Fix "invalid escape sequences" error on Python 3.6
[youtube-dl] / youtube_dl / extractor / twentyfourvideo.py
index c1ee1decc433627ffa52196d44f7563b46d309cc..1093a382945ba4a54e4b56499b90e61f03de1ceb 100644 (file)
@@ -5,37 +5,39 @@ from .common import InfoExtractor
 from ..utils import (
     parse_iso8601,
     int_or_none,
+    xpath_attr,
+    xpath_element,
 )
 
 
 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': 'd041af8b5b4246ea466226a0d6693345',
-            'info_dict': {
-                'id': '1044982',
-                'ext': 'mp4',
-                'title': 'Эротика каменного века',
-                'description': 'Как смотрели порно в каменном веке.',
-                'thumbnail': 're:^https?://.*\.jpg$',
-                'uploader': 'SUPERTELO',
-                'duration': 31,
-                'timestamp': 1275937857,
-                'upload_date': '20100607',
-                'age_limit': 18,
-                'like_count': int,
-                'dislike_count': int,
-            },
+    _VALID_URL = r'https?://(?:www\.)?24video\.(?:net|me|xxx)/(?:video/(?:view|xml)/|player/new24_play\.swf\?id=)(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.24video.net/video/view/1044982',
+        'md5': 'e09fc0901d9eaeedac872f154931deeb',
+        'info_dict': {
+            'id': '1044982',
+            'ext': 'mp4',
+            'title': 'Эротика каменного века',
+            'description': 'Как смотрели порно в каменном веке.',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            '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,
+    }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -45,7 +47,8 @@ class TwentyFourVideoIE(InfoExtractor):
 
         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))
@@ -61,36 +64,27 @@ 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'<div class="comments-title" id="comments-count">(\d+) комментари',
+            r'<a[^>]+href="#tab-comments"[^>]*>(\d+) комментари',
             webpage, 'comment count', fatal=False))
 
-        formats = []
+        # Sets some cookies
+        self._download_xml(
+            r'http://www.24video.net/video/xml/%s?mode=init' % video_id,
+            video_id, 'Downloading init XML')
 
-        pc_video = self._download_xml(
+        video_xml = self._download_xml(
             'http://www.24video.net/video/xml/%s?mode=play' % video_id,
-            video_id, 'Downloading PC video URL').find('.//video')
-
-        formats.append({
-            'url': pc_video.attrib['url'],
-            'format_id': 'pc',
-            'quality': 1,
-        })
-
-        like_count = int_or_none(pc_video.get('ratingPlus'))
-        dislike_count = int_or_none(pc_video.get('ratingMinus'))
-        age_limit = 18 if pc_video.get('adult') == 'true' else 0
+            video_id, 'Downloading video XML')
 
-        mobile_video = self._download_xml(
-            'http://www.24video.net/video/xml/%s' % video_id,
-            video_id, 'Downloading mobile video URL').find('.//video')
+        video = xpath_element(video_xml, './/video', 'video', fatal=True)
 
-        formats.append({
-            'url': mobile_video.attrib['url'],
-            'format_id': 'mobile',
-            'quality': 0,
-        })
+        formats = [{
+            'url': xpath_attr(video, '', 'url', 'video URL', fatal=True),
+        }]
 
-        self._sort_formats(formats)
+        like_count = int_or_none(video.get('ratingPlus'))
+        dislike_count = int_or_none(video.get('ratingMinus'))
+        age_limit = 18 if video.get('adult') == 'true' else 0
 
         return {
             'id': video_id,