def main():
site = pywikibot.Site('en', 'wikipedia')
generator = pagegenerators.PreloadingGenerator(
pagegenerators.LinksearchPageGenerator(u'www.artnet.com/artists/',
namespaces=[0],
site=site))
bot = ArtnetRobot(generator)
bot.run()
def file_from_external_link(self, uri):
"""Identify files from a Nationalmuseum uri.
Hits are any files containing a link to the eMuseumPlus uri.
@param uri: reference url on nationalmuseum.se
@type uri: str
@return: matching images
@rtype: list
"""
images = []
uri = uri.split('://')[1]
objgen = pagegenerators.LinksearchPageGenerator(uri,
namespaces=[6],
site=self.commons)
for page in objgen:
images.append(pywikibot.FilePage(self.commons, page.title()))
# I have no clue how the above results in duplicates, but it does so...
images = list(set(images))
return images
def main(*args):
"""
Process command line arguments and perform task.
If args is an empty list, sys.argv is used.
@param args: command line arguments
@type args: str
"""
spam_external_url = None
protocol = 'http'
options = {}
local_args = pywikibot.handle_args(args)
gen_factory = pagegenerators.GeneratorFactory()
for arg in local_args:
if arg == '-always':
options['always'] = True
elif arg.startswith('-protocol:'):
protocol = arg.partition(':')[2]
elif arg.startswith('-summary:'):
options['summary'] = arg.partition(':')[2]
elif gen_factory.handleArg(arg):
continue
else:
spam_external_url = arg
if not spam_external_url:
pywikibot.bot.suggest_help(missing_parameters=['spam site'])
return
link_search = pagegenerators.LinksearchPageGenerator(spam_external_url,
protocol=protocol)
generator = gen_factory.getCombinedGenerator(gen=link_search)
generator = pagegenerators.PreloadingGenerator(generator)
bot = SpamRemoveBot(generator, spam_external_url, **options)
bot.run()
