From: marcwebbie <marcwebbie@gmail.com>
Date: Sun, 8 Jun 2014 02:09:45 +0000 (-0300)
Subject: [GorillaVid] Added GorillaVid extractor
X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=617c0b2239f565d512a175d7fce4b5a6b3835b4c;p=youtube-dl

[GorillaVid] Added GorillaVid extractor
---

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 15a42ce44..6c9a7593a 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -109,6 +109,7 @@ from .gdcvault import GDCVaultIE
 from .generic import GenericIE
 from .googleplus import GooglePlusIE
 from .googlesearch import GoogleSearchIE
+from .gorillavid import GorillaVidIE
 from .hark import HarkIE
 from .helsinki import HelsinkiIE
 from .hentaistigma import HentaiStigmaIE
diff --git a/youtube_dl/extractor/gorillavid.py b/youtube_dl/extractor/gorillavid.py
new file mode 100644
index 000000000..bdf6e30c2
--- /dev/null
+++ b/youtube_dl/extractor/gorillavid.py
@@ -0,0 +1,38 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+class GorillaVidIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www.)?gorillavid.in/(?:embed-)?(?P<id>\w+)(?:\-\d+x\d+)?.html'
+    _TEST = {
+        'url': "http://gorillavid.in/kdk7i5r1p5ye.html",
+        'md5': '5a01b05ed3da82a10c6659e954b80108',
+        'info_dict': {
+            'id': 'kdk7i5r1p5ye',
+            'ext': 'flv',
+            'title': 'Full House 1x16 - But Seriously, Folks.avi',
+        }
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_regex(r"name=['\"]fname['\"]\s+value=['\"](.*?)['\"]", webpage, u"video title")
+
+        # download embed page again with cookies to get url
+        embed_url = "http://gorillavid.in/embed-{0}-960x480.html".format(video_id)
+        webpage = self._download_webpage(embed_url, video_id, note=u'Downloading webpage again (with cookie)')
+        url = self._html_search_regex(r'file:\s+["\'](http://.*?video.\w{3})["\']', webpage, url)
+
+        info_dict = {
+            'id': video_id,
+            'title': title,
+            'url': url,
+        }
+
+        return info_dict