def handleArgs():
"""
Picks the generator per argument passed in command line
Usage:
gen = pagegen.handleArgs()
for page in gen:
...do something
"""
for arg in wiki.getArgs():
if arg.startswith('-catlinks'):
if len(arg) == 9:
pg = raw_input('Which page should be operated on? ')
return catlinks(wiki.Page(pg))
else: #means that page has been supplied
pg = arg[10:]
return catlinks(wiki.Page(pg))
if arg.startswith('-cat'):
if len(arg) == 4:
cat = raw_input('Which category should be operated on? ')
if not 'category' in cat.lower():
cat = 'Category:' + cat
return category(wiki.Page(cat))
else: #means that category has been supplied
cat = arg[5:]
if not 'category' in cat.lower():
cat = 'Category:' + cat
return category(wiki.Page(cat))
if arg.startswith('-file'):
if len(arg) == 5:
fil = raw_input('Which file should be read? ')
else: #means that file has been supplied
fil = arg[6:]
try:
file = open(fil, 'r')
except IOError, err:
print err
sys.exit(1)
text = file.read()
list = re.findall('\[\[(.*?)\]\]', text)
newlist = []
for i in list:
newlist.append(wiki.Page(i))
return newlist
if arg.startswith('-new'):
if len(arg) == 4:
return recentchanges()
else:
try:
limit = int(arg[5:])
except:
return recentchanges()
return recentchanges(limit=limit)
def checktalk():
page = wiki.Page('User:%s/Stop' % (usernames[config.wiki]))
try:
wikitext = page.get()
except:
sys.exit()
if wikitext.lower() != 'run':
sys.exit()
def checktalk():
page = wiki.Page('User:Legobot III/Stop')
try:
text = page.get()
if text.lower() != 'run':
sys.exit('Run page disabled')
except:
sys.exit('Run page disabled')
def get_pages():
vapage = wiki.Page('Wikipedia:Vital articles')
gen = pagegen.links(vapage, ns=0) #we only need mainspace articles
text = state0 = vapage.get()
num = 0
for page in gen:
if page.namespace() == 0:
text = do_page(page, text)
wiki.showDiff(state0, text)
vapage.put(text, 'Bot: Updating Vital Articles', bot=True)
def main():
gen = pagegen.category(wiki.Page('Category:Wikipedia pages with incorrect protection templates'))
for page in gen:
checktalk()
print page.title() +' is being processed.'
if page.namespace() in [2, 3, 10]:
print 'Skipping userspace/template pages.'
else:
y=dopage(page)
if y == 'Prot':
logerror(page)
def docat(cat2):
gen = pagegen.category(wiki.Page('Category:' + cat2))
for page in gen:
if page.namespace() == 0:
try:
process_article(page)
except UnicodeEncodeError:
pass
checktalk()
else:
print 'Skipping %s because it is not in the mainspace' % (
page.title())
print 'Done with Category:%s' % (cat2)
def whatlinkshere(page):
"""
[[Special:WhatLinksHere]]
"""
API = wiki.API(wiki=page.getSite())
params = {
'action': 'query',
'bltitle': page.title(),
'list': 'backlinks',
'bllimit': 'max',
}
res = API.query(params)['query']['backlinks']
for i in res:
yield wiki.Page(i['title'])
def all(self, recurse=False):
"""
Returns all articles in the category
"""
print 'Getting %s...' % self.page.aslink()
params = 'action=query&list=categorymembers&cmlimit=max&cmtitle=' + self.title
res = self.API.query(params)['query']['categorymembers']
if not isinstance(recurse, bool) and recurse:
recurse = recurse - 1
for i in res:
yield wiki.Page(i['title'], wiki=self.page.getSite())
if recurse:
for subcat in self.subcats(recurse):
for mem in subcat.memvers(recurse):
yield mem
def transclude(page):
"""
Returns pages that transclude a certain template
"""
API = wiki.API(wiki=page.getSite())
print 'Getting references to [[%s]]...' % (page.title())
params = {
'action': 'query',
'list': 'embeddedin',
'eititle': page.title(),
'eilimit': 'max',
}
res = API.query(params)
for page in res['query']['embeddedin']:
yield wiki.Page(page['title'])
def prefixindex(page):
"""
Returns list of pages with prefix of the page ([[Special:PrefixIndex]])
"""
API = wiki.API(wiki=page.getSite())
ns = page.namespace()
prefix = page.titlewonamespace()
params = {
'action': 'query',
'list': 'allpages',
'apprefix': prefix,
'apnamespace': str(ns),
'aplimit': 'max',
}
res = API.query(params)['query']['allpages']
list = []
for page in res:
yield wiki.Page(page['title'])
def updatelog(self, text):
rightime = time.localtime(time.time())
year = str(rightime[0])
month = str(rightime[1])
day = str(rightime[2])
if len(month) == 1:
month = u'0' + month
try:
self.log = logs[wiki.translate()]
except KeyError: #no log on wiki
return
if not self.log:
return
target = self.log + '/' + year + '/' + month + '/' + day
log = wiki.Page(target)
if not log.exists():
text = '{|border="2" cellpadding="4" cellspacing="0" style="margin: 0.5em 0.5em 0.5em 1em; padding: 0.5em; background: #bfcda5; border: 1px #b6fd2c solid; border-collapse: collapse; font-size: 95%;"\n!User\n!Contribs\n' + text
log.put(text, self.logupmess)
def recentchanges(limit=500,
nobot=True,
onlyanon=False,
hidepatrolled=True,
nponly=False,
wiki=config.wiki):
"""
Returns a list of articles that were recently changed ([[Special:RecentChanges]])
If nponly = True, returns only newpages ([[Special:NewPages]])
"""
rcshow = []
if nobot:
rcshow.append('!bot')
if onlyanon:
rcshow.append('anon')
# if hidepatrolled:
# rcshow.append('!patrolled')
rcshowparam = ''
if len(rcshow) != 0:
for i in rcshow:
if i == rcshow[len(rcshow) - 1]: #meaning it is the last one..
rcshowparam += i
else:
rcshowparam += i + '|'
params = {
'action': 'query',
'list': 'recentchanges',
'rcshow': rcshowparam,
'rcprop': 'title',
'rclimit': limit
}
if nponly:
print 'Fetching the %s newest pages' % limit
params['rctype'] = 'new'
else:
print 'Fetching the %s latest edits' % limit
API = wiki.API(qcontinue=False, wiki=wiki)
res = API.query(params)['query']['recentchanges']
for page in res:
yield wiki.Page(page['title'])
def run(self):
url = wiki.getWiki().getIndex() + '?title=Special:Log/newusers&limit=' + str(self.loadusers)
text = wiki.getURL(url)
rec = '\<a href="/w/index\.php\?title=User:(.*?)&action=edit&redlink=1"'
list = re.findall(rec, text)
userlist = []
for i in list:
userlist.append(userlib.User(wiki.Page('User:'******''
for user in userlist:
logpost += self.doUser(user)
time.sleep(2)
self.updatelog(logpost)
if not self.quitafterrun:
print 'Sleeping %s' %self.waittime
time.sleep(self.waittime)
bot = WelcomeBot()
bot.run()
else:
sys.exit()
def subcats(self, recurse=False):
print 'Getting %s...' % self.page.aslink()
params = 'action=query&list=categorymembers&cmlimit=max&cmnamespace=14&cmtitle=' + self.title
res = self.API.query(params)['query']['categorymembers']
if not isinstance(recurse, bool) and recurse:
recurse = recurse - 1
if not hasattr(self, "_subcats"):
self._subcats = []
for i in res:
subcat = Category(
wiki.Page(i['title'], wiki=self.page.getSite()))
self._subcats.append(subcat)
yield subcat
if recurse:
for i in subcat.subcats(recurse):
yield i
else:
for subcat in self._subcats:
yield subcat
if recurse:
for i in subcat.subcats(recurse):
yield i
def main():
gen = pagegen.category(
wiki.Page(
'Category:WikiProject Korea articles using the wg parameter'))
for page in gen:
do_page(page)
#!usr/bin/python
#
# (C) Legoktm, 2009 MIT License
#
__version__ = '$Id$'
"""
Tags pages for RFD
Usage: python rfd.py
"""
import re
import wiki
o = wiki.Page('User:Arthur Rubin/Roman redirects')
list = re.findall('\[\[:M(.*?)\]\]', o.get())
newlist = []
for i in list:
newlist.append(wiki.Page('M' + i))
append = '{{rfd}}\n'
summary = 'Tagging for [[WP:RFD]] per [[WP:BOTR#Roman_redirects|request]]'
for b in newlist:
oldtext = b.get(force=True)
if 'rfd' in oldtext:
print 'Skipping: ' + b.title()
pass
else:
wiki.showDiff(oldtext, append + oldtext)
b.put(append + oldtext, summary)
def main():
gen = pagegen.category(wiki.Page('Category:Wikipedia pages with broken references'))
for page in gen:
print page
dopage(page)
time.sleep(15)
#!usr/bin/python
import wiki
from wiki import pagegen, timedate
import re, time, sys
wiki.setUser('Legobot III')
#get the list of protection templates...
fulllist = []
gen = pagegen.category(wiki.Page('Category:Protection templates'))
for page in gen:
if page.isTemplate():
name = page.titlewonamespace()
fulllist.append(name)
moveprot = ['pp-move-dispute','pp-move-vandalism','pp-move-indef','pp-move']
def logerror(page):
try:
orig = open('Errors.txt', 'r')
content = orig.read()
orig.close()
except:
content = ''
new = open('Errors.txt', 'w')
new.write(content + '\n' + page.title())
print 'Logging an error on ' + page.title()
new.close()
def convertexpiry(ts):
epochts = int(time.mktime(time.strptime(ts, '%Y-%m-%dT%H:%M:%SZ')))
st = time.gmtime(epochts)
year = str(st.tm_year)
monthname = timedate.monthname(st.tm_month)