Python:ScanCancellate.py

#!/usr/bin/python
#! -*- coding: utf-8 -*-
 
# Author: Lusum
# License: GPL2
# Description: Program to find if a new page has been already deleted
"""
You can run the bot with the following commandline parameters:
 
-new - Choose the number of new pages to analyze
 
Examples:
  python scanCancellate.py -new:60   #exam 60 new pages
"""
import wikipedia, pagegenerators
import query
 
def get_log_delete( title ):
 
    params = {
        'action'    :'query',
        'list'      :'logevents',
        'letype'    :'delete',
        'letitle'    :title,
        'leprop'    :'timestamp|comment|type',
    }
 
    results = query.GetData(params, useAPI = True, encodeTitle = False)
 
    events = results['query']['logevents']
 
    return events
 
def pagina_da_esaminare( title ):
    templista = []
    events = get_log_delete( title )
    for res in events:
        comment = res['comment']
        if comment.find('semplificata') != -1:
                wikipedia.output("\03{lightred}Cancellata in semplificata %s \n"  % ( title ))
        if comment.find('C4') != -1:
                wikipedia.output("\03{lightred}Cancellata promozionale %s \n"  % ( title ))
        if comment.find('C7') != -1:
                wikipedia.output("\03{lightred}Cancellata reinserita %s \n"  % ( title ))
 
def main():
    gen = None
 
    # Number of pages to load at a time by Preload generator
    pageNumber = 40
    # Default number of pages for NewPages generator
    number = 60
 
    # Which namespaces should be processed?
    # default to [] which means all namespaces will be processed
    namespaces = []
    genFactory = pagegenerators.GeneratorFactory()
 
    args = wikipedia.handleArgs()
 
    for arg in args:
        if arg.startswith('-new'):
            if len(arg) >=5:
              number = int(arg[5:])
 
    gen = pagegenerators.NewpagesPageGenerator(number = number)
    # Preload generator work better if 'pageNumber' is not major than 'number',
    # this avoid unnecessary delay.
    if number < pageNumber:
            pageNumber = number
 
    if namespaces != []:
        gen =  pagegenerators.NamespaceFilterPageGenerator(gen, namespaces)
    preloadingGen = pagegenerators.PreloadingGenerator(gen, pageNumber = pageNumber)
 
    for page in preloadingGen:
        try:
            # Load the page's text from the wiki
                wikipedia.output(page.title())
        except wikipedia.NoPage:
            wikipedia.output(u'Page %s not found' % page.title())
            continue
        except wikipedia.IsRedirectPage:
            newpage = page.getRedirectTarget()
            wikipedia.output(u'Page %s redirect to \'%s\'' % (page.aslink(), newpage.title()))
            continue
 
        if page.isDisambig():
            wikipedia.output(u'Page %s is a disambiguation page' % page.aslink())
            continue
 
        pagina_da_esaminare( page.title() )
 
if __name__ == "__main__":
    try:
        main()
    finally:
        wikipedia.stopme()