Convert HTML to markup for Jekyll

jekll_html2text_wrapper.py

#
# The Jekyll import tool (http://import.jekyllrb.com/docs/blogger/)
# creates HTML files. I'd like to use html2text
# (https://github.com/aaronsw/html2text) to convert those to Markdown.
# The challenge is that Jekyll files have a YAML header at the top that gets
# mangled by the conversion. This strips the header, passes the remainder 
# of the body into html2text, then adds the header back to the result.
#

import os
import subprocess
import sys
import tempfile
import html2text

for filename in sys.argv[1:]:
    with open(filename, 'r') as infile:
        contents = infile.read()

    # Find the end of the YAML header
    endheader = contents.find('\n---\n')
    header = contents[:endheader + 5]
    new_body = html2text.html2text(contents[endheader + 5:].decode('unicode_escape'))
    with open(os.path.splitext(filename)[0]+'.markdown', 'w') as f:
        f.write(header)
        f.write('\n')
        f.write(new_body.encode('utf8'))