Merge branch 'lecture2go' of https://github.com/nichdu/youtube-dl into nichdu-lecture2go

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

diff --git a/youtube_dl/extractor/vodlocker.py b/youtube_dl/extractor/vodlocker.py
index dfc570930266891c76fec70b8719943eba6b079a..ccf1928b5d323f277b4e8a47bd4d008e821b147c 100644 (file)
--- a/youtube_dl/extractor/vodlocker.py
+++ b/youtube_dl/extractor/vodlocker.py
@@ -1,18 +1,15 @@
 # -*- coding: utf-8 -*-
 from __future__ import unicode_literals
 
-import re
-import time
 from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_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',
@@ -26,16 +23,10 @@ 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!
@@ -46,7 +37,7 @@ class VodlockerIE(InfoExtractor):
                 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(