def main():
xmlFilename = None
always = False
ignorepdf = False
limit = None
namespaces = []
generator = None
summary = None
# Process global args and prepare generator args parser
local_args = pywikibot.handleArgs()
genFactory = pagegenerators.GeneratorFactory()
for arg in local_args:
if arg.startswith('-namespace:'):
try:
namespaces.append(int(arg[11:]))
except ValueError:
namespaces.append(arg[11:])
elif arg.startswith('-summary:'):
summary = arg[9:]
elif arg == '-always':
always = True
elif arg == '-ignorepdf':
ignorepdf = True
elif arg.startswith('-limit:'):
limit = int(arg[7:])
elif arg.startswith('-xmlstart'):
if len(arg) == 9:
xmlStart = pywikibot.input(
u'Please enter the dumped article to start with:')
else:
xmlStart = arg[10:]
elif arg.startswith('-xml'):
if len(arg) == 4:
xmlFilename = pywikibot.input(
u'Please enter the XML dump\'s filename:')
else:
xmlFilename = arg[5:]
else:
genFactory.handleArg(arg)
if xmlFilename:
try:
xmlStart
except NameError:
xmlStart = None
generator = XmlDumpPageGenerator(xmlFilename, xmlStart, namespaces)
if not generator:
generator = genFactory.getCombinedGenerator()
if not generator:
# syntax error, show help text from the top of this file
pywikibot.showHelp()
return
generator = pagegenerators.PreloadingGenerator(generator, step=50)
generator = pagegenerators.RedirectFilterPageGenerator(generator)
bot = ReferencesRobot(generator, always, limit, ignorepdf, summary)
bot.run()
def main(*args):
"""
Process command line arguments and invoke bot.
If args is an empty list, sys.argv is used.
@param args: command line arguments
@type args: list of unicode
"""
xmlFilename = None
xmlStart = None
options = {}
generator = None
# Process global args and prepare generator args parser
local_args = pywikibot.handle_args(args)
genFactory = pagegenerators.GeneratorFactory()
for arg in local_args:
if arg.startswith('-summary:'):
options['summary'] = arg[9:]
elif arg == '-always':
options['always'] = True
elif arg == '-ignorepdf':
options['ignorepdf'] = True
elif arg == '-repair':
options['repair'] = True
elif arg.startswith('-limit:'):
options['limit'] = int(arg[7:])
elif arg.startswith('-xmlstart'):
if len(arg) == 9:
xmlStart = pywikibot.input(
u'Please enter the dumped article to start with:')
else:
xmlStart = arg[10:]
elif arg.startswith('-xml'):
if len(arg) == 4:
xmlFilename = pywikibot.input(
u'Please enter the XML dump\'s filename:')
else:
xmlFilename = arg[5:]
else:
genFactory.handleArg(arg)
if xmlFilename:
generator = XmlDumpPageGenerator(xmlFilename, xmlStart,
genFactory.namespaces)
if not generator:
generator = genFactory.getCombinedGenerator()
if not generator:
pywikibot.bot.suggest_help(missing_generator=True)
return False
if not genFactory.nopreload:
generator = pagegenerators.PreloadingGenerator(generator)
generator = pagegenerators.RedirectFilterPageGenerator(generator)
bot = ReferencesRobot(generator, **options)
bot.run()
return True
def main(*args):
"""
Process command line arguments and invoke bot.
If args is an empty list, sys.argv is used.
@param args: command line arguments
@type args: str
"""
xml_filename = None
xml_start = None
options = {}
generator = None
# Process global args and prepare generator args parser
local_args = pywikibot.handle_args(args)
gen_factory = pagegenerators.GeneratorFactory()
for arg in local_args:
opt, _, value = arg.partition(':')
if opt in ('-summary', '-limit'):
options[opt[1:]] = value
elif opt in ('-always', '-ignorepdf'):
options[opt[1:]] = True
elif opt == '-xmlstart':
xml_start = value or pywikibot.input(
'Please enter the dumped article to start with:')
elif opt == '-xml':
xml_filename = value or pywikibot.input(
"Please enter the XML dump's filename:")
else:
gen_factory.handle_arg(arg)
if xml_filename:
generator = XmlDumpPageGenerator(xml_filename, xml_start,
gen_factory.namespaces)
if not generator:
generator = gen_factory.getCombinedGenerator()
if not generator:
pywikibot.bot.suggest_help(missing_generator=True)
return
if not gen_factory.nopreload:
generator = pagegenerators.PreloadingGenerator(generator)
generator = pagegenerators.RedirectFilterPageGenerator(generator)
bot = ReferencesRobot(generator=generator, **options)
bot.run()
def main(*args):
"""
Process command line arguments and invoke bot.
If args is an empty list, sys.argv is used.
@param args: command line arguments
@type args: unicode
"""
gen = None
xmlFilename = None
HTTPignore = []
if isinstance(memento_client, ImportError):
warn('memento_client not imported: {0}'.format(memento_client),
ImportWarning)
# Process global args and prepare generator args parser
local_args = pywikibot.handle_args(args)
genFactory = pagegenerators.GeneratorFactory()
for arg in local_args:
if arg == '-talk':
config.report_dead_links_on_talk = True
elif arg == '-notalk':
config.report_dead_links_on_talk = False
elif arg == '-repeat':
gen = RepeatPageGenerator()
elif arg.startswith('-ignore:'):
HTTPignore.append(int(arg[8:]))
elif arg.startswith('-day:'):
config.weblink_dead_days = int(arg[5:])
elif arg.startswith('-xmlstart'):
if len(arg) == 9:
xmlStart = pywikibot.input(
'Please enter the dumped article to start with:')
else:
xmlStart = arg[10:]
elif arg.startswith('-xml'):
if len(arg) == 4:
xmlFilename = i18n.input('pywikibot-enter-xml-filename')
else:
xmlFilename = arg[5:]
else:
genFactory.handleArg(arg)
if xmlFilename:
try:
xmlStart
except NameError:
xmlStart = None
gen = XmlDumpPageGenerator(xmlFilename, xmlStart,
genFactory.namespaces)
if not gen:
gen = genFactory.getCombinedGenerator()
if gen:
if not genFactory.nopreload:
# fetch at least 240 pages simultaneously from the wiki, but more
# if a high thread number is set.
pageNumber = max(240, config.max_external_links * 2)
gen = pagegenerators.PreloadingGenerator(gen, groupsize=pageNumber)
gen = pagegenerators.RedirectFilterPageGenerator(gen)
bot = WeblinkCheckerRobot(gen, HTTPignore, config.weblink_dead_days)
try:
bot.run()
finally:
waitTime = 0
# Don't wait longer than 30 seconds for threads to finish.
while countLinkCheckThreads() > 0 and waitTime < 30:
try:
pywikibot.output('Waiting for remaining {0} threads to '
'finish, please wait...'.format(
countLinkCheckThreads()))
# wait 1 second
time.sleep(1)
waitTime += 1
except KeyboardInterrupt:
pywikibot.output('Interrupted.')
break
if countLinkCheckThreads() > 0:
pywikibot.output(
'Remaining {0} threads will be killed.'.format(
countLinkCheckThreads()))
# Threads will die automatically because they are daemonic.
if bot.history.reportThread:
bot.history.reportThread.shutdown()
# wait until the report thread is shut down; the user can
# interrupt it by pressing CTRL-C.
try:
while bot.history.reportThread.isAlive():
time.sleep(0.1)
except KeyboardInterrupt:
pywikibot.output('Report thread interrupted.')
bot.history.reportThread.kill()
pywikibot.output('Saving history...')
bot.history.save()
return True
else:
pywikibot.bot.suggest_help(missing_generator=True)
return False
def main():
gen = None
singlePageTitle = []
xmlFilename = None
# Which namespaces should be processed?
# default to [] which means all namespaces will be processed
namespaces = []
HTTPignore = []
day = 7
# Process global args and prepare generator args parser
local_args = pywikibot.handleArgs()
genFactory = pagegenerators.GeneratorFactory()
for arg in local_args:
if arg == '-talk':
config.report_dead_links_on_talk = True
elif arg == '-notalk':
config.report_dead_links_on_talk = False
elif arg.startswith('-namespace:'):
try:
namespaces.append(int(arg[11:]))
except ValueError:
namespaces.append(arg[11:])
elif arg == '-repeat':
gen = RepeatPageGenerator()
elif arg.startswith('-ignore:'):
HTTPignore.append(int(arg[8:]))
elif arg.startswith('-day:'):
day = int(arg[5:])
elif arg.startswith('-xmlstart'):
if len(arg) == 9:
xmlStart = pywikibot.input(
u'Please enter the dumped article to start with:')
else:
xmlStart = arg[10:]
elif arg.startswith('-xml'):
if len(arg) == 4:
xmlFilename = i18n.input('pywikibot-enter-xml-filename')
else:
xmlFilename = arg[5:]
else:
if not genFactory.handleArg(arg):
singlePageTitle.append(arg)
if singlePageTitle:
singlePageTitle = ' '.join(singlePageTitle)
page = pywikibot.Page(pywikibot.Site(), singlePageTitle)
gen = iter([page])
if xmlFilename:
try:
xmlStart
except NameError:
xmlStart = None
gen = XmlDumpPageGenerator(xmlFilename, xmlStart, namespaces)
if not gen:
gen = genFactory.getCombinedGenerator()
if gen:
if namespaces != []:
gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces)
# fetch at least 240 pages simultaneously from the wiki, but more if
# a high thread number is set.
pageNumber = max(240, config.max_external_links * 2)
gen = pagegenerators.PreloadingGenerator(gen, step=pageNumber)
gen = pagegenerators.RedirectFilterPageGenerator(gen)
bot = WeblinkCheckerRobot(gen, HTTPignore, day)
try:
bot.run()
finally:
waitTime = 0
# Don't wait longer than 30 seconds for threads to finish.
while countLinkCheckThreads() > 0 and waitTime < 30:
try:
pywikibot.output(u"Waiting for remaining %i threads to "
u"finish, please wait..." %
countLinkCheckThreads())
# wait 1 second
time.sleep(1)
waitTime += 1
except KeyboardInterrupt:
pywikibot.output(u'Interrupted.')
break
if countLinkCheckThreads() > 0:
pywikibot.output(u'Remaining %i threads will be killed.' %
countLinkCheckThreads())
# Threads will die automatically because they are daemonic.
if bot.history.reportThread:
bot.history.reportThread.shutdown()
# wait until the report thread is shut down; the user can
# interrupt it by pressing CTRL-C.
try:
while bot.history.reportThread.isAlive():
time.sleep(0.1)
except KeyboardInterrupt:
pywikibot.output(u'Report thread interrupted.')
bot.history.reportThread.kill()
pywikibot.output(u'Saving history...')
bot.history.save()
else:
pywikibot.showHelp()
def main(*args):
"""
Process command line arguments and invoke bot.
If args is an empty list, sys.argv is used.
@param args: command line arguments
@type args: list of unicode
"""
xmlFilename = None
options = {}
namespaces = []
generator = None
# Process global args and prepare generator args parser
local_args = pywikibot.handle_args(args)
genFactory = pagegenerators.GeneratorFactory()
for arg in local_args:
if arg.startswith('-namespace:'):
try:
namespaces.append(int(arg[11:]))
except ValueError:
namespaces.append(arg[11:])
elif arg.startswith('-summary:'):
options['summary'] = arg[9:]
elif arg == '-always':
options['always'] = True
elif arg == '-ignorepdf':
options['ignorepdf'] = True
elif arg.startswith('-limit:'):
options['limit'] = int(arg[7:])
elif arg.startswith('-xmlstart'):
if len(arg) == 9:
xmlStart = pywikibot.input(
u'Please enter the dumped article to start with:')
else:
xmlStart = arg[10:]
elif arg.startswith('-xml'):
if len(arg) == 4:
xmlFilename = pywikibot.input(
u'Please enter the XML dump\'s filename:')
else:
xmlFilename = arg[5:]
else:
genFactory.handleArg(arg)
if xmlFilename:
try:
xmlStart
except NameError:
xmlStart = None
generator = XmlDumpPageGenerator(xmlFilename, xmlStart, namespaces)
if not generator:
generator = genFactory.getCombinedGenerator()
if not generator:
# syntax error, show help text from the top of this file
pywikibot.showHelp()
return
generator = pagegenerators.PreloadingGenerator(generator, step=50)
generator = pagegenerators.RedirectFilterPageGenerator(generator)
bot = ReferencesRobot(generator, **options)
bot.run()
