[slutload] Fix and improve extraction (closes #17001)

diff --git a/youtube_dl/extractor/slutload.py b/youtube_dl/extractor/slutload.py
index 6fc2ff60d2a923f763fc834127eb62b667c542d5..661f9e59d0310a6c6def25e20de33a9cbc65e09f 100644 (file)
--- a/youtube_dl/extractor/slutload.py
+++ b/youtube_dl/extractor/slutload.py
@@ -1,12 +1,10 @@
 from __future__ import unicode_literals
 
-import re
-
 from .common import InfoExtractor
 
 
 class SlutloadIE(InfoExtractor):
-    _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
+    _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',
@@ -16,33 +14,52 @@ class SlutloadIE(InfoExtractor):
             '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):
         video_id = self._match_id(url)
 
-        desktop_url = re.sub(r'^(https?://)mobile\.', r'\1', url)
-        webpage = self._download_webpage(desktop_url, video_id)
+        embed_page = self._download_webpage(
+            'http://www.slutload.com/embed_player/%s' % video_id, video_id,
+            'Downloading embed page', fatal=False)
 
-        video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
-                                              webpage, 'title').strip()
+        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')
 
-        video_url = self._html_search_regex(
-            r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
-            webpage, 'video URL')
-        thumbnail = self._html_search_regex(
-            r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
-            webpage, 'thumbnail', fatal=False)
+            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 {
+        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,
-            'url': video_url,
-            'title': video_title,
-            'thumbnail': thumbnail,
-            'age_limit': 18
-        }
+            'title': title,
+            'age_limit': 18,
+        })
+        return info