Ejemplo n.º 1
0
def main():
    genFactory = pagegenerators.GeneratorFactory()
    # The generator gives the pages that should be worked upon.
    gen = None
    pageTitleParts = []

    for arg in pywikibot.handleArgs():
        if arg.startswith("-reg"):
            arg = '-transcludes:Infobox film'
        if not genFactory.handleArg(arg):
            pageTitleParts.append(arg)

    if pageTitleParts != []:
        # We will only work on a single page.
        pageTitle = ' '.join(pageTitleParts)
        page = pywikibot.Page(pywikibot.getSite(), pageTitle)
        gen = iter([page])

    if not gen:
        gen = genFactory.getCombinedGenerator()
    if gen:
        # The preloading generator is responsible for downloading multiple
        # pages from the wiki simultaneously.
        gen = pagegenerators.PreloadingGenerator(gen)
        bot = FilmBannerBot(gen)
        bot.run()
    else:
        pywikibot.showHelp()
def main():
    wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))

    # Connect database, we need that
    conn = None
    cursor = None
    (conn, cursor) = connectDatabase()

    generator = None
    genFactory = pagegenerators.GeneratorFactory()

    for arg in wikipedia.handleArgs():
        genFactory.handleArg(arg)

    generator = genFactory.getCombinedGenerator()

    if not generator:
        generator = getRijksmonumentWithoutLocation()

    # Get a preloading generator with only images
    pgenerator = pagegenerators.PreloadingGenerator(
        pagegenerators.NamespaceFilterPageGenerator(generator, [6]))
    for page in pgenerator:
        locationTemplate = locateImage(page, conn, cursor)
        if locationTemplate:
            addLocation(page, locationTemplate)
Ejemplo n.º 3
0
def main(*args):
    try:
        genFactory = pagegenerators.GeneratorFactory()
        for arg in pywikibot.handleArgs(*args):
            if not genFactory.handleArg(arg):
                pywikibot.showHelp()
                break
        else:
            gen = genFactory.getCombinedGenerator()
            if gen:
                page_match = re.compile('\{\{AFC submission\|')
                summary = u"[[User:HasteurBot|HasteurBot Task 3]]: Removing " + \
                  u"maint category that does not apply"
                disclude_list = [
                    u'Wikipedia talk:WikiProject Articles for creation',
                    u'Wikipedia talk:WikiProject Articles for creation/2013 5',
                    u'Wikipedia talk:WikiProject Articles for creation/2011',
                ]
                for article in gen:
                    if article.title() in disclude_list:
                        continue
                    art_text = article.get()
                    if page_match.match(art_text) is not None:
                        print article
                        art_1 = re.sub(
                            '\\\n\[\[\:Category\:AfC_submissions_with_missing_AfC_template\]\]',
                            '', art_text)
                        art_2 = re.sub(
                            '\\\n\[\[\:Category\:AfC submissions with missing AfC template\]\]',
                            '', art_1)
                        article.put(art_2, comment=summary)
            else:
                pywikibot.showHelp()
    finally:
        pywikibot.stopme()
Ejemplo n.º 4
0
def main(args):
    """ Grab a bunch of images and tag them if they are not categorized. """
    generator = None
    genFactory = pagegenerators.GeneratorFactory()

    site = pywikibot.getSite(u'commons', u'commons')
    pywikibot.setSite(site)
    for arg in pywikibot.handleArgs():
        if arg.startswith('-yesterday'):
            generator = uploadedYesterday(site)
        elif arg.startswith('-recentchanges'):
            generator = recentChanges(site=site, delay=120)
        else:
            genFactory.handleArg(arg)
    if not generator:
        generator = genFactory.getCombinedGenerator()
    if not generator:
        pywikibot.output(u'You have to specify the generator you want to use '
                         u'for the program!')
    else:
        pregenerator = pagegenerators.PreloadingGenerator(generator)
        for page in pregenerator:
            if page.exists() and (page.namespace() == 6) \
               and (not page.isRedirectPage()):
                if isUncat(page):
                    addUncat(page)
Ejemplo n.º 5
0
def main(args):
    '''
    Main loop. Get a generator and options. Work on all images in the generator.
    '''
    generator = None
    onlyFilter = False
    onlyUncat = False
    genFactory = pagegenerators.GeneratorFactory()

    global search_wikis
    global hint_wiki

    site = pywikibot.getSite(u'commons', u'commons')
    pywikibot.setSite(site)
    for arg in pywikibot.handleArgs():
        if arg == '-onlyfilter':
            onlyFilter = True
        elif arg == '-onlyuncat':
            onlyUncat = True
        elif arg.startswith('-hint:'):
            hint_wiki = arg [len('-hint:'):]
        elif arg.startswith('-onlyhint'):
            search_wikis = arg [len('-onlyhint:'):]
        else:
            genFactory.handleArg(arg)

    generator = genFactory.getCombinedGenerator()
    if not generator:
        generator = pagegenerators.CategorizedPageGenerator(
            catlib.Category(site, u'Category:Media needing categories'),
            recurse=True)
    initLists()
    categorizeImages(generator, onlyFilter, onlyUncat)
    pywikibot.output(u'All done')
Ejemplo n.º 6
0
def main(*args):
    # Disable cosmetic changes because we don't want to modify any page
    # content, so that we don't flood the histories with minor changes.
    config.cosmetic_changes = False
    #page generator
    gen = None
    genFactory = pagegenerators.GeneratorFactory()
    redirs = False
    # If the user chooses to work on a single page, this temporary array is
    # used to read the words from the page title. The words will later be
    # joined with spaces to retrieve the full title.
    pageTitle = []
    for arg in pywikibot.handleArgs(*args):
        if genFactory.handleArg(arg):
            continue
        if arg == '-redir':
            redirs = True
        else:
            pageTitle.append(arg)

    gen = genFactory.getCombinedGenerator()
    if not gen:
        if pageTitle:
            # work on a single page
            page = pywikibot.Page(pywikibot.getSite(), ' '.join(pageTitle))
            gen = iter([page])
        else:
            pywikibot.showHelp()
            return
    preloadingGen = pagegenerators.PreloadingGenerator(gen)
    bot = TouchBot(preloadingGen, redirs)
    bot.run()
Ejemplo n.º 7
0
def main():
    #page generator
    gen = None
    # This temporary array is used to read the page title if one single
    # page to work on is specified by the arguments.
    pageTitle = []
    # Which namespaces should be processed?
    # default to [] which means all namespaces will be processed
    namespaces = []
    # Never ask before changing a page
    always = False
    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs():
        if arg.startswith('-xml'):
            if len(arg) == 4:
                xmlFilename = i18n.input('pywikibot-enter-xml-filename')
            else:
                xmlFilename = arg[5:]
            gen = XmlDumpNoReferencesPageGenerator(xmlFilename)
        elif arg.startswith('-namespace:'):
            try:
                namespaces.append(int(arg[11:]))
            except ValueError:
                namespaces.append(arg[11:])
        elif arg == '-always':
            always = True
        else:
            if not genFactory.handleArg(arg):
                pageTitle.append(arg)

    if pageTitle:
        page = pywikibot.Page(pywikibot.getSite(), ' '.join(pageTitle))
        gen = iter([page])
    if not gen:
        gen = genFactory.getCombinedGenerator()
    if not gen:
        site = pywikibot.getSite()
        try:
            cat = maintenance_category[site.family.name][site.lang]
        except:
            pass
        else:
            import catlib
            if not namespaces:
                namespaces = [0]
            cat = catlib.Category(site,
                                  "%s:%s" % (site.category_namespace(), cat))
            gen = pagegenerators.CategorizedPageGenerator(cat)
    if not gen:
        pywikibot.showHelp('noreferences')
    else:
        if namespaces:
            gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces)
        preloadingGen = pagegenerators.PreloadingGenerator(gen)
        bot = NoReferencesBot(preloadingGen, always)
        bot.run()
Ejemplo n.º 8
0
def main():
    #page generator
    gen = None
    # If the user chooses to work on a single page, this temporary array is
    # used to read the words from the page title. The words will later be
    # joined with spaces to retrieve the full title.
    pageTitle = []
    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs():
        if not genFactory.handleArg(arg):
            pageTitle.append(arg)

    if pageTitle:
        # work on a single page
        page = pywikibot.Page(pywikibot.getSite(), ' '.join(pageTitle))
        gen = iter([page])
    if not gen:
        gen = genFactory.getCombinedGenerator()
    if not gen:
        pywikibot.showHelp('inline_images')
    else:
        preloadingGen = pagegenerators.PreloadingGenerator(gen)
        bot = InlineImagesRobot(preloadingGen)
        bot.run()
Ejemplo n.º 9
0
def main():
    wikipedia.output(u'Testing 1 2 3')
    generator = None
    genFactory = pagegenerators.GeneratorFactory()

    site = wikipedia.getSite(u'commons', u'commons')
    wikipedia.setSite(site)
    for arg in wikipedia.handleArgs():
        if arg.startswith('-page'):
            if len(arg) == 5:
                generator = [
                    wikipedia.Page(
                        site,
                        wikipedia.input(u'What page do you want to use?'))
                ]
            else:
                generator = [wikipedia.Page(site, arg[6:])]
        else:
            generator = genFactory.handleArg(arg)
    if generator:
        for page in generator:
            if (page.namespace() == 14):
                sort_TOL_Category(catlib.Category(site, page.title()))
    else:
        wikipedia.output(u'No categories to work on!')
Ejemplo n.º 10
0
def main():
    genFactory = pagegenerators.GeneratorFactory()
    commandline_arguments = list()
    templateTitle = u''
    for arg in pywikibot.handleArgs():
        if arg.startswith('-template'):
            if len(arg) == 9:
                templateTitle = pywikibot.input(
                    u'Please enter the template to work on:')
            else:
                templateTitle = arg[10:]
        elif genFactory.handleArg(arg):
            continue
        else:
            commandline_arguments.append(arg)

    if len(commandline_arguments) % 2 or not templateTitle:
        raise ValueError  # or something.
    fields = dict()

    for i in xrange(0, len(commandline_arguments), 2):
        fields[commandline_arguments[i]] = commandline_arguments[i + 1]
    if templateTitle:
        gen = pagegenerators.ReferringPageGenerator(pywikibot.Page(
            pywikibot.getSite(), "Template:%s" % templateTitle),
                                                    onlyTemplateInclusion=True)
    else:
        gen = genFactory.getCombinedGenerator()
    if not gen:
        # TODO: Build a transcluding generator based on templateTitle
        return

    bot = HarvestRobot(gen, templateTitle, fields)
    bot.run()
Ejemplo n.º 11
0
def main(args):
    '''
    Main loop. Get a generator and options.
    '''
    generator = None
    parent = u''
    basename = u''
    always = False

    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs():
        if arg == '-always':
            always = True
        elif arg.startswith('-parent:'):
            parent = arg [len('-parent:'):].strip()
        elif arg.startswith('-basename'):
            basename = arg [len('-basename:'):].strip()
        else:
            genFactory.handleArg(arg)

    generator = genFactory.getCombinedGenerator()
    if generator:
        for page in generator:
            createCategory(page, parent, basename)
    else:
        pywikibot.output(u'No pages to work on')

    pywikibot.output(u'All done')
Ejemplo n.º 12
0
def Manual_main():
    wikipedia.config.put_throttle = 0
    wikipedia.put_throttle.setDelay()
    gen= None
    word=u''
    PageTitles = []
    genFactory = pagegenerators.GeneratorFactory()
    for arg in wikipedia.handleArgs():
        if arg.startswith( '-page' ):
            PageTitles.append( arg[6:] )
            break
        else:
            generator = genFactory.handleArg( arg )
            if generator:
                gen = generator
    if PageTitles:
        pages = [wikipedia.Page(wikipedia.getSite(),PageTitle) for PageTitle in PageTitles]
        gen = iter( pages )
    if not gen:
        wikipedia.stopme()    
        sys.exit()
    preloadingGen = pagegenerators.PreloadingGenerator(gen,pageNumber = 60)
    for faTitle in preloadingGen:
        wikipedia.output(u'---'+faTitle.title()+u'-----')
        OurResult=main(faTitle.title(),word)
        OurResult=Open_json(OurResult,faTitle.title())
        if OurResult.strip():
            wikipedia.output(OurResult)
            with codecs.open(BotAdress_main+u'zz_most_miss_result.txt' ,mode = 'a',encoding = 'utf8' ) as f:
                f.write(OurResult.strip()+u'\n')
            with codecs.open(BotAdress_main+u'zz_most_miss_result_number.txt' ,mode = 'a',encoding = 'utf8' ) as f:
                f.write(OurResult.split(u'@')[0].strip()+u'\n')
Ejemplo n.º 13
0
def main():
    bot = None
    action = None

    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()
    gen = None

    for arg in wikipedia.handleArgs():
        if action == None:
            action = arg
        else:
            generator = genFactory.handleArg(arg)
            if generator:
                gen = generator

    if action == 'export':
        if gen == None:
            wikipedia.output(
                u'\03{lightred}Export bot needs a page generator to itterate over.\03{default}'
            )
            return
        bot = GEExport(gen)
    elif action == 'import':
        bot = GEImport()
    if bot == None:
        wikipedia.output(
            u'\03{lightred}Invalid bot action to run.\03{default}')
        return
    bot.run()
Ejemplo n.º 14
0
def main():
    featured = False
    gen = None

    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs():
        if arg == '-featured':
            featured = True
        else:
            genFactory.handleArg(arg)

    mysite = pywikibot.getSite()
    if mysite.sitename() == 'wikipedia:nl':
        pywikibot.output(
            u'\03{lightred}There is consensus on the Dutch Wikipedia that bots should not be used to fix redirects.\03{default}'
        )
        sys.exit()

    if featured:
        featuredList = pywikibot.translate(mysite, featured_articles)
        ref = pywikibot.Page(pywikibot.getSite(), featuredList)
        gen = pagegenerators.ReferringPageGenerator(ref)
        gen = pagegenerators.NamespaceFilterPageGenerator(gen, [0])
    if not gen:
        gen = genFactory.getCombinedGenerator()
    if gen:
        for page in pagegenerators.PreloadingGenerator(gen):
            workon(page)
    else:
        pywikibot.showHelp('fixing_redirects')
Ejemplo n.º 15
0
def main():
    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()
    # The generator gives the pages that should be worked upon.
    gen = None
    # This temporary array is used to read the page title if one single
    # page to work on is specified by the arguments.
    pageTitleParts = []

    # Parse command line arguments
    for arg in pywikibot.handleArgs():
        if arg.startswith("-reg"):
            arg = '-cat:Unassessed film articles'
        if not genFactory.handleArg(arg):
            pageTitleParts.append(arg)

    if pageTitleParts != []:
        # We will only work on a single page.
        pageTitle = ' '.join(pageTitleParts)
        page = pywikibot.Page(pywikibot.getSite(), pageTitle)
        gen = iter([page])

    if not gen:
        gen = genFactory.getCombinedGenerator()
    if gen:
        # The preloading generator is responsible for downloading multiple
        # pages from the wiki simultaneously.
        gen = pagegenerators.PreloadingGenerator(
            filmfunctions.PagesFromTalkPagesGenerator(gen))
        bot = FilmAssessBot(gen)
        bot.run()
    else:
        pywikibot.showHelp()
Ejemplo n.º 16
0
def main(args):
    pywikibot.output(u'WARNING: This is an experimental bot')
    pywikibot.output(
        u'WARNING: It will only work on self published work images')
    pywikibot.output(u'WARNING: This bot is still full of bugs')
    pywikibot.output(u'WARNING: Use at your own risk!')

    generator = None
    autonomous = False
    checkTemplate = True

    # Load a lot of default generators
    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs():
        if arg == '-nochecktemplate':
            checkTemplate = False
        elif arg == '-autonomous':
            autonomous = True
        else:
            genFactory.handleArg(arg)

    if not supportedSite():
        pywikibot.output(u'Sorry, this site is not supported (yet).')
        return False

    generator = genFactory.getCombinedGenerator()
    if not generator:
        raise add_text.NoEnoughData(
            'You have to specify the generator you want to use for the script!'
        )

    pregenerator = pagegenerators.PreloadingGenerator(generator)

    prefetchQueue = Queue(maxsize=50)
    uploadQueue = Queue(maxsize=200)

    imageFetcherThread = imageFetcher(pregenerator, prefetchQueue)
    userInteractionThread = userInteraction(prefetchQueue, uploadQueue)
    uploaderThread = uploader(uploadQueue)

    imageFetcherThread.daemon = False
    userInteractionThread.daemon = False
    uploaderThread.daemon = False

    if autonomous:
        pywikibot.output(
            u'Bot is running in autonomous mode. There will be no user interaction.'
        )
        userInteractionThread.setAutonomous()

    if not checkTemplate:
        pywikibot.output(
            u'No check template will be added to the uploaded files.')
        uploaderThread.nochecktemplate()

    fetchDone = imageFetcherThread.start()
    userDone = userInteractionThread.start()
    uploadDone = uploaderThread.start()
Ejemplo n.º 17
0
def main():
    #page generator
    gen = None
    # This temporary array is used to read the page title if one single
    # page to work on is specified by the arguments.
    pageTitle = []
    # Which namespaces should be processed?
    # default to [] which means all namespaces will be processed
    namespaces = []
    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()
    always = False

    for arg in pywikibot.handleArgs():
        if arg.startswith('-xml'):
            if len(arg) == 4:
                xmlFilename = pywikibot.input(
                    u'Please enter the XML dump\'s filename:')
            else:
                xmlFilename = arg[5:]
            gen = XmlDumpSelflinkPageGenerator(xmlFilename)
        elif arg == '-sql':
            # NOT WORKING YET
            query = """
SELECT page_namespace, page_title
FROM page JOIN pagelinks JOIN text ON (page_id = pl_from AND page_id = old_id)
WHERE pl_title = page_title
AND pl_namespace = page_namespace
AND page_namespace = 0
AND (old_text LIKE concat('%[[', page_title, ']]%')
    OR old_text LIKE concat('%[[', page_title, '|%'))
LIMIT 100"""
            gen = pagegenerators.MySQLPageGenerator(query)
        elif arg.startswith('-namespace:'):
            try:
                namespaces.append(int(arg[11:]))
            except ValueError:
                namespaces.append(arg[11:])
        elif arg == '-always':
            always = True
        else:
            if not genFactory.handleArg(arg):
                pageTitle.append(arg)

    if pageTitle:
        page = pywikibot.Page(pywikibot.getSite(), ' '.join(pageTitle))
        gen = iter([page])
    if not gen:
        gen = genFactory.getCombinedGenerator()
    if not gen:
        pywikibot.showHelp('selflink')
    else:
        if namespaces != []:
            gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces)
        preloadingGen = pagegenerators.PreloadingGenerator(gen)
        bot = SelflinkBot(preloadingGen, always)
        bot.run()
Ejemplo n.º 18
0
def main(args):
    '''
    Main loop.
    '''

    genFactory = pagegenerators.GeneratorFactory()

    start_id = 0
    end_id = 0
    updaterun = False
    site = wikipedia.getSite('commons', 'commons')
    wikipedia.setSite(site)
    updatePage = wikipedia.Page(site, u'User:BotMultichillT/Air_Force_latest')
    interval = 100

    for arg in wikipedia.handleArgs():
        if arg.startswith('-start_id'):
            if len(arg) == 9:
                start_id = wikipedia.input(
                    u'What is the id of the photo you want to start at?')
            else:
                start_id = arg[10:]
        elif arg.startswith('-end_id'):
            if len(arg) == 7:
                end_id = wikipedia.input(
                    u'What is the id of the photo you want to end at?')
            else:
                end_id = arg[8:]
        elif arg == u'-updaterun':
            updaterun = True
        elif arg.startswith('-interval'):
            if len(arg) == 9:
                interval = wikipedia.input(
                    u'What interval do you want to use?')
            else:
                interval = arg[10:]
        else:
            genFactory.handleArg(arg)
    generator = genFactory.getCombinedGenerator()
    # Do we have a pagenerator?
    if generator:
        for page in generator:
            if page.namespace() == 14:
                processCategory(page)

    # Is updaterun set?
    elif updaterun:
        start_id = int(updatePage.get())
        end_id = start_id + int(interval)
        last_id = processPhotos(int(start_id), int(end_id))
        comment = u'Worked from ' + str(start_id) + u' to ' + str(last_id)
        updatePage.put(str(last_id), comment)

    # Do we have a start_id and a end_id
    elif int(start_id) > 0 and int(end_id) > 0:
        last_id = processPhotos(int(start_id), int(end_id))
    # Use the default generator
    else:
        print "Screw this, will implement later"
Ejemplo n.º 19
0
def main():
    summary_commandline,template,gen = None,None,None
    exceptions,PageTitles,namespaces = [],[],[]
    cat=''
    autoText,autoTitle = False,False
    genFactory = pagegenerators.GeneratorFactory()
    arg=False#------if you dont want to work with arguments leave it False if you want change it to True---
    if arg==False:
        for arg in wikipedia.handleArgs():
            if arg == '-autotitle':
                autoTitle = True
            elif arg == '-autotext':
                autoText = True
            elif arg.startswith( '-page:' ):
                if len(arg) == 6:
                    PageTitles.append(wikipedia.input( u'Which page do you want to chage?' ))
                else:
                    PageTitles.append(arg[6:])
            elif arg.startswith( '-cat:' ):
                if len(arg) == 5:
                    cat=wikipedia.input( u'Which Category do you want to chage?' )
                else:
                    cat='Category:'+arg[5:]
            elif arg.startswith( '-template:' ):
                if len(arg) == 10:
                    template.append(wikipedia.input( u'Which Template do you want to chage?' ))
                else:
                    template.append('Template:'+arg[10:])
            elif arg.startswith('-except:'):
                exceptions.append(arg[8:])
            elif arg.startswith( '-namespace:' ):
                namespaces.append( int( arg[11:] ) )
            elif arg.startswith( '-ns:' ):
                namespaces.append( int( arg[4:] ) )    
            elif arg.startswith( '-summary:' ):
                wikipedia.setAction( arg[9:] )
                summary_commandline = True
            else:
                generator = genFactory.handleArg(arg)
                if generator:
                    gen = generator
    else:
        PageTitles = [raw_input(u'Page:> ').decode('utf-8')]
    if cat!='':
        facatfalist=facatlist(cat)
        if facatfalist!=False:
            run(facatfalist)    
    if PageTitles:
        pages = [wikipedia.Page(faSite,PageTitle) for PageTitle in PageTitles]
        gen = iter( pages )
    if not gen:
        wikipedia.stopme()
        sys.exit()
    if namespaces != []:
        gen = pagegenerators.NamespaceFilterPageGenerator( gen,namespaces )
    preloadingGen = pagegenerators.PreloadingGenerator( gen,pageNumber = 60 )#---number of pages that you want load at same time
    run(preloadingGen)
Ejemplo n.º 20
0
def main():
    summary_commandline, gen, template = None, None, None
    namespaces, PageTitles, exceptions = [], [], []
    encat = ''
    autoText, autoTitle = False, False
    recentcat, newcat = False, False
    genFactory = pagegenerators.GeneratorFactory()
    for arg in wikipedia.handleArgs():
        if arg == '-autotitle':
            autoTitle = True
        elif arg == '-autotext':
            autoText = True
        elif arg.startswith('-except:'):
            exceptions.append(arg[8:])

        elif arg.startswith('-start'):
            firstPageTitle = arg[7:]
            if not firstPageTitle:
                firstPageTitle = wikipedia.input(
                    u'At which page do you want to start?')
            firstPageTitle = wikipedia.Page(
                fasite, firstPageTitle).title(withNamespace=False)
            gen = pagegenerators.AllpagesPageGenerator(firstPageTitle,
                                                       0,
                                                       includeredirects=True)
        elif arg.startswith('-template:'):
            template = arg[10:]
        elif arg.startswith('-namespace:'):
            namespaces.append(int(arg[11:]))
        elif arg.startswith('-summary:'):
            wikipedia.setAction(arg[9:])
            summary_commandline = True
        else:
            generator = genFactory.handleArg(arg)
            if generator:
                gen = generator
    if not gen:
        wikipedia.stopme()
        sys.exit()
    if namespaces != []:
        gen = pagegenerators.PreloadingGenerator(gen, pageNumber=60)
        preloadingGen = pagegenerators.NamespaceFilterPageGenerator(
            gen, namespaces)
    else:
        preloadingGen = pagegenerators.PreloadingGenerator(gen, pageNumber=60)
    _cache, last_timestamp = get_cache()
    add_text(preloadingGen)

    now = str(datetime.now())
    todaynum = int(now.split('-')[2].split(' ')[0]) + int(
        now.split('-')[1]) * 30 + (int(now.split('-')[0]) - 2000) * 365

    if last_timestamp + 3 < todaynum:
        put_cache(_cache, todaynum)
    else:
        put_cache({}, 0)
Ejemplo n.º 21
0
def main():
    # HACK: This can be removed when pywikipedia bug 3315395 has been fixed
    safetyLock = 'birthcat-unlock.dat'
    if not os.path.exists(safetyLock):
        choice = pywikibot.inputChoice(
            u'Have you patched textlib.py in pywikipedia?', ['Yes', 'No'],
            ['y', 'N'], 'N')
        if choice == 'y':
            open(safetyLock, 'w').close()
        else:
            return False
    # END OF HACK

    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()
    # The generator gives the pages that should be worked upon.
    gen = None
    # This temporary array is used to read the page title if one single
    # page to work on is specified by the arguments.
    pageTitleParts = []
    # If dry is True, doesn't do any real changes, but only show
    # what would have been changed.
    dry = False
    # If auto is True, run in autonomous mode.
    auto = False

    # Parse command line arguments
    for arg in pywikibot.handleArgs():
        if arg.startswith("-dry"):
            dry = True
        elif arg.startswith("-auto"):
            auto = True
        else:
            # check if a standard argument like
            # -start:XYZ or -ref:Asdf was given.
            if not genFactory.handleArg(arg):
                pageTitleParts.append(arg)

    if pageTitleParts != []:
        # We will only work on a single page.
        pageTitle = ' '.join(pageTitleParts)
        page = pywikibot.Page(pywikibot.getSite(), pageTitle)
        gen = iter([page])

    if not gen:
        gen = genFactory.getCombinedGenerator()
    if gen:
        # The preloading generator is responsible for downloading multiple
        # pages from the wiki simultaneously.
        gen = pagegenerators.PreloadingGenerator(gen)
        bot = BirthCatBot(gen, auto, dry)
        bot.run()
    else:
        pywikibot.showHelp()
Ejemplo n.º 22
0
def main(*args):
    global catDB

    fromGiven = False
    toGiven = False
    batchMode = False
    editSummary = ''
    inPlace = False
    overwrite = False
    showImages = False
    talkPages = False
    recurse = False
    withHistory = False
    titleRegex = None
    pagesonly = False

    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()
    # The generator gives the pages that should be worked upon.
    gen = None

    # If this is set to true then the custom edit summary given for removing
    # categories from articles will also be used as the deletion reason.
    useSummaryForDeletion = True
    catDB = CategoryDatabase()
    action = None
    sort_by_last_name = False
    restore = False
    create_pages = False
    action = 'listify'
    #for arg in pywikibot.handleArgs(*args):
    #    if arg == 'listify':
    #        action = 'listify'
    #    else:
    #        genFactory.handleArg(arg)

    if action == 'listify':
        oldCatTitle = 'test'
        #if (fromGiven == False):
        #    oldCatTitle = pywikibot.input(
        #        u'Please enter the name of the category to nominate over:')
        newCatTitle = "User:HasteurBot/Log"
        recurse = True
        bot = CategoryListifyRobot(oldCatTitle,
                                   newCatTitle,
                                   editSummary,
                                   overwrite,
                                   showImages,
                                   subCats=True,
                                   talkPages=talkPages,
                                   recurse=recurse)
        bot.run()
    else:
        pywikibot.showHelp('category')
Ejemplo n.º 23
0
def main():
    genFactory = pagegenerators.GeneratorFactory()

    PageTitles = []
    xmlFilename = None
    always = False
    ignorepdf = False
    limit = None
    namespaces = []
    generator = None
    for arg in pywikibot.handleArgs():
        if arg.startswith('-namespace:'):
            try:
                namespaces.append(int(arg[11:]))
            except ValueError:
                namespaces.append(arg[11:])
        elif arg.startswith('-summary:'):
            pywikibot.setAction(arg[9:])
        elif arg == '-always':
            always = True
        elif arg == '-ignorepdf':
            ignorepdf = True
        elif arg.startswith('-limit:'):
            limit = int(arg[7:])
        elif arg.startswith('-xmlstart'):
            if len(arg) == 9:
                xmlStart = pywikibot.input(
                    u'Please enter the dumped article to start with:')
            else:
                xmlStart = arg[10:]
        elif arg.startswith('-xml'):
            if len(arg) == 4:
                xmlFilename = pywikibot.input(
                    u'Please enter the XML dump\'s filename:')
            else:
                xmlFilename = arg[5:]
        else:
            genFactory.handleArg(arg)

    if xmlFilename:
        try:
            xmlStart
        except NameError:
            xmlStart = None
        generator = XmlDumpPageGenerator(xmlFilename, xmlStart, namespaces)
    if not generator:
        generator = genFactory.getCombinedGenerator()
    if not generator:
        # syntax error, show help text from the top of this file
        pywikibot.showHelp('reflinks')
        return
    generator = pagegenerators.PreloadingGenerator(generator, pageNumber=50)
    generator = pagegenerators.RedirectFilterPageGenerator(generator)
    bot = ReferencesRobot(generator, always, limit, ignorepdf)
    bot.run()
Ejemplo n.º 24
0
def main():
    args = wikipedia.handleArgs()
    all = False
    genFactory = pagegenerators.GeneratorFactory()
    
    for currentArgument in args:   
        if currentArgument.startswith("-always"):
            all = True
        else:
            generator = genFactory.handleArg(currentArgument)
              
    # Check if pages on which the bot should work are specified.
    if not generator:
        raise Exception('You have to specify which pages the script has to work on!')
    
    # Main Loop
    for i in generator:
        attenzioneIo = False # Dubbio su "I", che può essere articolo determinativo italiano o pronome personale inglese
        titolo = i.title()
        wikipedia.output(">>>>> " + titolo + " <<<<<")
          
        nuovoTitolo = re.sub("^(The |A |An |Il |Lo |La |I |Gli |Le |L'|Uno |Una |Un'|Un )([A-Z0-9].*)", r"{{DEFAULTSORT:\2, \1}}", titolo)
        if titolo == nuovoTitolo:
            wikipedia.output("Non c'è nessun articolo. Prossima pagina...")
            continue
        
        if re.search("^I ", titolo):
            attenzioneIo = True
                
        nuovoTitolo = re.sub("[ ']\}\}", "}}", nuovoTitolo) # Toglie spazi, apostrofi...
        
        try:
            oldtext = i.get()
        except wikipedia.IsRedirectPage:
            wikipedia.output(u"%s is a redirect, I'll ignore it." % i.title())
            continue
        
        if re.search("\{\{DEFAULTSORT:", oldtext):
            wikipedia.output("C'è già un DEFAULTSORT. Prossima pagina...")
            continue
            
        newtext = add_text(page = i, addText = nuovoTitolo, putText = False, oldTextGiven = oldtext)[1]
        wikipedia.showDiff(oldtext, newtext)
        if not all or attenzioneIo:
            choice = wikipedia.inputChoice(u"Modificare?",  ['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N')
        else:
            choice = 'y'
        if choice in ['A', 'a']:
            all = True
            choice = 'y'
        if choice in ['Y', 'y']:
            i.put_async(newtext, comment="Aggiungo: " + nuovoTitolo)    
Ejemplo n.º 25
0
def main():
    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()
    # The generator gives the pages that should be worked upon.
    gen = None
    # This temporary array is used to read the page title if one single
    # page to work on is specified by the arguments.
    pageTitleParts = []
    # If dry is True, doesn't do any real changes, but only show
    # what would have been changed.
    dry = False
    # will become True when the user uses the -always flag.
    always = False
    # will input Yomi data
    input = False
    # will input Yomi data
    outputwiki = False

    # Parse command line arguments
    for arg in pywikibot.handleArgs():
        if arg.startswith("-dry"):
            dry = True
        elif arg.startswith("-always"):
            always = True
        elif arg.startswith("-input"):
            input = True
        elif arg.startswith("-outputwiki"):
            outputwiki = True
        else:
            # check if a standard argument like
            # -start:XYZ or -ref:Asdf was given.
            if not genFactory.handleArg(arg):
                pageTitleParts.append(arg)

    if pageTitleParts != []:
        # We will only work on a single page.
        pageTitle = ' '.join(pageTitleParts)
        page = pywikibot.Page(pywikibot.getSite(), pageTitle)
        gen = iter([page])

    if not gen:
        gen = genFactory.getCombinedGenerator()
    if gen:
        # The preloading generator is responsible for downloading multiple
        # pages from the wiki simultaneously.
        gen = pagegenerators.PreloadingGenerator(gen)
        bot = MuseumCategoryBot(gen, dry, always, input, outputwiki)
        bot.run()
    else:
        pywikibot.showHelp()
Ejemplo n.º 26
0
def main():
    #page generator
    gen = None
    pageTitle = []
    editSummary = ''
    answer = 'y'
    always = False
    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs():
        if arg.startswith('-summary:'):
            editSummary = arg[len('-summary:'):]
        elif arg == '-always':
            always = True
        elif not genFactory.handleArg(arg):
            pageTitle.append(arg)

    if editSummary == '':
        # Load default summary message.
        editSummary = pywikibot.translate(pywikibot.getSite(), msg_standalone)

    # Disabled this check. Although the point is still valid, there
    # is now a warning and a prompt (see below).
    #if pywikibot.getSite() == pywikibot.getSite('nl','wikipedia'):
    #print "Deze bot is op WikipediaNL niet gewenst."
    #print "Het toevoegen van cosmetic changes bij andere wijzigingen is toegestaan,"
    #print "maar cosmetic_changes als stand-alone bot niet."
    #print "Zoek alstublieft een nuttig gebruik voor uw bot."
    #sys.exit()

    if pageTitle:
        page = pywikibot.Page(pywikibot.getSite(), ' '.join(pageTitle))
        gen = iter([page])
    if not gen:
        gen = genFactory.getCombinedGenerator()
    if not gen:
        pywikibot.showHelp()
    elif not always:
        answer = pywikibot.inputChoice(
            warning + '\nDo you really want to continue?', ['yes', 'no'],
            ['y', 'N'], 'N')

    if answer == 'y':
        preloadingGen = pagegenerators.PreloadingGenerator(gen)
        bot = CosmeticChangesBot(preloadingGen,
                                 acceptall=always,
                                 comment=editSummary)
        bot.run()
Ejemplo n.º 27
0
def main():
    """
    Process command line arguments and invoke bot.
    """
    #page generator
    gen = None
    # This temporary array is used to read the page title if one single
    # page to work on is specified by the arguments.
    pageTitle = []
    # Which namespaces should be processed?
    # default to [] which means all namespaces will be processed
    namespaces = []
    # This factory is responsible for processing command line arguments
    # that are also used by other scripts and that determine on which pages
    # to work on.
    genFactory = pagegenerators.GeneratorFactory()
    # Never ask before changing a page
    always = False
    to13 = False
    format = False

    for arg in pywikibot.handleArgs():
        if arg.startswith('-namespace:'):
            try:
                namespaces.append(int(arg[11:]))
            except ValueError:
                namespaces.append(arg[11:])
        elif arg == '-always':
            always = True
        elif arg == '-to13':
            to13 = True
        elif arg == '-format':
            format = True
        else:
            if not genFactory.handleArg(arg):
                pageTitle.append(arg)

    site = pywikibot.getSite()
    if pageTitle:
        gen = iter([pywikibot.Page(site, t) for t in pageTitle])
    if not gen:
        gen = genFactory.getCombinedGenerator()
    if not gen:
        pywikibot.showHelp('isbn')
    else:
        if namespaces != []:
            gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces)
        preloadingGen = pagegenerators.PreloadingGenerator(gen)
        bot = IsbnBot(preloadingGen, to13=to13, format=format, always=always)
        bot.run()
Ejemplo n.º 28
0
def main(args):
    generator = None
    always = False

    # Load a lot of default generators
    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs():
        genFactory.handleArg(arg)

    generator = genFactory.getCombinedGenerator()
    if not generator:
        raise add_text.NoEnoughData(
            'You have to specify the generator you want to use for the script!'
        )

    pregenerator = pagegenerators.PreloadingGenerator(generator)

    for page in pregenerator:
        if page.exists() and (page.namespace() == 6) and \
            (not page.isRedirectPage()):
            imagepage = pywikibot.ImagePage(page.site(), page.title())
            foundNowCommons = False
            for template in imagepage.templates():
                #FIXME: Move the templates list to a lib.
                if template in pywikibot.translate(imagepage.site(),
                                                   nowCommons):
                    foundNowCommons = True
            if foundNowCommons:
                pywikibot.output(
                    u'The file %s is already tagged with NowCommons' %
                    imagepage.title())
            else:
                imagehash = imagepage.getHash()
                commons = pywikibot.getSite(u'commons', u'commons')
                duplicates = commons.getFilesFromAnHash(imagehash)
                if duplicates:
                    duplicate = duplicates.pop()
                    pywikibot.output(u'Found duplicate image at %s' %
                                     duplicate)
                    comment = i18n.twtranslate(
                        imagepage.site(), 'commons-file-now-available', {
                            'localfile': imagepage.titleWithoutNamespace(),
                            'commonsfile': duplicate
                        })
                    template = pywikibot.translate(imagepage.site(),
                                                   nowCommonsTemplate)
                    newtext = imagepage.get() + template % (duplicate, )
                    pywikibot.showDiff(imagepage.get(), newtext)
                    imagepage.put(newtext, comment)
Ejemplo n.º 29
0
def main(args):
    generator = None
    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs():
        genFactory.handleArg(arg)

    generator = genFactory.getCombinedGenerator()
    if not generator:
        return False

    for page in generator:
        if page.exists() and page.namespace() == 14:
            filterCategory(page)
Ejemplo n.º 30
0
def main(*args):
    """
    Process command line arguments and invoke bot.

    If args is an empty list, sys.argv is used.

    @param args: command line arguments
    @type args: list of unicode
    """
    summary = None
    generator = None
    always = False
    ns = []
    ns.append(14)

    # Process global args and prepare generator args parser

    genFactory = pagegenerators.GeneratorFactory()

    for arg in pywikibot.handleArgs(*args):
        if arg.startswith('-summary'):
            if len(arg) == 8:
                summary = pywikibot.input(u'What summary do you want to use?')
            else:
                summary = arg[9:]
        elif arg.startswith('-checkcurrent'):
            primaryCommonscat, commonscatAlternatives = \
                CommonscatBot.getCommonscatTemplate(
                    pywikibot.getSite().language())
            generator = pagegenerators.NamespaceFilterPageGenerator(
                pagegenerators.ReferringPageGenerator(
                    pywikibot.Page(pywikibot.getSite(),
                                   u'Template:' + primaryCommonscat),
                    onlyTemplateInclusion=True), ns)

        elif arg == '-always':
            always = True
        else:
            genFactory.handleArg(arg)

    if not generator:
        generator = genFactory.getCombinedGenerator()

    if generator:
        pregenerator = pagegenerators.PreloadingGenerator(generator)
        bot = CommonscatBot(pregenerator, always, summary)
        bot.run()
    else:
        pywikibot.showHelp()