Created
May 4, 2020 11:14
-
-
Save goldzulu/76004ec9f41151ad17fd10b68c7f06c2 to your computer and use it in GitHub Desktop.
Convert HTML to Text (Javascript)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// CONVERT HTML TO TEXT | |
var returnText = htmlSource; | |
//-- remove BR tags and replace them with line break | |
returnText=returnText.replace(/<br>/gi, "\n"); | |
returnText=returnText.replace(/<br\s\/>/gi, "\n"); | |
returnText=returnText.replace(/<br\/>/gi, "\n"); | |
//-- remove P and A tags but preserve what's inside of them | |
returnText=returnText.replace(/<p.*>/gi, "\n"); | |
returnText=returnText.replace(/<a.*href="(.*?)".*>(.*?)<\/a>/gi, " $2 ($1)"); | |
//-- remove all inside SCRIPT and STYLE tags | |
returnText=returnText.replace(/<script.*>[\w\W]{1,}(.*?)[\w\W]{1,}<\/script>/gi, ""); | |
returnText=returnText.replace(/<style.*>[\w\W]{1,}(.*?)[\w\W]{1,}<\/style>/gi, ""); | |
//-- remove all else | |
returnText=returnText.replace(/<(?:.|\s)*?>/g, ""); | |
//-- get rid of more than 2 multiple line breaks: | |
returnText=returnText.replace(/(?:(?:\r\n|\r|\n)\s*){2,}/gim, "\n\n"); | |
//-- get rid of more than 2 spaces: | |
returnText = returnText.replace(/ +(?= )/g,''); | |
//-- get rid of html-encoded characters: | |
returnText=returnText.replace(/ /gi," "); | |
returnText=returnText.replace(/&/gi,"&"); | |
returnText=returnText.replace(/"/gi,'"'); | |
returnText=returnText.replace(/</gi,'<'); | |
returnText=returnText.replace(/>/gi,'>'); | |
myVar = returnText; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment