X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/415fdb62500dca2e22067a05008dfbf87c75b662..aebf9c8f14c9f5d45f8c6aa523ee135fdfd421b2:/youtube_dl/extractor/metacafe.py

diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 6436c05..67d6271 100644
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -3,12 +3,16 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_parse_qs,
     compat_urllib_parse,
-    compat_urllib_request,
+    compat_urllib_parse_unquote,
+)
+from ..utils import (
     determine_ext,
     ExtractorError,
+    int_or_none,
+    sanitized_Request,
 )
 
 
@@ -21,7 +25,7 @@ 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',
@@ -83,6 +87,21 @@ class MetacafeIE(InfoExtractor):
                 '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):
@@ -98,7 +117,7 @@ class MetacafeIE(InfoExtractor):
             'filters': '0',
             'submit': "Continue - I'm over 18",
         }
-        request = compat_urllib_request.Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
+        request = sanitized_Request(self._FILTER_POST, compat_urllib_parse.urlencode(disclaimer_form))
         request.add_header('Content-Type', 'application/x-www-form-urlencoded')
         self.report_age_confirmation()
         self._download_webpage(request, None, False, 'Unable to confirm age')
@@ -123,7 +142,7 @@ class MetacafeIE(InfoExtractor):
                 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 
         # Retrieve video webpage to extract further information
-        req = compat_urllib_request.Request('http://www.metacafe.com/watch/%s/' % video_id)
+        req = sanitized_Request('http://www.metacafe.com/watch/%s/' % video_id)
 
         # AnyClip videos require the flashversion cookie so that we get the link
         # to the mp4 file
@@ -134,10 +153,11 @@ class MetacafeIE(InfoExtractor):
 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
-        mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+        video_url = None
+        mobj = re.search(r'(?m)&(?:media|video)URL=([^&]+)', webpage)
         if mobj is not None:
-            mediaURL = compat_urllib_parse.unquote(mobj.group(1))
-            video_ext = mediaURL[-3:]
+            mediaURL = compat_urllib_parse_unquote(mobj.group(1))
+            video_ext = determine_ext(mediaURL)
 
             # Extract gdaKey if available
             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)
@@ -146,16 +166,17 @@ 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(
@@ -165,26 +186,68 @@ 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":|"rating",)"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,
         }