Merge tag 'upstream/2013.12.23'

[youtubedl] / youtube_dl / extractor / statigram.py

diff --git a/youtube_dl/extractor/statigram.py b/youtube_dl/extractor/statigram.py
index 95d2ee3c046fa70289fc5ab07e7062db7a66f047..1ea4a9f2f82edce03340d28414d1a77b695d8e52 100644 (file)
--- a/youtube_dl/extractor/statigram.py
+++ b/youtube_dl/extractor/statigram.py
@@ -4,30 +4,33 @@ from .common import InfoExtractor
 
 class StatigramIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
 
 class StatigramIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'

+    _TEST = {
+        u'url': u'http://statigr.am/p/522207370455279102_24101272',
+        u'file': u'522207370455279102_24101272.mp4',
+        u'md5': u'6eb93b882a3ded7c378ee1d6884b1814',
+        u'info_dict': {
+            u'uploader_id': u'aguynamedpatrick',
+            u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
+        },
+    }

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)

-        video_url = self._html_search_regex(
-            r'<meta property="og:video:secure_url" content="(.+?)">',
-            webpage, u'video URL')
-        thumbnail_url = self._html_search_regex(
-            r'<meta property="og:image" content="(.+?)" />',
-            webpage, u'thumbnail URL', fatal=False)

         html_title = self._html_search_regex(
             r'<title>(.+?)</title>',
             webpage, u'title')
         html_title = self._html_search_regex(
             r'<title>(.+?)</title>',
             webpage, u'title')

-        title = html_title.rpartition(u' | Statigram')[0]
+        title = re.sub(r'(?: *\(Videos?\))? \| Statigram$', '', html_title)

         uploader_id = self._html_search_regex(
             r'@([^ ]+)', title, u'uploader name', fatal=False)
         ext = 'mp4'
 
         return [{
             'id':        video_id,
         uploader_id = self._html_search_regex(
             r'@([^ ]+)', title, u'uploader name', fatal=False)
         ext = 'mp4'
 
         return [{
             'id':        video_id,

-            'url':       video_url,
+            'url':       self._og_search_video_url(webpage),

             'ext':       ext,
             'title':     title,
             'ext':       ext,
             'title':     title,

-            'thumbnail': thumbnail_url,
+            'thumbnail': self._og_search_thumbnail(webpage),

             'uploader_id' : uploader_id
         }]
             'uploader_id' : uploader_id
         }]