我试图抓取传递给 scrape 函数的任何网页,但无论 page.goto() 设置的超时如何,我都会收到超时错误,如果设置为 0,应用程序只会继续等待。
const express = require('express');
const cors = require('cors');
const MYPORT = process.env.PORT || 4001;
const app = express();
const puppeteer = require('puppeteer');
app.use(express.json());
app.use(cors());
const scrape = async (url) => {
var body;
try {
const browser = await puppeteer.launch({
headless: true,
args: ['--no-sandbox'],
timeout: 0
});
console.log('Browser launched');
const page = await browser.newPage();
console.log('Page opened');
await page.goto(url, { waitUntil: 'load', timeout: 3 * 60000 });
await page.waitForSelector('body', {waitUntil: 'load'})
console.log('Link opened');
await page.waitForNavigation({waitUntil: …Run Code Online (Sandbox Code Playgroud)node.js express windows-subsystem-for-linux puppeteer ubuntu-18.04