Python:Notoc.py

#!/usr/bin/python
# -*- coding: utf-8  -*-
 
"""
Bot written by Filnik to delete the __NOTOC__ in the pages that have it inside (working only for it.wiki).
"""
 
#
# (C) Filnik, 2007
#
# Distributed under the terms of the MIT license.
#
__version__ = '$Id: $'
#
 
import wikipedia
import re
 
def main():
    arg = wikipedia.handleArgs()
    pagename = 'Wikipedia:Elenchi_generati_offline/NOTOC'
    site = wikipedia.getSite()
    page = wikipedia.Page(site, pagename)
    # This page should exists always, it not there is a great bug.
    text = page.get()
    pagesToParse = re.findall(r'# ?\[\[(.*?)\]\]', text)
    for ParsePage in pagesToParse:
        wikipedia.output(u'Loading %s...' % ParsePage)
        for i in ['lista', 'cronologia', 'elenco', 'episodi']:
            if i.lower() in ParsePage.lower():
                wikipedia.output(u'%s in %s! Skip page!' % (i, ParsePage))
                continue
        ParsePage = wikipedia.Page(site, ParsePage)
        try:
            testo = ParsePage.get()
        except wikipedia.NoPage:
            wikipedia.output(u"%s doesn't exist, skip." % ParsePage.title())
            continue
        except wikipedia.IsRedirectPage:
            wikipedia.output(u"%s is a redirect, skip" % ParsePage.title())
            continue
        if '{{wikimedia:toc}}' in testo.lower():
            wikipedia.output(u'{{WikiMedia:Toc}} in text of %s, skip.' % ParsePage.title())
            continue
        newtext = re.sub(r'__NOTOC__', '', testo)
        if newtext != testo:
            ParsePage.put(newtext, 'Bot: Tolgo __NOTOC__ inutile')
        else:
            wikipedia.output(u'__NOTOC__ not found!')
            continue
 
if __name__ == "__main__":
    # Use try and finally, to put the wikipedia.stopme() always at the end of the code.
    try:
        main()
    finally:
        wikipedia.stopme()