nodeJS 学习--用cheerio 制作超简单的网络爬虫

前置: 
1.安装好了nodejs
2.npm i cheerio
3.jquery选择器基础知识

var https = require('https')
var cheerio = require('cheerio')

// 简书首页
var url = "https://www.jianshu.com/"

function filterSection(html) {
  //加载爬到的html结构
  var $ = cheerio.load(html)
  var noteList = $('.note-list')

  var sectionData = []

  noteList.each(function(item) {
    var content = $(this).find('.content')
    // note 作者
    var author = content.find('.author').find('.info').text()
    // note title
    var title = content.find('.title').text()
    // note 内容摘要 
    var abstract = content.find('.abstract').text()

    var noteListData = {
      author: author,
      title: title,
      abstract: abstract
    }
    sectionData.push(noteListData)
  })
  return sectionData

}

function print(sectionData) {
  sectionData.forEach((item) => {
    var author = item.author,
      title = item.title,
      abstract = item.abstract;

    console.log(author + '\n' + title + '\n' + abstract + '\n')
  })
}

https.get(url, (res) => {
  var html = ''
  res.on('data', (data) => {
    html += data
  })
  res.on('end', () => {
    var sectionData = filterSection(html)

    print(sectionData)
  }).on('error', () => {
    console.log('错误')
  })
})

 

转载于:https://www.cnblogs.com/footstep/p/8275084.html