Puppeteer 爬取网页数据返回空数组问题解决方案

const puppeteer = require("puppeteer");
const express = require("express");
const cors = require("cors");
const app = express();
app.use(cors());
let data = [];
(async () => {
  const browser = await puppeteer.launch({
    headless: true, // 建议使用 headless 模式
    defaultViewport: null,
  });
  const page = await browser.newPage();
  for (let pageNumber = 1; pageNumber <= 42; pageNumber++) {
    await page.goto(`https://naamhinaam.com/baby-girl-names-a?page=${pageNumber}`);
    await page.waitForTimeout(3000);

    // 使用更简洁、稳定的选择器
    let nameElements = await page.$$(`a.nsg__name`);
    let meaningElements = await page.$$(`div.nsg__meaning > i`);

    // 确保名字和含义的数量一致
    if (nameElements.length !== meaningElements.length) {
      console.warn(`页面 ${pageNumber} 上的名字和含义数量不一致，可能存在问题。`);
      continue; // 跳过当前页面
    }

    for (let i = 0; i < nameElements.length; i++) {
      let fullName = "";
      try {
        let name = await page.evaluate(el => el.textContent, nameElements[i]);
        let meaning = await page.evaluate(el => el.textContent, meaningElements[i]);
        fullName = `${name.split(/[\n\t]/).join('').trim()}, ${meaning}`;
        data.push({ fullName });
      } catch (error) {
        console.error(`处理页面 ${pageNumber} 的第 ${i} 个元素时出错：`, error);
      }
    }
  }
  console.log(data);
  await browser.close();
})();
app.get("/", (req, res) => {
  res.status(200).json(data);
});

app.listen(3000, () => {
  console.log("App is running...");
});