[Pywikipedia-l] SVN: [5675] trunk/pywikipedia
siebrand at svn.wikimedia.org
siebrand at svn.wikimedia.org
Sat Jul 5 18:21:04 UTC 2008
Revision: 5675
Author: siebrand
Date: 2008-07-05 18:21:03 +0000 (Sat, 05 Jul 2008)
Log Message:
-----------
svn:eol-style:native
Modified Paths:
--------------
trunk/pywikipedia/archive/mediawiki_messages.py
trunk/pywikipedia/category_redirect.py
trunk/pywikipedia/commonsdelinker/plugins.txt
trunk/pywikipedia/families/README-family.txt
trunk/pywikipedia/protect.py
Property Changed:
----------------
trunk/pywikipedia/archive/mediawiki_messages.py
trunk/pywikipedia/category_redirect.py
trunk/pywikipedia/commonsdelinker/plugins.txt
trunk/pywikipedia/families/README-family.txt
trunk/pywikipedia/protect.py
Modified: trunk/pywikipedia/archive/mediawiki_messages.py
===================================================================
--- trunk/pywikipedia/archive/mediawiki_messages.py 2008-07-05 12:57:13 UTC (rev 5674)
+++ trunk/pywikipedia/archive/mediawiki_messages.py 2008-07-05 18:21:03 UTC (rev 5675)
@@ -1,218 +1,218 @@
-# -*- coding: utf-8 -*-
-"""
-Allows access to the MediaWiki messages, that's the label texts of the MediaWiki
-software in the current language. These can be used in other bots.
-
-The function refresh_messages() downloads all the current messages and saves
-them to disk. It is run automatically when a bot first tries to access one of
-the messages. It can be updated manually by running this script, e.g. when
-somebody changed the current message at the wiki. The texts will also be
-reloaded automatically once a month.
-
-Syntax: python mediawiki_messages [-all]
-
-Command line options:
- -refresh - Reloads messages for the home wiki or for the one defined via
- the -lang and -family parameters.
-
- -all - Reloads messages for all wikis where messages are already present
-
- If another parameter is given, it will be interpreted as a MediaWiki key.
- The script will then output the respective value, without refreshing..
-
-"""
-
-# (C) Daniel Herding, 2004
-#
-# Distributed under the terms of the MIT license.
-
-##THIS MODULE IS DEPRECATED AND HAS BEEN REPLACED BY NEW FUNCTIONALITY IN
-##WIKIPEDIA.PY. It is being retained solely for compatibility in case any
-##custom-written bots rely upon it. Bot authors should replace any uses
-##of this module as follows:
-##
-## OLD: mediawiki_messages.get(key, site)
-## NEW: site.mediawiki_message(key)
-##
-## OLD: mediawiki_messages.has(key, site)
-## NEW: site.has_mediawiki_message(key)
-##
-## OLD: mediawiki_messages.makepath(path)
-## NEW: wikipedia.makepath(path)
-##
-##########################################################################
-
-import warnings
-warnings.warn(
-"""The mediawiki_messages module is deprecated and no longer
-maintained; see the source code for new methods to replace
-calls to this module.""",
- DeprecationWarning, stacklevel=2)
-
-
-import wikipedia
-import re, sys, pickle
-import os.path
-import time
-import codecs
-import urllib
-from BeautifulSoup import *
-
-__version__='$Id: mediawiki_messages.py 3731 2007-06-20 14:42:55Z russblau $'
-
-loaded = {}
-
-def get(key, site = None, allowreload = True):
- site = site or wikipedia.getSite()
- if loaded.has_key(site):
- # Use cached copy if it exists.
- dictionary = loaded[site]
- else:
- fn = 'mediawiki-messages/mediawiki-messages-%s-%s.dat' % (site.family.name, site.lang)
- try:
- # find out how old our saved dump is (in seconds)
- file_age = time.time() - os.path.getmtime(fn)
- # if it's older than 1 month, reload it
- if file_age > 30 * 24 * 60 * 60:
- print 'Current MediaWiki message dump is one month old, reloading'
- refresh_messages(site)
- except OSError:
- # no saved dumped exists yet
- refresh_messages(site)
- f = open(fn, 'r')
- dictionary = pickle.load(f)
- f.close()
- loaded[site] = dictionary
- key = key[0].lower() + key[1:]
- if dictionary.has_key(key):
- return dictionary[key]
- elif allowreload:
- refresh_messages(site = site)
- return get(key, site = site, allowreload = False)
- else:
- raise KeyError('MediaWiki Key %s not found' % key)
-
-def has(key, site = None, allowreload = True):
- try:
- get(key, site, allowreload)
- return True
- except KeyError:
- return False
-
-def makepath(path):
- """ creates missing directories for the given path and
- returns a normalized absolute version of the path.
-
- - if the given path already exists in the filesystem
- the filesystem is not modified.
-
- - otherwise makepath creates directories along the given path
- using the dirname() of the path. You may append
- a '/' to the path if you want it to be a directory path.
-
- from holger at trillke.net 2002/03/18
- """
- from os import makedirs
- from os.path import normpath,dirname,exists,abspath
-
- dpath = normpath(dirname(path))
- if not exists(dpath): makedirs(dpath)
- return normpath(abspath(path))
-
-def refresh_messages(site = None):
- site = site or wikipedia.getSite()
- # get 'all messages' special page's path
- path = site.allmessages_address()
- print 'Retrieving MediaWiki messages for %s' % repr(site)
- wikipedia.put_throttle() # It actually is a get, but a heavy one.
- allmessages = site.getUrl(path)
-
- print 'Parsing MediaWiki messages'
- soup = BeautifulSoup(allmessages,
- convertEntities=BeautifulSoup.HTML_ENTITIES)
- # The MediaWiki namespace in URL-encoded format, as it can contain
- # non-ASCII characters and spaces.
- quotedMwNs = urllib.quote(site.namespace(8).replace(' ', '_').encode(site.encoding()))
- mw_url = site.path() + "?title=" + quotedMwNs + ":"
- altmw_url = site.path() + "/" + quotedMwNs + ":"
- nicemw_url = site.nice_get_address(quotedMwNs + ":")
- shortmw_url = "/" + quotedMwNs + ":"
- ismediawiki = lambda url:url and (url.startswith(mw_url)
- or url.startswith(altmw_url)
- or url.startswith(nicemw_url)
- or url.startswith(shortmw_url))
- # we will save the found key:value pairs here
- dictionary = {}
-
- try:
- for keytag in soup('a', href=ismediawiki):
- # Key strings only contain ASCII characters, so we can save them as
- # strs
- key = str(keytag.find(text=True))
- keyrow = keytag.parent.parent
- if keyrow['class'] == "orig":
- valrow = keyrow.findNextSibling('tr')
- assert valrow['class'] == "new"
- value = unicode(valrow.td.string).strip()
- elif keyrow['class'] == 'def':
- value = unicode(keyrow('td')[1].string).strip()
- else:
- raise AssertionError("Unknown tr class value: %s" % keyrow['class'])
- dictionary[key] = value
- except Exception, e:
- wikipedia.debugDump( 'MediaWiki_Msg', site, u'%s: %s while processing URL: %s' % (repr(e), str(e), unicode(path)), allmessages)
- raise
-
- # Save the dictionary to disk
- # The file is stored in the mediawiki_messages subdir. Create if necessary.
- if dictionary == {}:
- wikipedia.debugDump( 'MediaWiki_Msg', site, u'Error URL: '+unicode(path), allmessages )
- sys.exit()
- else:
- f = open(makepath('mediawiki-messages/mediawiki-messages-%s-%s.dat' % (site.family.name, site.lang)), 'w')
- pickle.dump(dictionary, f)
- f.close()
- print "Loaded %i values from %s" % (len(dictionary.keys()), site)
- #print dictionary['sitestatstext']
-
-def refresh_all_messages():
- import dircache, time
- filenames = dircache.listdir('mediawiki-messages')
- message_filenameR = re.compile('mediawiki-messages-([a-z:]+)-([a-z:]+).dat')
- for filename in filenames:
- match = message_filenameR.match(filename)
- if match:
- family = match.group(1)
- lang = match.group(2)
- site = wikipedia.getSite(code = lang, fam = family)
- refresh_messages(site)
-
-def main():
- refresh_all = False
- refresh = False
- key = None
- for arg in wikipedia.handleArgs():
- if arg == '-all':
- refresh_all = True
- elif arg == '-refresh':
- refresh = True
- else:
- key = arg
- if key:
- wikipedia.output(get(key), toStdout = True)
- elif refresh_all:
- refresh_all_messages()
- elif refresh:
- refresh_messages(wikipedia.getSite())
- else:
- wikipedia.showHelp('mediawiki_messages')
-
-if __name__ == "__main__":
- try:
- main()
- except:
- wikipedia.stopme()
- raise
- else:
- wikipedia.stopme()
-
+# -*- coding: utf-8 -*-
+"""
+Allows access to the MediaWiki messages, that's the label texts of the MediaWiki
+software in the current language. These can be used in other bots.
+
+The function refresh_messages() downloads all the current messages and saves
+them to disk. It is run automatically when a bot first tries to access one of
+the messages. It can be updated manually by running this script, e.g. when
+somebody changed the current message at the wiki. The texts will also be
+reloaded automatically once a month.
+
+Syntax: python mediawiki_messages [-all]
+
+Command line options:
+ -refresh - Reloads messages for the home wiki or for the one defined via
+ the -lang and -family parameters.
+
+ -all - Reloads messages for all wikis where messages are already present
+
+ If another parameter is given, it will be interpreted as a MediaWiki key.
+ The script will then output the respective value, without refreshing..
+
+"""
+
+# (C) Daniel Herding, 2004
+#
+# Distributed under the terms of the MIT license.
+
+##THIS MODULE IS DEPRECATED AND HAS BEEN REPLACED BY NEW FUNCTIONALITY IN
+##WIKIPEDIA.PY. It is being retained solely for compatibility in case any
+##custom-written bots rely upon it. Bot authors should replace any uses
+##of this module as follows:
+##
+## OLD: mediawiki_messages.get(key, site)
+## NEW: site.mediawiki_message(key)
+##
+## OLD: mediawiki_messages.has(key, site)
+## NEW: site.has_mediawiki_message(key)
+##
+## OLD: mediawiki_messages.makepath(path)
+## NEW: wikipedia.makepath(path)
+##
+##########################################################################
+
+import warnings
+warnings.warn(
+"""The mediawiki_messages module is deprecated and no longer
+maintained; see the source code for new methods to replace
+calls to this module.""",
+ DeprecationWarning, stacklevel=2)
+
+
+import wikipedia
+import re, sys, pickle
+import os.path
+import time
+import codecs
+import urllib
+from BeautifulSoup import *
+
+__version__='$Id: mediawiki_messages.py 3731 2007-06-20 14:42:55Z russblau $'
+
+loaded = {}
+
+def get(key, site = None, allowreload = True):
+ site = site or wikipedia.getSite()
+ if loaded.has_key(site):
+ # Use cached copy if it exists.
+ dictionary = loaded[site]
+ else:
+ fn = 'mediawiki-messages/mediawiki-messages-%s-%s.dat' % (site.family.name, site.lang)
+ try:
+ # find out how old our saved dump is (in seconds)
+ file_age = time.time() - os.path.getmtime(fn)
+ # if it's older than 1 month, reload it
+ if file_age > 30 * 24 * 60 * 60:
+ print 'Current MediaWiki message dump is one month old, reloading'
+ refresh_messages(site)
+ except OSError:
+ # no saved dumped exists yet
+ refresh_messages(site)
+ f = open(fn, 'r')
+ dictionary = pickle.load(f)
+ f.close()
+ loaded[site] = dictionary
+ key = key[0].lower() + key[1:]
+ if dictionary.has_key(key):
+ return dictionary[key]
+ elif allowreload:
+ refresh_messages(site = site)
+ return get(key, site = site, allowreload = False)
+ else:
+ raise KeyError('MediaWiki Key %s not found' % key)
+
+def has(key, site = None, allowreload = True):
+ try:
+ get(key, site, allowreload)
+ return True
+ except KeyError:
+ return False
+
+def makepath(path):
+ """ creates missing directories for the given path and
+ returns a normalized absolute version of the path.
+
+ - if the given path already exists in the filesystem
+ the filesystem is not modified.
+
+ - otherwise makepath creates directories along the given path
+ using the dirname() of the path. You may append
+ a '/' to the path if you want it to be a directory path.
+
+ from holger at trillke.net 2002/03/18
+ """
+ from os import makedirs
+ from os.path import normpath,dirname,exists,abspath
+
+ dpath = normpath(dirname(path))
+ if not exists(dpath): makedirs(dpath)
+ return normpath(abspath(path))
+
+def refresh_messages(site = None):
+ site = site or wikipedia.getSite()
+ # get 'all messages' special page's path
+ path = site.allmessages_address()
+ print 'Retrieving MediaWiki messages for %s' % repr(site)
+ wikipedia.put_throttle() # It actually is a get, but a heavy one.
+ allmessages = site.getUrl(path)
+
+ print 'Parsing MediaWiki messages'
+ soup = BeautifulSoup(allmessages,
+ convertEntities=BeautifulSoup.HTML_ENTITIES)
+ # The MediaWiki namespace in URL-encoded format, as it can contain
+ # non-ASCII characters and spaces.
+ quotedMwNs = urllib.quote(site.namespace(8).replace(' ', '_').encode(site.encoding()))
+ mw_url = site.path() + "?title=" + quotedMwNs + ":"
+ altmw_url = site.path() + "/" + quotedMwNs + ":"
+ nicemw_url = site.nice_get_address(quotedMwNs + ":")
+ shortmw_url = "/" + quotedMwNs + ":"
+ ismediawiki = lambda url:url and (url.startswith(mw_url)
+ or url.startswith(altmw_url)
+ or url.startswith(nicemw_url)
+ or url.startswith(shortmw_url))
+ # we will save the found key:value pairs here
+ dictionary = {}
+
+ try:
+ for keytag in soup('a', href=ismediawiki):
+ # Key strings only contain ASCII characters, so we can save them as
+ # strs
+ key = str(keytag.find(text=True))
+ keyrow = keytag.parent.parent
+ if keyrow['class'] == "orig":
+ valrow = keyrow.findNextSibling('tr')
+ assert valrow['class'] == "new"
+ value = unicode(valrow.td.string).strip()
+ elif keyrow['class'] == 'def':
+ value = unicode(keyrow('td')[1].string).strip()
+ else:
+ raise AssertionError("Unknown tr class value: %s" % keyrow['class'])
+ dictionary[key] = value
+ except Exception, e:
+ wikipedia.debugDump( 'MediaWiki_Msg', site, u'%s: %s while processing URL: %s' % (repr(e), str(e), unicode(path)), allmessages)
+ raise
+
+ # Save the dictionary to disk
+ # The file is stored in the mediawiki_messages subdir. Create if necessary.
+ if dictionary == {}:
+ wikipedia.debugDump( 'MediaWiki_Msg', site, u'Error URL: '+unicode(path), allmessages )
+ sys.exit()
+ else:
+ f = open(makepath('mediawiki-messages/mediawiki-messages-%s-%s.dat' % (site.family.name, site.lang)), 'w')
+ pickle.dump(dictionary, f)
+ f.close()
+ print "Loaded %i values from %s" % (len(dictionary.keys()), site)
+ #print dictionary['sitestatstext']
+
+def refresh_all_messages():
+ import dircache, time
+ filenames = dircache.listdir('mediawiki-messages')
+ message_filenameR = re.compile('mediawiki-messages-([a-z:]+)-([a-z:]+).dat')
+ for filename in filenames:
+ match = message_filenameR.match(filename)
+ if match:
+ family = match.group(1)
+ lang = match.group(2)
+ site = wikipedia.getSite(code = lang, fam = family)
+ refresh_messages(site)
+
+def main():
+ refresh_all = False
+ refresh = False
+ key = None
+ for arg in wikipedia.handleArgs():
+ if arg == '-all':
+ refresh_all = True
+ elif arg == '-refresh':
+ refresh = True
+ else:
+ key = arg
+ if key:
+ wikipedia.output(get(key), toStdout = True)
+ elif refresh_all:
+ refresh_all_messages()
+ elif refresh:
+ refresh_messages(wikipedia.getSite())
+ else:
+ wikipedia.showHelp('mediawiki_messages')
+
+if __name__ == "__main__":
+ try:
+ main()
+ except:
+ wikipedia.stopme()
+ raise
+ else:
+ wikipedia.stopme()
+
Property changes on: trunk/pywikipedia/archive/mediawiki_messages.py
___________________________________________________________________
Name: svn:eol-style
+ native
Modified: trunk/pywikipedia/category_redirect.py
===================================================================
--- trunk/pywikipedia/category_redirect.py 2008-07-05 12:57:13 UTC (rev 5674)
+++ trunk/pywikipedia/category_redirect.py 2008-07-05 18:21:03 UTC (rev 5675)
@@ -1,71 +1,71 @@
-#!/usr/bin/python
-# -*- coding: utf-8 -*-
-"""
-Script to clean up http://commons.wikimedia.org/wiki/Category:Non-empty_category_redirects
-
-Moves all images, pages and categories in redirect categories to the target category.
-
-"""
-
-#
-# (C) Multichill, 2008
-#
-# Distributed under the terms of the MIT license.
-#
-
-import wikipedia, config, catlib
-from category import *
-
-redirect_templates = [u'Category redirect', u'Categoryredirect', u'See cat', u'Seecat', u'Catredirect', u'Cat redirect', u'CatRed', u'Catredir']
-move_message = u'Moving from [[%s|%s]] to [[%s|%s]] (following [[Template:Category redirect|category redirect]])'
-
-def get_redirect_cat(category=None):
- '''
- Return the target category
- '''
- destination = None
- site = wikipedia.getSite(u'commons', u'commons')
- for template in category.templatesWithParams():
- if ((template[0] in redirect_templates) and (len(template[1]) > 0)):
- #destination = template[1][0];
- destination =catlib.Category(site, template[1][0])
- if not destination.exists():
- return None
- return destination
-
-
-def main():
- '''
- Main loop. Loop over all categories of Category:Non-empty_category_redirects and move all content.
- '''
-
- site = wikipedia.getSite(u'commons', u'commons')
- dirtycat = catlib.Category(site, u'Category:Non-empty category redirects')
- destination = None
- catbot = None
-
- for old_category in dirtycat.subcategories():
- destination = get_redirect_cat(old_category)
- if destination:
- wikipedia.output(destination.title())
- for page in old_category.articles():
- try:
- catlib.change_category(page, old_category, destination, move_message % (old_category.title(), old_category.titleWithoutNamespace(), destination.title(), destination.titleWithoutNamespace()))
- except wikipedia.IsRedirectPage:
- wikipedia.output(page.title() + u' is a redirect!')
- for cat in old_category.subcategories():
- try:
- catlib.change_category(cat, old_category, destination, move_message % (old_category.title(), old_category.titleWithoutNamespace(), destination.title(), destination.titleWithoutNamespace()))
- except wikipedia.IsRedirectPage:
- wikipedia.output(page.title() + u' is a redirect!')
- #Dummy edit to refresh the page, shouldnt show up in any logs.
- try:
- old_category.put(old_category.get())
- except:
- wikipedia.output(u'Dummy edit at ' + old_category.title() + u' failed')
-
-if __name__ == "__main__":
- try:
- main()
- finally:
- wikipedia.stopme()
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+"""
+Script to clean up http://commons.wikimedia.org/wiki/Category:Non-empty_category_redirects
+
+Moves all images, pages and categories in redirect categories to the target category.
+
+"""
+
+#
+# (C) Multichill, 2008
+#
+# Distributed under the terms of the MIT license.
+#
+
+import wikipedia, config, catlib
+from category import *
+
+redirect_templates = [u'Category redirect', u'Categoryredirect', u'See cat', u'Seecat', u'Catredirect', u'Cat redirect', u'CatRed', u'Catredir']
+move_message = u'Moving from [[%s|%s]] to [[%s|%s]] (following [[Template:Category redirect|category redirect]])'
+
+def get_redirect_cat(category=None):
+ '''
+ Return the target category
+ '''
+ destination = None
+ site = wikipedia.getSite(u'commons', u'commons')
+ for template in category.templatesWithParams():
+ if ((template[0] in redirect_templates) and (len(template[1]) > 0)):
+ #destination = template[1][0];
+ destination =catlib.Category(site, template[1][0])
+ if not destination.exists():
+ return None
+ return destination
+
+
+def main():
+ '''
+ Main loop. Loop over all categories of Category:Non-empty_category_redirects and move all content.
+ '''
+
+ site = wikipedia.getSite(u'commons', u'commons')
+ dirtycat = catlib.Category(site, u'Category:Non-empty category redirects')
+ destination = None
+ catbot = None
+
+ for old_category in dirtycat.subcategories():
+ destination = get_redirect_cat(old_category)
+ if destination:
+ wikipedia.output(destination.title())
+ for page in old_category.articles():
+ try:
+ catlib.change_category(page, old_category, destination, move_message % (old_category.title(), old_category.titleWithoutNamespace(), destination.title(), destination.titleWithoutNamespace()))
+ except wikipedia.IsRedirectPage:
+ wikipedia.output(page.title() + u' is a redirect!')
+ for cat in old_category.subcategories():
+ try:
+ catlib.change_category(cat, old_category, destination, move_message % (old_category.title(), old_category.titleWithoutNamespace(), destination.title(), destination.titleWithoutNamespace()))
+ except wikipedia.IsRedirectPage:
+ wikipedia.output(page.title() + u' is a redirect!')
+ #Dummy edit to refresh the page, shouldnt show up in any logs.
+ try:
+ old_category.put(old_category.get())
+ except:
+ wikipedia.output(u'Dummy edit at ' + old_category.title() + u' failed')
+
+if __name__ == "__main__":
+ try:
+ main()
+ finally:
+ wikipedia.stopme()
Property changes on: trunk/pywikipedia/category_redirect.py
___________________________________________________________________
Name: svn:eol-style
+ native
Modified: trunk/pywikipedia/commonsdelinker/plugins.txt
===================================================================
--- trunk/pywikipedia/commonsdelinker/plugins.txt 2008-07-05 12:57:13 UTC (rev 5674)
+++ trunk/pywikipedia/commonsdelinker/plugins.txt 2008-07-05 18:21:03 UTC (rev 5675)
@@ -1,53 +1,53 @@
-CommonsDelinker supports a plugin system, which allows modifying the delink and
-replace parameters on a case by case basis.
-
-Plugins should be registered in the configuration file. CommonsDelinker expects
-the configuration value CommonsDelinker['plugins'] to be an iterable object.
-The items of this iterable should be module.object strings of the plugin. The
-plugin is expected to reside as module.py in commonsdelinker/plugins. The
-object should exist and should be a callable object or type with an attribute
-'hook' being a string indicating the hook name.
-
-Some parameters are modyfiable by the plugin. Those include the mutable objects
-and some immutable object wrapped in an ImmutableByReference object. The value
-of such an object can be get/set by the get and set method. Modyfiable
-parameters are preceded by an ampersand & in this documentation.
-
-A hook that gives False as return value will terminate the hook chain and for
-most hooks also terminate the caller.
-
-== List of hooks and their parameters ==
-
-before_delink(image, usage, timestamp, admin, reason, replacement)
- Called once per image. Returing False will cancel delinking this image.
-
-simple_replace(page, summary, image, &replacement, match, groups)
-gallery_replace(page, summary, image, &replacement, match, groups)
-complex_replace(page, summary, image, &replacement, match, groups)
- Called each time an occerence is to be replaced. Returning False will not
- replace this occerence.
-
-before_save(page, text, &new_text, &summary)
- Called before the page is saved. Returning False will not save the page.
-
-after_delink(image, usage, timestamp, admin, reason, replacement)
- Called once per image after delink.
-
-== Example ==
-# Saves a diff for every delink.
-import difflib
-
-class Diff(object):
- hook = 'before_save'
- def __init__(self, CommonsDelinker):
- self.CommonsDelinker = CommonsDelinker
- def __call__(self, page, text, new_text, summary):
- diff = difflib.context_diff(
- text.encode('utf-8').splitlines(True),
- new_text.get().encode('utf-8').splitlines(True))
-
- f = open((u'diff/%s-%s-%s.txt' % (page.urlname().replace('/', '-'),
- page.site().dbName(), page.editTime())).encode('utf-8', 'ignore'), 'w')
-
- f.writelines(diff)
- f.close()
\ No newline at end of file
+CommonsDelinker supports a plugin system, which allows modifying the delink and
+replace parameters on a case by case basis.
+
+Plugins should be registered in the configuration file. CommonsDelinker expects
+the configuration value CommonsDelinker['plugins'] to be an iterable object.
+The items of this iterable should be module.object strings of the plugin. The
+plugin is expected to reside as module.py in commonsdelinker/plugins. The
+object should exist and should be a callable object or type with an attribute
+'hook' being a string indicating the hook name.
+
+Some parameters are modyfiable by the plugin. Those include the mutable objects
+and some immutable object wrapped in an ImmutableByReference object. The value
+of such an object can be get/set by the get and set method. Modyfiable
+parameters are preceded by an ampersand & in this documentation.
+
+A hook that gives False as return value will terminate the hook chain and for
+most hooks also terminate the caller.
+
+== List of hooks and their parameters ==
+
+before_delink(image, usage, timestamp, admin, reason, replacement)
+ Called once per image. Returing False will cancel delinking this image.
+
+simple_replace(page, summary, image, &replacement, match, groups)
+gallery_replace(page, summary, image, &replacement, match, groups)
+complex_replace(page, summary, image, &replacement, match, groups)
+ Called each time an occerence is to be replaced. Returning False will not
+ replace this occerence.
+
+before_save(page, text, &new_text, &summary)
+ Called before the page is saved. Returning False will not save the page.
+
+after_delink(image, usage, timestamp, admin, reason, replacement)
+ Called once per image after delink.
+
+== Example ==
+# Saves a diff for every delink.
+import difflib
+
+class Diff(object):
+ hook = 'before_save'
+ def __init__(self, CommonsDelinker):
+ self.CommonsDelinker = CommonsDelinker
+ def __call__(self, page, text, new_text, summary):
+ diff = difflib.context_diff(
+ text.encode('utf-8').splitlines(True),
+ new_text.get().encode('utf-8').splitlines(True))
+
+ f = open((u'diff/%s-%s-%s.txt' % (page.urlname().replace('/', '-'),
+ page.site().dbName(), page.editTime())).encode('utf-8', 'ignore'), 'w')
+
+ f.writelines(diff)
+ f.close()
Property changes on: trunk/pywikipedia/commonsdelinker/plugins.txt
___________________________________________________________________
Name: svn:eol-style
+ native
Modified: trunk/pywikipedia/families/README-family.txt
===================================================================
--- trunk/pywikipedia/families/README-family.txt 2008-07-05 12:57:13 UTC (rev 5674)
+++ trunk/pywikipedia/families/README-family.txt 2008-07-05 18:21:03 UTC (rev 5675)
@@ -1,183 +1,183 @@
-How to create a new family file to add a new wiki to the bot framework.
-
-(c) 2008, the Pywikipediabot team
-
-Copy and paste the text below "COPY HERE" into your favorite text editor, and
-save it as WIKINAME_family.py in the families/ subdirectory. Replace
-WIKINAME with the name you want to use for the new wiki family, making sure
-that it doesn't duplicate any existing name.
-
-A "family" is any group of wikis located on the same server; usually they
-are versions of the same type of content in different languages, but this
-isn't required. A family can consist of just one wiki, or more; if there is
-more than one wiki, each wiki needs to be identified by a unique code.
-
-After you copy the text, go through and edit it, based upon the comment
-lines. First, do a global search-and-replace to change all instances of
-'WIKINAME' to your actual wiki name. Everything in the example below is
-based on the bot's default settings, except for the namespace names, which
-are made-up examples. You only need to change it if your wiki's value is
-different from the default. You can delete anything that is not indicated as
-"REQUIRED", if your new wiki doesn't vary from the default settings.
-
-== COPY HERE ==
-
-# -*- coding: utf-8 -*- # REQUIRED
-import config, family, urllib # REQUIRED
-
-class Family(family.Family): # REQUIRED
- def __init__(self): # REQUIRED
- family.Family.__init__(self) # REQUIRED
- self.name = 'WIKINAME' # REQUIRED; replace with actual name
-
- self.langs = { # REQUIRED
- 'en': 'www.example.com', # Include one line for each wiki in family
- 'fr': 'www.example.fr', # in the format 'code': 'hostname',
- }
-
- # Translation used on all wikis for the different namespaces.
- # Most namespaces are inherited from family.Family.
- # Check the family.py file (in main directory) to see the standard
- # namespace translations for each known language.
-
- # You only need to enter translations that differ from the default.
- # There are two ways of entering namespace translations.
- # 1. If you only need to change the translation of a particular
- # namespace for one or two languages, use this format:
- self.namespaces[2]['en'] = u'Wikiuser'
- self.namespaces[3]['en'] = u'Wikiuser talk'
-
- # 2. If you need to change the translation for many languages
- # for the same namespace number, use this format (this is common
- # for namespaces 4 and 5, because these are usually given a
- # unique name for each wiki):
- self.namespaces[4] = {
- '_default': [u'WIKINAME', self.namespaces[4]['_default']], # REQUIRED
- 'de': 'Name des wiki',
- 'es': 'Nombre del wiki',
- 'fr': 'Nom du wiki',
- # ETC.
- }
-
- # Wikimedia wikis all use "bodyContent" as the id of the <div>
- # element that contains the actual page content; change this for
- # wikis that use something else (e.g., mozilla family)
- self.content_id = "bodyContent"
-
- # On most wikis page names must start with a capital letter, but some
- # languages don't use this. This should be a list of languages that
- # _don't_ require the first letter to be capitalized; e.g.,
- # self.nocapitalize = ['foo', 'bar']
- self.nocapitalize = []
-
- # SETTINGS FOR WIKIS THAT USE DISAMBIGUATION PAGES:
-
- # A list of disambiguation template names in different languages
- self.disambiguationTemplates = {
- 'en': ['disambig', 'disambiguation'],
- }
-
- # A list with the name of the category containing disambiguation
- # pages for the various languages. Only one category per language,
- # and without the namespace, so add things like:
- self.disambcatname = {
- 'en': "Disambiguation",
- }
-
- # SETTINGS FOR WIKIS THAT USE INTERLANGUAGE LINKS:
-
- # attop is a list of languages that prefer to have the interwiki
- # links at the top of the page.
- self.interwiki_attop = []
-
- # on_one_line is a list of languages that want the interwiki links
- # one-after-another on a single line
- self.interwiki_on_one_line = []
-
- # String used as separator between interwiki links and the text
- self.interwiki_text_separator = '\r\n\r\n'
-
- # Which languages have a special order for putting interlanguage links,
- # and what order is it? If a language is not in interwiki_putfirst,
- # alphabetical order on language code is used. For languages that are in
- # interwiki_putfirst, interwiki_putfirst is checked first, and
- # languages are put in the order given there. All other languages are put
- # after those, in code-alphabetical order.
- self.interwiki_putfirst = {}
-
- # Languages in interwiki_putfirst_doubled should have a number plus a list
- # of languages. If there are at least the number of interwiki links, all
- # languages in the list should be placed at the front as well as in the
- # normal list.
- self.interwiki_putfirst_doubled = {}
-
- # Some families, e. g. commons and meta, are not multilingual and
- # forward interlanguage links to another family (wikipedia).
- # These families can set this variable to the name of the target
- # family.
- self.interwiki_forward = None
-
- # Which language codes no longer exist and by which language code
- # should they be replaced. If for example the language with code xx:
- # has been replaced by code yy:, add {'xx':'yy'} to obsolete.
- # If all links to language xx: should be removed, add {'xx': None}.
- self.obsolete = {}
-
- # SETTINGS FOR CATEGORY LINKS:
-
- # Languages that want the category links at the top of the page
- self.category_attop = []
-
- # languages that want the category links
- # one-after-another on a single line
- self.category_on_one_line = []
-
- # String used as separator between category links and the text
- self.category_text_separator = '\r\n\r\n'
-
- # When both at the bottom should categories come after interwikilinks?
- self.categories_last = []
-
- # SETTINGS FOR LDAP AUTHENTICATION
- # If your wiki uses:
- # http://www.mediawiki.org/wiki/Extension:LDAP_Authentication.
- # then uncomment this line and define the user's domain required
- # at login.
- #self.name = 'domain here'
-
- def protocol(self, code):
- """
- Can be overridden to return 'https'. Other protocols are not supported.
- """
- return 'http'
-
- def scriptpath(self, code):
- """The prefix used to locate scripts on this wiki.
-
- This is the value displayed when you enter {{SCRIPTPATH}} on a
- wiki page (often displayed at [[Help:Variables]] if the wiki has
- copied the master help page correctly).
-
- The default value is the one used on Wikimedia Foundation wikis,
- but needs to be overridden in the family file for any wiki that
- uses a different value.
-
- """
- return '/w'
-
- # IMPORTANT: if your wiki does not support the api.php interface,
- # you must uncomment the second line of this method:
- def apipath(self, code):
- # raise NotImplementedError, "%s wiki family does not support api.php" % self.name
- return '%s/api.php' % self.scriptpath(code)
-
- # Which version of MediaWiki is used?
- def version(self, code):
- # Replace with the actual version being run on your wiki
- return '1.13alpha'
-
- def code2encoding(self, code):
- """Return the encoding for a specific language wiki"""
- # Most wikis nowadays use UTF-8, but change this if yours uses
- # a different encoding
- return 'utf-8'
+How to create a new family file to add a new wiki to the bot framework.
+
+(c) 2008, the Pywikipediabot team
+
+Copy and paste the text below "COPY HERE" into your favorite text editor, and
+save it as WIKINAME_family.py in the families/ subdirectory. Replace
+WIKINAME with the name you want to use for the new wiki family, making sure
+that it doesn't duplicate any existing name.
+
+A "family" is any group of wikis located on the same server; usually they
+are versions of the same type of content in different languages, but this
+isn't required. A family can consist of just one wiki, or more; if there is
+more than one wiki, each wiki needs to be identified by a unique code.
+
+After you copy the text, go through and edit it, based upon the comment
+lines. First, do a global search-and-replace to change all instances of
+'WIKINAME' to your actual wiki name. Everything in the example below is
+based on the bot's default settings, except for the namespace names, which
+are made-up examples. You only need to change it if your wiki's value is
+different from the default. You can delete anything that is not indicated as
+"REQUIRED", if your new wiki doesn't vary from the default settings.
+
+== COPY HERE ==
+
+# -*- coding: utf-8 -*- # REQUIRED
+import config, family, urllib # REQUIRED
+
+class Family(family.Family): # REQUIRED
+ def __init__(self): # REQUIRED
+ family.Family.__init__(self) # REQUIRED
+ self.name = 'WIKINAME' # REQUIRED; replace with actual name
+
+ self.langs = { # REQUIRED
+ 'en': 'www.example.com', # Include one line for each wiki in family
+ 'fr': 'www.example.fr', # in the format 'code': 'hostname',
+ }
+
+ # Translation used on all wikis for the different namespaces.
+ # Most namespaces are inherited from family.Family.
+ # Check the family.py file (in main directory) to see the standard
+ # namespace translations for each known language.
+
+ # You only need to enter translations that differ from the default.
+ # There are two ways of entering namespace translations.
+ # 1. If you only need to change the translation of a particular
+ # namespace for one or two languages, use this format:
+ self.namespaces[2]['en'] = u'Wikiuser'
+ self.namespaces[3]['en'] = u'Wikiuser talk'
+
+ # 2. If you need to change the translation for many languages
+ # for the same namespace number, use this format (this is common
+ # for namespaces 4 and 5, because these are usually given a
+ # unique name for each wiki):
+ self.namespaces[4] = {
+ '_default': [u'WIKINAME', self.namespaces[4]['_default']], # REQUIRED
+ 'de': 'Name des wiki',
+ 'es': 'Nombre del wiki',
+ 'fr': 'Nom du wiki',
+ # ETC.
+ }
+
+ # Wikimedia wikis all use "bodyContent" as the id of the <div>
+ # element that contains the actual page content; change this for
+ # wikis that use something else (e.g., mozilla family)
+ self.content_id = "bodyContent"
+
+ # On most wikis page names must start with a capital letter, but some
+ # languages don't use this. This should be a list of languages that
+ # _don't_ require the first letter to be capitalized; e.g.,
+ # self.nocapitalize = ['foo', 'bar']
+ self.nocapitalize = []
+
+ # SETTINGS FOR WIKIS THAT USE DISAMBIGUATION PAGES:
+
+ # A list of disambiguation template names in different languages
+ self.disambiguationTemplates = {
+ 'en': ['disambig', 'disambiguation'],
+ }
+
+ # A list with the name of the category containing disambiguation
+ # pages for the various languages. Only one category per language,
+ # and without the namespace, so add things like:
+ self.disambcatname = {
+ 'en': "Disambiguation",
+ }
+
+ # SETTINGS FOR WIKIS THAT USE INTERLANGUAGE LINKS:
+
+ # attop is a list of languages that prefer to have the interwiki
+ # links at the top of the page.
+ self.interwiki_attop = []
+
+ # on_one_line is a list of languages that want the interwiki links
+ # one-after-another on a single line
+ self.interwiki_on_one_line = []
+
+ # String used as separator between interwiki links and the text
+ self.interwiki_text_separator = '\r\n\r\n'
+
+ # Which languages have a special order for putting interlanguage links,
+ # and what order is it? If a language is not in interwiki_putfirst,
+ # alphabetical order on language code is used. For languages that are in
+ # interwiki_putfirst, interwiki_putfirst is checked first, and
+ # languages are put in the order given there. All other languages are put
+ # after those, in code-alphabetical order.
+ self.interwiki_putfirst = {}
+
+ # Languages in interwiki_putfirst_doubled should have a number plus a list
+ # of languages. If there are at least the number of interwiki links, all
+ # languages in the list should be placed at the front as well as in the
+ # normal list.
+ self.interwiki_putfirst_doubled = {}
+
+ # Some families, e. g. commons and meta, are not multilingual and
+ # forward interlanguage links to another family (wikipedia).
+ # These families can set this variable to the name of the target
+ # family.
+ self.interwiki_forward = None
+
+ # Which language codes no longer exist and by which language code
+ # should they be replaced. If for example the language with code xx:
+ # has been replaced by code yy:, add {'xx':'yy'} to obsolete.
+ # If all links to language xx: should be removed, add {'xx': None}.
+ self.obsolete = {}
+
+ # SETTINGS FOR CATEGORY LINKS:
+
+ # Languages that want the category links at the top of the page
+ self.category_attop = []
+
+ # languages that want the category links
+ # one-after-another on a single line
+ self.category_on_one_line = []
+
+ # String used as separator between category links and the text
+ self.category_text_separator = '\r\n\r\n'
+
+ # When both at the bottom should categories come after interwikilinks?
+ self.categories_last = []
+
+ # SETTINGS FOR LDAP AUTHENTICATION
+ # If your wiki uses:
+ # http://www.mediawiki.org/wiki/Extension:LDAP_Authentication.
+ # then uncomment this line and define the user's domain required
+ # at login.
+ #self.name = 'domain here'
+
+ def protocol(self, code):
+ """
+ Can be overridden to return 'https'. Other protocols are not supported.
+ """
+ return 'http'
+
+ def scriptpath(self, code):
+ """The prefix used to locate scripts on this wiki.
+
+ This is the value displayed when you enter {{SCRIPTPATH}} on a
+ wiki page (often displayed at [[Help:Variables]] if the wiki has
+ copied the master help page correctly).
+
+ The default value is the one used on Wikimedia Foundation wikis,
+ but needs to be overridden in the family file for any wiki that
+ uses a different value.
+
+ """
+ return '/w'
+
+ # IMPORTANT: if your wiki does not support the api.php interface,
+ # you must uncomment the second line of this method:
+ def apipath(self, code):
+ # raise NotImplementedError, "%s wiki family does not support api.php" % self.name
+ return '%s/api.php' % self.scriptpath(code)
+
+ # Which version of MediaWiki is used?
+ def version(self, code):
+ # Replace with the actual version being run on your wiki
+ return '1.13alpha'
+
+ def code2encoding(self, code):
+ """Return the encoding for a specific language wiki"""
+ # Most wikis nowadays use UTF-8, but change this if yours uses
+ # a different encoding
+ return 'utf-8'
Property changes on: trunk/pywikipedia/families/README-family.txt
___________________________________________________________________
Name: svn:eol-style
+ native
Modified: trunk/pywikipedia/protect.py
===================================================================
--- trunk/pywikipedia/protect.py 2008-07-05 12:57:13 UTC (rev 5674)
+++ trunk/pywikipedia/protect.py 2008-07-05 18:21:03 UTC (rev 5675)
@@ -1,252 +1,252 @@
-# -*- coding: utf-8 -*-
-"""
-This script can be used to protect and unprotect pages en masse.
-Of course, you will need an admin account on the relevant wiki.
-
-Syntax: python protect.py OPTION...
-
-Command line options:
-
--page: Protect specified page
--cat: Protect all pages in the given category.
--nosubcats: Don't protect pages in the subcategories.
--links: Protect all pages linked from a given page.
--file: Protect all pages listed in a text file.
--ref: Protect all pages referring from a given page.
--images: Protect all images used on a given page.
--always: Don't prompt to protect pages, just do it.
--summary: Supply a custom edit summary.
--unprotect: Actually unprotect pages instead of protecting
--edit:PROTECTION_LEVEL Set edit protection level to PROTECTION_LEVEL
--move:PROTECTION_LEVEL Set move protection level to PROTECTION_LEVEL
-
-## Without support ##
-## -create:PROTECTION_LEVEL Set move protection level to PROTECTION_LEVEL ##
-
-Values for PROTECTION_LEVEL are: sysop, autoconfirmed, none.
-If an operation parameter (edit, move or create) is not specified, default
-protection level is 'sysop' (or 'none' if -unprotect).
-
-Examples:
-
-Protect everything in the category "To protect" prompting.
- python protect.py -cat:"To protect" -always
-
-Unprotect all pages listed in text file "unprotect.txt" without prompting.
- python protect.py -file:unprotect.txt -unprotect
-"""
-
-# Written by http://it.wikisource.org/wiki/Utente:Qualc1
-# Created by modifying delete.py
-__version__ = '$Id: delete.py 4946 2008-01-29 14:58:25Z wikipedian $'
-
-#
-# Distributed under the terms of the MIT license.
-#
-
-import wikipedia, catlib
-import pagegenerators
-
-# Summary messages for protecting from a category.
-msg_simple_protect = {
- 'en': u'Bot: Protecting a list of files.',
- 'ar': u'بوت: حماية قائمة من الملفات.',
- 'it': u'Bot: Protezione di una lista di pagine.',
- 'pt': u'Bot: Protegendo uma lista de artigos.',
-}
-msg_protect_category = {
- 'en': u'Robot - Protecting all pages from category %s',
- 'ar': u'روبوت - حماية كل الصفحات من التصنيف %s',
- 'it': u'Bot: Protezione di tutte le pagine nella categoria %s.',
- 'pt': u'Bot: Protegendo todos os artigos da categoria %s',
-}
-msg_protect_links = {
- 'en': u'Robot - Protecting all pages linked from %s',
- 'ar': u'روبوت - حماية كل الصفحات الموصولة من %s',
- 'it': u'Bot: Protezione di tutte le pagine linkate da %s.',
- 'pt': u'Bot: Protegendo todos os artigos ligados a %s',
-}
-msg_protect_ref = {
- 'en': u'Robot - Protecting all pages referring from %s',
- 'ar': u'روبوت - حماية كل الصفحات الراجعة من %s',
- 'it': u'Bot: Protezione di tutte le pagine con link verso %s.',
- 'pt': u'Bot: Protegendo todos os artigos afluentes a %s',
-}
-msg_protect_images = {
- 'en': u'Robot - Protecting all images on page %s',
- 'ar': u'روبوت - حماية كل الصور في الصفحة %s',
- 'it': u'Bot: Protezione di tutte le immagini presenti in %s.',
- 'pt': u'Bot: Protegendo todas as imagens do artigo %s',
-}
-
-class ProtectionRobot:
- """
- This robot allows protection of pages en masse.
- """
-
- def __init__(self, generator, summary, always = False, unprotect=False,
- edit='sysop', move='sysop', create='sysop'):
- """
- Arguments:
- * generator - A page generator.
- * always - Protect without prompting?
- * edit, move, create - protection level for these operations
- * unprotect - unprotect pages (and ignore edit, move, create params)
- """
- self.generator = generator
- self.summary = summary
- self.always = always
- self.unprotect = unprotect
- self.edit = edit
- self.move = move
-
- def run(self):
- """
- Starts the robot's action.
- """
- #Loop through everything in the page generator and (un)protect it.
- for page in self.generator:
- wikipedia.output(u'Processing page %s' % page.title())
- print self.edit, self.move#, self.create
- page.protect(unprotect=self.unprotect, reason=self.summary, prompt=self.always,
- edit=self.edit, move=self.move)
-
-# Asks a valid protection level for "operation".
-# Returns the protection level chosen by user.
-def choiceProtectionLevel(operation, default):
- default = default[0]
- firstChar = map(lambda level: level[0], protectionLevels)
- choiceChar = wikipedia.inputChoice('Choice a protection level to %s:' % operation,
- protectionLevels, firstChar, default = default)
- for level in protectionLevels:
- if level.startswith(choiceChar):
- return level
-
-def main():
- global protectionLevels
- protectionLevels = ['sysop', 'autoconfirmed', 'none']
-
- pageName = ''
- summary = ''
- always = False
- doSinglePage = False
- doCategory = False
- protectSubcategories = True
- doRef = False
- doLinks = False
- doImages = False
- fileName = ''
- gen = None
- edit = ''
- move = ''
- defaultProtection = 'sysop'
-
- # read command line parameters
- for arg in wikipedia.handleArgs():
- if arg == '-always':
- always = True
- elif arg.startswith('-file'):
- if len(arg) == len('-file'):
- fileName = wikipedia.input(u'Enter name of file to protect pages from:')
- else:
- fileName = arg[len('-file:'):]
- elif arg.startswith('-summary'):
- if len(arg) == len('-summary'):
- summary = wikipedia.input(u'Enter a reason for the protection:')
- else:
- summary = arg[len('-summary:'):]
- elif arg.startswith('-cat'):
- doCategory = True
- if len(arg) == len('-cat'):
- pageName = wikipedia.input(u'Enter the category to protect from:')
- else:
- pageName = arg[len('-cat:'):]
- elif arg.startswith('-nosubcats'):
- protectSubcategories = False
- elif arg.startswith('-links'):
- doLinks = True
- if len(arg) == len('-links'):
- pageName = wikipedia.input(u'Enter the page to protect from:')
- else:
- pageName = arg[len('-links:'):]
- elif arg.startswith('-ref'):
- doRef = True
- if len(arg) == len('-ref'):
- pageName = wikipedia.input(u'Enter the page to protect from:')
- else:
- pageName = arg[len('-ref:'):]
- elif arg.startswith('-page'):
- doSinglePage = True
- if len(arg) == len('-page'):
- pageName = wikipedia.input(u'Enter the page to protect:')
- else:
- pageName = arg[len('-page:'):]
- elif arg.startswith('-images'):
- doImages = True
- if len(arg) == len('-images'):
- pageName = wikipedia.input(u'Enter the page with the images to protect:')
- else:
- pageName = arg[len('-images:'):]
- elif arg.startswith('-unprotect'):
- defaultProtection = 'none'
- elif arg.startswith('-edit'):
- edit = arg[len('-edit:'):]
- if edit not in protectionLevels:
- edit = choiceProtectionLevel('edit', defaultProtection)
- elif arg.startswith('-move'):
- move = arg[len('-move:'):]
- if move not in protectionLevels:
- move = choiceProtectionLevel('move', defaultProtection)
- elif arg.startswith('-create'):
- create = arg[len('-create:'):]
- if create not in protectionLevels:
- create = choiceProtectionLevel('create', defaultProtection)
-
- mysite = wikipedia.getSite()
-
- if doSinglePage:
- if not summary:
- summary = wikipedia.input(u'Enter a reason for the protection:')
- page = wikipedia.Page(mysite, pageName)
- gen = iter([page])
- elif doCategory:
- if not summary:
- summary = wikipedia.translate(mysite, msg_protect_category) % pageName
- ns = mysite.category_namespace()
- categoryPage = catlib.Category(mysite, ns + ':' + pageName)
- gen = pagegenerators.CategorizedPageGenerator(categoryPage, recurse = protectSubcategories)
- elif doLinks:
- if not summary:
- summary = wikipedia.translate(mysite, msg_protect_links) % pageName
- linksPage = wikipedia.Page(mysite, pageName)
- gen = pagegenerators.LinkedPageGenerator(linksPage)
- elif doRef:
- if not summary:
- summary = wikipedia.translate(mysite, msg_protect_ref) % pageName
- refPage = wikipedia.Page(mysite, pageName)
- gen = pagegenerators.ReferringPageGenerator(refPage)
- elif fileName:
- if not summary:
- summary = wikipedia.translate(mysite, msg_simple_protect)
- gen = pagegenerators.TextfilePageGenerator(fileName)
- elif doImages:
- if not summary:
- summary = wikipedia.translate(mysite, msg_protect_images) % pageName
- gen = pagegenerators.ImagesPageGenerator(wikipedia.Page(mysite, pageName))
-
- if gen:
- wikipedia.setAction(summary)
- # We are just protecting pages, so we have no need of using a preloading page generator
- # to actually get the text of those pages.
- if not edit: edit = defaultProtection
- if not move: move = defaultProtection
- bot = ProtectionRobot(gen, summary, always, edit=edit, move=move)
- bot.run()
- else:
- wikipedia.showHelp(u'protect')
-
-if __name__ == "__main__":
- try:
- main()
- finally:
- wikipedia.stopme()
+# -*- coding: utf-8 -*-
+"""
+This script can be used to protect and unprotect pages en masse.
+Of course, you will need an admin account on the relevant wiki.
+
+Syntax: python protect.py OPTION...
+
+Command line options:
+
+-page: Protect specified page
+-cat: Protect all pages in the given category.
+-nosubcats: Don't protect pages in the subcategories.
+-links: Protect all pages linked from a given page.
+-file: Protect all pages listed in a text file.
+-ref: Protect all pages referring from a given page.
+-images: Protect all images used on a given page.
+-always: Don't prompt to protect pages, just do it.
+-summary: Supply a custom edit summary.
+-unprotect: Actually unprotect pages instead of protecting
+-edit:PROTECTION_LEVEL Set edit protection level to PROTECTION_LEVEL
+-move:PROTECTION_LEVEL Set move protection level to PROTECTION_LEVEL
+
+## Without support ##
+## -create:PROTECTION_LEVEL Set move protection level to PROTECTION_LEVEL ##
+
+Values for PROTECTION_LEVEL are: sysop, autoconfirmed, none.
+If an operation parameter (edit, move or create) is not specified, default
+protection level is 'sysop' (or 'none' if -unprotect).
+
+Examples:
+
+Protect everything in the category "To protect" prompting.
+ python protect.py -cat:"To protect" -always
+
+Unprotect all pages listed in text file "unprotect.txt" without prompting.
+ python protect.py -file:unprotect.txt -unprotect
+"""
+
+# Written by http://it.wikisource.org/wiki/Utente:Qualc1
+# Created by modifying delete.py
+__version__ = '$Id: delete.py 4946 2008-01-29 14:58:25Z wikipedian $'
+
+#
+# Distributed under the terms of the MIT license.
+#
+
+import wikipedia, catlib
+import pagegenerators
+
+# Summary messages for protecting from a category.
+msg_simple_protect = {
+ 'en': u'Bot: Protecting a list of files.',
+ 'ar': u'بوت: حماية قائمة من الملفات.',
+ 'it': u'Bot: Protezione di una lista di pagine.',
+ 'pt': u'Bot: Protegendo uma lista de artigos.',
+}
+msg_protect_category = {
+ 'en': u'Robot - Protecting all pages from category %s',
+ 'ar': u'روبوت - حماية كل الصفحات من التصنيف %s',
+ 'it': u'Bot: Protezione di tutte le pagine nella categoria %s.',
+ 'pt': u'Bot: Protegendo todos os artigos da categoria %s',
+}
+msg_protect_links = {
+ 'en': u'Robot - Protecting all pages linked from %s',
+ 'ar': u'روبوت - حماية كل الصفحات الموصولة من %s',
+ 'it': u'Bot: Protezione di tutte le pagine linkate da %s.',
+ 'pt': u'Bot: Protegendo todos os artigos ligados a %s',
+}
+msg_protect_ref = {
+ 'en': u'Robot - Protecting all pages referring from %s',
+ 'ar': u'روبوت - حماية كل الصفحات الراجعة من %s',
+ 'it': u'Bot: Protezione di tutte le pagine con link verso %s.',
+ 'pt': u'Bot: Protegendo todos os artigos afluentes a %s',
+}
+msg_protect_images = {
+ 'en': u'Robot - Protecting all images on page %s',
+ 'ar': u'روبوت - حماية كل الصور في الصفحة %s',
+ 'it': u'Bot: Protezione di tutte le immagini presenti in %s.',
+ 'pt': u'Bot: Protegendo todas as imagens do artigo %s',
+}
+
+class ProtectionRobot:
+ """
+ This robot allows protection of pages en masse.
+ """
+
+ def __init__(self, generator, summary, always = False, unprotect=False,
+ edit='sysop', move='sysop', create='sysop'):
+ """
+ Arguments:
+ * generator - A page generator.
+ * always - Protect without prompting?
+ * edit, move, create - protection level for these operations
+ * unprotect - unprotect pages (and ignore edit, move, create params)
+ """
+ self.generator = generator
+ self.summary = summary
+ self.always = always
+ self.unprotect = unprotect
+ self.edit = edit
+ self.move = move
+
+ def run(self):
+ """
+ Starts the robot's action.
+ """
+ #Loop through everything in the page generator and (un)protect it.
+ for page in self.generator:
+ wikipedia.output(u'Processing page %s' % page.title())
+ print self.edit, self.move#, self.create
+ page.protect(unprotect=self.unprotect, reason=self.summary, prompt=self.always,
+ edit=self.edit, move=self.move)
+
+# Asks a valid protection level for "operation".
+# Returns the protection level chosen by user.
+def choiceProtectionLevel(operation, default):
+ default = default[0]
+ firstChar = map(lambda level: level[0], protectionLevels)
+ choiceChar = wikipedia.inputChoice('Choice a protection level to %s:' % operation,
+ protectionLevels, firstChar, default = default)
+ for level in protectionLevels:
+ if level.startswith(choiceChar):
+ return level
+
+def main():
+ global protectionLevels
+ protectionLevels = ['sysop', 'autoconfirmed', 'none']
+
+ pageName = ''
+ summary = ''
+ always = False
+ doSinglePage = False
+ doCategory = False
+ protectSubcategories = True
+ doRef = False
+ doLinks = False
+ doImages = False
+ fileName = ''
+ gen = None
+ edit = ''
+ move = ''
+ defaultProtection = 'sysop'
+
+ # read command line parameters
+ for arg in wikipedia.handleArgs():
+ if arg == '-always':
+ always = True
+ elif arg.startswith('-file'):
+ if len(arg) == len('-file'):
+ fileName = wikipedia.input(u'Enter name of file to protect pages from:')
+ else:
+ fileName = arg[len('-file:'):]
+ elif arg.startswith('-summary'):
+ if len(arg) == len('-summary'):
+ summary = wikipedia.input(u'Enter a reason for the protection:')
+ else:
+ summary = arg[len('-summary:'):]
+ elif arg.startswith('-cat'):
+ doCategory = True
+ if len(arg) == len('-cat'):
+ pageName = wikipedia.input(u'Enter the category to protect from:')
+ else:
+ pageName = arg[len('-cat:'):]
+ elif arg.startswith('-nosubcats'):
+ protectSubcategories = False
+ elif arg.startswith('-links'):
+ doLinks = True
+ if len(arg) == len('-links'):
+ pageName = wikipedia.input(u'Enter the page to protect from:')
+ else:
+ pageName = arg[len('-links:'):]
+ elif arg.startswith('-ref'):
+ doRef = True
+ if len(arg) == len('-ref'):
+ pageName = wikipedia.input(u'Enter the page to protect from:')
+ else:
+ pageName = arg[len('-ref:'):]
+ elif arg.startswith('-page'):
+ doSinglePage = True
+ if len(arg) == len('-page'):
+ pageName = wikipedia.input(u'Enter the page to protect:')
+ else:
+ pageName = arg[len('-page:'):]
+ elif arg.startswith('-images'):
+ doImages = True
+ if len(arg) == len('-images'):
+ pageName = wikipedia.input(u'Enter the page with the images to protect:')
+ else:
+ pageName = arg[len('-images:'):]
+ elif arg.startswith('-unprotect'):
+ defaultProtection = 'none'
+ elif arg.startswith('-edit'):
+ edit = arg[len('-edit:'):]
+ if edit not in protectionLevels:
+ edit = choiceProtectionLevel('edit', defaultProtection)
+ elif arg.startswith('-move'):
+ move = arg[len('-move:'):]
+ if move not in protectionLevels:
+ move = choiceProtectionLevel('move', defaultProtection)
+ elif arg.startswith('-create'):
+ create = arg[len('-create:'):]
+ if create not in protectionLevels:
+ create = choiceProtectionLevel('create', defaultProtection)
+
+ mysite = wikipedia.getSite()
+
+ if doSinglePage:
+ if not summary:
+ summary = wikipedia.input(u'Enter a reason for the protection:')
+ page = wikipedia.Page(mysite, pageName)
+ gen = iter([page])
+ elif doCategory:
+ if not summary:
+ summary = wikipedia.translate(mysite, msg_protect_category) % pageName
+ ns = mysite.category_namespace()
+ categoryPage = catlib.Category(mysite, ns + ':' + pageName)
+ gen = pagegenerators.CategorizedPageGenerator(categoryPage, recurse = protectSubcategories)
+ elif doLinks:
+ if not summary:
+ summary = wikipedia.translate(mysite, msg_protect_links) % pageName
+ linksPage = wikipedia.Page(mysite, pageName)
+ gen = pagegenerators.LinkedPageGenerator(linksPage)
+ elif doRef:
+ if not summary:
+ summary = wikipedia.translate(mysite, msg_protect_ref) % pageName
+ refPage = wikipedia.Page(mysite, pageName)
+ gen = pagegenerators.ReferringPageGenerator(refPage)
+ elif fileName:
+ if not summary:
+ summary = wikipedia.translate(mysite, msg_simple_protect)
+ gen = pagegenerators.TextfilePageGenerator(fileName)
+ elif doImages:
+ if not summary:
+ summary = wikipedia.translate(mysite, msg_protect_images) % pageName
+ gen = pagegenerators.ImagesPageGenerator(wikipedia.Page(mysite, pageName))
+
+ if gen:
+ wikipedia.setAction(summary)
+ # We are just protecting pages, so we have no need of using a preloading page generator
+ # to actually get the text of those pages.
+ if not edit: edit = defaultProtection
+ if not move: move = defaultProtection
+ bot = ProtectionRobot(gen, summary, always, edit=edit, move=move)
+ bot.run()
+ else:
+ wikipedia.showHelp(u'protect')
+
+if __name__ == "__main__":
+ try:
+ main()
+ finally:
+ wikipedia.stopme()
Property changes on: trunk/pywikipedia/protect.py
___________________________________________________________________
Name: svn:eol-style
+ native
More information about the Pywikipedia-l
mailing list