any2markdown.sh

#!/bin/sh

# any2markdown.sh
#
# A shell script that converts documents to markdown
#
# https://gist.github.com/creativecoder/4990796
#
# Depends on: 
# pandoc:    http://johnmacfarlane.net/pandoc/
#            a utility for converting lots of things to lots of things
# html2text: https://github.com/aaronsw/html2text
#            a utilty for converting html to markdown text; used instead
#            of pandoc for better handling of nested html lists
# textutil:  a built-in OS X utility for converting lots of things to 
#            lots of things.
# pdftohtml: http://pdftohtml.sourceforge.net/
#            a utility for converting pdf to html
#
# Forked from:
# https://gist.github.com/dsanson/1181510

for file in "$@"
do
		base="${file%%.*}"
		ext="${file#*.}"
	case $ext in
		doc | docx | webarchive | rtf | rtfd | odt )
			if [ ! $(which textutil) ]; then
				echo "textutil not found:"
				echo "  unable to process doc, docx, webarchive, rtf, rtfd, or odt files"
					exit
			fi
				# Convert text with Courier New font to <code></code>
				# Convert ordered lists to unordered lists
				textutil -format "$ext" -convert "html" -stdout "$file" \
				| perl -pe 's:<span class="s1">(.*?)</span>:<code>$1</code>:g' \
				| perl -pe 's:(<li class="li3">.*?<span.*?</span>)(.*?)<:$1<code>$2</code><:g' \
				| perl -pe 's:<ol:<ul:g' \
				| perl -pe 's:</ol>:</ul>:g' \
				| html2text > "${base}.md"
		;;
		pdf )
			if [ ! $(which pdftohtml) ]; then
				echo "pdftohtml not found: unable to process pdf files."
				exit
			fi
			pdftohtml -noframes -stdout "$file" \
				| html2text > "${base}.md"
		;;
		tex )
			pandoc -f latex -s "$file" -o "${base}.md"
		;;
		* )
			pandoc -s  "$file" -o "${base}.md"
		;;
	esac
done