diff options
Diffstat (limited to 'youtube_dl/extractor/generic.py')
| -rw-r--r-- | youtube_dl/extractor/generic.py | 40 |
1 files changed, 31 insertions, 9 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py index fd32370c2..bdb4f58d6 100644 --- a/youtube_dl/extractor/generic.py +++ b/youtube_dl/extractor/generic.py @@ -11,12 +11,14 @@ from ..utils import ( compat_urlparse, ExtractorError, + HEADRequest, smuggle_url, unescapeHTML, unified_strdate, url_basename, ) from .brightcove import BrightcoveIE +from .ooyala import OoyalaIE class GenericIE(InfoExtractor): @@ -83,7 +85,17 @@ class GenericIE(InfoExtractor): u'title': u'trailer', u'upload_date': u'20100513', } - } + }, + # ooyala video + { + u'url': u'http://www.rollingstone.com/music/videos/norwegian-dj-cashmere-cat-goes-spartan-on-with-me-premiere-20131219', + u'md5': u'5644c6ca5d5782c1d0d350dad9bd840c', + u'info_dict': { + u'id': u'BwY2RxaTrTkslxOfcan0UCf0YqyvWysJ', + u'ext': u'mp4', + u'title': u'2cc213299525360.mov', #that's what we get + }, + }, ] def report_download_webpage(self, video_id): @@ -98,21 +110,18 @@ class GenericIE(InfoExtractor): def _send_head(self, url): """Check if it is a redirect, like url shorteners, in case return the new url.""" - class HeadRequest(compat_urllib_request.Request): - def get_method(self): - return "HEAD" class HEADRedirectHandler(compat_urllib_request.HTTPRedirectHandler): """ Subclass the HTTPRedirectHandler to make it use our - HeadRequest also on the redirected URL + HEADRequest also on the redirected URL """ def redirect_request(self, req, fp, code, msg, headers, newurl): if code in (301, 302, 303, 307): newurl = newurl.replace(' ', '%20') newheaders = dict((k,v) for k,v in req.headers.items() if k.lower() not in ("content-length", "content-type")) - return HeadRequest(newurl, + return HEADRequest(newurl, headers=newheaders, origin_req_host=req.get_origin_req_host(), unverifiable=True) @@ -141,7 +150,7 @@ class GenericIE(InfoExtractor): compat_urllib_request.HTTPErrorProcessor, compat_urllib_request.HTTPSHandler]: opener.add_handler(handler()) - response = opener.open(HeadRequest(url)) + response = opener.open(HEADRequest(url)) if response is None: raise ExtractorError(u'Invalid URL protocol') return response @@ -222,8 +231,11 @@ class GenericIE(InfoExtractor): return self.url_result(surl, 'Vimeo') # Look for embedded YouTube player - matches = re.findall( - r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/embed/.+?)\1', webpage) + matches = re.findall(r'''(?x) + (?:<iframe[^>]+?src=|embedSWF\(\s*) + (["\'])(?P<url>(?:https?:)?//(?:www\.)?youtube\.com/ + (?:embed|v)/.+?) + \1''', webpage) if matches: urlrs = [self.url_result(unescapeHTML(tuppl[1]), 'Youtube') for tuppl in matches] @@ -277,6 +289,16 @@ class GenericIE(InfoExtractor): if mobj is not None: return self.url_result(mobj.group('url')) + # Look for Ooyala videos + mobj = re.search(r'player.ooyala.com/[^"?]+\?[^"]*?(?:embedCode|ec)=([^"&]+)', webpage) + if mobj is not None: + return OoyalaIE._build_url_result(mobj.group(1)) + + # Look for Aparat videos + mobj = re.search(r'<iframe src="(http://www.aparat.com/video/[^"]+)"', webpage) + if mobj is not None: + return self.url_result(mobj.group(1), 'Aparat') + # Start with something easy: JW Player in SWFObject mobj = re.search(r'flashvars: [\'"](?:.*&)?file=(http[^\'"&]*)', webpage) if mobj is None: |