例如：百度输入ip查看是自己本机的ip，通过UA伪装成其他机器的ip,
爬虫代码：
1 import scrapy 2 3 4 class UatestSpider(scrapy.Spider): 5 name = 'UATest' 6 # allowed_domains = ['www.xxx.com'] 7 start_urls = ['https://www.baidu.com/s?wd=ip'] 8 def parse(self, response): 9 with open('./ip.html','w',encoding='utf-8')as fp: 10 fp.write(response.text) 11 print('over!!!')
Middlewares中间件代码：
1 from scrapy import signals 2 from scrapy.contrib.downloadermiddleware.useragent import UserAgentMiddleware 3 import random 4 user_agent_list = [ 5 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 " 6 "(KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1", 7 "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 " 8 "(KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", 9 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 " 10 "(KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", 11 "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 " 12 "(KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", 13 "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 " 14 "(KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", 15 "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 " 16 "(KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", 17 "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 " 18 "(KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", 19 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " 20 "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", 21 "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/536.3 " 22 "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", 23 "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 " 24 "(KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", 25 "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " 26 "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", 27 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " 28 "(KHTML, like Gecko) Chrome/19.0.1062.0 Safari/536.3", 29 "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " 30 "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", 31 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 " 32 "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", 33 "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 " 34 "(KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", 35 "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 " 36 "(KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", 37 "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 " 38 "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", 39 "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 " 40 "(KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" 41 ] 42 43 class UAPool(UserAgentMiddleware): 44 def process_request(self,request,spider): 45 ua=random.choice(user_agent_list) 46 request.headers['User-Agent']=ua 47 print(request.headers['User-Agent']) 48 49 proxy_http = ['125.27.10.150:56292','114.34.168.157:46160'] 50 proxy_https = ['1.20.101.81:35454','113.78.254.156:9000'] 51 class UapoolDownloaderMiddleware(object): 52 #request参数就是拦截到的 请求对象 53 #spider就是爬虫对象 54 def process_request(self, request, spider): 55 if request.url.split(':')[0]=='https': 56 request.meta['proxy']='https://'+random.choice(proxy_https) 57 else: 58 request.meta['proxy'] = 'http://' + random.choice(proxy_http) 59 print(request.meta['proxy']) 60 return None
注：setting需要解开中间件，并添加自己写的中间件类