ChunkMarkdown.py

#!/usr/bin/python

# Chunk a big markdown file into smaller files
# at the h2 level. Throw away anything above that. 
# This assumes a 'well-formed' file. I.e. if you put an 
# h1 below an h2, this happily sticks it in the file 
# for it's parent h2. 

# Name output files based on heading names, replacing
# spaces with - and adding ".html.md". No other bad characters
# are stripped from the heading. 

import re

with open('concepts.html.markdown') as file:
    data = file.readlines()

    data.reverse()

    headings = []

    for line in data:
        m = re.match("^## ", line)
	if m:
            headings.append(line)

    section = []

    for line in data:
	section.append(line)

        if len(headings) > 0  and line == headings[0]:
            section.reverse()
            filename = line.split("## ",1)[1].replace(" ","-").rstrip().lower() + ".html.md"
            sectionFile = open(filename,'w')
            for lline in section:
                sectionFile.write('%s'% lline)
            sectionFile.close()
            section = []
            del headings[0]