- url = entry['URL'] % LANGCODE
- except:
- url = entry['URL']
- pass
-
- response = urllib2.urlopen(url)
- filename = urllib2.unquote(os.path.basename(response.geturl()))
- destfile = os.path.join(OUTPUT_DIR, filename)
+ response = urllib2.urlopen(src_url)
+ except Exception, e:
+ if hasattr(e, 'reason'):
+ print 'Downloading from', src_url, 'failed. Reason: ', e.reason
+ elif hasattr(e, 'code'):
+ print 'Downloading from', src_url, 'failed. Error code: ', e.code
+ 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'))
+
+ if filename == "":
+ sys.stderr.write("Debug (%s): filename: %s url: %s\n" % (pkg['package_name'], filename, url))
+ return
+
+ # TODO: Add some integrity verification of downloaded files (md5, sha256?)
+
+ destfile = os.path.join(dest_dir, filename)