From 49807b4ac6aab2db702afbde20215641210e0413 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sat, 16 Aug 2014 13:56:22 +0700 Subject: [PATCH] [yahoo] Add support for embedded videos (Closes #3525) --- youtube_dl/extractor/generic.py | 7 +++++++ youtube_dl/extractor/yahoo.py | 15 +++++++++++++-- 2 files changed, 20 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index bcb0765940..8e915735ea 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -706,6 +706,13 @@ def _real_extract(self, url): url = unescapeHTML(mobj.group('url')) return self.url_result(url, ie='MTVServicesEmbedded') + # Look for embedded yahoo player + mobj = re.search( + r']+?src=(["\'])(?Phttps?://(?:screen|movies)\.yahoo\.com/.+?\.html\?format=embed)\1', + webpage) + if mobj is not None: + return self.url_result(mobj.group('url'), 'Yahoo') + # Start with something easy: JW Player in SWFObject found = re.findall(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if not found: diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index d84be25620..0e3b33b165 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -15,7 +15,7 @@ class YahooIE(InfoExtractor): IE_DESC = 'Yahoo screen and movies' - _VALID_URL = r'https?://(?:screen|movies)\.yahoo\.com/.*?-(?P[0-9]+)(?:-[a-z]+)?\.html' + _VALID_URL = r'(?Phttps?://(?:screen|movies)\.yahoo\.com/.*?-(?P[0-9]+)(?:-[a-z]+)?\.html)' _TESTS = [ { 'url': 'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', @@ -46,12 +46,23 @@ class YahooIE(InfoExtractor): 'title': 'The World Loves Spider-Man', 'description': '''People all over the world are celebrating the release of \"The Amazing Spider-Man 2.\" We're taking a look at the enthusiastic response Spider-Man has received from viewers all over the world.''', } - } + }, + { + 'url': 'https://screen.yahoo.com/community/community-sizzle-reel-203225340.html?format=embed', + 'md5': '60e8ac193d8fb71997caa8fce54c6460', + 'info_dict': { + 'id': '4fe78544-8d48-39d8-97cd-13f205d9fcdb', + 'ext': 'mp4', + 'title': "Yahoo Saves 'Community'", + 'description': 'md5:4d4145af2fd3de00cbb6c1d664105053', + } + }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + url = mobj.group('url') webpage = self._download_webpage(url, video_id) items_json = self._search_regex(