我正在尝试使用node.js和puppeteer爬取一个网站以获取实时足球信息，但是在console.log("trying to select team element")之后，我的浏览器立即关闭。
const puppeteer = require("puppeteer"); async function openPage() { const browser = await puppeteer.launch( {headless: true} ); const page = await browser.newPage(); await page.setViewport({ width: 1000, height: 926 }); await page.goto("https://www.livescore.com/en/"); // 接受cookies const button = await page.waitForSelector('#onetrust-accept-btn-handler'); if (button) { await button.click(); console.log("clicked cookie button"); }; return page; } async function scrapeData(page) { let content = []; // 获取比赛元素 let elements = await page.waitForSelector(".Ip") console.log("trying to select team element") for (let i=0; i < elements.length; i++) { let homeTeamElement = await elements[i].$(".Ip") if (homeTeamElement) { const homeTeamText = await homeTeamElement.evaluate(node => node.textContent); content.push(homeTeamText); } }; return content; }; (async () => { const page = await openPage(); const dataScraped = await scrapeData(page); console.log(dataScraped) await page.browser().close(); })(); 对于为什么会这样以及对我的代码的进一步批评，欢迎提出任何想法！
await page.waitForSelector(".Ip")只返回一个元素，而不是一个数组，所以无法循环遍历。应该有一个清晰的错误消息来解释这个问题。相反，可以使用page.$$eval（或者如果你想尝试最新的定位器 API）来提取数据。const puppeteer = require("puppeteer"); // ^21.0.2 const url = "
"; let browser; (async () => { browser = await puppeteer.launch(); const [page] = await browser.pages(); await page.setViewport({width: 1000, height: 926}); await page.goto(url, {waitUntil: "domcontentloaded"}); // not really necessary const button = await page.waitForSelector("#onetrust-accept-btn-handler"); await button.click(); await page.waitForSelector(".Ip"); const content = await page.$$eval(".Ip", els => els.map(e => { const text = id => e.querySelector(`[id*=${id}]`).textContent.trim(); return { time: text("status-or-time"), home: text("home-team-name"), away: text("away-team-name"), homeTeamScore: +text("home-team-score"), awaitTeamScore: +text("away-team-score"), }; }) ); console.log(content); })() .catch(err => console.error(err)) .finally(() => browser?.close());
注：
waitForSelector的返回值。它保证是该元素，否则如果在规定时间内找不到它，它会抛出异常。await elements[i].$(".Ip")不会帮助你访问任何内容，因为在你已经持有的.Ip元素内部没有.Ip。