Search code examples
javascriptgoogle-apps-scripthtml-parsing

How to get value of variable from HTML text in Google Applicatioin Script?

I get valid HTML code using UrlFetchApp.fetch(url,options). The part I am interested in looks like

<script type="text/javascript">

    var map = am4core.create("mapdiv", am4maps.MapChart);
    map.geodata = am4geodata_worldLow;
    map.projection = new am4maps.projections.Miller();
    var polygonSeries = new am4maps.MapPolygonSeries();
    polygonSeries.useGeodata = true;
    map.series.push(polygonSeries);
    // Configure series
    var polygonTemplate = polygonSeries.mapPolygons.template;

    polygonSeries.data = [{
                  "id": "AF",
                      "value0": "2",
                  "value3": 3.2,
                  "fill": am4core.color("#0C6175")
            }, {
                  "id": "AL",
                      "value0": "2",
                  "value3": 2.5,
                  "fill": am4core.color("#0C6175")
            }, {
                  "id": "DZ",
                  "name": "Algeria",
                      "value0": "1",
                  "value3": 3.2,
                  "fill": am4core.color("#68C2C3")
            }];
    polygonTemplate.propertyFields.fill = "fill";


</script>

Could you suggest how to get the value of polygonSeries.data javascript variable assigned to GAS variable? I cannot think of anything besides parsing the HTML line by line, find polygonSeries.data and then parse till I get }]; I do not think it is the best way though.

Solution

  • Suggestion

    You can use this sample regex method script & adjust it based on your needs:

    Script:

    function getData() {
  var htmlcontent = HtmlService.createHtmlOutputFromFile('Index').getContent(); //Sample line to get the content of the Html file
  var clean = htmlcontent.replace(/ /g,''); //Clean the code by removing multiple spaces
  var regExp = new RegExp("polygonSeries.data=(.*)polygonTemplate", "s");
  var data = regExp.exec(clean)[1];
  var arr = data.split(/\r?\n/) //split all data by new lines
  var newArr = []; //container of all the values
  arr.forEach(res => { //Sample lines of code to clean each values to be placed later as array values
    if(res.length > 3){
      try{
      var temp = res.replace(",","").split(":");
      newArr.push([temp[0].replace(/"/gm, ''),temp[1].replace(/"/gm, '')])
      }catch{
        var temp = res.split(":");
        newArr.push([temp[0].replace(/"/gm, ''),temp[1].replace(/"/gm, '')])
      }
    }
  });
  Logger.log(newArr);
}

    Sample Index.html file:

    <!DOCTYPE html>
<HTML>
<HEAD>
<TITLE>Your Title Here</TITLE>
    <script type="text/javascript">

        var map = am4core.create("mapdiv", am4maps.MapChart);
        map.geodata = am4geodata_worldLow;
        map.projection = new am4maps.projections.Miller();
        var polygonSeries = new am4maps.MapPolygonSeries();
        polygonSeries.useGeodata = true;
        map.series.push(polygonSeries);
        // Configure series
        var polygonTemplate = polygonSeries.mapPolygons.template;

        polygonSeries.data = [{
                      "id": "AF",
                      "value0": "2",
                      "value3": 3.2,
                      "fill": am4core.color("#0C6175")
                }, {
                      "id": "AL",
                      "value0": "2",
                      "value3": 2.5,
                      "fill": am4core.color("#0C6175")
                }, {
                      "id": "DZ",
                      "name": "Algeria",
                      "value0": "1",
                      "value3": 3.2,
                      "fill": am4core.color("#68C2C3")
                }];
        polygonTemplate.propertyFields.fill = "fill";


    </script>
</HEAD>
<BODY BGCOLOR="FFFFFF">
<CENTER><IMG SRC="clouds.jpg" ALIGN="BOTTOM"> </CENTER>
<HR>
<a href="http://somegreatsite.com">Link Name</a>
is a link to another nifty site
<H1>This is a Header</H1>
<H2>This is a Medium Header</H2>
Send me mail at <a href="mailto:support@yourcompany.com">
support@yourcompany.com</a>.
<P> This is a new paragraph!
<P> <B>This is a new paragraph!</B>
<BR> <B><I>This is a new sentence without a paragraph break, in bold italics.</I></B>
<HR>
</BODY>
</HTML>

    Sample Result:

    enter image description here