+ hdr = {
+ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; rv:22.0) Gecko/20130405 Firefox/22.0',
+ }
+ request = urllib2.Request(src_url, headers=hdr)
+ response = urllib2.urlopen(request)
+ except Exception, e:
+ print 'Downloading from', src_url, 'failed.', e
+ return
+
+ # get the final URL after possible redirect have been followed
+ url = response.geturl()
+
+ filename = ""
+
+ # From http://paste.pound-python.org/show/9545/
+ # TODO: use a proper module to parse HTTP headers
+ if 'Content-Disposition' in response.info() and len(response.info()['Content-Disposition'].split('filename=')) > 1:
+ # If the response has Content-Disposition, we take file name from it
+ filename = response.info()['Content-Disposition'].split('filename=')[1].decode('utf-8')
+ if filename[0] == '"' or filename[0] == "'":
+ filename = urllib2.unquote(filename.split('"')[1])
+ else:
+ filename = urllib2.unquote(url.split('/')[-1].decode('utf_8'))