Python:NC oderer.py

#!/usr/bin/python
# -*- coding: utf-8  -*-
"""
Bot to report only the images with the same license in a page to delete them easlier.
"""
#
# (C) Filnik, 2008
#
# Distributed under the terms of the MIT license.
#
__version__ = '$Id: $'
#
 
import wikipedia, re
from nowcommons import word_to_skip
from imagetransfer import licenseTemplates # take the license combinations
 
def main():
    arg = wikipedia.handleArgs()
    site = wikipedia.getSite()
    page = wikipedia.Page(site, 'Utente:Filnik/Nowcommons')
    source_text = page.get()
    list_of_words_to_skip = wikipedia.translate(site, word_to_skip)
    #*[[:Image:Cercola-Stemma.png]] - 	[[:Commons:Image:Cercola-Stemma.png]]
    array = re.findall(r'\*\[\[:Image:(.*?)\]\]\s*?-\s*?\[\[:Commons:Image:(.*?)\]\]', source_text)
    same_name_array = list()
    for element in array:
        wiki_image = element[0].replace('_', ' ')
        commons_image = element[1].replace('_', ' ')
        skip = False        
        for word in list_of_words_to_skip:
            if word.lower() in wiki_image.lower():
                skip = True
        if skip:
            continue
        if wiki_image == commons_image:
            wikipedia.output(u'%s = %s' % (wiki_image, commons_image))
            same_name_array.append([wiki_image, commons_image])
    output_page = wikipedia.Page(site, 'Utente:Filnik/Nowcommons/Same_Name')
    string = ''
    for element in same_name_array:
        string += '*[[:Image:%s]] - [[:Commons:Image:%s]]\n' % (element[0], element[1])
    output_page.put(string, 'Bot: Reporting the log') 
 
if __name__ == "__main__":
    try:
        main()
    finally:
        wikipedia.stopme()