'url': 'http://www.nbcsports.com//college-basketball/ncaab/tom-izzo-michigan-st-has-so-much-respect-duke', + 'md5': 'ba6c93f96b67bf05344f78bd523dac0f', + 'info_dict': { + 'id': 'PHJSaFWbrTY9', + 'ext': 'flv', + 'title': 'Tom Izzo, Michigan St. has \'so much respect\' for Duke', + 'description': 'md5:ecb459c9d59e0766ac9c7d5d0eda8113', + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) + return self.url_result( + NBCSportsVPlayerIE._extract_url(webpage), 'NBCSportsVPlayer') + + class NBCNewsIE(InfoExtractor): _VALID_URL = r'''(?x)https?://(?:www\.)?nbcnews\.com/ (?:video/.+?/(?P\d+)| diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 6e72f1e55..43776d1e6 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -17,6 +17,8 @@ int_or_none, ) +from .nbc import NBCSportsVPlayerIE + class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' @@ -132,6 +134,7 @@ class YahooIE(InfoExtractor): }, { 'note': 'NBC Sports embeds', 'url': 'http://sports.yahoo.com/blogs/ncaab-the-dagger/tyler-kalinoski-s-buzzer-beater-caps-davidson-s-comeback-win-185609842.html?guid=nbc_cbk_davidsonbuzzerbeater_150313', + 'md5': 'ceae8dced5c14a1c1ffcb7a32194cca5', 'info_dict': { 'id': '9CsDKds0kvHI', 'ext': 'flv', @@ -161,10 +164,9 @@ def _real_extract(self, url): video_id = items[0]['id'] return self._get_info(video_id, display_id, webpage) # Look for NBCSports iframes - iframe_m = re.search( - r']+src="(?Phttps?://vplayer\.nbcsports\.com/[^"]+)"', webpage) - if iframe_m: - return self.url_result(iframe_m.group('url'), 'NBCSports') + nbc_sports_url = NBCSportsVPlayerIE._extract_url(webpage) + if nbc_sports_url: + return self.url_result(nbc_sports_url, 'NBCSportsVPlayer') items_json = self._search_regex( r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,