Node.js实现简单的爬取的示例代码

//引入依赖

//https请求

const https = require('https');

//简称node版的jquery

const cheerio = require('cheerio');

//解决防止出现乱码

const iconv = require('iconv-lite')

//http请求

const request = require("request");

//负责读写文件

const fs = require('fs');

//处理文件路径

const path = require('path');

const url = 'https://unsplash.com/';

//方法对象

const util = {

 

  getsrc: function (url) {

    https.get(url, res => {

      const chunks = [];

      res.on('data', chunk => {

        // chunks里面存储着网页的html内容

        chunks.push(chunk);

      });

      res.on('end', e => {

 

        let ALL = [];

        //编码格式

        let html = iconv.decode(Buffer.concat(chunks), 'utf8');

        let $ = cheerio.load(html, { decodeEntities: false });

 

        //标签遍历

        $("figure img").each(function (idex, elent) {

          let $elent = $(elent);

          let $srcset = $elent.attr("srcset");

          if ($srcset != undefined) {

            let src = ($srcset.split(',').pop()).split('?')[0];

            ALL.push({

              src: src

            })

          }

        });

        //遍历数组 每个后面加.jpg

        ALL.forEach(item => {

          util.downloadimg(item.src, path.basename(item.src) + ".jpg", function () {

            console.log(path.basename(item.src) + ".jpg");

          });

        })

      });

 

      res.on('error', e => {

        console.log('Error: ' + e.message);

      });

    });

  },

 

  //运行主函数

  main: function () {

    console.log("------start--------");

    util.getsrc(url);

  },

  //下载图片函数

  downloadimg: function (src, srcname, callback) {

 

    //http请求

    request.head(src, function (err, res, body) {

      if (err) {

        console.log('err:' + err);

        return false;

      }

      console.log('res: ' + res);

      //保存数据，这里是防止未来得及记录数据又开始读取数据而导致数据丢失

      request(src).pipe(fs.createWriteStream('./img/' + srcname)).on('close', callback);

    });

  }

}

 

//主函数

util.main();