抓包代码

//引入模块
const http = require('http')
const fs = require('fs')
const cheerio = require('cheerio')
const iconv = require('iconv-lite')
const request = require('request')
const async = require('async');

const urlList = [] //地址列表
var id = 0 //计数器

//由于煎蛋妹子图的地址格式一样，所以只要拼接地址就好了
for (var i = 193; i > 190; i--) {
  urlList.push('http://jandan.net/ooxx/page-' + i)
}

function getPages(url, callback) {
  http.get(url, res => {
    const html = []
    res.on('data', (chunk) => {
    html.push(chunk)
})
  res.on('end', () => {
    //如果网站是gbk编码，可以转成utf8，否则可能乱码
    const html1 = iconv.decode(Buffer.concat(html), 'utf8')
    //cheerio模块用来一jQuery的语法解析爬取的页面
    const $ = cheerio.load(html1, {
      decodeEntities: false
    })
    const link = []
    $('.view_img_link').each((i, v) => {
    link.push($(v).attr('href'))
})
  callback(null, link)
})
})
}


function saveImage(links) {
  if (!fs.existsSync(`images/jiandan`)) {
    fs.mkdirSync(`images/jiandan`)
  }

  //此处links为一个二维数组，每个元素也是数组，保存了每个地址的多张图片地址，所以需要合并
  var newArr = []
  for (var i = 0; i < links.length; i++) {
    newArr = newArr.concat(links[i])
  }

  console.log('length:' + newArr.length)

  async.mapLimit(newArr, 5, function (link, callback) {
    id++  //id充当计数器，保存一张图片就打印一次
    requestAndwrite(link, callback, id)
  }, function (err, results) {
    if (err) {
      console.log(err)
    } else {
      console.log(results)
    }
  })
}

var requestAndwrite = function (link, callback, id) {
  const url = 'http:' + link
  request.head(url, function (err, res, body) {
    if (err) {
      console.log(err)
    } else {
      request(url).pipe(fs.createWriteStream(`images/jiandan/${link.split('/').pop()}`)).on('close', function () {
        console.log(id)
        callback(null, 'result')
      })
    }
  })
}

//
async.mapLimit(urlList, 5, function (url, callback) {
  getPages(url, callback)
}, function (err, links) {
  saveImage(links)
})

　　

转载于:https://www.cnblogs.com/znj211985211/p/7267467.html