Import an atom feed to blogofile markdown files.

blogger2blogofile.py

#!/usr/bin/env python
import os
import re
import sys
import urllib
import datetime
from xml.etree import ElementTree as ET

MARKDOWN_TEMPLATE="""
---
title: "%(title)s"
date: %(date)s
categories: %(categories)s
permalink: %(permalink)s
---

%(content)s
"""

ATOM_NS="{http://www.w3.org/2005/Atom}"
ENTRY=ATOM_NS+"entry"
TITLE=ATOM_NS+"title"
DATE=ATOM_NS+"published"
CONTENT=ATOM_NS+"content"
CATEGORY=ATOM_NS+"category"
LINK=ATOM_NS+"link"

def fix_title(t):
    replacements = [('\'', ''),
                    ('.', ''),
                    ('/', '-')]

    for a, b in replacements:
        t = t.replace(a, b)

    return t

def categories(entry):
    cats = []
    for c in entry.findall(CATEGORY):
        cats.append(c.attrib['term'])

    return ','.join(cats)


def permalink(entry):
    for l in entry.findall(LINK):
        if l.attrib['rel'] == 'alternate':
            return '/'+'/'.join(l.attrib['href'].split('/')[3:])

def content(c):
    nuke_tags = [r'<div.*?>',
                 r'<img width=\'1\'.*?googleusercontent.*?>',
                 r'</div>',
                 r'<span.*?>',
                 r'</span>',
                 r' style=\".*?\"']
    for r in nuke_tags:
        c = re.sub(r, '', c)
    return c


def convert(url):
    e = ET.parse(urllib.urlopen(url))

    files = []

    for entry in e.findall(ENTRY):
        t = entry.find(TITLE).text

        files.append((t, MARKDOWN_TEMPLATE % {
                    'title': t,
                    'date': datetime.datetime.strptime(
                        entry.find(DATE).text.split('.')[0],
                        "%Y-%m-%dT%H:%M:%S").strftime('%Y/%m/%d %H:%M:%S'),
                    'content': content(entry.find(CONTENT).text),
                    'categories': categories(entry),
                    'permalink': permalink(entry)
                    }))

    files.reverse()

    if not os.path.exists('_posts'):
        os.mkdir('_posts')

    c = 1
    for title, f in files:
        file('_posts/%04d - %s.markdown' % (c,
                                            fix_title(title).encode('utf-8')),
             'w').write(f.encode('utf-8'))

        c += 1


if __name__ == '__main__':
    convert(sys.argv[1])