Browse Source

[wimp] minor readability improvements (#940)

Philipp Hagemeister 12 years ago
parent
commit
ed92bc9f6e
3 changed files with 39 additions and 0 deletions
  1. 9 0
      test/tests.json
  2. 2 0
      youtube_dl/extractor/__init__.py
  3. 28 0
      youtube_dl/extractor/wimp.py

+ 9 - 0
test/tests.json

@@ -705,5 +705,14 @@
         "title": "Attorney General Eric Holder on Voting Rights Act Decision"
     },
     "skip": "Requires rtmpdump"
+  },
+  {
+    "name": "Wimp",
+    "url": "http://www.wimp.com/deerfence/",
+    "file": "deerfence.flv",
+    "md5": "8b215e2e0168c6081a1cf84b2846a2b5",
+    "info_dict": {
+        "title": "Watch Till End: Herd of deer jump over a fence."
+    }
   }
 ]

+ 2 - 0
youtube_dl/extractor/__init__.py

@@ -50,6 +50,7 @@ from .vbox7 import Vbox7IE
 from .vevo import VevoIE
 from .vimeo import VimeoIE
 from .vine import VineIE
+from .wimp import WimpIE
 from .worldstarhiphop import WorldStarHipHopIE
 from .xhamster import XHamsterIE
 from .xnxx import XNXXIE
@@ -134,6 +135,7 @@ def gen_extractors():
         JukeboxIE(),
         TudouIE(),
         CSpanIE(),
+        WimpIE(),
         GenericIE()
     ]
 

+ 28 - 0
youtube_dl/extractor/wimp.py

@@ -0,0 +1,28 @@
+import re
+import base64
+
+from .common import InfoExtractor
+
+
+class WimpIE(InfoExtractor):
+    _VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group(1)
+        webpage = self._download_webpage(url, video_id)
+        title = self._search_regex(r'<meta name="description" content="(.+?)" />',webpage, 'video title')
+        thumbnail_url = self._search_regex(r'<meta property="og\:image" content="(.+?)" />', webpage,'video thumbnail')
+        googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url')
+        googleString = base64.b64decode(googleString).decode('ascii')
+        final_url = self._search_regex('","(.*?)"', googleString,'final video url')
+        ext = final_url.rpartition(u'.')[2]
+
+        return [{
+            'id':        video_id,
+            'url':       final_url,
+            'ext':       ext,
+            'title':     title,
+            'thumbnail': thumbnail_url,
+        }]
+