InfoExtractor: add some helper methods to extract OpenGraph info

[youtube-dl] / youtube_dl / extractor / statigram.py

diff --git a/youtube_dl/extractor/statigram.py b/youtube_dl/extractor/statigram.py
index 2f4aaaa509654f408e49b9448b8abfe88d65fb46..b8e6b3bf91a05a793db631db9325bb2bc605b8b9 100644 (file)
--- a/youtube_dl/extractor/statigram.py
+++ b/youtube_dl/extractor/statigram.py
@@ -10,7 +10,7 @@ class StatigramIE(InfoExtractor):
         u'md5': u'deda4ff333abe2e118740321e992605b',
         u'info_dict': {
             u"uploader_id": u"videoseconds", 
-            u"title": u"Instagram photo by @videoseconds (Video)"
+            u"title": u"Instagram photo by @videoseconds"
         }
     }
 
@@ -18,25 +18,19 @@ class StatigramIE(InfoExtractor):
         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')
-        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,
-            'url':       video_url,
+            'url':       self._og_search_video_url(webpage),
             'ext':       ext,
             'title':     title,
-            'thumbnail': thumbnail_url,
+            'thumbnail': self._og_search_thumbnail(webpage),
             'uploader_id' : uploader_id
         }]