def process_request(self, request, spider):
parsed_url = urlparse.urlparse(request.url)
if not self.test_mode or not parsed_url.path in ["/", ""]:
return None
if not Domain.is_onion_url(request.url):
return None
d = Domain.find_by_url(request.url)
if d is None:
return None
now = datetime.now()
if now > d.next_scheduled_check:
return None
else:
raise IgnoreRequest('FilterNotScheduledMiddleware: %s is not scheduled to check' % d.host)
评论列表
文章目录