版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/u014744118/article/details/85565386
var https = require('https')
var cheerio = require('cheerio')
var baseUrl = 'https://www.imooc.com/learn/'
var url = 'https://www.imooc.com/learn/348'
var videoIds = [348, 259, 197, 134, 75]
function filterChapters(html) {
var $ = cheerio.load(html)
var chapters = $('.chapter')
var title = $('hd h2').text()
var number = parseInt($('.js-learn-num').text())
var coursesData = {
title: title,
number: number,
videos: []
}
chapters.each(function (item) {
var chapter = $(this)
var chapterTitle = chapter.find('.chapter-description').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
})
})
coursesData.videos.push(chapterData)
})
return coursesData
}
function printCourseInfo(coursesData) {
coursesData.forEach((courseData) => {
console.log(courseData.number) + '人学过' + courseData.title + '\n'
})
coursesData.forEach(courseData => {
console.log('###' + courseData.title + '\n')
courseData.videos.forEach((item) => {
var chapterTitle = item.chapterTitle
console.log(chapterTitle + '\n')
item.videos.forEach(video => {
console.log('【' + video.id + '】' + video.title + '\n')
})
})
});
}
function getPageAsync(url) {
return new Promise(function (resolve, reject) {
console.log("正在爬取" + url)
https.get(url, function (res) {
var html = ''
res.on('data', function (data) {
html += data
})
res.on('end', function () {
resolve(html)
})
}).on('error', function () {
console.log('获取出错')
reject(e)
})
})
}
var fetchCourseArray = []
videoIds.forEach((id) => {
fetchCourseArray.push(getPageAsync(baseUrl + id))
})
Promise.all(fetchCourseArray).then(function (pages) {
//
var courseData = []
pages.forEach(function (html) {
var courses = filterChapters(html)
courseData.push(courses)
})
courseData.sort((a, b) => {
return a.number < b.number
})
printCourseInfo(courseData)
})