def makeList(self):
self.site = pywikibot.Site()
self.cat = pywikibot.Category(self.site, 'Category:Nuclear power')
self.gen = pagegenerators.CategorizedPageGenerator(self.cat)
self.err = False
someList = []
for page in self.gen:
someList.append(page)
self.cat = pywikibot.Category(self.site, 'Category:Nuclear technology')
self.gen = pagegenerators.CategorizedPageGenerator(self.cat)
for page in self.gen:
someList.append(page)
return someList
def getCategory(cat):
tempDict = []
category = pywikibot.Category(site, cat)
if cat == 'Kategoria:Szablony odmiany':
categoryGen = pagegenerators.CategorizedPageGenerator(category, recurse=1)
else:
categoryGen = pagegenerators.CategorizedPageGenerator(category)
for template in categoryGen:
if template.namespace() == 'Template:':
if cat != 'Kategoria:Szablony odmiany':
tempDict.append('{{%s}}' % template.title(withNamespace=False))
else:
tempDict.append('%s' % template.title(withNamespace=False))
return tempDict
def result():
if request.method == 'POST':
catname = 'Catégorie:Portail:' + request.form[
'portal'] + '/Articles liés'
wikisite = pywikibot.Site('fr', u'wikipedia')
wikicat = pywikibot.Category(wikisite, catname)
pages = pagegenerators.CategorizedPageGenerator(wikicat, recurse=False)
listArticles = []
for page in pages:
title = page.title()
print(title)
# On recherche le contenu du modèle Portail
paramscount = getTemplateContentCount('Portail', page)
# Si le modèle n'a qu'un seul paramètre, on l'ajoute à la liste
if paramscount == 1:
listArticles.append(title)
print("compteur : " + str(len(listArticles)))
message = "Recherche récursive d'articles à un seul portail dans la Catégorie:" + catname + " : "
message = message + str(len(listArticles)) + " article(s) concerné(s)"
return render_template("result.html",
message=message,
articles=listArticles)
def main(site, Wikiproject, Category, Threshold):
cat = pywikibot.Category(site, Category)
gen = pagegenerators.CategorizedPageGenerator(cat)
redlinks = {}
for page in gen:
article = page.toggleTalkPage()
linkgen = article.linkedPages()
for link in linkgen:
if link.exists() != True:
if link.title() in redlinks:
redlinks[link.title()] = redlinks[link.title()] + 1
else:
redlinks[link.title()] = 1
# Writing output to page
listpage = pywikibot.Page(
site, 'User:ProjectRequestedPagesBot/Most Requested ' + Wikiproject +
' pages')
entries = len(redlinks)
if entries < 1:
listpage.put('No redlinks found',
summary='No redlinks found',
minorEdit=False)
else:
text = createPage(redlinks, entries, Threshold)
listpage.put(text,
summary='Adding the ' + entries +
' most requested articles in the ' + Wikiproject +
' scope',
minorEdit=False)
print text
def get_authors_list():
authors = []
category = pywikibot.Category(site, 'Categoria:Autori')
gen = pagegenerators.CategorizedPageGenerator(category)
for page in pagegenerators.PreloadingGenerator(gen):
authors.append(page.title().replace('Autore:', ''))
return authors
def main(*args):
site = pywikibot.Site(u'en', u'wikipedia')
repo = site.data_repository() # this is a DataSite object
site.login()
cat = pywikibot.Category(site, 'Category:Articles with short description')
gen = pagegenerators.CategorizedPageGenerator(cat)
f = open('WD.txt', 'w+')
blacklist = ['16th Brigade (Australia)']
for page in gen:
if page.title() in blacklist:
continue
try:
item = pywikibot.ItemPage.fromPage(
page) # this can be used for any page object
item.get()
except:
f.write("%s\n" % page.title())
continue
try:
if not item.descriptions['en']:
print(page.title())
addDesc(page, item)
except KeyError:
print(page.title())
addDesc(page, item)
f.close()
async def download_category(category, search_depth, limit_number_of_articles,
output_path):
"""Creates an article generator based on a specific category and iterates over it to write article.
Parameters
----------
category : Category
Name of the category
search_depth: int
Depth of search
limit_number_of_articles: int
Limits the number of total articles
output_path: str
Output folder
"""
logger.info("Downloading: " + category.title())
category_title = category.title().replace(":", "_")
generated_pages = pagegenerators.CategorizedPageGenerator(
category, recurse=search_depth, total=limit_number_of_articles)
article_idx = 1
for page in tqdm(generated_pages):
text = page.text
await write_to_file(text, category_title, article_idx, output_path)
article_idx = article_idx + 1
def main():
"""Main loop. Get a generator and options. Work on all images in the generator."""
generator = None
onlyFilter = False
onlyUncat = False
# Process global args and prepare generator args parser
local_args = pywikibot.handleArgs()
genFactory = pagegenerators.GeneratorFactory()
global search_wikis
global hint_wiki
for arg in local_args:
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:
site = pywikibot.Site(u'commons', u'commons')
generator = pagegenerators.CategorizedPageGenerator(pywikibot.Category(
site, u'Category:Media needing categories'),
recurse=True)
initLists()
categorizeImages(generator, onlyFilter, onlyUncat)
pywikibot.output(u'All done')
def files_to_check(start: Optional[str] = None) -> pywikibot.page.BasePage:
"""Iterate list of files needing review from Commons"""
category = pywikibot.Category(site, "Category:INaturalist review needed")
for page in pagegenerators.CategorizedPageGenerator(category,
namespaces=6,
start=start):
yield page
def main():
cat = pywikibot.Category(swwsite, "Categoria:Páginas sendo editadas")
gen = pagegenerators.CategorizedPageGenerator(cat, recurse=False)
dataLimite = 60 * 60 * 24 * 30 * 3
for page in gen:
nome = page.title()
if (nome == "Predefinição:Emuso/preload"):
continue
pywikibot.output(u">>> \03{lightpurple}%s\03{default} <<<" %
page.title())
historico = page.revisions(reverse=True, content=True)
jaAchei = False
retirando = False
for hist in historico:
dataAki = str(hist.timestamp).split("T")[0]
dataUTC = time.mktime(
datetime.datetime.strptime(dataAki, "%Y-%m-%d").timetuple())
dataAgora = time.time()
dataDif = int(dataAgora) - int(dataUTC)
textoAki = hist.text
textoAkiL = textoAki.lower()
if (textoAkiL.find("{{emuso") > -1 and jaAchei == False):
print("Achei!")
jaAchei = True
userAki = hist.user
print(" ID: " + str(hist.revid) + "\n User: "******"\n Qndo: " + str(hist.timestamp))
userEmuso = hist.user
if (dataDif > dataLimite):
retirando = True
else:
pywikibot.output(
"\03{lightgreen}Mantendo esta {{Emuso}}...\03{default}"
)
retirando = False
break
elif (jaAchei == True and hist.user == userEmuso):
if (dataDif > dataLimite):
retirando = True
else:
pywikibot.output(
"\03{lightgreen}Mantendo esta {{Emuso}}...\03{default}"
)
retirando = False
break
else:
print("Ainda não... ")
if (retirando == True):
pywikibot.output(
"\03{red}Partiu retirar esta {{Emuso}}\03{default}!")
conteudo = page.text
if (conteudo.find("{{emuso|") > -1):
conteudo = conteudo.replace("{{emuso", "{{Emuso")
auxiliarEmuso = conteudo.split("{{Emuso")
novoTexto = auxiliarEmuso[0]
auxiliar = auxiliarEmuso[1].split("}}")
novoTexto += "}}".join(auxiliar[1:])
page.text = novoTexto
page.save(u'([[User:Thales César|Thales]]) 5.3 Emuso removida')
time.sleep(3)
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: str
"""
onlyUncat = False
# Process global args and prepare generator args parser
local_args = pywikibot.handle_args(args)
site = pywikibot.Site('commons', 'commons')
genFactory = pagegenerators.GeneratorFactory(site=site)
for arg in local_args:
if arg == '-onlyuncat':
onlyUncat = True
else:
genFactory.handle_arg(arg)
generator = genFactory.getCombinedGenerator()
if not generator:
generator = pagegenerators.CategorizedPageGenerator(pywikibot.Category(
site, 'Media needing categories'),
recurse=True)
initLists()
categorizeImages(generator, onlyUncat)
pywikibot.output('All done')
def add_template(cat):
gen = pagegenerators.CategorizedPageGenerator(pywikibot.Category(
SITE, cat))
summary = "Adding {{Do not crop}} template, requested by Pigsonthewing @ commons.wikimedia.org/w/index.php?title=Commons:Bots/Work_requests&oldid=414102776"
for file in gen:
file_name = file.title()
if file_name.startswith("File:"):
page = pywikibot.Page(SITE, file_name)
old_rev = page.oldest_revision
if 'crop' in (old_rev.comment).lower():
out('already cropped', color="white")
continue
old_text = page.get()
if 'do not crop' in old_text.lower():
out('already marked with DNC', color="white")
continue
end = findEndOfTemplate(old_text, "[Ss]pecimen")
new_text = (old_text[:end] + "\n{{Do not crop}}\n" +
old_text[end:])
try:
commit(
old_text,
new_text,
page,
summary,
)
except:
continue
def main():
site = pywikibot.Site("es", "wikipedia")
cat = pywikibot.Category(site, 'Categoría:Wikipedia:Fusionar')
gen = pg.CategorizedPageGenerator(cat, namespaces=[0, 100])
articles = pg.PreloadingGenerator(gen)
for page in articles:
print("<<<<<<<<<<<<<< {0} ".format(page.title()))
page_str = page.get()
tmpl_list = pywikibot.textlib.extract_templates_and_params(page_str)
templates_to_check = filter(
lambda x: x[0].lower() in categories_fusionar, tmpl_list)
for tipo in templates_to_check:
plantilla, parametros = tipo
if '1' not in parametros:
tools.write(data='[!!] Falta parámetro en {0}'.format(
str(page.title())), filename="fusionar.txt")
continue
else:
try:
nueva_pagina = pywikibot.Page(site, str(parametros['1']))
if(nueva_pagina.exists() == False):
tools.write(data=str(page.title()),
filename="fusionar.txt")
else:
print('La página {0} existe'.format(
nueva_pagina.title()))
except Exception:
tools.write(data='[!] Error en {0}'.format(
str(page.title())), filename="fusionar.txt")
def main():
cat = pywikibot.Category(site, 'Category:Courses')
gen = pagegenerators.CategorizedPageGenerator(cat)
global allcourses
allcourses = {i.title()[:7]: i for i in gen}
# allcourses = dict(allcourses.items()[0:20])
# Update existing courses
alreadyExistingGrades = []
print 'Fetching existing grades'
with progressbar.ProgressBar(max_value=len(allcourses)) as bar:
for n, i in enumerate(allcourses):
if re.findall(r'{{Grades.*[0-9].* }}', allcourses[i].text,
re.DOTALL):
alreadyExistingGrades.append(i)
bar.update(n)
for code in alreadyExistingGrades:
try:
if not currentGradesOnWiki(code) == newGrades[code]['grades']:
updateGrades(code)
except:
pass
# Add grades for new courses
notExistingGrades = [
i for i in allcourses
if i in newGrades and i not in alreadyExistingGrades
]
for code in notExistingGrades:
addGrades(code)
def createPageGenerator(
self, firstPageTitle) -> Generator[pywikibot.Page, None, None]:
"""Generator to retrieve misspelling pages or misspelling redirects."""
mycode = self.site.code
if mycode in self.misspellingCategory:
categories = self.misspellingCategory[mycode]
if isinstance(categories, UnicodeType):
categories = (categories, )
generators = (pagegenerators.CategorizedPageGenerator(
pywikibot.Category(self.site, misspellingCategoryTitle),
recurse=True,
start=firstPageTitle)
for misspellingCategoryTitle in categories)
elif mycode in self.misspellingTemplate:
templates = self.misspellingTemplate[mycode]
if isinstance(templates, UnicodeType):
templates = (templates, )
generators = (pagegenerators.ReferringPageGenerator(
pywikibot.Page(self.site, misspellingTemplateName, ns=10),
onlyTemplateInclusion=True)
for misspellingTemplateName in templates)
if firstPageTitle:
pywikibot.output(
'-start parameter unsupported on this wiki because there '
'is no category for misspellings.')
else:
pywikibot.output(HELP_MSG.format(site=self.site))
empty_gen = (i for i in [])
return empty_gen
generator = chain(*generators)
preloadingGen = pagegenerators.PreloadingGenerator(generator)
return preloadingGen
def main():
data = '20110310'
site = pywikibot.getSite()
cat = Category(site, 'Kategoria:francuski (indeks)')
lista = pagegenerators.CategorizedPageGenerator(cat)
#lista_stron1 = xmlreader.XmlDump('plwiktionary-%s-pages-articles.xml' % data)
#lista = xmlreader.XmlDump.parse(lista_stron1)
for a in lista:
h = Haslo(a.title())
#h = HasloXML(a.title, a.text)
if h.type != 4 and ' ' in h.title:
h.langs()
for c in h.list_lang:
c.pola()
if c.type != 2 and c.lang == 'hiszpański':
if ('rzeczownik' in c.znaczenia.tresc) and (
'rzeczownika' not in c.znaczenia.tresc):
print('\n' + h.title)
text = '*[[%s]]\n' % h.title
file = open("log/rzeczownik.txt", 'a')
file.write(text.encode("utf-8"))
file.close
def main():
global mysite, linktrail, page
start = []
for arg in pywikibot.handleArgs():
start.append(arg)
if start:
start = " ".join(start)
else:
start = "!"
mysite = pywikibot.Site()
linktrail = mysite.linktrail()
try:
generator = pagegenerators.CategorizedPageGenerator(
mysite.disambcategory(), start=start)
except pywikibot.NoPage:
pywikibot.output(
"The bot does not know the disambiguation category for your wiki.")
raise
# only work on articles
generator = pagegenerators.NamespaceFilterPageGenerator(generator, [0])
generator = pagegenerators.PreloadingGenerator(generator)
pagestodo = []
pagestoload = []
for page in generator:
if page.isRedirectPage():
continue
linked = page.linkedPages()
pagestodo.append((page, linked))
pagestoload += linked
if len(pagestoload) > 49:
pagestoload = pagegenerators.PreloadingGenerator(pagestoload)
for page, links in pagestodo:
workon(page, links)
pagestoload = []
pagestodo = []
def createPageGenerator(self, firstPageTitle):
mysite = pywikibot.Site()
mylang = mysite.code
if mylang in self.misspellingCategory:
misspellingCategoryTitle = self.misspellingCategory[mylang]
misspellingCategory = pywikibot.Category(mysite,
misspellingCategoryTitle)
generator = pagegenerators.CategorizedPageGenerator(
misspellingCategory, recurse=True, start=firstPageTitle)
elif mylang in self.misspellingTemplate:
misspellingTemplateName = 'Template:%s' % self.misspellingTemplate[
mylang]
misspellingTemplate = pywikibot.Page(mysite,
misspellingTemplateName)
generator = pagegenerators.ReferringPageGenerator(
misspellingTemplate, onlyTemplateInclusion=True)
if firstPageTitle:
pywikibot.output(
u'-start parameter unsupported on this wiki because there '
u'is no category for misspellings.')
else:
pywikibot.output(HELP_MSG.format(site=mysite))
empty_gen = (i for i in [])
return empty_gen
preloadingGen = pagegenerators.PreloadingGenerator(generator)
return preloadingGen
def main(argv):
global startCat
global debug
debug = False
state = False
parser = argparse.ArgumentParser()
parser.add_argument('--debug',
'-d',
help='enable debugging output',
action='store_true')
parser.add_argument('--place',
'-p',
'--location',
'-l',
help='specify location to start (required)',
required=True)
args = parser.parse_args(argv[1:])
debug = args.debug
startCat = startCat % args.place
site = pywikibot.Site()
cat = pywikibot.Category(site, startCat)
gen = pagegenerators.CategorizedPageGenerator(cat)
bot = PhotoCountyBot(state=args.place, generator=gen)
bot.run()
def actuallistes(nomorigen,
diccipa,
diccigpcv,
diccbic,
diccsipca,
diccmerimee,
diccart,
existents,
pagprova=False):
if re.match("llistes", nomorigen.casefold()):
cat = pwb.Category(site, 'Category:' + nomorigen)
print(cat)
llistes = pagegenerators.CategorizedPageGenerator(cat, recurse=True)
else:
llistes = [pwb.Page(site, nomorigen)]
for llista in llistes:
print(llista)
actuallista(llista,
diccipa,
diccigpcv,
diccbic,
diccsipca,
diccmerimee,
diccart,
existents,
pagprova=False)
return ()
def get_authors_list():
authors = []
category = pywikibot.Category(site, 'Categoria:Autori')
gen = pagegenerators.CategorizedPageGenerator(category)
for page in pagegenerators.PreloadingGenerator(gen):
authors.append(page.title(withNamespace=False))
return authors
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
"""
local_args = pywikibot.handle_args(args)
start = local_args[0] if local_args else '!'
mysite = pywikibot.Site()
try:
mysite.disambcategory()
except pywikibot.Error as e:
pywikibot.bot.suggest_help(exception=e)
return False
generator = pagegenerators.CategorizedPageGenerator(
mysite.disambcategory(), start=start, content=True, namespaces=[0])
bot = DisambiguationRedirectBot(generator=generator)
bot.run()
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:
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()
def run(self):
cat = pywikibot.Category(self.site, self.cat)
gen = pagegenerators.CategorizedPageGenerator(cat)
for page in pagegenerators.PreloadingGenerator(gen):
ignored_extensions = ['.pdf', '.svg', '.ogg', 'webm']
if ignored_extensions.count(page.title()[-4:].lower()) == 0:
self.treat(page)
def main(dry_run):
always = False
site = pywikibot.Site()
cat = pywikibot.Category(site, 'Virtue Deeds')
gen = pagegenerators.CategorizedPageGenerator(cat, recurse=True)
for page in gen:
always = edit_page(page, 'Drono-bot:virtue conversion', always,
dry_run)
def iterate_category(
site,
action,
category_name=u'Категория:Списки культурного наследия России'):
category = pywikibot.Category(site, category_name)
generator = pagegenerators.CategorizedPageGenerator(category)
for list_page in generator:
action(list_page)
def test_intersect_newpages_csd(self):
site = self.get_site()
self.assertEqualItertools([
pagegenerators.NewpagesPageGenerator(site=site, total=10),
pagegenerators.CategorizedPageGenerator(
pywikibot.Category(site,
'Category:Candidates_for_speedy_deletion'))
])
def main(*args: str) -> None:
"""
Process command line arguments and perform task.
If args is an empty list, sys.argv is used.
:param args: command line arguments
"""
# Loading the comments
global categoryToCheck, project_inserted
options = {}
generator = None
# Process global args and prepare generator args parser
local_args = pywikibot.handle_args(args)
site = pywikibot.Site()
if site.code not in project_inserted:
pywikibot.output('Your project is not supported by this script.\n'
'You have to edit the script and add it!')
return
# Process pagegenerators arguments
gen_factory = pagegenerators.GeneratorFactory(site)
local_args = gen_factory.handle_args(local_args)
# Process local args
for arg in local_args:
arg, sep, value = arg.partition(':')
option = arg[1:]
if arg in ('-always', '-move', '-show'):
options[option] = True
elif arg in ('-protectedpages', '-moveprotected'):
protect_type = 'move' if option.startswith('move') else 'edit'
generator = site.protectedpages(namespace=int(value or 0),
type=protect_type)
if not generator:
generator = gen_factory.getCombinedGenerator()
if not generator:
# Define the category if no other generator has been set
gen = []
categories = i18n.translate(site, categoryToCheck)
for category_name in categories:
cat = pywikibot.Category(site, category_name)
# Define the generator
gen.append(pagegenerators.CategorizedPageGenerator(cat))
generator = chain.from_iterable(gen)
if not gen_factory.nopreload:
generator = pagegenerators.PreloadingGenerator(generator, groupsize=60)
bot = CheckerBot(site=site, generator=generator, **options)
bot.run()
def get_candidate_items():
# Won't be definitive (can be non-items in this category)
# Can still use as a filter.
cat = pywikibot.Category(site, "Category:Items")
#
gen = pagegenerators.CategorizedPageGenerator(cat)
return gen
def setup(self):
"""Refresh generator."""
generator = pagegenerators.CategorizedPageGenerator(
self.csd_cat, start=self.saved_progress)
# wrap another generator around it so that we won't produce orphaned
# talk pages.
generator = pagegenerators.PageWithTalkPageGenerator(generator)
self.generator = pagegenerators.PreloadingGenerator(generator,
groupsize=20)
self.saved_progress = None
