]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/wimp.py
Merge tag 'upstream/2017.03.07'
[youtubedl] / youtube_dl / extractor / wimp.py
index b9c3b13f918f5fbffa73010cbefb46543dac9586..c022fb33e94ef7f9e6f0e90d73300f866e8ffc76 100644 (file)
@@ -1,36 +1,57 @@
-import re
-import base64
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 
 
 class WimpIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
-    _TEST = {
-        u'url': u'http://www.wimp.com/deerfence/',
-        u'file': u'deerfence.flv',
-        u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5',
-        u'info_dict': {
-            u"title": u"Watch Till End: Herd of deer jump over a fence."
+    _VALID_URL = r'https?://(?:www\.)?wimp\.com/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'http://www.wimp.com/maru-is-exhausted/',
+        'md5': 'ee21217ffd66d058e8b16be340b74883',
+        'info_dict': {
+            'id': 'maru-is-exhausted',
+            'ext': 'mp4',
+            'title': 'Maru is exhausted.',
+            'description': 'md5:57e099e857c0a4ea312542b684a869b8',
         }
-    }
+    }, {
+        'url': 'http://www.wimp.com/clowncar/',
+        'md5': '5c31ad862a90dc5b1f023956faec13fe',
+        'info_dict': {
+            'id': 'cG4CEr2aiSg',
+            'ext': 'webm',
+            'title': 'Basset hound clown car...incredible!',
+            'description': '5 of my Bassets crawled in this dog loo! www.bellinghambassets.com\n\nFor licensing/usage please contact: licensing(at)jukinmediadotcom',
+            'upload_date': '20140303',
+            'uploader': 'Gretchen Hoey',
+            'uploader_id': 'gretchenandjeff1',
+        },
+        'add_ie': ['Youtube'],
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group(1)
+        video_id = self._match_id(url)
+
         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,
-        }]
 
+        youtube_id = self._search_regex(
+            r"videoId\s*:\s*[\"']([0-9A-Za-z_-]{11})[\"']",
+            webpage, 'video URL', default=None)
+        if youtube_id:
+            return {
+                '_type': 'url',
+                'url': youtube_id,
+                'ie_key': YoutubeIE.ie_key(),
+            }
+
+        info_dict = self._extract_jwplayer_data(
+            webpage, video_id, require_title=False)
+
+        info_dict.update({
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+        })
+
+        return info_dict