/*超简易的一个爬虫，爬慕课网的数据，并做处理*/

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

//http模块发出get请求，执行回调函数
http.get(url, (res) => {
  var html = ''

  //res触发data事件，拼接html字符串
  res.on('data', (data) => {
    html += data
  })

  //res最后触发end事件，输出html字符串源码
  res.on('end', () => {
    let courseData = filterChapters(html) //res结束后，把拼装好的html过滤处理
    printCourseInfo(courseData)
  })
}).on('error', () => {
  console.log('获取数据出错！');
})

//用cheerio模块解析获取的html字符串，爬取数据
function filterChapters(html) {
  let $ = cheerio.load(html)
  let chapters = $('.chapter')

  // 期望获取的数据结构
  //   [{
  //     chapterTitle: '',
  //     videos: [{
  //       title: '',
  //       id: ''
  //     }]
  //   }]

  let courseData = []

  chapters.each((index, item) => { //不能用箭头函数，因为没有this
    let chapter = $(item) //用箭头函数就要找出回调,回调参数log大法找
    let chapterTitle = chapter.find('h3 strong').text()
    let videos = chapter.find('.video').children('li')
    let chapterData = {
      chapterTitle,
      videos: []
    }

    videos.each((index, item) => { //不能用箭头函数，因为没有this
      let video = $(item) //用箭头函数就要找出回调,回调参数log大法找
      let videoTitle = video.find('.J-media-item').text()
      let id = video.data('media-id')
      chapterData.videos.push({
        title: videoTitle,
        id: id
      })
    })

    courseData.push(chapterData)
  })
  return courseData
}

//打印出爬取信息
function printCourseInfo(courseData) {
  courseData.forEach((item) => {
    let chapterTitle = item.chapterTitle
    console.log(chapterTitle);
    item.videos.forEach((video) => {
      console.log(`[${video.id}] ${video.title}`);
    })
  })
}