1.在Scrapy工程下新建“middlewares.py”
# Importing base64 library because we'll need it ONLY in case if the proxy we are going to use requires authentication import base64 # Start your middleware class class ProxyMiddleware(object): # overwrite process request def process_request(self, request, spider): # Set the location of the proxy request.meta['proxy'] = "http://YOUR_PROXY_IP:PORT" # Use the following lines if your proxy requires authentication proxy_user_pass = "USERNAME:PASSWORD" # setup basic authentication for the proxy encoded_user_pass = base64.encodestring(proxy_user_pass) request.headers['Proxy-Authorization'] = 'Basic ' + encoded_user_pass
2.在项目配置文件里(./project_name/settings.py)添加
DOWNLOADER_MIDDLEWARES = { 'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware': 110, 'project_name.middlewares.ProxyMiddleware': 100, }
只要两步，现在请求就是通过代理的了。测试一下^_^
from scrapy.spider import BaseSpider from scrapy.contrib.spiders import CrawlSpider, Rule from scrapy.http import Request class TestSpider(CrawlSpider): name = "test" domain_name = "whatismyip.com" # The following url is subject to change, you can get the last updated one from here : # http://www.whatismyip.com/faq/automation.asp start_urls = ["http://xujian.info"] def parse(self, response): open('test.html', 'wb').write(response.body)
3.使用随机user-agent
默认情况下scrapy采集时只能使用一种user-agent，这样容易被网站屏蔽，下面的代码可以从预先定义的user- agent的列表中随机选择一个来采集不同的页面
在settings.py中添加以下代码
DOWNLOADER_MIDDLEWARES = { 'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware' : None, 'Crawler.comm.rotate_useragent.RotateUserAgentMiddleware' :400 }
注意: Crawler; 是你项目的名字 ，通过它是一个目录的名称 下面是蜘蛛的代码
#!/usr/bin/python #-*-coding:utf-8-*- import random from scrapy.contrib.downloadermiddleware.useragent import UserAgentMiddleware class RotateUserAgentMiddleware(UserAgentMiddleware): def __init__(self, user_agent=''): self.user_agent = user_agent def process_request(self, request, spider): #这句话用于随机选择user-agent ua = random.choice(self.user_agent_list) if ua: request.headers.setdefault('User-Agent', ua) #the default user_agent_list composes chrome,I E,firefox,Mozilla,opera,netscape #for more user agent strings,you can find it in http://www.useragentstring.com/pages/useragentstring.php user_agent_list = [ "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/22.0.1207.1 Safari/537.1" "Mozilla/5.0 (X11; CrOS i686 2268.111.0) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.57 Safari/536.11", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1092.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.6 (KHTML, like Gecko) Chrome/20.0.1090.0 Safari/536.6", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/19.77.34.5 Safari/537.1", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.9 Safari/536.5", "Mozilla/5.0 (Windows NT 6.0) AppleWebKit/536.5 (KHTML, like Gecko) Chrome/19.0.1084.36 Safari/536.5", "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 5.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_0) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1063.0 Safari/536.3", "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/19.0.1062.0 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.1 Safari/536.3", "Mozilla/5.0 (Windows NT 6.2) AppleWebKit/536.3 (KHTML, like Gecko) Chrome/19.0.1061.0 Safari/536.3", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24", "Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/535.24 (KHTML, like Gecko) Chrome/19.0.1055.1 Safari/535.24" ]
【讲解Python的Scrapy爬虫框架使用代理进行采集的方法】相关文章：
★ 在python的WEB框架Flask中使用多个配置文件的解决方法