[vgtv] Add new extractor

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

diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py
index e7abbb5d676675b28e4ff19e4cd18c821c077627..e6952588fbdfa08167935fc2b1c0381804328943 100644 (file)
--- a/youtube_dl/extractor/empflix.py
+++ b/youtube_dl/extractor/empflix.py
@@ -1,46 +1,54 @@
+from __future__ import unicode_literals
+
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
+
 
 class EmpflixIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<videoid>[^\.]+)\.html'
+    _VALID_URL = r'^https?://www\.empflix\.com/videos/.*?-(?P<id>[0-9]+)\.html'
     _TEST = {
-        u'url': u'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
-        u'file': u'Amateur-Finger-Fuck-33051.flv',
-        u'md5': u'5e5cc160f38ca9857f318eb97146e13e',
-        u'info_dict': {
-            u"title": u"Amateur Finger Fuck",
-            u"age_limit": 18,
+        'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
+        'md5': 'b1bc15b6412d33902d6e5952035fcabc',
+        'info_dict': {
+            'id': '33051',
+            'ext': 'mp4',
+            'title': 'Amateur Finger Fuck',
+            'description': 'Amateur solo finger fucking.',
+            'age_limit': 18,
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
 
-        video_id = mobj.group('videoid')
-
-        # Get webpage content
         webpage = self._download_webpage(url, video_id)
-
         age_limit = self._rta_search(webpage)
 
-        # Get the video title
-        video_title = self._html_search_regex(r'name="title" value="(?P<title>[^"]*)"',
-            webpage, u'title').strip()
-
-        cfg_url = self._html_search_regex(r'flashvars\.config = escape\("([^"]+)"',
-            webpage, u'flashvars.config').strip()
-
-        cfg_xml = self._download_xml(cfg_url, video_id, note=u'Downloading metadata')
-        video_url = cfg_xml.find('videoLink').text
-
-        info = {'id': video_id,
-                'url': video_url,
-                'title': video_title,
-                'ext': 'flv',
-                'age_limit': age_limit}
-
-        return [info]
+        video_title = self._html_search_regex(
+            r'name="title" value="(?P<title>[^"]*)"', webpage, 'title')
+        video_description = self._html_search_regex(
+            r'name="description" value="([^"]*)"', webpage, 'description', fatal=False)
+
+        cfg_url = self._html_search_regex(
+            r'flashvars\.config = escape\("([^"]+)"',
+            webpage, 'flashvars.config')
+
+        cfg_xml = self._download_xml(
+            cfg_url, video_id, note='Downloading metadata')
+
+        formats = [
+            {
+                'url': item.find('videoLink').text,
+                'format_id': item.find('res').text,
+            } for item in cfg_xml.findall('./quality/item')
+        ]
+
+        return {
+            'id': video_id,
+            'title': video_title,
+            'description': video_description,
+            'formats': formats,
+            'age_limit': age_limit,
+        }