Merge remote-tracking branch 'lenaten/8tracks'
[youtube-dl] / youtube_dl / extractor / videofyme.py
index 94f64ffa5aaba21ec4ca4470d6034352acbf411e..94f9e9be94f9a420fd0207339085cbc35aba6805 100644 (file)
@@ -1,48 +1,50 @@
-import re
-import xml.etree.ElementTree
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from ..utils import (
     find_xpath_attr,
-    determine_ext,
+    int_or_none,
 )
 
+
 class VideofyMeIE(InfoExtractor):
-    _VALID_URL = r'https?://(www.videofy.me/.+?|p.videofy.me/v)/(?P<id>\d+)(&|#|$)'
-    IE_NAME = u'videofy.me'
+    _VALID_URL = r'https?://(?:www\.videofy\.me/.+?|p\.videofy\.me/v)/(?P<id>\d+)(&|#|$)'
+    IE_NAME = 'videofy.me'
 
     _TEST = {
-        u'url': u'http://www.videofy.me/thisisvideofyme/1100701',
-        u'file':  u'1100701.mp4',
-        u'md5': u'c77d700bdc16ae2e9f3c26019bd96143',
-        u'info_dict': {
-            u'title': u'This is VideofyMe',
-            u'description': None,
-            u'uploader': u'VideofyMe',
-            u'uploader_id': u'thisisvideofyme',
+        'url': 'http://www.videofy.me/thisisvideofyme/1100701',
+        'md5': 'c77d700bdc16ae2e9f3c26019bd96143',
+        'info_dict': {
+            'id': '1100701',
+            'ext': 'mp4',
+            'title': 'This is VideofyMe',
+            'description': None,
+            'uploader': 'VideofyMe',
+            'uploader_id': 'thisisvideofyme',
+            'view_count': int,
         },
-        
+
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-        config_xml = self._download_webpage('http://sunshine.videofy.me/?videoId=%s' % video_id,
-                                            video_id)
-        config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
+        video_id = self._match_id(url)
+        config = self._download_xml('http://sunshine.videofy.me/?videoId=%s' % video_id,
+                                    video_id)
         video = config.find('video')
         sources = video.find('sources')
-        url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key) 
-            for key in ['on', 'av', 'off']] if node is not None)
+        url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key)
+                                          for key in ['on', 'av', 'off']] if node is not None)
         video_url = url_node.find('url').text
+        view_count = int_or_none(self._search_regex(
+            r'([0-9]+)', video.find('views').text, 'view count', fatal=False))
 
-        return {'id': video_id,
-                'title': video.find('title').text,
-                'url': video_url,
-                'ext': determine_ext(video_url),
-                'thumbnail': video.find('thumb').text,
-                'description': video.find('description').text,
-                'uploader': config.find('blog/name').text,
-                'uploader_id': video.find('identifier').text,
-                'view_count': re.search(r'\d+', video.find('views').text).group(),
-                }
+        return {
+            'id': video_id,
+            'title': video.find('title').text,
+            'url': video_url,
+            'thumbnail': video.find('thumb').text,
+            'description': video.find('description').text,
+            'uploader': config.find('blog/name').text,
+            'uploader_id': video.find('identifier').text,
+            'view_count': view_count,
+        }