Skip to content

Instantly share code, notes, and snippets.

@baotuo

baotuo/gist:e444e236af08f873435b

Last active November 11, 2021 09:22
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save baotuo/e444e236af08f873435b to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save baotuo/e444e236af08f873435b to your computer and use it in GitHub Desktop.
Download ZIP
Remove HTML formatting from a String
Raw
gistfile1.js
// removes MS Office generated guff
function cleanHTML(input) {
// 1. remove line breaks / Mso classes
var stringStripper = /(\n|\r| class=(")?Mso[a-zA-Z]+(")?)/g;
var output = input.replace(stringStripper, ' ');
// 2. strip Word generated HTML comments
var commentSripper = new RegExp('<!--(.*?)-->','g');
var output = output.replace(commentSripper, '');
var tagStripper = new RegExp('<(/)*(meta|link|span|\\?xml:|st1:|o:|font)(.*?)>','gi');
// 3. remove tags leave content if any
output = output.replace(tagStripper, '');
// 4. Remove everything in between and including tags '<style(.)style(.)>'
var badTags = ['style', 'script','applet','embed','noframes','noscript'];
for (var i=0; i< badTags.length; i++) {
tagStripper = new RegExp('<'+badTags[i]+'.*?'+badTags[i]+'(.*?)>', 'gi');
output = output.replace(tagStripper, '');
}
// 5. remove attributes ' style="..."'
var badAttributes = ['style', 'start'];
for (var i=0; i< badAttributes.length; i++) {
var attributeStripper = new RegExp(' ' + badAttributes[i] + '="(.*?)"','gi');
output = output.replace(attributeStripper, '');
}
return output;
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment