def workon(page):
mysite = wikipedia.getSite()
try:
text = page.get()
except wikipedia.IsRedirectPage:
wikipedia.output(u'%s is a redirect page. Skipping' % page.aslink())
return
except wikipedia.NoPage:
wikipedia.output(u'%s does not exist. Skipping' % page.aslink())
return
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
links = page.linkedPages()
if len(links) > 0:
wikipedia.getall(mysite,links)
else:
wikipedia.output('Nothing left to do.')
return
for page2 in links:
try:
target = page2.getRedirectTarget()
except (wikipedia.Error,wikipedia.SectionError):
continue
text = treat(text, page2, target)
if text != page.get():
comment = wikipedia.translate(mysite, msg)
wikipedia.showDiff(page.get() ,text)
try:
page.put(text, comment)
except (wikipedia.Error):
wikipedia.output('Error: unable to put %s' % page.aslink())
def oneQuery(self):
"""Perform one step in the solution process"""
# First find the best language to work on
code = self.selectQueryCode()
if code == None:
print "NOTE: Nothing left to do"
return False
# Now assemble a reasonable list of pages to get
group = []
plgroup = []
for subj in self.subjects:
# Promise the subject that we will work on the code language
# We will get a list of pages we can do.
x = subj.willWorkOn(code)
if x:
plgroup.extend(x)
group.append(subj)
if len(plgroup)>=globalvar.maxquerysize:
break
if len(plgroup) == 0:
print "NOTE: Nothing left to do 2"
return False
# Get the content of the assembled list in one blow
try:
wikipedia.getall(code, plgroup)
except wikipedia.SaxError:
# Ignore this error, and get the pages the traditional way.
pass
# Tell all of the subjects that the promised work is done
for subj in group:
subj.workDone(self)
return True
def workon(page):
mysite = pywikibot.getSite()
try:
text = page.get()
except pywikibot.IsRedirectPage:
pywikibot.output(u'%s is a redirect page. Skipping'
% page.title(asLink=True))
return
except pywikibot.NoPage:
pywikibot.output(u'%s does not exist. Skipping'
% page.title(asLink=True))
return
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
links = page.linkedPages()
if len(links) > 0:
pywikibot.getall(mysite,links)
else:
pywikibot.output('Nothing left to do.')
return
for page2 in links:
try:
target = page2.getRedirectTarget()
except (pywikibot.Error,pywikibot.SectionError):
continue
text = treat(text, page2, target)
if text != page.get():
comment = i18n.twtranslate(mysite, 'fixing_redirects-fixing')
pywikibot.showDiff(page.get() ,text)
try:
page.put(text, comment)
except (pywikibot.Error):
pywikibot.output('Error: unable to put %s'
% page.title(asLink=True))
def workon(page):
mysite = pywikibot.getSite()
try:
text = page.get()
except pywikibot.IsRedirectPage:
pywikibot.output(u'%s is a redirect page. Skipping' %
page.title(asLink=True))
return
except pywikibot.NoPage:
pywikibot.output(u'%s does not exist. Skipping' %
page.title(asLink=True))
return
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
links = page.linkedPages()
if len(links) > 0:
pywikibot.getall(mysite, links)
else:
pywikibot.output('Nothing left to do.')
return
for page2 in links:
try:
target = page2.getRedirectTarget()
except (pywikibot.Error, pywikibot.SectionError):
continue
text = treat(text, page2, target)
if text != page.get():
comment = pywikibot.translate(mysite, msg)
pywikibot.showDiff(page.get(), text)
try:
page.put(text, comment)
except (pywikibot.Error):
pywikibot.output('Error: unable to put %s' %
page.title(asLink=True))
def main():
global mysite, linktrail, page
start = []
for arg in wikipedia.handleArgs():
start.append(arg)
if start:
start = " ".join(start)
else:
start = "!"
mysite = wikipedia.getSite()
linktrail = mysite.linktrail()
try:
generator = pagegenerators.CategorizedPageGenerator(
mysite.disambcategory(), start=start)
except wikipedia.NoPage:
print "The bot does not know the disambiguation category for your wiki."
raise
# only work on articles
generator = pagegenerators.NamespaceFilterPageGenerator(generator, [0])
generator = pagegenerators.PreloadingGenerator(generator)
pagestodo = []
pagestoload = []
for page in generator:
if page.isRedirectPage():
continue
linked = page.linkedPages()
pagestodo.append((page, linked))
pagestoload += linked
if len(pagestoload) > 49:
wikipedia.getall(mysite, pagestoload)
for page, links in pagestodo:
workon(page, links)
pagestoload = []
pagestodo = []
def main():
global mysite, linktrail, page
start = []
for arg in wikipedia.handleArgs():
start.append(arg)
if start:
start = " ".join(start)
else:
start = "!"
mysite = wikipedia.getSite()
linktrail = mysite.linktrail()
try:
generator = pagegenerators.CategorizedPageGenerator(mysite.disambcategory(), start = start)
except wikipedia.NoPage:
print "The bot does not know the disambiguation category for your wiki."
raise
# only work on articles
generator = pagegenerators.NamespaceFilterPageGenerator(generator, [0])
generator = pagegenerators.PreloadingGenerator(generator)
pagestodo = []
pagestoload = []
for page in generator:
if page.isRedirectPage():
continue
linked = page.linkedPages()
pagestodo.append((page,linked))
pagestoload += linked
if len(pagestoload) > 49:
wikipedia.getall(mysite,pagestoload)
for page, links in pagestodo:
workon(page,links)
pagestoload = []
pagestodo = []
def testSite(site):
try:
wikipedia.getall(site, [wikipedia.Page(site, 'Any page name')])
except KeyboardInterrupt:
raise
except wikipedia.NoSuchSite:
wikipedia.output( u'No such language %s' % site.lang )
except:
wikipedia.output( u'Error processing language %s' % site.lang )
wikipedia.output( u''.join(traceback.format_exception(*sys.exc_info())))
def testSite(site):
try:
wikipedia.getall(site, [wikipedia.Page(site, "Any page name")])
except KeyboardInterrupt:
raise
except wikipedia.NoSuchSite:
wikipedia.output(u"No such language %s" % site.lang)
except:
wikipedia.output(u"Error processing language %s" % site.lang)
wikipedia.output(u"".join(traceback.format_exception(*sys.exc_info())))
def testSite(site):
try:
pywikibot.getall(site, [pywikibot.Page(site, 'Any page name')])
except KeyboardInterrupt:
raise
except pywikibot.NoSuchSite:
pywikibot.output( u'No such language %s' % site.lang )
except:
pywikibot.output( u'Error processing language %s' % site.lang )
pywikibot.output( u''.join(traceback.format_exception(*sys.exc_info())))
def workon(page):
mysite = pywikibot.getSite()
try:
text = page.get()
except pywikibot.IsRedirectPage:
pywikibot.output(u'%s is a redirect page. Skipping' % page)
return
except pywikibot.NoPage:
pywikibot.output(u'%s does not exist. Skipping' % page)
return
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
links = page.linkedPages()
if len(links) > 0:
pywikibot.getall(mysite,links)
else:
pywikibot.output('Nothing left to do.')
return
for page2 in links:
try:
target = page2.getRedirectTarget()
except pywikibot.NoPage:
gen = mysite.logpages(number=1, mode='move', title=page2.title(),
dump=True)
try:
lastmove = gen.next()['move']
except StopIteration:
continue
target = pywikibot.Page(mysite, lastmove['new_title'])
except (pywikibot.Error, pywikibot.SectionError):
continue
# no fix to user namespaces
if target.namespace() in [0, 1] and not page2.namespace() in [0, 1]:
continue
text = treat(text, page2, target)
if text != page.get():
comment = i18n.twtranslate(mysite, 'fixing_redirects-fixing')
pywikibot.showDiff(page.get(), text)
try:
page.put(text, comment)
except (pywikibot.Error):
pywikibot.output('Error: unable to put %s' % page)
def workon(page):
mysite = pywikibot.getSite()
try:
text = page.get()
except pywikibot.IsRedirectPage:
pywikibot.output(u'%s is a redirect page. Skipping' % page)
return
except pywikibot.NoPage:
pywikibot.output(u'%s does not exist. Skipping' % page)
return
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
links = page.linkedPages()
if len(links):
pywikibot.getall(mysite, links)
else:
pywikibot.output('Nothing left to do.')
return
for page2 in links:
try:
target = page2.getRedirectTarget()
except pywikibot.NoPage:
try:
target = page2.getMovedTarget()
except pywikibot.NoPage:
continue
target = pywikibot.Page(mysite, lastmove['new_title'])
except (pywikibot.Error, pywikibot.SectionError):
continue
# no fix to user namespaces
if target.namespace() in [0, 1] and not page2.namespace() in [0, 1]:
continue
text = treat(text, page2, target)
if text != page.get():
comment = i18n.twtranslate(mysite, 'fixing_redirects-fixing')
pywikibot.showDiff(page.get(), text)
try:
page.put(text, comment)
except (pywikibot.Error):
pywikibot.error('unable to put %s' % page)
def preload(self, page_list, retry=False):
try:
while len(page_list) > 0:
# It might be that the pages are on different sites,
# e.g. because the -interwiki parameter was used.
# Query the sites one by one.
site = page_list[0].site()
pagesThisSite = [page for page in page_list if page.site() == site]
page_list = [page for page in page_list if page.site() != site]
pywikibot.getall(site, pagesThisSite)
for page in pagesThisSite:
yield page
except IndexError:
# Can happen if the pages list is empty. Don't care.
pass
except pywikibot.SaxError:
if not retry:
# Retry once.
self.preload(page_list, retry=True)
# Ignore this error, and get the pages the traditional way later.
pass
def workon(page):
mysite = wikipedia.getSite()
try:
text = page.get()
except wikipedia.IsRedirectPage:
return
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
links = page.linkedPages()
wikipedia.getall(mysite,links)
for page2 in links:
try:
target = page2.getRedirectTarget()
except (wikipedia.Error,wikipedia.SectionError):
continue
text = treat(text, page2, target)
if text != page.get():
comment = wikipedia.translate(mysite, msg)
try:
page.put(text, comment)
except (wikipedia.Error):
wikipedia.output('Error : unable to put %s' % page.aslink())
def preload(self, page_list, retry=False):
try:
while len(page_list) > 0:
# It might be that the pages are on different sites,
# e.g. because the -interwiki parameter was used.
# Query the sites one by one.
site = page_list[0].site()
pagesThisSite = [
page for page in page_list if page.site() == site
]
page_list = [page for page in page_list if page.site() != site]
wikipedia.getall(site, pagesThisSite)
for page in pagesThisSite:
yield page
except IndexError:
# Can happen if the pages list is empty. Don't care.
pass
except wikipedia.SaxError:
if not retry:
# Retry once.
self.preload(page_list, retry=True)
# Ignore this error, and get the pages the traditional way later.
pass
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 not spamSite 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)
exclude(line, real_exclude=False)
pl = pywikibot.Page(mysite, line)
checked[pl] = pl
f.close()
excludefile = codecs.open(filename, 'a', encoding=mysite.encoding())
except IOError:
# File does not exist
excludefile = codecs.open(filename, 'w', encoding=mysite.encoding())
try:
parentcats = workingcat.categories()
except pywikibot.Error:
parentcats = []
# Do not include articles already in subcats; only checking direct subcats
subcatlist = workingcat.subcategoriesList()
if subcatlist:
pywikibot.getall(mysite, subcatlist)
for cat in subcatlist:
list = cat.articlesList()
for page in list:
exclude(page.title(), real_exclude=False)
checked[page] = page
list = workingcat.articlesList()
if list:
for pl in list:
checked[pl] = pl
pywikibot.getall(mysite, list)
for pl in list:
include(pl)
else:
pywikibot.output(
u"Category %s does not exist or is empty. Which page to start with?"
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)
exclude(line,real_exclude=False)
pl = wikipedia.Page(mysite,line)
checked[pl] = pl
f.close()
excludefile = codecs.open(filename, 'a', encoding = mysite.encoding())
except IOError:
# File does not exist
excludefile = codecs.open(filename, 'w', encoding = mysite.encoding())
try:
parentcats = workingcat.categories()
except wikipedia.Error:
parentcats = []
# Do not include articles already in subcats; only checking direct subcats
subcatlist = workingcat.subcategoriesList()
if subcatlist:
wikipedia.getall(mysite,subcatlist)
for cat in subcatlist:
list = cat.articlesList()
for page in list:
exclude(page.title(),real_exclude=False)
checked[page] = page
list = workingcat.articlesList()
if list:
for pl in list:
checked[pl]=pl
wikipedia.getall(mysite,list)
for pl in list:
include(pl)
else:
wikipedia.output(u"Category %s does not exist or is empty. Which page to start with?"%workingcatname)
answer = wikipedia.input(u"(Default is [[%s]]):"%workingcatname)
exclude(line,real_exclude=False)
pl = wikipedia.Page(mysite,line)
checked[pl] = pl
f.close()
excludefile = codecs.open(filename, 'a', encoding = mysite.encoding())
except IOError:
# File does not exist
excludefile = codecs.open(filename, 'w', encoding = mysite.encoding())
try:
parentcats = workingcat.categories()
except wikipedia.Error:
parentcats = []
# Do not include articles already in subcats; only checking direct subcats
subcatlist = workingcat.subcategoriesList()
if subcatlist:
wikipedia.getall(mysite,subcatlist)
for cat in subcatlist:
list = cat.articlesList()
for page in list:
exclude(page.title(),real_exclude=False)
checked[page] = page
list = workingcat.articlesList()
if list:
for pl in list:
checked[pl]=pl
wikipedia.getall(mysite,list)
for pl in list:
include(pl)
else:
wikipedia.output(u"Category %s does not exist or is empty. Which page to start with?"%workingcatname)
answer = wikipedia.input(u"(Default is [[%s]]):"%workingcatname)
else:
start = "!"
mysite = wikipedia.getSite()
linktrail = mysite.linktrail()
try:
generator = pagegenerators.CategorizedPageGenerator(mysite.disambcategory(), start = start)
except wikipedia.NoPage:
print "The bot does not know the disambiguation category for your wiki."
raise
# only work on articles
generator = pagegenerators.NamespaceFilterPageGenerator(generator, [0])
generator = pagegenerators.PreloadingGenerator(generator)
pagestodo = []
pagestoload = []
for page in generator:
if page.isRedirectPage():
continue
linked = page.linkedPages()
pagestodo.append((page,linked))
pagestoload += linked
if len(pagestoload) > 49:
wikipedia.getall(mysite,pagestoload)
for page, links in pagestodo:
workon(page,links)
pagestoload = []
pagestodo = []
finally:
wikipedia.stopme()
exclude(line,real_exclude=False)
pl = pywikibot.Page(mysite,line)
checked[pl] = pl
f.close()
excludefile = codecs.open(filename, 'a', encoding = mysite.encoding())
except IOError:
# File does not exist
excludefile = codecs.open(filename, 'w', encoding = mysite.encoding())
try:
parentcats = workingcat.categories()
except pywikibot.Error:
parentcats = []
# Do not include articles already in subcats; only checking direct subcats
subcatlist = workingcat.subcategoriesList()
if subcatlist:
pywikibot.getall(mysite,subcatlist)
for cat in subcatlist:
list = cat.articlesList()
for page in list:
exclude(page.title(),real_exclude=False)
checked[page] = page
list = workingcat.articlesList()
if list:
for pl in list:
checked[pl]=pl
pywikibot.getall(mysite,list)
for pl in list:
include(pl)
else:
pywikibot.output(
u"Category %s does not exist or is empty. Which page to start with?"
i += 1
if i == 480:
break
start = todo[len(todo) - 1].title() + '_0'
# todo is a list of pages to do, donow are the pages we will be doing in this run.
if len(todo) > 60:
# Take the first 60.
donow = todo[0:60]
todo = todo[60:]
else:
donow = todo
# If there was more to do, the 'if len(todo)<61' part would have extended
# todo beyond this size.
cont = False
try:
wikipedia.getall(mysite, donow)
except wikipedia.SaxError:
# Ignore this error, and get the pages the traditional way.
pass
checked += len(donow)
for pl in donow:
R = re.compile(r'http://[^\s}<\]]+[^\s.,:;)\?!\]}<]')
try:
for url in R.findall(pl.get()):
url = wikipedia.unicode2html(url, 'ascii')
try:
error = URLerrorFinder().open(url)
except IOError:
error = -1
if error in allowederrorcodes:
working += 1
i += 1
if i == 480:
break
start = todo[len(todo) - 1].title() + "_0"
# todo is a list of pages to do, donow are the pages we will be doing in this run.
if len(todo) > 60:
# Take the first 60.
donow = todo[0:60]
todo = todo[60:]
else:
donow = todo
# If there was more to do, the 'if len(todo)<61' part would have extended
# todo beyond this size.
cont = False
try:
wikipedia.getall(mysite, donow)
except wikipedia.SaxError:
# Ignore this error, and get the pages the traditional way.
pass
checked += len(donow)
for pl in donow:
R = re.compile(r"http://[^\s}<\]]+[^\s.,:;)\?!\]}<]")
try:
for url in R.findall(pl.get()):
url = wikipedia.unicode2html(url, "ascii")
try:
error = URLerrorFinder().open(url)
except IOError:
error = -1
if error in allowederrorcodes:
working += 1
def treat(self, page):
"""
"" Finds links, checks if they exist on wikibooks, then checks if they
"" exist on Wikipedia, if not removes the link entirely. Also remove
"" all "citation needed" tags.
"""
text = self.load(page)
newText = text
linksFoundInPage = []
wikibooksPages = []
wikipediaPages = []
linksOnWikipedia = []
redlinks = []
def linkName(link):
link = link.strip('[')
link = link.strip(']')
if link.find("|") != -1:
return link[ link.find("|")+1:]
else: return None
def linkURL(link):
link = link.strip('[')
link = link.strip(']')
if link.find("|") != -1:
return link[ :link.find("|")]
else: return link
# Matches text between "[[" and "]]"
linkRegex = re.compile("\[\[.*?]]")
linksFoundInPage = linkRegex.findall(text)
# Remove items that aren't links
cleanLinks = []
for link in linksFoundInPage:
if link.find("#") != -1:
continue
elif link.find("Image:") != -1:
continue
elif link.find("File:") != -1:
continue
else:
cleanLinks.append(link)
linksFoundInPage = cleanLinks
pregen = pagegenerators.PreloadingGenerator(self.generator)
# Download wikibooksPages
for link in linksFoundInPage:
wikibooksPages.append( pywikibot.Page( page.site(), linkURL(link) ) )
pywikibot.getall(page.site(), wikibooksPages)
# Download wikipediaPages
wikipediaSite = pywikibot.getSite(page.site().language(), 'wikipedia')
for link in linksFoundInPage:
wikipediaPages.append( pywikibot.Page( wikipediaSite, linkURL(link)) )
pywikibot.getall(wikipediaSite, wikipediaPages)
# sort links, sending to linksOnWikibooks, linksOnWikipedia, or redlinks
i = 0
for link in linksFoundInPage:
if wikibooksPages[i].exists():
print "Page \"" + wikibooksPages[i].title() + "\" exists on wikibooks."
# no need to keep a list links on wikipedia
else:
#check on wikipedia
if wikipediaPages[i].exists():
print "Page \"" + wikipediaPages[i].title() + "\" exists on wikipedia."
linksOnWikipedia.append( linksFoundInPage[i] )
else:
print "Could not find page \"" + wikibooksPages[i].title() + "\" removing."
redlinks.append( linksFoundInPage[i] )
i += 1
#
# remove redlinks, and change wikipedia links to use w:
#
for link in linksOnWikipedia:
if linkName(link) == None:
print linkURL(link)
newLink = "[[w:" + linkURL(link) + "|" + linkURL(link) + "]]"
newText = newText.replace(link, newLink)
else:
newText = newText.replace(link, "[[w:" + linkURL(link) + "|" + linkName(link) + "]]" )
print "-" + linkName(link)
for link in redlinks:
if linkName(link) == None:
newText = newText.replace(link, linkURL(link))
else:
newText = newText.replace(link, linkName(link) )
text = newText
"""
"" Finished
"""
if not self.save(text, page, self.summary):
pywikibot.output(u'Page %s not saved.' % page.title(asLink=True))