Issue 2951 - Fix handling of URLs without a scheme

run.py

Index: run.py
===================================================================
--- a/run.py
+++ b/run.py
@@ -41,17 +41,20 @@ class CrawlerApp:
         request_body_size = int(environ.get('CONTENT_LENGTH', 0))
       except (ValueError):
         start_response('400 Bad Request', [])
         return ''
 
       data = json.loads(environ['wsgi.input'].read(request_body_size))
       self.urls.remove(data['url'])
 
-      parsedurl = urlparse.urlparse(data['url'])
+      fullurl = data['url']
+      if not urlparse.urlparse(fullurl).scheme:
+        fullurl = 'http://' + fullurl
+      parsedurl = urlparse.urlparse(fullurl)
       urlhash = hashlib.new('md5', data['url']).hexdigest()
       timestamp = datetime.datetime.fromtimestamp(data['startTime'] / 1000.0).strftime('%Y-%m-%dT%H%M%S.%f')
       basename = "%s-%s-%s" % (parsedurl.hostname, timestamp, urlhash)
       datapath = os.path.join(self.parameters.outdir, basename + ".json")
       screenshotpath = os.path.join(self.parameters.outdir, basename + ".jpg")
       sourcepath = os.path.join(self.parameters.outdir, basename + ".xml")
 
       try: