Helper script to migrate blog posts from octopress to pelican.

octopress2pelican.py

#!/bin/env python
##
## Copyright (c) 2014 Rodolphe Breard
## 
## Permission to use, copy, modify, and/or distribute this software for any
## purpose with or without fee is hereby granted, provided that the above
## copyright notice and this permission notice appear in all copies.
## 
## THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
## WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
## MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
## ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
## WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
## ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
## OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
##

INPUT_DIR = 'source/_posts/'
OUTPUT_DIR = 'content/'
ARTICLE_PATTERN = '*.markdown'
METADATA_SEPARATOR = '---\n'
DATETIME_FORMAT = '%Y-%m-%d %H:%M'

import distutils.core
import datetime
import shlex
import glob
import os

def strip_quotes(s):
    return s.strip('"\'')

def date_convert(s):
    return datetime.datetime.strptime(s, DATETIME_FORMAT)

def list_convert(s):
    lst = [e.strip(',') for e in shlex.split(s.strip('[]'))]
    return ', '.join(lst)

def status_conversion(s):
    return 'published' if distutils.util.strtobool(s) else 'draft'

class Article:
    _metadatas = {
        # original_name: (new_name, content_conversion_function),
        'title': ('Title', strip_quotes),
        'date': ('Date', date_convert),
        'categories': ('Tags', list_convert),
        'published': ('Status', status_conversion),
    }

    def __init__(self, path):
        self.file_name = os.path.basename(path)
        self.metadatas = [('Slug', os.path.splitext(self.file_name[11:])[0])]
        self.initial_path = path
        self.new_path = os.path.join(OUTPUT_DIR, self.file_name)
        self.load_data()

    def load_data(self):
        with open(self.initial_path, 'r') as f:
            _, *content = f.readlines()
            split_index = content.index(METADATA_SEPARATOR)
            for line in [line.strip() for line in content[:split_index]]:
                self._set_metadata(line)
            self.content = ''.join(content[split_index + 1:])

    def _set_metadata(self, line):
        split_index = line.index(':')
        name, content = line[:split_index].strip(), line[split_index + 1:].strip()
        if name in self._metadatas:
            new_name, func = self._metadatas[name]
            self.metadatas.append((new_name, func(content)))

    def save(self):
        with open(self.new_path, 'w') as f:
            for name, content in self.metadatas:
                f.write('%s: %s\n' % (name, content))
            f.write('\n%s' % self.content)

if __name__ == '__main__':
    for article_path in glob.glob(os.path.join(INPUT_DIR, ARTICLE_PATTERN)):
        article = Article(article_path)
        article.save()