debian/control: Update list of supported sites/extractors.

[youtubedl] / youtube_dl / extractor / spankbang.py

diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py
index 7f060b15b69908a71ff45a44f13e92ab0089ff5b..67500b69c1b8b076f147c5da3afb3df8cc5bd6fd 100644 (file)
--- a/youtube_dl/extractor/spankbang.py
+++ b/youtube_dl/extractor/spankbang.py
@@ -3,11 +3,17 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

+from ..utils import (
+    ExtractorError,
+    parse_duration,
+    parse_resolution,
+    str_to_int,
+)

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


@@ -15,37 +21,65 @@ class SpankBangIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'fantasy solo',
             'description': 'dillion harper masturbates on a bed',
             'ext': 'mp4',
             'title': 'fantasy solo',
             'description': 'dillion harper masturbates on a bed',

-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',

             '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,
+    }, {
+        # 4k
+        'url': 'https://spankbang.com/1vwqx/video/jade+kush+solo+4k',
+        'only_matching': True,
+    }]

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

-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(url, video_id, headers={
+            'Cookie': 'country=US'
+        })

 
 

-        stream_key = self._html_search_regex(
-            r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
-            webpage, 'stream key')
+        if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
+            raise ExtractorError(
+                'Video %s is not available' % video_id, expected=True)

 
 

-        formats = [{
-            'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
-            'ext': 'mp4',
-            'format_id': '%sp' % height,
-            'height': int(height),
-        } for height in re.findall(r'<span[^>]+q_(\d+)p', webpage)]
+        formats = []
+        for mobj in re.finditer(
+                r'stream_url_(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
+                webpage):
+            format_id, format_url = mobj.group('id', 'url')
+            f = parse_resolution(format_id)
+            f.update({
+                'url': format_url,
+                'format_id': format_id,
+            })
+            formats.append(f)

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

-            r'(?s)<h1>(.+?)</h1>', webpage, 'title')
+            r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')

         description = self._search_regex(
         description = self._search_regex(

-            r'class="desc"[^>]*>([^<]+)',
-            webpage, 'description', default=None)
+            r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
+            webpage, 'description', fatal=False)

         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)
+        duration = parse_duration(self._search_regex(
+            r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
+            webpage, 'duration', fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))

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


@@ -55,6 +89,8 @@ class SpankBangIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,
             'description': description,
             'thumbnail': thumbnail,
             'uploader': uploader,

+            'duration': duration,
+            'view_count': view_count,

             'formats': formats,
             'age_limit': age_limit,
         }
             'formats': formats,
             'age_limit': age_limit,
         }