d/rules: Run offline tests.

[youtubedl] / youtube_dl / extractor / metacafe.py

diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 8bc333b0277e27e6fd8f3d4f11b3c9c7eabdd7d7..9e92416d1d804cfd7d0569d20c26f591655adf09 100644 (file)
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -1,22 +1,25 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import json

 import re
 
 from .common import InfoExtractor
 from ..compat import (
     compat_parse_qs,
     compat_urllib_parse,
 import re
 
 from .common import InfoExtractor
 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,
 )
 from ..utils import (
     determine_ext,
     ExtractorError,
     int_or_none,

+    get_element_by_attribute,
+    mimetype2ext,

 )
 
 
 class MetacafeIE(InfoExtractor):
 )
 
 
 class MetacafeIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+    _VALID_URL = r'https?://(?:www\.)?metacafe\.com/watch/(?P<video_id>[^/]+)/(?P<display_id>[^/?#]+)'

     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
     IE_NAME = 'metacafe'
     _DISCLAIMER = 'http://www.metacafe.com/family_filter/'
     _FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
     IE_NAME = 'metacafe'


@@ -46,6 +49,22 @@ class MetacafeIE(InfoExtractor):
                 'uploader': 'ign',
                 'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
             },
                 'uploader': 'ign',
                 'description': 'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
             },

+            'skip': 'Page is temporarily unavailable.',
+        },
+        # metacafe video with family filter
+        {
+            'url': 'http://www.metacafe.com/watch/2155630/adult_art_by_david_hart_156/',
+            'md5': 'b06082c5079bbdcde677a6291fbdf376',
+            'info_dict': {
+                'id': '2155630',
+                'ext': 'mp4',
+                'title': 'Adult Art By David Hart 156',
+                'uploader': '63346',
+                'description': 'md5:9afac8fc885252201ad14563694040fc',
+            },
+            'params': {
+                'skip_download': True,
+            },

         },
         # AnyClip video
         {
         },
         # AnyClip video
         {


@@ -54,8 +73,8 @@ class MetacafeIE(InfoExtractor):
                 'id': 'an-dVVXnuY7Jh77J',
                 'ext': 'mp4',
                 'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
                 'id': 'an-dVVXnuY7Jh77J',
                 'ext': 'mp4',
                 'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',

-                'uploader': 'anyclip',
-                'description': 'md5:38c711dd98f5bb87acf973d573442e67',
+                'uploader': 'AnyClip',
+                'description': 'md5:cbef0460d31e3807f6feb4e7a5952e5b',

             },
         },
         # age-restricted video
             },
         },
         # age-restricted video


@@ -80,6 +99,9 @@ class MetacafeIE(InfoExtractor):
                 'title': 'Open: This is Face the Nation, February 9',
                 'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476',
                 'duration': 96,
                 'title': 'Open: This is Face the Nation, February 9',
                 'description': 'md5:8a9ceec26d1f7ed6eab610834cc1a476',
                 'duration': 96,

+                'uploader': 'CBSI-NEW',
+                'upload_date': '20140209',
+                'timestamp': 1391959800,

             },
             'params': {
                 # rtmp download
             },
             'params': {
                 # rtmp download


@@ -106,31 +128,12 @@ class MetacafeIE(InfoExtractor):
     def report_disclaimer(self):
         self.to_screen('Retrieving disclaimer')
 
     def report_disclaimer(self):
         self.to_screen('Retrieving disclaimer')
 

-    def _real_initialize(self):
-        # Retrieve disclaimer
-        self.report_disclaimer()
-        self._download_webpage(self._DISCLAIMER, None, False, 'Unable to retrieve disclaimer')
-
-        # Confirm age
-        disclaimer_form = {
-            'filters': '0',
-            'submit': "Continue - I'm over 18",
-        }
-        request = compat_urllib_request.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')
-

     def _real_extract(self, url):
         # Extract id and simplified title from URL
     def _real_extract(self, url):
         # Extract id and simplified title from URL

-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError('Invalid URL: %s' % url)
-
-        video_id = mobj.group(1)
+        video_id, display_id = re.match(self._VALID_URL, url).groups()

 
         # the video may come from an external site
 
         # the video may come from an external site

-        m_external = re.match('^(\w{2})-(.*)$', video_id)
+        m_external = re.match(r'^(\w{2})-(.*)$', video_id)

         if m_external is not None:
             prefix, ext_id = m_external.groups()
             # Check if video comes from YouTube
         if m_external is not None:
             prefix, ext_id = m_external.groups()
             # Check if video comes from YouTube


@@ -140,23 +143,34 @@ class MetacafeIE(InfoExtractor):
             if prefix == 'cb':
                 return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 
             if prefix == 'cb':
                 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)
+        headers = {
+            # Disable family filter
+            'Cookie': 'user=%s; ' % compat_urllib_parse.quote(json.dumps({'ffilter': False}))
+        }

 
         # AnyClip videos require the flashversion cookie so that we get the link
         # to the mp4 file
 
         # AnyClip videos require the flashversion cookie so that we get the link
         # to the mp4 file

-        mobj_an = re.match(r'^an-(.*?)$', video_id)
-        if mobj_an:
-            req.headers['Cookie'] = 'flashVersion=0;'
-        webpage = self._download_webpage(req, video_id)
+        if video_id.startswith('an-'):
+            headers['Cookie'] += 'flashVersion=0; '
+
+        # Retrieve video webpage to extract further information
+        webpage = self._download_webpage(url, video_id, headers=headers)
+
+        error = get_element_by_attribute(
+            'class', 'notfound-page-title', webpage)
+        if error:
+            raise ExtractorError(error, expected=True)
+
+        video_title = self._html_search_meta(
+            ['og:title', 'twitter:title'], webpage, 'title', default=None) or self._search_regex(r'<h1>(.*?)</h1>', webpage, 'title')

 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
         video_url = None
 
         # Extract URL, uploader and title from webpage
         self.report_extraction(video_id)
         video_url = None

-        mobj = re.search(r'(?m)&mediaURL=([^&]+)', webpage)
+        mobj = re.search(r'(?m)&(?:media|video)URL=([^&]+)', webpage)

         if mobj is not None:
         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)
 
             # Extract gdaKey if available
             mobj = re.search(r'(?m)&gdaKey=(.*?)&', webpage)


@@ -212,23 +226,43 @@ class MetacafeIE(InfoExtractor):
                         'player_url': player_url,
                         'ext': play_path.partition(':')[0],
                     })
                         'player_url': player_url,
                         'ext': play_path.partition(':')[0],
                     })

+        if video_url is None:
+            flashvars = self._parse_json(self._search_regex(
+                r'flashvars\s*=\s*({.*});', webpage, 'flashvars',
+                default=None), video_id, fatal=False)
+            if flashvars:
+                video_url = []
+                for source in flashvars.get('sources'):
+                    source_url = source.get('src')
+                    if not source_url:
+                        continue
+                    ext = mimetype2ext(source.get('type')) or determine_ext(source_url)
+                    if ext == 'm3u8':
+                        video_url.extend(self._extract_m3u8_formats(
+                            source_url, video_id, 'mp4',
+                            'm3u8_native', m3u8_id='hls', fatal=False))
+                    else:
+                        video_url.append({
+                            'url': source_url,
+                            'ext': ext,
+                        })

 
         if video_url is None:
             raise ExtractorError('Unsupported video type')
 
 
         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)
+        description = self._html_search_meta(
+            ['og:description', 'twitter:description', 'description'],
+            webpage, 'title', fatal=False)
+        thumbnail = self._html_search_meta(
+            ['og:image', 'twitter:image'], webpage, 'title', fatal=False)

         video_uploader = self._html_search_regex(
             r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
             webpage, 'uploader nickname', fatal=False)
         duration = int_or_none(
         video_uploader = self._html_search_regex(
             r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
             webpage, 'uploader nickname', fatal=False)
         duration = int_or_none(

-            self._html_search_meta('video:duration', webpage))
-
+            self._html_search_meta('video:duration', webpage, default=None))

         age_limit = (
             18
         age_limit = (
             18

-            if re.search(r'"contentRating":"restricted"', webpage)
+            if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage)

             else 0)
 
         if isinstance(video_url, list):
             else 0)
 
         if isinstance(video_url, list):


@@ -238,10 +272,11 @@ class MetacafeIE(InfoExtractor):
                 'url': video_url,
                 'ext': video_ext,
             }]
                 'url': video_url,
                 'ext': video_ext,
             }]

-

         self._sort_formats(formats)
         self._sort_formats(formats)

+

         return {
             'id': video_id,
         return {
             'id': video_id,

+            'display_id': display_id,

             'description': description,
             'uploader': video_uploader,
             'title': video_title,
             'description': description,
             'uploader': video_uploader,
             'title': video_title,