python scrapy 网络采集使用代理的方法
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)