node的爬取网页图片

Question

使用node爬区一个网站当中所有的图片的链接，不用下载，该怎么样写代码

Answer 1

给你一个案例

const http = require("http");
const fs = require('fs');
const cheerio = require('cheerio');
const request = require('request');
let iconv = require("iconv-lite");
let index = 13;
// const url = 'http://www.netbian.com'
const url = 'http://www.netbian.com/index_13.htm'

const getData = (url) => {
    http.get(url, (res) => {
        let buffer = [];
        let bufferLength = 0;
        res.on("data", chunk => {
            buffer.push(chunk);
            bufferLength += chunk.length;
        });
        res.on("end", () => {
            // 现在将所有buffer组合为一个整体buffer
            let bufferData = Buffer.concat(buffer, bufferLength);
            // 使用 iconv 以 GBK 编码转换为字符串。
            var html = iconv.decode(bufferData, "GBK");
            // console.log(html); // 现在得到的页面内容就没有乱码的了。
            var $ = cheerio.load(html);
            $('.list img').each((i, el) => {
                const text = $(el).attr('alt').replace(/\s*/g,"")
                const img_url = $(el).attr('src')
                console.log(text,'=====',  index + '_' + (i+1))
                console.log(img_url)
                request.head(img_url, function(error, res,body){
                    if(error){
                        console.log('失败了')
                    }
                });
                //通过管道的方式用fs模块将图片写到本地的images文件下
                request(img_url).pipe(fs.createWriteStream('./images/' + index + '_' + (i+1) + '.jpg'));
            })
            if (index > 1228) return;
            index++;
            getData(`http://www.netbian.com/index_${index}.htm`);
        });
    });
}

fs.stat('images', (error,stats) => {
    if (error) {
        fs.mkdir("images", (err) => {
            if (err) console.log('err', err)
            console.log('创建目录成功');
        });
    }
})
getData(url)




```javascript

```