小小代码，有点意思哈
var http = require('http')
var cheerio = require('cheerio')
var Promise = require('bluebird')
var baseUrl = 'http://www.imooc.com/learn/'
var videoIds = [348,259,197,134,75]
function filterChapters(html) {
var $ = cheerio.load(html)
var chapters = $('.chapter')
var title = $('.course-infos .path span').text()
// var num = parseInt($($('.meta-value strong')[3]).text().trim(), 10)
var num = 0
// coursesData = {
// title: title,
// number: number,
// videos: [{
// chapterTitle : '',
// videos : [
// title: '',
// id: ''
// ]
// }]
// }
var courseData = {
video: [],
num: num,
title: title
}
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 = $(this).find('.J-media-item')
var videoTitle = video.text()
var id = video.attr('href').split('video/')[1]
chapterData.videos.push({
title: videoTitle,
id: id
})
})
courseData.video.push(chapterData)
})
return courseData
}
function printCourseInfo(coursesData) {
coursesData.forEach(function(courseData){
console.log('------------------------------------------'+courseData.num + '人学过 '+ courseData.title +'------------------------------------------'+ '\n' )
courseData.video.forEach(function(val) {
console.log('############# ' + (val.chapterTitle).replace(/(^\s*)|(\s*$)/g, "") + '############# ')
console.log("\n")
// console.log('\t'+'【 id'+ (val.videos[0].id).replace(/(^\s*)|(\s*$)/g, "")+' 】'+((val.videos)[0].title).replace(/(^\s*)|(\s*$)/g, "") +'\n')
// console.log("-----------------------------------------------------")
val.videos.forEach(function(item){
console.log('\t 【 id '+item.id+" 】 "+(item.title).replace(/(^\s*)|(\s*$)/g, ""))
})
})
})
}
function getPageAsync(url){
return new Promise(function(resolve, reject){
console.log('正在爬取'+url)
http.get(url, function(res){
var html = ''
res.on('data', function(data) {
html += data
})
res.on('end', function() {
resolve(html)
})
}).on('error', function(e) {
reject(e)
console.log('获取数据失败');
})
})
}
var fetchCourseArray = []
videoIds.forEach(function(id){
fetchCourseArray.push(getPageAsync(baseUrl + id))
})
Promise
.all(fetchCourseArray)
.then(function(pages){
var coursesData = []
pages.forEach(function(html){
var course = filterChapters(html)
coursesData.push(course)
})
coursesData.sort(function(a, b){
return a.number < b.number
})
printCourseInfo(coursesData)
})
