homemoviestube extractor in working state

youtube_dl/extractor/homemoviestube.py

@@ -1,38 +1,39 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 
 
 class HomeMoviesTubeIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?homemoviestube\.com/watch/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?homemoviestube\.com/videos/(?P<id>[0-9]+)/(?P<display_id>[^/]+)\.html'
     _TEST = {
-        'url': 'https://homemoviestube.com/watch/42',
-        'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
+        'url': 'https://www.homemoviestube.com/videos/314747/creamed-again.html',
+        'md5': 'a1f827520d82c0b70da391a8aed410c9',
         'info_dict': {
-            'id': '42',
+            'id': '314747',
+            'display_id': 'creamed-again',
             'ext': 'mp4',
-            'title': 'Video title goes here',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            # TODO more properties, either as:
-            # * A value
-            # * MD5 checksum; start the string with md5:
-            # * A regular expression; start the string with re:
-            # * Any Python type (for example int or float)
+            'title': 'Creamed again',
         }
     }
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        mobj = re.match(self._VALID_URL, url)
+        display_id = mobj.group('display_id')
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, display_id)
+
+        video_url = self._html_search_regex(
+            r'<source src="(.+?)"', webpage, 'video URL')
 
-        # TODO more code goes here, for example ...
         title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': title,
-            'description': self._og_search_description(webpage),
-            'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
-            # TODO more properties (see youtube_dl/extractor/common.py)
+            'url': video_url,
         }