]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/tube8.py
debian/control: Prefer mplayer to mplayer2 in Recommends.
[youtubedl] / youtube_dl / extractor / tube8.py
index 64a1e903022a78fa3a2b15eeff5eed20afce568d..c9cb69333f7da0a9f4fe009e79b06433bca83726 100644 (file)
@@ -4,9 +4,11 @@ import json
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
+)
+from ..utils import (
     int_or_none,
     str_to_int,
 )
     int_or_none,
     str_to_int,
 )
@@ -45,7 +47,7 @@ class Tube8IE(InfoExtractor):
         webpage = self._download_webpage(req, display_id)
 
         flashvars = json.loads(self._html_search_regex(
         webpage = self._download_webpage(req, display_id)
 
         flashvars = json.loads(self._html_search_regex(
-            r'var flashvars\s*=\s*({.+?})', webpage, 'flashvars'))
+            r'flashvars\s*=\s*({.+?});\r?\n', webpage, 'flashvars'))
 
         video_url = flashvars['video_url']
         if flashvars.get('encrypted') is True:
 
         video_url = flashvars['video_url']
         if flashvars.get('encrypted') is True:
@@ -56,19 +58,19 @@ class Tube8IE(InfoExtractor):
         thumbnail = flashvars.get('image_url')
 
         title = self._html_search_regex(
         thumbnail = flashvars.get('image_url')
 
         title = self._html_search_regex(
-            r'videotitle\s*=\s*"([^"]+)', webpage, 'title')
+            r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
         description = self._html_search_regex(
         description = self._html_search_regex(
-            r'>Description:</strong>(.+?)<', webpage, 'description', fatal=False)
+            r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
         uploader = self._html_search_regex(
         uploader = self._html_search_regex(
-            r'<strong class="video-username">(?:<a href="[^"]+">)?([^<]+)(?:</a>)?</strong>',
+            r'<span class="username">\s*(.+?)\s*<',
             webpage, 'uploader', fatal=False)
 
         like_count = int_or_none(self._html_search_regex(
             webpage, 'uploader', fatal=False)
 
         like_count = int_or_none(self._html_search_regex(
-            r"rupVar\s*=\s*'(\d+)'", webpage, 'like count', fatal=False))
+            r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
         dislike_count = int_or_none(self._html_search_regex(
         dislike_count = int_or_none(self._html_search_regex(
-            r"rdownVar\s*=\s*'(\d+)'", webpage, 'dislike count', fatal=False))
+            r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
         view_count = self._html_search_regex(
         view_count = self._html_search_regex(
-            r'<strong>Views: </strong>([\d,\.]+)</li>', webpage, 'view count', fatal=False)
+            r'<strong>Views: </strong>([\d,\.]+)\s*</li>', webpage, 'view count', fatal=False)
         if view_count:
             view_count = str_to_int(view_count)
         comment_count = self._html_search_regex(
         if view_count:
             view_count = str_to_int(view_count)
         comment_count = self._html_search_regex(