Parse XML to Google Spreadsheet in google Apps Script - google-apps-script

Question

I need to parse a XML file to Google Spreadsheet. I need all the data from each row "row".
Every URL should have its own row in spreadsheet for all its values.
XML File, example:
<response>
<method>domain.urls</method>
<answer>
<row url="https://www.example.com/1" top10="3048" top100="4490" visindex="9.1068505804717"/>
<row url="https://www.example.com/2" top10="2633" top100="2720" visindex="8.6659210425021"/>
<row url="https://www.example.com/3" top10="875" top100="964" visindex="2.7381900000597"/>
</answer>
<credits used="4"/>
</response>
I started with this function and got one value back (yay!)
for (var i = 0; i < items.length; i++) {
if(items[i].getName() == 'answer'){
var answer = items[i].getChildren();
return answer[0].getAttribute('visindex').getValue();
}
}
Tis function writes the value (answer) to spreadhseet
var seoValue = getSeoValue(apikey, seoMetric, keyword, country);
outputSheet.getRange(outputLastRow, 6 + i ).setValue(seoValue/1); //aktuell nur 1 outputwert
}
// increase the last output row by one
outputLastRow++;
}
I dont knwo how to collect all the values from a row and save them to spreadhseet.
Output spreadhsheet example:
INPUT - (excerpt)
<row url="https://www.example.com/1" top10="3048" top100="4490" visindex="9.1068505804717"/>
<row url="https://www.example.com/2" top10="2633" top100="2720" visindex="8.6659210425021"/>
<row url="https://www.example.com/3" top10="875" top100="964" visindex="2.7381900000597"/>
OUTPUT - Row A1 | B1 | C1 | D1
values row-1 -> URL-1-value | top-10-value-1 | top-100-value-1 | visindex-value-1
values row-2 -> URL-2-value | top-10-value-2 | top-100-value-2 | visindex-value-2
And one more thing that kills me: as far as I understand, I need to convert the URL to a string.

Answer 1

Apps Script has an XML Service that you can use to parse data. Here's a way you can do it based on one of the examples there. You can just paste it on a new Sheet's Apps Script project to test and modify at your convenience.
function xmlParser() {
//input should be your xml file as text
let xml = '<response><method>domain.urls</method><answer><row url="https://www.example.com/1" top10="3048" top100="4490" visindex="9.1068505804717"/><row url="https://www.example.com/2" top10="2633" top100="2720" visindex="8.6659210425021"/><row url="https://www.example.com/3" top10="875" top100="964" visindex="2.7381900000597"/></answer><credits used="4"/></response>';
let document = XmlService.parse(xml); //have the XML service parse the document
let root = document.getRootElement(); //get the root element of the document
let answers = root.getChild("answer").getChildren("row"); //gets the 'answer' node, and a list of its subnodes, note that we use getChildren() to get them all in an array
//now the answers array contains each <row> element with all its attributes
const list = [] //we create an array that will hold the data
answers.forEach(function (row) {
//forEach function that iterates through all the row nodes and uses
//getAttribute() to get their values based on the names we know already
//we push each element to our list array
list.push([row.getAttribute("url").getValue(), row.getAttribute("top10").getValue(), row.getAttribute("top100").getValue(), row.getAttribute("visindex").getValue()])
}
)
writeToSheet(list) // after the array is populated you can call another function to paste in the Sheet
}
function writeToSheet(list) {
//first set a range where you will paste the data. You have to define the length with the input array
//the first two parameters are "1, 1" for row 1, column 1, but you can change this depending on your needs.
let range = SpreadsheetApp.getActiveSheet().getRange(1, 1, list.length, list[0].length)
//once we have the array set you can just call setValues() on it which pastes the array on its own
range.setValues(list)
}
Output looks like this:
References:
XML Service
getRange()
setValues()

Answer 2

Holy frak that worked Daniel.
I put some scripts together and it gives me what I need.
Google Apps Script: SISTRIX API Call page.urls. Its crap but output is okay.
function getData() {
var spreadSheet = SpreadsheetApp.getActiveSpreadsheet();
var inputSheet = spreadSheet.getSheets()[0];
var outputSheet = spreadSheet.getSheets()[1];
// get the last non-empty row number in the input sheet
var inputLastRow = inputSheet.getLastRow();
// get the first empty row number in the output sheet
var outputLastRow = outputSheet.getLastRow() + 1;
// get the api key from the input sheet
var apikey = inputSheet.getRange('A2').getValue();
//var week = getWeek();
// get the input for queries
var inputs = inputSheet.getRange('A11:E' + inputLastRow).getValues();
// specify the SISTRIX KPIs for the client and the competitor(s)
var clientSeoMetrics = inputSheet.getRange('A5').getValue().split(',');
// loop over rows in the input
for (var row = 0; row < inputLastRow - 10; row++) {
// specify inputs - which column means what
//var keyword = inputs[row][0].toLowerCase();
//var country = inputs[row][2].toLowerCase();
var domain = inputs[row][0].toLowerCase();
var limit = inputs[row][1];
//write the basic information to output
//outputSheet.getRange('A'+outputLastRow).setValue(keyword);
//B Suchvolumen
//outputSheet.getRange('C'+outputLastRow).setValue(country.toUpperCase());
//D wird Search Intent
//outputSheet.getRange('E'+outputLastRow).setValue(week);
// check if competition or client and take proper KPIs
var seoMetrics;
seoMetrics = clientSeoMetrics; //eigenltich unnoetig - evtl. fuer intent sinnvoll (if intent dann)
// loop over seometrics - falls weitere Metriken
for (var i = 0; i < seoMetrics.length; i++) {
var seoMetric = seoMetrics[i];
if (seoMetric == ""){
break;
}
// run seoMetric query
//var seoValue = getSeoValue(apikey, seoMetric, domain, limit);
//outputSheet.getRange(outputLastRow, 5 + i ).setValue(seoValue/1); //aktuell nur 1 outputwert
//var seoValue = getSeoValue(apikey, seoMetric, domain, limit);
//outputSheet.getRange(outputLastRow, 5 + i ).setValue(seoValue/1); //aktuell nur 1 outputwert
var seoValue = [] ;
var seoValue = getSeoValue(apikey, seoMetric, domain, limit);
}
// increase the last output row by one
outputLastRow++;
}
function getSeoValue(apikey, seoMetric, domain, limit){
var url = "https://api.sistrix.com/"+seoMetric+"?domain="+domain+"&api-key="+apikey+"&country=de&limit="+limit;
var xml = UrlFetchApp.fetch(url).getContentText();
var document = XmlService.parse(xml);
var root = document.getRootElement(); //get the root element of the document
var answers = root.getChild("answer").getChildren("row"); //gets the 'answer' node, and a list of its subnodes, note that we use getChildren() to get them all in an array
//now the answers array contains each <row> element with all its attributes
const list = [] //we create an array that will hold the data
answers.forEach(function (row) {
//forEach function that iterates through all the row nodes and uses
//getAttribute() to get their values based on the names we know already
//we push each element to our list array
list.push([row.getAttribute("url").getValue(), row.getAttribute("top10").getValue(), row.getAttribute("top100").getValue(), row.getAttribute("visindex").getValue()])
}
)
writeToSheet(list) // after the array is populated you can call another function to paste in the Sheet
}
function writeToSheet(list) {
//let range = SpreadsheetApp.getActiveSheet().getRange(1, 1, list.length, list[0].length)
//range.setValues(list)
//outputSheet.getRange(outputLastRow, 5 + i ).setValue(list/1); //aktuell nur 1 outputwert
let range = outputSheet.getRange(outputLastRow, 1, list.length, list[0].length)
range.setValues(list)
}
}