def do_cat(self, d):
cat = pywikibot.Category(
self.site,
'Category:Transport infrastructure completed in %(year)s' % d)
if cat.exists():
subcats = list(cat.subcategories())
else:
subcats = []
good_to_go = False
shouldhave = []
for c in ALL_CATS:
real = pywikibot.Category(self.site, c % d)
if real.exists():
good_to_go = True
if not (real in subcats):
shouldhave.append(real)
if not good_to_go:
return
if not cat.exists():
self.edit(
cat, TRANSPORT_TEXT % d,
'BOT: Creating Transport infrastructure by year category')
self.output('\n* creating [[:%s]]' % cat.title())
for i in shouldhave:
t = i.get()
n = pywikibot.replaceCategoryLinks(t, [cat], addOnly=True)
self.edit(i, n, 'BOT: Adding [[:%s]]' % cat.title())
self.output('\n*adding [[:%s]] to [[:%s]]' %
(cat.title(), i.title()))
def treat(self, page):
text = self.load(page)
if text is None:
return
cats = [c for c in page.categories()]
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(
u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
pywikibot.output(u"Current categories:")
for cat in cats:
pywikibot.output(u"* %s" % cat.title())
catpl = pywikibot.Page(self.site, self.newcatTitle, defaultNamespace=14)
if catpl in cats:
pywikibot.output(u"%s is already in %s."
% (page.title(), catpl.title()))
else:
if self.sort:
catpl = self.sorted_by_last_name(catpl, page)
pywikibot.output(u'Adding %s' % catpl.title(asLink=True))
cats.append(catpl)
text = pywikibot.replaceCategoryLinks(text, cats)
if not self.save(text, page, self.editSummary):
pywikibot.output(u'Page %s not saved.'
% page.title(asLink=True))
def run(self):
for merge in self.merges:
source_cat = pywikibot.Category(site, merge[0])
target_cat1 = pywikibot.Category(site, merge[1])
target_cat2 = pywikibot.Category(site, merge[2])
if not (source_cat.exists() and target_cat1.exists()
and target_cat2.exists()):
continue
for page in source_cat.articles():
if page.namespace() != 0:
continue
text = page.get()
page_cats = pywikibot.getCategoryLinks(text)
if source_cat in page_cats:
page_cats.remove(source_cat)
if not target_cat1 in page_cats:
page_cats.append(target_cat1)
if not target_cat2 in page_cats:
page_cats.append(target_cat2)
new_text = pywikibot.replaceCategoryLinks(text, page_cats)
if text == new_text:
continue
pywikibot.showDiff(text, new_text)
page.put(
new_text,
"[[Wikipedia:Bots|Bot]]: Merging from %s to %s and %s per CFD outcome"
% (source_cat.title(asLink=True),
target_cat1.title(asLink=True),
target_cat2.title(asLink=True)))
break
def run(self):
for merge in self.merges:
source_cat = pywikibot.Category(site, merge[0])
target_cat1 = pywikibot.Category(site, merge[1])
target_cat2 = pywikibot.Category(site, merge[2])
if not (source_cat.exists() and target_cat1.exists() and target_cat2.exists()):
continue
for page in source_cat.articles():
if page.namespace() != 0:
continue
text = page.get()
page_cats = pywikibot.getCategoryLinks(text)
if source_cat in page_cats:
page_cats.remove(source_cat)
if not target_cat1 in page_cats:
page_cats.append(target_cat1)
if not target_cat2 in page_cats:
page_cats.append(target_cat2)
new_text = pywikibot.replaceCategoryLinks(text, page_cats)
if text == new_text:
continue
pywikibot.showDiff(text, new_text)
page.put(
new_text,
"[[Wikipedia:Bots|Bot]]: Merging from %s to %s and %s per CFD outcome" % (
source_cat.title(asLink=True),
target_cat1.title(asLink=True),
target_cat2.title(asLink=True)
)
)
break
def treat(self, page):
text = self.load(page)
if text is None:
return
cats = [c for c in page.categories()]
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
pywikibot.output(u"Current categories:")
for cat in cats:
pywikibot.output(u"* %s" % cat.title())
newcatTitle = self.newcatTitle
if not page.site.nocapitalize:
newcatTitle = newcatTitle[:1].upper() + newcatTitle[1:]
catpl = pywikibot.Page(page.site, newcatTitle, ns=14)
if catpl in cats:
pywikibot.output(u"%s is already in %s." %
(page.title(), catpl.title()))
else:
if self.sort:
catpl = self.sorted_by_last_name(catpl, page)
pywikibot.output(u'Adding %s' % catpl.title(asLink=True))
cats.append(catpl)
text = pywikibot.replaceCategoryLinks(text, cats)
if not self.save(text, page, newcatTitle):
pywikibot.output(u'Page %s not saved.' %
page.title(asLink=True))
def do_cat(self, d):
cat = pywikibot.Category(self.site, 'Category:Transport infrastructure completed in %(year)s' % d)
if cat.exists():
subcats = list(cat.subcategories())
else:
subcats = []
good_to_go = False
shouldhave = []
for c in ALL_CATS:
real = pywikibot.Category(self.site, c % d)
if real.exists():
good_to_go = True
if not (real in subcats):
shouldhave.append(real)
if not good_to_go:
return
if not cat.exists():
self.edit(cat, TRANSPORT_TEXT % d, 'BOT: Creating Transport infrastructure by year category')
self.output('\n* creating [[:%s]]' % cat.title())
for i in shouldhave:
t= i.get()
n=pywikibot.replaceCategoryLinks(t, [cat],addOnly=True)
self.edit(i, n, 'BOT: Adding [[:%s]]' % cat.title())
self.output('\n*adding [[:%s]] to [[:%s]]' % (cat.title(), i.title()))
def categories(self):
for page in self.generator:
try:
pywikibot.output(u'\n>>>> %s <<<<' % page.title())
commons = pywikibot.Site().image_repository()
commonsCategory = pywikibot.Category(
commons, 'Category:%s' % page.title())
try:
getcommonscat = commonsCategory.text
commonsCategoryTitle = commonsCategory.title()
categoryname = commonsCategoryTitle.split('Category:',
1)[1]
if page.title() == categoryname:
oldText = page.get()
text = oldText
# for commonscat template
findTemplate = re.compile(ur'\{\{[Cc]ommons')
s = findTemplate.search(text)
findTemplate2 = re.compile(ur'\{\{[Ss]isterlinks')
s2 = findTemplate2.search(text)
if s or s2:
pywikibot.output(u'** Already done.')
else:
text = pywikibot.replaceCategoryLinks(
text + u'{{commonscat|%s}}' % categoryname,
list(page.categories()))
if oldText != text:
pywikibot.showDiff(oldText, text)
if not self.acceptall:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'All'], ['y', 'N', 'a'],
'N')
if choice == 'a':
self.acceptall = True
if self.acceptall or choice == 'y':
try:
msg = i18n.twtranslate(
pywikibot.Site(),
'commons_link-cat-template-added')
page.put(text, msg)
except pywikibot.EditConflict:
pywikibot.output(
u'Skipping %s because of edit '
u'conflict' % (page.title()))
except pywikibot.NoPage:
pywikibot.output(u'Category does not exist in Commons!')
except pywikibot.NoPage:
pywikibot.output(u'Page %s does not exist?!' % page.title())
except pywikibot.IsRedirectPage:
pywikibot.output(u'Page %s is a redirect; skipping.' %
page.title())
except pywikibot.LockedPage:
pywikibot.output(u'Page %s is locked?!' % page.title())
def make_categories(page, list, site=None):
if site is None:
site = pywikibot.getSite()
pllist = []
for p in list:
cattitle = "%s:%s" % (site.category_namespace(), p)
pllist.append(pywikibot.Page(site, cattitle))
page.put_async(pywikibot.replaceCategoryLinks(page.get(), pllist),
comment=i18n.twtranslate(site.lang, 'catall-changing'))
def make_categories(page, list, site=None):
if site is None:
site = pywikibot.Site()
pllist = []
for p in list:
cattitle = "%s:%s" % (site.category_namespace(), p)
pllist.append(pywikibot.Page(site, cattitle))
page.put_async(pywikibot.replaceCategoryLinks(page.get(), pllist),
comment=i18n.twtranslate(site.code, 'catall-changing'))
def categories(self):
for page in self.generator:
try:
pywikibot.output(u'\n>>>> %s <<<<' % page.title())
commons = pywikibot.getSite().image_repository()
commonsCategory = pywikibot.Category(commons,
'Category:%s' % page.title())
try:
getcommonscat = commonsCategory.get(get_redirect=True)
commonsCategoryTitle = commonsCategory.title()
categoryname = commonsCategoryTitle.split('Category:', 1)[1]
if page.title() == categoryname:
oldText = page.get()
text = oldText
# for commonscat template
findTemplate = re.compile(ur'\{\{[Cc]ommons')
s = findTemplate.search(text)
findTemplate2 = re.compile(ur'\{\{[Ss]isterlinks')
s2 = findTemplate2.search(text)
if s or s2:
pywikibot.output(u'** Already done.')
else:
text = pywikibot.replaceCategoryLinks(
text + u'{{commonscat|%s}}' % categoryname,
list(page.categories()))
if oldText != text:
pywikibot.showDiff(oldText, text)
if not self.acceptall:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'All'], ['y', 'N', 'a'],
'N')
if choice == 'a':
self.acceptall = True
if self.acceptall or choice == 'y':
try:
msg = i18n.twtranslate(
pywikibot.getSite(), 'commons_link-cat-template-added')
page.put(text, msg)
except pywikibot.EditConflict:
pywikibot.output(
u'Skipping %s because of edit '
u'conflict'
% (page.title()))
except pywikibot.NoPage:
pywikibot.output(u'Category does not exist in Commons!')
except pywikibot.NoPage:
pywikibot.output(u'Page %s does not exist?!' % page.title())
except pywikibot.IsRedirectPage:
pywikibot.output(u'Page %s is a redirect; skipping.'
% page.title())
except pywikibot.LockedPage:
pywikibot.output(u'Page %s is locked?!' % page.title())
def putAfterTemplate(oldtext, template, toadd, loose=True):
'''
Try to put text after template.
If the template is not found return False if loose is set to False
If loose is set to True: Remove interwiki's, categories, add template, restore categories, restore interwiki's.
Based on cc-by-sa-3.0 code by Dschwen
'''
newtext = u''
templatePosition = oldtext.find(u'{{%s' % (template,))
if templatePosition >= 0:
previousChar = u''
currentChar = u''
templatePosition += 2
curly = 1
square = 0
while templatePosition < len(oldtext):
currentChar = oldtext[templatePosition]
if currentChar == u'[' and previousChar == u'[':
square += 1
previousChar = u''
if currentChar == u']' and previousChar == u']':
square -= 1
previousChar = u''
if currentChar == u'{' and previousChar == u'{':
curly += 1
previousChar = u''
if currentChar == u'}' and previousChar == u'}':
curly -= 1
previousChar = u''
previousChar = currentChar
templatePosition += 1
if curly == 0 and square <= 0:
# Found end of template
break
newtext = oldtext[:templatePosition] + \
u'\n' + toadd + oldtext[templatePosition:]
else:
if loose:
newtext = oldtext
cats = pywikibot.getCategoryLinks(newtext)
ll = pywikibot.getLanguageLinks(newtext)
newtext = pywikibot.removeLanguageLinks(newtext)
newtext = pywikibot.removeCategoryLinks(newtext)
newtext += u'\n' + toadd
newtext = pywikibot.replaceCategoryLinks(newtext, cats)
newtext = pywikibot.replaceLanguageLinks(newtext, ll)
return newtext
def addRemoveRepoCats(article, repos, allRepoCats, comment=None):
# Create list of repos to be removed
notRepos = []
if not article.canBeEdited():
pywikibot.output("Can't edit %s, skipping it..." % article.aslink())
return False
cats = article.categories(get_redirect=True)
site = article.site
changesMade = False
newCatList = []
newCatSet = set()
repoCatList = []
#remove all repos
for cat in cats:
if cat in allRepoCats:
changesMade = True
continue
if cat.title() not in newCatSet:
newCatSet.add(cat.title())
newCatList.append(cat)
#add relevant repos
for i in range(len(repos)):
repo = repos[i]
newCatList.append(catlib.Category(site, 'Category:' + repoCats[repo]))
changesMade = True
if not changesMade:
pywikibot.output(u'No changes necessary to %s!' % article.title())
else:
text = article.get(get_redirect=True)
try:
text = pywikibot.replaceCategoryLinks(text, newCatList)
except ValueError:
# Make sure that the only way replaceCategoryLinks() can return
# a ValueError is in the case of interwiki links to self.
pywikibot.output(u'Skipping %s because of interwiki link to self' %
article)
try:
article.put(text,
comment='Addon-Bot repo category update',
watchArticle=None,
minorEdit=True)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict' %
article.title())
except pywikibot.SpamfilterError, e:
pywikibot.output(u'Skipping %s because of blacklist entry %s' %
(article.title(), e.url))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s because page is locked' %
article.title())
def standardizePageFooter(self, text):
"""
Makes sure that categories are put to the correct position, but
does not sort them.
"""
# The PyWikipediaBot is no longer allowed to touch categories on the German Wikipedia. See http://de.wikipedia.org/wiki/Hilfe_Diskussion:Personendaten/Archiv/bis_2006#Position_der_Personendaten_am_.22Artikelende.22
if self.site != pywikibot.getSite('de', 'wikipedia') and not self.template:
categories = pywikibot.getCategoryLinks(text, site = self.site)
text = pywikibot.replaceCategoryLinks(text, categories, site = self.site)
return text
def addRemoveRepoCats(article, repos, allRepoCats, comment=None):
# Create list of repos to be removed
notRepos = []
if not article.canBeEdited():
pywikibot.output("Can't edit %s, skipping it..." % article.aslink())
return False
cats = article.categories(get_redirect=True)
site = article.site
changesMade = False
newCatList = []
newCatSet = set()
repoCatList = []
#remove all repos
for cat in cats:
if cat in allRepoCats:
changesMade = True
continue
if cat.title() not in newCatSet:
newCatSet.add(cat.title())
newCatList.append(cat)
#add relevant repos
for i in range(len(repos)):
repo = repos[i]
newCatList.append(catlib.Category(site, 'Category:'+ repoCats[repo]))
changesMade = True
if not changesMade:
pywikibot.output(u'No changes necessary to %s!' % article.title())
else:
text = article.get(get_redirect=True)
try:
text = pywikibot.replaceCategoryLinks(text, newCatList)
except ValueError:
# Make sure that the only way replaceCategoryLinks() can return
# a ValueError is in the case of interwiki links to self.
pywikibot.output(
u'Skipping %s because of interwiki link to self' % article)
try:
article.put(text, comment='Addon-Bot repo category update', watchArticle = None, minorEdit = True)
except pywikibot.EditConflict:
pywikibot.output(
u'Skipping %s because of edit conflict' % article.title())
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Skipping %s because of blacklist entry %s'
% (article.title(), e.url))
except pywikibot.LockedPage:
pywikibot.output(
u'Skipping %s because page is locked' % article.title())
def do_page(page, cat):
text = page.get()
if cat.title().lower() in text.lower():
print 'Skipping '+page.title(asLink=True)
return
newtext = pywikibot.replaceCategoryLinks(text, [cat], site=site, addOnly=True)
pywikibot.showDiff(text, newtext)
print 'Saving '+page.title(asLink=True)
try:
page.put(newtext, 'Robot: Adding [[:%s]]' % cat.title())
except pywikibot.exceptions.LockedPage:
pass
def filterSubCategory(subcat, category):
'''
Filter category from all articles and files in subcat
'''
articleGen = pagegenerators.PreloadingGenerator(pagegenerators.CategorizedPageGenerator(subcat))
for article in articleGen:
pywikibot.output(u'Working on %s' % (article.title(),))
articleCategories = article.categories()
if category in articleCategories:
articleCategories.remove(category)
text = article.get()
newtext = pywikibot.replaceCategoryLinks(text, articleCategories)
pywikibot.showDiff(text, newtext)
comment = u'Removing [[%s]]: Is already in the subcategory [[%s]]' % (category.title(), subcat.title())
article.put(newtext, comment)
def filterSubCategory(subcat, category):
""" Filter category from all articles and files in subcat """
articleGen = pagegenerators.PreloadingGenerator(
pagegenerators.CategorizedPageGenerator(subcat))
for article in articleGen:
pywikibot.output(u'Working on %s' % (article.title(), ))
articleCategories = article.categories()
if category in articleCategories:
articleCategories.remove(category)
text = article.get()
newtext = pywikibot.replaceCategoryLinks(text, articleCategories)
pywikibot.showDiff(text, newtext)
comment = (
u'Removing [[%s]]: Is already in the subcategory [[%s]]' %
(category.title(), subcat.title()))
article.put(newtext, comment)
def subthread(pagep, catinp, cat, page):
if not page:
pywikibot.output(pagep.title() + " not found")
return
pywikibot.output("thread %s >>> adding..." % page.title())
try:
if page.namespace() not in wp.conf.nstl:
oldcat = set(page.categories(fromtext=True))
newcat = (oldcat - set([catinp])) | set([cat])
if oldcat != newcat:
pywikibot.output("Change!")
text = pywikibot.replaceCategoryLinks(page.get(), list(newcat), site)
page.put(text, u"autoCategory")
else:
pywikibot.output("Nothing changes!")
except:
wp.error()
def include(pl, checklinks=True, realinclude=True, linkterm=None):
cl = checklinks
if linkterm:
actualworkingcat = pywikibot.Category(mysite,
workingcat.title(),
sortKey=linkterm)
else:
actualworkingcat = workingcat
if realinclude:
try:
text = pl.get()
except pywikibot.NoPage:
pass
except pywikibot.IsRedirectPage:
cl = True
pass
else:
cats = [x for x in pl.categories()]
if workingcat not in cats:
cats = [x for x in pl.categories()]
for c in cats:
if c in parentcats:
if removeparent:
pl.change_category(actualworkingcat)
break
else:
pl.put(
pywikibot.replaceCategoryLinks(
text, cats + [actualworkingcat]))
if cl:
if checkforward:
for page2 in pl.linkedPages():
if needcheck(page2):
tocheck.append(page2)
checked[page2] = page2
if checkbackward:
for refPage in pl.getReferences():
if needcheck(refPage):
tocheck.append(refPage)
checked[refPage] = refPage
def include(pl, checklinks=True, realinclude=True, linkterm=None):
cl = checklinks
if linkterm:
actualworkingcat = pywikibot.Category(mysite, workingcat.title(),
sortKey=linkterm)
else:
actualworkingcat = workingcat
if realinclude:
try:
text = pl.get()
except pywikibot.NoPage:
pass
except pywikibot.IsRedirectPage:
cl = True
pass
else:
cats = [x for x in pl.categories()]
if workingcat not in cats:
cats = [x for x in pl.categories()]
for c in cats:
if c in parentcats:
if removeparent:
pl.change_category(actualworkingcat)
break
else:
pl.put(pywikibot.replaceCategoryLinks(
text, cats + [actualworkingcat]))
if cl:
if checkforward:
for page2 in pl.linkedPages():
if needcheck(page2):
tocheck.append(page2)
checked[page2] = page2
if checkbackward:
for refPage in pl.getReferences():
if needcheck(refPage):
tocheck.append(refPage)
checked[refPage] = refPage
def standardizePageFooter(self, text):
"""
Makes sure that interwiki links, categories and star templates are
put to the correct position and into the right order. This combines the
old instances standardizeInterwiki and standardizeCategories
The page footer has the following section in that sequence:
1. categories
2. ## TODO: template beyond categories ##
3. additional information depending on local site policy
4. stars templates for featured and good articles
5. interwiki links
"""
starsList = [
u"bueno",
u"bom interwiki",
u"cyswllt[ _]erthygl[ _]ddethol",
u"dolen[ _]ed",
u"destacado",
u"destaca[tu]",
u"enllaç[ _]ad",
u"enllaz[ _]ad",
u"leam[ _]vdc",
u"legătură[ _]a[bcf]",
u"liamm[ _]pub",
u"lien[ _]adq",
u"lien[ _]ba",
u"liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt",
u"liên[ _]kết[ _]chọn[ _]lọc",
u"ligam[ _]adq",
u"ligoelstara",
u"ligoleginda",
u"link[ _][afgu]a",
u"link[ _]adq",
u"link[ _]f[lm]",
u"link[ _]km",
u"link[ _]sm",
u"linkfa",
u"na[ _]lotura",
u"nasc[ _]ar",
u"tengill[ _][úg]g",
u"ua",
u"yüm yg",
u"רא",
u"وصلة مقالة جيدة",
u"وصلة مقالة مختارة",
]
categories = None
interwikiLinks = None
allstars = []
hasCommentLine = False
# The PyWikipediaBot is no longer allowed to touch categories on the
# German Wikipedia. See
# http://de.wikipedia.org/wiki/Hilfe_Diskussion:Personendaten/Archiv/1#Position_der_Personendaten_am_.22Artikelende.22
# ignoring nn-wiki of cause of the comment line above iw section
if (
not self.template
and not "{{Personendaten" in text
and not "{{SORTIERUNG" in text
and not "{{DEFAULTSORT" in text
and not self.site.lang in ("et", "it", "bg", "ru")
):
categories = pywikibot.getCategoryLinks(text, site=self.site)
if not self.talkpage: # and pywikibot.calledModuleName() <> 'interwiki':
subpage = False
if self.template:
loc = None
try:
tmpl, loc = moved_links[self.site.lang]
del tmpl
except KeyError:
pass
if loc != None and loc in self.title:
subpage = True
interwikiLinks = pywikibot.getLanguageLinks(text, insite=self.site, template_subpage=subpage)
# Removing the interwiki
text = pywikibot.removeLanguageLinks(text, site=self.site)
# Removing the stars' issue
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile("(\{\{(?:template:|)%s\|.*?\}\}[\s]*)" % star, re.I)
found = regex.findall(starstext)
if found != []:
text = regex.sub("", text)
allstars += found
# nn got a message between the categories and the iw's
# and they want to keep it there, first remove it
if self.site.lang in msg_interwiki:
iw_msg = msg_interwiki[self.site.lang]
if isinstance(iw_msg, tuple):
iw_reg = iw_msg[1]
iw_msg = iw_msg[0]
else:
iw_reg = u"(%s)" % iw_msg
regex = re.compile(iw_reg)
found = regex.findall(text)
if found:
hasCommentLine = True
text = regex.sub("", text)
# Adding categories
if categories:
##Sorting categories in alphabetic order. beta test only on Persian Wikipedia, TODO fix bug for sorting
# if self.site.language() == 'fa':
# categories.sort()
##Taking main cats to top
# for name in categories:
# if re.search(u"(.+?)\|(.{,1}?)",name.title()) or name.title()==name.title().split(":")[0]+title:
# categories.remove(name)
# categories.insert(0, name)
text = pywikibot.replaceCategoryLinks(text, categories, site=self.site)
# Put the iw message back
if not self.talkpage and (
(interwikiLinks or hasCommentLine)
and self.site.language() == "nn"
or (interwikiLinks and hasCommentLine)
and self.site.language() == "fr"
):
text += config.line_separator * 2 + iw_msg
# Adding stars templates
if allstars:
text = text.strip() + self.site.family.interwiki_text_separator
allstars.sort()
for element in allstars:
text += "%s%s" % (element.strip(), config.line_separator)
pywikibot.log(u"%s" % element.strip())
# Adding the interwiki
if interwikiLinks:
text = pywikibot.replaceLanguageLinks(
text, interwikiLinks, site=self.site, template=self.template, template_subpage=subpage
)
return text
def run(self):
"""
Starts the robot.
"""
# Run the generator which will yield Pages which might need to be
# changed.
for page in self.generator:
if self.isTitleExcepted(page.title()):
pywikibot.output(
u'Skipping %s because the title is on the exceptions list.'
% page.title(asLink=True))
continue
try:
# Load the page's text from the wiki
original_text = page.get(get_redirect=True)
if not (self.articles or page.canBeEdited()):
pywikibot.output(u"You can't edit page %s" %
page.title(asLink=True))
continue
except pywikibot.NoPage:
pywikibot.output(u'Page %s not found' %
page.title(asLink=True))
continue
new_text = original_text
while True:
if self.isTextExcepted(new_text):
pywikibot.output(u'Skipping %s because it contains text '
u'that is on the exceptions list.' %
page.title(asLink=True))
break
new_text = self.doReplacements(new_text)
if new_text == original_text:
pywikibot.output(u'No changes were necessary in %s' %
page.title(asLink=True))
break
if self.recursive:
newest_text = self.doReplacements(new_text)
while newest_text != new_text:
new_text = newest_text
newest_text = self.doReplacements(new_text)
if hasattr(self, "addedCat"):
cats = page.categories()
if self.addedCat not in cats:
cats.append(self.addedCat)
new_text = pywikibot.replaceCategoryLinks(
new_text, cats)
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(
u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
pywikibot.showDiff(original_text, new_text)
if self.acceptall:
break
if self.exctitles:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?', [
'Yes', 'No', 'no+eXcept', 'Edit',
'open in Browser', 'All', 'Quit'
], ['y', 'N', 'x', 'e', 'b', 'a', 'q'], 'N')
else:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?', [
'Yes', 'No', 'Edit', 'open in Browser', 'All',
'Quit'
], ['y', 'N', 'e', 'b', 'a', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(original_text)
# if user didn't press Cancel
if as_edited and as_edited != new_text:
new_text = as_edited
continue
if choice == 'b':
webbrowser.open("http://%s%s" %
(page.site.hostname(),
page.site.nice_get_address(page.title())))
i18n.input('pywikibot-enter-finished-browser')
try:
original_text = page.get(get_redirect=True, force=True)
except pywikibot.NoPage:
pywikibot.output(u'Page %s has been deleted.' %
page.title())
break
new_text = original_text
continue
if choice == 'q':
self.writeEditCounter()
self.writeExceptCounter()
return
if choice == 'a':
self.acceptall = True
if choice == 'x': # May happen only if self.exctitles isn't None
self.exctitles.write(u"ur'^%s$',\n" %
re.escape(page.title()))
self.exctitles.flush()
self.exceptcounter += 1
if choice == 'y':
if not self.articles:
# Primary behaviour: working on wiki
page.put_async(new_text, self.editSummary)
self.editcounter += 1
# Bug: this increments even if put_async fails
# This is separately in two clauses of if for
# future purposes to get feedback form put_async
else:
# Save the title for later processing instead of editing
self.editcounter += 1
self.articles.write(u'#%s\n%s' % (page.title(
asLink=True, textlink=True), self.splitLine()))
self.articles.flush() # For the peace of our soul :-)
# choice must be 'N'
break
if self.acceptall and new_text != original_text:
if not self.articles:
#Primary behaviour: working on wiki
try:
page.put(new_text, self.editSummary)
self.editcounter += 1 # increment only on success
except pywikibot.EditConflict:
pywikibot.output(
u'Skipping %s because of edit conflict' %
(page.title(), ))
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s' %
(page.title(), e.url))
except pywikibot.PageNotSaved, error:
pywikibot.error(u'putting page: %s' % (error.args, ))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)' %
(page.title(), ))
def add_text(page=None, addText=None, summary=None, regexSkip=None,
regexSkipUrl=None, always=False, up=False, putText=True,
oldTextGiven=None, reorderEnabled=True, create=False):
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
starsList = [
u'bueno',
u'bom interwiki',
u'cyswllt[ _]erthygl[ _]ddethol', u'dolen[ _]ed',
u'destacado', u'destaca[tu]',
u'enllaç[ _]ad',
u'enllaz[ _]ad',
u'leam[ _]vdc',
u'legătură[ _]a[bcf]',
u'liamm[ _]pub',
u'lien[ _]adq',
u'lien[ _]ba',
u'liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt',
u'liên[ _]kết[ _]chọn[ _]lọc',
u'ligam[ _]adq',
u'ligoelstara',
u'ligoleginda',
u'link[ _][afgu]a', u'link[ _]adq', u'link[ _]f[lm]', u'link[ _]km',
u'link[ _]sm', u'linkfa',
u'na[ _]lotura',
u'nasc[ _]ar',
u'tengill[ _][úg]g',
u'ua',
u'yüm yg',
u'רא',
u'وصلة مقالة جيدة',
u'وصلة مقالة مختارة',
]
errorCount = 0
site = pywikibot.getSite()
pathWiki = site.family.nicepath(site.lang)
site = pywikibot.getSite()
if oldTextGiven is None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!"
% page.title())
text = u''
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always)
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always)
else:
text = oldTextGiven
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace('\\n', '\n')
if (reorderEnabled):
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# Adding the text
newtext += u"\n%s" % addText
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext,
categoriesInside, site,
True)
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)'
% star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub('', newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + '\r\n\r\n'
allstars.sort()
for element in allstars:
newtext += '%s\r\n' % element.strip()
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside,
site)
else:
newtext += u"\n%s" % addText
else:
newtext = addText + '\n' + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
#pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if always or choice == 'y':
try:
pass
if always:
page.put(newtext, summary,
minorEdit=False)
else:
page.put_async(newtext, summary,
minorEdit=False)
except pywikibot.EditConflict:
pywikibot.output(u'Edit conflict! skip!')
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < 5:
pywikibot.output(u'Server Error! Wait..')
time.sleep(5)
continue
else:
raise pywikibot.ServerError(u'Fifth Server Error!')
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved, error:
pywikibot.output(u'Error putting page: %s' % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
def add_text(page=None, addText=None, summary=None, regexSkip=None,
regexSkipUrl=None, always=False, up=False, putText=True,
oldTextGiven=None, reorderEnabled=True, create=False):
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
starsList = [
u'bueno',
u'bom interwiki',
u'cyswllt[ _]erthygl[ _]ddethol', u'dolen[ _]ed',
u'destacado', u'destaca[tu]',
u'enllaç[ _]ad',
u'enllaz[ _]ad',
u'leam[ _]vdc',
u'legătură[ _]a[bcf]',
u'liamm[ _]pub',
u'lien[ _]adq',
u'lien[ _]ba',
u'liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt',
u'liên[ _]kết[ _]chọn[ _]lọc',
u'ligam[ _]adq',
u'ligoelstara',
u'ligoleginda',
u'link[ _][afgu]a', u'link[ _]adq', u'link[ _]f[lm]', u'link[ _]km',
u'link[ _]sm', u'linkfa',
u'na[ _]lotura',
u'nasc[ _]ar',
u'tengill[ _][úg]g',
u'ua',
u'yüm yg',
u'רא',
u'وصلة مقالة جيدة',
u'وصلة مقالة مختارة',
]
errorCount = 0
site = pywikibot.getSite()
pathWiki = site.family.nicepath(site.lang)
site = pywikibot.getSite()
if oldTextGiven is None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!"
% page.title())
text = u''
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always)
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always)
else:
text = oldTextGiven
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace('\\n', '\n')
if (reorderEnabled):
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# Adding the text
newtext += u"\n%s" % addText
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext,
categoriesInside, site,
True)
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)'
% star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub('', newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + '\r\n\r\n'
allstars.sort()
for element in allstars:
newtext += '%s\r\n' % element.strip()
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside,
site)
else:
newtext += u"\n%s" % addText
else:
newtext = addText + '\n' + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
#pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if always or choice == 'y':
try:
pass
if always:
page.put(newtext, summary,
minorEdit=False)
else:
page.put_async(newtext, summary,
minorEdit=False)
except pywikibot.EditConflict:
pywikibot.output(u'Edit conflict! skip!')
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < 5:
pywikibot.output(u'Server Error! Wait..')
time.sleep(5)
continue
else:
raise pywikibot.ServerError(u'Fifth Server Error!')
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved, error:
pywikibot.output(u'Error putting page: %s' % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
def add_text(page=None,
addText=None,
summary=None,
regexSkip=None,
regexSkipUrl=None,
always=False,
up=False,
putText=True,
oldTextGiven=None,
reorderEnabled=True,
create=False):
if not addText:
raise NoEnoughData('You have to specify what text you want to add!')
site = page.site
if not summary:
summary = i18n.twtranslate(site, 'add_text-adding',
{'adding': addText[:200]})
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
errorCount = 0
if putText:
pywikibot.output(u'Loading %s...' % page.title())
if oldTextGiven is None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!" %
page.title())
text = u''
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always)
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always)
else:
text = oldTextGiven
# Understand if the bot has to skip the page or not
# In this way you can use both -except and -excepturl
if regexSkipUrl is not None:
url = site.nice_get_address(page.title(asUrl=True))
result = re.findall(regexSkipUrl, site.getUrl(url))
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -exceptUrl is in the page. Skip!
Match was: %s''' % result)
return (False, False, always)
if regexSkip is not None:
result = re.findall(regexSkip, text)
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -except is in the page. Skip!
Match was: %s''' % result)
return (False, False, always)
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace('\\n', config.line_separator)
if (reorderEnabled):
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# Adding the text
newtext += u"%s%s" % (config.line_separator, addText)
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext, categoriesInside,
site, True)
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile(
'(\{\{(?:template:|)%s\|.*?\}\}[\s]*)' % star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub('', newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + config.line_separator * 2
allstars.sort()
for element in allstars:
newtext += '%s%s' % (element.strip(), config.LS)
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside,
site)
else:
newtext += u"%s%s" % (config.line_separator, addText)
else:
newtext = addText + config.line_separator + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if not always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'All', 'open in Browser'],
['y', 'n', 'a', 'b'], 'n')
if choice == 'a':
always = True
elif choice == 'n':
return (False, False, always)
elif choice == 'b':
webbrowser.open(
"http://%s%s" %
(site.hostname(),
site.nice_get_address(page.title(asUrl=True))))
pywikibot.input("Press Enter when finished in browser.")
if always or choice == 'y':
try:
if always:
page.put(newtext,
summary,
minorEdit=page.namespace() != 3)
else:
page.put_async(newtext,
summary,
minorEdit=page.namespace() != 3)
except pywikibot.EditConflict:
pywikibot.output(u'Edit conflict! skip!')
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < config.max_retries:
pywikibot.output(u'Server Error! Wait..')
time.sleep(config.retry_wait)
continue
else:
raise pywikibot.ServerError(u'Fifth Server Error!')
except pywikibot.SpamfilterError as e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s' %
(page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved as error:
pywikibot.output(u'Error putting page: %s' % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)' %
page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
else:
return (text, newtext, always)
def standardizePageFooter(self, text):
"""
Makes sure that interwiki links, categories and star templates are
put to the correct position and into the right order. This combines the
old instances standardizeInterwiki and standardizeCategories
The page footer has the following section in that sequence:
1. categories
2. ## TODO: template beyond categories ##
3. additional information depending on local site policy
4. stars templates for featured and good articles
5. interwiki links
"""
starsList = [
u'bueno',
u'bom interwiki',
u'cyswllt[ _]erthygl[ _]ddethol', u'dolen[ _]ed',
u'destacado', u'destaca[tu]',
u'enllaç[ _]ad',
u'enllaz[ _]ad',
u'leam[ _]vdc',
u'legătură[ _]a[bcf]',
u'liamm[ _]pub',
u'lien[ _]adq',
u'lien[ _]ba',
u'liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt',
u'liên[ _]kết[ _]chọn[ _]lọc',
u'ligam[ _]adq',
u'ligazón[ _]a[bd]',
u'ligoelstara',
u'ligoleginda',
u'link[ _][afgu]a', u'link[ _]adq', u'link[ _]f[lm]', u'link[ _]km',
u'link[ _]sm', u'linkfa',
u'na[ _]lotura',
u'nasc[ _]ar',
u'tengill[ _][úg]g',
u'ua',
u'yüm yg',
u'רא',
u'وصلة مقالة جيدة',
u'وصلة مقالة مختارة',
]
categories = None
interwikiLinks = None
allstars = []
# The PyWikipediaBot is no longer allowed to touch categories on the
# German Wikipedia. See
# https://de.wikipedia.org/wiki/Hilfe_Diskussion:Personendaten/Archiv/1#Position_der_Personendaten_am_.22Artikelende.22
# ignoring nn-wiki of cause of the comment line above iw section
if not self.template and '{{Personendaten' not in text and \
'{{SORTIERUNG' not in text and '{{DEFAULTSORT' not in text and \
self.site.lang not in ('et', 'it', 'bg', 'ru'):
categories = pywikibot.getCategoryLinks(text, site=self.site)
if not self.talkpage: # and pywikibot.calledModuleName() <> 'interwiki':
subpage = False
if self.template:
loc = None
try:
tmpl, loc = moved_links[self.site.lang]
del tmpl
except KeyError:
pass
if loc is not None and loc in self.title:
subpage = True
interwikiLinks = pywikibot.getLanguageLinks(
text, insite=self.site, template_subpage=subpage)
# Removing the interwiki
text = pywikibot.removeLanguageLinks(text, site=self.site)
# Removing the stars' issue
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)'
% star, re.I)
found = regex.findall(starstext)
if found != []:
text = regex.sub('', text)
allstars += found
# Adding categories
if categories:
##Sorting categories in alphabetic order. beta test only on Persian Wikipedia, TODO fix bug for sorting
#if self.site.language() == 'fa':
# categories.sort()
##Taking main cats to top
# for name in categories:
# if re.search(u"(.+?)\|(.{,1}?)",name.title()) or name.title()==name.title().split(":")[0]+title:
# categories.remove(name)
# categories.insert(0, name)
text = pywikibot.replaceCategoryLinks(text, categories,
site=self.site)
# Adding stars templates
if allstars:
text = text.strip() + self.site.family.interwiki_text_separator
allstars.sort()
for element in allstars:
text += '%s%s' % (element.strip(), config.line_separator)
pywikibot.log(u'%s' % element.strip())
# Adding the interwiki
if interwikiLinks:
text = pywikibot.replaceLanguageLinks(text, interwikiLinks,
site=self.site,
template=self.template,
template_subpage=subpage)
return text
def run(self):
"""
Starts the bot.
"""
# Run the generator which will yield Pages which might need to be
# changed.
for page in self.generator:
if self.isTitleExcepted(page.title()):
pywikibot.output(
u'Skipping %s because the title is on the exceptions list.'
% page.title(asLink=True))
continue
try:
# Load the page's text from the wiki
original_text = page.get(get_redirect=True)
if not page.canBeEdited():
pywikibot.output(u"You can't edit page %s" %
page.title(asLink=True))
continue
except pywikibot.NoPage:
pywikibot.output(u'Page %s not found' %
page.title(asLink=True))
continue
new_text = original_text
while True:
if self.isTextExcepted(new_text):
pywikibot.output(u'Skipping %s because it contains text '
u'that is on the exceptions list.' %
page.title(asLink=True))
break
new_text = self.doReplacements(new_text)
if new_text == original_text:
pywikibot.output(u'No changes were necessary in %s' %
page.title(asLink=True))
break
if self.recursive:
newest_text = self.doReplacements(new_text)
while (newest_text != new_text):
new_text = newest_text
newest_text = self.doReplacements(new_text)
if hasattr(self, "addedCat"):
cats = page.categories(nofollow_redirects=True)
if self.addedCat not in cats:
cats.append(self.addedCat)
new_text = pywikibot.replaceCategoryLinks(
new_text, cats)
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(
u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
pywikibot.showDiff(original_text, new_text)
if self.acceptall:
break
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Edit', 'open in Browser', 'All', 'Quit'],
['y', 'N', 'e', 'b', 'a', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(original_text)
# if user didn't press Cancel
if as_edited and as_edited != new_text:
new_text = as_edited
continue
if choice == 'b':
webbrowser.open(
"http://%s%s" %
(page.site.hostname(),
page.site.nice_get_address(page.title(asUrl=True))))
i18n.input('pywikibot-enter-finished-browser')
try:
original_text = page.get(get_redirect=True, force=True)
except pywikibot.NoPage:
pywikibot.output(u'Page %s has been deleted.' %
page.title())
break
new_text = original_text
continue
if choice == 'q':
return
if choice == 'a':
self.acceptall = True
if choice == 'y':
page.put_async(new_text, self.summary)
# choice must be 'N'
break
if self.acceptall and new_text != original_text:
try:
page.put(new_text, self.summary)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict' %
(page.title(), ))
except pywikibot.SpamfilterError as e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s' %
(page.title(), e.url))
except pywikibot.PageNotSaved as error:
pywikibot.output(u'Error putting page: %s' %
(error.args, ))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)' %
(page.title(), ))
def standardizePageFooter(self, text):
"""
Makes sure that interwiki links, categories and star templates are
put to the correct position and into the right order. This combines the
old instances standardizeInterwiki and standardizeCategories
The page footer has the following section in that sequence:
1. categories
2. ## TODO: template beyond categories ##
3. additional information depending on local site policy
4. stars templates for featured and good articles
5. interwiki links
"""
starsList = [
u'bueno',
u'bom interwiki',
u'cyswllt[ _]erthygl[ _]ddethol', u'dolen[ _]ed',
u'destacado', u'destaca[tu]',
u'enllaç[ _]ad',
u'enllaz[ _]ad',
u'leam[ _]vdc',
u'legătură[ _]a[bcf]',
u'liamm[ _]pub',
u'lien[ _]adq',
u'lien[ _]ba',
u'liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt',
u'liên[ _]kết[ _]chọn[ _]lọc',
u'ligam[ _]adq',
u'ligoelstara',
u'ligoleginda',
u'link[ _][afgu]a', u'link[ _]adq', u'link[ _]f[lm]', u'link[ _]km',
u'link[ _]sm', u'linkfa',
u'na[ _]lotura',
u'nasc[ _]ar',
u'tengill[ _][úg]g',
u'ua',
u'yüm yg',
u'רא',
u'وصلة مقالة جيدة',
u'وصلة مقالة مختارة',
]
categories = None
interwikiLinks = None
allstars = []
# The PyWikipediaBot is no longer allowed to touch categories on the
# German Wikipedia. See
# http://de.wikipedia.org/wiki/Hilfe_Diskussion:Personendaten/Archiv/1#Position_der_Personendaten_am_.22Artikelende.22
# ignoring nn-wiki of cause of the comment line above iw section
if not self.template and not '{{Personendaten' in text and \
not '{{SORTIERUNG' in text and not '{{DEFAULTSORT' in text and \
not self.site.lang in ('et', 'it', 'bg', 'ru'):
categories = pywikibot.getCategoryLinks(text, site=self.site)
if not self.talkpage: # and pywikibot.calledModuleName() <> 'interwiki':
subpage = False
if self.template:
loc = None
try:
tmpl, loc = moved_links[self.site.lang]
del tmpl
except KeyError:
pass
if loc is not None and loc in self.title:
subpage = True
interwikiLinks = pywikibot.getLanguageLinks(
text, insite=self.site, template_subpage=subpage)
# Removing the interwiki
text = pywikibot.removeLanguageLinks(text, site=self.site)
# Removing the stars' issue
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)'
% star, re.I)
found = regex.findall(starstext)
if found != []:
text = regex.sub('', text)
allstars += found
# Adding categories
if categories:
##Sorting categories in alphabetic order. beta test only on Persian Wikipedia, TODO fix bug for sorting
#if self.site.language() == 'fa':
# categories.sort()
##Taking main cats to top
# for name in categories:
# if re.search(u"(.+?)\|(.{,1}?)",name.title()) or name.title()==name.title().split(":")[0]+title:
# categories.remove(name)
# categories.insert(0, name)
text = pywikibot.replaceCategoryLinks(text, categories,
site=self.site)
# Adding stars templates
if allstars:
text = text.strip() + self.site.family.interwiki_text_separator
allstars.sort()
for element in allstars:
text += '%s%s' % (element.strip(), config.line_separator)
pywikibot.log(u'%s' %element.strip())
# Adding the interwiki
if interwikiLinks:
text = pywikibot.replaceLanguageLinks(text, interwikiLinks,
site=self.site,
template=self.template,
template_subpage=subpage)
return text
def doall(title, titlep):
global sitep
pywikibot.output("autoCategory: %s, %s" % (title, titlep))
page = wp.Page(title)
if not titlep:
pagep = page.getLang(pywikibot.Site("en"))
else:
pagep = wp.Page(titlep)
sitep = pagep.site
if page.exists():
missingcats = set(page.categories(fromtext=True))
oldtext = page.get()
else:
missingcats = set()
oldtext = ""
oldcats = set(missingcats)
catsp = list(pagep.categories(fromtext=True))
cats = site.getLang(catsp)
for i, catp in enumerate(catsp):
if not cats[i]:
missingcats.add(wp.Category(catp.title()))
if page.namespace() not in wp.conf.nstl:
text = pywikibot.replaceCategoryLinks(oldtext, list(missingcats), site)
else:
return NotImplementedError
if (oldcats != missingcats) or (text == ""):
pywikibot.output(">>> add untranslated categories")
page.put(text or dummytext, u"เพิ่มหมวดหมู่")
data = pywikibot.ItemPage.fromPage(page)
datap = pywikibot.ItemPage.fromPage(pagep)
if (not data.exists()) and (not datap.exists()):
importiw(pagep, page)
elif not datap.exists():
addItem(data, pagep)
elif not data.exists():
addItem(datap, page)
elif data.getID() != datap.getID():
return False
pool = lthread.ThreadPool(10)
if page.isCategory():
doCategory(pool, page, pagep)
for i, catp in enumerate(catsp):
pywikibot.output(catp.title())
if not lre.pats["maintaincat"].search(catp.title()) and cats[i]:
page.add_category([cats[i]])
# doCategory(pool, cats[i], catp)
pool.wait_completion()
text = lre.pats["dummy"].sub("", page.get())
if page.get() != text:
page.put(text, u"ลบข้อความ dummy")
return True
def add_text(page=None, addText=None, summary=None, regexSkip=None,
regexSkipUrl=None, always=False, up=False, putText=True,
oldTextGiven=None, reorderEnabled=True, create=False):
if not addText:
raise NoEnoughData('You have to specify what text you want to add!')
if not summary:
summary = i18n.twtranslate(pywikibot.Site(), 'add_text-adding',
{'adding': addText[:200]})
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
errorCount = 0
site = pywikibot.Site()
pathWiki = site.family.nicepath(site.code)
if putText:
pywikibot.output(u'Loading %s...' % page.title())
if oldTextGiven is None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!"
% page.title())
text = u''
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always)
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always)
else:
text = oldTextGiven
# Understand if the bot has to skip the page or not
# In this way you can use both -except and -excepturl
if regexSkipUrl is not None:
url = '%s%s' % (pathWiki, page.title(asUrl=True))
result = re.findall(regexSkipUrl, site.getUrl(url))
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -exceptUrl is in the page. Skip!
Match was: %s''' % result)
return (False, False, always)
if regexSkip is not None:
result = re.findall(regexSkip, text)
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -except is in the page. Skip!
Match was: %s''' % result)
return (False, False, always)
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace('\\n', config.line_separator)
if (reorderEnabled):
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# Adding the text
newtext += u"%s%s" % (config.line_separator, addText)
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext,
categoriesInside, site,
True)
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)'
% star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub('', newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + config.line_separator * 2
allstars.sort()
for element in allstars:
newtext += '%s%s' % (element.strip(), config.LS)
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside,
site)
else:
newtext += u"%s%s" % (config.line_separator, addText)
else:
newtext = addText + config.line_separator + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if not always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'All', 'open in Browser'],
['y', 'n', 'a', 'b'], 'n')
if choice == 'a':
always = True
elif choice == 'n':
return (False, False, always)
elif choice == 'b':
webbrowser.open("http://%s%s" % (
page.site.hostname(),
page.site.nice_get_address(page.title())
))
pywikibot.input("Press Enter when finished in browser.")
if always or choice == 'y':
try:
if always:
page.put(newtext, summary,
minorEdit=page.namespace() != 3)
else:
page.put_async(newtext, summary,
minorEdit=page.namespace() != 3)
except pywikibot.EditConflict:
pywikibot.output(u'Edit conflict! skip!')
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < config.max_retries:
pywikibot.output(u'Server Error! Wait..')
time.sleep(config.retry_wait)
continue
else:
raise pywikibot.ServerError(u'Fifth Server Error!')
except pywikibot.SpamfilterError as e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved as error:
pywikibot.output(u'Error putting page: %s' % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
else:
return (text, newtext, always)
def run(self):
"""
Starts the robot.
"""
# Run the generator which will yield Pages which might need to be
# changed.
for page in self.generator:
if self.isTitleExcepted(page.title()):
pywikibot.output(
u'Skipping %s because the title is on the exceptions list.'
% page.title(asLink=True))
continue
try:
# Load the page's text from the wiki
original_text = page.get(get_redirect=True)
if not page.canBeEdited():
pywikibot.output(u"You can't edit page %s"
% page.title(asLink=True))
continue
except pywikibot.NoPage:
pywikibot.output(u'Page %s not found' % page.title(asLink=True))
continue
new_text = original_text
while True:
if self.isTextExcepted(new_text):
pywikibot.output(
u'Skipping %s because it contains text that is on the exceptions list.'
% page.title(asLink=True))
break
new_text = self.doReplacements(new_text)
if new_text == original_text:
pywikibot.output(u'No changes were necessary in %s'
% page.title(asLink=True))
break
if self.recursive:
newest_text = self.doReplacements(new_text)
while (newest_text!=new_text):
new_text = newest_text
newest_text = self.doReplacements(new_text)
if hasattr(self, "addedCat"):
cats = page.categories(nofollow_redirects=True)
if self.addedCat not in cats:
cats.append(self.addedCat)
new_text = pywikibot.replaceCategoryLinks(new_text,
cats)
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
pywikibot.showDiff(original_text, new_text)
if self.acceptall:
break
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Edit', 'open in Browser', 'All',
'Quit'],
['y', 'N', 'e', 'b', 'a', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(original_text)
# if user didn't press Cancel
if as_edited and as_edited != new_text:
new_text = as_edited
continue
if choice == 'b':
webbrowser.open("http://%s%s" % (
page.site.hostname(),
page.site.nice_get_address(page.title())
))
i18n.input('pywikibot-enter-finished-browser')
try:
original_text = page.get(get_redirect=True, force=True)
except pywikibot.NoPage:
pywikibot.output(u'Page %s has been deleted.'
% page.title())
break
new_text = original_text
continue
if choice == 'q':
return
if choice == 'a':
self.acceptall = True
if choice == 'y':
page.put_async(new_text, self.summary)
# choice must be 'N'
break
if self.acceptall and new_text != original_text:
try:
page.put(new_text, self.summary)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict'
% (page.title(),))
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
except pywikibot.PageNotSaved, error:
pywikibot.output(u'Error putting page: %s'
% (error.args,))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% (page.title(),))
def run(self):
"""
Starts the robot.
"""
# Run the generator which will yield Pages which might need to be
# changed.
for page in self.generator:
if self.isTitleExcepted(page.title()):
pywikibot.output(
u'Skipping %s because the title is on the exceptions list.'
% page.title(asLink=True))
continue
try:
# Load the page's text from the wiki
original_text = page.get(get_redirect=True)
if not (self.articles or page.canBeEdited()):
pywikibot.output(u"You can't edit page %s"
% page.title(asLink=True))
continue
except pywikibot.NoPage:
pywikibot.output(u'Page %s not found' % page.title(asLink=True))
continue
new_text = original_text
while True:
if self.isTextExcepted(new_text):
pywikibot.output(u'Skipping %s because it contains text '
u'that is on the exceptions list.'
% page.title(asLink=True))
break
new_text = self.doReplacements(new_text)
if new_text == original_text:
pywikibot.output(u'No changes were necessary in %s'
% page.title(asLink=True))
break
if self.recursive:
newest_text = self.doReplacements(new_text)
while newest_text != new_text:
new_text = newest_text
newest_text = self.doReplacements(new_text)
if hasattr(self, "addedCat"):
cats = page.categories()
if self.addedCat not in cats:
cats.append(self.addedCat)
new_text = pywikibot.replaceCategoryLinks(new_text,
cats)
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
pywikibot.showDiff(original_text, new_text)
if self.acceptall:
break
if self.exctitles:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'no+eXcept', 'Edit',
'open in Browser', 'All', 'Quit'],
['y', 'N', 'x', 'e', 'b', 'a', 'q'], 'N')
else:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Edit', 'open in Browser', 'All', 'Quit'],
['y', 'N', 'e', 'b', 'a', 'q'], 'N')
if choice == 'e':
editor = editarticle.TextEditor()
as_edited = editor.edit(original_text)
# if user didn't press Cancel
if as_edited and as_edited != new_text:
new_text = as_edited
continue
if choice == 'b':
webbrowser.open("http://%s%s" % (
page.site.hostname(),
page.site.nice_get_address(page.title())
))
i18n.input('pywikibot-enter-finished-browser')
try:
original_text = page.get(get_redirect=True, force=True)
except pywikibot.NoPage:
pywikibot.output(u'Page %s has been deleted.'
% page.title())
break
new_text = original_text
continue
if choice == 'q':
self.writeEditCounter()
self.writeExceptCounter()
return
if choice == 'a':
self.acceptall = True
if choice == 'x': # May happen only if self.exctitles isn't None
self.exctitles.write(
u"ur'^%s$',\n" % re.escape(page.title()))
self.exctitles.flush()
self.exceptcounter += 1
if choice == 'y':
if not self.articles:
# Primary behaviour: working on wiki
page.put_async(new_text, self.editSummary)
self.editcounter += 1
# Bug: this increments even if put_async fails
# This is separately in two clauses of if for
# future purposes to get feedback form put_async
else:
# Save the title for later processing instead of editing
self.editcounter += 1
self.articles.write(u'#%s\n%s'
% (page.title(asLink=True,
textlink=True),
self.splitLine()))
self.articles.flush() # For the peace of our soul :-)
# choice must be 'N'
break
if self.acceptall and new_text != original_text:
if not self.articles:
#Primary behaviour: working on wiki
try:
page.put(new_text, self.editSummary)
self.editcounter += 1 # increment only on success
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict'
% (page.title(),))
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
except pywikibot.PageNotSaved, error:
pywikibot.error(u'putting page: %s'
% (error.args,))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% (page.title(),))
