<div class="c-footer w1190 " monkey="erji-footer"><div class="container"><div class="left-wrap clearfix"><a href="https://www.hao123.com" rel="external nofollow" rel="external nofollow" class="logo" target="_blank" monkey="logo">hao123 上网导航第一品牌<div class="bottom-nav" monkey="nav"><a href="http://www.hao123.com/abouthao123.htm" rel="external nofollow" class="item" target="_target">关于我们<a href="http://www.hao123.com/redian/problem.htm" rel="external nofollow" class="item" target="_taregt">常见问题<a href="http://www.hao123.com/feedback" rel="external nofollow" rel="external nofollow" class="item" target="_blank">反馈意见<a href="http://www.hao123.com/sitemap" rel="external nofollow" class="item" target="_blank">全站地图<span class="item">京ICP证030173号<div class="right-wrap"><div class="extend-nav clearfix" monkey="tools"><a href="http://www.hao123.com/shouji" rel="external nofollow" class="item" target="_blank"><i class="icon-phone">下载
手机端<a href="javascript:;" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" rel="external nofollow" class="item" target="_black" data-hook="addBookmark"><i class="icon-collect">收藏
本站

<script type="text/javascript" src="http://s0.hao123img.com/res/js/common/as.min.js?_=2434"&gt;

<script src="http://s2.hao123img.com/resource/fe/js/lib/main.5a7c104a8.js"&gt;
@H_30125@BigPipe.lazyPagelets = [];
@H301_25@BigPipe.loadedResource(["5a7c104a8_7959","d8b3cc9ac_29e3","38645dd_f7dd","8d1d978b0_a316","6cca09af6_f07f","a0832ac19_fb25","25330c25d_ce62","deba0d4c0_c8fe","1c81d5fc6_a695","0c7877e81_8719","6e9548c75_e646","38645dd_0f3e","3f6d691_9321","4d7a174_ccfc","9e71d5b_bed3","b016c1d_d1a3","e073b71_9403","77f7c66_45f3","95a1383250731"]);@H301_25@BigPipe.hooks["__cb_0_1"]=function(){'use strict';

var $ = require('fe:widget/js/base/jquery.js');
var fixreferrer = require('fe:widget/js/base/fixreferrer.js');
HAO.https && fixreferrer.init($(document));
};
@H_301_25@BigPipe.hooks["cb_02"]=function(){'use strict';
var $ = require('fe:widget/js/base/jquery.js');$('div[data-hook="sitemap"]').on('mouseenter',function (e) {$(this).addClass('sitemap-hover');}).on('mouseleave',function (e) {$(this).removeClass('sitemap-hover');});};
@H301_25@BigPipe.hooks["__cb_03"]=function(){'use strict';
var $ = require('fe:widget/js/base/jquery.js');var Search = require('fe:widget/js/base/search.js');var headerSearchInstance = new Search($('form[data-hook="search-form"]'));};
@H301_25@BigPipe.hooks["cb_04"]=function(){'use strict';
var $ = require('fe:widget/js/base/jquery.js');var events = require('fe:widget/js/lib/events.js');var login = require('fe:widget/js/base/login.js');var sethome = require('fe:widget/js/base/sethome.js');var $loginCon = $('div[data-hook="c-header-login"]');var $loginDrop = $('div[js-hook="popup-list"]');login.init();events.on('loginSuccess',function(userinfo) {$loginCon.addClass('success');$loginCon.find('.key .word').html(userinfo.userName);/ if ($loginCon.find('.key .word').width() >= 60) {$loginCon.find('.key .word').width(50);$loginDrop.outerWidth($loginCon.outerWidth());}/$('[data-hook=login]').removeAttr('data-hook');});$loginCon.mouseenter(function() {if($(this).hasClass('success')) {$(this).addClass('hover');}}).mouseleave(function() {$(this).removeClass('hover');});$('div[data-hhok="qrcode"]').on('mouseenter',function () {$(this).children('div').show();}).on('mouseleave',function () {$(this).children('div').hide();}).on('click',function (ev) {if ($(this).children('div').length > 0) {return false;}});if($('[data-hook=setHome]').length) {sethome.init();}};
@H301_25@BigPipe.hooks["cb_05"]=function(){'use strict';
var $ = require('fe:widget/js/base/jquery.js');var popupWidth;$('div[data-hook="nav-more"]').on('mouseenter',function () {popupWidth = $(this).children('div').width();$(this).addClass('nav-more-hover');}).on('mouseleave',function () {$(this).removeClass('nav-more-hover');});};
@H301_25@BigPipe.hooks["__cb_06"]=function(){'use strict';
var $ = require('fe:widget/js/base/jquery.js');var $v2Header = $('#erjiV2Header');var $fixedNav = $('#fixedNav');if ($v2Header.hasClass('v2-fixed') && !($.browser.msie && $.browser.version < 7)) {var offHeight = 0;$(window).scroll(function () {offHeight = $v2Header.offset().top + 60;if ($(window).scrollTop() >= offHeight) {if (!$fixedNav.hasClass('nav-v2-fixed')) {$fixedNav.addClass('nav-v2-fixed').find('li.cur').removeClass('cur').addClass('cur');}}else if ($fixedNav.hasClass('nav-v2-fixed')) {$fixedNav.removeClass('nav-v2-fixed').find('li.cur').removeClass('cur').addClass('cur');}});}};
@H301_25@BigPipe.hooks["cb_07"]=function(){'use strict';
var $ = require('fe:widget/js/base/jquery.js');var Slider = require('fe:widget/js/util/slider.js');new Slider($('.slider'));};
@H301_25@BigPipe.hooks["cb_0_8"]=function(){'use strict';
if(typeof BAIDU_SS_HHRUN!='function'){var d=document;(d.getElementsByTagName('head')[0]||d.body).appendChild(d.createElement('script')).src='http://su.bdimg.com/static/dspui/js/ls.js?v='+~(-new Date()/5600e5)}else{BAIDU_SSHHRUN()}};
@H301_25@BigPipe.hooks["__cb_09"]=function(){'use strict';
var lifttop = require('tuijian:widget/lift/lifttop.js');lifttop();};
@H301_25@BigPipe.hooks["cb_0_10"]=function(){'use strict';

window._bd_share_config = {
common : {
bdText : '',bdDesc : '',bdUrl : '',bdPic : ''
},share : {
"bdSize" : 24
},selectShare : [{
"bdselectMiniList" : ['tsina','weixin','qzone']
}]
};
(document.getElementsByTagName('head')[0]||document.body)
.appendChild(document.createElement('script')).src='http://bdimg.share.baidu.com/static/api/js/share.js?v=89860593.js?cdnversion='+~(-new Date());

var shareEvent = require('tuijian:widget/index/content/shareEvent.js');
shareEvent();
};
@H_301_25@BigPipe.hooks["__cb_011"]=function(){'use strict';
var addBookmark = require('fe:widget/js/base/addbookmark.js');addBookmark.init();};
@H301_25@BigPipe.hooks["__cb_0_12"]=function(){'use strict';

(function initTrack(o){
var d = document;
var x = d.createElement("script");
x.src = HAO.httpsTrans('http://s0.hao123img.com/res/js/track.js') + '?'+~(new Date/36e5);
var a=[];
if(o){
for(var i in o){
a.push(i + ":" + (o[i]))
}
var config = a.join(";");
x.setAttribute("data-log-config",config);
var s = d.getElementsByTagName("script")[0].parentNode;
var p= s || d.head;
if(p) {
setTimeout(function() {
p.appendChild(x)
},0);
}
}
})({
pageId: window.pageId,page: window.pageId,level: 2,vp: window.pageVP || window.pageId,aid: window.aid || ''
});

window.js_track_loaded = function (success) {
if (success) {
window.js_track_loaded = null;
if (window.aid) {
/ globals Monkey /
Monkey && Monkey.set && Monkey.set('aid',window.aid);
}
}
};

// 跨站资源统计
/ (function (doc) {
var s = doc.createElement('script');
s.src = HAO.httpsTrans('http://s0.hao123img.com/res/js/fe/cspalog.js') + '?t=' + (+new Date);
var parent = doc.getElementsByTagName('script')[0].parentNode;
parent.appendChild(s);
})(document); /
};
@H_301_25@BigPipe.hooks["__cb_0_13"]=function(){'use strict';

require.defer(["fe:widget/js/base/jquery.js","fe:widget/js/base/detect.js","tuijian:widget/index/kuaixun.js"],function ($,detect,kuaixun) {
$(document).ready(function() {
detect();
kuaixun.init();
});
});
};
@H_301_25@BigPipe.setResourceMap({"d8b3cc9ac_29e3":{"src":"http:\/\/s1.hao123img.com\/resource\/fe\/pkg\/aio-eef856ab5.231bb088c.css","type":"css","deps":[],"mods":["fe:resource\/css\/base.less"]},"38645dd_f7dd":{"src":"http:\/\/s2.hao123img.com\/resource\/tuijian\/css\/hotrank.38645dd.css","mods":["tuijian:resource\/css\/hotrank.less"]},"8d1d978b0_a316":{"src":"http:\/\/s1.hao123img.com\/resource\/fe\/widget\/ui\/header\/common\/v2\/header.8d1d978b0.css","mods":["fe:widget\/ui\/header\/common\/v2\/header.less"]},"6cca09af6_f07f":{"src":"http:\/\/s0.hao123img.com\/resource\/fe\/widget\/ui\/header\/common\/v2\/logo\/logo.6cca09af6.css","mods":["fe:widget\/ui\/header\/common\/v2\/logo\/logo.less"]},"a0832ac19_fb25":{"src":"http:\/\/s1.hao123img.com\/resource\/fe\/widget\/ui\/header\/common\/v2\/sitemap\/sitemap.a0832ac19.css","mods":["fe:widget\/ui\/header\/common\/v2\/sitemap\/sitemap.less"]},"25330c25d_ce62":{"src":"http:\/\/s2.hao123img.com\/resource\/fe\/widget\/ui\/header\/common\/v2\/adv\/adv.25330c25d.css","mods":["fe:widget\/ui\/header\/common\/v2\/adv\/adv.less"]},"deba0d4c0_c8fe":{"src":"http:\/\/s0.hao123img.com\/resource\/fe\/widget\/ui\/header\/common\/v2\/form\/form.deba0d4c0.css","mods":["fe:widget\/ui\/header\/common\/v2\/form\/form.less"]},"1c81d5fc6_a695":{"src":"http:\/\/s0.hao123img.com\/resource\/fe\/widget\/ui\/header\/common\/v2\/tools\/tools.1c81d5fc6.css","mods":["fe:widget\/ui\/header\/common\/v2\/tools\/tools.less"]},"0c7877e81_8719":{"src":"http:\/\/s2.hao123img.com\/resource\/fe\/widget\/ui\/header\/common\/v2\/nav\/nav.0c7877e81.css","mods":["fe:widget\/ui\/header\/common\/v2\/nav\/nav.less"]},"6e9548c75_e646":{"src":"http:\/\/s2.hao123img.com\/resource\/fe\/widget\/ui\/header\/common\/v2\/tuiguang\/tuiguang.6e9548c75.css","mods":["fe:widget\/ui\/header\/common\/v2\/tuiguang\/tuiguang.less"]},"38645dd_0f3e":{"src":"http:\/\/s0.hao123img.com\/resource\/tuijian\/widget\/index\/hotrank\/hotrank.38645dd.css","mods":["tuijian:widget\/index\/hotrank\/hotrank.less"]},"3f6d691_9321":{"src":"http:\/\/s2.hao123img.com\/resource\/tuijian\/widget\/index\/hotrank\/index\/slider\/slider.3f6d691.css","mods":["tuijian:widget\/index\/hotrank\/index\/slider\/slider.less"]},"4d7a174_ccfc":{"src":"http:\/\/s0.hao123img.com\/resource\/tuijian\/widget\/index\/hotrank\/common\/slider\/slider.4d7a174.css","mods":["tuijian:widget\/index\/hotrank\/common\/slider\/slider.less"]},"9e71d5b_bed3":{"src":"http:\/\/s0.hao123img.com\/resource\/tuijian\/widget\/index\/hotrank\/index\/news\/news.9e71d5b.css","mods":["tuijian:widget\/index\/hotrank\/index\/news\/news.less"]},"b016c1d_d1a3":{"src":"http:\/\/s1.hao123img.com\/resource\/tuijian\/widget\/index\/hotrank\/index\/fyb\/fyb.b016c1d.css","mods":["tuijian:widget\/index\/hotrank\/index\/fyb\/fyb.less"]},"e073b71_9403":{"src":"http:\/\/s0.hao123img.com\/resource\/tuijian\/widget\/index\/hotrank\/index\/top\/top.e073b71.css","mods":["tuijian:widget\/index\/hotrank\/index\/top\/top.less"]},"77f7c66_45f3":{"src":"http:\/\/s0.hao123img.com\/resource\/tuijian\/widget\/lift\/lift.77f7c66.css","mods":["tuijian:widget\/lift\/lift.less"]},"95a138325_0731":{"src":"http:\/\/s2.hao123img.com\/resource\/fe\/pkg\/aio-8155b5719.3dd99d32e.css","mods":["fe:widget\/ui\/footer\/common\/footer.less"]},"ed29b1dff_99f2":{"src":"http:\/\/s1.hao123img.com\/resource\/fe\/pkg\/aio-752ba7752.ed29b1dff.js","type":"js","mods":["fe:widget\/js\/base\/jquery.js"]},"499abaa0e_acda":{"src":"http:\/\/s0.hao123img.com\/resource\/fe\/pkg\/aio-eef856ab5.499abaa0e.js","deps":["ed29b1dff_99f2","15f327f0a_5d72"],"mods":["fe:widget\/js\/base\/browser.js","fe:widget\/js\/base\/fixreferrer.js"]},"15f327f0a_5d72":{"src":"http:\/\/s0.hao123img.com\/resource\/fe\/pkg\/aio-95cc3013d.15f327f0a.js","deps":["ed29b1dff_99f2"],"mods":["fe:widget\/js\/base\/cookie.js"]},"331938377_b942":{"src":"http:\/\/s0.hao123img.com\/resource\/fe\/pkg\/aio-1c2d6f9f2.2b182a527.css","mods":["fe:widget\/ui\/header\/common\/header.less"]},"2009b1512_46d0":{"src":"http:\/\/s0.hao123img.com\/resource\/fe\/pkg\/aio-1c2d6f9f2.2009b1512.js","15f327f0a_5d72","331938377_b942"],"mods":["fe:widget\/js\/base\/sethome.js","fe:widget\/js\/lib\/events.js","fe:widget\/js\/base\/login.js","fe:widget\/js\/third\/arttemplate\/template-native.js","fe:widget\/js\/base\/autocomplete.js","fe:widget\/js\/base\/search.js","fe:widget\/ui\/header\/common\/header.js"]},"9a092a7f1_2a6f":{"src":"http:\/\/s0.hao123img.com\/resource\/fe\/widget\/js\/util\/slider.9a092a7f1.js","mods":["fe:widget\/js\/util\/slider.js"]},"f271c78_c7d7":{"src":"http:\/\/s0.hao123img.com\/resource\/tuijian\/widget\/lift\/lifttop.f271c78.js","mods":["tuijian:widget\/lift\/lifttop.js"]},"4d39d64_93de":{"src":"http:\/\/s1.hao123img.com\/resource\/tuijian\/widget\/index\/content\/shareEvent.4d39d64.js","mods":["tuijian:widget\/index\/content\/shareEvent.js"]},"3ac67f28c_b365":{"src":"http:\/\/s2.hao123img.com\/resource\/fe\/pkg\/aio-8155b5719.3ac67f28c.js","mods":["fe:widget\/js\/base\/addbookmark.js"]},"67402ee5d_d72b":{"src":"http:\/\/s2.hao123img.com\/resource\/fe\/widget\/js\/base\/track.67402ee5d.js","mods":["fe:widget\/js\/base\/track.js"]},"f97e9ecfd_31c5":{"src":"http:\/\/s1.hao123img.com\/resource\/fe\/widget\/js\/base\/detect.f97e9ecfd.js","deps":["67402ee5d_d72b"],"mods":["fe:widget\/js\/base\/detect.js"]},"2e29525_fe44":{"src":"http:\/\/s1.hao123img.com\/resource\/tuijian\/widget\/index\/kuaixun.2e29525.js","mods":["tuijian:widget\/index\/kuaixun.js"]},"5a7c104a87959":{"src":"http:\/\/s2.hao123img.com\/resource\/fe\/js\/lib\/main.5a7c104a8.js","mods":["fe:resource\/js\/lib\/main.js"]}});
@H301_25@BigPipe.onPageletArrive({"id":null,"children":[],"renderMode":"default","parent":null,"deps":{"beforedisplay":["d8b3cc9ac_29e3","95a138325_0731"],"load":["ed29b1dff_99f2","499abaa0e_acda","2009b1512_46d0","9a092a7f1_2a6f","f271c78_c7d7","4d39d64_93de","3ac67f28c_b365"]},"hooks":{"load":["cb_0_1","cb_0_2","cb_0_3","cb_0_4","cb_0_5","cb_0_6","cb_0_7","cb_0_8","cb_0_9","cb_0_10","cb_0_11","cb_0_12","__cb_0_13"]}});

筛选数据

以网页中的综艺热点部分

相关源代码如下

　　通过分析可知，‘综艺'模块与其他模块都位于

名称位于

cheerio

我们怎么从源代码中获取到有用的数据呢？首先，nodeJS不支持document对象。如果要使用笨办法，只能使用正则表达式来处理

cheerio 是nodejs特别为服务端定制的，能够快速灵活的对JQuery核心进行实现。它工作于DOM模型上，且解析、操作、呈送都很高效

【安装】

@H_529_403@

【使用】

它的使用方法和jQuery相当类似，上手非常容易。以获取综艺热度前10名的节目名称为例

搜索量前10的综艺节目标题 var result = []; //将页面源代码转换为$对象 var $ = cheerio.load(data); //查找每个综艺节目标题的外层div var temp_arr = $('[monkey = "zy"]').find('.point-bd').find('.point-title'); //将综艺节目标题依次保存到结果数组中 temp_arr.each(function(index,item){ result.push($(item).text()); }) //[ '变形计','来吧冠军','拜托了冰箱','昆仑决','天生是优我','姐姐好饿','脑力男人时代','奔跑吧兄弟','我想和你唱','玫瑰之旅' ] console.log(result); }

爬虫代码

下面将hao123网页中的'实时热点'、'今日热点'、'民生热点'、'电影'、'电视剧'、'综艺'这6部分的排名爬下来，分别到对象名为'result'中的数组中，分别命令为'ss'、'jr'、'ms'、'dy'、'dsj'、'zy'

【代码如下】

搜索量前10的名称 //对象名为榜单名，如'实时热点' //对象内容为10个标题名称组成的数组 var result = {}; //将页面源代码转换为$对象 var $ = cheerio.load(data); //查找'实时热点'、'今日热点'、'民生热点'、'电影'、'电视剧'、'综艺'这6个榜单所在的div var temp_div = $('.top-wrap');

//保存榜单名称
var temp_title = [];

temp_div.each(function(index,item){
//查找榜单名，并保存到temp_title文件夹中
temp_title.push($(item).find('h2').text());

//查找每类下每个标题的外层div
var temp_arr = $(item).find('.point-bd').find('.point-title');

//将result下的每个榜单初始化为一个数组
var innerResult = result[temp_title[index]] = [];

//将节目标题依次保存到相应榜单的数组中
temp_arr.each(function(_index,_item){
innerResult.push($(_item).text())
})
})
console.log(result);
}

【结果如下】

以上这篇nodeJS实现简单网页爬虫功能的实例(分享)就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持编程之家。

• 上一篇：详解Node.js 命令行程序开发教程下一篇：Node.js 使用命令行工具检查更新

猜你在找的Node.js相关文章

[javascript] typescript的安装

现在的js代码都是这种高级点的方式语法 ， 就是ts语法 ，要使用ts语法那就要先安装一下 先...

作者：前端之家 时间：2021-02-05

node版本管理工具nvm

nvm是node版本管理工具 为了解决node各种版本存在不兼容现象 nvm是让你在同一台机器上安装...

作者：前端之家 时间：2020-12-29

node起一个简单服务，打开本地项目或文件浏览

1、安装nodejs 2、在项目文件夹目录下创建一个js文件，命名server.js(自定义名称),内容如下...

作者：前端之家 时间：2020-12-29

path的join和resolve的使用区别

1.连接路径：path.join([path1][, path2][, ...]) path.join()方法可以连接任意多个路径字...

作者：前端之家 时间：2020-12-29

nodejs与javascript中的aes加密

简介 1.aes加密简单来说，在密码学中又称Rijndael加密法，是美国联邦政府采用的一种区块加...

作者：前端之家 时间：2020-12-23

带你玩转七牛云存储——高级篇

七牛云图片存储优点 1. 支持各种尺寸的图片缩放； 2. 支持图片自动压缩； 3. 支持水印添加...

作者：前端之家 时间：2020-12-23

VueJs生产环境部署

VueJs为客户端语言，所以部署的时候是不需要基于nodejs或其他服务器运行环境，只需要像其他...

作者：前端之家 时间：2020-12-23

vuejs深入浅出—基础篇

一、从HelloWorld说起 任何语言的都是从Hello World开始的，VueJs也不例外，直接上代码： ...

作者：前端之家 时间：2020-12-23

你必须知道的session与cookie

Session本质 提到Session我们能联想到的就是用户登录功能，而本身我们使用Session的基础是...

作者：前端之家 时间：2020-12-23

es6新特性分享

1、字符串查找es5使用是indexOf() 返回字符第一次出现的位置int值es6新增了3个方法：inclu...

作者：前端之家 时间：2020-12-23