Python wikipedia.replaceCategoryLinks函数代码示例

 def treat(self, page):
     text = self.load(page)
     if text is None:
         return
     cats = page.categories()
     # Show the title of the page we're working on.
     # Highlight the title in purple.
     pywikibot.output(
         u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
         % page.title())
     pywikibot.output(u"Current categories:")
     for cat in cats:
         pywikibot.output(u"* %s" % cat.title())
     catpl = pywikibot.Page(self.site, self.newcatTitle, defaultNamespace=14)
     if catpl in cats:
         pywikibot.output(u"%s is already in %s."
                          % (page.title(), catpl.title()))
     else:
         if self.sort:
             catpl = self.sorted_by_last_name(catpl, page)
         pywikibot.output(u'Adding %s' % catpl.title(asLink=True))
         cats.append(catpl)
         text = pywikibot.replaceCategoryLinks(text, cats)
         if not self.save(text, page, self.editSummary):
             pywikibot.output(u'Page %s not saved.'
                              % page.title(asLink=True))

def make_categories(page, list, site=None):
    if site is None:
        site = wikipedia.getSite()
    pllist = []
    for p in list:
        cattitle = "%s:%s" % (site.category_namespace(), p)
        pllist.append(wikipedia.Page(site, cattitle))
    page.put_async(wikipedia.replaceCategoryLinks(page.get(), pllist), comment=wikipedia.translate(site.lang, msg))

def make_categories(page, list, site = None):
    if site is None:
        site = pywikibot.getSite()
    pllist=[]
    for p in list:
        cattitle="%s:%s" % (site.category_namespace(), p)
        pllist.append(pywikibot.Page(site,cattitle))
    page.put_async(pywikibot.replaceCategoryLinks(page.get(), pllist),
                   comment=i18n.twtranslate(site.lang, 'catall-changing'))

    def categories(self):
        for page in self.generator:
            try:
                pywikibot.output(u'\n>>>> %s <<<<' % page.title())
                commons = pywikibot.getSite().image_repository()
                commonsCategory = catlib.Category(commons,
                                                  'Category:%s' % page.title())
                try:
                    getcommonscat = commonsCategory.get(get_redirect=True)
                    commonsCategoryTitle = commonsCategory.title()
                    categoryname = commonsCategoryTitle.split('Category:', 1)[1]
                    if page.title() == categoryname:
                        oldText = page.get()
                        text = oldText

                        # for commonscat template
                        findTemplate = re.compile(ur'\{\{[Cc]ommons')
                        s = findTemplate.search(text)
                        findTemplate2 = re.compile(ur'\{\{[Ss]isterlinks')
                        s2 = findTemplate2.search(text)
                        if s or s2:
                            pywikibot.output(u'** Already done.')
                        else:
                            text = pywikibot.replaceCategoryLinks(
                                text + u'{{commonscat|%s}}' % categoryname,
                                page.categories())
                            if oldText != text:
                                pywikibot.showDiff(oldText, text)
                                if not self.acceptall:
                                    choice = pywikibot.inputChoice(
                                        u'Do you want to accept these changes?',
                                        ['Yes', 'No', 'All'], ['y', 'N', 'a'],
                                        'N')
                                    if choice == 'a':
                                        self.acceptall = True
                                if self.acceptall or choice == 'y':
                                    try:
                                        msg = pywikibot.translate(
                                            pywikibot.getSite(), comment2)
                                        page.put(text, msg)
                                    except pywikibot.EditConflict:
                                        pywikibot.output(
                                            u'Skipping %s because of edit '
                                            u'conflict'
                                            % (page.title()))

                except pywikibot.NoPage:
                    pywikibot.output(u'Category does not exist in Commons!')

            except pywikibot.NoPage:
                pywikibot.output(u'Page %s does not exist' % page.title())
            except pywikibot.IsRedirectPage:
                pywikibot.output(u'Page %s is a redirect; skipping.'
                                 % page.title())
            except pywikibot.LockedPage:
                pywikibot.output(u'Page %s is locked' % page.title())

def putAfterTemplate (page, template, toadd, loose=True):
    '''
    Try to put text after template.
    If the template is not found return False if loose is set to False
    If loose is set to True: Remove interwiki's, categories, add template, restore categories, restore interwiki's.

    Based on cc-by-sa-3.0 code by Dschwen
    '''
    oldtext = page.get()
    newtext = u''

    templatePosition = oldtext.find(u'{{%s' % (template,))

    if templatePosition >= 0:
	previousChar = u''
	currentChar = u''
	templatePosition += 2
	curly = 1
	square = 0
	
	while templatePosition < len(oldtext):
	    currentChar = oldtext[templatePosition]

	    if currentChar == u'[' and previousChar == u'[' :
		square += 1
                previousChar = u''
            if currentChar == u']' and previousChar == u']' :
                square -= 1
                previousChar = u''
            if currentChar == u'{' and previousChar == u'{' :
                curly += 1
                previousChar = u''
            if currentChar == u'}' and previousChar == u'}' :
                curly -= 1
                previousChar = u''

	    previousChar = currentChar
	    templatePosition +=1

	    if curly == 0 and square <= 0 :
		# Found end of template
		break
	newtext = oldtext[:templatePosition] + u'\n' + toadd + oldtext[templatePosition:]
    
    else:
	if loose:
	    newtext = oldtext
	    cats = wikipedia.getCategoryLinks(newtext)
	    ll = wikipedia.getLanguageLinks(newtext)
	    nextext = wikipedia.removeLanguageLinks (newtext)
	    newtext = wikipedia.removeCategoryLinks(newtext)
	    newtext = newtext + u'\n' + toadd
	    newtext = wikipedia.replaceCategoryLinks(newtext, cats)
	    newtext = wikipedia.replaceLanguageLinks(newtext, ll)
    
    return newtext

 def standardizeCategories(self, text):
     """
     Makes sure that categories are put to the correct position, but
     does not sort them.
     """
     # The PyWikipediaBot is no longer allowed to touch categories on the German Wikipedia. See http://de.wikipedia.org/wiki/Hilfe_Diskussion:Personendaten/Archiv/bis_2006#Position_der_Personendaten_am_.22Artikelende.22
     if self.site != wikipedia.getSite('de', 'wikipedia'):
         categories = wikipedia.getCategoryLinks(text, site = self.site)
         text = wikipedia.replaceCategoryLinks(text, categories, site = self.site)
     return text

    def categories(self):
        for page in self.generator:
            try:
                wikipedia.output(u"\n>>>> %s <<<<" % page.title())
                getCommons = wikipedia.getSite("commons", "commons")
                commonsCategory = catlib.Category(getCommons, "Category:%s" % page.title())
                try:
                    getcommonscat = commonsCategory.get(get_redirect=True)
                    commonsCategoryTitle = commonsCategory.title()
                    categoryname = commonsCategoryTitle.split("Category:", 1)[1]
                    if page.title() == categoryname:
                        oldText = page.get()
                        text = oldText

                        # for commonscat template
                        findTemplate = re.compile(ur"\{\{[Cc]ommons")
                        s = findTemplate.search(text)
                        findTemplate2 = re.compile(ur"\{\{[Ss]isterlinks")
                        s2 = findTemplate2.search(text)
                        if s or s2:
                            wikipedia.output(u"** Already done.")
                        else:
                            text = wikipedia.replaceCategoryLinks(
                                text + u"{{commonscat|%s}}" % categoryname, page.categories()
                            )
                            if oldText != text:
                                wikipedia.showDiff(oldText, text)
                                if not self.acceptall:
                                    choice = wikipedia.inputChoice(
                                        u"Do you want to accept these changes?",
                                        ["Yes", "No", "All"],
                                        ["y", "N", "a"],
                                        "N",
                                    )
                                    if choice == "a":
                                        self.acceptall = True
                                if self.acceptall or choice == "y":
                                    try:
                                        msg = wikipedia.translate(wikipedia.getSite(), comment2)
                                        page.put(text, msg)
                                    except wikipedia.EditConflict:
                                        wikipedia.output(u"Skipping %s because of edit conflict" % (page.title()))

                except wikipedia.NoPage:
                    wikipedia.output(u"Category does not exist in Commons!")

            except wikipedia.NoPage:
                wikipedia.output(u"Page %s does not exist?!" % page.title())
            except wikipedia.IsRedirectPage:
                wikipedia.output(u"Page %s is a redirect; skipping." % page.title())
            except wikipedia.LockedPage:
                wikipedia.output(u"Page %s is locked?!" % page.title())

    def pages(self):
        for page in self.generator:
            try:
                pywikibot.output(u"\n>>>> %s <<<<" % page.title())
                commons = pywikibot.getSite().image_repository()
                commonspage = pywikibot.Page(commons, page.title())
                try:
                    getcommons = commonspage.get(get_redirect=True)
                    if page.title() == commonspage.title():
                        oldText = page.get()
                        text = oldText

                        # for commons template
                        findTemplate = re.compile(ur"\{\{[Cc]ommonscat")
                        s = findTemplate.search(text)
                        findTemplate2 = re.compile(ur"\{\{[Ss]isterlinks")
                        s2 = findTemplate2.search(text)
                        if s or s2:
                            pywikibot.output(u"** Already done.")
                        else:
                            text = pywikibot.replaceCategoryLinks(
                                text + u"{{commons|%s}}" % commonspage.title(), page.categories()
                            )
                            if oldText != text:
                                pywikibot.showDiff(oldText, text)
                                if not self.acceptall:
                                    choice = pywikibot.inputChoice(
                                        u"Do you want to accept these changes?",
                                        ["Yes", "No", "All"],
                                        ["y", "N", "a"],
                                        "N",
                                    )
                                    if choice == "a":
                                        self.acceptall = True
                                if self.acceptall or choice == "y":
                                    try:
                                        msg = pywikibot.translate(pywikibot.getSite(), comment1)
                                        page.put(text, msg)
                                    except pywikibot.EditConflict:
                                        pywikibot.output(u"Skipping %s because of edit " u"conflict" % (page.title()))

                except pywikibot.NoPage:
                    pywikibot.output(u"Page does not exist in Commons!")

            except pywikibot.NoPage:
                pywikibot.output(u"Page %s does not exist?!" % page.title())
            except pywikibot.IsRedirectPage:
                pywikibot.output(u"Page %s is a redirect; skipping." % page.title())
            except pywikibot.LockedPage:
                pywikibot.output(u"Page %s is locked?!" % page.title())

def replaceCategories(page, oldcats, newcat):
    oldtext = page.get()
    newcats = []
    newcats.append(newcat)

    for cat in page.categories():
	if not (cat.titleWithoutNamespace()==oldcats[0].titleWithoutNamespace() or cat.titleWithoutNamespace()==oldcats[1].titleWithoutNamespace()):
	    newcats.append(cat)

    newtext = wikipedia.replaceCategoryLinks (oldtext, newcats)
    comment = u'[[' + oldcats[0].title() + u']] \u2229 [[' + oldcats[1].title() + u']] (and 3 levels of subcategories) -> [[' + newcat.title() + u']]' 

    wikipedia.showDiff(oldtext, newtext)
    page.put(newtext, comment)

def add_category(article, category, comment=None, createEmptyPages=False):
    """Given an article and a category, adds the article to the category."""
    cats = article.categories(get_redirect=True)
    if not category in cats:
        cats.append(category)
        try:
            text = article.get()
        except pywikibot.NoPage:
            if createEmptyPages:
                text = ""
            else:
                raise

        text = pywikibot.replaceCategoryLinks(text, cats)
        try:
            article.put(text, comment=comment)
        except pywikibot.EditConflict:
            pywikibot.output(u"Skipping %s because of edit conflict" % article.title())

    def pages(self):
        for page in self.generator:
            try:
                wikipedia.output(u'\n>>>> %s <<<<' % page.title())
                commons = wikipedia.getSite('commons', 'commons')
                commonspage = wikipedia.Page(commons, page.title())
                try:
                    getcommons = commonspage.get(get_redirect=True)
                    if page.title() == commonspage.title():
                        oldText = page.get()
                        text = oldText

                        # for commons template
                        findTemplate=re.compile(ur'\{\{[Cc]ommonscat')
                        s = findTemplate.search(text)
                        findTemplate2=re.compile(ur'\{\{[Ss]isterlinks')
                        s2 = findTemplate2.search(text)
                        if s or s2:
                            wikipedia.output(u'** Already done.')
                        else:
                            text = wikipedia.replaceCategoryLinks(text+u'{{commons|%s}}'%commonspage.title(), page.categories())
                            if oldText != text:
                                wikipedia.showDiff(oldText, text)
                                if not self.acceptall:
                                    choice = wikipedia.inputChoice(u'Do you want to accept these changes?', ['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N')
                                    if choice == 'a':
                                        self.acceptall = True
                                if self.acceptall or choice == 'y':
                                    try:
                                        msg = wikipedia.translate(wikipedia.getSite(), comment1)
                                        page.put(text, msg)
                                    except wikipedia.EditConflict:
                                        wikipedia.output(u'Skipping %s because of edit conflict' % (page.title()))

                except wikipedia.NoPage:
                    wikipedia.output(u'Page does not exist in Commons!')

            except wikipedia.NoPage:
                wikipedia.output(u'Page %s does not exist?!' % page.title())
            except wikipedia.IsRedirectPage:
                wikipedia.output(u'Page %s is a redirect; skipping.' % page.title())
            except wikipedia.LockedPage:
                wikipedia.output(u'Page %s is locked?!' % page.title())

def categorizeImage(page, conn, cursor):
    wikipedia.output(u'Working on: %s' % page.title())
    
    templates = page.templates()
    if not u'Rijksmonument' in page.templates():
	wikipedia.output(u'Rijksmonument template not found at: %s' % page.title())
	return False

    rijksmonumentid=-1
    
    for (template, params) in page.templatesWithParams():
	if template==u'Rijksmonument':
	    if len(params)==1:
		try:
		    rijksmonumentid = int(params[0])
		except ValueError:
		    wikipedia.output(u'Unable to extract a valid id')
		break

    if (rijksmonumentid < 0 or 600000 < rijksmonumentid ):
	wikipedia.output(u'Invalid id')
	return False
		
    rijksmonumentenLijst = getList(rijksmonumentid, conn, cursor)
    if not rijksmonumentenLijst:
	return False

    oldtext = page.get()
    currentcats = page.categories()
    newcats = getCategories(rijksmonumentenLijst) 
    if newcats:
	for currentcat in currentcats:
	    if not currentcat.title()==u'Category:Rijksmonumenten':
		newcats.append(currentcat)
	# Remove dupes
	newcats = list(set(newcats))
	newtext = wikipedia.replaceCategoryLinks(oldtext, newcats)

	comment = u'Adding categories based on Rijksmonument identifier'
	wikipedia.showDiff(oldtext, newtext)
	page.put(newtext, comment)

def include(pl,checklinks=True,realinclude=True,linkterm=None):
    cl = checklinks
    if linkterm:
        actualworkingcat = catlib.Category(mysite,workingcat.title(),
                                           sortKey=linkterm)
    else:
        actualworkingcat = workingcat
    if realinclude:
        try:
            text = pl.get()
        except pywikibot.NoPage:
            pass
        except pywikibot.IsRedirectPage:
            cl = True
            pass
        else:
            cats = pl.categories()
            if not workingcat in cats:
                cats = pl.categories()
                for c in cats:
                    if c in parentcats:
                        if removeparent:
                            catlib.change_category(pl,c,actualworkingcat)
                            break
                else:
                    pl.put(pywikibot.replaceCategoryLinks(
                        text, cats + [actualworkingcat]))
    if cl:
        if checkforward:
            for page2 in pl.linkedPages():
                if needcheck(page2):
                    tocheck.append(page2)
                    checked[page2] = page2
        if checkbackward:
            for refPage in pl.getReferences():
                 if needcheck(refPage):
                    tocheck.append(refPage)
                    checked[refPage] = refPage

def main(args):
    '''
    Main loop.
    '''
    site = wikipedia.getSite(u'commons', u'commons')
    wikipedia.setSite(site)

    conn = None
    cursor = None
    (conn, cursor) = connectDatabase()

    conn2 = None
    cursor2 = None
    (conn2, cursor2) = connectDatabase2('commonswiki-p.db.toolserver.org', u'commonswiki_p')

    imageSet = getImagesToCorrect(cursor2)
    #print imageSet
    for (pageName, fileId) in imageSet:
	wikipedia.output(pageName)
	if not pageName==u'' and not fileId==u'':
	    #Get page contents
	    page = wikipedia.Page(site, pageName)
	    if page.exists():
		categories = page.categories()

		#Get metadata
		metadata = getMetadata(fileId, cursor)

		#Check if we got metadata
		if metadata:
		    #Get description
		    description = getDescription(metadata)

		    description = wikipedia.replaceCategoryLinks(description, categories, site)
		    comment= u'Fixing description of Geograph image with broken template'
		    wikipedia.output(description)
		    page.put(description, comment)

def add_category(sort_by_last_name=False, create_pages=False):
    """A robot to mass-add a category to a list of pages."""
    site = pywikibot.getSite()
    if gen:
        newcatTitle = pywikibot.input(u"Category to add (do not give namespace):")
        if not site.nocapitalize:
            newcatTitle = newcatTitle[:1].capitalize() + newcatTitle[1:]

        # set edit summary message
        editSummary = pywikibot.translate(site, msg_add) % newcatTitle

        cat_namespace = site.category_namespaces()[0]

        answer = ""
        for page in gen:
            if answer != "a":
                answer = ""

            while answer not in ("y", "n", "a"):
                answer = pywikibot.inputChoice(u"%s" % (page.aslink()), ["Yes", "No", "All"], ["y", "n", "a"], "n")
                if answer == "a":
                    confirm = pywikibot.inputChoice(
                        u"""\
This should be used if and only if you are sure that your links are correct!
Are you sure?""",
                        ["Yes", "No"],
                        ["y", "n"],
                        "n",
                    )
                    if confirm == "n":
                        answer = ""

            if answer == "y" or answer == "a":
                try:
                    text = page.get()
                except pywikibot.NoPage:
                    if create_pages:
                        pywikibot.output(u"%s doesn't exist yet. Creating." % (page.title()))
                        text = ""
                    else:
                        pywikibot.output(u"%s doesn't exist yet. Ignoring." % (page.title()))
                        continue
                except pywikibot.IsRedirectPage, arg:
                    redirTarget = pywikibot.Page(site, arg.args[0])
                    pywikibot.output(u"WARNING: %s is redirect to %s. Ignoring." % (page.title(), redirTarget.title()))
                    continue
                cats = page.categories()
                # Show the title of the page we're working on.
                # Highlight the title in purple.
                pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
                pywikibot.output(u"Current categories:")
                for cat in cats:
                    pywikibot.output(u"* %s" % cat.title())
                catpl = pywikibot.Page(site, cat_namespace + ":" + newcatTitle)
                if sort_by_last_name:
                    catpl = sorted_by_last_name(catpl, page)
                if catpl in cats:
                    pywikibot.output(u"%s is already in %s." % (page.title(), catpl.title()))
                else:
                    pywikibot.output(u"Adding %s" % catpl.aslink())
                    cats.append(catpl)
                    text = pywikibot.replaceCategoryLinks(text, cats)
                    try:
                        page.put(text, comment=editSummary)
                    except pywikibot.EditConflict:
                        pywikibot.output(u"Skipping %s because of edit conflict" % (page.title()))