Python wikipedia.showDiff函数代码示例

def sort_by_country_subcat(subcat, subject):
    print subcat
    subcat = subcat.replace('_', ' ')
    subject = subject.replace('_', ' ')
    if subcat.startswith(subject):
	temp1 = subcat[len(subject):].lstrip()
	if temp1.startswith('from'):
	    temp2 = temp1[len('from'):].lstrip()
	elif temp1.startswith('of'):
            temp2 = temp1[len('of'):].lstrip()
        elif temp1.startswith('in'):
            temp2 = temp1[len('in'):].lstrip()
	else:
	    temp2 = ''
	if temp2:
	    if temp2.startswith('the'):
		country = temp2[len('the'):].lstrip() 
	    else:
		country = temp2
	    page = wikipedia.Page(wikipedia.getSite(), 'Category:' + subcat)
	    old = u'\[\[[cC]ategory:' + subject + u' by country[^\]]*\]\]'
	    new = u'[[Category:' + subject + u' by country|' + country + u']]'
	    comment = u'Sorting [[:Category:' + subject + u' by country]]'
	    newtext = wikipedia.replaceExcept(page.get(), old, new, [])
	    wikipedia.showDiff(page.get(), newtext)
	    page.put(newtext, comment)

    def updateInterwiki (self, wikipediaPage = None, commonsPage = None):
        '''
        Update the interwiki's at commons from a wikipedia page. The bot just
        replaces the interwiki links at the commons page with the interwiki's from
        the wikipedia page. This should probably be more intelligent. We could use
        add all the interwiki's and remove duplicates. Or only remove language links
        if multiple language links to the same language exist.

        This function is disabled for the moment untill i figure out what the best
        way is to update the interwiki's.
        '''
        interwikis = {}
        comment= u''
        interwikilist = wikipediaPage.interwiki()
        interwikilist.append(wikipediaPage)

        for interwikiPage in interwikilist:
            interwikis[interwikiPage.site()]=interwikiPage
        oldtext = commonsPage.get()
        # The commonssite object doesnt work with interwiki's
        newtext = pywikibot.replaceLanguageLinks(oldtext, interwikis,
                                                 pywikibot.getSite(u'nl'))
        comment = u'Updating interwiki\'s from [[' + \
                  wikipediaPage.site().language()  + \
                  u':' + wikipediaPage.title() + u']]'

        if newtext != oldtext:
            #This doesnt seem to work. Newtext has some trailing whitespace
            pywikibot.showDiff(oldtext, newtext)
            commonsPage.put(newtext=newtext, comment=comment)

    def revert(self, item):
        predata = {
            'action': 'query',
            'titles': item['title'],
            'prop': 'revisions',
            'rvprop': 'ids|timestamp|user|content',
            'rvlimit': '2',
            'rvstart': item['timestamp'],
        }
        data = query.GetData(predata, self.site)

        if 'error' in data:
            raise RuntimeError(data['error'])

        pages = data['query'].get('pages', ())
        if not pages: return False
        page = pages.itervalues().next()
        if len(page.get('revisions', ())) != 2: return False
        rev = page['revisions'][1]

        comment = u'Reverted to revision %s by %s on %s' % (rev['revid'],
            rev['user'], rev['timestamp'])
        if self.comment: comment += ': ' + self.comment

        page = pywikibot.Page(self.site, item['title'])
        pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
                         % page.aslink(True, True))
        old = page.get()
        new = rev['*']
        pywikibot.showDiff(old, new)
        page.put(new, comment)
        return comment

def tagNowCommons(wImage, cImage, timestamp):
    site = wikipedia.getSite()
    language = site.language()
    family = site.family.name

    imagepage = wikipedia.ImagePage(wikipedia.getSite(), wImage)
    if not imagepage.exists() or imagepage.isRedirectPage():
	return

    if skips.get(family) and skips.get(family).get(language):
	localskips = skips.get(family).get(language)
    else:
	localskips = skips.get('_default')

    for template in imagepage.templates():
	title = template.replace(u'_', u' ').strip()
	if title in localskips:
	    return
    text = imagepage.get()
    oldtext = text

    text = u'{{NowCommons|File:%s|date=%s|bot=~~~}}\n' % (cImage.replace(u'_', u' '), timestamp) + text
    comment = u'File is available on Wikimedia Commons.'
    wikipedia.showDiff(oldtext, text)
    try:
	imagepage.put(text, comment)
	#print u'put'
    except wikipedia.LockedPage:
	return

    def tagNowcommons(self, imagepage, filename):
        """ Tagged the imag which has been moved to Commons for deletion. """
        if pywikibot.Page(pywikibot.getSite('commons', 'commons'),
                          u'File:' + filename).exists():
            # Get a fresh copy, force to get the page so we dont run into edit
            # conflicts
            imtxt = imagepage.get(force=True)

            # Remove the move to commons templates
            if imagepage.site().language() in moveToCommonsTemplate:
                for moveTemplate in moveToCommonsTemplate[imagepage.site().language()]:
                    imtxt = re.sub(u'(?i)\{\{' + moveTemplate +
                                   u'[^\}]*\}\}', u'', imtxt)

            # add {{NowCommons}}
            if imagepage.site().language() in nowCommonsTemplate:
                addTemplate = nowCommonsTemplate[
                    imagepage.site().language()] % filename
            else:
                addTemplate = nowCommonsTemplate['_default'] % filename

            commentText = i18n.twtranslate(
                imagepage.site(), 'commons-file-now-available',
                {'localfile': imagepage.title(withNamespace=False),
                 'commonsfile': filename})

            pywikibot.showDiff(imagepage.get(), imtxt + addTemplate)
            imagepage.put(imtxt + addTemplate, comment=commentText)

def workon(page):
    mysite = wikipedia.getSite()
    try:
        text = page.get()
    except wikipedia.IsRedirectPage:
        wikipedia.output(u'%s is a redirect page. Skipping' % page.aslink())
        return
    except wikipedia.NoPage:
        wikipedia.output(u'%s does not exist. Skipping' % page.aslink())
        return
    wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
    links = page.linkedPages()
    if len(links) > 0:
        wikipedia.getall(mysite,links)
    else:
        wikipedia.output('Nothing left to do.')
        return
    
    for page2 in links:
        try:
            target = page2.getRedirectTarget()
        except (wikipedia.Error,wikipedia.SectionError):
            continue
        text = treat(text, page2, target)
    if text != page.get():
        comment = wikipedia.translate(mysite, msg)
        wikipedia.showDiff(page.get() ,text)
        try:
            page.put(text, comment)
        except (wikipedia.Error):
            wikipedia.output('Error: unable to put %s' % page.aslink())

def process_article(page, tag):
		EditMsg = "Robot: Tagging {{Film|%s}}" %tag
		wikipedia.setAction(EditMsg)
		try:
			wikitext = page.get()
		except wikipedia.NoPage:
			page.put("{{Film|%s}}" %tag)
			return
		except wikipedia.IsRedirectPage:
			return
		if re.search(tag,wikitext,re.I):
			print "Skipping " + str(page)
			return
		# Fix Casing (Reduces the number of possible expressions)
		wikitext = re.compile(r'\{\{\s*(template:|)film', re.IGNORECASE).sub(r'{{Film', wikitext)
		state0 = wikitext
 
		# Add tf parameter
		wikitext = re.compile(r'\{\{\s*film(.*?)\}\}', re.IGNORECASE).sub(r'{{Film\1|%s}}' %tag, wikitext)
 
		wikipedia.showDiff(state0, wikitext)
 
		if (wikitext != state0):
			try:
				print 'Going to edit %s' %str(page)
				wikipedia.output(u'WRITE:	Adding %s bytes.' % str(len(wikitext)-len(state0)))
				page.put(wikitext)	
			except KeyboardInterrupt:
				sys.exit()

def fes(pagina):
    pag = wikipedia.Page(wikipedia.getSite('ca'), pagina) # creem un objecte page on poder treballar
    noutext = text = pag.get() # obtenuim el text
    noutext = re.sub(u"\| ?pàgines ?= p\.?", "|pàgines=", text)
    wikipedia.showDiff(text, noutext)
    if raw_input(u"Vols penjar la pàgina [y/n]?") == "y":
        pag.put(noutext, comment=u"Robot fent canvis per la {{tl|ref-llibre}}")

    def tagNowcommons(self, imagepage, filename):
        '''
        Tagged the imag which has been moved to Commons for deletion.
        '''
        if pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:' + filename).exists():
            #Get a fresh copy, force to get the page so we dont run into edit conflicts
            imtxt=imagepage.get(force=True)

            #Remove the move to commons templates
            if imagepage.site().language() in moveToCommonsTemplate:
                for moveTemplate in moveToCommonsTemplate[imagepage.site().language()]:
                    imtxt = re.sub(u'(?i)\{\{' + moveTemplate + u'[^\}]*\}\}', u'', imtxt)

            #add {{NowCommons}}
            if imagepage.site().language() in nowCommonsTemplate:
                addTemplate = nowCommonsTemplate[imagepage.site().language()] % filename
            else:
                addTemplate = nowCommonsTemplate['_default'] % filename

            if imagepage.site().language() in nowCommonsMessage:
                commentText = nowCommonsMessage[imagepage.site().language()]
            else:
                commentText = nowCommonsMessage['_default']

            pywikibot.showDiff(imagepage.get(), imtxt + addTemplate)
            imagepage.put(imtxt + addTemplate, comment = commentText)

def addCoords(sourceWiki, lang, article, lat, lon, region, type, dim):
    '''
    Add the coordinates to article.
    '''

    if (article and lang and type):
        coordTemplate = 'Coordinate'
        site = wikipedia.getSite(lang, 'wikipedia')

        page = wikipedia.Page(site, article)
        try:
            text = page.get()
        except wikipedia.NoPage: # First except, prevent empty pages
            logging.warning('Page empty: %s', article)
            return False
        except wikipedia.IsRedirectPage: # second except, prevent redirect
            logging.warning('Page is redirect: %s', article)
            wikipedia.output(u'%s is a redirect!' % article)
            return False
        except wikipedia.Error: # third exception, take the problem and print
            logging.warning('Some error: %s', article)
            wikipedia.output(u"Some error, skipping..")
            return False       
    
        if coordTemplate in page.templates():
            logging.info('Already has Coordinate template: %s', article)
            return False

        if 'Linn' in page.templates():
            logging.info('Linn template without coords: %s', article)
            return False
            
        newtext = text
        replCount = 1
        coordText = u'{{Coordinate |NS=%s |EW=%s |type=%s |region=%s' % (lat, lon, type, region)
        if (dim):
            coordText += u' |dim=%s' % ( int(dim),)
        coordText += '}}'
        localCatName = wikipedia.getSite().namespace(WP_CATEGORY_NS)
        catStart = r'\[\[(' + localCatName + '|Category):'
        catStartPlain = u'[[' + localCatName + ':'
        replacementText = u''
        replacementText = coordText + '\n\n' + catStartPlain
    
        # insert coordinate template before categories
        newtext = re.sub(catStart, replacementText, newtext, replCount, flags=re.IGNORECASE)

        if text != newtext:
            logging.info('Adding coords to: %s', article)
            comment = u'lisan artikli koordinaadid %s.wikist' % (sourceWiki)
            wikipedia.showDiff(text, newtext)
            modPage = wikipedia.input(u'Modify page: %s ([y]/n) ?' % (article) )
            if (modPage.lower == 'y' or modPage == ''):
                page.put(newtext, comment)
            return True
        else:
            logging.info('Nothing to change: %s', article)
            return False
    else:
        return False

    def tagNowcommons(self, imagepage, filename):
        """
        Tagged the imag which has been moved to Commons for deletion.
        """
        if pywikibot.Page(pywikibot.getSite("commons", "commons"), u"File:" + filename).exists():
            # Get a fresh copy, force to get the page so we dont run into edit conflicts
            imtxt = imagepage.get(force=True)

            # Remove the move to commons templates
            if imagepage.site().language() in moveToCommonsTemplate:
                for moveTemplate in moveToCommonsTemplate[imagepage.site().language()]:
                    imtxt = re.sub(u"(?i)\{\{" + moveTemplate + u"[^\}]*\}\}", u"", imtxt)

            # add {{NowCommons}}
            if imagepage.site().language() in nowCommonsTemplate:
                addTemplate = nowCommonsTemplate[imagepage.site().language()] % filename
            else:
                addTemplate = nowCommonsTemplate["_default"] % filename

            if imagepage.site().language() in nowCommonsMessage:
                commentText = nowCommonsMessage[imagepage.site().language()]
            else:
                commentText = nowCommonsMessage["_default"]

            pywikibot.showDiff(imagepage.get(), imtxt + addTemplate)
            imagepage.put(imtxt + addTemplate, comment=commentText)

def sort_by_country_subcat(subcat, subject):
    print subcat
    subcat = subcat.replace("_", " ")
    subject = subject.replace("_", " ")
    if subcat.startswith(subject):
        temp1 = subcat[len(subject) :].lstrip()
        if temp1.startswith("from"):
            temp2 = temp1[len("from") :].lstrip()
        elif temp1.startswith("of"):
            temp2 = temp1[len("of") :].lstrip()
        elif temp1.startswith("in"):
            temp2 = temp1[len("in") :].lstrip()
        else:
            temp2 = ""
        if temp2:
            if temp2.startswith("the"):
                country = temp2[len("the") :].lstrip()
            else:
                country = temp2
            page = wikipedia.Page(wikipedia.getSite(), "Category:" + subcat)
            old = u"\[\[[cC]ategory:" + subject + u" by country[^\]]*\]\]"
            new = u"[[Category:" + subject + u" by country|" + country + u"]]"
            comment = u"Sorting [[:Category:" + subject + u" by country]]"
            newtext = wikipedia.replaceExcept(page.get(), old, new, [])
            wikipedia.showDiff(page.get(), newtext)
            page.put(newtext, comment)

    def revert(self, item):
        predata = {
            "action": "query",
            "titles": item["title"],
            "prop": "revisions",
            "rvprop": "ids|timestamp|user|content",
            "rvlimit": "2",
            "rvstart": item["timestamp"],
        }
        data = query.GetData(predata, self.site)

        if "error" in data:
            raise RuntimeError(data["error"])

        pages = data["query"].get("pages", ())
        if not pages:
            return False
        page = pages.itervalues().next()
        if len(page.get("revisions", ())) != 2:
            return False
        rev = page["revisions"][1]

        comment = u"Reverted to revision %s by %s on %s" % (rev["revid"], rev["user"], rev["timestamp"])
        if self.comment:
            comment += ": " + self.comment

        page = pywikibot.Page(self.site, item["title"])
        pywikibot.output(
            u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title(asLink=True, forceInterwiki=True, textlink=True)
        )
        old = page.get()
        new = rev["*"]
        pywikibot.showDiff(old, new)
        page.put(new, comment)
        return comment

def convertList(page):
    '''
    Convert a list of NRHP entries. Both headers and items will be converted.
    '''
    wikipedia.output(u'Working on %s' % page.title())
    
    text = page.get()
    try:
        newtext = convertHeaders(page, text)
        newtext = convertItems(page, newtext)
    except TypeError or AttributeError:
        wikipedia.output(u'One of the regexes failed at %s, skipping this page' % (page.title,))
        traceback.print_exc(file=sys.stdout)
        time.sleep(10)
        return u'Failed'

    if not text==newtext:
        wikipedia.showDiff(text, newtext)
        
        comment = u'Converting list to use [[Template:NRHP header]] and [[Template:NRHP row]]'

        #choice = wikipedia.inputChoice(u'Do you want to accept these changes?', ['Yes', 'No'], ['y', 'n'], 'n')
        choice = 'y'

        if choice == 'y':
            #DEBUG
            page.put(newtext, comment)
            return u'Success'
            #wikipedia.output(newtext)

    return u'Unchanged'

    def save(self, page, newText):
        """
        Saves the page to the wiki, if the user accepts the changes made.
        """
        pywikibot.showDiff(page.get(), newText)
        if not self.always:
            choice = pywikibot.inputChoice(
                u'Do you want to accept these changes?',
                ['Yes', 'No', 'Always yes'], ['y', 'N', 'a'], 'Y')
            if choice == 'n':
                return
            elif choice == 'a':
                self.always = True

        if self.always:
            try:
                page.put(newText)
            except pywikibot.EditConflict:
                pywikibot.output(u'Skipping %s because of edit conflict'
                                 % (page.title(),))
            except pywikibot.SpamfilterError, e:
                pywikibot.output(
                    u'Cannot change %s because of blacklist entry %s'
                    % (page.title(), e.url))
            except pywikibot.LockedPage:
                pywikibot.output(u'Skipping %s (locked page)' % (page.title(),))