#!/usr/bin/env python

from __future__ import print_function

import sys

import os.path

import mammoth

from bs4 import BeautifulSoup

def docx2html(infile, outfile):

with open(infile) as fp:

mammout = mammoth.convert_to_html(fp)

for m in mammout.messages:

print("Mammoth %s: %s" % (m.type, m.message))

# Prettyprint it

soup = BeautifulSoup(mammout.value, "lxml")

html = soup.prettify().encode("utf-8")

if outfile == "--":

print(html)

else:

with open(outfile, "w") as fp:

print(html, file=fp)

if __name__ == "__main__":

if len(sys.argv) < 2 or len(sys.argv) > 3 \

or sys.argv[1] == "-h" or sys.argv[1] == "--help":

print("Usage: %s infile.docx [outfile.html]")

sys.exit(1)

infile = sys.argv[1]

if len(sys.argv) == 3:

outfile = sys.argv[2]

else:

base, ext = os.path.splitext(infile)

if ext.lower() == ".docx":

outfile = base + ".html"

else:

outfile = infile + ".html"

print("mammoth", infile, outfile)

docx2html(infile, outfile)