scrapy 使用代理
来源:互联网 发布:英语词汇书籍推荐知乎 编辑:程序博客网 时间:2024/05/22 17:16
# Importing base64 library because we'll need it ONLY#in case if the proxy we are going to use requires authenticationimport base64# Start your middleware classclass 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