How to capture proxy IP in node.js?

This article mainly introduces the relevant information about node.js grabbing proxy ip example code. Friends in need can refer to it

node.js implements grabbing proxy ip

Main file: index.js

/*
* 支持：node.js v7.9.0
*/
const cheerio=require('cheerio');
const fetch =require('node-fetch');
const Promise=require('bluebird');
let mongoose=require('mongoose');

Promise.promisifyAll(mongoose);
let Schema=mongoose.Schema;
mongoose.connect('mongodb://localhost:27017/ipproxypool');
let IPpool=new Schema({
  ip:{type:String,unique:true}
})
let Ipproxy=mongoose.model('IP',IPpool);

function fetchUrl(url){
  fetch(url,{
    method:'get',
    headers:{
    }
  })
  .then(res=>res.text())
  .then(body=>{
    let $=cheerio.load(body);
    let length=$('#list table tbody').find('tr').length;
    for (let i=0;i<length;i++){
    let ipaddress= $(&#39;#list table tbody&#39;).find(&#39;tr&#39;).eq(i).find(&#39;td&#39;).eq(0).text() ;
    let port = $(&#39;#list table tbody&#39;).find(&#39;tr&#39;).eq(i).find(&#39;td&#39;).eq(1).text();
    console.log(`IP:${ipaddress}:${port}`);
    let ip=`${ipaddress}:${port}`
    let ippool=new Ipproxy({
      ip:ip
    })
    ippool.save();
    }
  })
}

var sleep = function (time) {
  return new Promise(function (resolve, reject) {
    setTimeout(function () {
      resolve(&#39;ok&#39;);
    }, time);
  })
};
const pageNumber=10;
var start = async function(){
  for(let j=1;j<pageNumber;j++){
     console.log(`当前是第${j}次等待..`);
    fetchUrl(`http://www.kuaidaili.com/free/inha/${j}/`);
    await sleep(1500);
  }
}
start();

Package support: package.json

{
 "name": "demo-4-ipproxypool",
 "version": "1.0.0",
 "description": "",
 "main": "index.js",
 "scripts": {
  "test": "echo \"Error: no test specified\" && exit 1"
 },
 "author": "false-l",
 "license": "",
 "devDependencies": {
  "babel-preset-es2015": "^6.24.1",
  "babel-preset-react": "^6.24.1",
  "babel-preset-stage-3": "^6.24.1"
 },
 "dependencies": {
  "babel-core": "^6.24.1",
  "bluebird": "^3.5.0",
  "cheerio": "^0.22.0",
  "koa": "^2.2.0",
  "koa-router": "^7.1.1",
  "mongoose": "^4.9.6",
  "node-fetch": "^1.6.3"
 }
}

The mongodb database needs to be installed locally for Store the captured IP. IP verification is not yet implemented. I write this mainly out of curiosity.

The above code can capture the IP of the IP proxy website and store it in the mongodb database.

The following is a simple server implementation based on the koa2 api interface

server

const Promise=require('bluebird');
let mongoose=require('mongoose');
const koa=require('koa');
const app=new koa();
var router = require('koa-router')();
Promise.promisifyAll(mongoose);
let Schema=mongoose.Schema;
mongoose.connect('mongodb://localhost:27017/ipproxypool');
let IPpool=new Schema({
  ip:{type:String,unique:true}
})
let Ipproxy=mongoose.model('IP',IPpool);

app.use(async (ctx, next) => {
 await next();
 var data=await Ipproxy.find({},function(err,ips){
  var ipmap=[];
   ips.forEach(function(ip){
     ipmap[ip._id]=ip;
     //console.log(ip)
   });
 })
 var map=data.map(ip=>ip.ip);
 ctx.response.type = 'text/json';
 ctx.response.body = map;
});
app.listen(3000);
console.log('server listen:3000')

As for why there is both promise and async, it is because I’m not very familiar with asynchronous syntax, so how do I know how to write it?

Usage:

According to package.json

npm install //Installation support

node index.js //Get Proxy ip

node server.js //Run simple ip interface

The above is the detailed content of How to capture proxy IP in node.js?. For more information, please follow other related articles on the PHP Chinese website!