[GenericIE] Outsource embedded blip.tv player video id extraction to BlipTVIE and...

[youtube-dl] / youtube_dl / extractor / generic.py

diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index fd32370c2db0c4e3e6c7c6a4039a656e846c64c9..f1b152f623e1b1361a9bbfdb9475f1264969bd3b 100644 (file)
--- 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
@@ -213,7 +222,7 @@ class GenericIE(InfoExtractor):
             self.to_screen(u'Brightcove video detected.')
             return self.url_result(bc_url, 'Brightcove')
 
-        # Look for embedded Vimeo player
+        # Look for embedded (iframe) Vimeo player
         mobj = re.search(
             r'<iframe[^>]+?src="(https?://player.vimeo.com/video/.+?)"', webpage)
         if mobj:
@@ -221,9 +230,18 @@ class GenericIE(InfoExtractor):
             surl = smuggle_url(player_url, {'Referer': url})
             return self.url_result(surl, 'Vimeo')
 
+        # Look for embedded (swf embed) Vimeo player
+        mobj = re.search(
+            r'<embed[^>]+?src="(https?://(?:www\.)?vimeo.com/moogaloop.swf.+?)"', webpage)
+        if mobj:
+            return self.url_result(mobj.group(1), '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]
@@ -253,16 +271,12 @@ class GenericIE(InfoExtractor):
             }
 
         # Look for embedded blip.tv player
-        mobj = re.search(r'<meta\s[^>]*https?://api.blip.tv/\w+/redirect/\w+/(\d+)', webpage)
+        mobj = re.search(r'<meta\s[^>]*https?://api\.blip\.tv/\w+/redirect/\w+/(\d+)', webpage)
         if mobj:
-            return self.url_result('http://blip.tv/seo/-'+mobj.group(1), 'BlipTV')
-        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*https?://(?:\w+\.)?blip.tv/(?:play/|api\.swf#)([a-zA-Z0-9]+)', webpage)
+            return self.url_result('http://blip.tv/a/a-'+mobj.group(1), 'BlipTV')
+        mobj = re.search(r'<(?:iframe|embed|object)\s[^>]*(https?://(?:\w+\.)?blip\.tv/(?:play/|api\.swf#)[a-zA-Z0-9]+)', webpage)
         if mobj:
-            player_url = 'http://blip.tv/play/%s.x?p=1' % mobj.group(1)
-            player_page = self._download_webpage(player_url, mobj.group(1))
-            blip_video_id = self._search_regex(r'data-episode-id="(\d+)', player_page, u'blip_video_id', fatal=False)
-            if blip_video_id:
-                return self.url_result('http://blip.tv/seo/-'+blip_video_id, 'BlipTV')
+            return self.url_result(mobj.group(1), 'BlipTV')
 
         # Look for Bandcamp pages with custom domain
         mobj = re.search(r'<meta property="og:url"[^>]*?content="(.*?bandcamp\.com.*?)"', webpage)
@@ -277,6 +291,16 @@ 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: