def process_request(self, request, spider):
if not request.url:
return None
url_hash = hashlib.md5(request.url.encode("utf8")).hexdigest()
if self.redis_client.sismember(spider.name, url_hash):
raise IgnoreRequest("Spider : %s, IgnoreRequest : %s" % (spider.name, request.url))
else:
self.redis_client.sadd(spider.name, url_hash)
评论列表
文章目录