Merge branch 'karrierevideos' of https://github.com/misterhat/youtube-dl into misterh...

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

diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py
index e7abbb5d676675b28e4ff19e4cd18c821c077627..9a5a8f4bb44039e6c52968801033a3d12a73d835 100644 (file)
--- a/youtube_dl/extractor/empflix.py
+++ b/youtube_dl/extractor/empflix.py
@@ -1,46 +1,31 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-)
-
-class EmpflixIE(InfoExtractor):
-    _VALID_URL = r'^https?://www\.empflix\.com/videos/(?P<videoid>[^\.]+)\.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,
+from __future__ import unicode_literals
+
+from .tnaflix import TNAFlixIE
+
+
+class EMPFlixIE(TNAFlixIE):
+    _VALID_URL = r'https?://(?:www\.)?empflix\.com/videos/(?P<display_id>.+?)-(?P<id>[0-9]+)\.html'
+
+    _TITLE_REGEX = r'name="title" value="(?P<title>[^"]*)"'
+    _DESCRIPTION_REGEX = r'name="description" value="([^"]*)"'
+    _CONFIG_REGEX = r'flashvars\.config\s*=\s*escape\("([^"]+)"'
+
+    _TESTS = [
+        {
+            'url': 'http://www.empflix.com/videos/Amateur-Finger-Fuck-33051.html',
+            'md5': 'b1bc15b6412d33902d6e5952035fcabc',
+            'info_dict': {
+                'id': '33051',
+                'display_id': 'Amateur-Finger-Fuck',
+                'ext': 'mp4',
+                'title': 'Amateur Finger Fuck',
+                'description': 'Amateur solo finger fucking.',
+                'thumbnail': 're:https?://.*\.jpg$',
+                'age_limit': 18,
+            }
+        },
+        {
+            'url': 'http://www.empflix.com/videos/[AROMA][ARMD-718]-Aoi-Yoshino-Sawa-25826.html',
+            'matching_only': True,
         }
-    }
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-
-        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]
+    ]