Skrypt konwertujący XML z danymi wpisów wyeksportowanymi z panelu administracyjnego Joggera na pliki .markdown gotowe do katalogu postów w Octopresie

jogger2octopress.py

import re
from xml.dom import minidom
from html.parser import HTMLParser

XMLFILENAME = 'jogger_eksport.xml'

def createFileName(date, permalink, subject):
    """Data wymagana, w formacie YYYY-mm-dd"""
    fileName = date[:10] + '-'
    if permalink != None:
        fileName += permalink
    else:
        fileName += re.sub(r'[^a-zA-Z\d\.-]', '_', subject.lower())
    return fileName + '.markdown'


DOMTree = minidom.parse(XMLFILENAME)
cNodes = DOMTree.childNodes

postNo = 1
for i in cNodes[0].getElementsByTagName("entry"):

    date = i.getElementsByTagName("date")[0].childNodes[0].toxml()

    subject = 'Bez tytułu ' + str(postNo)
    postNo = postNo + 1
    if i.getElementsByTagName("subject")[0].firstChild != None:
        subject = i.getElementsByTagName("subject")[0].firstChild.toxml()

    permalink = None
    if i.getElementsByTagName("permalink")[0].firstChild != None:
        permalink = i.getElementsByTagName("permalink")[0].firstChild.toxml()

    fileName = createFileName(date, permalink, subject)

    body = ''
    if i.getElementsByTagName("body")[0].firstChild != None:
        body = i.getElementsByTagName("body")[0].firstChild.toxml()
    body = HTMLParser().unescape(body).replace('<EXCERPT>', '\n<!-- more -->\n')

    categories = []
    for cat in i.getElementsByTagName("category"):
        categories.append(cat.firstChild.nodeValue)

    text_file = open(fileName, "w", encoding="utf-8")
    text_file.write('---\n')
    text_file.write('layout: post\n')
    text_file.write('title: "' + subject + '"\n')
    text_file.write('date: ' + date[:16] + '\n')
    text_file.write('comments: true\n')
    text_file.write('categories:\n')
    for cat in categories:
        text_file.write('- ' + cat + '\n')
    text_file.write('---\n')
    text_file.write(body)
    text_file.close()