Moved packaging to salsa.debian.org

[youtubedl] / youtube_dl / extractor / spankbang.py

diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py
index 7f060b15b69908a71ff45a44f13e92ab0089ff5b..e6c2dcfc438b758bf43080799817fb8f6a3e2075 100644 (file)
--- a/youtube_dl/extractor/spankbang.py
+++ b/youtube_dl/extractor/spankbang.py
@@ -3,28 +3,45 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..utils import ExtractorError

 
 
 class SpankBangIE(InfoExtractor):
 
 
 class SpankBangIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
-    _TEST = {
+    _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
+    _TESTS = [{

         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
         'md5': '1cc433e1d6aa14bc376535b8679302f7',
         'info_dict': {
             'id': '3vvn',
             'ext': 'mp4',
             'title': 'fantasy solo',
         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
         'md5': '1cc433e1d6aa14bc376535b8679302f7',
         'info_dict': {
             'id': '3vvn',
             'ext': 'mp4',
             'title': 'fantasy solo',

-            'description': 'dillion harper masturbates on a bed',
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'description': 'Watch fantasy solo free HD porn video - 05 minutes -  Babe,Masturbation,Solo,Toy  - dillion harper masturbates on a bed free adult movies sexy clips.',
+            'thumbnail': r're:^https?://.*\.jpg$',

             'uploader': 'silly2587',
             'age_limit': 18,
         }
             'uploader': 'silly2587',
             'age_limit': 18,
         }

-    }
+    }, {
+        # 480p only
+        'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
+        'only_matching': True,
+    }, {
+        # no uploader
+        'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
+        'only_matching': True,
+    }, {
+        # mobile page
+        'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 

+        if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
+            raise ExtractorError(
+                'Video %s is not available' % video_id, expected=True)
+

         stream_key = self._html_search_regex(
             r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
             webpage, 'stream key')
         stream_key = self._html_search_regex(
             r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
             webpage, 'stream key')


@@ -34,18 +51,17 @@ class SpankBangIE(InfoExtractor):
             'ext': 'mp4',
             'format_id': '%sp' % height,
             'height': int(height),
             'ext': 'mp4',
             'format_id': '%sp' % height,
             'height': int(height),

-        } for height in re.findall(r'<span[^>]+q_(\d+)p', webpage)]
+        } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
+        self._check_formats(formats, video_id)

         self._sort_formats(formats)
 
         title = self._html_search_regex(
         self._sort_formats(formats)
 
         title = self._html_search_regex(

-            r'(?s)<h1>(.+?)</h1>', webpage, 'title')
-        description = self._search_regex(
-            r'class="desc"[^>]*>([^<]+)',
-            webpage, 'description', default=None)
+            r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
+        description = self._og_search_description(webpage)

         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._search_regex(
         thumbnail = self._og_search_thumbnail(webpage)
         uploader = self._search_regex(

-            r'class="user"[^>]*>([^<]+)',
-            webpage, 'uploader', fatal=False)
+            r'class="user"[^>]*><img[^>]+>([^<]+)',
+            webpage, 'uploader', default=None)

 
         age_limit = self._rta_search(webpage)
 
 
         age_limit = self._rta_search(webpage)