def getPDFTitle(self, ref, f):
"""Use pdfinfo to retrieve title from a PDF.
FIXME: Unix-only, I'm afraid.
"""
pywikibot.output(u'PDF file.')
fd, infile = tempfile.mkstemp()
urlobj = os.fdopen(fd, 'w+')
urlobj.write(f.content)
try:
pdfinfo_out = subprocess.Popen([r"pdfinfo", "/dev/stdin"],
stdin=urlobj, stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
shell=False).communicate()[0]
for aline in pdfinfo_out.splitlines():
if aline.lower().startswith('title'):
ref.title = aline.split(None)[1:]
ref.title = ' '.join(ref.title)
if ref.title != '':
pywikibot.output(u'title: %s' % ref.title)
pywikibot.output(u'PDF done.')
except ValueError:
pywikibot.output(u'pdfinfo value error.')
except OSError:
pywikibot.output(u'pdfinfo OS error.')
except Exception: # Ignore errors
pywikibot.output(u'PDF processing error.')
pywikibot.exception()
finally:
urlobj.close()
os.unlink(infile)
def main():
local_args = pywikibot.handleArgs()
cache_paths = None
delete = False
command = None
for arg in local_args:
if command == '':
command = arg
elif arg == '-delete':
delete = True
elif arg == '-password':
command = 'has_password(entry)'
elif arg == '-c':
if command:
pywikibot.error('Only one command may be executed.')
exit(1)
command = ''
else:
if not cache_paths:
cache_paths = [arg]
else:
cache_paths.append(arg)
func = None
if not cache_paths:
cache_paths = ['apicache', 'tests/apicache']
# Also process the base directory, if it isnt the current directory
if os.path.abspath(os.getcwd()) != pywikibot.config2.base_dir:
cache_paths += [
os.path.join(pywikibot.config2.base_dir, 'apicache')]
# Also process the user home cache, if it isnt the config directory
if os.path.expanduser('~/.pywikibot') != pywikibot.config2.base_dir:
cache_paths += [
os.path.join(os.path.expanduser('~/.pywikibot'), 'apicache')]
if delete:
action_func = lambda entry: entry._delete()
else:
action_func = lambda entry: pywikibot.output(entry)
if command:
try:
command_func = eval('lambda entry: ' + command)
except:
pywikibot.exception()
pywikibot.error(u'Can not compile command: %s' % command)
exit(1)
func = lambda entry: command_func(entry) and action_func(entry)
else:
func = action_func
for cache_path in cache_paths:
if len(cache_paths) > 1:
pywikibot.output(u'Processing %s' % cache_path)
process_entries(cache_path, func)
def revert(self, item):
history = pywikibot.Page(self.site, item['title']).fullVersionHistory(
total=2, rollback=self.rollback)
if len(history) > 1:
rev = history[1]
else:
return False
comment = i18n.twtranslate(pywikibot.Site(), 'revertbot-revert', {'revid': rev[0], 'author': rev[2], 'timestamp': rev[1]})
if self.comment:
comment += ': ' + self.comment
page = pywikibot.Page(self.site, item['title'])
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title(asLink=True, forceInterwiki=True,
textlink=True))
if not self.rollback:
old = page.text
page.text = rev[3]
pywikibot.showDiff(old, page.text)
page.save(comment)
return comment
try:
pywikibot.data.api.Request(action="rollback", title=page.title(), user=self.user,
token=rev[4], markbot=1).submit()
except pywikibot.data.api.APIError as e:
if e.code == 'badtoken':
pywikibot.error("There was an API token error rollbacking the edit")
else:
pywikibot.exception()
return False
return u"The edit(s) made in %s by %s was rollbacked" % (page.title(), self.user)
def revert(self, item):
history = pywikibot.Page(self.site, item["title"]).fullVersionHistory(total=2, rollback=self.rollback)
if len(history) > 1:
rev = history[1]
else:
return False
comment = i18n.twtranslate(
pywikibot.Site(), "revertbot-revert", {"revid": rev[0], "author": rev[2], "timestamp": rev[1]}
)
if self.comment:
comment += ": " + self.comment
page = pywikibot.Page(self.site, item["title"])
pywikibot.output(
"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title(asLink=True, forceInterwiki=True, textlink=True)
)
if not self.rollback:
old = page.text
page.text = rev[3]
pywikibot.showDiff(old, page.text)
page.save(comment)
return comment
try:
pywikibot.data.api.Request(
self.site,
parameters={"action": "rollback", "title": page, "user": self.user, "token": rev[4], "markbot": True},
).submit()
except pywikibot.data.api.APIError as e:
if e.code == "badtoken":
pywikibot.error("There was an API token error rollbacking the edit")
else:
pywikibot.exception()
return False
return "The edit(s) made in %s by %s was rollbacked" % (page.title(), self.user)
def run(self):
"""Process all pages in generator."""
if not hasattr(self, 'generator'):
raise NotImplementedError('Variable %s.generator not set.'
% self.__class__.__name__)
treat_missing_item = hasattr(self, 'treat_missing_item')
try:
for page in self.generator:
if not page.exists():
pywikibot.output('%s doesn\'t exist.' % page)
try:
item = pywikibot.ItemPage.fromPage(page)
except pywikibot.NoPage:
item = None
if not item:
if not treat_missing_item:
pywikibot.output(
'%s doesn\'t have a wikidata item.' % page)
#TODO FIXME: Add an option to create the item
continue
self.treat(page, item)
except QuitKeyboardInterrupt:
pywikibot.output('\nUser quit %s bot run...' %
self.__class__.__name__)
except KeyboardInterrupt:
if config.verbose_output:
raise
else:
pywikibot.output('\nKeyboardInterrupt during %s bot run...' %
self.__class__.__name__)
except Exception as e:
pywikibot.exception(msg=e, tb=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: list of unicode
"""
all = False
new = False
sysop = False
for arg in pywikibot.handle_args(args):
if arg in ('-all', '-update'):
all = True
elif arg == '-new':
new = True
elif arg == '-sysop':
sysop = True
if all:
refresh_all(sysop=sysop)
elif new:
refresh_new(sysop=sysop)
else:
site = pywikibot.Site()
watchlist = refresh(site, sysop=sysop)
pywikibot.output(u'{0:d} pages in the watchlist.'.format(len(watchlist)))
for page in watchlist:
try:
pywikibot.stdout(page.title())
except pywikibot.InvalidTitle:
pywikibot.exception()
def main_script(page, rev=None, params=NotImplemented): # pylint: disable=unused-argument
"""Main thread."""
# http://opensourcehacker.com/2011/02/23/temporarily-capturing-python-logging-output-to-a-string-buffer/
# https://docs.python.org/release/2.6/library/logging.html
from io import StringIO
import logging
# safety; default mode is safe (no writing)
pywikibot.config.simulate = True
pywikibot.output(u'--- ' * 20)
buffer = StringIO()
rootLogger = logging.getLogger()
logHandler = logging.StreamHandler(buffer)
formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
logHandler.setFormatter(formatter)
rootLogger.addHandler(logHandler)
sys.stdout = buffer
sys.stderr = buffer
# all output to logging and stdout/stderr is catched BUT NOT lua output (!)
if rev is None:
code = page.get() # shell; "on demand"
else:
code = page.getOldVersion(rev) # crontab; scheduled
try:
exec(code)
except:
# (done according to subster in trunk and submit in rewrite/.../data/api.py)
pywikibot.exception(tb=True) # secure traceback print (from api.py submit)
sys.stdout = sys.__stdout__
sys.stderr = sys.__stderr__
# Remove our handler
rootLogger.removeHandler(logHandler)
logHandler.flush()
buffer.flush()
pywikibot.output(u'--- ' * 20)
# safety; restore settings
pywikibot.config.simulate = __simulate
sys.argv = __sys_argv
pywikibot.output(
u'environment: garbage; %s / memory; %s / members; %s' % (
gc.collect(),
resource.getrusage(resource.RUSAGE_SELF).ru_maxrss * resource.getpagesize(),
len(dir())))
# 'len(dir())' is equivalent to 'len(inspect.getmembers(__main__))'
# append result to output page
if rev is None:
wiki_logger(buffer.getvalue(), page, rev)
def run(self):
"""Starts the robot."""
self.templateTitles = self.getTemplateSynonyms(self.templateTitle)
for page in self.generator:
try:
self.processPage(page)
except Exception as e:
pywikibot.exception(msg=e, tb=True)
def main():
local_args = pywikibot.handleArgs()
cache_paths = None
delete = False
command = None
for arg in local_args:
if command == "":
command = arg
elif arg == "-delete":
delete = True
elif arg == "-password":
command = "has_password(entry)"
elif arg == "-c":
if command:
pywikibot.error("Only one command may be executed.")
exit(1)
command = ""
else:
if not cache_paths:
cache_paths = [arg]
else:
cache_paths.append(arg)
func = None
if not cache_paths:
cache_paths = ["apicache", "tests/apicache"]
# Also process the base directory, if it isnt the current directory
if os.path.abspath(os.getcwd()) != pywikibot.config2.base_dir:
cache_paths += [os.path.join(pywikibot.config2.base_dir, "apicache")]
# Also process the user home cache, if it isnt the config directory
if os.path.expanduser("~/.pywikibot") != pywikibot.config2.base_dir:
cache_paths += [os.path.join(os.path.expanduser("~/.pywikibot"), "apicache")]
if delete:
action_func = lambda entry: entry._delete()
else:
action_func = lambda entry: pywikibot.output(entry)
if command:
try:
command_func = eval("lambda entry: " + command)
except:
pywikibot.exception()
pywikibot.error("Can not compile command: %s" % command)
exit(1)
func = lambda entry: command_func(entry) and action_func(entry)
else:
func = action_func
for cache_path in cache_paths:
if len(cache_paths) > 1:
pywikibot.output("Processing %s" % cache_path)
process_entries(cache_path, func)
def test_exception(self):
class TestException(Exception):
pass
try:
raise TestException("Testing Exception")
except TestException:
pywikibot.exception("exception")
self.assertEqual(newstdout.getvalue(), "")
self.assertEqual(newstderr.getvalue(), "ERROR: TestException: Testing Exception\n")
def treat(self, page):
pywikibot.output(u'parsing {}'.format(page))
item = pywikibot.ItemPage.fromPage(page)
if not item.exists():
pywikibot.warning(u'item not found for {}'.format(page))
return
text = page.text
code = mwparserfromhell.parse(page.text)
removed = []
for template in code.ifilter_templates():
if template.name.strip().title() != 'Autore':
continue
for pcode, pname in self.params.items():
if template.has(pname, False):
val = template.get(pname).value.strip()
if val == '' or getattr(self, 'handle_' + pcode)(val, item) is True:
template.remove(pname, keep_field=False)
removed.append(pname)
sections = {}
sbeg = None
elements = code.filter()
for el in code.ifilter_tags():
if el.tag == 'section' and el.self_closing is True:
if el.has('begin'):
sbeg = el
elif sbeg and el.has('end'):
sname = unicode(sbeg.get('begin').value)
if unicode(el.get('end').value) == sname:
start = elements.index(sbeg) + 2 + len(sbeg.attributes) * 2
sections[sname] = [sbeg] + elements[start:elements.index(el) + 1]
for scode, sname in self.params.items():
if sname in sections:
val = ''.join(map(unicode, sections[sname][1:-1])).strip()
if val == '' or getattr(self, 'handle_' + scode)(val, item) is True:
for el in sections[sname]:
code.remove(el)
removed.append(sname)
if len(removed) == 6:
remset = list(set(removed))
if len(remset) != 3:
return
removed = list(remset)
text = unicode(code)
text = re.sub('(?<=\/\>)(\n\s*)+(?=\n\<)', '', text)
comment = i18n.translate(page.site, wikidata_summary[1],
{'counter': len(removed),
'params': page.site.list_to_text(removed),
'id': item.getID()
})
try:
self.userPut(page, page.text, text, comment=comment, minor=True, botflag=True)
except Exception as e:
pywikibot.exception(e)
def setUpClass(cls):
"""
Set up the test class.
Prevent tests running if the host is down.
"""
super(CheckHostnameMixin, cls).setUpClass()
if not hasattr(cls, 'sites'):
return
for key, data in cls.sites.items():
if 'hostname' not in data:
raise Exception('%s: hostname not defined for %s'
% (cls.__name__, key))
hostname = data['hostname']
if hostname in cls._checked_hostnames:
if isinstance(cls._checked_hostnames[hostname], Exception):
raise unittest.SkipTest(
'%s: hostname %s failed (cached): %s'
% (cls.__name__, hostname,
cls._checked_hostnames[hostname]))
elif cls._checked_hostnames[hostname] is False:
raise unittest.SkipTest('%s: hostname %s failed (cached)'
% (cls.__name__, hostname))
else:
continue
e = None
try:
if '://' not in hostname:
hostname = 'http://' + hostname
r = http.fetch(uri=hostname,
default_error_handling=False)
if r.exception:
e = r.exception
else:
if r.status not in [200, 301, 302, 303, 307, 308]:
raise ServerError('HTTP status: %d' % r.status)
r.content # default decode may raise exception
except Exception as e2:
pywikibot.error('%s: accessing %s caused exception:'
% (cls.__name__, hostname))
pywikibot.exception(e2, tb=True)
e = e2
pass
if e:
cls._checked_hostnames[hostname] = e
raise unittest.SkipTest(
'%s: hostname %s failed: %s'
% (cls.__name__, hostname, e))
cls._checked_hostnames[hostname] = True
def test_exception(self):
class TestException(Exception):
"""Test exception."""
try:
raise TestException('Testing Exception')
except TestException:
pywikibot.exception('exception')
self.assertEqual(newstdout.getvalue(), '')
self.assertEqual(newstderr.getvalue(), 'ERROR: TestException: Testing Exception\n')
def safe_execute(self, method, text):
"""Execute the method and catch exceptions if enabled."""
result = None
try:
result = method(text)
except Exception as e:
if self.ignore == CANCEL_METHOD:
pywikibot.warning('Unable to perform "{0}" on "{1}"!'.format(method.__name__, self.title))
pywikibot.exception(e)
else:
raise
return text if result is None else result
def do_check(self, page_title, rev=None, params=None):
# Create two threads as follows
# (simple 'thread' for more sophisticated code use 'threading')
try:
thread.start_new_thread(main_script, (self.refs[page_title], rev, params))
except:
# (done according to subster in trunk and submit in rewrite/.../data/api.py)
# TODO: is this error handling here needed at all??!?
pywikibot.exception(tb=True) # secure traceback print (from api.py submit)
pywikibot.warning("Unable to start thread")
wiki_logger(traceback.format_exc(), self.refs[page_title], rev)
def _parse_command(command, name):
obj = globals().get(command)
if callable(obj):
return obj
else:
try:
return eval('lambda entry: ' + command)
except:
pywikibot.exception()
pywikibot.error(
'Cannot compile {0} command: {1}'.format(name, command))
return None
def _parse_command(command, name):
"""Parse command."""
obj = globals().get(command)
if callable(obj):
return obj
else:
try:
return eval('lambda entry: ' + command)
except Exception:
pywikibot.exception()
pywikibot.error(
'Cannot compile {0} command: {1}'.format(name, command))
return None
def safe_execute(self, method, text):
"""Execute the method and catch exceptions if enabled."""
result = None
try:
result = method(text)
except Exception as e:
if self.ignore == CANCEL_METHOD:
pywikibot.warning('Unable to perform "{0}" on "{1}"!'.format(
method.__name__, self.title))
pywikibot.exception(e)
else:
raise
return text if result is None else result
def save_list(page_list: list[pywikibot.Page], page: Page) -> None:
"""
Write the given page_list to the given page.
:param page_list: List of pages to output
:param page: Page to save to
"""
list_text = ""
for item in sorted(page_list):
list_text += f"\n# {item.title(as_link=True, textlink=True)}"
try:
page.save_bot_start_end(list_text, summary="Updating list", force=True)
except pywikibot.exceptions.Error:
pywikibot.exception(tb=True)
def userIsExperienced(self, username):
"""
Check whether is this user is experienced.
user is experienced if edits >= 50
changed to 25 // 20150309
"""
try:
user = pywikibot.User(self.site, username)
except pywikibot.InvalidTitle:
pywikibot.exception()
return False
return user.editCount() >= self.useredits
def do_check(self, page_title, rev=None, params=None):
# Create two threads as follows
# (simple 'thread' for more sophisticated code use 'threading')
try:
thread.start_new_thread(main_script,
(self.refs[page_title], rev, params))
except:
# (done according to subster in trunk and submit in rewrite/.../data/api.py)
# TODO: is this error handling here needed at all??!?
pywikibot.exception(
tb=True) # secure traceback print (from api.py submit)
pywikibot.warning(u"Unable to start thread")
wiki_logger(traceback.format_exc(), self.refs[page_title], rev)
def wrapper(*args, **kwargs):
try:
func(*args, **kwargs)
except AssertionError:
tb = traceback.extract_tb(sys.exc_info()[2])
for depth, line in enumerate(tb):
if re.match('^assert[A-Z]', line[2]):
break
tb = traceback.format_list(tb[:depth])
pywikibot.error('\n' + ''.join(tb)[:-1]) # remove \n at the end
raise unittest.SkipTest('Test is allowed to fail.')
except Exception:
pywikibot.exception(tb=True)
raise unittest.SkipTest('Test is allowed to fail.')
def process_entries(cache_dir, func):
""" Check the contents of the cache. """
# This program tries to use file access times to determine
# whether cache files are being used.
# However file access times are not always usable.
# On many modern filesystems, they have been disabled.
# On unix, check the filesystem mount options. You may
# need to remount with 'strictatime'.
# - None = detect
# - False = dont use
# - True = always use
use_accesstime = None
if not cache_dir:
cache_dir = os.path.join(pywikibot.config2.base_dir, 'apicache')
for filename in os.listdir(cache_dir):
filepath = os.path.join(cache_dir, filename)
if use_accesstime is not False:
stinfo = os.stat(filepath)
entry = CacheEntry(cache_dir, filename)
entry._load_cache()
if use_accesstime is None:
stinfo2 = os.stat(filepath)
use_accesstime = stinfo.st_atime != stinfo2.st_atime
if use_accesstime:
# Reset access times to values before loading cache entry.
os.utime(filepath, (stinfo.st_atime, stinfo.st_mtime))
entry.stinfo = stinfo
try:
entry.parse_key()
except ParseError:
pywikibot.error(u'Problems parsing %s with key %s' %
(entry.filename, entry.key))
pywikibot.exception()
continue
try:
entry._rebuild()
except Exception:
pywikibot.error(u'Problems loading %s with key %s, %r' %
(entry.filename, entry.key, entry._parsed_key))
pywikibot.exception()
continue
func(entry)
def wrapper(*args, **kwargs):
try:
func(*args, **kwargs)
except AssertionError:
tb = traceback.extract_tb(sys.exc_info()[2])
for depth, line in enumerate(tb):
if re.match('^assert[A-Z]', line[2]):
break
tb = traceback.format_list(tb[:depth])
pywikibot.error('\n' + ''.join(tb)[:-1]) # remove \n at the end
raise unittest.SkipTest('Test is allowed to fail.')
except Exception:
pywikibot.exception(tb=True)
raise unittest.SkipTest('Test is allowed to fail.')
def process_entries(cache_dir, func):
""" Check the contents of the cache. """
# This program tries to use file access times to determine
# whether cache files are being used.
# However file access times are not always usable.
# On many modern filesystems, they have been disabled.
# On unix, check the filesystem mount options. You may
# need to remount with 'strictatime'.
# - None = detect
# - False = dont use
# - True = always use
use_accesstime = None
if not cache_dir:
cache_dir = os.path.join(pywikibot.config2.base_dir, 'apicache')
for filename in os.listdir(cache_dir):
filepath = os.path.join(cache_dir, filename)
if use_accesstime is not False:
stinfo = os.stat(filepath)
entry = CacheEntry(cache_dir, filename)
entry._load_cache()
if use_accesstime is None:
stinfo2 = os.stat(filepath)
use_accesstime = stinfo.st_atime != stinfo2.st_atime
if use_accesstime:
# Reset access times to values before loading cache entry.
os.utime(filepath, (stinfo.st_atime, stinfo.st_mtime))
entry.stinfo = stinfo
try:
entry.parse_key()
except ParseError:
pywikibot.error(u'Problems parsing %s with key %s'
% (entry.filename, entry.key))
pywikibot.exception()
continue
try:
entry._rebuild()
except Exception:
pywikibot.error(u'Problems loading %s with key %s, %r'
% (entry.filename, entry.key, entry._parsed_key))
pywikibot.exception()
continue
func(entry)
def change(self, text):
"""Execute all clean up methods and catch errors if activated."""
try:
new_text = self._change(text)
except Exception as e:
if self.ignore == CANCEL_PAGE:
pywikibot.warning(u'Skipped "{0}", because an error occured.'.format(self.title))
pywikibot.exception(e)
return False
else:
raise
else:
if self.diff:
pywikibot.showDiff(text, new_text)
return new_text
def checkORES(self, page):
revision = page._rcinfo.get('revision')
ores = str(revision.get('new'))
url = 'https://ores.wmflabs.org/v3/scores/eswiki/' + ores
retornar = {}
r = requests.get(url=url)
data = r.json()
try:
goodfaith = data.get('eswiki').get('scores').get(ores).get('goodfaith')
damaging = data.get('eswiki').get('scores').get(ores).get('damaging')
buena_fe = goodfaith.get('score').get('probability').get('true')
danina = damaging.get('score').get('probability').get('true')
return (ores, buena_fe, danina, True if buena_fe < self.getOption('gf') or danina > self.getOption('dm') else False)
except:
pywikibot.exception()
def change(self, text):
"""Execute all clean up methods and catch errors if activated."""
try:
new_text = self._change(text)
except Exception as e:
if self.ignore == CANCEL_PAGE:
pywikibot.warning(u'Skipped "{0}", because an error occured.'.format(self.title))
pywikibot.exception(e)
return False
else:
raise
else:
if self.diff:
pywikibot.showDiff(text, new_text)
return new_text
def test_exception_tb(self):
class TestException(Exception):
pass
try:
raise TestException("Testing Exception")
except TestException:
pywikibot.exception("exception", tb=True)
self.assertEqual(newstdout.getvalue(), "")
stderrlines = newstderr.getvalue().split("\n")
self.assertEqual(stderrlines[0], "ERROR: TestException: Testing Exception")
self.assertEqual(stderrlines[1], "Traceback (most recent call last):")
self.assertEqual(stderrlines[3], """ raise TestException("Testing Exception")""")
self.assertEqual(stderrlines[4], "TestException: Testing Exception")
self.assertNotEqual(stderrlines[-1], "\n")
def test_exception_tb(self):
try:
raise TestExceptionError('Testing Exception')
except TestExceptionError:
pywikibot.exception('exception', tb=True)
self.assertEqual(newstdout.getvalue(), '')
stderrlines = newstderr.getvalue().split('\n')
self.assertEqual(stderrlines[0],
'ERROR: TestExceptionError: Testing Exception')
self.assertEqual(stderrlines[1], 'Traceback (most recent call last):')
self.assertEqual(stderrlines[3],
" raise TestExceptionError('Testing Exception')")
self.assertTrue(stderrlines[4].endswith(': Testing Exception'))
self.assertNotEqual(stderrlines[-1], '\n')
def revert(self, item):
"""Revert a single item."""
page = pywikibot.Page(self.site, item['title'])
history = list(page.revisions(total=2))
if len(history) > 1:
rev = history[1]
else:
return False
comment = i18n.twtranslate(self.site, 'revertbot-revert', {
'revid': rev.revid,
'author': rev.user,
'timestamp': rev.timestamp
})
additional_comment = self.getOption('comment')
if additional_comment:
comment += ': ' + additional_comment
pywikibot.output(
color_format(
'\n\n>>> {lightpurple}{0}{default} <<<',
page.title(as_link=True, force_interwiki=True, textlink=True)))
if not self.getOption('rollback'):
old = page.text
page.text = page.getOldVersion(rev.revid)
pywikibot.showDiff(old, page.text)
page.save(comment)
return comment
try:
pywikibot.data.api.Request(self.site,
parameters={
'action': 'rollback',
'title': page,
'user': self.user,
'token': rev.rollbacktoken,
'markbot': True
}).submit()
except pywikibot.data.api.APIError as e:
if e.code == 'badtoken':
pywikibot.error(
'There was an API token error rollbacking the edit')
else:
pywikibot.exception()
return False
return 'The edit(s) made in {0} by {1} was rollbacked'.format(
page.title(), self.user)
def process_result(self, result):
entity_gid, url_gid, wikipage = result
wp.debug("» {wp} https://musicbrainz.org/{entitytype}/{gid}".format(
entitytype=self._current_entity_type.replace("_", "-"),
wp=wikipage,
gid=entity_gid),
layer="")
try:
itempage = get_wikidata_itempage_from_wikilink(wikipage)
except wp.NoSuchSite:
wp.warning("{page} no supported family".format(page=wikipage))
return
except (wp.BadTitle, wp.InvalidTitle) as e:
wp.error(
"Bad or invalid title received while processing {page}".format(
page=wikipage))
wp.exception(e, tb=True)
return
except IsDisambigPage:
wp.warning("{page} is a disambiguation page".format(page=wikipage))
return
except IsRedirectPage as e:
wp.debug("{page} is a redirect".format(page=wikipage), layer="")
self.fix_redirect(url_gid, e.old, e.new)
return
except ValueError as e:
wp.output(e)
return
if itempage is None:
wp.debug(
u"There's no wikidata page for {mbid}".format(mbid=entity_gid),
layer="")
return
if any((key.lower() == self.property_id.lower()
and claim.target == entity_gid)
for key, claims in itempage.claims.items() for claim in claims):
wp.debug(
u"{page} already has property {pid} with value {mbid}".format(
page=wikipage, mbid=entity_gid, pid=self.property_id),
layer="")
self.donefunc(entity_gid)
return
wp.debug("{mbid} is not linked in Wikidata".format(mbid=entity_gid),
layer="")
self.add_mbid_claim_to_item(itempage, entity_gid)
def process_result(self, result):
entity_gid, url_gid, wikipage = result
wp.debug("» {wp} https://musicbrainz.org/{entitytype}/{gid}".format(
entitytype=self._current_entity_type.replace("_", "-"),
wp=wikipage,
gid=entity_gid
), layer="")
try:
itempage = get_wikidata_itempage_from_wikilink(wikipage)
except wp.NoSuchSite:
wp.warning("{page} no supported family".format(page=wikipage))
return
except (wp.BadTitle, wp.InvalidTitle) as e:
wp.error("Bad or invalid title received while processing {page}".format(page=wikipage))
wp.exception(e, tb=True)
return
except SkipPage as e:
wp.warning("{page} is being skipped because: {reason}".format(page=wikipage,
reason=e))
return
except IsRedirectPage as e:
wp.debug("{page} is a redirect".format(page=wikipage), layer="")
if self.can_edit:
self.fix_redirect(url_gid, e.old, e.new)
return
except ValueError as e:
wp.output(e)
return
if itempage is None:
wp.debug(u"There's no wikidata page for {mbid}".format(mbid=entity_gid),
layer="")
return
if any((key.lower() == self.property_id.lower() and
claim.target == entity_gid)
for key, claims in itempage.claims.items() for claim in claims):
wp.debug(u"{page} already has property {pid} with value {mbid}".
format(page=wikipage,
mbid=entity_gid,
pid=self.property_id), layer="")
self.donefunc(entity_gid)
return
wp.debug("{mbid} is not linked in Wikidata".format(
mbid=entity_gid), layer="")
self.add_mbid_claim_to_item(itempage, entity_gid)
def _get_voter(username, eligibility_dict):
voter = pywikibot.User(COMMONS, username)
sul = COMMONS._simple_request(action='query',
meta='globaluserinfo',
guiprop='merged',
guiuser=voter.username).submit()
try:
sul = sul['query']['globaluserinfo']['merged']
except KeyError:
newusername = eligibility_dict['possiblerenames'][voter.username]
logger.warn('Following rename "%s" -> "%s"' % (username, newusername))
return get_voter(newusername, eligibility_dict)
sul = sorted(sul, key=lambda item: item['editcount'], reverse=True)
eligible_register = eligible_edits = False
for sulentry in sul:
eligible_register = eligible_register or (
min(pywikibot.Timestamp.fromISOformat(sulentry['registration']),
pywikibot.Timestamp.fromISOformat(sulentry['timestamp'])) <
eligibility_dict['register']['before'])
if not eligible_edits:
# Being lazy
if sulentry['editcount'] >= eligibility_dict['edits']['atleast']:
try:
sul_site = COMMONS.fromDBName(sulentry['wiki'])
except pywikibot.exceptions.UnknownFamily:
pywikibot.exception(
'Failed to get Site object for {}, skipping'.format(
sulentry['wiki']))
continue
if eligibility_dict['edits']['includedeleted']:
raise NotImplementedError(
'counting deleted edits is not implemented')
else:
contribs = sul_site.usercontribs(
voter.username,
start=eligibility_dict['edits']['before'],
total=eligibility_dict['edits']['atleast'])
eligible_edits = (len(list(contribs)) >=
eligibility_dict['edits']['atleast'])
if eligible_register and eligible_edits:
# logger.warn('[[User:{}]]: eligible'.format(voter.username))
return voter
return None
def proposed_by(self, textvalue):
prop = self.current_page
if 'P3254' not in prop.claims:
try:
int(textvalue)
except ValueError as e:
pywikibot.exception(e)
else:
claim = pywikibot.Claim(self.repo, 'P3254')
target = ('https://www.wikidata.org/wiki/'
'Wikidata:Property_proposal/Archive/{}#{}'
).format(textvalue, prop.id)
claim.setTarget(target)
claim.addSource(self.get_source())
return self.user_add_claim(
prop, claim, summary=self.make_summary())
return False
def test_exception_tb(self):
class TestException(Exception):
"""Test exception."""
try:
raise TestException('Testing Exception')
except TestException:
pywikibot.exception('exception', tb=True)
self.assertEqual(newstdout.getvalue(), '')
stderrlines = newstderr.getvalue().split('\n')
self.assertEqual(stderrlines[0], 'ERROR: TestException: Testing Exception')
self.assertEqual(stderrlines[1], 'Traceback (most recent call last):')
self.assertEqual(stderrlines[3], " raise TestException('Testing Exception')")
self.assertTrue(stderrlines[4].endswith(': Testing Exception'))
self.assertNotEqual(stderrlines[-1], '\n')
def checkORES(self, page):
headers = {'User-Agent': 'SeroBOT - an ORES counter vandalism tool'}
wiki = self.available_options.get('wiki')
revision = page._rcinfo.get('revision')
ores = str(revision.get('new'))
url = 'https://ores.wikimedia.org/v3/scores/{0}/{1}'.format(wiki, ores)
r = requests.get(url=url, headers=headers)
data = r.json()
try:
goodfaith = data.get(wiki).get('scores').get(ores).get('goodfaith')
damaging = data.get(wiki).get('scores').get(ores).get('damaging')
buena_fe = goodfaith.get('score').get('probability').get('true')
danina = damaging.get('score').get('probability').get('true')
return (ores, buena_fe, danina,
True if buena_fe < self.available_options.get('gf')
or danina > self.available_options.get('dm') else False)
except:
pywikibot.exception()
def get_wiki(self):
"""Get wiki from base_url."""
import pywikibot
print('Generating family file from ' + self.base_url)
for verify in (True, False):
try:
w = self.Wiki(self.base_url, verify=verify)
except pywikibot.FatalServerError:
print('ERROR: ' +
pywikibot.comms.http.SSL_CERT_VERIFY_FAILED_MSG)
pywikibot.exception()
if not pywikibot.bot.input_yn(
'Retry with disabled ssl certificate validation',
automatic_quit=False):
break
else:
return w, verify
return None, None
def proposed_by(self, textvalue):
prop = self.current_page
if 'P3254' not in prop.claims:
try:
int(textvalue)
except ValueError as e:
pywikibot.exception(e)
else:
claim = pywikibot.Claim(self.repo, 'P3254')
target = ('https://www.wikidata.org/wiki/'
'Wikidata:Property_proposal/Archive/{}#{}').format(
textvalue, prop.id)
claim.setTarget(target)
claim.addSource(self.get_source())
return self.user_add_claim(prop,
claim,
summary=self.make_summary())
return False
def generator(self):
"""Retrieve new users."""
if globalvar.timeoffset != 0:
start = self.site.server_time() - timedelta(
minutes=globalvar.timeoffset)
else:
start = globalvar.offset
for ue in self.site.logevents('newusers',
total=globalvar.queryLimit,
start=start):
if ue.action() == 'create' or (ue.action() == 'autocreate'
and globalvar.welcomeAuto):
try:
user = ue.page()
except HiddenKeyError:
pywikibot.exception()
else:
yield user
def parse(self) -> None:
"""Parse the page."""
text = removeDisabledParts(self.text, tags=EXCEPTIONS, site=self.site)
wikicode = mwparserfromhell.parse(text, skip_style_tags=True)
for section in wikicode.get_sections(flat=True, include_lead=False):
heading = section.filter_headings()[0]
section_title = str(heading.title).lower()
for mode in self.MODES:
if mode in section_title:
self.mode = mode
break
else:
continue
try:
self._parse_section(str(section))
except (ValueError, pywikibot.Error):
pywikibot.exception(tb=True)
self._check_run()
def revert(self, item) -> Union[str, bool]:
"""Revert a single item."""
page = pywikibot.Page(self.site, item['title'])
history = list(page.revisions(total=2))
if len(history) <= 1:
return False
rev = history[1]
pywikibot.output(
color_format(
'\n\n>>> {lightpurple}{0}{default} <<<',
page.title(as_link=True, force_interwiki=True, textlink=True)))
if not self.opt.rollback:
comment = i18n.twtranslate(self.site, 'revertbot-revert', {
'revid': rev.revid,
'author': rev.user,
'timestamp': rev.timestamp
})
if self.opt.comment:
comment += ': ' + self.opt.comment
old = page.text
page.text = page.getOldVersion(rev.revid)
pywikibot.showDiff(old, page.text)
page.save(comment)
return comment
try:
self.site.rollbackpage(page, user=self.user, markbot=True)
except APIError as e:
if e.code == 'badtoken':
pywikibot.error(
'There was an API token error rollbacking the edit')
return False
except Error:
pass
else:
return 'The edit(s) made in {} by {} was rollbacked'.format(
page.title(), self.user)
pywikibot.exception()
return False
def generator(self):
if not self.getOption('date'):
self.options['date'] = pywikibot.input(
'Enter the date when the reports were created')
url = '%s/%s/%s/' % (self.labs_url, self.sub_directory,
self.getOption('date'))
response = urlopen(url)
regex = re.compile('href="([^"]+)"')
not_yet = bool(self.getOption('start'))
for match in regex.finditer(response.read().decode()):
file_name = match.group(1)
dbname = file_name.partition('-')[0]
if not_yet:
if dbname == self.getOption('start'):
not_yet = False
else:
continue
if dbname in self.getOption('skip'):
continue
try:
site = pywikibot.site.APISite.fromDBName(dbname)
except ValueError as e:
pywikibot.exception(e)
continue
pywikibot.output("Working on '%s'" % dbname)
resp = urlopen(url + file_name)
lines = resp.readlines()
if not lines:
continue
lines.pop(0)
f = map(methodcaller('decode', 'utf-8'), lines)
for row in csv.reader(f, delimiter='\t'):
if len(set(row[1:3])) > 1:
continue
if int(row[1]) not in self.namespaces:
continue
if '#' in row[4]:
continue
yield pywikibot.Page(site, row[3], ns=int(row[1]))
def getTags(self) -> List[str]:
try:
try:
r = self.getRevisions(self.revInfo.newRevision, self.revInfo.newRevision)
except pywikibot.data.api.APIError as e:
if e.code == "badid_rvstartid":
self.output("getTags() rvstartid not found. Retrying... ")
time.sleep(10)
r = self.getRevisions(self.revInfo.newRevision, self.revInfo.newRevision)
else:
raise
except Exception as e:
pywikibot.exception(e)
return []
else:
try:
return cast(List[str], r[0]["tags"])
except KeyError:
return []
def treat_page(self) -> None:
"""Treat page with the cosmetic toolkit.
.. versionchanged:: 7.0
skip if InvalidPageError is raised
"""
cc_toolkit = CosmeticChangesToolkit(self.current_page,
ignore=self.opt.ignore)
try:
old_text = self.current_page.text
except InvalidPageError:
pywikibot.exception()
return
new_text = cc_toolkit.change(old_text)
if new_text is not False:
self.put_current(new_text=new_text,
summary=self.opt.summary,
asynchronous=self.opt['async'])
def treat_page(self):
"""Change all redirects from the current page to actual links."""
try:
newtext = self.current_page.text
except InvalidPageError:
pywikibot.exception()
return
with ThreadPoolExecutor() as executor:
futures = {
executor.submit(self.get_target, p)
for p in self.current_page.linkedPages()
}
for future in as_completed(futures):
page, target = future.result()
if target:
newtext = self.replace_links(newtext, page, target)
self.put_current(newtext)
def revert(self, item):
"""Revert a single item."""
page = pywikibot.Page(self.site, item["title"])
history = list(page.revisions(total=2))
if len(history) > 1:
rev = history[1]
else:
return False
comment = i18n.twtranslate(
self.site, "revertbot-revert", {"revid": rev.revid, "author": rev.user, "timestamp": rev.timestamp}
)
if self.comment:
comment += ": " + self.comment
pywikibot.output(
color_format(
"\n\n>>> {lightpurple}{0}{default} <<<", page.title(asLink=True, forceInterwiki=True, textlink=True)
)
)
if not self.rollback:
old = page.text
page.text = rev.text
pywikibot.showDiff(old, page.text)
page.save(comment)
return comment
try:
pywikibot.data.api.Request(
self.site,
parameters={
"action": "rollback",
"title": page,
"user": self.user,
"token": rev.rollbacktoken,
"markbot": True,
},
).submit()
except pywikibot.data.api.APIError as e:
if e.code == "badtoken":
pywikibot.error("There was an API token error rollbacking the edit")
else:
pywikibot.exception()
return False
return "The edit(s) made in %s by %s was rollbacked" % (page.title(), self.user)
def revert(self, item):
page = pywikibot.Page(self.site, item['title'])
history = list(page.revisions(total=2))
if len(history) > 1:
rev = history[1]
else:
return False
comment = i18n.twtranslate(self.site, 'revertbot-revert', {
'revid': rev.revid,
'author': rev.user,
'timestamp': rev.timestamp
})
if self.comment:
comment += ': ' + self.comment
pywikibot.output(
color_format(
'\n\n>>> {lightpurple}{0}{default} <<<',
page.title(asLink=True, forceInterwiki=True, textlink=True)))
if not self.rollback:
old = page.text
page.text = rev.text
pywikibot.showDiff(old, page.text)
page.save(comment)
return comment
try:
pywikibot.data.api.Request(self.site,
parameters={
'action': 'rollback',
'title': page,
'user': self.user,
'token': rev.rollbacktoken,
'markbot': True
}).submit()
except pywikibot.data.api.APIError as e:
if e.code == 'badtoken':
pywikibot.error(
"There was an API token error rollbacking the edit")
else:
pywikibot.exception()
return False
return u"The edit(s) made in %s by %s was rollbacked" % (page.title(),
self.user)
def test_exception_tb(self):
try:
raise TestExceptionError('Testing Exception')
except TestExceptionError:
pywikibot.exception('exception', tb=True)
self.assertEqual(newstdout.getvalue(), '')
stderrlines = newstderr.getvalue().split('\n')
self.assertEqual(stderrlines[0],
'ERROR: TestExceptionError: Testing Exception')
self.assertEqual(stderrlines[1], 'Traceback (most recent call last):')
self.assertEqual(stderrlines[3],
" raise TestExceptionError('Testing Exception')")
end_str = ': Testing Exception'
traceback_line = stderrlines[4 + (PYTHON_VERSION >= (3, 11))]
self.assertTrue(
traceback_line.endswith(end_str),
'\n{!r} does not end with {!r}'.format(traceback_line, end_str))
self.assertNotEqual(stderrlines[-1], '\n')
def number_of_ids(self, textvalue):
prop = self.current_page
if prop.type == 'external-id' and 'P4876' not in prop.claims:
remove = False
match = self.regexes['quantity'].search(textvalue)
if match:
try:
num = int(match.group('value'))
except ValueError as e:
pywikibot.exception(e)
else:
target = pywikibot.WbQuantity(num, site=self.repo)
claim = pywikibot.Claim(self.repo, 'P4876')
claim.setTarget(target)
claim.addSource(self.get_source())
remove = self.user_add_claim(
prop, claim, summary=self.make_summary())
else:
remove = True
return remove
def test_exception_tb(self):
class TestException(Exception):
pass
try:
raise TestException("Testing Exception")
except TestException:
pywikibot.exception("exception", tb=True)
self.assertEqual(newstdout.getvalue(), "")
stderrlines = newstderr.getvalue().split("\n")
self.assertEqual(stderrlines[0],
"ERROR: TestException: Testing Exception")
self.assertEqual(stderrlines[1],
"Traceback (most recent call last):")
self.assertEqual(
stderrlines[3],
""" raise TestException("Testing Exception")""")
self.assertEqual(stderrlines[4],
"TestException: Testing Exception")
self.assertNotEqual(stderrlines[-1], "\n")
def number_of_ids(self, textvalue):
prop = self.current_page
if prop.type == 'external-id' and 'P4876' not in prop.claims:
remove = False
match = self.regexes['quantity'].search(textvalue)
if match:
try:
num = int(match.group('value'))
except ValueError as e:
pywikibot.exception(e)
else:
target = pywikibot.WbQuantity(num, site=self.repo)
claim = pywikibot.Claim(self.repo, 'P4876')
claim.setTarget(target)
claim.addSource(self.get_source())
remove = self.user_add_claim(prop,
claim,
summary=self.make_summary())
else:
remove = True
return remove
def revert(self, item):
"""Revert a single item."""
page = pywikibot.Page(self.site, item['title'])
history = list(page.revisions(total=2))
if len(history) > 1:
rev = history[1]
else:
return False
comment = i18n.twtranslate(
self.site, 'revertbot-revert',
{'revid': rev.revid,
'author': rev.user,
'timestamp': rev.timestamp})
if self.comment:
comment += ': ' + self.comment
pywikibot.output(color_format(
'\n\n>>> {lightpurple}{0}{default} <<<',
page.title(asLink=True, forceInterwiki=True, textlink=True)))
if not self.rollback:
old = page.text
page.text = page.getOldVersion(rev.revid)
pywikibot.showDiff(old, page.text)
page.save(comment)
return comment
try:
pywikibot.data.api.Request(
self.site, parameters={'action': 'rollback',
'title': page,
'user': self.user,
'token': rev.rollbacktoken,
'markbot': True}).submit()
except pywikibot.data.api.APIError as e:
if e.code == 'badtoken':
pywikibot.error(
'There was an API token error rollbacking the edit')
else:
pywikibot.exception()
return False
return 'The edit(s) made in %s by %s was rollbacked' % (page.title(),
self.user)
def revert(self, item):
history = pywikibot.Page(self.site, item['title']).fullVersionHistory(
total=2, rollback=self.rollback)
if len(history) > 1:
rev = history[1]
else:
return False
comment = i18n.twtranslate(pywikibot.Site(), 'revertbot-revert', {
'revid': rev[0],
'author': rev[2],
'timestamp': rev[1]
})
if self.comment:
comment += ': ' + self.comment
page = pywikibot.Page(self.site, item['title'])
pywikibot.output(
u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title(asLink=True, forceInterwiki=True, textlink=True))
if not self.rollback:
old = page.text
page.text = rev[3]
pywikibot.showDiff(old, page.text)
page.save(comment)
return comment
try:
pywikibot.data.api.Request(action="rollback",
title=page.title(),
user=self.user,
token=rev[4],
markbot=1).submit()
except pywikibot.data.api.APIError as e:
if e.code == 'badtoken':
pywikibot.error(
"There was an API token error rollbacking the edit")
else:
pywikibot.exception()
return False
return u"The edit(s) made in %s by %s was rollbacked" % (page.title(),
self.user)
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
"""
opt_all = False
opt_new = False
opt_count = False
opt_count_all = False
for arg in pywikibot.handle_args(args):
if arg in ('-all', '-update'):
opt_all = True
elif arg == '-new':
opt_new = True
elif arg == '-count':
opt_count = True
elif arg == '-count:all':
opt_count_all = True
if opt_all:
refresh_all()
elif opt_new:
refresh_new()
elif opt_count:
count_watchlist()
elif opt_count_all:
count_watchlist_all()
else:
site = pywikibot.Site()
count_watchlist(site)
watchlist = list(site.watched_pages(force=True))
for page in watchlist:
try:
pywikibot.stdout(page.title())
except pywikibot.InvalidTitle:
pywikibot.exception()
def get_target(page):
"""Get the target page for a given page."""
target = None
if not page.exists():
with suppress(pywikibot.NoMoveTarget, pywikibot.CircularRedirect,
pywikibot.InvalidTitle):
target = page.moved_target()
elif page.isRedirectPage():
try:
target = page.getRedirectTarget()
except (pywikibot.CircularRedirect, pywikibot.InvalidTitle):
pass
except RuntimeError:
pywikibot.exception()
else:
section = target.section()
if section and not does_text_contain_section(
target.text, section):
pywikibot.warning(
'Section #{} not found on page {}'.format(
section,
target.title(as_link=True, with_section=False)))
target = None
return target
def treat_page(self) -> None:
"""Process one page."""
self.check_disabled()
try:
errors = self.validate_svg()
except (AssertionError, RequestException, RuntimeError):
pywikibot.exception()
return
if errors:
n_errors = len(errors)
new_tpl = Template('Invalid SVG')
new_tpl.add('1', n_errors)
summary = 'W3C invalid SVG: {} error{}'.format(
n_errors, 's' if n_errors > 1 else '')
else:
new_tpl = Template('Valid SVG')
summary = 'W3C valid SVG'
wikicode = mwparserfromhell.parse(self.current_page.text,
skip_style_tags=True)
for tpl in wikicode.ifilter_templates():
try:
template = pywikibot.Page(
self.site,
removeDisabledParts(str(tpl.name), site=self.site).strip(),
ns=10,
)
template.title()
except pywikibot.InvalidTitle:
continue
if template in self.templates:
wikicode.replace(tpl, new_tpl)
break
else:
wikicode.insert(0, '\n')
wikicode.insert(0, new_tpl)
self.put_current(str(wikicode), summary=summary, minor=not errors)
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
"""
filename = None
pagename = None
namespace = None
salt = None
force = False
calc = None
sleep = 10
args = []
def if_arg_value(arg, name):
if arg.startswith(name):
yield arg[len(name) + 1:]
for arg in pywikibot.handle_args(args):
for v in if_arg_value(arg, '-file'):
filename = v
for v in if_arg_value(arg, '-locale'):
# Required for english month names
locale.setlocale(locale.LC_TIME, v.encode('utf8'))
for v in if_arg_value(arg, '-timezone'):
os.environ['TZ'] = v.timezone
# Or use the preset value
if hasattr(time, 'tzset'):
time.tzset()
for v in if_arg_value(arg, '-calc'):
calc = v
for v in if_arg_value(arg, '-salt'):
salt = v
for v in if_arg_value(arg, '-force'):
force = True
for v in if_arg_value(arg, '-filename'):
filename = v
for v in if_arg_value(arg, '-page'):
pagename = v
for v in if_arg_value(arg, '-namespace'):
namespace = v
for v in if_arg_value(arg, '-sleep'):
sleep = int(v)
if not arg.startswith('-'):
args.append(arg)
site = pywikibot.Site()
if calc:
if not salt:
pywikibot.bot.suggest_help(missing_parameters=['-salt'])
return False
page = pywikibot.Page(site, calc)
if page.exists():
calc = page.title()
else:
pywikibot.output(u'NOTE: the specified page "%s" does not (yet) exist.' % calc)
s = md5()
s.update(salt + '\n')
s.update(calc + '\n')
pywikibot.output(u'key = ' + s.hexdigest())
return
if not salt:
salt = ''
if not args:
pywikibot.bot.suggest_help(additional_text='No template was specified.')
return False
for a in args:
pagelist = []
a = pywikibot.Page(site, a, ns=10).title()
if not filename and not pagename:
if namespace is not None:
ns = [str(namespace)]
else:
ns = []
for pg in generate_transclusions(site, a, ns):
pagelist.append(pg)
if filename:
for pg in open(filename, 'r').readlines():
pagelist.append(pywikibot.Page(site, pg, ns=10))
if pagename:
pagelist.append(pywikibot.Page(site, pagename, ns=3))
pagelist = sorted(pagelist)
for pg in iter(pagelist):
pywikibot.output(u'Processing %s' % pg)
# Catching exceptions, so that errors in one page do not bail out
# the entire process
try:
archiver = PageArchiver(pg, a, salt, force)
archiver.run()
except ArchiveBotSiteConfigError as e:
# no stack trace for errors originated by pages on-site
pywikibot.error('Missing or malformed template in page %s: %s'
% (pg, e))
except Exception:
pywikibot.error(u'Error occurred while processing page %s' % pg)
pywikibot.exception(tb=True)
finally:
time.sleep(sleep)
#
from __future__ import absolute_import, unicode_literals
import re
import sys
import pywikibot
from pywikibot import i18n
try:
import pycountry
except ImportError:
pywikibot.error('This script requires the python-pycountry module')
pywikibot.error('See: https://pypi.python.org/pypi/pycountry')
pywikibot.exception()
sys.exit(1)
class StatesRedirectBot(pywikibot.Bot):
"""Bot class used for implementation of re-direction norms."""
def __init__(self, start, force):
"""Constructor.
Parameters:
@param start:xxx Specify the place in the alphabet to start
searching.
@param force: Don't ask whether to create pages, just create
them.
