nodejs使用爬虫代理的方案

const http = require(“http”);
const url = require(“url”);

// 要访问的目标页面
const targetUrl = "http://httpbin.org/ip";


const urlParsed = url.parse(targetUrl);

// 代理服务器
const proxyHost = "t.16yun.cn";
const proxyPort = "36600";

// 生成一个随机 proxy tunnel
var seed = 1;
function random() {
    var x = Math.sin(seed++) * 10000;
    return x - Math.floor(x);
}
const tunnel = random()*100;

// 代理验证信息
const proxyUser = "username";
const proxyPass = "password";

const base64    = new Buffer.from(proxyUser + ":" + proxyPass).toString("base64");

const options = {
    host: proxyHost,
    port: proxyPort,
    path: targetUrl,
    method: "GET",
    headers: {
        "Host": urlParsed.hostname,
        "Proxy-Tunnel": tunnel,
        "Proxy-Authorization" : "Basic " + base64
    }
};

http.request(options, function (res) {
    console.log("got response: " + res.statusCode);
    res.pipe(process.stdout);
}).on("error", function (err) {
    console.log(err);
}).end();

你可能感兴趣的:(网络爬虫,数据采集,http代理,爬虫代理)