youtube-dl

commit 25e9953c6f28521b474e32c4269ebd7b00afca08
parent f9df094ca51db94ee63d138f3fe8f2d226f30655
Author: pulpe <Pulpan3@gmail.com>
Date:   Tue, 17 Jun 2014 15:14:18 +0200

Merge pull request #3059 from marcwebbie/gorillavid

* marcwebbie/gorillavid:
  Changed video url to a public video
  [GorillaVid] Added GorillaVid extractor

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/gorillavid.py
 | 
38
++++++++++++++++++++++++++++++++++++++

2 files changed, 39 insertions(+), 0 deletions(-)
diff --git 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
@@ -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/z08zf8le23c6",
+        'md5': 'c9e293ca74d46cad638e199c3f3fe604',
+        'info_dict': {
+            'id': 'z08zf8le23c6',
+            'ext': 'mp4',
+            'title': 'Say something nice',
+        }
+    }
+
+    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