Switch codebase to use sanitized_Request instead of

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

diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py
index 68c59364bc7f48e453b85e70ecc750b4418f0a75..be0a2780f5299571ee134ac47e17eda6476673ac 100644 (file)
--- a/youtube_dl/extractor/vodlocker.py
+++ b/youtube_dl/extractor/vodlocker.py
@@ -1,16 +1,13 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
-    compat_urllib_request,
-)
+from ..compat import compat_urllib_parse
+from ..utils import sanitized_Request
 
 
 class VodlockerIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?vodlocker.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
+    _VALID_URL = r'https?://(?:www\.)?vodlocker\.com/(?P<id>[0-9a-zA-Z]+)(?:\..*?)?'
 
     _TESTS = [{
         'url': 'http://vodlocker.com/e8wvyzz4sl42',
@@ -24,27 +21,21 @@ class VodlockerIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
-        fields = dict(re.findall(r'''(?x)<input\s+
-            type="hidden"\s+
-            name="([^"]+)"\s+
-            (?:id="[^"]+"\s+)?
-            value="([^"]*)"
-            ''', webpage))
+        fields = self._hidden_inputs(webpage)
 
         if fields['op'] == 'download1':
             self._sleep(3, video_id)  # they do detect when requests happen too fast!
             post = compat_urllib_parse.urlencode(fields)
-            req = compat_urllib_request.Request(url, post)
+            req = sanitized_Request(url, post)
             req.add_header('Content-type', 'application/x-www-form-urlencoded')
             webpage = self._download_webpage(
                 req, video_id, 'Downloading video page')
 
         title = self._search_regex(
-            r'id="file_title".*?>\s*(.*?)\s*<span', webpage, 'title')
+            r'id="file_title".*?>\s*(.*?)\s*<(?:br|span)', webpage, 'title')
         thumbnail = self._search_regex(
             r'image:\s*"(http[^\"]+)",', webpage, 'thumbnail')
         url = self._search_regex(