Switch codebase to use sanitized_Request instead of

[youtube-dl] / youtube_dl / extractor / tube8.py

diff --git a/youtube_dl/extractor/tube8.py b/youtube_dl/extractor/tube8.py
index d73ad3762a1b455cfd4bc384c27e2dd85e776dde..46ef61ff5cafbac172b975e64be9e86ae5e3de91 100644 (file)
--- a/youtube_dl/extractor/tube8.py
+++ b/youtube_dl/extractor/tube8.py
@@ -4,12 +4,10 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_urllib_parse_urlparse,
-    compat_urllib_request,
-)
+from ..compat import compat_urllib_parse_urlparse
 from ..utils import (
     int_or_none,
+    sanitized_Request,
     str_to_int,
 )
 from ..aes import aes_decrypt_text
@@ -42,12 +40,12 @@ class Tube8IE(InfoExtractor):
         video_id = mobj.group('id')
         display_id = mobj.group('display_id')
 
-        req = compat_urllib_request.Request(url)
+        req = sanitized_Request(url)
         req.add_header('Cookie', 'age_verified=1')
         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:
@@ -58,19 +56,19 @@ class Tube8IE(InfoExtractor):
         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(
-            r'>Description:</strong>(.+?)<', webpage, 'description', fatal=False)
+            r'>Description:</strong>\s*(.+?)\s*<', webpage, 'description', fatal=False)
         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(
-            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(
-            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(
-            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(