def choosecats(pagetext):
chosen = []
flag = False
length = 1000
print("Give the new categories, one per line.")
print("Empty line: if the first, don't change. Otherwise: Ready.")
print("-: I made a mistake, let me start over.")
print("?: Give the text of the page with GUI.")
print("??: Give the text of the page in console.")
print("xx: if the first, remove all categories and add no new.")
print("q: quit.")
while flag == False:
choice = pywikibot.input(u"?")
if choice == "":
flag = True
elif choice == "-":
chosen = choosecats(pagetext)
flag = True
elif choice == "?":
import editarticle
editor = editarticle.TextEditor()
newtext = editor.edit(pagetext)
elif choice == "??":
pywikibot.output(pagetext[0:length])
length = length + 500
elif choice == "xx" and chosen == []:
chosen = None
flag = True
elif choice == "q":
print "quit..."
sys.exit()
else:
chosen.append(choice)
return chosen
def handleNextLink(self, text, match, context=100):
"""
Returns a tuple (text, jumpToBeginning).
text is the unicode string after the current link has been processed.
jumpToBeginning is a boolean which specifies if the cursor position
should be reset to 0. This is required after the user has edited the
article.
"""
# ignore interwiki links and links to sections of the same page as well
# as section links
if not match.group('title') \
or self.pageToUnlink.site().isInterwikiLink(match.group('title')) \
or match.group('section'):
return text, False
linkedPage = pywikibot.Page(self.pageToUnlink.site(),
match.group('title'))
# Check whether the link found is to the current page itself.
if linkedPage != self.pageToUnlink:
# not a self-link
return text, False
else:
# at the beginning of the link, start red color.
# at the end of the link, reset the color to default
if self.always:
choice = 'a'
else:
pywikibot.output(
text[max(0, match.start() - context):match.start()]
+ '\03{lightred}' + text[match.start():match.end()]
+ '\03{default}' + text[match.end():match.end() + context])
choice = pywikibot.inputChoice(
u'\nWhat shall be done with this link?\n',
['unlink', 'skip', 'edit', 'more context',
'unlink all', 'quit'],
['U', 's', 'e', 'm', 'a', 'q'], 'u')
pywikibot.output(u'')
if choice == 's':
# skip this link
return text, False
elif choice == 'e':
editor = editarticle.TextEditor()
newText = editor.edit(text, jumpIndex=match.start())
# if user didn't press Cancel
if newText:
return newText, True
else:
return text, True
elif choice == 'm':
# show more context by recursive self-call
return self.handleNextLink(text, match,
context=context + 100)
elif choice == 'a':
self.always = True
elif choice == 'q':
self.done = True
return text, False
new = match.group('label') or match.group('title')
new += match.group('linktrail')
return text[:match.start()] + new + text[match.end():], False
def process_filename(self):
# Isolate the pure name
filename = self.url
if '/' in filename:
filename = filename.split('/')[-1]
if '\\' in filename:
filename = filename.split('\\')[-1]
if self.urlEncoding:
filename = urllib.unquote(filename.decode(self.urlEncoding))
if self.useFilename:
filename = self.useFilename
if not self.keepFilename:
wikipedia.output(u"The filename on the target wiki will default to: %s" % filename)
# ask newfn until it's valid
ok = False
# FIXME: these 2 belong somewhere else, presumably in family
forbidden = '/' # to be extended
allowed_formats = (u'gif', u'jpg', u'jpeg', u'mid', u'midi', u'ogg', u'png', u'svg', u'xcf', u'djvu')
while not ok:
ok = True
newfn = wikipedia.input(u'Enter a better name, or press enter to accept:')
if newfn == "":
newfn = filename
ext = os.path.splitext(newfn)[1].lower().strip('.')
for c in forbidden:
if c in newfn:
print "Invalid character: %s. Please try again" % c
ok = False
if ext not in allowed_formats and ok:
choice = wikipedia.inputChoice(u"File format is not one of [%s], but %s. Continue?" % (u' '.join(allowed_formats), ext), ['yes', 'no'], ['y', 'N'], 'N')
if choice == 'n':
ok = False
if newfn != '':
filename = newfn
# MediaWiki doesn't allow spaces in the file name.
# Replace them here to avoid an extra confirmation form
filename = filename.replace(' ', '_')
# A proper description for the submission.
wikipedia.output(u"The suggested description is:")
wikipedia.output(self.description)
if self.verifyDescription:
newDescription = u''
choice = wikipedia.inputChoice(u'Do you want to change this description?', ['Yes', 'No'], ['y', 'N'], 'n')
if choice == 'y':
import editarticle
editor = editarticle.TextEditor()
newDescription = editor.edit(self.description)
# if user saved / didn't press Cancel
if newDescription:
self.description = newDescription
return filename
def showQuest(site, page):
quest = pywikibot.inputChoice(u'Do you want to open the page?',
['with browser', 'with gui', 'no'],
['b','g','n'], 'n')
pathWiki = site.family.nicepath(site.lang)
url = 'http://%s%s%s?&redirect=no' % (pywikibot.getSite().hostname(), pathWiki, page.urlname())
if quest == 'b':
webbrowser.open(url)
elif quest == 'g':
import editarticle
editor = editarticle.TextEditor()
text = editor.edit(page.get())
def process_filename(self):
"""Return base filename portion of self.url"""
# Isolate the pure name
filename = self.url
# Filename may be either a local file path or a URL
if '/' in filename:
filename = filename.split('/')[-1]
if '\\' in filename:
filename = filename.split('\\')[-1]
if self.urlEncoding:
filename = urllib.unquote(filename.decode(self.urlEncoding))
if self.useFilename:
filename = self.useFilename
if not self.keepFilename:
pywikibot.output(
u"The filename on the target wiki will default to: %s" %
filename)
ok = False
ext = os.path.splitext(filename)[1].lower().strip('.')
# FIXME: these 2 belong somewhere else, presumably in family
forbidden = '/' # to be extended
allowed_formats = (u'gif', u'jpg', u'jpeg', u'mid', u'midi',
u'ogg', u'png', u'svg', u'xcf', u'djvu', u'ogv',
u'oga', u'tif', u'tiff')
# ask until it's valid
ok = True
filename = tempfile.gettempprefix()
# MediaWiki doesn't allow spaces in the file name.
# Replace them here to avoid an extra confirmation form
filename = filename.replace(' ', '_')
# A proper description for the submission.
pywikibot.output(u"The suggested description is:")
pywikibot.output(self.description)
if self.verifyDescription:
newDescription = u''
choice = pywikibot.inputChoice(
u'Do you want to change this description?', ['Yes', 'No'],
['y', 'N'], 'n')
if choice == 'y':
import editarticle
editor = editarticle.TextEditor()
newDescription = editor.edit(self.description)
# if user saved / didn't press Cancel
if newDescription:
self.description = newDescription
return filename
def spellcheck(page, checknames=True, knownonly=False, title=''):
pageskip = []
text = page
if correct_html_codes:
text = removeHTML(text)
loc = 0
while True:
wordsearch = re.compile(r'([\s\=\<\>\_]*)([^\s\=\<\>\_]+)')
match = wordsearch.search(text, loc)
if not match:
# No more words on this page
break
loc += len(match.group(1))
bigword = Word(match.group(2))
smallword = bigword.derive()
if not Word(smallword).isCorrect(checkalternative=knownonly) and \
(checknames or not smallword[0].isupper()):
replacement = askAlternative(
smallword,
context=text[max(0, loc - 40):loc + len(match.group(2)) + 40],
title=title)
if replacement == edit:
import editarticle
editor = editarticle.TextEditor()
# TODO: Don't know to which index to jump
newtxt = editor.edit(text, jumpIndex=0, highlight=smallword)
if newtxt:
text = newtxt
elif replacement == endpage:
loc = len(text)
else:
replacement = bigword.replace(replacement)
text = text[:loc] + replacement + text[loc +
len(match.group(2)):]
loc += len(replacement)
if knownonly == 'plus' and text != page:
knownonly = False
loc = 0
else:
loc += len(match.group(2))
if correct_html_codes:
text = removeHTML(text)
pageskip = []
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 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
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())))
pywikibot.input("Press Enter when finished in browser.")
original_text = page.get(get_redirect=True, force=True)
new_text = original_text
continue
if choice == 'q':
self.writeEditCounter()
return
if choice == 'a':
self.acceptall = True
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), 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.output(u'Error putting page: %s' %
(error.args, ))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)' %
(page.title(), ))
class SelflinkBot:
def __init__(self, generator, always=False):
self.generator = generator
linktrail = pywikibot.getSite().linktrail()
# The regular expression which finds links. Results consist of four groups:
# group title is the target page title, that is, everything before | or ].
# group section is the page section. It'll include the # to make life easier for us.
# group label is the alternative link title, that's everything between | and ].
# group linktrail is the link trail, that's letters after ]] which are part of the word.
# note that the definition of 'letter' varies from language to language.
self.linkR = re.compile(
r'\[\[(?P<title>[^\]\|#]*)(?P<section>#[^\]\|]*)?(\|(?P<label>[^\]]*))?\]\](?P<linktrail>'
+ linktrail + ')')
self.always = always
self.done = False
def handleNextLink(self, page, text, match, context=100):
"""
Returns a tuple (text, jumpToBeginning).
text is the unicode string after the current link has been processed.
jumpToBeginning is a boolean which specifies if the cursor position
should be reset to 0. This is required after the user has edited the
article.
"""
# ignore interwiki links and links to sections of the same page as well
# as section links
if not match.group('title') \
or page.site().isInterwikiLink(match.group('title')) \
or match.group('section'):
return text, False
try:
linkedPage = pywikibot.Page(page.site(), match.group('title'))
except pywikibot.InvalidTitle, err:
pywikibot.warning(u'%s' % err)
return text, False
# Check whether the link found is to the current page itself.
if linkedPage != page:
# not a self-link
return text, False
else:
# at the beginning of the link, start red color.
# at the end of the link, reset the color to default
if self.always:
choice = 'a'
else:
pywikibot.output(
text[max(0, match.start() - context):match.start()] \
+ '\03{lightred}' + text[match.start():match.end()] \
+ '\03{default}' + text[match.end():match.end() + context])
choice = pywikibot.inputChoice(
u'\nWhat shall be done with this selflink?\n', [
'unlink', 'make bold', 'skip', 'edit', 'more context',
'unlink all', 'quit'
], ['U', 'b', 's', 'e', 'm', 'a', 'q'], 'u')
pywikibot.output(u'')
if choice == 's':
# skip this link
return text, False
elif choice == 'e':
editor = editarticle.TextEditor()
newText = editor.edit(text, jumpIndex=match.start())
# if user didn't press Cancel
if newText:
return newText, True
else:
return text, True
elif choice == 'm':
# show more context by recursive self-call
return self.handleNextLink(page,
text,
match,
context=context + 100)
elif choice == 'a':
self.always = True
elif choice == 'q':
self.done = True
return text, False
new = match.group('label') or match.group('title')
new += match.group('linktrail')
if choice == 'b':
# make bold
return text[:match.start(
)] + "'''" + new + "'''" + text[match.end():], False
else:
return text[:match.start()] + new + text[match.end():], False
def handlebadpage(self):
try:
self.content = self.page.get()
except pywikibot.IsRedirectPage:
pywikibot.output(u'Already redirected, skipping.')
return
except pywikibot.NoPage:
pywikibot.output(u'Already deleted')
return
for d in pywikibot.translate(pywikibot.getSite(), done):
if d in self.content:
pywikibot.output(
u'Found: "%s" in content, nothing necessary' % d)
return
print "---- Start content ----------------"
pywikibot.output(u"%s" % self.content)
print "---- End of content ---------------"
# Loop other user answer
answered = False
while not answered:
answer = pywikibot.input(question)
if answer == 'q':
sys.exit("Exiting")
if answer == 'd':
pywikibot.output(u'Trying to delete page [[%s]].'
% self.page.title())
self.page.delete()
return
if answer == 'e':
oldText = self.page.get()
text = oldText
editor = editarticle.TextEditor()
text = editor.edit(self.page.get())
if oldText != text:
pywikibot.showDiff(oldText, text)
msg = pywikibot.input(u'Summary message:')
self.page.put(text, msg)
return
if answer == 'b':
pywikibot.output(u'Blanking page [[%s]].' % self.page.title())
try:
self.page.put('',
comment=pywikibot.translate(
pywikibot.getSite(), blanking)
% self.content)
except EditConflict:
print "An edit conflict occured ! Automatically retrying"
handlebadpage(self)
return
if answer == '':
print 'Page correct ! Proceeding with next pages.'
return
# Check user input:
if answer[0] == 'u':
# Answer entered as an utf8 string
try:
choices = answer[1:].split(',')
except ValueError:
# User entered wrong value
pywikibot.error(u'"%s" is not valid' % answer)
continue
else:
try:
choices = answer.split(',')
except ValueError:
# User entered wrong value
pywikibot.error(u'"%s" is not valid' % answer)
continue
#test input
for choice in choices:
try:
x = int(choice)
except ValueError:
break
else:
answered = x in range(1, len(questionlist)+1)
if not answered:
pywikibot.error(u'"%s" is not valid' % answer)
continue
summary = u''
for choice in choices:
answer = int(choice)
# grab the template parameters
tpl = pywikibot.translate(pywikibot.getSite(),
templates)[questionlist[answer]]
if tpl['pos'] == 'top':
pywikibot.output(u'prepending %s...' % questionlist[answer])
self.content = questionlist[answer] + '\n' + self.content
elif tpl['pos'] == 'bottom':
pywikibot.output(u'appending %s...' % questionlist[answer])
self.content += '\n' + questionlist[answer]
else:
pywikibot.error(
u'"pos" should be "top" or "bottom" for template '
u'%s. Contact a developer.' % questionlist[answer])
sys.exit("Exiting")
summary += tpl['msg']+' '
pywikibot.output(u'Probably added %s' % questionlist[answer])
# pywikibot.output(newcontent) bug #2986247
self.page.put(self.content, comment=summary)
pywikibot.output(u'with comment %s\n' % summary)
def treat(self, refPage, disambPage):
"""
Parameters:
disambPage - The disambiguation page or redirect we don't want
anything to link to
refPage - A page linking to disambPage
Returns False if the user pressed q to completely quit the program.
Otherwise, returns True.
"""
# TODO: break this function up into subroutines!
dn_template_str = pywikibot.translate(self.mysite, dn_template)
include = False
unlink = False
new_targets = []
try:
text = refPage.get(throttle=False)
ignoreReason = self.checkContents(text)
if ignoreReason:
pywikibot.output(
'\n\nSkipping %s because it contains %s.\n\n' %
(refPage.title(), ignoreReason))
else:
include = True
except pywikibot.IsRedirectPage:
pywikibot.output(u'%s is a redirect to %s' %
(refPage.title(), disambPage.title()))
if disambPage.isRedirectPage():
target = self.alternatives[0]
choice = pywikibot.inputChoice(
u'Do you want to make redirect %s point to %s?' %
(refPage.title(), target), ['yes', 'no'], ['y', 'N'], 'N')
if choice == 'y':
redir_text = '#%s [[%s]]' \
% (self.mysite.redirect(default=True), target)
try:
refPage.put_async(redir_text, comment=self.comment)
except pywikibot.PageNotSaved as error:
pywikibot.output(u'Page not saved: %s' % error.args)
else:
choice = pywikibot.inputChoice(
u'Do you want to work on pages linking to %s?' %
refPage.title(), ['yes', 'no', 'change redirect'],
['y', 'N', 'c'], 'N')
if choice == 'y':
gen = ReferringPageGeneratorWithIgnore(
refPage, self.primary)
preloadingGen = pagegenerators.PreloadingGenerator(gen)
for refPage2 in preloadingGen:
# run until the user selected 'quit'
if not self.treat(refPage2, refPage):
break
elif choice == 'c':
text = refPage.get(throttle=False, get_redirect=True)
include = "redirect"
except pywikibot.NoPage:
pywikibot.output(
u'Page [[%s]] does not seem to exist?! Skipping.' %
refPage.title())
include = False
if include in (True, "redirect"):
# make a backup of the original text so we can show the changes later
original_text = text
n = 0
curpos = 0
dn = False
edited = False
# This loop will run until we have finished the current page
while True:
m = self.linkR.search(text, pos=curpos)
if not m:
if n == 0:
pywikibot.output(u"No changes necessary in %s" %
refPage.title())
return True
else:
# stop loop and save page
break
# Make sure that next time around we will not find this same hit.
curpos = m.start() + 1
# ignore interwiki links and links to sections of the same page
if m.group('title') == '' or self.mysite.isInterwikiLink(
m.group('title')):
continue
else:
try:
linkPage = pywikibot.Page(disambPage.site(),
m.group('title'))
# Check whether the link found is to disambPage.
except pywikibot.InvalidTitle:
continue
if linkPage != disambPage:
continue
n += 1
# how many bytes should be displayed around the current link
context = 60
#there's a {{dn}} here already
already_dn = text[m.end():m.end() + 8].find(
dn_template_str[:4]) > -1
if already_dn and self.dnSkip:
continue
# This loop will run while the user doesn't choose an option
# that will actually change the page
while True:
# Show the title of the page where the link was found.
# Highlight the title in purple.
pywikibot.output(
u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
refPage.title())
if not self.always:
# at the beginning of the link, start red color.
# at the end of the link, reset the color to default
pywikibot.output(text[max(0,
m.start() -
context):m.start()] +
'\03{lightred}' +
text[m.start():m.end()] +
'\03{default}' +
text[m.end():m.end() + context])
if edited:
choice = pywikibot.input(
u"Option (#, r#, [s]kip link, [e]dit page, [n]ext page, [u]nlink, [q]uit,\n"
u" [t]ag template " + dn_template_str +
",\n"
u" [m]ore context, [l]ist, [a]dd new, x=save in this form):"
)
else:
choice = pywikibot.input(
u"Option (#, r#, [s]kip link, [e]dit page, [n]ext page, [u]nlink, [q]uit,\n"
u" [t]ag template " + dn_template_str +
",\n"
u" [m]ore context, show [d]isambiguation page, [l]ist, [a]dd new):"
)
else:
choice = self.always
if choice in ['a', 'A']:
newAlternative = pywikibot.input(u'New alternative:')
self.alternatives.append(newAlternative)
self.listAlternatives()
elif choice in ['e', 'E']:
editor = editarticle.TextEditor()
newText = editor.edit(text,
jumpIndex=m.start(),
highlight=disambPage.title())
# if user didn't press Cancel
if newText and newText != text:
text = newText
break
elif choice in ['d', 'D']:
editor = editarticle.TextEditor()
if disambPage.isRedirectPage():
disambredir = disambPage.getRedirectTarget()
disambigText = editor.edit(
disambredir.get(),
jumpIndex=m.start(),
highlight=disambredir.title())
else:
editor.edit(disambPage.get(),
jumpIndex=m.start(),
highlight=disambPage.title())
elif choice in ['l', 'L']:
self.listAlternatives()
elif choice in ['m', 'M']:
# show more text around the link we're working on
context *= 2
else:
break
if choice in ['e', 'E']:
# user has edited the page and then pressed 'OK'
edited = True
curpos = 0
continue
elif choice in ['n', 'N']:
# skip this page
if self.primary:
# If run with the -primary argument, skip this
# occurence next time.
self.primaryIgnoreManager.ignore(refPage)
return True
elif choice in ['q', 'Q']:
# quit the program
return False
elif choice in ['s', 'S']:
# Next link on this page
n -= 1
continue
elif choice in ['x', 'X'] and edited:
# Save the page as is
break
# The link looks like this:
# [[page_title|link_text]]trailing_chars
page_title = m.group('title')
link_text = m.group('label')
if not link_text:
# or like this: [[page_title]]trailing_chars
link_text = page_title
if m.group('section') is None:
section = ''
else:
section = m.group('section')
trailing_chars = m.group('linktrail')
if trailing_chars:
link_text += trailing_chars
# '?', '/' for old choice
if choice in ['t', 'T', '?', '/']:
# small chunk of text to search
search_text = text[m.end():m.end() + context]
# figure out where the link (and sentance) ends, put note
# there
end_of_word_match = re.search("\s", search_text)
if end_of_word_match:
position_split = end_of_word_match.start(0)
else:
position_split = 0
#insert dab needed template
text = (text[:m.end() + position_split] + dn_template_str +
text[m.end() + position_split:])
dn = True
continue
elif choice in ['u', 'U']:
# unlink - we remove the section if there's any
text = text[:m.start()] + link_text + text[m.end():]
unlink = True
continue
else:
if len(choice) > 0 and choice[0] == 'r':
# we want to throw away the original link text
replaceit = True
choice = choice[1:]
elif include == "redirect":
replaceit = True
else:
replaceit = False
try:
choice = int(choice)
except ValueError:
pywikibot.output(u"Unknown option")
# step back to ask the user again what to do with the
# current link
curpos -= 1
continue
if choice >= len(self.alternatives) or choice < 0:
pywikibot.output(
u"Choice out of range. Please select a number "
u"between 0 and %i." %
(len(self.alternatives) - 1))
# show list of possible choices
self.listAlternatives()
# step back to ask the user again what to do with the
# current link
curpos -= 1
continue
new_page_title = self.alternatives[choice]
repPl = pywikibot.Page(disambPage.site(), new_page_title)
if (new_page_title[0].isupper() or link_text[0].isupper()):
new_page_title = repPl.title()
else:
new_page_title = repPl.title()
new_page_title = (new_page_title[0].lower() +
new_page_title[1:])
if new_page_title not in new_targets:
new_targets.append(new_page_title)
if replaceit and trailing_chars:
newlink = "[[%s%s]]%s" % (new_page_title, section,
trailing_chars)
elif replaceit or (new_page_title == link_text
and not section):
newlink = "[[%s]]" % new_page_title
# check if we can create a link with trailing characters
# instead of a pipelink
elif ((len(new_page_title) <= len(link_text))
and (firstcap(link_text[:len(new_page_title)])
== firstcap(new_page_title))
and (re.sub(self.trailR, '',
link_text[len(new_page_title):]) == '')
and (not section)):
newlink = "[[%s]]%s" \
% (link_text[:len(new_page_title)],
link_text[len(new_page_title):])
else:
newlink = "[[%s%s|%s]]" \
% (new_page_title, section, link_text)
text = text[:m.start()] + newlink + text[m.end():]
continue
pywikibot.output(text[max(0, m.start() - 30):m.end() + 30])
if text == original_text:
pywikibot.output(u'\nNo changes have been made:\n')
else:
pywikibot.output(u'\nThe following changes have been made:\n')
pywikibot.showDiff(original_text, text)
pywikibot.output(u'')
# save the page
self.setSummaryMessage(disambPage, new_targets, unlink, dn)
try:
refPage.put_async(text, comment=self.comment)
except pywikibot.LockedPage:
pywikibot.output(u'Page not saved: page is locked')
except pywikibot.PageNotSaved as error:
pywikibot.output(u'Page not saved: %s' % error.args)
return True
def main():
automatic = False
namespaces = []
msg = {
'ar': u'إزالة الوصلات إلى موقع سبام %s',
'de': u'Entferne in Spam-Blacklist eingetragenen Weblink auf %s',
'en': u'Removing links to spamming site %s',
'es': u'Removiendo enlaces a sitio publicitario %s',
'fa': u'حذف پیوند به وبگاه هرزنگاری %s',
'he': u'מסיר קישורים לאתר ספאם %s',
'fr': u'Suppression du lien blacklisté %s',
'it': u'Rimuovo link contenuto nella Spam-Blacklist %s',
'ja': u'ロボットによる: 迷惑リンク削除 %s',
'nl': u'Links naar gespamde site: %s verwijderd',
'pt': u'Removendo links de spam do site %s',
'ta': u'எரிதமாக இணைக்கப்பட்ட %s இணையத்தளம் நீக்கப்பட்டது',
'vi': u'xóa các liên kết đến website spam %s',
'zh': u'機器人: 移除廣告黑名單連結 %s',
}
spamSite = ''
for arg in pywikibot.handleArgs():
if arg.startswith("-automatic"):
automatic = True
elif arg.startswith('-namespace:'):
try:
namespaces.append(int(arg[len('-namespace:'):]))
except ValueError:
namespaces.append(arg[len('-namespace:'):])
else:
spamSite = arg
if not automatic:
pywikibot.put_throttle.setDelay(1)
if not spamSite:
pywikibot.showHelp('spamremove')
pywikibot.output(u"No spam site specified.")
sys.exit()
mysite = pywikibot.getSite()
pages = list(set(mysite.linksearch(spamSite)))
if namespaces:
pages = list(
set(pagegenerators.NamespaceFilterPageGenerator(pages,
namespaces)))
if len(pages) == 0:
pywikibot.output('No page found.')
else:
pywikibot.getall(mysite, pages)
for p in pages:
text = p.get()
if spamSite not in text:
continue
# 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} <<<" %
p.title())
lines = text.split('\n')
newpage = []
lastok = ""
for line in lines:
if spamSite in line:
if lastok:
pywikibot.output(lastok)
pywikibot.output('\03{lightred}%s\03{default}' % line)
lastok = None
else:
newpage.append(line)
if line.strip():
if lastok is None:
pywikibot.output(line)
lastok = line
if automatic:
answer = "y"
else:
answer = pywikibot.inputChoice(u'\nDelete the red lines?',
['yes', 'no', 'edit'],
['y', 'N', 'e'], 'n')
if answer == "n":
continue
elif answer == "e":
editor = editarticle.TextEditor()
newtext = editor.edit(text,
highlight=spamSite,
jumpIndex=text.find(spamSite))
else:
newtext = "\n".join(newpage)
if newtext != text:
p.put(newtext, pywikibot.translate(mysite, msg) % spamSite)
