javascript - 卡在从第三帧抓取数据

Question

我不是专业人士，只是想从网站上抓取一些数据。这里的一些人帮助我选择了第一个“帧”，但我需要从第三帧中抓取数据并将来自第 1 帧 + 第 2 帧 + 第 3 帧的数据连接到一个结果中。这是网站这是我的:

const puppeteer = require('puppeteer');

let scrape = async() => {
    const browser = await puppeteer.launch({
        headless: false,
        slowMo: 250
    });
    const page = await browser.newPage();
    await page.goto('', {
        waituntil: "networkidle0"
    });
    const frame = await page.frames().find(f => f.name() === 'stanga');
    const button = await frame.$('body > form > font > select > option:nth-child(12)');
    button.click();
    await page.waitFor(1000);
    const frame1 = await page.frames().find(a => a.name() ==='centru');
    const select = await frame1.$('body > form > font > select > option:nth-child(1)');
    await page.waitFor(500);
    select.click();
    await page.waitFor(500);

    const result = await page.$$eval("body > font", (options) => {
        const timpi = options.map(option => option.innerText);

        return timpi

    });

    await browser.close();
    return result;
};
scrape().then((value) => {
    console.log(value);
});

感谢您的帮助。

Answer 1

我已经修复了我们的脚本:

const puppeteer = require('puppeteer');

let scrape = async () => {
const browser = await puppeteer.launch({headless: false});
const page = await browser.newPage();

await page.goto('http://example.com/txt', { waitUntil: "networkidle2" });
const optionSelector = 'body > form > font > select > option';
const frames = await page.frames();
const expectedFrames = ['stanga', 'centru'];
const scrapedText = [];


const getOptions = (frameName) => { 
  return frameName.$$eval(optionSelector, (options) => {
    const result = options.map(option => option.innerText);

    return result;
  }, optionSelector);
}

for (const frame of frames) {
  const name = frame.name();

  if (expectedFrames.includes(name)) {
    await frame.click(optionSelector);
    await page.waitFor(1000);
    const result = await getOptions(frame);

    scrapedText.push({[name]: result});
  } else if (name === 'dreapta') {
    const result = await frame.$eval('body', elm =>  elm.innerText);

    scrapedText.push({[name]: result.split(/\n+/g)});
  }
}


await browser.close();

return scrapedText;
};

scrape().then((value) => {
  console.log(value); 
});

输出:

[{ 
   stanga: ['Mures','A Saguna', 'A.Guttenbrun_1', ... and more items]
 },
 {
   centru: ['[0] E3'] 
 },
 { 
   dreapta: ['Linia: E3','2019-07-25 23:19:40','Sosire1: 23:39','Sosire2: 23:41'] 
}]