node使用代理ip抓取 node使用代理ip抓取

node使用代理ip抓取

var request = require("request");
var iconv = require('iconv-lite');
var Promise = require("bluebird");
function getProxyList() {
    var apiURL = 'http://www.66ip.cn/mo.php?sxb=&tqsl=100&port=&export=&ktip=&sxa=&submit=%CC%E1++%C8%A1&textarea=http%3A%2F%2Fwww.66ip.cn%2F%3Fsxb%3D%26tqsl%3D100%26ports%255B%255D2%3D%26ktip%3D%26sxa%3D%26radio%3Dradio%26submit%3D%25CC%25E1%2B%2B%25C8%25A1';

    return new Promise((resolve, reject) => {
        var options = {
            method: 'GET',
            url: apiURL,
            gzip: true,
            encoding: null,
            headers: {
               // 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
                //'Accept-Encoding': 'gzip, deflate',
                //'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6,zh-TW;q=0.4',
               // 'User-Agent': 'Mozilla/8.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36',
               // 'referer': 'http://www.66ip.cn/',
//'cookie':'yd_cookie=05e6639e-848d-48585a8dd83b82f4a8c7d2cf196d74d83ee8; Hm_lvt_1761fabf3c988e7f04bec51acd4073f4=1549174243; Hm_lpvt_1761fabf3c988e7f04bec51acd4073f4=1549174380; _ydclearance=562d0b4456ca1cc873e260da-4915-47f9-9b27-ae7cecbbce3d-1549191147'
'Connection': 'keep-alive',
'Cache-Control': 'max-age=0',
'Upgrade-Insecure-Requests': 1,
'User-Agent': 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3423.2 Safari/537.36',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Referer': 'http://www.66daili.cn/',
'Accept-Encoding':'gzip, deflate',
'Accept-Language':'zh-CN,zh;q=0.9',
'Cookie': 'yd_cookie=05e6639e-848d-48585a8dd83b82f4a8c7d2cf196d74d83ee8; Hm_lvt_1761fabf3c988e7f04bec51acd4073f4=1549174243; Hm_lpvt_1761fabf3c988e7f04bec51acd4073f4=1549174380; _ydclearance=562d0b4456ca1cc873e260da-4915-47f9-9b27-ae7cecbbce3d-1549191147'
    
        },

        };

        request(options, function (error, response, body) {
            try {

                if (error) throw error;

                if (/meta.*charset=gb2312/.test(body)) {
                    body = iconv.decode(body, 'gb2312');
                }
                var ret = body.match(/\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,4}/g);


                resolve(ret);

            } catch (e) {
                return reject(e);
            }


        });
    })
}


getProxyList().then(function (proxyList) {

    var targetOptions = {
        method: 'GET',
        url: 'http://lininn.cn',
        timeout: 8000,
        encoding: null,
    };

  
    proxyList.forEach(function (proxyurl) {

        console.log(`testing ${proxyurl}`);

        targetOptions.proxy = 'http://' + proxyurl;
        request(targetOptions, function (error, response, body) {
            try {
                if (error) throw error;


                body = body.toString();

                console.log(body);

                eval(`var ret = ${body}`);


                if (ret) {
                    console.log(` ${ret.address}`);
                }
            } catch (e) {
                 console.error('error'+e);
            }


        });

    });
}).catch(e => {
    console.log(e);
})
分享本文至:

评论 0

挤眼 亲亲 咆哮 开心 想想 可怜 糗大了 委屈 哈哈 小声点 右哼哼 左哼哼 疑问 坏笑 赚钱啦 悲伤 耍酷 勾引 厉害 握手 耶 嘻嘻 害羞 鼓掌 馋嘴 抓狂 抱抱 围观 威武 给力
提交评论

清空信息
关闭评论