如何使用 Google Apps 脚本抓取网站的特定关键词？

Question

我在网上找到了这段代码，但是当我将它“复制并粘贴”到 Google Apps 脚本中时它不起作用：

https://webscraping.pro/scrape-google-app-script/

我必须进行哪些更改才能使其正常工作，或者是否有一种直接的方法可以在网站上搜索特定关键词并在 Google 表格中返回结果？

Answer 1

在工作表中尝试此代码，然后过滤一些不可用的行

function textOnly() {
  var url='https://stackoverflow.com/questions/69148306/how-do-i-use-google-apps-script-to-scrape-a-website-for-specific-key-words?noredirect=1#comment122219344_69148306'
  var sh=SpreadsheetApp.getActiveSpreadsheet().getActiveSheet()
  sh.clear()
  var data=UrlFetchApp.fetch(url).getContentText().replace(/(\r\n|\n|\r|\t)/gm," ").split('>')
  data.forEach(function (part){
    var text = part.split('<')[0]
    if (text.replace(/([ ]+)/gm,"")!='') {
      sh.appendRow([part.split('<')[0].replace(/([ ]{2,})/gm," ").replace(/(^ )/gm,"")])
    }
  })
}

然后，您将能够使用您的特定关键词进行过滤。要将这些关键字包含在脚本中，假设它们位于 keywords 范围内：

function textOnly() {
  var url='https://stackoverflow.com/questions/69148306/how-do-i-use-google-apps-script-to-scrape-a-website-for-specific-key-words?noredirect=1#comment122219344_69148306'
  var sh=SpreadsheetApp.getActiveSpreadsheet().getActiveSheet()
  sh.clear()
  var data=UrlFetchApp.fetch(url).getContentText().replace(/(\r\n|\n|\r|\t)/gm," ").split('>')
  var list = SpreadsheetApp.getActiveSpreadsheet().getRangeByName('keywords').getValues().join('|').toLowerCase().split('|')
  var n=0
  data.forEach(function (part){
    var text = part.split('<')[0]
    var myText = part.split('<')[0].replace(/([ ]{2,})/gm," ").replace(/(^ )/gm,"")
    if (text.replace(/([ ]+)/gm,"")!='') {
      list.forEach(function (term){
        if (myText.toLowerCase().includes(term)){
          sh.appendRow([myText])
          n++
        }
      })
    }
  })
  SpreadsheetApp.getActive().toast(n+" item(s) found", "End of script !", 5);
}