cheerio 安装方法 以及 爬虫代码
安装方法：
npm install -g cheerio
爬虫代码1：
var http = require('http');
var url = 'http://www.imooc.com/learn/348';
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('获取课程数据出错！')
});
爬虫代码2：
var http=require('http');
var cheerio=require('cheerio');
var url='http://www.imooc.com/learn/348';
function filterChapters(html){
var $ = cheerio.load(html);
var chapters = $('.chapter');
/**
[{
chapterTitle:'',
videos:[
title:'',
id:''
]
}]
*/
var courseData=[];
chapters.each(function(item){
var chapter = $(this);
var chapterTitle = chapter.find('strong').text();
var videos = chapter.find('.video').children('li');
var chapterData = {
chapterTitle : chapterTitle,
videos :[]
};
videos.each(function(item){
var video = $(this).find('.J-media-item');
var videoTitle = video.text();
var id = video.attr('href').split('video/')[1];
chapterData.videos.push({
title: videoTitle,
id:id
});
});
courseData.push(chapterData);
});
return courseData;
};
function printCourseInfo(courseData){
courseData.forEach(function(item){
var chapterTitle = item.chapterTitle;
console.log(chapterTitle+"\n");
item.videos.forEach(function(item){
console.log('【'+item.id+'】'+item.title+'\n');
});
});
};
http.get(url , function(res){
var html='';
res.on('data',function(data){
html+=data;
});
res.on('end',function(){
// console.log(html);
var courseData = filterChapters(html);
//打印
printCourseInfo(courseData);
});
}).on('error',function(){
console.log('获取课程数据出错！')
});
