User:John Bot III/Code

" in on_commons_text:

wikipedia.output(u"But, the image doesn't exist on your project! Skip...")

# Problems? Yes! We have to skip the check part for that image!

# Because it's on commons but someone has added something on your project.

return False

elif 'stemma' in image.lower() and self.site.lang == 'it':

wikipedia.output(u'%s has "stemma" inside, means that it\'s ok.' % image)

return True # Problems? No, it's only not on commons but the image needs a check

else:

repme = "\n*:Image:%s is also on Commons: commons:Image:%s"

self.report_image(self.image, self.rep_page, self.com, repme)

# Problems? No, return True

return True

else:

# Problems? No, return True

return True

def report_image(self, image, rep_page = None, com = None, rep_text = None):

if rep_page == None:

rep_page = self.rep_page

if com == None:

com = self.com

if rep_text == None:

rep_text = self.rep_text

another_page = wikipedia.Page(self.site, rep_page)

if another_page.exists():

text_get = another_page.get()

else:

text_get = str()

if len(text_get) >= self.logFulNumber:

raise LogIsFull("The log page (%s) is full! Please delete the old images reported." % another_page.title())

pos = 0

# The talk page includes "_" between the two names, in this way i replace them to " "

regex = image

n = re.compile(regex, re.UNICODE)

y = n.search(text_get, pos)

if y == None:

# Adding the log :)

if "\'\'\'Commons\'\'\'" in rep_text:

rep_text = rep_text % (image, image)

else:

rep_text = rep_text % image

another_page.put(text_get + rep_text, comment = com, minorEdit = False)

wikipedia.output(u"...Reported...")

reported = True

else:

pos = y.end()

wikipedia.output(u"%s is already in the report page." % image)

reported = False

return reported

def takesettings(self):

pos = 0

if self.settings == None: lista = None

else:

x = wikipedia.Page(self.site, self.settings)

lista = list()

try:

testo = x.get()

rxp = "<------- ------->\n\*[Nn]ame ?= ?['\"](.*?)['\"]\n\*([Ff]ind|[Ff]indonly)=(.*?)\n\*[Ii]magechanges=(.*?)\n\*[Ss]ummary=['\"](.*?)['\"]\n\*[Hh]ead=['\"](.*?)['\"]\n\*[Tt]ext ?= ?['\"](.*?)['\"]\n\*[Mm]ex ?= ?['\"]?(.*?)['\"]?$"

r = re.compile(rxp, re.UNICODE|re.M)

number = 1

while 1:

m = r.search(testo, pos)

if m == None:

if lista == list():

wikipedia.output(u"You've set wrongly your settings, please take a look to the relative page. (run without them)")

lista = None

else:

break

else:

pos = m.end()

name = str(m.group(1))

find_tipe = str(m.group(2))

find = str(m.group(3))

imagechanges = str(m.group(4))

summary = str(m.group(5))

head = str(m.group(6))

text = str(m.group(7))

mexcatched = str(m.group(8))

tupla = [number, name, find_tipe, find, imagechanges, summary, head, text, mexcatched]

lista += [tupla]

number += 1

except wikipedia.NoPage:

wikipedia.output(u"The settings' page doesn't exist!")

lista = None

return lista

def load(self, raw):

list_loaded = list()

pos = 0

load_2 = True

# I search with a regex how many user have not the talk page

# and i put them in a list (i find it more easy and secure)

while 1:

regl = "(\"|\')(.*?)(\"|\')(, |\])"

pl = re.compile(regl, re.UNICODE)

xl = pl.search(raw, pos)

if xl == None:

if len(list_loaded) >= 1:

return list_loaded

break

elif len(done) == 0:

break

pos = xl.end()

word = xl.group(2)

if word not in list_loaded:

list_loaded.append(word)

1. I've seen that the report class before (the main) was to long to be called so,
2. here there is a function that has all the settings, so i can call it once ^__^

def report(newtext, image, notification, head, notification2 = None, unver = True, commx = None, bot_list = bot_list):

botolist = wikipedia.translate(wikipedia.getSite(), bot_list)

while 1:

run = main(site = wikipedia.getSite())

secondrun = run.general(newtext, image, notification, head, botolist)

if unver == True:

try:

resPutMex = run.put_mex()

except wikipedia.NoPage:

wikipedia.output(u"The page has been deleted! Skip!")

break

except wikipedia.EditConflict:

wikipedia.output(u"Edit conflict! Skip!")

break

except wikipedia.LockedPage:

wikipedia.output(u"Page Locked. Skip!")

break

else:

if resPutMex == False:

break

else:

try:

resPutMex = run.put_mex(False)

except wikipedia.NoPage:

wikipedia.output(u"The page has been deleted!")

break

except wikipedia.EditConflict:

wikipedia.output(u"Edit conflict! Skip!")

break

except wikipedia.LockedPage:

wikipedia.output(u"Page Locked. Skip!")

break

else:

if resPutMex == False:

break

try:

run.put_talk(notification, head, notification2, commx)

except wikipedia.EditConflict:

wikipedia.output(u"Edit Conflict! Retrying...")

try:

run.put_talk(notification, head, notification2, commx)

except:

wikipedia.output(u"Another error... skipping the user..")

break

else:

break

def checkbot():

# Command line configurable parameters

repeat = True # Restart after having check all the images?

limit = 80 # How many images check?

time_sleep = 30 # How many time sleep after the check?

skip_number = 0 # How many images to skip before checking?

wait_number = 0 # How many time sleep before the check?

commonsActive = False # Check if on commons there's an image with the same name?

normal = False # Check the new images or use another generator?

urlUsed = False # Use the url-related function instead of the new-pages generator

regexGen = False # Use the regex generator

untagged = False # Use the untagged generator

skip_list = list() # Inizialize the skip list used below

# Here below there are the parameters.

for arg in wikipedia.handleArgs():

if arg.startswith('-limit'):

if len(arg) == 7:

limit = int(wikipedia.input(u'How many images do you want to check?'))

else:

limit = int(arg[7:])

if arg.startswith('-time'):

if len(arg) == 5:

time_sleep = int(wikipedia.input(u'How many seconds do you want runs to be apart?'))

else:

time_sleep = int(arg[6:])

elif arg == '-break':

repeat = False

elif arg == '-commons':

commonsActive = True

elif arg.startswith('-skip'):

if len(arg) == 5:

skip = True

skip_number = int(wikipedia.input(u'How many images do you want to skip?'))

elif len(arg) > 5:

skip = True

skip_number = int(arg[6:])

elif arg.startswith('-wait'):

if len(arg) == 5:

wait = True

wait_number = int(wikipedia.input(u'How many time do you want to wait before checking the images?'))

elif len(arg) > 5:

wait = True

wait_number = int(arg[6:])

elif arg.startswith('-start'):

if len(arg) == 6:

firstPageTitle = str(wikipedia.input(u'From witch page do you want to start?'))

elif len(arg) > 6:

firstPageTitle = str(arg[7:])

generator = wikipedia.getSite().allpages(start='Image:%s' % firstPageTitle)

repeat = False

elif arg.startswith('-page'):

if len(arg) == 5:

regexPageName = str(wikipedia.input(u'Which page do you want to use for the regex?'))

elif len(arg) > 5:

regexPageName = str(arg[6:])

repeat = False

regexGen = True

elif arg.startswith('-url'):

if len(arg) == 4:

regexPageUrl = str(wikipedia.input(u'Which url do you want to use for the regex?'))

elif len(arg) > 4:

regexPageUrl = str(arg[5:])

urlUsed = True

repeat = False

regexGen = True

elif arg.startswith('-regex'):

if len(arg) == 6:

regexpToUse = str(wikipedia.input(u'Which regex do you want to use?'))

elif len(arg) > 6:

regexpToUse = str(arg[7:])

generator = 'regex'

repeat = False

elif arg.startswith('-cat'):

if len(arg) == 4:

catName = str(wikipedia.input(u'In which category do I work?'))

elif len(arg) > 4:

catName = str(arg[5:])

catSelected = catlib.Category(wikipedia.getSite(), 'Category:%s' % catName)

generator = pagegenerators.CategorizedPageGenerator(catSelected)

repeat = False

elif arg.startswith('-untagged'):

untagged = True

if len(arg) == 9:

projectUntagged = str(wikipedia.input(u'In which project should I work?'))

elif len(arg) > 9:

projectUntagged = str(arg[10:])

# Understand if the generator it's the default or not.

try:

generator

except NameError:

normal = True

# Define the site.

site = wikipedia.getSite()

# Block of text to translate the parameters set above.

image_n = site.image_namespace()

image_namespace = "%s:" % image_n # Example: "User_talk:"

if untagged == True:

unvertext = wikipedia.translate(site, n2_txt)

else:

unvertext = wikipedia.translate(site, n_txt)

di = wikipedia.translate(site, delete_immediately)

dih = wikipedia.translate(site, delete_immediately_head)

din = wikipedia.translate(site, delete_immediately_notification)

nh = wikipedia.translate(site, nothing_head)

nn = wikipedia.translate(site, nothing_notification)

dels = wikipedia.translate(site, del_comm)

smwl = wikipedia.translate(site, second_message_without_license)

TextFind = wikipedia.translate(site, txt_find)

hiddentemplate = wikipedia.translate(site, HiddenTemplate)

# If there's an hidden template, change the used

HiddenTN = wikipedia.translate(site, HiddenTemplateNotification)

# A template as {{en is not a license! Adding also them in the whitelist template...

for langK in wikipedia.Family('wikipedia').langs.keys():

hiddentemplate.append('%s' % langK)

# If the images to skip are 0, set the skip variable to False (the same for the wait time)

if skip_number == 0:

skip = False

if wait_number == 0:

wait = False

# nothing = Defining an empty image description

nothing = ['', ' ', ' ', ' ', '\n', '\n ', '\n ', '\n\n', '\n \n', ' \n', ' \n ', ' \n \n']

# something = Minimal requirements for an image description.

# If this fits, no tagging will take place (if there aren't other issues)

# MIT license is ok on italian wikipedia, let also this here

something = ['{{', "MIT license"] # Don't put "}}" here, please. Useless and can give problems.

# Unused file extensions. Does not contain PDF.

notallowed = ("xcf", "xls", "sxw", "sxi", "sxc", "sxd")

# A little block-statement to ensure that the bot will not start with en-parameters

if site.lang not in project_inserted:

wikipedia.output(u"Your project is not supported by this script. You have to edit the script and add it!")

wikipedia.stopme()

# Some formatting for delete immediately template

di = '\n%s' % di

dels = dels % di

# Reading the log of the new images if another generator is not given.

if normal == True:

if limit == 1:

wikipedia.output(u"Retrieving the latest file for checking...")

else:

wikipedia.output(u"Retrieving the latest %d files for checking..." % limit)

# Main Loop

while 1:

# Defing the Main Class.

mainClass = main(site)

# Untagged is True? Let's take that generator

if untagged == True:

generator = mainClass.untaggedGenerator(projectUntagged, limit)

normal = False # Ensure that normal is False

# Normal True? Take the default generator

if normal == True:

generator = pagegenerators.NewimagesPageGenerator(number = limit, site = site)

# if urlUsed and regexGen, get the source for the generator

if urlUsed == True and regexGen == True:

textRegex = pagetext(regexPageUrl)

# Not an url but a wiki page as "source" for the regex

elif regexGen == True:

pageRegex = wikipedia.Page(site, regexPageName)

try:

textRegex = pageRegex.get()

except wikipedia.NoPage:

wikipedia.output(u"%s doesn't exist!" % page.title())

textRegex = '' # No source, so the bot will quit later.

# If generator is the regex' one, use your own Generator using an url or page and a regex.

if generator == 'regex' and regexGen == True:

generator = mainClass.regexGenerator(regexpToUse, textRegex)

# Ok, We (should) have a generator, so let's go on.

try:

# Take the additional settings for the Project

tupla_written = mainClass.takesettings()

except wikipedia.Error:

# Error? Settings = None

wikipedia.output(u'Problems with loading the settigs, run without them.')

tupla_written = None

some_problem = False

# Ensure that if the list given is empty it will be converted to "None"

# (but it should be already done in the takesettings() function)

if tupla_written == []: tupla_written = None

# Real-Time page loaded

if tupla_written != None: wikipedia.output(u'\t >> Loaded the real-time page... <<')

# No settings found, No problem, continue.

else: wikipedia.output(u'\t >> No additional settings found! <<')

# Not the main, but the most important loop.

for image in generator:

# If I don't inizialize the generator, wait part and skip part are useless

if wait:

printWithTimeZone(u'Waiting %s seconds before checking the images,' % wait_number)

# Let's sleep...

time.sleep(wait_number)

# Never sleep again (we are in a loop)

wait = False

# If the generator returns something that is not an image, simply skip it.

if normal == False and regexGen == False:

if image_namespace.lower() not in image.title().lower() and \

'image:' not in image.title().lower():

wikipedia.output(u'%s seems not an image, skip it...' % image.title())

continue

imageName = image.title().split(image_namespace)[1] # Deleting the namespace (useless here)

# Skip block

if skip == True:

# If the images to skip are more the images to check, make them the same number

if skip_number > limit: skip_number = limit

# Print a starting message only if no images has been skipped

if skip_list == []:

if skip_number == 1:

wikipedia.output(u'Skipping the first image:\n')

else:

wikipedia.output(u'Skipping the first %s images:\n' % skip_number)

# If we still have pages to skip:

if len(skip_list) < skip_number:

wikipedia.output(u'Skipping %s...' % imageName)

skip_list.append(imageName)

if skip_number == 1:

wikipedia.output('')

skip = False

continue

else:

wikipedia.output('') # Print a blank line.

skip = False

elif skip_list == []: # Skip must be false if we are here but

# the user has set 0 as images to skip

wikipedia.output(u'\t\t>> No images to skip...<<')

skip_list.append('skip = Off') # Only to print it once

# Check on commons if there's already an image with the same name

if commonsActive == True:

response = mainClass.checkImage(imageName)

if response == False:

continue

parentesi = False # parentesi are these in italian: { ( ) } []

delete = False

tagged = False

extension = imageName.split('.')[-1] # get the extension from the image's name

# Page => ImagePage

p = wikipedia.ImagePage(site, image.title())

# Get the text in the image (called g)

try:

g = p.get()

except wikipedia.NoPage:

wikipedia.output(u"Skipping %s because it has been deleted." % imageName)

continue

except wikipedia.IsRedirectPage:

wikipedia.output(u"The file description for %s is a redirect?!" % imageName )

continue

# Is the image already tagged? If yes, no need to double-check, skip

for i in TextFind:

# If there are {{ use regex, otherwise no (if there's not the {{ may not be a template

# and the regex will be wrong)

if '{{' in i:

regexP = re.compile('\{\{(?:template|)%s ?(?:\||\n|\}) ?' % i.split('{{')[1].replace(' ', '[ _]'), re.I)

result = regexP.findall(g)

if result != []:

tagged = True

elif i.lower() in g:

tagged = True

# Deleting the useless template from the description (before adding something

# in the image the original text will be reloaded, don't worry).

hiddenTemplateFound = False

for l in hiddentemplate:

if tagged == False:

res = re.findall(r'\{\{(?:[Tt]emplate:|)%s(?: \n|\||\n|\})' % l.lower(), g.lower())

if res != []:

wikipedia.output(u'\03{yellow}A white template found, skipping the template...\03{default}')

if l != '' and l != ' ': # Check that l is not nothing or a space

# Deleting! (replace the template with nothing)

g = g.lower().replace('{{%s' % l, '')

hiddenTemplateFound = True

for a_word in something: # something is the array with {{, MIT License and so on.

if a_word in g:

# There's a template, probably a license (or I hope so)

parentesi = True

# Is the extension allowed? (is it an image or f.e. a .xls file?)

for parl in notallowed:

if parl.lower() in extension.lower():

delete = True

some_problem = False # If it has "some_problem" it must check

# the additional settings.

# if tupla_writte, use addictional settings

if tupla_written != None:

# In every tupla there's a setting configuration

for tupla in tupla_written:

name = tupla[1]

find_tipe = tupla[2]

find = tupla[3]

find_list = mainClass.load(find)

imagechanges = tupla[4]

if imagechanges.lower() == 'false':

imagestatus = False

elif imagechanges.lower() == 'true':

imagestatus = True

else:

wikipedia.output(u"Error! Imagechanges set wrongly!")

tupla_written = None

break

summary = tupla[5]

head_2 = tupla[6]

text = tupla[7]

text = text % imageName

mexCatched = tupla[8]

wikipedia.setAction(summary)

for k in find_list:

if find_tipe.lower() == 'findonly':

if k.lower() == g.lower():

some_problem = True

text_used = text

head_used = head_2

imagestatus_used = imagestatus

name_used = name

summary_used = summary

mex_used = mexCatched

break

elif find_tipe.lower() == 'find':

if k.lower() in g.lower():

some_problem = True

text_used = text

head_used = head_2

imagestatus_used = imagestatus

name_used = name

summary_used = summary

mex_used = mexCatched

continue

# If the image exists (maybe it has been deleting during the oder

# checking parts or something, who knows? ;-))

if p.exists():

# Here begins the check block.

if tagged == True:

# Tagged? Yes, skip.

printWithTimeZone(u'\03{yellow}%s is already tagged...\03{default}' % imageName)

continue

if some_problem == True:

if mex_used in g:

wikipedia.output(u'Image already fixed. Skip.')

continue

wikipedia.output(u"The image description for %s contains %s..." % (imageName, name_used))

if mex_used.lower() == 'default':

mex_used = unvertext

if imagestatus_used == False:

reported = mainClass.report_image(imageName)

else:

reported = True

if reported == True:

#if imagestatus_used == True:

report(mex_used, imageName, text_used, "\n%s\n" % head_used, None, imagestatus_used, summary_used)

else:

wikipedia.output(u"Skipping the image...")

some_problem = False

continue

elif parentesi == True:

printWithTimeZone(u"\03{green}%s seems ok,\03{default}" % imageName)

# It works also without this... but i want only to be sure ^^

parentesi = False

continue

elif delete == True:

wikipedia.output(u"%s is not a file!" % imageName)

# Modify summary text

wikipedia.setAction(dels)

canctext = di % extension

notification = din % imageName

head = dih

report(canctext, imageName, notification, head)

delete = False

continue

elif g in nothing:

wikipedia.output(u"\03{red}The image description for %s does not contain a license template!\03{default}" % imageName)

if hiddenTemplateFound and HiddenTN != None and HiddenTN != '' and HiddenTN != ' ':

notification = HiddenTN % imageName

else:

notification = nn % imageName

head = nh

report(unvertext, imageName, notification, head, smwl)

continue

else:

wikipedia.output(u"\03{red}%s has only text and not the specific license...\03{default}" % imageName)

if hiddenTemplateFound and HiddenTN != None and HiddenTN != '' and HiddenTN != ' ':

notification = HiddenTN % imageName

else:

notification = nn % imageName

head = nh

report(unvertext, imageName, notification, head, smwl)

continue

# A little block to perform the repeat or to break.

if repeat == True:

printWithTimeZone(u"\03{lightblue}Waiting for %s seconds,\03{default}" % time_sleep)

time.sleep(time_sleep)

elif repeat == False:

wikipedia.output(u"\t\t\t>> STOP! <<")

return True # Exit

1. Here there is the main loop. I'll take all the (name of the) images and then i'll check them.

if __name__ == "__main__":

try:

try:

#cyclec = 1

checkbot()

except wikipedia.BadTitle:

wikipedia.output(u"Wikidown or server's problem, quit")

wikipedia.stopme()

finally:

wikipedia.stopme()