A backup script that uses the pbworks API to download all pages and files in a given wiki workspace.

pbackup.py

#!/usr/bin/python
# -*- coding: utf -*-

import urllib2, json, datetime, os, unicodedata, re, codecs
from threading import Thread

API_KEY = '#'
WIKI = '#'

def slugify(value):
    if isinstance(value, unicode):
        value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore')
    value = unicode(re.sub('[^\w\s-]', '', value).strip().lower())
    return re.sub('[-\s]+', '-', value)

class Page(Thread):
    
    def __init__ (self, page, dir):
        Thread.__init__(self)

        self.file = '%s/%s.html' % (dir, slugify(page['name']))
        self.oid = page['oid']

    def run(self):
        html = json.loads(urllib2.urlopen("https://%s.pbworks.com/api_v2/op/GetPage/oid/%s/read_key/%s"
                                          % (WIKI, self.oid, API_KEY)).read().split('\n')[1])['html']
        with codecs.open(self.file, 'w', 'utf-8') as f:
            f.write(html)

if __name__ == '__main__':

    dir = WIKI + '-' + datetime.datetime.now().strftime('%Y-%m-%d-%H%M')
    os.makedirs(dir)

    for page in json.loads(urllib2.urlopen("https://%s.pbworks.com/api_v2/op/GetPages/read_key/%s"
                                           % (WIKI, API_KEY)).read().split('\n')[1])['pages']:
        t = Page(page, dir)
        t.start()