Merge pull request #7045 from remitamine/ign

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

diff --git a/youtube_dl/extractor/anitube.py b/youtube_dl/extractor/anitube.py
index 2954966a6e6d8d8517e90aa5efa464d85dcfef81..23f942ae2d039cf92c9a67934a07d3062f744b0d 100644 (file)
--- a/youtube_dl/extractor/anitube.py
+++ b/youtube_dl/extractor/anitube.py
@@ -1,21 +1,24 @@
+from __future__ import unicode_literals
+
 import re
-import xml.etree.ElementTree
 
 from .common import InfoExtractor
 
 
 class AnitubeIE(InfoExtractor):
-    IE_NAME = u'anitube.se'
-    _VALID_URL = r'http?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
+    IE_NAME = 'anitube.se'
+    _VALID_URL = r'https?://(?:www\.)?anitube\.se/video/(?P<id>\d+)'
 
     _TEST = {
-        u'url': u'http://www.anitube.se/video/36621',
-        u'md5': u'0c4e4f1051bf50f5982f829f7230f539',
-        u'info_dict': {
-            u'id': u'36621',
-            u'ext': u'mp4',
-            u'title': u'Recorder to Randoseru 01',
+        'url': 'http://www.anitube.se/video/36621',
+        'md5': '59d0eeae28ea0bc8c05e7af429998d43',
+        'info_dict': {
+            'id': '36621',
+            'ext': 'mp4',
+            'title': 'Recorder to Randoseru 01',
+            'duration': 180.19,
         },
+        'skip': 'Blocked in the US',
     }
 
     def _real_extract(self, url):
@@ -23,27 +26,23 @@ class AnitubeIE(InfoExtractor):
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
+        key = self._search_regex(
+            r'src=["\']https?://[^/]+/embed/([A-Za-z0-9_-]+)', webpage, 'key')
 
-        key = self._html_search_regex(r'http://www\.anitube\.se/embed/([A-Za-z0-9_-]*)',
-                                      webpage, u'key')
-
-        webpage_config = self._download_webpage('http://www.anitube.se/nuevo/econfig.php?key=%s' % key,
-                                                key)
-
-        config_xml = xml.etree.ElementTree.fromstring(webpage_config.encode('utf-8'))
+        config_xml = self._download_xml(
+            'http://www.anitube.se/nuevo/econfig.php?key=%s' % key, key)
 
         video_title = config_xml.find('title').text
-
+        thumbnail = config_xml.find('image').text
+        duration = float(config_xml.find('duration').text)
 
         formats = []
-
         video_url = config_xml.find('file')
         if video_url is not None:
             formats.append({
                 'format_id': 'sd',
                 'url': video_url.text,
             })
-
         video_url = config_xml.find('filehd')
         if video_url is not None:
             formats.append({
@@ -54,6 +53,7 @@ class AnitubeIE(InfoExtractor):
         return {
             'id': video_id,
             'title': video_title,
-            'ext': 'mp4',
+            'thumbnail': thumbnail,
+            'duration': duration,
             'formats': formats
         }