def test_nobots(self):
"""Test that {{nobots}} raise the appropriate exception."""
page = pywikibot.Page(self.site, 'User:John Vandenberg/nobots')
with patch.object(config, 'ignore_bot_templates', False):
self.assertRaisesRegex(OtherPageSaveError, 'nobots', page.save)
import bisect
import json
import os
import re
import pymysql
os.environ['PYWIKIBOT_DIR'] = os.path.dirname(os.path.realpath(__file__))
import pywikibot
import requests
from config import config_page_name, host, password, user # pylint: disable=E0611,W0614
site = pywikibot.Site('zh', 'wikipedia')
site.login()
config_page = pywikibot.Page(site, config_page_name)
cfg = config_page.text
cfg = json.loads(cfg)
print(json.dumps(cfg, indent=4, ensure_ascii=False))
if not cfg['enable']:
exit('disabled\n')
conn = pymysql.connect(host=host, user=user, password=password, charset="utf8")
with conn.cursor() as cur:
cur.execute('use zhwiki_p')
cur.execute("""
SELECT rc_actor, actor_name, actor_user,
up_value AS `nickname`
FROM (
def handleArg(self, arg):
"""Parse one argument at a time.
If it is recognized as an argument that specifies a generator, a
generator is created and added to the accumulation list, and the
function returns true. Otherwise, it returns false, so that caller
can try parsing the argument. Call getCombinedGenerator() after all
arguments have been parsed to get the final output generator.
"""
site = pywikibot.getSite()
gen = None
if arg.startswith('-filelinks'):
fileLinksPageTitle = arg[11:]
if not fileLinksPageTitle:
fileLinksPageTitle = i18n.input(
'pywikibot-enter-file-links-processing')
if fileLinksPageTitle.startswith(site.namespace(6)
+ ":"):
fileLinksPage = pywikibot.ImagePage(site,
fileLinksPageTitle)
else:
fileLinksPage = pywikibot.ImagePage(site,
'Image:' +
fileLinksPageTitle)
gen = FileLinksGenerator(fileLinksPage)
elif arg.startswith('-unusedfiles'):
if len(arg) == 12:
gen = UnusedFilesGenerator()
else:
gen = UnusedFilesGenerator(number = int(arg[13:]))
elif arg.startswith('-unwatched'):
if len(arg) == 10:
gen = UnwatchedPagesPageGenerator()
else:
gen = UnwatchedPagesPageGenerator(number = int(arg[11:]))
elif arg.startswith('-usercontribs'):
gen = UserContributionsGenerator(arg[14:])
elif arg.startswith('-withoutinterwiki'):
if len(arg) == 17:
gen = WithoutInterwikiPageGenerator()
else:
gen = WithoutInterwikiPageGenerator(number = int(arg[18:]))
elif arg.startswith('-interwiki'):
title = arg[11:]
if not title:
title = i18n.input('pywikibot-enter-page-processing')
page = pywikibot.Page(pywikibot.Link(title,
pywikibot.Site()))
gen = InterwikiPageGenerator(page)
elif arg.startswith('-recentchanges'):
if len(arg) >= 15:
gen = RecentChangesPageGenerator(total=int(arg[15:]))
else:
gen = RecentChangesPageGenerator(total=60)
gen = DuplicateFilterPageGenerator(gen)
elif arg.startswith('-file'):
textfilename = arg[6:]
if not textfilename:
textfilename = pywikibot.input(
u'Please enter the local file name:')
gen = TextfilePageGenerator(textfilename)
elif arg.startswith('-namespace'):
if len(arg) == len('-namespace'):
self.namespaces.append(
pywikibot.input(u'What namespace are you filtering on?'))
else:
self.namespaces.extend(arg[len('-namespace:'):].split(","))
return True
elif arg.startswith('-ns'):
if len(arg) == len('-ns'):
self.namespaces.append(
pywikibot.input(u'What namespace are you filtering on?'))
else:
self.namespaces.extend(arg[len('-ns:'):].split(","))
return True
elif arg.startswith('-step'):
if len(arg) == len('-step'):
self.step = int(pywikibot.input("What is the step value?"))
else:
self.step = int(arg[len('-step:'):])
return True
elif arg.startswith('-limit'):
if len(arg) == len('-limit'):
self.limit = int(pywikibot.input("What is the limit value?"))
else:
self.limit = int(arg[len('-limit:'):])
return True
elif arg.startswith('-catr'):
gen = self.getCategoryGen(arg, len('-catr'), recurse = True)
elif arg.startswith('-category'):
gen = self.getCategoryGen(arg, len('-category'))
elif arg.startswith('-cat'):
gen = self.getCategoryGen(arg, len('-cat'))
elif arg.startswith('-subcatsr'):
gen = self.setSubCategoriesGen(arg, 9, recurse = True)
elif arg.startswith('-subcats'):
gen = self.setSubCategoriesGen(arg, 8)
elif arg.startswith('-page'):
if len(arg) == len('-page'):
gen = [pywikibot.Page(
pywikibot.Link(
pywikibot.input(
u'What page do you want to use?'),
pywikibot.getSite())
)]
else:
gen = [pywikibot.Page(pywikibot.Link(arg[len('-page:'):],
pywikibot.getSite())
)]
elif arg.startswith('-uncatfiles'):
gen = UnCategorizedImageGenerator()
elif arg.startswith('-uncatcat'):
gen = UnCategorizedCategoryGenerator()
elif arg.startswith('-uncat'):
gen = UnCategorizedPageGenerator()
elif arg.startswith('-ref'):
referredPageTitle = arg[5:]
if not referredPageTitle:
referredPageTitle = pywikibot.input(
u'Links to which page should be processed?')
referredPage = pywikibot.Page(pywikibot.Link(referredPageTitle,
pywikibot.Site()))
gen = ReferringPageGenerator(referredPage)
elif arg.startswith('-links'):
linkingPageTitle = arg[7:]
if not linkingPageTitle:
linkingPageTitle = pywikibot.input(
u'Links from which page should be processed?')
linkingPage = pywikibot.Page(pywikibot.Link(linkingPageTitle,
pywikibot.Site()))
gen = LinkedPageGenerator(linkingPage)
elif arg.startswith('-weblink'):
url = arg[9:]
if not url:
url = pywikibot.input(
u'Pages with which weblink should be processed?')
gen = LinksearchPageGenerator(url)
elif arg.startswith('-transcludes'):
transclusionPageTitle = arg[len('-transcludes:'):]
if not transclusionPageTitle:
transclusionPageTitle = pywikibot.input(
u'Pages that transclude which page should be processed?')
transclusionPage = pywikibot.Page(
pywikibot.Link(transclusionPageTitle,
defaultNamespace=10,
source=pywikibot.Site()))
gen = ReferringPageGenerator(transclusionPage,
onlyTemplateInclusion=True)
elif arg.startswith('-start'):
firstPageTitle = arg[7:]
if not firstPageTitle:
firstPageTitle = pywikibot.input(
u'At which page do you want to start?')
firstpagelink = pywikibot.Link(firstPageTitle,
pywikibot.Site())
namespace = firstpagelink.namespace
firstPageTitle = firstpagelink.title
gen = AllpagesPageGenerator(firstPageTitle, namespace,
includeredirects=False)
elif arg.startswith('-prefixindex'):
prefix = arg[13:]
namespace = None
if not prefix:
prefix = pywikibot.input(
u'What page names are you looking for?')
gen = PrefixingPageGenerator(prefix=prefix)
elif arg.startswith('-newimages'):
limit = arg[11:] or pywikibot.input(
u'How many images do you want to load?')
gen = NewimagesPageGenerator(total=int(limit))
elif arg.startswith('-newpages'):
if len(arg) >= 10:
gen = NewpagesPageGenerator(total=int(arg[10:]))
else:
gen = NewpagesPageGenerator(total=60)
elif arg.startswith('-imagesused'):
imagelinkstitle = arg[len('-imagesused:'):]
if not imagelinkstitle:
imagelinkstitle = pywikibot.input(
u'Images on which page should be processed?')
imagelinksPage = pywikibot.Page(pywikibot.Link(imagelinkstitle,
pywikibot.Site()))
gen = ImagesPageGenerator(imagelinksPage)
elif arg.startswith('-search'):
mediawikiQuery = arg[8:]
if not mediawikiQuery:
mediawikiQuery = pywikibot.input(
u'What do you want to search for?')
# In order to be useful, all namespaces are required
gen = SearchPageGenerator(mediawikiQuery, namespaces = [])
elif arg.startswith('-google'):
gen = GoogleSearchPageGenerator(arg[8:])
elif arg.startswith('-titleregex'):
if len(arg) == 6:
regex = pywikibot.input(
u'What page names are you looking for?')
else:
regex = arg[7:]
gen = RegexFilterPageGenerator(pywikibot.Site().allpages(), regex)
elif arg.startswith('-yahoo'):
gen = YahooSearchPageGenerator(arg[7:])
else:
pass
if gen:
self.gens.append(gen)
return True
else:
return False
if name not in wd:
continue
if '. gads' in name:
continue
wddata = wd[name]
row = "|-\n| [[{}]] || {} || {}".format(name, article[2], len(wddata))
rows.append(row)
counter +=1
"""
cur_date = datetime.now().strftime("%Y-%m-%d")
table = '\n'.join(rows[:200])
reportpage = """Atjaunināts: {}
{{| class="wikitable sortable"
|-
! Nr.p.k. !! Raksts !! Raksta garums !! Vērtīgo/labo rakstu<br>skaits citu valodu<br>Vikipēdijās
{}
|}}
""".format(cur_date, table)
lvpage = pywikibot.Page(lvsite, 'Dalībnieks:Edgars2007/Īsākie raksti')
lvpage.text = reportpage
lvpage.save(summary='Bots: atjaunināts', botflag=False, minor=False)
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
"""
global workingcat, parentcats
global checked
global excludefile
checked = set()
workingcatname = ''
options = {}
local_args = pywikibot.handle_args(args)
for arg in local_args:
option = arg[1:]
if not arg.startswith('-'):
if not workingcatname:
options['catnames'] = workingcatname = arg
else:
pywikibot.warning(
'Working category "{}" is already given.'.format(
workingcatname))
else:
options[option] = True
if not workingcatname:
pywikibot.bot.suggest_help(missing_parameters=['working category'])
return
mysite = pywikibot.Site()
summary = i18n.twtranslate(mysite, 'makecat-create',
{'cat': workingcatname})
bot = MakeCatBot(site=mysite, summary=summary, **options)
workingcat = pywikibot.Category(
mysite, '{0}{1}'.format(mysite.namespaces.CATEGORY, workingcatname))
filename = pywikibot.config.datafilepath(
'category',
workingcatname.encode('ascii', 'xmlcharrefreplace').decode('ascii') +
'_exclude.txt')
try:
with codecs.open(filename, 'r', encoding=mysite.encoding()) as f:
for line in f.readlines():
# remove leading and trailing spaces, LF and CR
line = line.strip()
if not line:
continue
pl = pywikibot.Page(mysite, line)
checked.add(pl)
excludefile = codecs.open(filename, 'a', encoding=mysite.encoding())
except IOError:
# File does not exist
excludefile = codecs.open(filename, 'w', encoding=mysite.encoding())
# Get parent categories in order to `removeparent`
try:
parentcats = workingcat.categories()
except pywikibot.Error:
parentcats = []
# Do not include articles already in subcats; only checking direct subcats
subcatlist = list(workingcat.subcategories())
if subcatlist:
subcatlist = pagegenerators.PreloadingGenerator(subcatlist)
for cat in subcatlist:
artlist = list(cat.articles())
for page in artlist:
checked.add(page)
# Fetch articles in category, and mark as already checked (seen)
# If category is empty, ask user if they want to look for pages
# in a different category.
articles = list(workingcat.articles(content=True))
if not articles:
pywikibot.output('Category {} does not exist or is empty. '
'Which page to start with?'.format(workingcatname))
answer = pywikibot.input('(Default is [[{}]]):'.format(workingcatname))
if not answer:
answer = workingcatname
pywikibot.output('' + answer)
pl = pywikibot.Page(mysite, answer)
articles = [pl]
for pl in articles:
checked.add(pl)
bot.include(pl)
bot.run()
def get_all_pages(self):
template = pywikibot.Page(self.site, self.template_name, ns=10)
return pagegenerators.ReferringPageGenerator(
template, onlyTemplateInclusion=True)
def BACK(site, name, hide):
p = pywikibot.Page(site, name, ns=10)
return [
page for page in p.getReferences(follow_redirects=False,
only_template_inclusion=True)
]
def init_page(self, item) -> pywikibot.Page:
"""Get the tuple and return the page object to be processed."""
title, content = item
page = pywikibot.Page(self.site, title)
page.text = content.strip()
return super().init_page(page)
def main(*args):
"""
Process command line arguments and perform task.
If args is an empty list, sys.argv is used.
@param args: command line arguments
@type args: unicode
"""
cfd_page = DEFAULT_CFD_PAGE
local_args = pywikibot.handle_args(args)
for arg in local_args:
if arg.startswith('-page'):
if len(arg) == len('-page'):
cfd_page = pywikibot.input(
'Enter the CFD working page to use:')
else:
cfd_page = arg[len('-page:'):]
page = pywikibot.Page(pywikibot.Site(), cfd_page)
try:
page.get()
except pywikibot.NoPage:
pywikibot.error(
'CFD working page "{0}" does not exist!'.format(cfd_page))
sys.exit(1)
# Variable declarations
day = 'None'
mode = 'None'
summary = ''
action_summary = ''
robot = None
m = ReCheck()
for line in page.text.split('\n'):
if nobots.search(line):
# NO BOTS!!!
pass
elif example.search(line):
# Example line
pass
elif speedymode.search(line):
mode = 'Speedy'
day = 'None'
elif movemode.search(line):
mode = 'Move'
day = 'None'
elif emptymode.search(line):
mode = 'Empty'
day = 'None'
elif deletemode.search(line):
mode = 'Delete'
day = 'None'
elif maintenance.search(line):
# It's probably best not to try to handle these in an automated
# fashion.
mode = 'None'
day = 'None'
elif m.check(dateheader, line):
day = m.result.group(1)
pywikibot.output('Found day header: {}'.format(day))
elif m.check(movecat, line):
src = m.result.group(1)
dest = m.result.group(2)
thisDay = findDay(src, day)
if mode == 'Move' and thisDay != 'None':
summary = (
'Robot - Moving category ' + src + ' to [[:Category:'
+ dest + ']] per [[WP:CFD|CFD]] at ' + thisDay + '.')
action_summary = \
'Robot - Result of [[WP:CFD|CFD]] at ' + thisDay + '.'
elif mode == 'Speedy':
summary = (
'Robot - Speedily moving category ' + src
+ ' to [[:Category:' + dest + ']] per [[WP:CFDS|CFDS]].')
action_summary = 'Robot - Speedily moved per [[WP:CFDS|CFDS]].'
else:
continue
# If the category is redirect, we do NOT want to move articles to
# it. The safest thing to do here is abort and wait for human
# intervention.
destpage = pywikibot.Page(page.site, dest, ns=14)
if destpage.isCategoryRedirect():
summary = 'CANCELED. Destination is redirect: ' + summary
pywikibot.stdout(summary)
robot = None
else:
deletion_comment_same = (
CategoryMoveBot.DELETION_COMMENT_SAME_AS_EDIT_COMMENT)
robot = CategoryMoveBot(oldcat=src, newcat=dest, batch=True,
comment=summary, inplace=True,
move_oldcat=True, delete_oldcat=True,
deletion_comment=deletion_comment_same,
move_comment=action_summary)
elif m.check(deletecat, line):
src = m.result.group(1)
# I currently don't see any reason to handle these two cases
# separately, though if are guaranteed that the category in the
# "Delete" case is empty, it might be easier to call delete.py on
# it.
thisDay = findDay(src, day)
if (mode == 'Empty' or mode == 'Delete') and thisDay != 'None':
summary = (
'Robot - Removing category {0} per [[WP:CFD|CFD]] '
'at {1}.'.format(src, thisDay))
action_summary = \
'Robot - Result of [[WP:CFD|CFD]] at ' + thisDay + '.'
else:
continue
robot = CategoryMoveBot(oldcat=src, batch=True, comment=summary,
deletion_comment=action_summary,
inplace=True)
if summary and robot is not None:
pywikibot.stdout(summary)
# Run, robot, run!
robot.run()
summary = ''
robot = None
def run(self):
self.page = pywikibot.Page(self.site,
self.change['title'],
ns=self.change['namespace'])
self.output(u"Handling")
if self.page.isRedirectPage():
self.output(u"Redirect")
return
if self.page.namespace() == 4:
# Project pages needs attention (__NEWSECTIONLINK__)
if not self.isDiscussion(self.page):
self.output(u"Not a discussion")
return
user = pywikibot.User(self.site, self.change['user'])
if self.isOptout(user):
self.output(u"%s opted-out" % user)
return
# diff-reading.
if self.change['type'] == 'new':
old_text = ''
else:
old_text = self.page.getOldVersion(self.change['revision']['old'])
new_text = self.page.getOldVersion(self.change['revision']['new'])
if "{{speedy" in new_text.lower():
self.output(u"{{speedy -- ignored")
return
diff = PatchManager(old_text.split("\n") if old_text else [],
new_text.split("\n"),
by_letter=True)
diff.print_hunks()
tosignstr = False
tosignnum = False
for block in diff.blocks:
if block[0] < 0: continue
hunk = diff.hunks[block[0]]
group = hunk.group
# print ("%7s a[%d:%d] (%s) b[%d:%d] (%s)" %
# (block[0], block[1][0], block[1][1], hunk.a[block[1][0]:block[1][1]], block[2][0], block[2][1], hunk.b[block[2][0]:block[2][1]]))
for tag, i1, i2, j1, j2 in group:
# print ("%7s a[%d:%d] (%s) b[%d:%d] (%s)" %
# (tag, i1, i2, hunk.a[i1:i2], j1, j2, hunk.b[j1:j2]))
if tag == 'insert':
for j in range(j1, j2):
line = hunk.b[j]
if self.page == user.getUserTalkPage(
) or self.page.title().startswith(
user.getUserTalkPage().title() + '/'):
if "{{" in line.lower():
self.output(
u"User adding templates to his own talk page -- ignored"
)
return
excluderegextest = self.matchExcludeRegex(line)
if excluderegextest is not None:
self.output(u"%s -- ignored" % excluderegextest)
return
if self.isComment(line):
tosignnum = j
tosignstr = line
if self.isSigned(user, tosignstr):
self.output(u"Signed")
return
if tosignstr is False:
self.output(u"No inserts")
return
if self.isSigned(user, tosignstr):
self.output(u"Signed")
return
if not self.isFreqpage(self.page):
self.output(u"Waiting")
time.sleep(60)
pass
currenttext = self.page.get(force=True).split("\n")
if currenttext[tosignnum] == tosignstr:
currenttext[tosignnum] += self.getSignature(tosignstr, user)
elif currenttext.count(tosignstr) == 1:
currenttext[currenttext.index(tosignstr)] += self.getSignature(
tosignstr, user)
else:
self.output(u"Line no longer found, probably signed")
return
summary = u'Signing comment by %s - "%s"' % (self.userlink(user),
self.change['comment'])
self.userPut(self.page,
self.page.get(),
u"\n".join(currenttext),
comment=summary)
# self.notify(user) {{subst:Please sign}} -- ignore {{bots}}
if self.controller.checknotify(user):
self.output(u"Notifying %s" % user)
talk = user.getUserTalkPage()
if talk.isRedirectPage(): talk = talk.getRedirectTarget()
try:
talktext = talk.get(force=True, get_redirect=True) + u'\n\n'
except pywikibot.NoPage:
talktext = ''
talktext += u'{{subst:Please sign}} --~~~~'
self.userPut(
talk,
talk.text,
talktext,
comment=
u"Added {{subst:[[Template:Please sign|Please sign]]}} note.",
minor=False)
def target_page(self):
"""Return target page object."""
if not hasattr(self, '_target_page'):
self._target_page = pywikibot.Page(self.site, self.target_title)
return self._target_page
import json
import sys
import csv
from BaseHTTPServer import BaseHTTPRequestHandler, HTTPServer
import urlparse
'''
variables
will add in input later
'''
PORT_NUMBER = 8080
varietal = "Merlot"
region = "Long Island"
year = '2008'
enwp = pywikibot.Site('en', 'wikipedia')
page = pywikibot.Page(enwp, varietal)
wikitext=page.get()
wikicode=mwparserfromhell.parse(wikitext)
templates=wikicode.filter_templates()
infobox = templates[1]
climate = ""
flavor = ""
detail_desc = ""
vintage = ""
def summary():
'''
Use the Google Knowledge Graph API to get a general summary about this wine.
Right now, the summary can be more than a sentence, but it can be trimmed down.
'''
def test_nocreate(self):
"""Test that Page.save with nocreate fails if page does not exist."""
page = pywikibot.Page(self.site, 'User:John_Vandenberg/no_recreate')
self.assertRaises(NoCreateError, page.save, nocreate=True)
def test_createonly(self):
"""Test that Page.save with createonly fails if page exists."""
page = pywikibot.Page(self.site, 'User:Xqt/sandbox')
self.assertRaises(PageCreatedConflict, page.save, createonly=True)
def test_nobots(self):
"""Test that {{nobots}} raise the appropriate exception."""
page = pywikibot.Page(self.site, 'User:John Vandenberg/nobots')
self.assertRaisesRegex(OtherPageSaveError, 'nobots', page.save)
def __init__(self, generator, templates, **kwargs):
"""
Constructor.
@param generator: the pages to work on
@type generator: iterable
@param templates: a dictionary which maps old template names to
their replacements. If remove or subst is True, it maps the
names of the templates that should be removed/resolved to None.
@type templates: dict
"""
self.availableOptions.update({
'subst': False,
'remove': False,
'summary': None,
'addedCat': None,
})
Bot.__init__(self, generator=generator, **kwargs)
self.templates = templates
# get edit summary message if it's empty
if not self.getOption('summary'):
comma = self.site.mediawiki_message('comma-separator')
params = {'list': comma.join(self.templates.keys()),
'num': len(self.templates)}
if self.getOption('remove'):
self.options['summary'] = i18n.twtranslate(
self.site, 'template-removing', params)
elif self.getOption('subst'):
self.options['summary'] = i18n.twtranslate(
self.site, 'template-substituting', params)
else:
self.options['summary'] = i18n.twtranslate(
self.site, 'template-changing', params)
replacements = []
exceptions = {}
builder = textlib._MultiTemplateMatchBuilder(self.site)
for old, new in self.templates.items():
templateRegex = builder.pattern(old)
if self.getOption('subst') and self.getOption('remove'):
replacements.append((templateRegex,
r'{{subst:%s\g<parameters>}}' % new))
exceptions['inside-tags'] = ['ref', 'gallery', 'poem',
'pagelist', ]
elif self.getOption('subst'):
replacements.append((templateRegex,
r'{{subst:%s\g<parameters>}}' % old))
exceptions['inside-tags'] = ['ref', 'gallery', 'poem',
'pagelist', ]
elif self.getOption('remove'):
replacements.append((templateRegex, ''))
else:
template = pywikibot.Page(self.site, new, ns=10)
if not template.exists():
pywikibot.warning(u'Template "%s" does not exist.' % new)
if not pywikibot.input_yn('Do you want to proceed anyway?',
default=False, automatic_quit=False):
continue
replacements.append((templateRegex,
r'{{%s\g<parameters>}}' % new))
super(TemplateRobot, self).__init__(
generator, replacements, exceptions,
always=self.getOption('always'),
addedCat=self.getOption('addedCat'),
summary=self.getOption('summary'))
def process_one_page(self, page_title):
page = pywikibot.Page(self.site, page_title)
pywikibot.output("Processing page %s" % page.title())
self.process_page(page)
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
"""
templateNames = []
templates = {}
options = {}
# If xmlfilename is None, references will be loaded from the live wiki.
xmlfilename = None
user = None
skip = False
timestamp = None
# read command line parameters
local_args = pywikibot.handle_args(args)
# Avoid conflicts with pagegenerators.py parameters.
if any(arg.startswith('-category:') for arg in local_args):
warn('-category (to append a category to each edited page) has been'
' renamed to -addcat; make sure you are using the correct param.',
ArgumentDeprecationWarning)
site = pywikibot.Site()
genFactory = pagegenerators.GeneratorFactory()
for arg in local_args:
if arg == '-remove':
options['remove'] = True
elif arg == '-subst':
options['subst'] = True
elif arg == '-assubst':
options['subst'] = options['remove'] = True
elif arg == '-always':
options['always'] = True
elif arg.startswith('-xml'):
if len(arg) == 4:
xmlfilename = pywikibot.input(
u'Please enter the XML dump\'s filename: ')
else:
xmlfilename = arg[5:]
elif arg.startswith('-addcat:'):
options['addedCat'] = arg[len('-addcat:'):]
elif arg.startswith('-summary:'):
options['summary'] = arg[len('-summary:'):]
elif arg.startswith('-onlyuser:'******'-onlyuser:'******'-skipuser:'******'-skipuser:'******'-timestamp:'):
timestamp = arg[len('-timestamp:'):]
else:
if not genFactory.handleArg(arg):
templateName = pywikibot.Page(site, arg, ns=10)
templateNames.append(templateName.title(withNamespace=False))
if not templateNames:
pywikibot.bot.suggest_help(missing_parameters=['templates'])
return False
if options.get('subst', False) ^ options.get('remove', False):
for templateName in templateNames:
templates[templateName] = None
else:
try:
for i in range(0, len(templateNames), 2):
templates[templateNames[i]] = templateNames[i + 1]
except IndexError:
pywikibot.output('Unless using solely -subst or -remove, '
'you must give an even number of template names.')
return
oldTemplates = []
for templateName in templates.keys():
oldTemplate = pywikibot.Page(site, templateName, ns=10)
oldTemplates.append(oldTemplate)
if xmlfilename:
builder = textlib._MultiTemplateMatchBuilder(site)
predicate = builder.search_any_predicate(oldTemplates)
gen = XMLDumpPageGenerator(
xmlfilename, site=site, text_predicate=predicate)
else:
gen = genFactory.getCombinedGenerator()
if not gen:
gens = [
pagegenerators.ReferringPageGenerator(t, onlyTemplateInclusion=True)
for t in oldTemplates
]
gen = pagegenerators.CombinedPageGenerator(gens)
gen = pagegenerators.DuplicateFilterPageGenerator(gen)
if user:
gen = pagegenerators.UserEditFilterGenerator(gen, user, timestamp, skip,
max_revision_depth=100,
show_filtered=True)
if not genFactory.gens:
# make sure that proper namespace filtering etc. is handled
gen = genFactory.getCombinedGenerator(gen)
if not genFactory.nopreload:
gen = pagegenerators.PreloadingGenerator(gen)
bot = TemplateRobot(gen, templates, site=site, **options)
bot.run()
def findTranslated(self, page, oursite=None):
quiet = self.getOption('quiet')
if not oursite:
oursite = self.site
if page.isRedirectPage():
page = page.getRedirectTarget()
ourpage = None
for link in page.iterlanglinks():
if link.site == oursite:
ourpage = pywikibot.Page(link)
break
if not ourpage:
if not quiet:
pywikibot.output('%s -> no corresponding page in %s' %
(page.title(), oursite))
elif ourpage.section():
pywikibot.output('%s -> our page is a section link: %s' %
(page.title(), ourpage.title()))
elif not ourpage.exists():
pywikibot.output("%s -> our page doesn't exist: %s" %
(page.title(), ourpage.title()))
else:
if ourpage.isRedirectPage():
ourpage = ourpage.getRedirectTarget()
pywikibot.output('%s -> corresponding page is %s' %
(page.title(), ourpage.title()))
if ourpage.namespace() != 0:
pywikibot.output('%s -> not in the main namespace, skipping' %
page.title())
elif ourpage.isRedirectPage():
pywikibot.output('%s -> double redirect, skipping' %
page.title())
elif not ourpage.exists():
pywikibot.output("%s -> page doesn't exist, skipping" %
ourpage.title())
else:
backpage = None
for link in ourpage.iterlanglinks():
if link.site == page.site:
backpage = pywikibot.Page(link)
break
if not backpage:
pywikibot.output('%s -> no back interwiki ref' %
page.title())
elif backpage == page:
# everything is ok
yield ourpage
elif backpage.isRedirectPage():
backpage = backpage.getRedirectTarget()
if backpage == page:
# everything is ok
yield ourpage
else:
pywikibot.output(
'%s -> back interwiki ref target is redirect to %s'
% (page.title(), backpage.title()))
else:
pywikibot.output('%s -> back interwiki ref target is %s' %
(page.title(), backpage.title()))
def main():
"The main function."
wiki = pywikibot.Site("en", "wikipedia")
wiki.login()
global wikitools_wiki
wikitools_login()
wpgo = pywikibot.Page(wiki, "Wikipedia:Goings-on")
wpgo_content = wpgo.get()
new_fc = wpgo_content[wpgo_content.find("==New featured content=="):]
# Trim it down to just the list of featured content
new_fc = new_fc[:new_fc.find("|-") - 2]
# Remove the section heading
new_fc = new_fc[len("==New featured content=="):]
# Create fc_cats, which looks like this: {type: [title of content]}
fc_cats = dict()
for fc_cat in re.finditer(WP_GO_HEADING, new_fc):
fc_cat_name = fc_cat.groups()[0]
fc_cat_raw_list = new_fc[fc_cat.start():]
fc_cat_raw_list = fc_cat_raw_list[len(fc_cat_name) + 1:]
next_heading = re.search(WP_GO_HEADING, fc_cat_raw_list)
if next_heading:
fc_cat_raw_list = fc_cat_raw_list[:next_heading.start()]
fc_cat_raw_list = fc_cat_raw_list.strip()
# Now that we have just the list, parse out the items
for fc_item in re.finditer(WP_GO_ITEM, fc_cat_raw_list):
name, _, label, date = fc_item.groups()
print u"{} (a {}) was promoted on {}".format(
label if label else name, fc_cat_name[:-1], date)
fc_cats[fc_cat_name] = fc_cats.get(fc_cat_name,
[]) + [(name, label, date)]
# Get notification metadata
for fc_cat, fc_items in fc_cats.items():
def add_metadata(fc_item):
name, label, date = fc_item
nom_link = "Wikipedia:Featured " + fc_cat[:-1] + " candidates/"
if fc_cat == "pictures":
nom_link += label[2:-2] if "''" in label else label
#if not WikitoolsPage(wikitools_wiki, title=nom_link).exists:
if not wiki.page_exists(nom_link):
print(nom_link + " DOESN'T EXIST")
else:
nom_link += name[2:-2] if "''" in name else name
nom_link += "/archive1"
return (name, label, date, nom_link)
fc_cats[fc_cat] = map(add_metadata, fc_items)
# Build "report"
report = ""
for fc_cat, fc_items in fc_cats.items():
report += "\n\n===Featured {}===".format(fc_cat)
report += "\n{} {} were promoted this week.".format(
len(fc_items), FC_LINKS[fc_cat])
for fc_item in fc_items:
name, label, date, nom_link = fc_item
piped = "|" + label if label else ""
report += u"\n* '''[[{}{}]]''' <small>([[{}|nominated]] by [[User:Example|Example]])</small> Description.".format(
name, piped, nom_link)
report = report.strip()
# Write report to Wikipedia
report_page = WikitoolsPage(wikitools_wiki,
title="User:APersonBot/sandbox")
print("Editing report page...")
result = report_page.edit(text=report.encode("ascii", "ignore"),
bot=True,
summary="Test FC report")
if result[u"edit"][u"result"] == u"Success":
print "Success!"
else:
print "Error! Couldn't write report - result: {}".format(str(result))
name = article[0].replace('_',' ')
if name not in wd:
continue
if '. gads' in name:
continue
wddata = wd[name]
row = "|-\n| [[{}]] || {} || {}".format(name, article[2], len(wddata))
rows.append(row)
counter +=1
"""
cur_date = datetime.now().strftime("%Y-%m-%d")
table = '\n'.join(rows[:200])
reportpage = """Upd: {}
{{| class="wikitable sortable"
|-
! Nr.p.k. !! Raksts !! Raksta garums !! FA/GA
{}
|}}
""".format(cur_date, table)
#with open("isakieraksti.txt", "w", encoding='utf-8') as file:
# file.write(str(for_list))
lvpage = pywikibot.Page(lvsite, u'User:Edgars2007/Shortest')
lvpage.text = reportpage
lvpage.save(summary=u'Bots: upd', botflag=False, minor=False)
def __init__(self, generator, templates: dict, **kwargs) -> None:
"""
Initializer.
@param generator: the pages to work on
@type generator: iterable
@param templates: a dictionary which maps old template names to
their replacements. If remove or subst is True, it maps the
names of the templates that should be removed/resolved to None.
"""
self.available_options.update({
'addcat': None,
'remove': False,
'subst': False,
'summary': None,
})
SingleSiteBot.__init__(self, generator=generator, **kwargs)
self.templates = templates
# get edit summary message if it's empty
if not self.opt.summary:
comma = self.site.mediawiki_message('comma-separator')
params = {
'list': comma.join(self.templates.keys()),
'num': len(self.templates)
}
if self.opt.remove:
tw_key = 'template-removing'
elif self.opt.subst:
tw_key = 'template-substituting'
else:
tw_key = 'template-changing'
self.opt.summary = i18n.twtranslate(self.site, tw_key, params)
replacements = []
exceptions = {}
builder = textlib._MultiTemplateMatchBuilder(self.site)
for old, new in self.templates.items():
template_regex = builder.pattern(old)
if self.opt.subst and self.opt.remove:
replacements.append(
(template_regex, r'{{subst:%s\g<parameters>}}' % new))
exceptions['inside-tags'] = [
'ref',
'gallery',
'poem',
'pagelist',
]
elif self.opt.subst:
replacements.append(
(template_regex,
r'{{%s:%s\g<parameters>}}' % (self.opt.subst, old)))
exceptions['inside-tags'] = [
'ref',
'gallery',
'poem',
'pagelist',
]
elif self.opt.remove:
separate_line_regex = re.compile(
r'^[*#:]* *{0} *\n'.format(template_regex.pattern),
re.DOTALL | re.MULTILINE)
replacements.append((separate_line_regex, ''))
spaced_regex = re.compile(
r' +{0} +'.format(template_regex.pattern), re.DOTALL)
replacements.append((spaced_regex, ' '))
replacements.append((template_regex, ''))
else:
template = pywikibot.Page(self.site, new, ns=10)
if not template.exists():
pywikibot.warning(
'Template "{0}" does not exist.'.format(new))
if not pywikibot.input_yn('Do you want to proceed anyway?',
default=False,
automatic_quit=False):
continue
replacements.append(
(template_regex, r'{{%s\g<parameters>}}' % new))
super().__init__(generator,
replacements,
exceptions,
always=self.opt.always,
addcat=self.opt.addcat,
summary=self.opt.summary)
def treat_page(self):
"""Work on current page and ask to add article to category."""
global checked
global excludefile
pl = self.current_page
ctoshow = 500
pywikibot.output('')
pywikibot.output('== {} =='.format(pl.title()))
while True:
answer = pywikibot.input_choice('Add to category {}?'.format(
self.workingcatname),
self.treat_options,
default='i')
if answer == 'y':
self.include(pl)
break
if answer == 'c':
self.include(pl, realinclude=False)
break
if answer == 'k':
if pl.exists() and not pl.isRedirectPage():
linkterm = pywikibot.input(
'In what manner should it be alphabetized?')
self.include(pl, linkterm=linkterm)
break
self.include(pl)
break
if answer == 'n':
excludefile.write('%s\n' % pl.title())
break
if answer == 'i':
break
if answer in 'er':
self.treat_options = self.option_bar[answer]
elif answer == 'h':
pywikibot.output("""
[y]es: Add the page and check links')
[n]o: Never add the page, saved to exclusion list
[i]gnore: Neither do not add the page not check links
[m]ore: show more content of the page starting from the beginning
sort [k]ey: Add with sort key like [[Category|Title]]
[s]kip: Add the page, but skip checking links
[c]heck: Do not add the page, but do check links
[o]ther: Add another page
[l]ist: Show a list of the pages to check
[e]xtend: A more extended option list
[r]educe: Reduce option list
[q]uit: Save exclusion list and exit this script
""")
elif answer == 'o':
pagetitle = pywikibot.input('Specify page to add:')
page = pywikibot.Page(pywikibot.Site(), pagetitle)
if page not in checked:
self.include(page)
elif answer == 's':
if not pl.exists():
pywikibot.output('Page does not exist; not added.')
elif pl.isRedirectPage():
pywikibot.output(
'Redirect page. Will be included normally.')
self.include(pl, realinclude=False)
else:
self.include(pl, checklinks=False)
break
elif answer == 'l':
length = len(self.tocheck)
pywikibot.output(
'Number of pages still to check: {}'.format(length))
if length:
pywikibot.output('Pages to be checked:')
pywikibot.output(
fill(' - '.join(page.title()
for page in self.tocheck)))
self.highlight_title(page)
elif answer == 'm':
self.highlight_title(pl, ctoshow > 500)
if pl.exists():
pywikibot.output(pl.text[0:ctoshow])
else:
pywikibot.output('Page does not exist.')
ctoshow += 500
def main(*args) -> None:
"""
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
"""
template_names = []
templates = {}
options = {}
# If xmlfilename is None, references will be loaded from the live wiki.
xmlfilename = None
user = None
skip = False
timestamp = None
# read command line parameters
local_args = pywikibot.handle_args(args)
site = pywikibot.Site()
gen_factory = pagegenerators.GeneratorFactory()
for arg in local_args:
if arg == '-remove':
options['remove'] = True
elif arg.startswith('-subst'):
options['subst'] = arg[len('-subst:'):] + 'subst'
assert options['subst'] in ('subst', 'safesubst')
elif arg == '-assubst':
options['subst'] = 'subst'
options['remove'] = True
elif arg == '-always':
options['always'] = True
elif arg.startswith('-xml'):
if len(arg) == 4:
xmlfilename = pywikibot.input(
"Please enter the XML dump's filename: ")
else:
xmlfilename = arg[5:]
elif arg.startswith('-addcat:'):
options['addcat'] = arg[len('-addcat:'):]
elif arg.startswith('-summary:'):
options['summary'] = arg[len('-summary:'):]
elif arg.startswith('-onlyuser:'******'-onlyuser:'******'-skipuser:'******'-skipuser:'******'-timestamp:'):
timestamp = arg[len('-timestamp:'):]
else:
if not gen_factory.handle_arg(arg):
template_name = pywikibot.Page(site, arg, ns=10)
template_names.append(template_name.title(with_ns=False))
if not template_names:
pywikibot.bot.suggest_help(missing_parameters=['templates'])
return False
if bool(options.get('subst', False)) ^ options.get('remove', False):
for template_name in template_names:
templates[template_name] = None
else:
try:
for i in range(0, len(template_names), 2):
templates[template_names[i]] = template_names[i + 1]
except IndexError:
pywikibot.output('Unless using solely -subst or -remove, '
'you must give an even number of template names.')
return
old_templates = []
for template_name in templates.keys():
old_template = pywikibot.Page(site, template_name, ns=10)
old_templates.append(old_template)
if xmlfilename:
builder = textlib._MultiTemplateMatchBuilder(site)
predicate = builder.search_any_predicate(old_templates)
gen = XMLDumpPageGenerator(xmlfilename,
site=site,
text_predicate=predicate)
else:
gen = gen_factory.getCombinedGenerator()
if not gen:
gens = (t.getReferences(only_template_inclusion=True,
follow_redirects=False) for t in old_templates)
gen = chain(*gens)
gen = filter_unique(gen, key=lambda p: '{}:{}:{}'.format(*p._cmpkey()))
if user:
gen = pagegenerators.UserEditFilterGenerator(gen,
user,
timestamp,
skip,
max_revision_depth=100,
show_filtered=True)
if not gen_factory.gens:
# make sure that proper namespace filtering etc. is handled
gen = gen_factory.getCombinedGenerator(gen)
if not gen_factory.nopreload:
gen = pagegenerators.PreloadingGenerator(gen)
bot = TemplateRobot(gen, templates, site=site, **options)
bot.run()
# put list of alternatives into listbox
self.list = list
# find required area
laenge = len(list)
maxbreite = 0
for i in range(laenge):
# cycle through all listitems to find maxlength
if len(list[i]) + len(str(i)) > maxbreite:
maxbreite = len(list[i]) + len(str(i))
# show list as formerly in DOS-window
self.listbox.insert(Tkinter.END, str(i) + ' - ' + list[i])
# set optimized height & width
self.listbox.config(height=laenge, width=maxbreite + 2)
# wait for user to push a button which will destroy (close) the window
return self.list
if __name__ == "__main__":
import pywikibot
try:
root = Tkinter.Tk()
root.resizable(width=Tkinter.FALSE, height=Tkinter.FALSE)
root.title("pywikibot GUI")
page = pywikibot.Page(pywikibot.Site(), u'Main Page')
content = page.get()
myapp = EditBoxWindow(root)
myapp.bind("<Control-d>", myapp.debug)
v = myapp.edit(content, highlight=page.title())
finally:
pywikibot.stopme()
def test_protected(self):
"""Test that protected titles raise the appropriate exception."""
if self.site._username[1]:
raise unittest.SkipTest('Testing failure of edit protected with a sysop account')
page = pywikibot.Page(self.site, 'Wikipedia:Create a new page')
self.assertRaises(LockedPage, page.save)
import os
import re
import time
from datetime import datetime
os.environ['PYWIKIBOT_DIR'] = os.path.dirname(os.path.realpath(__file__))
import pywikibot
from config import config_page_name # pylint: disable=E0611,W0614
os.environ['TZ'] = 'UTC'
site = pywikibot.Site()
site.login()
config_page = pywikibot.Page(site, config_page_name)
cfg = config_page.text
cfg = json.loads(cfg)
print(json.dumps(cfg, indent=4, ensure_ascii=False))
if not cfg["enable"]:
exit("disabled\n")
mainPage = pywikibot.Page(site, cfg["main_page_name"])
text = mainPage.text
rndstr = hashlib.md5(str(time.time()).encode()).hexdigest()
text = re.sub(r'^(===[^=]+===)$', rndstr + r'\1', text, flags=re.M)
text = text.split(rndstr)
mainPageText = text[0].strip()
def test_spam(self):
"""Test that spam in content raise the appropriate exception."""
page = pywikibot.Page(self.site, 'Wikipedia:Sandbox')
page.text = 'http://badsite.com'
self.assertRaisesRegex(SpamfilterError, 'badsite.com', page.save)
def InterwikiPageGenerator(page):
"""Iterator over all interwiki (non-language) links on a page."""
for link in page.interwiki():
yield pywikibot.Page(link)
def test_titleblacklist(self):
"""Test that title blacklist raise the appropriate exception."""
page = pywikibot.Page(self.site, 'User:UpsandDowns1234/Blacklisttest')
self.assertRaises(TitleblacklistError, page.save)