[youtube] Fix extraction.

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

diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py
index 095adfc15fb074226a03be575dcba9a406c6f99d..661f9e59d0310a6c6def25e20de33a9cbc65e09f 100644 (file)
--- a/youtube_dl/extractor/slutload.py
+++ b/youtube_dl/extractor/slutload.py
@@ -1,46 +1,65 @@
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+
 
 class SlutloadIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<videoid>[^/]+)/?$'
-    _TEST = {
-        u'url': u'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
-        u'file': u'TD73btpBqSxc.mp4',
-        u'md5': u'0cf531ae8006b530bd9df947a6a0df77',
-        u'info_dict': {
-            u"title": u"virginie baisee en cam",
-            u"age_limit": 18,
-        }
-    }
+    _VALID_URL = r'https?://(?:\w+\.)?slutload\.com/(?:video/[^/]+|embed_player|watch)/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
+        'md5': '868309628ba00fd488cf516a113fd717',
+        'info_dict': {
+            'id': 'TD73btpBqSxc',
+            'ext': 'mp4',
+            'title': 'virginie baisee en cam',
+            'age_limit': 18,
+            'thumbnail': r're:https?://.*?\.jpg'
+        },
+    }, {
+        # mobile site
+        'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.slutload.com/embed_player/TD73btpBqSxc/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.slutload.com/watch/TD73btpBqSxc/Virginie-Baisee-En-Cam.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        video_id = mobj.group('videoid')
-
-        # Get webpage content
-        webpage = self._download_webpage(url, video_id)
-
-        # Get the video title
-        video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
-            webpage, u'title').strip()
+        video_id = self._match_id(url)
 
-        # Get the video url
-        result = re.compile(r'<div id="vidPlayer"\s+data-url="([^"]+)"\s+previewer-file="([^"]+)"', re.S).search(webpage)
-        if result is None:
-            raise ExtractorError(u'ERROR: unable to extract video_url')
+        embed_page = self._download_webpage(
+            'http://www.slutload.com/embed_player/%s' % video_id, video_id,
+            'Downloading embed page', fatal=False)
 
-        video_url, video_thumb = result.group(1,2)
+        if embed_page:
+            def extract(what):
+                return self._html_search_regex(
+                    r'data-video-%s=(["\'])(?P<url>(?:(?!\1).)+)\1' % what,
+                    embed_page, 'video %s' % what, default=None, group='url')
 
-        info = {'id': video_id,
-                'url': video_url,
-                'title': video_title,
-                'thumbnail': video_thumb,
-                'ext': 'mp4',
-                'age_limit': 18}
+            video_url = extract('url')
+            if video_url:
+                title = self._html_search_regex(
+                    r'<title>([^<]+)', embed_page, 'title', default=video_id)
+                return {
+                    'id': video_id,
+                    'url': video_url,
+                    'title': title,
+                    'thumbnail': extract('preview'),
+                    'age_limit': 18
+                }
 
-        return [info]
+        webpage = self._download_webpage(
+            'http://www.slutload.com/video/_/%s/' % video_id, video_id)
+        title = self._html_search_regex(
+            r'<h1><strong>([^<]+)</strong>', webpage, 'title').strip()
+        info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+        info.update({
+            'id': video_id,
+            'title': title,
+            'age_limit': 18,
+        })
+        return info