nodejs爬虫淘宝详情图

第一步：cmd 进入命令版界面
第二步：输入D: 进入D盘
第三步：创建项目文件：mkdir nodetaobao(项目名)
第四步：进入创建的项目：cd nodetaobao
第五步：初始化项目：npm init
然后安装各种依赖模块，新建一个images文件夹装爬虫下拉的图片，创建start.js文件
复制一下内容代码，然后node start.js就可以下载文件了

var https = require('https')
var request = require('request')
var cheerio = require('cheerio')
var fs = require('fs')
var images = require('images')


// 商品详情网址(每次只需替换这个地址就行了) 运行文件 node start.js
var url = 'https://item.taobao.com/item.htm?id=592293023396&scm=1007.12144.81309.359571_0_0&pvid=56bf99e6-c060-4ff0-8354-998718dde11f&utparam=%7B%22x_hestia_source%22%3A%22359571%22%2C%22x_object_type%22%3A%22item%22%2C%22x_mt%22%3A8%2C%22x_src%22%3A%22359571%22%2C%22x_pos%22%3A9%2C%22x_pvid%22%3A%2256bf99e6-c060-4ff0-8354-998718dde11f%22%2C%22x_object_id%22%3A592293023396%7D'

function startPage(x) {
  https.get(x, function(res) {
    var html ='' //用来存储请求网页的整个html内容
    res.setEncoding('utf-8') // 防止中文乱码
    // 监听data事件，每次取一次数据
    res.on('data', function(chunk) {
      html +=chunk
      
    })
    res.on('end', function() {
      var $ =cheerio.load(html) // 采用cheerio模块解析html
      var content = $('html').find('script')
      // console.log(content)
      content.each(function(i, elem) {
        var script = $(this).html();
        if (script.match('apiImgInfo  :')){
          var newarry = script.split(',')
          for (const key in newarry) {
           if(newarry[key].indexOf('apiImgInfo  ')>0){
            var newUrl = newarry[key].split(':')
            // console.log(newUrl)
            var pageUrl = 'http:'+newUrl[1].replace(/\\/g, "").replace(/\'/g,'').replace(/^\s*/,"");
            // console.log(pageUrl)
            // var pageUrl= 'http://tds.alicdn.com/json/item_imgs.htm?t=TB1B7_Tbhn1gK0jSZKPXXXvUXXa&sid=2144097515&id=573011542300&s=f4fc2076503684f96bf9fa5a7eccecde&v=2&m=1'
            var pageUrls = pageUrl.split('&')
            for (const key in pageUrls) {
              if(pageUrls[key].indexOf('id') > 0) {
                var idVaule = pageUrls[key].split('=')[1]
                setTimeout(() => {
                  sendpage(pageUrl,idVaule)
                }, 2200);
                
              }
            }
           }
          }
        }
    });
    getMainImages($)
    })
  })
}

// 获取详情图
function sendpage(y,idVaule){
  request({url:y}, function (error, response, body) {
    if (!error && response.statusCode == 200) {
        var reuslt = body.split(':')
        for (const key in reuslt) {
          if(reuslt[key].indexOf(idVaule)>0){
            var index = reuslt[key].indexOf(',')
            var text = reuslt[key].slice(index+1).replace(/\"/g, "")
            var img_src = 'https://img.alicdn.com/imgextra/i2/'+idVaule+'/' + text; //获取图片的url
             // 采用request模块，向服务器发起一次请求，获取图片资源
            request.head(img_src, function(err,res,body) {
              if(err) {
                console.log(err)
              }
            })
            // request(img_src).pipe(fs.createWriteStream('./images/' + '详情图' + key + '.jpg'))
     
            var writeStream = fs.createWriteStream('./images/' + '详情图' + key +'.jpg');
            var readStream = request(img_src)
            readStream.pipe(writeStream);
            readStream.on('end', function(response) {
                console.log('详情图'+key+'下载成功');
                writeStream.end();
            });
            writeStream.on("finish", function() {
                // console.log("ok");
                setTimeout(() => {
                  images('./images/'+'详情图' + key + '.jpg').size(750).save('./images/'+'详情图' + key + '.jpg');
                }, 2000);
            })
          }
        }
      }
    })
  }

// 获取主图
 function getMainImages($) {
  $('.tb-s50 a img').each(function(index,item){
    var srcImg = ''
    if($(this).attr('data-src').indexOf('htt') > -1){
      var srcImg =$(this).attr('data-src').replace('50x50','800x800')
    } else{
      var srcImg ='https:'+$(this).attr('data-src').replace('50x50','800x800')
    }
      
    // 采用request模块，向服务器发起一次请求，获取图片资源
       request.head(srcImg, function(err,res,body) {
        if(err) {
          console.log(err)
        }
      })
      // request(srcImg).pipe(fs.createWriteStream('./images/' + '主图' + index +'.jpg'))

      var writeStream = fs.createWriteStream('./images/' + '主图' + index +'.jpg');
      var readStream = request(srcImg)
      readStream.pipe(writeStream);
      readStream.on('end', function(response) {
          console.log('主图'+index+'下载成功');
          writeStream.end();
      });
      writeStream.on("finish", function() {
          // console.log("ok");
          images('./images/'+'主图' + index + '.jpg').size(750).save('./images/'+'主图' + index + '.jpg');
      })
  })
 }


startPage(url)

一定要安装nodejs才可以
运行成功下载的图片