nodejs 之 小爬虫

一、简单的单页面
var http = require('http') var url = 'http://www.imooc.com/learn/348' 
http.get(url,function(res){ 
  var html = ''
    //有data触发时
    res.on('data',function(data){
        html += data
    })
    res.on('end',function(){
        console.log(html)
    })
//出现异常时
}).on('error',function(){
    console.log('获取出错')
})

var server = http.createServer(function(req,res){
        res.writeHead(200,{'Content-Type':'text/plain'})
        res.end();
    })
server.listen(2017)

  

运行结果

二、获取页面的课程列表

安装cheerio

cmd 执行命令 npm install  cheerio 然后就可以require cheerio

var http = require('http')
var cheerio = require('cheerio')
var url = 'http://www.imooc.com/learn/348'

//过滤页面,获取到列表的名称与id等信息 与javascript方法一致 function filterChapters(html){ var $ = cheerio.load(html) // console.log($) var chapters = $('.chapter') 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, video:[] } // console.log(videos + '24') videos.each(function(item){ // var video = $(this).find('.studyvideo') var videoTitle = $(this).text() var id = $(this).attr("data-media-id") chapterData.video.push({ title:videoTitle, id:id }) }) courseData.push(chapterData) }) return courseData } //将获取到的信息打印出来 function printCourseInfo(courseData) { courseData.forEach(function(item){ var chapterTitle = item.chapterTitle item.video.forEach(function(video){ console.log('【' +video.id+'】' +video.title +' ') }) }) } http.get(url,function(res){ var html = '' res.on('data',function(data){ html += data }) res.on('end',function(){ //过滤页面信息 // console.log(html) var courseData = filterChapters(html) printCourseInfo(courseData) }) }).on('error',function(){ console.log('获取出错') }) var server = http.createServer(function(req,res){ res.writeHead(200,{'Content-Type':'text/plain'}) res.end(); }) server.listen(1337)

运行结果

原文地址:https://www.cnblogs.com/xwtbk/p/7132618.html