HTTP小爬虫

1 爬取某个URL页面 var http = require('http')// 所要爬取的页面urlvar url = '...'http.get(url, function (res) {

1 爬取某个URL页面

var http = require('http')// 所要爬取的页面urlvar url = '...'http.get(url, function (res) {    var html = ''    res.on('data',function (data) {        html += data    })    res.on('end',function () {        console.log(html)    })}).on('error',function () {    console.log('获取页面数据出错!')})

2 通过cheerio解析数据

首先安装cheerio模块: npm install cheerio

引入cheerio模块：require('cheerio')

var http = require('http')var cheerio = require('cheerio')var url = '...'http.get(url, function (res) {    var html = ''    res.on('data',function (data) {        html += data    })    res.on('end',function () {        var html_obj = filterData(html)        printInfo(html_obj)    })}).on('error',function () {    console.log('获取页面数据出错!')})function filterData(html) {    var $ = cheerio.load(html)    var payObj = $('.payModeContent')    var pay_types = payObj.find('.payName')    var pay_icons = payObj.find('.payIcon img')    var pay_type_array = []    var pay_icon_array = []    pay_types.each(function () {        var pay_type = $(this).text()        pay_type_array.push(pay_type)    })    pay_icons.each(function () {        var pay_icon = $(this).attr('src').split('images/')[1]        pay_icon_array.push(pay_icon)    })    var payInfo = {        payType:pay_type_array,        payIcon:pay_icon_array    }    return payInfo;}function printInfo(obj) {    console.log(obj)}

结果：

{ payType: [ '微信支付方式', '支付宝钱包支付', '储蓄卡支付' ],

  payIcon: [ 'weichatIcon.png', 'alipayIcon.png', 'depositcardpayIcon.png' ] }