[cracked] Add new extractor
authorhassaanaliw <hassaanaliw@gmail.com>
Wed, 16 Jul 2014 13:45:42 +0000 (18:45 +0500)
committerhassaanaliw <hassaanaliw@gmail.com>
Wed, 16 Jul 2014 13:45:42 +0000 (18:45 +0500)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/cracked.py [new file with mode: 0644]

index e49ac3e52783608942b34deed950703d2a85dc39..78b95c2a5f050f634219b54eef9520a71d254638 100644 (file)
@@ -52,6 +52,7 @@ from .cnn import (
 from .collegehumor import CollegeHumorIE
 from .comedycentral import ComedyCentralIE, ComedyCentralShowsIE
 from .condenast import CondeNastIE
+from .cracked import CrackedIE
 from .criterion import CriterionIE
 from .crunchyroll import CrunchyrollIE
 from .cspan import CSpanIE
@@ -396,6 +397,7 @@ from .youtube import (
     YoutubeUserIE,
     YoutubeWatchLaterIE,
 )
+
 from .zdf import ZDFIE
 
 
diff --git a/youtube_dl/extractor/cracked.py b/youtube_dl/extractor/cracked.py
new file mode 100644 (file)
index 0000000..37c0f7f
--- /dev/null
@@ -0,0 +1,46 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+
+class CrackedIE(InfoExtractor):
+    _VALID_URL = r'http?://.*?\.cracked\.com/video_+(?P<id>.*)_.*'
+    _TEST = {
+        'url': 'http://www.cracked.com/video_18803_4-social-criticisms-hidden-in-sonic-hedgehog-games.html',
+
+        'info_dict': {
+            'id': '18803',
+            'ext': 'mp4',
+            'title': "4 Social Criticisms Hidden in 'Sonic the Hedgehog' Games | Cracked.com",
+            'height': 375,
+            'width': 666,
+
+
+        }
+    }
+
+    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._search_regex(r'<title>(.*?)</title>',webpage,'title')
+        video_url = self._search_regex(r'var CK_vidSrc = "+(.*)"',webpage,'url')
+        width = self._search_regex(r'width="(.*?)"',webpage,'width')
+        height = re.findall(r'height="(.*?)"',webpage)[1]
+
+
+
+
+        return {
+            'url':video_url,
+            'id': video_id,
+            'ext':'mp4',
+            'title':title,
+            'height':int(height),
+            'width':int(width)
+
+
+        }
\ No newline at end of file