youtube-dl

commit 6be17c08703ad8ec89c6fb62f31f280956694cee
parent 8652770bd23ff5f46c5687d94f71cec08d2c5886
Author: Sergey M․ <dstftw@gmail.com>
Date:   Wed, 17 Aug 2016 05:45:49 +0700

[mofosex] Extract all formats and modernize (Closes #10335)

Diffstat:
M
youtube_dl/extractor/mofosex.py
 | 
87
+++++++++++++++++++++++++++++++++++++++++--------------------------------------

1 file changed, 45 insertions(+), 42 deletions(-)
diff --git a/youtube_dl/extractor/mofosex.py b/youtube_dl/extractor/mofosex.py
@@ -1,53 +1,56 @@
 from __future__ import unicode_literals
 
-import os
-import re
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_unquote,
-    compat_urllib_parse_urlparse,
+from ..utils import (
+    int_or_none,
+    str_to_int,
+    unified_strdate,
 )
-from ..utils import sanitized_Request
+from .keezmovies import KeezMoviesIE
 
 
-class MofosexIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>mofosex\.com/videos/(?P<id>[0-9]+)/.*?\.html)'
-    _TEST = {
-        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
-        'md5': '1b2eb47ac33cc75d4a80e3026b613c5a',
+class MofosexIE(KeezMoviesIE):
+    _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
+    _TESTS = [{
+        'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
+        'md5': '39a15853632b7b2e5679f92f69b78e91',
         'info_dict': {
-            'id': '5018',
+            'id': '318131',
+            'display_id': 'amateur-teen-playing-and-masturbating-318131',
             'ext': 'mp4',
-            'title': 'Japanese Teen Music Video',
+            'title': 'amateur teen playing and masturbating',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20121114',
+            'view_count': int,
+            'like_count': int,
+            'dislike_count': int,
             'age_limit': 18,
         }
-    }
+    }, {
+        # This video is no longer available
+        'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        url = 'http://www.' + mobj.group('url')
-
-        req = sanitized_Request(url)
-        req.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(req, video_id)
-
-        video_title = self._html_search_regex(r'<h1>(.+?)<', webpage, 'title')
-        video_url = compat_urllib_parse_unquote(self._html_search_regex(r'flashvars.video_url = \'([^\']+)', webpage, 'video_url'))
-        path = compat_urllib_parse_urlparse(video_url).path
-        extension = os.path.splitext(path)[1][1:]
-        format = path.split('/')[5].split('_')[:2]
-        format = '-'.join(format)
-
-        age_limit = self._rta_search(webpage)
-
-        return {
-            'id': video_id,
-            'title': video_title,
-            'url': video_url,
-            'ext': extension,
-            'format': format,
-            'format_id': format,
-            'age_limit': age_limit,
-        }
+        webpage, info = self._extract_info(url)
+
+        view_count = str_to_int(self._search_regex(
+            r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
+        like_count = int_or_none(self._search_regex(
+            r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
+            'like count', fatal=False))
+        dislike_count = int_or_none(self._search_regex(
+            r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
+            'like count', fatal=False))
+        upload_date = unified_strdate(self._html_search_regex(
+            r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
+
+        info.update({
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'upload_date': upload_date,
+            'thumbnail': self._og_search_thumbnail(webpage),
+        })
+
+        return info