node.js实现简单爬虫示例详解

titles = [{
  chapterTitle: chapterTitle,
  id: id
}]

var http = require('http')
var url = 'http://www.imooc.com/course/list?c=nodejs'
http.get(url, function(res){
  var html = ''
  res.on('data', function(data){
    html += data
  })
  res.on('end', function(){
    var result = filterHml(html)
    print(result)
  })
}).on('error', function(){
  console.log('获取数据错误！')
})

function filterChapters(html) {
    var $ = cheerio.load(html)
    var chapters = $('.course-card-container')//以类名获取节点元素
    var titles = []
    chapters.each(function (item) {
        var chapter = $(this)
        var chapterTitle = chapter.find('h3').text()
        var id = chapter.find('a').attr('href').split('learn/')[1]
        titles.push({
            chapterTitle: chapterTitle,
            id: id
        })
    })
    return titles
}
function printCourseInfo(courseData){
    courseData.forEach(item => {
        console.log('【' + item.id + '】' + item.chapterTitle + '\n')
    });
}