javascript - 与 puppeteer 师一起刮 table

Question

我有以下带有 puppeter 的脚本，可以正常工作，此代码提取有关表的所有信息。

(async () => {
  const browser = await puppeteer.launch();
  const page = await browser.newPage();
  const tableRows = await page.$$('table > tbody tr');

    await page.goto("https://www.mismarcadores.com/baloncesto/espana/liga-endesa/partidos/");

    const time = await page.evaluate(() => {

        const tables = Array.from(document.querySelectorAll('table tr .time'));
        return tables.map(table => table.textContent)
     });

    const teamHome = await page.evaluate(() => {
        const tables = Array.from(document.querySelectorAll('table tr .team-home'));
        return tables.map(table => table.textContent)
     });

     const teamAway = await page.evaluate(() => {
        const tables = Array.from(document.querySelectorAll('table tr .team-away'));
        return tables.map(table => table.textContent)
     });


     for (let i = 0; i < time.length; i++) {
        console.log(time[i]);
        console.log(teamHome[i]);
        console.log(teamAway[i]);
     }  

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

现在我尝试以更好的方式创建它，并且我有以下代码。

(async () => {
  const browser = await puppeteer.launch({ headless: false });
  const page = await browser.newPage();
    await page.goto("https://www.mismarcadores.com/baloncesto/espana/liga-endesa/partidos/");
    console.log("started evalating");
    var data = await page.evaluate(() => {
      Array.from(
        document.querySelectorAll('table tr')
      ).map(row => {
        return {
          time: row.querySelector(".time"),
          teamHome: row.querySelector(".team-home"),
          teamAway: row.querySelector(".team-away")
        };
      });
    });
  console.log(data);
})();

当我尝试执行收到但未定义的第二个脚本时。

结果是将第一个脚本传递给第二个脚本。

有人可以帮助我吗？

Answer 1

您需要更多地指定 tr 元素(例如通过添加 .stage-scheduled 类)并返回 .textContent 属性而不是 fo 元素他们自己。试试这个:

    var data = await page.evaluate(() => {
      return Array.from(
        document.querySelectorAll('table tr.stage-scheduled')
      ).map(row => {
        return {
          time: row.querySelector(".time").textContent,
          teamHome: row.querySelector(".team-home").textContent,
          teamAway: row.querySelector(".team-away").textContent,
        };
      });
    });