fernandobarron/wordsoap

Clean up dirty HTML output from Microsoft Word

wordsoap

Clean up dirty HTML output from Microsoft Word

Usage

command line

$ npm install -g wordsoap
$ cat msword_garbage.html | wordsoap

module

$ npm install --save wordsoap

var wordsoap = require('wordsoap')

var dirty = "<p class=MsoNormal style='font-size:12pt'>Text</p>")
var clean = wordsoap(dirty) // <p>Text</p>

// access individual regex strings
wordsoap.regexes.msoAttributes // <(\w+)(?: (?:class|lang|style|size|face|[ovwxp]))=(?:'[^']*'|""[^""]*""|[^\s>]+)(?:[^>]*)>

// access individual regexes compiled with 'gi' flags
wordsoap.regexesCompiled.msoAttributes // <(\w+)(?: (?:class|lang|style|size|face|[ovwxp]))=(?:'[^']*'|""[^""]*""|[^\s>]+)(?:[^>]*)>

License

ISC © Raine Lourie