X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/71050031bb901b19a829cc44763bf68e67b1f648..7b550e005da7fd498cfbf1b7c04b05e5540eb6fc:/youtube_dl/extractor/metacafe.py

diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 91480ba..28f59f6 100644
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -1,132 +1,175 @@
+from __future__ import unicode_literals
+
 import re
-import socket
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_http_client,
+from ..compat import (
     compat_parse_qs,
-    compat_urllib_error,
-    compat_urllib_parse,
-    compat_urllib_request,
-    compat_str,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_urlencode,
+)
+from ..utils import (
     determine_ext,
     ExtractorError,
+    int_or_none,
+    get_element_by_attribute,
+    mimetype2ext,
 )
 
-class MetacafeIE(InfoExtractor):
-    """Information Extractor for metacafe.com."""
 
-    _VALID_URL = r'(?:http://)?(?:www\.)?metacafe\.com/watch/([^/]+)/([^/]+)/.*'
+class MetacafeIE(InfoExtractor):
+    _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 = u'metacafe'
+    IE_NAME = 'metacafe'
     _TESTS = [
-    # Youtube video
-    {
-        u"add_ie": ["Youtube"],
-        u"url":  u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
-        u"file":  u"_aUehQsCQtM.mp4",
-        u"info_dict": {
-            u"upload_date": u"20090102",
-            u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!",
-            u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8",
-            u"uploader": u"PBS",
-            u"uploader_id": u"PBS"
-        }
-    },
-    # Normal metacafe video
-    {
-        u'url': u'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
-        u'md5': u'6e0bca200eaad2552e6915ed6fd4d9ad',
-        u'info_dict': {
-            u'id': u'11121940',
-            u'ext': u'mp4',
-            u'title': u'News: Stuff You Won\'t Do with Your PlayStation 4',
-            u'uploader': u'ign',
-            u'description': u'Sony released a massive FAQ on the PlayStation Blog detailing the PS4\'s capabilities and limitations.',
+        # Youtube video
+        {
+            'add_ie': ['Youtube'],
+            '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!',
+                'description': 'md5:2439a8ef6d5a70e380c22f5ad323e5a8',
+                'uploader': 'PBS',
+                'uploader_id': 'PBS'
+            }
+        },
+        # Normal metacafe video
+        {
+            'url': 'http://www.metacafe.com/watch/11121940/news_stuff_you_wont_do_with_your_playstation_4/',
+            'md5': '6e0bca200eaad2552e6915ed6fd4d9ad',
+            'info_dict': {
+                'id': '11121940',
+                'ext': 'mp4',
+                'title': 'News: Stuff You Won\'t Do with Your PlayStation 4',
+                '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
-    {
-        u"url": u"http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/",
-        u"file": u"an-dVVXnuY7Jh77J.mp4",
-        u"info_dict": {
-            u"title": u"The Andromeda Strain (1971): Stop the Bomb Part 3",
-            u"uploader": u"anyclip",
-            u"description": u"md5:38c711dd98f5bb87acf973d573442e67",
+        # AnyClip video
+        {
+            'url': 'http://www.metacafe.com/watch/an-dVVXnuY7Jh77J/the_andromeda_strain_1971_stop_the_bomb_part_3/',
+            'info_dict': {
+                'id': 'an-dVVXnuY7Jh77J',
+                'ext': 'mp4',
+                'title': 'The Andromeda Strain (1971): Stop the Bomb Part 3',
+                'uploader': 'AnyClip',
+                'description': 'md5:cbef0460d31e3807f6feb4e7a5952e5b',
+            },
         },
-    },
-    # age-restricted video
-    {
-        u'url': u'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
-        u'md5': u'98dde7c1a35d02178e8ab7560fe8bd09',
-        u'info_dict': {
-            u'id': u'5186653',
-            u'ext': u'mp4',
-            u'title': u'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
-            u'uploader': u'Dwayne Pipe',
-            u'description': u'md5:950bf4c581e2c059911fa3ffbe377e4b',
-            u'age_limit': 18,
+        # age-restricted video
+        {
+            'url': 'http://www.metacafe.com/watch/5186653/bbc_internal_christmas_tape_79_uncensored_outtakes_etc/',
+            'md5': '98dde7c1a35d02178e8ab7560fe8bd09',
+            'info_dict': {
+                'id': '5186653',
+                'ext': 'mp4',
+                'title': 'BBC INTERNAL Christmas Tape \'79 - UNCENSORED Outtakes, Etc.',
+                'uploader': 'Dwayne Pipe',
+                'description': 'md5:950bf4c581e2c059911fa3ffbe377e4b',
+                'age_limit': 18,
+            },
         },
-    },
+        # cbs video
+        {
+            'url': 'http://www.metacafe.com/watch/cb-8VD4r_Zws8VP/open_this_is_face_the_nation_february_9/',
+            'info_dict': {
+                'id': '8VD4r_Zws8VP',
+                'ext': 'flv',
+                '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
+                '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(u'Retrieving disclaimer')
-
-    def _real_initialize(self):
-        # Retrieve disclaimer
-        request = compat_urllib_request.Request(self._DISCLAIMER)
-        try:
-            self.report_disclaimer()
-            compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to retrieve disclaimer: %s' % compat_str(err))
-
-        # 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')
-        try:
-            self.report_age_confirmation()
-            compat_urllib_request.urlopen(request).read()
-        except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
-            raise ExtractorError(u'Unable to confirm age: %s' % compat_str(err))
+        self.to_screen('Retrieving disclaimer')
 
     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(u'Invalid URL: %s' % url)
+        video_id, display_id = re.match(self._VALID_URL, url).groups()
 
-        video_id = mobj.group(1)
+        # the video may come from an external site
+        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 prefix == 'yt':
+                return self.url_result('http://www.youtube.com/watch?v=%s' % ext_id, 'Youtube')
+            # CBS videos use theplatform.com
+            if prefix == 'cb':
+                return self.url_result('theplatform:%s' % ext_id, 'ThePlatform')
 
-        # Check if video comes from YouTube
-        mobj2 = re.match(r'^yt-(.*)$', video_id)
-        if mobj2 is not None:
-            return [self.url_result('http://www.youtube.com/watch?v=%s' % mobj2.group(1), 'Youtube')]
-
-        # 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_urlencode({'ffilter': False})
+        }
 
         # 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)
-        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)
@@ -135,44 +178,109 @@ 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(u'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(u'Unable to extract media URL')
-                mobj = re.search(r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
+                    raise ExtractorError('Unable to extract media URL')
+                mobj = re.search(
+                    r'"mediaURL":"(?P<mediaURL>http.*?)",(.*?)"key":"(?P<key>.*?)"', vardict['mediaData'][0])
                 if mobj is None:
-                    raise ExtractorError(u'Unable to extract media URL')
+                    raise ExtractorError('Unable to extract media URL')
                 mediaURL = mobj.group('mediaURL').replace('\\/', '/')
                 video_url = '%s?__gda__=%s' % (mediaURL, mobj.group('key'))
                 video_ext = determine_ext(video_url)
+        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:
+            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')
 
-        video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
-        description = self._og_search_description(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, u'uploader nickname', fatal=False)
+            r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
+            webpage, 'uploader nickname', fatal=False)
+        duration = int_or_none(
+            self._html_search_meta('video:duration', webpage, default=None))
+        age_limit = (
+            18
+            if re.search(r'(?:"contentRating":|"rating",)"restricted"', webpage)
+            else 0)
 
-        if re.search(r'"contentRating":"restricted"', webpage) is not None:
-            age_limit = 18
+        if isinstance(video_url, list):
+            formats = video_url
         else:
-            age_limit = 0
+            formats = [{
+                'url': video_url,
+                'ext': video_ext,
+            }]
+        self._sort_formats(formats)
 
         return {
-            '_type':    'video',
-            'id':       video_id,
-            'url':      video_url,
+            'id': video_id,
+            'display_id': display_id,
             'description': description,
             'uploader': video_uploader,
-            'upload_date':  None,
-            'title':    video_title,
-            'ext':      video_ext,
+            'title': video_title,
+            'thumbnail': thumbnail,
             'age_limit': age_limit,
+            'formats': formats,
+            'duration': duration,
         }