Python:Screencopy.py

#!/usr/bin/env python
#-*- coding:utf-8 -*-
 
#
# (C) FiloSottile, 2010
#
# Distributed under the terms of the CC-GNU GPL License.
#
 
import wikipedia
import sys, webbrowser
import re
import catlib
from datetime import datetime
 
rec_templates = {'Film' : 'film',
                 'Fumetto e animazione' : 'cartone',
                 'ProgrammaTV' : 'tv', 'FictionTV' : 'tv',
                 'Gamebox' : 'videogioco',
                 'Software' : 'software', 'Infobox Software': 'software',
                 'Album' : 'video musicale',
                 'Spettacolo teatrale': 'teatro'}
 
categoria = 'Categoria:Screenshot copyrighted'
 
editSummary = 'Bot: fix {{Screenshot Copyrighted}} - categoria "%s" - [[Utente:BotSottile/Task#screencopy.py]]'
 
logpage = 'Utente:BotSottile/risultati/screencopy'
 
def capitalize(s):
    return (s[0].upper() + s[1:]).strip().replace('_', ' ')
 
class ScreenBot():
    def __init__(self, cat):
        self.images = cat.articles()
        #self.images = [wikipedia.ImagePage(wikipedia.getSite(), u'File:Ale e Franz - È tanto che aspetti.png')]
        self.acceptall = False
        self.log = ([], [], [])
 
    def run(self):
        for image in self.images:
            if not image.isImage(): continue
            wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
                                 % image.titleWithoutNamespace())
            using = list(wikipedia.ImagePage.usingPages(image))
            if len(using) != 1:
                wikipedia.output('\03{lightred}' + image.aslink() + '\03{default} used in more than one page or none at all')
                us = list(u.aslink() for u in using)
                self.log[0].append((image.aslink().replace('[[', '[[:'), us))
                continue
            templates = []
            othertl = []
            for tl in using[0].templatesWithParams():
                r = re.escape(image.titleWithoutNamespace()).replace('\ ', '***$$$***')     \
                                                            .replace('_', '***$$$***')      \
                                                            .replace('***$$$***', '[ _]')
                r = '[' + r[0].lower() + r[0].upper() + ']' + r[1:]
                #print r
                r = re.compile(r)
                if r.search(str(tl[1])):
                    if capitalize(tl[0]) in rec_templates.keys():
                        templates.append(tl[0])
                    else:
                        othertl.append(tl[0])
            if len(templates) != 1:
                if not othertl:
                    wikipedia.output('In \03{lightred}' + using[0].aslink() + '\03{default} there are more than one recognized template or none at all')
                    self.log[1].append((image.aslink().replace('[[', '[[:'), using[0].aslink()))
                    continue
                else:
                    wikipedia.output('In ' + using[0].aslink() + ' is/are used this/these template {{\03{lightred}' + '"\03{default}}}, {{\03{lightred}"'.join(othertl) + '\03{default}}}')
                    self.log[2].append((image.aslink().replace('[[', '[[:'), using[0].aslink(), \
                                       '{{tl|' + '}}<br />{{tl|'.join(othertl) + '}}'))
                    continue
            template = templates[0]
            category = rec_templates[capitalize(template)]
            wikipedia.output(u"Page: {{\03{lightblue}%s\03{default}}} - Template: {{\03{lightblue}%s\03{default}}}" \
                                                                    % (using[0].aslink(), template))
            text = image.get()
            param  = ''
            for tl in image.templatesWithParams():
                if capitalize(tl[0]) == 'Screenshot Copyrighted' or capitalize(tl[0]) == 'Screenshot copyrighted':
                    if len(tl[1]) > 0 and tl[1][0] != '': param = tl[1][0]
            new = re.sub(r'\{\{[sS]creenshot [Cc]opyrighted[^\}]*\}\}', '{{Screenshot Copyrighted|%s|%s}}' %(param, category), text)
            wikipedia.showDiff(text, new)
 
            if self.acceptall and new != text:
                try:
                    image.put(new, editSummary % category)
                    continue
                except wikipedia.EditConflict:
                    wikipedia.output(u'Skipping %s because of edit conflict'
                                     % (image.title(),))
                except wikipedia.SpamfilterError, e:
                    wikipedia.output(
                        u'Cannot change %s because of blacklist entry %s'
                        % (image.title(), e.url))
                except wikipedia.PageNotSaved, error:
                    wikipedia.output(u'Error putting page: %s'
                                     % (error.args,))
                except wikipedia.LockedPage:
                    wikipedia.output(u'Skipping %s (locked page)'
                                     % (image.title(),))
 
            while True:
                choice = wikipedia.inputChoice(
                            u'Do you want to accept these changes?',
                            ['Yes', 'No', 'open in Browser', 'All', "Quit"],
                            ['y', 'N', 'b', 'a', 'q'], 'N')
                if choice == 'b':
                    webbrowser.open("http://%s%s" % (
                        image.site().hostname(),
                        image.site().nice_get_address(image.title())
                    ))
                    wikipedia.input("Press Enter when finished in browser.")
                    text = image.get(get_redirect=True, force=True)
                    continue
                if choice == 'q':
                    return
                if choice == 'y':
                    image.put_async(new, editSummary % category)
                if choice == 'a':
                    image.put_async(new, editSummary % category)
                    self.acceptall = True
                # choice must be 'N'
                break
        self.put_log()
    def put_log(self):
        res = '==[[Utente:BotSottile/Task#screencopy.py]] - %s==\n\n' % datetime.now().strftime("%d %B %Y %I:%M%p")
        righe = list(e[0] + ': ' + ', '.join(e[1]) for e in self.log[0])
        res += "=== Immagini non usate in una sola pagina ===\n* "
        res += "\n* ".join(righe)
        righe = list(': '.join(e) for e in self.log[1])
        res += "\n\n=== Immagini non usate in template ===\n* "
        res += "\n* ".join(righe)
        righe = list(' || '.join(e) for e in self.log[2])
        res += """
 
=== Immagini usate in template sconosciuti ===
{| class="wikitable sortable"
! Immagine !! pagina !! template
|-
| """
        res += "\n|-\n| ".join(righe)
        res += "\n|}"
        wikipedia.Page(wikipedia.getSite(), logpage).put(res, 'Bot: risultato [[Utente:BotSottile/Task#screencopy.py]]')
 
if __name__ == "__main__":
    try:
        site = wikipedia.getSite()
        category = catlib.Category(site, categoria)
        bot = ScreenBot(category)
        bot.run()
    finally:
        try: bot.put_log()
        except: pass
        wikipedia.stopme()