export all LibreOffice or MS-Word files to html, uses OpenOffice or Libre Office and tidy

odf2html.sh

#!/bin/bash
# odf2html.sh - export all odt od doc files to html by shellscript
# Inspired by Marco Fioretti, 
# who wrote this Article in 2012: http://www.techrepublic.com/blog/linux-and-open-source/how-to-convert-doc-and-odf-files-to-clean-and-lean-html/
# Klaus Kappel

CONFIG=tidy.conf

# first clean the dir, if script runs in cron job
# rm -rf $2
mkdir -p $2

for F in `find $1 -type f -name "*.doc" -or -name "*.odt"`
    do
    BASE=`basename $F .doc` ; BASE=`basename $BASE .odt`
    libreoffice --headless --convert-to html --outdir $2 $F
    tidy -q -config $CONFIG -f $2/$BASE.err -i $2/$BASE.htm | sed 's/ class="c[0-9]*"//g' > $2/$BASE.html
    done

tidy.conf

# Tidy.conf to clean LibreOffice Html Output
clean: yes
drop-proprietary-attributes: yes
drop-empty-paras: yes
output-html: yes
input-encoding: utf8
output-encoding: utf8
join-classes: yes
join-styles: yes
show-body-only: yes
force-output: yes