WordPress.xml to Markdown (Octopress)

parse_wordpress_xml.py

""" parse_wordpress_xml.py

Takes a WordPress XML export file and converts it to Octopress flavored Markdown files.

Author: James Fee (http://github.com/cageyjames)

"""

import string
import sys
import feedparser

def sanitize_filename(filename):
    """Strips special chars from the blog post names.  e.g. <title>Suggestions?</title>    
    """
    valid_chars = "-_.() %s%s" % (string.ascii_letters, string.digits)
    return ''.join(c for c in filename if c in valid_chars)

# Path to WordPress export xml

atom_xml = r"~\Projects\Wordpress\wordpress.2011-09-29.xml"
atom_xml = open(atom_xml).read()
d = feedparser.parse(atom_xml)  # the url of the Atom feed can also be used here

for entry in d.entries:
    if entry["wp_status"] != "publish": continue
    date = "%s-%s-%s" % (entry.date_parsed[0],entry.date_parsed[1],entry.date_parsed[2])
    title = entry.title
    title = title.replace(" ","-")
    filename = "./_posts/"+sanitize_filename("%s-%s" % (date,title)) + ".markdown" 
    print filename
    of = open(filename,"w")
    of.write("""---
layout: blog
title: %s
post_author: %s
categories:
""" % (entry.title.encode("ascii","replace"),entry.author.encode("ascii","replace")))
    if entry.has_key("tags"):
        tag_list = []
        for tag in entry.tags:
            #if tag["scheme"] == "tag":
            if (
                 tag["term"] != "Uncategorized"
                 and tag["term"] not in tag_list
                ):
                tag_list.append(tag["term"])
        for atag in tag_list:
            of.write("- %s\n" % atag)

    of.write("---\n\n")
    content_str = entry.content[0].value
    of.write(content_str.encode("ascii","replace"))
    of.close()