def process_request(self, request, spider): # pylint:disable=unused-argument
"""Process incoming request."""
hostname = urlparse(request.url).hostname
if len(hostname.split(".")) > 4:
# Do not execute this request
request.meta['proxy'] = ""
msg = "Ignoring request {}, too many sub domains." \
.format(request.url)
logging.info(msg)
raise IgnoreRequest()
评论列表
文章目录