使用腾讯云TCB云函数抓取微信情报信息

'use strict';
const puppeteer = require('puppeteer')

exports.main = async (event, context) => {
  const browser = await puppeteer.launch({
    headless: true,
    args: ['--no-sandbox', '--disable-setuid-sandbox'],
    dumpio: false,
  })
  const page = await browser.newPage()
  page.setUserAgent(
    'Mozilla/5.0 (Linux; Android 10; Redmi K30 Pro Build/QKQ1.191117.002; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/78.0.3904.62 XWEB/2581 MMWEBSDK/200801 Mobile Safari/537.36',
  )
  await page.goto('https://www.newrank.cn/public/news.html?#', {
    waitUntil: 'networkidle0',
  })

  await page.click('.media-tags-more .row:last-child .float-left span:first-child')
  await page.waitFor(200)
  const wxInfoList = await page.evaluate(() => {
    const elements = Array.from(document.querySelectorAll('.media-main-left-news-list li'))
    return elements.map(s => {
      let a = s.getElementsByTagName('h3').item(0).getElementsByTagName('a').item(0)
      let txt = a.innerHTML
      let url = a.getAttribute('href')
      return { title: txt, url: url }
    })
  })
  await browser.close()
  return {list:wxInfoList}
}