详解如何使用Node.js开发一个简单图片爬取功能

# PNPM
pnpm add crawler
# NPM
npm i -S crawler
# Yarn 
yarn add crawler

// index.js
const Crawler = require("crawler");

// index.js
let crawler = new Crawler({
    timeout:10000,
    jQuery:true,
})
function getImages(uri) {
    crawler.queue({
        uri,
        callback: (err, res, done) => {
            if (err) throw err;
        }
    })
}

// index.js
let data = []
function getImages(uri) {
    crawler.queue({
        uri,
        callback: (err, res, done) => {
            if (err) throw err;
            let $ = res.$;
            try {
                let $imgs = $("img");
                Object.keys($imgs).forEach(index => {
                    let img = $imgs[index];
                    const { type, name, attribs = {} } = img;
                    let src = attribs.src || "";
                    if (type === "tag" && src && !data.includes(src)) {
                        let fileSrc = src.startsWith('http') ? src : `https:${src}`
                        let fileName = src.split("/")[src.split("/").length-1]
                        downloadFile(fileSrc, fileName) // 下载图片的方法
                        data.push(src)
                    }
                });
            } catch (e) {
                console.error(e);
                done()
            }
            done();
        }
    })
}

const { default: axios } = require("axios");
const fs = require('fs');

async function downloadFile(uri, name) {
    let dir = "./imgs"
    if (!fs.existsSync(dir)) {
        await fs.mkdirSync(dir)
    }
    let filePath = `${dir}/${name}`
    let res = await axios({
        url: uri,
        responseType: 'stream'
    })
    let ws = fs.createWriteStream(filePath)
    res.data.pipe(ws)
    res.data.on("close",()=>{
        ws.close();
    })
}

// index.js
getImages("https://juejin.cn/")

node index.js