Merge tag 'upstream/2016.06.25'

[youtubedl] / youtube_dl / extractor / twentyfourvideo.py

diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py
index 67e8bfea03476ccf78d2470a973655f2a7213730..4025edf02b4ca5b8c42e3324fb094fe43141ce68 100644 (file)
--- a/youtube_dl/extractor/twentyfourvideo.py
+++ b/youtube_dl/extractor/twentyfourvideo.py
@@ -5,6 +5,8 @@ from .common import InfoExtractor
 from ..utils import (
     parse_iso8601,
     int_or_none,
 from ..utils import (
     parse_iso8601,
     int_or_none,

+    xpath_attr,
+    xpath_element,

 )
 
 
 )
 
 


@@ -15,7 +17,7 @@ class TwentyFourVideoIE(InfoExtractor):
     _TESTS = [
         {
             'url': 'http://www.24video.net/video/view/1044982',
     _TESTS = [
         {
             'url': 'http://www.24video.net/video/view/1044982',

-            'md5': '48dd7646775690a80447a8dca6a2df76',
+            'md5': 'e09fc0901d9eaeedac872f154931deeb',

             'info_dict': {
                 'id': '1044982',
                 'ext': 'mp4',
             'info_dict': {
                 'id': '1044982',
                 'ext': 'mp4',


@@ -45,7 +47,8 @@ class TwentyFourVideoIE(InfoExtractor):
 
         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))
         thumbnail = self._og_search_thumbnail(webpage)
         duration = int_or_none(self._og_search_property(
             'duration', webpage, 'duration', fatal=False))


@@ -54,7 +57,7 @@ class TwentyFourVideoIE(InfoExtractor):
             webpage, 'upload date'))
 
         uploader = self._html_search_regex(
             webpage, 'upload date'))
 
         uploader = self._html_search_regex(

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

             webpage, 'uploader', fatal=False)
 
         view_count = int_or_none(self._html_search_regex(
             webpage, 'uploader', fatal=False)
 
         view_count = int_or_none(self._html_search_regex(


@@ -64,33 +67,24 @@ class TwentyFourVideoIE(InfoExtractor):
             r'<div class="comments-title" id="comments-count">(\d+) комментари',
             webpage, 'comment count', fatal=False))
 
             r'<div class="comments-title" id="comments-count">(\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,
             'http://www.24video.net/video/xml/%s?mode=play' % video_id,

-            video_id, 'Downloading PC video URL').find('.//video')
+            video_id, 'Downloading video XML')

 
 

-        formats.append({
-            'url': pc_video.attrib['url'],
-            'format_id': 'pc',
-            'quality': 1,
-        })
+        video = xpath_element(video_xml, './/video', 'video', fatal=True)

 
 

-        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
+        formats = [{
+            'url': xpath_attr(video, '', 'url', 'video URL', fatal=True),
+        }]

 
 

-        mobile_video = self._download_xml(
-            'http://www.24video.net/video/xml/%s' % video_id,
-            video_id, 'Downloading mobile video URL').find('.//video')
-
-        formats.append({
-            'url': mobile_video.attrib['url'],
-            'format_id': 'mobile',
-            'quality': 0,
-        })
-
-        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,
 
         return {
             'id': video_id,