Python:Gvf.py

#!/usr/bin/python
# -*- coding: utf-8  -*-
 
"""
This bot check all the references to the italian Template Bio, looking for a settings.
If this settings doesn't have |ExtImmagine (that define the extension of the image) the
bot will add the default ones. Unfortunately there are a lot of exceptions, and so the
code is become a little bit bigger of what I thought.
 
Bot written for Gvf, it.wiki
"""
 
#
# (C) Filnik, 2008
#
# Distributed under the terms of the MIT license.
#
__version__ = '$Id: $'
#
 
import wikipedia, pagegenerators, re
 
def main():
    arg = wikipedia.handleArgs()
    site = wikipedia.getSite()
    page = wikipedia.Page(site, 'Template:Bio')
    #pagegenerators.ReferringPageGenerator(page, False, True, True)
    pages_to_check = pagegenerators.ReferringPageGenerator(page, False, True, True)#[wikipedia.Page(site, 'Antonio Fogazzaro')]
    preloadingGen = pagegenerators.PreloadingGenerator(pages_to_check, pageNumber=60)
    for page in preloadingGen:
        wikipedia.output('Loading %s...' % page.title())
        try:
            text = page.get()
        except Exception, e:
            print e
            continue
        regex_image = re.compile(r'\{\{(?:[Tt]emplate|[Bb]io[^{]*?)\|[\s\n\t]*?[Ii]mmagine *?= *?(.*?)\s*?([|\n}])[^{]*?\}', re.DOTALL)
        regex_sub_image = re.compile(r'(\{\{(?:[Tt]emplate|)[Bb]io[^{]*?)\|[\s\n\t]*?[Ii]mmagine *?= *?(.*?)\s*?([|\n}])([^{]*?\})', re.DOTALL)
        image_inside_list = regex_image.findall(text)
 
        if image_inside_list == []:
            wikipedia.output(u'Image not found, skip.')
            continue
        else:
            if not re.findall(r'\w', image_inside_list[0][0]):
                wikipedia.output(u'No image, only setting empty, skip')
                continue
            extension = re.findall(r'\.(\w{3,5})[\s\n]*?$', image_inside_list[0][0])
            if extension != []:
                wikipedia.output(u'WARNING: Found %s as extension :S something is gone wrong' % extension)
                wikipedia.input(u'ping') # Wait that the mainteiner takes a look before go on
            extension_regex = re.compile(r'(\{\{(?:[Tt]emplate|)[Bb]io[^{]*?)\|[\s\n\t]*?[Ee]xt[Ii]mmagine *?= *?(.*?)(\s*?[|\n}])([^{]*?\})', re.DOTALL)
            find_ext_regex = re.compile(r'\{\{(?:[Tt]emplate|)[Bb]io[^{]*?\|[\s\n\t]*?[Ee]xt[Ii]mmagine *?= *?(.*?)\s*?[|\n}][^{]*?\}', re.DOTALL)
            extension_inside_list = find_ext_regex.findall(text)
            if extension_inside_list != []:
                if not re.findall(r'\w', extension_inside_list[0]):
                    newtext = extension_regex.sub(r'\1|ExtImmagine = jpg\2\3\4', text)
                else:
                    wikipedia.output(u'%s has the image %s with the extension: %s skip.' % (page.title(), image_inside_list[0][0], extension_inside_list[0]))
                    continue
            else:
                if image_inside_list[0][1] == '\n':
                    newtext = regex_sub_image.sub(r'\1|Immagine = \2\3|ExtImmagine = jpg\n\4', text)
                elif image_inside_list[0][1] == '|' or image_inside_list[0][1] == '}':
                    newtext = regex_sub_image.sub(r'\1|Immagine = \2\n|ExtImmagine = jpg\n\3\4', text)
                else:
                    newtext = regex_sub_image.sub(r'\1|Immagine = \2\4\n|ExtImmagine = jpg\n\3', text)
            if newtext != text:
                wikipedia.showDiff(text, newtext)
                try:
                    page.put(newtext, 'Bot: Aggiungo estensione al template bio')
                except Exception, e:
                    print "WARNING: %s" % e
                    wikipedia.input(u'ping') # Wait that the mainteiner takes a look before go on
                    continue
 
if __name__ == "__main__":
    try:
        main()
    finally:
        wikipedia.stopme()