Python wikipedia.setSite函数代码示例

def main():
    wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))

    bigcategory = u''
    target = u''

    generator = None
    for arg in wikipedia.handleArgs():
        if arg.startswith('-page'):
            if len(arg) == 5:
	        generator = [wikipedia.Page(wikipedia.getSite(), wikipedia.input(u'What page do you want to use?'))]
	    else:
                generator = [wikipedia.Page(wikipedia.getSite(), arg[6:])]
	elif arg.startswith('-bigcat'):
	    if len(arg) == 7:
		bigcategory = wikipedia.input(u'What category do you want to split out?')
	    else:
    		bigcategory = arg[8:]
	elif arg.startswith('-target'):
	    if len(arg) == 7:
		target = wikipedia.input(u'What category is the target category?')
	    else:
		target = arg[8:]

    if not bigcategory==u'':
	splitOutCategory(bigcategory, target)
    else:
	if not generator:
	    generator = pagegenerators.NamespaceFilterPageGenerator(pagegenerators.ReferringPageGenerator(wikipedia.Page(wikipedia.getSite(), u'Template:Intersect categories'), onlyTemplateInclusion=True), [14])
	for cat in generator:
	    intersectCategories(cat)

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')

def main():
    countrycode = u''

    # Connect database, we need that
    (conn, cursor) = connectDatabase()
    (conn2, cursor2) = connectDatabase2()

    generator = None
    genFactory = pagegenerators.GeneratorFactory()

    for arg in wikipedia.handleArgs():
        if arg.startswith('-countrycode:'):
            countrycode = arg [len('-countrycode:'):]

    lang = wikipedia.getSite().language()
    wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))
    
    if countrycode:
	if not mconfig.countries.get((countrycode, lang)):
	    wikipedia.output(u'I have no config for countrycode "%s" in language "%s"' % (countrycode, lang))
	    return False
	wikipedia.output(u'Working on countrycode "%s" in language "%s"' % (countrycode, lang))
	locateCountry(countrycode, lang, mconfig.countries.get((countrycode, lang)), conn, cursor, conn2, cursor2)
    else:
	for (countrycode, lang), countryconfig in mconfig.countries.iteritems():
            if not countryconfig.get('autoGeocode'):
                wikipedia.output(u'"%s" in language "%s" is not supported in auto geocode mode (yet).' % (countrycode, lang))
            else:
                wikipedia.output(u'Working on countrycode "%s" in language "%s"' % (countrycode, lang))
                locateCountry(countrycode, lang, countryconfig, conn, cursor, conn2, cursor2)

def main():
    '''
    The main loop
    '''
    wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))
    conn = None
    cursor = None
    (conn, cursor) = connectDatabase()

    imagerecat.initLists()
    generator = None;
    genFactory = pagegenerators.GeneratorFactory()

    mark = True

    for arg in wikipedia.handleArgs():
	if arg.startswith('-dontmark'):
	    mark = False
        elif arg.startswith('-page'):
            if len(arg) == 5:
                generator = [wikipedia.Page(wikipedia.getSite(), wikipedia.input(u'What page do you want to use?'))]
            else:
                generator = [wikipedia.Page(wikipedia.getSite(), arg[6:])]
	elif arg.startswith('-yesterday'):
	    generator = [wikipedia.Page(wikipedia.getSite(), u'Category:Media_needing_categories_as_of_' + getYesterday())]
        else:
            generator = genFactory.handleArg(arg)
    if generator:
        for page in generator:
	    if((page.namespace() == 14) and (page.title().startswith(u'Category:Media needing categories as of'))):
		wikipedia.output(u'Working on ' + page.title())
		for (image, gals, cats) in getImagesToCategorize(cursor, page.titleWithoutNamespace()):
		    categorizeImage(image, gals, imagerecat.applyAllFilters(cats))
		if (mark):
		    categoriesChecked(page.title())

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)

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 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)

def main(args):
    """
    Main loop.
    """
    workdir = u""
    textfile = u""
    records = {}

    site = wikipedia.getSite(u"commons", u"commons")
    wikipedia.setSite(site)

    if not (len(args) == 2):
        wikipedia.output(u"Too few arguments. Usage: NARA_uploader.py <directory> <textfile>")
        sys.exit()

    if os.path.isdir(args[0]):
        workdir = args[0]
    else:
        wikipedia.output(u"%s doesn't appear to be a directory. Exiting" % (args[0],))
        sys.exit()

    textfile = args[1]
    records = getRecords(textfile)
    # print records

    sourcefilenames = glob.glob(workdir + u"/*.TIF")

    for sourcefilename in sourcefilenames:
        filename = os.path.basename(sourcefilename)
        # This will give an ugly error if the id is unknown
        if not records.get(filename):
            wikipedia.output(u"Can't find %s in %s. Skipping this file." % (filename, textfile))
        elif os.path.getsize(sourcefilename) >= 1024 * 1024 * 100:
            wikipedia.output(u"%s too big. Skipping this file." % (sourcefilename,))
        else:
            fileId = records.get(filename)

            duplicates = findDuplicateImages(sourcefilename)
            if duplicates:
                wikipedia.output(u"Found duplicate image at %s" % duplicates.pop())
            else:
                # No metadata handling. We use a webtool
                description = getDescription(fileId)
                categories = u"{{Uncategorized-NARA|year=2011|month=September|day=21}}\n"
                description = description + categories

                print fileId
                title = getTitle(fileId, description)

                wikipedia.output(title)
                wikipedia.output(description)

                bot = upload.UploadRobot(
                    url=sourcefilename.decode(sys.getfilesystemencoding()),
                    description=description,
                    useFilename=title,
                    keepFilename=True,
                    verifyDescription=False,
                )
                bot.run()

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

    sourcedir=u'/mnt/user-store/OS_OpenData/1_250_000_Scale_Raster/data/'
    destinationdirjpg=u'/mnt/user-store/OS_OpenData/1_250_000_Scale_Raster/outputjpg/'
    destinationdirtif=u'/mnt/user-store/OS_OpenData/1_250_000_Scale_Raster/outputtif/'
    basefilename=u'Ordnance_Survey_1-250000_-_'
    sourcename=u'1:250 000 Scale Colour Raster'
    scale=u'250.000'
    squares = []

    for sourcefilename in glob.glob(sourcedir + u"*.tif"):
	square = sourcefilename.replace(sourcedir, u'').replace(u'.tif', u'')
	squares.append(square)

    for square in squares:
	print square
	OSlib.processSquare(square, squares, scale, sourcedir, sourcename, basefilename, u'jpg', destinationdirjpg)
	OSlib.processSquare(square, squares, scale, sourcedir, sourcename, basefilename, u'tif', destinationdirtif)
	

    '''

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('sql-s2.toolserver.org', u'u_multichill_commons_categories_p')

    conn3 = None
    cursor3 = None
    (conn3, cursor3) = connectDatabase2('commonswiki-p.db.toolserver.org', u'commonswiki_p')
    
    topics = getTopics(cursor)
    images = {}
    cats = []
    for (topic,) in topics:
	cats.extend(getCategoriesToSplit(cursor3, topic))

    outputCategoriesToSplit(cats)
    '''

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('sql-s2.toolserver.org', u'u_multichill_commons_categories_p')

    conn3 = None
    cursor3 = None
    (conn3, cursor3) = connectDatabase2('commonswiki-p.db.toolserver.org', u'commonswiki_p')
    
    topics = getTopics(cursor)
    images = {}
    for (topic,) in topics:
    	images[topic] = getImagesWithTopicCount(cursor3, topic)
    	print images[topic]

    outputStats(topics, images)
    '''

def main():
    '''
    The main loop
    '''
    wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))
    conn = None
    cursor = None
    (conn, cursor) = connectDatabase()
    
    # Get datetime
    date = datetime.utcnow().strftime('%Y%m%d%H%M')

    # Get number of uncategorized files
    uncatQuery=u"SELECT COUNT(DISTINCT(page_title)) FROM page JOIN categorylinks ON page_id=cl_from WHERE page_namespace=6 AND page_is_redirect=0 AND cl_to LIKE 'Media\_needing\_categories\_as\_of\_%'"
    uncatCount = getCount(cursor, uncatQuery)

    # Get number of files to be checked
    checkQuery=u"SELECT COUNT(DISTINCT(page_title)) FROM page JOIN categorylinks ON page_id=cl_from WHERE page_namespace=6 AND page_is_redirect=0 AND cl_to LIKE 'Media\_needing\_category\_review\_as\_of\_%'"
    checkCount = getCount(cursor, checkQuery)

    # Get total
    totalCount = int(uncatCount) + int(checkCount)

    # Update the stats page with this number
    updateStats(date, uncatCount, checkCount, totalCount)

def main():
    '''
    The main loop
    '''
    wikipedia.setSite(wikipedia.getSite(u'nl', u'wikipedia'))
    conn = None
    cursor = None
    (conn, cursor) = connectDatabase()

    items = getNumberOfItems(cursor)
    images = getNumberOfImages(cursor)
    addresses = {}
    names = {} 
    pages = list(set(items.keys() + images.keys()))
    pages.sort()

    for key in pages:
	print key
	page = wikipedia.Page(wikipedia.getSite(), key)
	text = page.get()
	addresses[key] = getNumberOfAddresses(text)
	names[key] = getNumberOfNames(text)
	#print key + u' - ' + str(addresses[key]) + u' - ' + str(names[key]) 
	
    updateStats(pages, items, addresses, names, images)

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"

def main():
    '''
    The main loop
    '''
    wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))
    conn = None
    cursor = None
    (conn, cursor) = connectDatabase()
    for templateTitle in getUncategorizedTemplates(cursor):
        tagUncategorized(templateTitle)

def main():
    '''
    The main loop
    '''
    wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))
    conn = None
    cursor = None
    (conn, cursor) = connectDatabase()
    #images = getImagesToCategorize(cursor)

    for (image, category) in getImagesToCategorize(cursor):
	categorizeImage(image, category)