def main():
args = []
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'are-identical')
if arg:
args.append(arg)
g = TwoPageGenerator(*args)
r = IdenticalRobot(g)
r.run()
def main():
args = []
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'are-identical')
if arg:
args.append(arg)
g = TwoPageGenerator(*args)
r = IdenticalRobot(g)
r.run()
def getfn():
fns = []
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'getimages')
if arg:
fns.append(arg)
if len(fns) == 0:
fns.append(raw_input("Please enter a filename: "))
return fns
def main():
# this temporary array is used to read the page title.
pageTitle = []
gen = None
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'windows_chars')
if arg:
if arg.startswith('-file'):
if len(arg) == 5:
filename = wikipedia.input(
u'please enter the list\'s filename: ')
else:
filename = arg[6:]
gen = pagegenerators.TextfilePageGenerator(filename)
elif arg.startswith('-sql'):
if len(arg) == 4:
sqlfilename = wikipedia.input(
u'please enter the SQL dump\'s filename: ')
else:
sqlfilename = arg[5:]
gen = SqlWindows1252PageGenerator(sqlfilename)
else:
pageTitle.append(arg)
# if a single page is given as a command line argument,
# reconnect the title's parts with spaces
if pageTitle != []:
page = wikipedia.Page(wikipedia.getSite(), ' '.join(pageTitle))
gen = iter([page])
# get edit summary message
wikipedia.setAction(wikipedia.translate(wikipedia.getSite(), msg))
if not gen:
wikipedia.showHelp('windows_chars')
elif wikipedia.getSite().encoding() == "utf-8":
print "There is no need to run this robot on UTF-8 wikis."
else:
preloadingGen = pagegenerators.PreloadingGenerator(gen)
bot = WindowsCharsBot(preloadingGen)
bot.run()
def main():
# this temporary array is used to read the page title.
pageTitle = []
gen = None
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'windows_chars')
if arg:
if arg.startswith('-file'):
if len(arg) == 5:
filename = wikipedia.input(u'please enter the list\'s filename: ')
else:
filename = arg[6:]
gen = pagegenerators.TextfilePageGenerator(filename)
elif arg.startswith('-sql'):
if len(arg) == 4:
sqlfilename = wikipedia.input(u'please enter the SQL dump\'s filename: ')
else:
sqlfilename = arg[5:]
gen = SqlWindows1252PageGenerator(sqlfilename)
else:
pageTitle.append(arg)
# if a single page is given as a command line argument,
# reconnect the title's parts with spaces
if pageTitle != []:
page = wikipedia.Page(wikipedia.getSite(), ' '.join(pageTitle))
gen = iter([page])
# get edit summary message
wikipedia.setAction(wikipedia.translate(wikipedia.getSite(), msg))
if not gen:
wikipedia.showHelp('windows_chars')
elif wikipedia.getSite().encoding() == "utf-8":
print "There is no need to run this robot on UTF-8 wikis."
else:
preloadingGen = pagegenerators.PreloadingGenerator(gen)
bot = WindowsCharsBot(preloadingGen)
bot.run()
if error in errname:
return errname[error]
elif (error > 300) and (error < 400):
return "Unknown Redirection Response"
else:
return "Unknown Error"
start = "!"
log = True
todo = []
do_all = False
for arg in sys.argv[1:]:
url = sys.argv[1]
arg = wikipedia.argHandler(arg, "check_extern")
if arg:
if arg.startswith("-start:"):
start = arg[7:]
do_all = True
elif arg == "-nolog":
log = False
else:
mysite = wikipedia.getSite()
todo.append(wikipedia.Page(mysite, arg))
# Make sure we have the final site
mysite = wikipedia.getSite()
if todo == []:
# No pages have been given; if also no start is given, we start at
L.append('Content-Type: %s' % get_content_type(filename))
L.append('')
L.append(value)
L.append('--' + BOUNDARY + '--')
L.append('')
body = CRLF.join(L)
content_type = 'multipart/form-data; boundary=%s' % BOUNDARY
return content_type, body
def get_content_type(filename):
import mimetypes
return mimetypes.guess_type(filename)[0] or 'application/octet-stream'
for arg in sys.argv[1:]:
if wikipedia.argHandler(arg):
pass
else:
print "Unknown argument: ",arg
sys.exit(1)
if not wikipedia.special.has_key(wikipedia.mylang):
print "Please add the translation for the Special: namespace in"
print "Your home wikipedia to the wikipedia.py module"
import sys
sys.exit(1)
if not wikipedia.cookies:
print "You must be logged in to upload images"
import sys
sys.exit(1)
import re, sys
import wikipedia
myComment = {'ar':u'بوت: URL تم إصلاحها',
'en':u'Bot: URL fixed',
'fa':u'ربات: URL اصلاح شد',
'he':u'בוט: תוקנה כתובת URL',
'pt':u'Bot: URL corrigido',
'zh':u'機器人: 網址已修復',
}
if __name__ == "__main__":
try:
for arg in sys.argv[1:]:
if wikipedia.argHandler(arg, 'brackethttp'):
pass
else:
pl = wikipedia.Page(wikipedia.getSite(), arg)
text = pl.get()
newText = re.sub("(http:\/\/([^ ]*[^\] ]))\)", "[\\1 \\2])", text)
if newText != text:
wikipedia.showDiff(text, newText)
status, reason, data = pl.put(newText, wikipedia.translate(wikipedia.mylang,myComment))
print status, reason
else:
print "No bad link found"
except:
wikipedia.stopme()
yield entry
elif action == 'unmountedcats':
for entry in sqldump.query_unmountedcats():
yield entry
elif action == 'baddisambiguation':
for entry in sqldump.entries():
if entry.namespace == 0 and entry.title.endswith(')') and entry.text.startswith("''") and not entry.text.startswith("'''"):
yield entry
if __name__=="__main__":
wikipedia.stopme() # No need to have me on the stack, as I'm not contacting the wiki
import sys
action = None
filename = None
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'sqldump')
if arg:
if arg.startswith('-sql'):
if len(arg) == 4:
filename = wikipedia.input(u'Please enter the SQL dump\'s filename: ')
else:
filename = arg[5:]
else:
action = arg
if not filename or not action:
wikipedia.output(__doc__, 'utf-8')
else:
sqldump = SQLdump(filename, wikipedia.myencoding())
for entry in query(sqldump, action):
wikipedia.output(u'*[[%s]]' % entry.full_title())
if error in errname:
return errname[error]
elif (error > 300) and (error < 400):
return 'Unknown Redirection Response'
else:
return 'Unknown Error'
start = '!'
log = True
todo = []
do_all = False
for arg in sys.argv[1:]:
url = sys.argv[1]
arg = wikipedia.argHandler(arg, 'check_extern')
if arg:
if arg.startswith('-start:'):
start = arg[7:]
do_all = True
elif arg == '-nolog':
log = False
else:
mysite = wikipedia.getSite()
todo.append(wikipedia.Page(mysite, arg))
# Make sure we have the final site
mysite = wikipedia.getSite()
if todo == []:
# No pages have been given; if also no start is given, we start at
import re, sys
import wikipedia
myComment = {
'ar': u'بوت: URL تم إصلاحها',
'en': u'Bot: URL fixed',
'he': u'בוט: תוקנה כתובת URL',
'pt': u'Bot: URL corrigido',
'zh': u'機器人: 網址已修復',
}
if __name__ == "__main__":
try:
for arg in sys.argv[1:]:
if wikipedia.argHandler(arg, 'brackethttp'):
pass
else:
pl = wikipedia.Page(wikipedia.getSite(), arg)
text = pl.get()
newText = re.sub("(http:\/\/([^ ]*[^\] ]))\)", "[\\1 \\2])",
text)
if newText != text:
wikipedia.showDiff(text, newText)
status, reason, data = pl.put(
newText,
wikipedia.translate(wikipedia.mylang, myComment))
print status, reason
else:
if __name__ == "__main__":
try:
# if the -file argument is used, page titles are dumped in this array.
# otherwise it will only contain one page.
page_list = []
# if -file is not used, this temporary array is used to read the page title.
page_title = []
from_lang = ""
type = ""
debug = False
copy_images = False
# read command line parameters
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'copy_table')
if arg:
if arg.startswith("-from"):
from_lang = arg[6:]
elif arg.startswith("-type:"):
type = arg[6:]
elif arg == "-debug":
debug = True
elif arg == "-image":
copy_images = True
elif arg.startswith('-file'):
if len(arg) == 5:
file = wikipedia.input(
u'Please enter the list\'s filename: ')
else:
file = arg[6:]
if __name__=="__main__":
try:
# if the -file argument is used, page titles are dumped in this array.
# otherwise it will only contain one page.
page_list = []
# if -file is not used, this temporary array is used to read the page title.
page_title = []
from_lang = ""
type = ""
debug = False
copy_images = False
# read command line parameters
for arg in sys.argv[1:]:
arg = wikipedia.argHandler(arg, 'copy_table')
if arg:
if arg.startswith("-from"):
from_lang = arg[6:]
elif arg.startswith("-type:"):
type = arg[6:]
elif arg == "-debug":
debug = True
elif arg == "-image":
copy_images = True
elif arg.startswith('-file'):
if len(arg) == 5:
file = wikipedia.input(u'Please enter the list\'s filename: ')
else:
file = arg[6:]
# open file and read page titles out of it
