X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmetacafe.py;h=858c1c0c31f4c08c3068a62983781129288dc3b8;hb=9e1a5b845586a0a5431fb72467142046d8571e6f;hp=3176ec2301a1ea467a4abd08108067bf62302faf;hpb=be3b8fa30f9b1fdc47a0f37678fec63fcf321c1d;p=youtube-dl

diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 3176ec230..858c1c0c3 100644
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -9,11 +9,12 @@ from ..utils import (
     compat_urllib_request,
     determine_ext,
     ExtractorError,
+    int_or_none,
 )
 
 
 class MetacafeIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+    _VALID_URL = r'http://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
     IE_NAME = 'metacafe'
@@ -21,12 +22,12 @@ class MetacafeIE(InfoExtractor):
         # Youtube video
         {
             'add_ie': ['Youtube'],
-            'url':  'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
+            'url': 'http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/',
             'info_dict': {
                 'id': '_aUehQsCQtM',
                 'ext': 'mp4',
                 'upload_date': '20090102',
-                'title': 'The Electric Company | \"Short I\" | PBS KIDS GO!',
+                'title': 'The Electric Company | "Short I" | PBS KIDS GO!',
                 'description': 'md5:2439a8ef6d5a70e380c22f5ad323e5a8',
                 'uploader': 'PBS',
                 'uploader_id': 'PBS'
@@ -70,23 +71,37 @@ class MetacafeIE(InfoExtractor):
         },
         # cbs video
         {
-            'url': 'http://www.metacafe.com/watch/cb-0rOxMBabDXN6/samsung_galaxy_note_2_samsungs_next_generation_phablet/',
+            'url': 'http://www.metacafe.com/watch/cb-8VD4r_Zws8VP/open_this_is_face_the_nation_february_9/',
             'info_dict': {
-                'id': '0rOxMBabDXN6',
+                'id': '8VD4r_Zws8VP',
                 'ext': 'flv',
-                'title': 'Samsung Galaxy Note 2: Samsung\'s next-generation phablet',
-                'description': 'md5:54d49fac53d26d5a0aaeccd061ada09d',
-                'duration': 129,
+                'title': 'Open: This is Face the Nation, February 9',
+                'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476',
+                'duration': 96,
             },
             'params': {
                 # rtmp download
                 'skip_download': True,
             },
         },
+        # Movieclips.com video
+        {
+            'url': 'http://www.metacafe.com/watch/mv-Wy7ZU/my_week_with_marilyn_do_you_love_me/',
+            'info_dict': {
+                'id': 'mv-Wy7ZU',
+                'ext': 'mp4',
+                'title': 'My Week with Marilyn - Do You Love Me?',
+                'description': 'From the movie My Week with Marilyn - Colin (Eddie Redmayne) professes his love to Marilyn (Michelle Williams) and gets her to promise to return to set and finish the movie.',
+                'uploader': 'movie_trailers',
+                'duration': 176,
+            },
+            'params': {
+                'skip_download': 'requires rtmpdump',
+            }
+        }
     ]
 
     def report_disclaimer(self):
-        """Report disclaimer retrieval."""
         self.to_screen('Retrieving disclaimer')
 
     def _real_initialize(self):
@@ -135,6 +150,7 @@ class MetacafeIE(InfoExtractor):
 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
+        video_url = None
         mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
         if mobj is not None:
             mediaURL = compat_urllib_parse.unquote(mobj.group(1))
@@ -147,16 +163,17 @@ class MetacafeIE(InfoExtractor):
             else:
                 gdaKey = mobj.group(1)
                 video_url = '%s?__gda__=%s' % (mediaURL, gdaKey)
-        else:
+        if video_url is None:
             mobj = re.search(r'<video src="([^"]+)"', webpage)
             if mobj:
                 video_url = mobj.group(1)
                 video_ext = 'mp4'
-            else:
-                mobj = re.search(r' name="flashvars" value="(.*?)"', webpage)
-                if mobj is None:
-                    raise ExtractorError('Unable to extract media URL')
-                vardict = compat_parse_qs(mobj.group(1))
+        if video_url is None:
+            flashvars = self._search_regex(
+                r' name="flashvars" value="(.*?)"', webpage, 'flashvars',
+                default=None)
+            if flashvars:
+                vardict = compat_parse_qs(flashvars)
                 if 'mediaData' not in vardict:
                     raise ExtractorError('Unable to extract media URL')
                 mobj = re.search(
@@ -166,26 +183,68 @@ class MetacafeIE(InfoExtractor):
                 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
                 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
                 video_ext = determine_ext(video_url)
-
-        video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, 'title')
+        if video_url is None:
+            player_url = self._search_regex(
+                r"swfobject\.embedSWF\('([^']+)'",
+                webpage, 'config URL', default=None)
+            if player_url:
+                config_url = self._search_regex(
+                    r'config=(.+)$', player_url, 'config URL')
+                config_doc = self._download_xml(
+                    config_url, video_id,
+                    note='Downloading video config')
+                smil_url = config_doc.find('.//properties').attrib['smil_file']
+                smil_doc = self._download_xml(
+                    smil_url, video_id,
+                    note='Downloading SMIL document')
+                base_url = smil_doc.find('./head/meta').attrib['base']
+                video_url = []
+                for vn in smil_doc.findall('.//video'):
+                    br = int(vn.attrib['system-bitrate'])
+                    play_path = vn.attrib['src']
+                    video_url.append({
+                        'format_id': 'smil-%d' % br,
+                        'url': base_url,
+                        'play_path': play_path,
+                        'page_url': url,
+                        'player_url': player_url,
+                        'ext': play_path.partition(':')[0],
+                    })
+
+        if video_url is None:
+            raise ExtractorError('Unsupported video type')
+
+        video_title = self._html_search_regex(
+            r'(?im)<title>(.*) - Video</title>', webpage, 'title')
         description = self._og_search_description(webpage)
         thumbnail = self._og_search_thumbnail(webpage)
         video_uploader = self._html_search_regex(
-                r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
-                webpage, 'uploader nickname', fatal=False)
-
-        if re.search(r'"contentRating":"restricted"', webpage) is not None:
-            age_limit = 18
+            r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
+            webpage, 'uploader nickname', fatal=False)
+        duration = int_or_none(
+            self._html_search_meta('video:duration', webpage))
+
+        age_limit = (
+            18
+            if re.search(r'"contentRating":"restricted"', webpage)
+            else 0)
+
+        if isinstance(video_url, list):
+            formats = video_url
         else:
-            age_limit = 0
+            formats = [{
+                'url': video_url,
+                'ext': video_ext,
+            }]
 
+        self._sort_formats(formats)
         return {
             'id': video_id,
-            'url': video_url,
             'description': description,
             'uploader': video_uploader,
             'title': video_title,
-            'thumbnail':thumbnail,
-            'ext': video_ext,
+            'thumbnail': thumbnail,
             'age_limit': age_limit,
+            'formats': formats,
+            'duration': duration,
         }