Removing html formatting when fetching gmail message body in javascript
I would like to remove html formatting in my google script apps. I am currently searching for email and printing the results to a google spreadsheet. I would like to know if there is a way to replace the text. I know about regex, but I don't think it works with the getBody function.
I would really appreciate some feedback or some help on this.
Code:
function Search() {
var sheet = SpreadsheetApp.getActiveSheet();
var row = 2;
// Clear existing search results
sheet.getRange(2, 1, sheet.getMaxRows() - 1, 4).clearContent();
// Which Gmail Label should be searched?
var label = sheet.getRange("F3").getValue();
// Get the Regular Expression Search Pattern
var pattern = sheet.getRange("F4").getValue();
// Retrieve all threads of the specified label
var threads = GmailApp.search("in:" + label);
for (var i = 0; i < threads.length; i++) {
var messages = threads[i].getMessages();
for (var m = 0; m < messages.length; m++) {
var msg = messages[m].getBody();
// Does the message content match the search pattern?
if (msg.search(pattern) !== -1) {
// Print the message subject
sheet.getRange(row,3).setValue(messages[m].getBody());
source to share
Replace this:
// Print the message subject
sheet.getRange(row,3).setValue(messages[m].getBody());
Wherein:
// Print the message subject
sheet.getRange(row,3).setValue(getTextFromHtml(messages[m].getBody()));
The feature getTextFromHtml()
was adapted from this answer , adding handling for some basic formatting (numbered and bullet lists, paragraph breaks).
function getTextFromHtml(html) {
return getTextFromNode(Xml.parse(html, true).getElement());
}
var _itemNum; // Used to lead unordered & ordered list items.
function getTextFromNode(x) {
switch(x.toString()) {
case 'XmlText': return x.toXmlString();
case 'XmlElement':
var name = x.getName().getLocalName();
Logger.log(name);
var pre = '';
var post = '';
switch (name) {
case 'br':
case 'p':
pre = '';
post = '\n';
break;
case 'ul':
pre = '';
post = '\n';
itemNum = 0;
break;
case 'ol':
pre = '';
post = '\n';
_itemNum = 1;
break;
case 'li':
pre = '\n' + (_itemNum == 0 ? ' - ' : (' '+ _itemNum++ +'. '));
post = '';
break;
default:
pre = '';
post = '';
break;
}
return pre + x.getNodes().map(getTextFromNode).join('') + post;
default: return '';
}
}
source to share
From this answer: Google Apps Scripting - Extracting data from gmail into a spreadsheet
You can drop the getTextFromHTML function entirely by simply using getPlainBody (); instead of getBody () ;.
source to share