Update what_crawler/what_crawler/spiders/request-spider.py

added regex escaping of special characters
Volvox · Dec 22, 2012 · 20ea133 · 20ea133
1 parent 1f443b1
commit 20ea133
Showing 1 changed file with 4 additions and 2 deletions.
diff --git a/what_crawler/what_crawler/spiders/request-spider.py b/what_crawler/what_crawler/spiders/request-spider.py
@@ -46,10 +46,11 @@ def parse_requests(self, response):
 
         for album in albums:
             item = WhatItem()
-
+            
             #regular expression for identifying links which incl. bracketed dates.
             p1 = re.compile('\[[^\]]*\]') 
             # p2 = re.compile('\[[2012\]]*\]') 
+
 
             # find links with [date]
             date = p1.search(album) 
@@ -61,8 +62,9 @@ def parse_requests(self, response):
             if date != None:
                 item['name'] = re.sub('\[[^\]]*\]','',album) #get rid of [date]
                 item['name'] = item['name'].strip()
+                item['name'] = re.escape(item['name'])
                 items.append(item)
 
 
         for item in items:  
-            yield item
+            yield item