对于抓取，我认为最好使用无头浏览器，如puppeteer。一些网站阻止 AJAX 请求。
下面是一个如何使用 puppet 师做你想要的例子。
1.获取所有a-tag和相应的href
1.转到您检索到的每个链接，并获得所有的图像链接

const puppeteer = require("puppeteer");

(async () => {
let browser;

async function initialisePage(link) {
    const page = await browser.newPage();
    // page.setDefaultNavigationTimeout(10000);
    // page.setDefaultTimeout(10000);
    await page.setExtraHTTPHeaders({
        'Accept-Language': 'en'
    });
    await page.setGeolocation({
        latitude: 40.75073264981463,
        longitude: -73.9859968851446
    });
    await page.setViewport({ width: 1920, height: 1080});
    await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36');
    await page.goto(link);

    await page.evaluateOnNewDocument(() => {
        Object.defineProperty(navigator, "language", {
            get: function() {
                return "en";
            }
        });
        Object.defineProperty(navigator, "languages", {
            get: function() {
                return ["en"];
            }
        });
    });

    const viewPortHeight = await page.evaluate(() => {
        return window.document.documentElement.scrollHeight;
    });

    await page.setViewport({
        width: 1920,
        height: Math.round(viewPortHeight)
    });

    try {
        await page.waitForNetworkIdle(); // wait till all requests have been finished, sometimes websites might fetch data using fetch, ajax and what not
    }
    catch (e) {
        console.error(e);
    }
    //accept cookies
    await page.evaluate(_ => { // script to try to accept cookies, maybe this accept cookies blocks the content
        const iframes = [...document.getElementsByTagName("iframe")];
        for (let iframe of iframes) {
            iframe.remove();
        }
        function xcc_contains(selector, text) {
            const elements = document.querySelectorAll(selector);
            return Array.prototype.filter.call(elements, function(element){
                return RegExp(text, "i").test(element.textContent.trim());
            });
        }
        const _xcc = xcc_contains('a, button', '^(Accept All|Accept|I understand|Agree|Okay|Agree & continue|OK)$');
        if (_xcc != null && _xcc.length !== 0) { _xcc[0].click(); }
    });

    /*try { // remove this block if you are sure there are no redirects after accepting cookies
        await page.waitForNavigation({
            timeout: 1000 // only wait 1 seconds because it might not redirect you
        }); // because the accept cookies click might redirect you
    }
    catch (e) {
        console.error("wait nav error", e);
    }*/

    return page;
}

try {
    browser = await puppeteer.launch({
        headless: true,
        args: ['--lang=en', '--accept-lang=en', '--no-sandbox']
    });

    const page = await initialisePage('https://nu.edu.pk/');

    const links = await page.evaluate(() => { // get all hrefs from all a tags
        return [...new Set([...document.getElementsByTagName("a")].filter(value => value.href).map(value => value.href))]; // new set because you have to make sure it's unique
    });

    let images = [];

    console.log("Getting images for ", links.length, " links...");

    for (let link of links) {
        console.log("Getting images for ", link);
        try {
            const page = await initialisePage(link);
            const imageLinks = await page.evaluate(() => { // get all image links for the current a tag
                return [...document.getElementsByTagName("img")].filter(value => value.src).map(value => value.src);
            });
            images.push(...imageLinks);
            console.log(imageLinks);

            await page.close();
        }
        catch (e) {
            console.error(e);
        }

    }

    images = new Set(images); // make the imageLinks unique
    console.log(images)
    await page.close();
}
catch (e) {
    console.error(e);
    throw e;
}
finally {
    browser && await browser.close();
}
})();

下面的代码可以正常工作，但存在一些问题
1.硬编码.jpg扩展名
1.它不处理循环链接。
1.它将在无效链路上崩溃
1.你将需要异步等待或承诺代码。
1.您必须添加额外的逻辑来清理URL
如果你运行下面的代码，它会在一段时间后中断。

const cheerio = require('cheerio');
const request = require('request');
const fs = require('fs');

const url = 'https://nu.edu.pk/';

async function downloadImages(url) {
  request(url, (error, response, html) => {
    if (!error && response.statusCode == 200) {
      const $ = cheerio.load(html);

      const images = $('img');

      images.each((i, image) => {
        const src = $(image).attr('src');
        console.log({ src })
        const fileName = `IMAGE_NAME-${i}.jpg`;
        const imgPath = `${url}${src}`;
        console.log({ imgPath })
        request(imgPath).pipe(fs.createWriteStream(fileName));
      });

      const links = $('a');

      links.each((i, link) => {
        const href = $(link).attr('href');
        downloadImages(href);
      });
    }
  });
}

downloadImages(url);