如何使用 Puppeteer 捕获页面中的所有链接？

Question

尝试捕获页面中的所有

<a>

console.log 返回未定义，但我不明白为什么 这是

const anchors = Array.from(document.querySelectorAll(sel));

正确吗？

const puppeteer = require('puppeteer');

(async () => {
  const browser = await puppeteer.launch({
                                            headless: false,
                                            userDataDir: "C:\\Users\\johndoe\\AppData\\Local\\Google\\Chrome\\User Data\\Default"
                                        });
  const page = await browser.newPage();
  await page.setViewport({
    width: 1920,
    height: 1080,
    deviceScaleFactor: 1,
  });
  await page.goto('https://www.facebook.com/groups/632312010245152/members');
  
  //https://github.com/puppeteer/puppeteer/blob/main/examples/search.js
  let membri = await page.evaluate((sel) => { 
    const anchors = Array.from(document.querySelectorAll(sel));
    return anchors;
  }, 'a');
  console.log(membri);
})();

Answer 1

const findLinks = await page.evaluate(() =>
  Array.from(document.querySelectorAll("a")).map((info) => ({
    information: info.href.split()
  }))
);
links = [];
findLinks.forEach((link) => {
  if (link.information.length) {
    links.push(link.information);
  }
});
await console.log(links);
await page.close();
return links;

不确定这是否是最优化的解决方案，但它确实有效。如果您能给我发送这段代码的清理版本，我将非常感激:)

Answer 2

const arrayList = await page.evaluate(() => {
    const nodeListLinks = document.querySelectorAll('a'),
          array = [...nodeListLinks],
          list = array.map(({href}) => ({href}))
    return list
})

console.log(arrayList)