Puppeteer脚本报错：page.waitForTimeout不是函数，求解决方案

运行Node.js Puppeteer脚本爬取LinkedIn职位时出现以下错误：

PS C:\Users\Win10\puppeteer-project> node linkedin_job_search.js
Retrying after 1 attempts...
C:\Users\Win10\puppeteer-project\linkedin_job_search.js:34
        await page.waitForTimeout(10000); // Wait for 10 seconds
                   ^

TypeError: page.waitForTimeout is not a function
    at C:\Users\Win10\puppeteer-project\linkedin_job_search.js:34:20

尝试过await waitForTimeout(10000)和await page.waitForTimeout(10000)两种方式，均无效。脚本代码如下：

const puppeteer = require('puppeteer');
const fs = require('fs');
const { waitForTimeout } = require('puppeteer-core');

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();

  // Navigate to LinkedIn login page
  await page.goto('https://www.linkedin.com/login');

  // Enter your LinkedIn email and password
  await page.type('#username', 'email');
  await page. Type('#password', 'password');

  // Submit the login form
  let retries = 0;
  let maxRetries = 3;

  while (retries < maxRetries) {
    try {
      await Promise.all([
        page.click('.btn__primary--large'),
        page.waitForNavigation({
          waitUntil: 'networkidle2',
          timeout: 60000, // 60 seconds
        }),
      ]);
      break;
    } catch (error) {
      if (retries < maxRetries - 1) {
        retries++;
        console.log(`Retrying after ${retries} attempts...`);
        await setTimeout(10000); // Wait for 10 seconds
      } else {
        console.error('Failed to log in after ' + maxRetries + ' attempts. Exiting...');
        await browser.close();
        process.exit(1);
      }
    }
  }

  // Navigate to the jobs search page
  await page.goto('https://www.linkedin.com/jobs/search/?keywords=Product%20Manager&location=India');

  // Wait for the search results to load
  await page.waitForSelector('.jobs-search-results__list');

  // Scrape the job listings
  const jobListings = await page.evaluate(() => {
    const listings = document.querySelectorAll('.jobs-search-results__list-item');
    return Array.from(listings).map((listing) => ({
      title: listing.querySelector('.job-card-list__title').textContent.trim(),
      company: listing.querySelector('.job-card-container__company-name').textContent.trim(),
      location: listing.querySelector('.job-card-container__metadata-item').textContent.trim(),
      link: `https://www.linkedin.com${listing.querySelector('.job-card-container__link').getAttribute('href')}`,
    }));
  });

  // Save the job listings to a text file
  const filePath = 'C:\\Users\\Win10\\Documents\\Python_Scripts\\job_listings.txt';
  const fileContent = jobListings.map((job) => `Title: ${job.title}\nCompany: ${job.company}\nLocation: ${job.location}\nLink: ${job.link}\n\n`).join('');
  fs.writeFileSync(filePath, fileContent);

  console.log(`Job listings saved to ${filePath}`);

  await browser.close();
})();

1. 替换page.waitForTimeout为自定义延迟函数 #

Puppeteer v19+已移除page.waitForTimeout和waitForTimeout内置方法，需自行封装Promise版延迟函数：

const delay = (ms) => new Promise(resolve => setTimeout(resolve, ms));

之后用await delay(10000)替代所有无效的等待代码。

2. 修复代码中的语法错误 #

• 第14行page. Type多了空格，改为page.type，否则会触发语法错误
• 原代码中await setTimeout(10000)无效，因为setTimeout不是Promise，必须使用上述自定义delay函数

3. 完整修正后的脚本 #

const puppeteer = require('puppeteer');
const fs = require('fs');

// 自定义延迟函数
const delay = (ms) => new Promise(resolve => setTimeout(resolve, ms));

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();

  // Navigate to LinkedIn login page
  await page.goto('https://www.linkedin.com/login');

  // Enter your LinkedIn email and password
  await page.type('#username', 'email');
  await page.type('#password', 'password'); // 修复空格问题

  // Submit the login form
  let retries = 0;
  let maxRetries = 3;

  while (retries < maxRetries) {
    try {
      await Promise.all([
        page.click('.btn__primary--large'),
        page.waitForNavigation({
          waitUntil: 'networkidle2',
          timeout: 60000, // 60 seconds
        }),
      ]);
      break;
    } catch (error) {
      if (retries < maxRetries - 1) {
        retries++;
        console.log(`Retrying after ${retries} attempts...`);
        await delay(10000); // 使用自定义延迟函数
      } else {
        console.error('Failed to log in after ' + maxRetries + ' attempts. Exiting...');
        await browser.close();
        process.exit(1);
      }
    }
  }

  // Navigate to the jobs search page
  await page.goto('https://www.linkedin.com/jobs/search/?keywords=Product%20Manager&location=India');

  // Wait for the search results to load
  await page.waitForSelector('.jobs-search-results__list');

  // Scrape the job listings
  const jobListings = await page.evaluate(() => {
    const listings = document.querySelectorAll('.jobs-search-results__list-item');
    return Array.from(listings).map((listing) => ({
      title: listing.querySelector('.job-card-list__title')?.textContent.trim() || 'N/A',
      company: listing.querySelector('.job-card-container__company-name')?.textContent.trim() || 'N/A',
      location: listing.querySelector('.job-card-container__metadata-item')?.textContent.trim() || 'N/A',
      link: listing.querySelector('.job-card-container__link') ? `https://www.linkedin.com${listing.querySelector('.job-card-container__link').getAttribute('href')}` : 'N/A',
    }));
  });

  // Save the job listings to a text file
  const filePath = 'C:\\Users\\Win10\\Documents\\Python_Scripts\\job_listings.txt';
  const fileContent = jobListings.map((job) => `Title: ${job.title}\nCompany: ${job.company}\nLocation: ${job.location}\nLink: ${job.link}\n\n`).join('');
  fs.writeFileSync(filePath, fileContent);

  console.log(`Job listings saved to ${filePath}`);

  await browser.close();
})();

额外优化：在page.evaluate中添加可选链操作符?.，避免因DOM元素不存在导致脚本崩溃。

内容的提问来源于stack exchange，提问作者Neil Bagchi