Exemplo n.º 1
0
 def process_spider_input(self,response, spider):
     key = spider.name
     url = response.url
     if not (url in spider.start_urls):
         if cache.existKey(key, url): #@UndefinedVariable
             raise DropItem()
         cache.setItem(key, url) #@UndefinedVariable
Exemplo n.º 2
0
 def process_spider_output(self,response, result, spider):
     for result in result:
         flag = True
         if isinstance(result,Request):
             flag = not cache.existKey(spider.name, result.url) #@UndefinedVariable
         if flag:
             yield result