使用node 爬取网上图片

依赖模块用到了以下几个
var fs = require(‘fs’);
var request = require(“request”);
var cheerio = require(“cheerio”);
var mkdirp = require(‘mkdirp’);

cheerio是nodejs的抓取页面模块，为服务器特别定制的，快速、灵活、实施的jQuery核心实现，用于解析html
代码如下

var fs = require('fs');
var request = require("request");
var cheerio = require("cheerio");
var mkdirp = require('mkdirp');

//目标网址
var url = 'http://desk.zol.com.cn/pad/';

//本地存储目录到D盘
var dir = 'D:/images';

//创建目录
mkdirp(dir, function(err) {
    if(err){
        console.log(err);
    }
});

//发送请求
request(url, function(error, response, body) {
    if(!error && response.statusCode == 200) {
        var $ = cheerio.load(body);
        $('.pic img').each(function() {
            var src = $(this).attr('src');
            console.log('正在下载' + src);
            download(src, dir, Math.floor(Math.random()*100000) + src.substr(-4,4));
            console.log('下载完成');
        });
    }
});

//下载方法
var download = function(url, dir, filename){
    request.head(url, function(err, res, body){
        request(url).pipe(fs.createWriteStream(dir + "/" + filename));
    });
};