一.反爬虫机制处理思路:
浏览器伪装、用户代理池;IP限制--------IP代理池;ajax、js异步-------抓包;验证码-------打码平台。二.散点知识:
def process_request(): #处理请求request.meta[“proxy”]=… #添加代理ipscrapy中如果请求2次就会放弃,说明该代理ip不行。 实战操作
目标网址:http://weixin.sogou.com/weixin?type=2&query=python&ie=utf8
实现:关于python文章的抓取,抓取标题、标题链接、描述。如下图所示。
1.middlewares.py主要代码
# -*- coding: utf-8 -*-import random'''遇到不懂的问题?Python学习交流群:821460695满足你的需求,资料都已经上传群文件,可以自行下载!'''from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware #代理ip,这是固定的导入from scrapy.downloadermiddlewares.useragent import UserAgentMiddleware #代理UA,固定导入class IPPOOLS(HttpProxyMiddleware): def __init__(self,ip=''): '''初始化''' self.ip=ip def process_request(self, request, spider): '''使用代理ip,随机选用''' ip=random.choice(self.ip_pools) #随机选择一个ip print '当前使用的IP是'+ip['ip'] try: request.meta["proxy"]="http://"+ip['ip'] except Exception,e: print e pass ip_pools=[ {'ip': '124.65.238.166:80'}, # {'ip':''}, ]class UAPOOLS(UserAgentMiddleware): def __init__(self,user_agent=''): self.user_agent=user_agent def process_request(self, request, spider): '''使用代理UA,随机选用''' ua=random.choice(self.user_agent_pools) print '当前使用的user-agent是'+ua try: request.headers.setdefault('User-Agent',ua) except Exception,e: print e pass user_agent_pools=[ 'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3', 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3', 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.75 Safari/537.36', ]2.setting.py主要代码
1 DOWNLOADER_MIDDLEWARES = {2 'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware':123,3 'weixin.middlewares.IPPOOLS':124,4 'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware' : 125,5 'weixin.middlewares.UAPOOLS':1266 }