diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-11-30 00:42:56 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-11-30 00:42:56 +0100 |
commit | b138de72f2f0fc197fe46154bcaeceddb5713e7f (patch) | |
tree | 3dcfa594e769513916ca7bf5de574d58e19a459b /youtube_dl/extractor | |
parent | 06dcbb71d8e19947eb6e71390a6a0640abe3dad0 (diff) | |
parent | c5171c454b4392f7276b7f9e94c25d7f1ad60375 (diff) | |
download | youtube-dl-b138de72f2f0fc197fe46154bcaeceddb5713e7f.tar.xz |
Merge branch 'master' of github.com:rg3/youtube-dl
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/__init__.py | 6 | ||||
-rw-r--r-- | youtube_dl/extractor/imdb.py | 3 | ||||
-rw-r--r-- | youtube_dl/extractor/yahoo.py | 46 |
3 files changed, 41 insertions, 14 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index fd890e251..664639b53 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -172,7 +172,11 @@ from .xhamster import XHamsterIE from .xnxx import XNXXIE from .xvideos import XVideosIE from .xtube import XTubeIE -from .yahoo import YahooIE, YahooSearchIE +from .yahoo import ( + YahooIE, + YahooNewsIE, + YahooSearchIE, +) from .youjizz import YouJizzIE from .youku import YoukuIE from .youporn import YouPornIE diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index 520edc7d0..d8e9712a7 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -46,8 +46,7 @@ class ImdbIE(InfoExtractor): formats.append({ 'format_id': f_id, 'url': format_info['url'], - 'height': format_info['height'], - 'width': format_info['width'], + 'height': int(info['titleObject']['encoding']['selected'][:-1]), }) return { diff --git a/youtube_dl/extractor/yahoo.py b/youtube_dl/extractor/yahoo.py index 617e3bb06..e457c4707 100644 --- a/youtube_dl/extractor/yahoo.py +++ b/youtube_dl/extractor/yahoo.py @@ -17,27 +17,21 @@ class YahooIE(InfoExtractor): _TESTS = [ { u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html', - u'file': u'214727115.flv', + u'file': u'214727115.mp4', + u'md5': u'4962b075c08be8690a922ee026d05e69', u'info_dict': { u'title': u'Julian Smith & Travis Legg Watch Julian Smith', u'description': u'Julian and Travis watch Julian Smith', }, - u'params': { - # Requires rtmpdump - u'skip_download': True, - }, }, { u'url': u'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html', - u'file': u'103000935.flv', + u'file': u'103000935.mp4', + u'md5': u'd6e6fc6e1313c608f316ddad7b82b306', u'info_dict': { u'title': u'Codefellas - The Cougar Lies with Spanish Moss', u'description': u'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?', }, - u'params': { - # Requires rtmpdump - u'skip_download': True, - }, }, ] @@ -53,8 +47,12 @@ class YahooIE(InfoExtractor): # The 'meta' field is not always in the video webpage, we request it # from another page long_id = info['id'] + return self._get_info(info['id'], video_id) + + def _get_info(self, long_id, video_id): query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"' - ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2"' % long_id) + ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"' + ' AND protocol="http"' % long_id) data = compat_urllib_parse.urlencode({ 'q': query, 'env': 'prod', @@ -100,6 +98,32 @@ class YahooIE(InfoExtractor): } +class YahooNewsIE(YahooIE): + IE_NAME = 'yahoo:news' + _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html' + + _TEST = { + u'url': u'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html', + u'md5': u'67010fdf3a08d290e060a4dd96baa07b', + u'info_dict': { + u'id': u'104538833', + u'ext': u'mp4', + u'title': u'China Moses Is Crazy About the Blues', + u'description': u'md5:9900ab8cd5808175c7b3fe55b979bed0', + }, + } + + # Overwrite YahooIE properties we don't want + _TESTS = [] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + webpage = self._download_webpage(url, video_id) + long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, u'long id') + return self._get_info(long_id, video_id) + + class YahooSearchIE(SearchInfoExtractor): IE_DESC = u'Yahoo screen search' _MAX_RESULTS = 1000 |