debian/changelog: Annotate the log with bugs to close.

[youtubedl] / youtube_dl / extractor / twentyfourvideo.py

diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py
index e03e2dbaa42f23a5107a50c67e7c12d9f378600b..4b3b3e705eb8f758afb466970ed50b8e2ee102fd 100644 (file)
--- a/youtube_dl/extractor/twentyfourvideo.py
+++ b/youtube_dl/extractor/twentyfourvideo.py
@@ -1,6 +1,8 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 

+import re
+

 from .common import InfoExtractor
 from ..utils import (
     parse_iso8601,
 from .common import InfoExtractor
 from ..utils import (
     parse_iso8601,


@@ -12,48 +14,54 @@ from ..utils import (
 
 class TwentyFourVideoIE(InfoExtractor):
     IE_NAME = '24video'
 
 class TwentyFourVideoIE(InfoExtractor):
     IE_NAME = '24video'

-    _VALID_URL = r'https?://(?:www\.)?24video\.net/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
-
-    _TESTS = [
-        {
-            'url': 'http://www.24video.net/video/view/1044982',
-            'md5': 'e09fc0901d9eaeedac872f154931deeb',
-            'info_dict': {
-                'id': '1044982',
-                'ext': 'mp4',
-                'title': 'Эротика каменного века',
-                'description': 'Как смотрели порно в каменном веке.',
-                'thumbnail': 're:^https?://.*\.jpg$',
-                'uploader': 'SUPERTELO',
-                'duration': 31,
-                'timestamp': 1275937857,
-                'upload_date': '20100607',
-                'age_limit': 18,
-                'like_count': int,
-                'dislike_count': int,
-            },
+    _VALID_URL = r'https?://(?P<host>(?:www\.)?24video\.(?:net|me|xxx|sexy?|tube|adult))/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.24video.net/video/view/1044982',
+        'md5': 'e09fc0901d9eaeedac872f154931deeb',
+        'info_dict': {
+            'id': '1044982',
+            'ext': 'mp4',
+            'title': 'Эротика каменного века',
+            'description': 'Как смотрели порно в каменном веке.',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'uploader': 'SUPERTELO',
+            'duration': 31,
+            'timestamp': 1275937857,
+            'upload_date': '20100607',
+            'age_limit': 18,
+            'like_count': int,
+            'dislike_count': int,

         },
         },

-        {
-            'url': 'http://www.24video.net/player/new24_play.swf?id=1044982',
-            'only_matching': True,
-        }
-    ]
+    }, {
+        'url': 'http://www.24video.net/player/new24_play.swf?id=1044982',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.24video.me/video/view/1044982',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.24video.tube/video/view/2363750',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
 
     def _real_extract(self, url):

-        video_id = self._match_id(url)
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        host = mobj.group('host')

 
         webpage = self._download_webpage(
 
         webpage = self._download_webpage(

-            'http://www.24video.net/video/view/%s' % video_id, video_id)
+            'http://%s/video/view/%s' % (host, video_id), video_id)

 
         title = self._og_search_title(webpage)
         description = self._html_search_regex(
 
         title = self._og_search_title(webpage)
         description = self._html_search_regex(

-            r'<span itemprop="description">([^<]+)</span>', webpage, 'description', fatal=False)
+            r'<(p|span)[^>]+itemprop="description"[^>]*>(?P<description>[^<]+)</\1>',
+            webpage, 'description', fatal=False, group='description')

         thumbnail = self._og_search_thumbnail(webpage)
         duration = int_or_none(self._og_search_property(
             'duration', webpage, 'duration', fatal=False))
         timestamp = parse_iso8601(self._search_regex(
         thumbnail = self._og_search_thumbnail(webpage)
         duration = int_or_none(self._og_search_property(
             'duration', webpage, 'duration', fatal=False))
         timestamp = parse_iso8601(self._search_regex(

-            r'<time id="video-timeago" datetime="([^"]+)" itemprop="uploadDate">',
-            webpage, 'upload date'))
+            r'<time[^>]+\bdatetime="([^"]+)"[^>]+itemprop="uploadDate"',
+            webpage, 'upload date', fatal=False))

 
         uploader = self._html_search_regex(
             r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
 
         uploader = self._html_search_regex(
             r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',


@@ -63,16 +71,16 @@ class TwentyFourVideoIE(InfoExtractor):
             r'<span class="video-views">(\d+) просмотр',
             webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(
             r'<span class="video-views">(\d+) просмотр',
             webpage, 'view count', fatal=False))
         comment_count = int_or_none(self._html_search_regex(

-            r'<div class="comments-title" id="comments-count">(\d+) комментари',
-            webpage, 'comment count', fatal=False))
+            r'<a[^>]+href="#tab-comments"[^>]*>(\d+) комментари',
+            webpage, 'comment count', default=None))

 
         # Sets some cookies
         self._download_xml(
 
         # Sets some cookies
         self._download_xml(

-            r'http://www.24video.net/video/xml/%s?mode=init' % video_id,
+            r'http://%s/video/xml/%s?mode=init' % (host, video_id),

             video_id, 'Downloading init XML')
 
         video_xml = self._download_xml(
             video_id, 'Downloading init XML')
 
         video_xml = self._download_xml(

-            'http://www.24video.net/video/xml/%s?mode=play' % video_id,
+            'http://%s/video/xml/%s?mode=play' % (host, video_id),

             video_id, 'Downloading video XML')
 
         video = xpath_element(video_xml, './/video', 'video', fatal=True)
             video_id, 'Downloading video XML')
 
         video = xpath_element(video_xml, './/video', 'video', fatal=True)