[empflix] Add new extractor
authorhojel <hojelei@gmail.com>
Mon, 12 May 2014 11:10:29 +0000 (04:10 -0700)
committerhojel <hojelei@gmail.com>
Mon, 12 May 2014 11:10:29 +0000 (04:10 -0700)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/empflix.py [new file with mode: 0644]

index 9529077c78be25b3de70add73af3a24566ab0a5b..23b7cbd8f27129fb9ddfd08cd675f519f18d1f2f 100644 (file)
@@ -72,6 +72,7 @@ from .ehow import EHowIE
 from .eighttracks import EightTracksIE
 from .eitb import EitbIE
 from .elpais import ElPaisIE
+from .empflix import EmpflixIE
 from .engadget import EngadgetIE
 from .escapist import EscapistIE
 from .everyonesmixtape import EveryonesMixtapeIE
diff --git a/youtube_dl/extractor/empflix.py b/youtube_dl/extractor/empflix.py
new file mode 100644 (file)
index 0000000..e7abbb5
--- /dev/null
@@ -0,0 +1,46 @@
+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,
+        }
+    }
+
+    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]