在middlewares中
ip代理的获取爬虫https://github.com/favoMJ/ippool
# -*- coding: utf-8 -*-
# Define here the models for your spider middleware
#
# See documentation in:
# http://doc.scrapy.org/en/latest/topics/spider-middleware.html
import random
import time
from scrapy import signals
from sctest.settings import IPPOOL
class SctestSpiderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the spider middleware does not modify the
# passed objects.
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_spider_input(self, response, spider):
# Called for each response that goes through the spider
# middleware and into the spider.
# Should return None or raise an exception.
return None
def process_spider_output(self, response, result, spider):
# Called with the results returned from the Spider, after
# it has processed the response.
# Must return an iterable of Request, dict or Item objects.
for i in result:
yield i
def process_spider_exception(self, response, exception, spider):
# Called when a spider or process_spider_input() method
# (from other spider middleware) raises an exception.
# Should return either None or an iterable of Response, dict
# or Item objects.
pass
def process_start_requests(self, start_requests, spider):
# Called with the start requests of the spider, and works
# similarly to the process_spider_output() method, except
# that it doesn’t have a response associated.
# Must return only requests (not items).
for r in start_requests:
yield r
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
class ProxyMiddleWare(object):
"""docstring for ProxyMiddleWare"""
def process_request(self, request, spider):
'''对request对象加上proxy'''
proxy = self.get_random_proxy()
# print("this is request ip:" + proxy)
request.meta['proxy'] = proxy
def process_response(self, request, response, spider):
'''对返回的response处理'''
# 如果返回的response状态不是200,重新生成当前request对象
if response.status != 200:
proxy = self.get_random_proxy()
# print("this is response ip:" + proxy)
# 对当前reque加上代理
request.meta['proxy'] = proxy
return request
return response
def get_random_proxy(self):
'''随机从文件中读取proxy'''
thisip = random.choice(IPPOOL)
# print("当前使用IP是:" + thisip["ipaddr"])
return "http://"+thisip["ipaddr"]
在setting.py中
IPPOOL=[
{"ipaddr": "xx.xx.xx.xx:xx"},
{"ipaddr": "xx.xx.xx.xx:xx"},
}