youtube-dl

commit 6b3f5a329bc1d1f91655d37222253de2d71fad96
parent 63ef586b056b8b50b7711c122f52ee472540a254
Author: Philipp Hagemeister <phihag@phihag.de>
Date:   Sun, 23 Jun 2013 18:58:53 +0200

Improve Statigr.am IE

Diffstat:
M
test/tests.json
 | 
2
+-
M
youtube_dl/InfoExtractors.py
 | 
26
+++++++++++++++++---------

2 files changed, 18 insertions(+), 10 deletions(-)
diff --git a/test/tests.json b/test/tests.json
@@ -632,7 +632,7 @@
     "skip": "Requires rtmpdump"
   },
   {
-    "name": "Statigr",
+    "name": "Statigram",
     "url": "http://statigr.am/p/484091715184808010_284179915",
     "file": "484091715184808010_284179915.mp4",
     "md5": "deda4ff333abe2e118740321e992605b",
diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
@@ -4552,20 +4552,28 @@ class GametrailersIE(InfoExtractor):
                 'description': video_description,
                 }
 
-class StatigrIE(InfoExtractor):
+class StatigramIE(InfoExtractor):
     _VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
+
         video_id = mobj.group(1)
         webpage = self._download_webpage(url, video_id)
-        video_url = re.search(r'<meta property="og:video:secure_url" content="(.+?)">',webpage).group(1)
-        thumbnail_url = re.search(r'<meta property="og:image" content="(.+?)" />',webpage).group(1)
-        title = (re.search(r'<title>(.+?)</title>',webpage).group(1)).strip("| Statigram")
-        uploader = re.search(r'@(.+) \(Videos\)',title).group(1)
-        ext = "mp4"
+        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]
+        uploader = self._html_search_regex(
+            r'@(.+) \(Videos\)', title, u'uploader name', fatal=False)
+        ext = 'mp4'
+
         return [{
             'id':        video_id,
             'url':       video_url,
@@ -4641,7 +4649,7 @@ def gen_extractors():
         HypemIE(),
         Vbox7IE(),
         GametrailersIE(),
-        StatigrIE(),
+        StatigramIE(),
         GenericIE()
     ]