Pywikipedia-svn October 2010

pywikipedia-svn@lists.wikimedia.org

6 participants
90 discussions

by xqt＠svn.wikimedia.org

Revision: 8630 Author: xqt Date: 2010-10-09 19:32:57 +0000 (Sat, 09 Oct 2010) Log Message: ----------- import wikipedia as pywikibot for merging to rewrite Modified Paths: -------------- trunk/pywikipedia/reflinks.py trunk/pywikipedia/revertbot.py trunk/pywikipedia/selflink.py trunk/pywikipedia/spamremove.py trunk/pywikipedia/speedy_delete.py trunk/pywikipedia/spellcheck.py trunk/pywikipedia/standardize_interwiki.py trunk/pywikipedia/standardize_notes.py Modified: trunk/pywikipedia/reflinks.py =================================================================== --- trunk/pywikipedia/reflinks.py 2010-10-09 16:11:46 UTC (rev 8629) +++ trunk/pywikipedia/reflinks.py 2010-10-09 19:32:57 UTC (rev 8630) @@ -33,15 +33,19 @@ Basic pagegenerators commands, -page, etc... """ # (C) 2008 - Nicolas Dumazet ( en:User:NicDumZ ) +# (C) Pywikipedia bot team, 2008-2010 # -# Distributed under the terms of the GPL - +# Distributed under the terms of the MIT license. +# __version__ = '$Id$' +# -from BeautifulSoup import UnicodeDammit import sys, re, urllib2, httplib, socket, codecs, ftplib -import wikipedia, pagegenerators, noreferences import subprocess, tempfile, os, gzip, StringIO +import wikipedia as pywikibot +from BeautifulSoup import UnicodeDammit +import pagegenerators +import noreferences stopPage = {'fr':u'Utilisateur:DumZiBoT/EditezCettePagePourMeStopper', 'de':u'Benutzer:DumZiBoT/EditThisPageToStopMe', @@ -90,9 +94,13 @@ 'it':u'Titolo generato automaticamente', } -soft404 = re.compile(ur'\D404(\D|\Z)|error|errdoc|Not.{0,3}Found|sitedown|eventlog', re.IGNORECASE) +soft404 = re.compile( + ur'\D404(\D|\Z)|error|errdoc|Not.{0,3}Found|sitedown|eventlog', + re.IGNORECASE) # matches an URL at the index of a website -dirIndex = re.compile(ur'^\w+://[^/]+/((default|index)\.(asp|aspx|cgi|htm|html|phtml|mpx|mspx|php|shtml|var))?$', re.IGNORECASE) +dirIndex = re.compile( + ur'^\w+://[^/]+/((default|index)\.(asp|aspx|cgi|htm|html|phtml|mpx|mspx|php|shtml|var))?$', + re.IGNORECASE) # Extracts the domain name domain = re.compile(ur'^(\w+)://(?:www.|)([^/]+)') @@ -156,7 +164,7 @@ self.xmlStart = xmlStart self.namespaces = namespaces self.skipping = bool(xmlStart) - self.site = wikipedia.getSite() + self.site = pywikibot.getSite() import xmlreader dump = xmlreader.XmlDump(xmlFilename) @@ -175,7 +183,7 @@ if entry.title != self.xmlStart: continue self.skipping = False - page=wikipedia.Page(self.site, entry.title) + page=pywikibot.Page(self.site, entry.title) if not self.namespaces == []: if page.namespace() not in self.namespaces: continue @@ -188,14 +196,16 @@ def __init__(self, link, name): self.refname = name self.link = link - self.site = wikipedia.getSite() - self.linkComment = wikipedia.translate(self.site, comment) + self.site = pywikibot.getSite() + self.linkComment = pywikibot.translate(self.site, comment) self.url = re.sub(u'#.*', '', self.link) self.title = None def refTitle(self): """Returns the <ref> with its new title""" - return '<ref%s>[%s %s]</ref>' % (self.refname, self.link, self.title, self.linkComment) + return '<ref%s>[%s %s]</ref>' % (self.refname, self.link, + self.title, + self.linkComment) def refLink(self): """No title has been found, return the unbracketed link""" @@ -203,14 +213,14 @@ def refDead(self): """Dead link, tag it with a {{dead link}}""" - tag = wikipedia.translate(self.site, deadLinkTag) % self.link + tag = pywikibot.translate(self.site, deadLinkTag) % self.link return '<ref%s>%s</ref>' % (self.refname, tag) def transform(self, ispdf = False): """Normalize the title""" #convert html entities if not ispdf: - self.title = wikipedia.html2unicode(self.title) + self.title = pywikibot.html2unicode(self.title) self.title = re.sub(r'-+', '-', self.title) #remove formatting, i.e long useless strings self.title = re.sub(r'[\.+\-=]{4,}', ' ', self.title) @@ -228,7 +238,7 @@ self.title = self.title.replace('}}', '}}') #prevent multiple quotes being interpreted as '' or ''' self.title = self.title.replace('\'\'', '\''') - self.title = wikipedia.unicode2html(self.title, self.site.encoding()) + self.title = pywikibot.unicode2html(self.title, self.site.encoding()) # TODO : remove HTML when both opening and closing tags are included def avoid_uppercase(self): @@ -257,10 +267,13 @@ """ def __init__(self): # Match references - self.REFS = re.compile(u'(?i)<ref(?P<params>[^>/]*)>(?P<content>.*?)</ref>') - self.NAMES = re.compile(u'(?i).*name\s*=\s*(?P<quote>"?)\s*(?P<name>.+)\s*(?P=quote).*') - self.GROUPS = re.compile(u'(?i).*group\s*=\s*(?P<quote>"?)\s*(?P<group>.+)\s*(?P=quote).*') - self.autogen = wikipedia.translate(wikipedia.getSite(), autogen) + self.REFS = re.compile( + u'(?i)<ref(?P<params>[^>/]*)>(?P<content>.*?)</ref>') + self.NAMES = re.compile( + u'(?i).*name\s*=\s*(?P<quote>"?)\s*(?P<name>.+)\s*(?P=quote).*') + self.GROUPS = re.compile( + u'(?i).*group\s*=\s*(?P<quote>"?)\s*(?P<group>.+)\s*(?P=quote).*') + self.autogen = pywikibot.translate(pywikibot.getSite(), autogen) def process(self, text): # keys are ref groups @@ -299,7 +312,7 @@ #First name associated with this content if name == 'population': - wikipedia.output(content) + pywikibot.output(content) if not name in foundRefNames: # first time ever we meet this name if name == 'population': @@ -350,11 +363,13 @@ name = v[0] if v[1]: name = u'"%s"' % name - text = re.sub(u'<ref name\s*=\s*(?P<quote>"?)\s*%s\s*(?P=quote)\s*/>' % k, u'<ref name=%s />' % name, text) + text = re.sub( + u'<ref name\s*=\s*(?P<quote>"?)\s*%s\s*(?P=quote)\s*/>' % k, + u'<ref name=%s />' % name, text) return text class ReferencesRobot: - def __init__(self, generator, acceptall = False, limit = None, ignorepdf = False ): + def __init__(self, generator, acceptall=False, limit=None, ignorepdf=False): """ - generator : Page generator - acceptall : boolean, is -always on ? @@ -365,10 +380,11 @@ self.acceptall = acceptall self.limit = limit self.ignorepdf = ignorepdf - self.site = wikipedia.getSite() - self.stopPage = wikipedia.Page(self.site, wikipedia.translate(self.site, stopPage)) + self.site = pywikibot.getSite() + self.stopPage = pywikibot.Page(self.site, + pywikibot.translate(self.site, stopPage)) - local = wikipedia.translate(self.site, badtitles) + local = pywikibot.translate(self.site, badtitles) if local: bad = '(' + globalbadtitles + '|' + local + ')' else: @@ -380,9 +396,9 @@ try : self.stopPageRevId = self.stopPage.latestRevision() - except wikipedia.NoPage : - wikipedia.output(u'The stop page %s does not exist' - % self.stopPage.aslink()) + except pywikibot.NoPage : + pywikibot.output(u'The stop page %s does not exist' + % self.stopPage.title(asLink=True)) raise # Regex to grasp content-type meta HTML tag in HTML source @@ -392,20 +408,22 @@ # Extract html title from page self.TITLE = re.compile(ur'(?is)(?<=<title>).*?(?=</title>)') # Matches content inside <script>/<style>/HTML comments - self.NON_HTML = re.compile(ur'(?is)<script[^>]*>.*?</script>|<style[^>]*>.*?</style>||<!\[CDATA\[.*?\]\]>') + self.NON_HTML = re.compile( + ur'(?is)<script[^>]*>.*?</script>|<style[^>]*>.*?</style>||<!\[CDATA\[.*?\]\]>') # Authorized mime types for HTML pages - self.MIME = re.compile(ur'application/(?:xhtml\+xml|xml)|text/(?:ht|x)ml') + self.MIME = re.compile( + ur'application/(?:xhtml\+xml|xml)|text/(?:ht|x)ml') def put_page(self, page, new): """ Prints diffs between orginal and new (text), puts new text for page """ - wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" + pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title()) - wikipedia.showDiff(page.get(), new) + pywikibot.showDiff(page.get(), new) if not self.acceptall: - choice = wikipedia.inputChoice(u'Do you want to accept ' + + choice = pywikibot.inputChoice(u'Do you want to accept ' + u'these changes?', ['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N') @@ -416,22 +434,24 @@ if self.acceptall: try: page.put(new) - except wikipedia.EditConflict: - wikipedia.output(u'Skipping %s because of edit conflict' + except pywikibot.EditConflict: + pywikibot.output(u'Skipping %s because of edit conflict' % (page.title(),)) - except wikipedia.SpamfilterError, e: - wikipedia.output(u'Cannot change %s because of blacklist entry %s' % (page.title(), e.url)) - except wikipedia.PageNotSaved, error: - wikipedia.output(u'Error putting page: %s' % (error.args,)) - except wikipedia.LockedPage: - wikipedia.output(u'Skipping %s (locked page)' + except pywikibot.SpamfilterError, e: + pywikibot.output( + u'Cannot change %s because of blacklist entry %s' + % (page.title(), e.url)) + except pywikibot.PageNotSaved, error: + pywikibot.output(u'Error putting page: %s' % (error.args,)) + except pywikibot.LockedPage: + pywikibot.output(u'Skipping %s (locked page)' % (page.title(),)) - except wikipedia.ServerError, e: - wikipedia.output(u'Server Error : %s' % e) + except pywikibot.ServerError, e: + pywikibot.output(u'Server Error : %s' % e) def httpError(self, err_num, link, pagetitleaslink): """Log HTTP Error""" - wikipedia.output(u'HTTP error (%s) for %s on %s' + pywikibot.output(u'HTTP error (%s) for %s on %s' % (err_num, link, pagetitleaslink), toStdout = True) @@ -440,24 +460,27 @@ Use pdfinfo to retrieve title from a PDF. Unix-only, I'm afraid. """ - wikipedia.output( u'PDF file.' ) + pywikibot.output( u'PDF file.' ) fd, infile = tempfile.mkstemp() urlobj = os.fdopen(fd, 'r+w') urlobj.write(f.read()) try: - pdfinfo_out = subprocess.Popen([r"pdfinfo","/dev/stdin"], stdin=urlobj, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=False).communicate()[0] + 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 != '': wikipedia.output(u'title: ' +ref.title ) - wikipedia.output( u'PDF done.' ) + if ref.title != '': + pywikibot.output(u'title: %s' % ref.title) + pywikibot.output(u'PDF done.') except ValueError: - wikipedia.output( u'pdfinfo value error.' ) + pywikibot.output(u'pdfinfo value error.') except OSError: - wikipedia.output( u'pdfinfo OS error.' ) + pywikibot.output(u'pdfinfo OS error.') except: # Ignore errors - wikipedia.output( u'PDF processing error.' ) + pywikibot.output(u'PDF processing error.') pass finally: urlobj.close() @@ -467,11 +490,12 @@ """ Runs the Bot """ - wikipedia.setAction(wikipedia.translate(self.site, msg)) + pywikibot.setAction(pywikibot.translate(self.site, msg)) try: deadLinks = codecs.open(listof404pages, 'r', 'latin_1').read() except IOError: - wikipedia.output('You need to download http://www.twoevils.org/files/wikipedia/404-links.txt.gz and to ungzip it in the same directory') + pywikibot.output( + 'You need to download http://www.twoevils.org/files/wikipedia/404-links.txt.gz and to ungzip it in the same directory') raise socket.setdefaulttimeout(30) editedpages = 0 @@ -480,17 +504,18 @@ # Load the page's text from the wiki new_text = page.get() if not page.canBeEdited(): - wikipedia.output(u"You can't edit page %s" - % page.aslink()) + pywikibot.output(u"You can't edit page %s" + % page.title(asLink=True)) continue - except wikipedia.NoPage: - wikipedia.output(u'Page %s not found' % page.aslink()) + except pywikibot.NoPage: + pywikibot.output(u'Page %s not found' % page.title(asLink=True)) continue - except wikipedia.IsRedirectPage: - wikipedia.output(u'Page %s is a redirect' % page.aslink()) + except pywikibot.IsRedirectPage: + pywikibot.output(u'Page %s is a redirect' + % page.title(asLink=True)) continue - for match in linksInRef.finditer(wikipedia.removeDisabledParts(page.get())): + for match in linksInRef.finditer(pywikibot.removeDisabledParts(page.get())): #for each link to change link = match.group(u'url') #debugging purpose @@ -508,17 +533,24 @@ headers = f.info() contentType = headers.getheader('Content-Type') if contentType and not self.MIME.search(contentType): - if ref.link.lower().endswith('.pdf') and not self.ignorepdf: + if ref.link.lower().endswith('.pdf') and \ + not self.ignorepdf: # If file has a PDF suffix self.getPDFTitle(ref, f) else: - wikipedia.output(u'\03{lightyellow}WARNING\03{default} : media : %s ' % ref.link) + pywikibot.output( + u'\03{lightyellow}WARNING\03{default} : media : %s ' + % ref.link) if ref.title: - if not re.match('(?i) *microsoft (word|excel|visio)', ref.title): + if not re.match( + '(?i) *microsoft (word|excel|visio)', + ref.title): ref.transform(ispdf=True) repl = ref.refTitle() else: - wikipedia.output('\03{lightyellow}WARNING\03{default} : PDF title blacklisted : %s ' % ref.title) + pywikibot.output( + '\03{lightyellow}WARNING\03{default} : PDF title blacklisted : %s ' + % ref.title) repl = ref.refLink() else: repl = ref.refLink() @@ -526,12 +558,19 @@ continue # Get the real url where we end (http redirects !) redir = f.geturl() - if redir != ref.link and domain.findall(redir) == domain.findall(link): - if soft404.search(redir) and not soft404.search(ref.link): - wikipedia.output(u'\03{lightyellow}WARNING\03{default} : Redirect 404 : %s ' % ref.link) + if redir != ref.link and \ + domain.findall(redir) == domain.findall(link): + if soft404.search(redir) and \ + not soft404.search(ref.link): + pywikibot.output( + u'\03{lightyellow}WARNING\03{default} : Redirect 404 : %s ' + % ref.link) continue - if dirIndex.match(redir) and not dirIndex.match(ref.link): - wikipedia.output(u'\03{lightyellow}WARNING\03{default} : Redirect to root : %s ' % ref.link) + if dirIndex.match(redir) and \ + not dirIndex.match(ref.link): + pywikibot.output( + u'\03{lightyellow}WARNING\03{default} : Redirect to root : %s ' + % ref.link) continue # uncompress if necessary @@ -548,15 +587,21 @@ socket.setdefaulttimeout(None) except UnicodeError: - #example : http://www.adminet.com/jo/20010615¦/ECOC0100037D.html in [[fr:Cyanure]] - wikipedia.output(u'\03{lightred}Bad link\03{default} : %s in %s' % (ref.url, page.aslink())) + #example : http://www.adminet.com/jo/20010615¦/ECOC0100037D.html + # in [[fr:Cyanure]] + pywikibot.output( + u'\03{lightred}Bad link\03{default} : %s in %s' + % (ref.url, page.title(asLink=True))) continue except urllib2.HTTPError, e: - wikipedia.output(u'HTTP error (%s) for %s on %s' - % (e.code, ref.url, page.aslink()), + pywikibot.output(u'HTTP error (%s) for %s on %s' + % (e.code, ref.url, + page.title(asLink=True)), toStdout = True) - # 410 Gone, indicates that the resource has been purposely removed - if e.code == 410 or (e.code == 404 and (u'\t%s\t' % ref.url in deadLinks)): + # 410 Gone, indicates that the resource has been purposely + # removed + if e.code == 410 or \ + (e.code == 404 and (u'\t%s\t' % ref.url in deadLinks)): repl = ref.refDead() new_text = new_text.replace(match.group(), repl) continue @@ -565,7 +610,8 @@ IOError, httplib.error), e: #except (urllib2.URLError, socket.timeout, ftplib.error, httplib.error, socket.error), e: - wikipedia.output(u'Can\'t retrieve page %s : %s' % (ref.url, e)) + pywikibot.output(u'Can\'t retrieve page %s : %s' + % (ref.url, e)) continue except ValueError: #Known bug of httplib, google for : @@ -606,21 +652,25 @@ else: enc.append(tmp) else: - wikipedia.output(u'No charset found for %s' % ref.link) + pywikibot.output(u'No charset found for %s' % ref.link) #continue # do not process pages without charset if not contentType: - wikipedia.output(u'No content-type found for %s' % ref.link) + pywikibot.output(u'No content-type found for %s' % ref.link) continue elif not self.MIME.search(contentType): - wikipedia.output(u'\03{lightyellow}WARNING\03{default} : media : %s ' % ref.link) + pywikibot.output( + u'\03{lightyellow}WARNING\03{default} : media : %s ' + % ref.link) repl = ref.refLink() new_text = new_text.replace(match.group(), repl) continue - # Ugly hacks to try to survive when both server and page return no encoding. + # Ugly hacks to try to survive when both server and page + # return no encoding. # Uses most used encodings for each national suffix if u'.ru' in ref.link or u'.su' in ref.link: - # see http://www.sci.aha.ru/ATL/ra13a.htm : no server encoding, no page encoding + # see http://www.sci.aha.ru/ATL/ra13a.htm : no server + # encoding, no page encoding enc = enc + ['koi8-r', 'windows-1251'] elif u'.jp' in ref.link: enc.append("shift jis 2004") @@ -641,7 +691,7 @@ #Can't easily parse them. (~1 on 1000) repl = ref.refLink() new_text = new_text.replace(match.group(), repl) - wikipedia.output('%s : Hybrid encoding...' % ref.link) + pywikibot.output('%s : Hybrid encoding...' % ref.link) continue @@ -657,24 +707,29 @@ if not ref.title: repl = ref.refLink() new_text = new_text.replace(match.group(), repl) - wikipedia.output(u'%s : No title found...' % ref.link) + pywikibot.output(u'%s : No title found...' % ref.link) continue if enc and u.originalEncoding not in enc: - # BeautifulSoup thinks that the original encoding of our page was not one - # of the encodings we specified. Output a warning. - wikipedia.output(u'\03{lightpurple}ENCODING\03{default} : %s (%s)' % (ref.link, ref.title)) + # BeautifulSoup thinks that the original encoding of our + # page was not one of the encodings we specified. Output a + # warning. + pywikibot.output( + u'\03{lightpurple}ENCODING\03{default} : %s (%s)' + % (ref.link, ref.title)) # XXX Ugly hack if u'Ã©' in ref.title: repl = ref.refLink() new_text = new_text.replace(match.group(), repl) - wikipedia.output(u'%s : Hybrid encoding...' % ref.link) + pywikibot.output(u'%s : Hybrid encoding...' % ref.link) continue if self.titleBlackList.match(ref.title): repl = ref.refLink() new_text = new_text.replace(match.group(), repl) - wikipedia.output(u'\03{lightred}WARNING\03{default} %s : Blacklisted title (%s)' % (ref.link, ref.title)) + pywikibot.output( + u'\03{lightred}WARNING\03{default} %s : Blacklisted title (%s)' + % (ref.link, ref.title)) continue # Truncate long titles. 175 is arbitrary @@ -692,22 +747,25 @@ new_text = self.deduplicator.process(new_text) if new_text == page.get(): - wikipedia.output('No changes were necessary in %s' - % page.aslink()) + pywikibot.output('No changes were necessary in %s' + % page.title(asLink=True)) continue editedpages += 1 self.put_page(page, new_text) if self.limit and editedpages >= self.limit: - wikipedia.output('Edited %s pages, stopping.' % self.limit) + pywikibot.output('Edited %s pages, stopping.' % self.limit) return if editedpages % 20 == 0: - wikipedia.output('\03{lightgreen}Checking stop page...\03{default}') + pywikibot.output( + '\03{lightgreen}Checking stop page...\03{default}') actualRev = self.stopPage.latestRevision() if actualRev != self.stopPageRevId: - wikipedia.output(u'[[%s]] has been edited : Someone wants us to stop.' % self.stopPage) + pywikibot.output( + u'[[%s]] has been edited : Someone wants us to stop.' + % self.stopPage) return def main(): @@ -720,14 +778,14 @@ limit = None namespaces = [] generator = None - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith('-namespace:'): try: namespaces.append(int(arg[11:])) except ValueError: namespaces.append(arg[11:]) elif arg.startswith('-summary:'): - wikipedia.setAction(arg[9:]) + pywikibot.setAction(arg[9:]) elif arg == '-always': always = True elif arg == '-ignorepdf': @@ -736,13 +794,13 @@ limit = int(arg[7:]) elif arg.startswith('-xmlstart'): if len(arg) == 9: - xmlStart = wikipedia.input( + xmlStart = pywikibot.input( u'Please enter the dumped article to start with:') else: xmlStart = arg[10:] elif arg.startswith('-xml'): if len(arg) == 4: - xmlFilename = wikipedia.input( + xmlFilename = pywikibot.input( u'Please enter the XML dump\'s filename:') else: xmlFilename = arg[5:] @@ -759,7 +817,7 @@ generator = genFactory.getCombinedGenerator() if not generator: # syntax error, show help text from the top of this file - wikipedia.showHelp('reflinks') + pywikibot.showHelp('reflinks') return generator = pagegenerators.PreloadingGenerator(generator, pageNumber = 50) generator = pagegenerators.RedirectFilterPageGenerator(generator) @@ -770,4 +828,4 @@ try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/revertbot.py =================================================================== --- trunk/pywikipedia/revertbot.py 2010-10-09 16:11:46 UTC (rev 8629) +++ trunk/pywikipedia/revertbot.py 2010-10-09 19:32:57 UTC (rev 8630) @@ -1,13 +1,21 @@ -import wikipedia, query, userlib - -__version__ = '$Id$' - +#!/usr/bin/python +# -*- coding: utf-8 -*- """ - (c) Bryan Tong Minh, 2008 - (c) Pywikipedia team, 2008-2010 - Licensed under the terms of the MIT license. """ +# +# (C) Bryan Tong Minh, 2008 +# (C) Pywikipedia bot team, 2008-2010 +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id$' +# +import re +import wikipedia as pywikibot +import query, userlib + + class BaseRevertBot(object): """ Base revert bot @@ -94,38 +102,39 @@ rev['user'], rev['timestamp']) if self.comment: comment += ': ' + self.comment - page = wikipedia.Page(self.site, item['title']) - wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.aslink(True, True)) + page = pywikibot.Page(self.site, item['title']) + pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" + % page.aslink(True, True)) old = page.get() new = rev['*'] - wikipedia.showDiff(old, new) + pywikibot.showDiff(old, new) page.put(new, comment) return comment def log(self, msg): - wikipedia.output(msg) + pywikibot.output(msg) -import re class myRevertBot(BaseRevertBot): def callback(self, item): if 'top' in item: - page = wikipedia.Page(self.site, item['title']) + page = pywikibot.Page(self.site, item['title']) text=page.get() pattern = re.compile(u'\[\[.+?:.+?\..+?\]\]', re.UNICODE) return pattern.search(text) >= 0 return False + def main(): item = None - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): continue - bot = myRevertBot(site = wikipedia.getSite()) + bot = myRevertBot(site = pywikibot.getSite()) bot.revert_contribs() if __name__ == "__main__": try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/selflink.py =================================================================== --- trunk/pywikipedia/selflink.py 2010-10-09 16:11:46 UTC (rev 8629) +++ trunk/pywikipedia/selflink.py 2010-10-09 19:32:57 UTC (rev 8630) @@ -25,12 +25,18 @@ All other parameters will be regarded as part of the title of a single page, and the bot will only work on that single page. """ - +# +# (C) Pywikipedia bot team, 2006-2010 +# +# Distributed under the terms of the MIT license. +# __version__='$Id$' +# -import wikipedia, pagegenerators, catlib +import re, sys +import wikipedia as pywikibot +import pagegenerators, catlib import editarticle -import re, sys # This is required for the text that is shown when you run this script # with the parameter -help. @@ -78,7 +84,7 @@ def __iter__(self): import xmlreader - mysite = wikipedia.getSite() + mysite = pywikibot.getSite() dump = xmlreader.XmlDump(self.xmlFilename) for entry in dump.parse(): if mysite.nocapitalize: @@ -89,14 +95,14 @@ re.escape(entry.title[1:])) selflinkR = re.compile(r'\[\[' + title + '(\|[^\]]*)?\]\]') if selflinkR.search(entry.text): - yield wikipedia.Page(mysite, entry.title) + yield pywikibot.Page(mysite, entry.title) continue class SelflinkBot: def __init__(self, generator, always=False): self.generator = generator - linktrail = wikipedia.getSite().linktrail() + linktrail = pywikibot.getSite().linktrail() # The regular expression which finds links. Results consist of four groups: # group title is the target page title, that is, everything before | or ]. # group section is the page section. It'll include the # to make life easier for us. @@ -122,9 +128,9 @@ or match.group('section'): return text, False try: - linkedPage = wikipedia.Page(page.site(), match.group('title')) - except wikipedia.InvalidTitle, err: - wikipedia.output(u'Warning: %s' % err) + linkedPage = pywikibot.Page(page.site(), match.group('title')) + except pywikibot.InvalidTitle, err: + pywikibot.output(u'Warning: %s' % err) return text, False # Check whether the link found is to the current page itself. @@ -137,16 +143,16 @@ if self.always: choice = 'a' else: - wikipedia.output( + pywikibot.output( text[max(0, match.start() - context) : match.start()] \ + '\03{lightred}' + text[match.start() : match.end()] \ + '\03{default}' + text[match.end() : match.end() + context]) - choice = wikipedia.inputChoice( + choice = pywikibot.inputChoice( u'\nWhat shall be done with this selflink?\n', ['unlink', 'make bold', 'skip', 'edit', 'more context', 'unlink all', 'quit'], ['U', 'b', 's', 'e', 'm', 'a', 'q'], 'u') - wikipedia.output(u'') + pywikibot.output(u'') if choice == 's': # skip this link @@ -161,7 +167,8 @@ return text, True elif choice == 'm': # show more context by recursive self-call - return self.handleNextLink(page, text, match, context = context + 100) + return self.handleNextLink(page, text, match, + context=context + 100) elif choice == 'a': self.always = True elif choice == 'q': @@ -178,14 +185,17 @@ def treat(self, page): # Show the title of the page we're working on. # Highlight the title in purple. - wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title()) + pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" + % page.title()) try: oldText = page.get() # Inside image maps, don't touch selflinks, as they're used # to create tooltip labels. See for example: # http://de.wikipedia.org/w/index.php?title=Innenstadt_%28Bautzen%29&diff=nex… if '<imagemap>' in oldText: - wikipedia.output(u'Skipping page %s because it contains an image map.' % page.aslink()) + pywikibot.output( + u'Skipping page %s because it contains an image map.' + % page.title(asLink=True)) return text = oldText curpos = 0 @@ -193,27 +203,30 @@ match = self.linkR.search(text, pos = curpos) if not match: break - # Make sure that next time around we will not find this same hit. + # Make sure that next time around we will not find this same + # hit. curpos = match.start() + 1 text, jumpToBeginning = self.handleNextLink(page, text, match) if jumpToBeginning: curpos = 0 if oldText == text: - wikipedia.output(u'No changes necessary.') + pywikibot.output(u'No changes necessary.') else: - wikipedia.showDiff(oldText, text) + pywikibot.showDiff(oldText, text) page.put_async(text) - except wikipedia.NoPage: - wikipedia.output(u"Page %s does not exist?!" % page.aslink()) - except wikipedia.IsRedirectPage: - wikipedia.output(u"Page %s is a redirect; skipping." % page.aslink()) - except wikipedia.LockedPage: - wikipedia.output(u"Page %s is locked?!" % page.aslink()) + except pywikibot.NoPage: + pywikibot.output(u"Page %s does not exist?!" + % page.title(asLink=True)) + except pywikibot.IsRedirectPage: + pywikibot.output(u"Page %s is a redirect; skipping." + % page.title(asLink=True)) + except pywikibot.LockedPage: + pywikibot.output(u"Page %s is locked?!" % page.title(asLink=True)) def run(self): - comment = wikipedia.translate(wikipedia.getSite(), msg) - wikipedia.setAction(comment) + comment = pywikibot.translate(pywikibot.getSite(), msg) + pywikibot.setAction(comment) for page in self.generator: if self.done: break @@ -234,10 +247,11 @@ genFactory = pagegenerators.GeneratorFactory() always = False - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith('-xml'): if len(arg) == 4: - xmlFilename = wikipedia.input(u'Please enter the XML dump\'s filename:') + xmlFilename = pywikibot.input( + u'Please enter the XML dump\'s filename:') else: xmlFilename = arg[5:] gen = XmlDumpSelflinkPageGenerator(xmlFilename) @@ -265,12 +279,12 @@ pageTitle.append(arg) if pageTitle: - page = wikipedia.Page(wikipedia.getSite(), ' '.join(pageTitle)) + page = pywikibot.Page(pywikibot.getSite(), ' '.join(pageTitle)) gen = iter([page]) if not gen: gen = genFactory.getCombinedGenerator() if not gen: - wikipedia.showHelp('selflink') + pywikibot.showHelp('selflink') else: if namespaces != []: gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces) @@ -282,4 +296,4 @@ try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/spamremove.py =================================================================== --- trunk/pywikipedia/spamremove.py 2010-10-09 16:11:46 UTC (rev 8629) +++ trunk/pywikipedia/spamremove.py 2010-10-09 19:32:57 UTC (rev 8630) @@ -23,11 +23,20 @@ """ +# +# (C) Pywikipedia bot team, 2007-2010 +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id$' + +# + import sys -import wikipedia, editarticle, pagegenerators +import wikipedia as pywikibot +import pagegenerators +import editarticle -__version__ = '$Id$' - def main(): automatic = False namespaces = [] @@ -48,7 +57,7 @@ 'zh': u'機器人: 移除廣告黑名單連結 %s', } spamSite = '' - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith("-automatic"): automatic = True elif arg.startswith('-namespace:'): @@ -59,56 +68,61 @@ else: spamSite = arg if not automatic: - wikipedia.put_throttle.setDelay(1) + pywikibot.put_throttle.setDelay(1) if not spamSite: - wikipedia.showHelp('spamremove') - wikipedia.output(u"No spam site specified.") + pywikibot.showHelp('spamremove') + pywikibot.output(u"No spam site specified.") sys.exit() - mysite = wikipedia.getSite() + mysite = pywikibot.getSite() pages = list(set(mysite.linksearch(spamSite))) if namespaces: - pages = list(set(pagegenerators.NamespaceFilterPageGenerator(pages, namespaces))) + pages = list(set(pagegenerators.NamespaceFilterPageGenerator(pages, + namespaces))) if len(pages) == 0: - wikipedia.output('No page found.') + pywikibot.output('No page found.') else: - wikipedia.getall(mysite, pages) + pywikibot.getall(mysite, pages) for p in pages: text = p.get() if not spamSite in text: continue # Show the title of the page we're working on. # Highlight the title in purple. - wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % p.title()) + pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" + % p.title()) lines = text.split('\n') newpage = [] lastok = "" for line in lines: if spamSite in line: if lastok: - wikipedia.output(lastok) - wikipedia.output('\03{lightred}%s\03{default}' % line) + pywikibot.output(lastok) + pywikibot.output('\03{lightred}%s\03{default}' % line) lastok = None else: newpage.append(line) if line.strip(): if lastok is None: - wikipedia.output(line) + pywikibot.output(line) lastok = line if automatic: answer = "y" else: - answer = wikipedia.inputChoice(u'\nDelete the red lines?', ['yes', 'no', 'edit'], ['y', 'N', 'e'], 'n') + answer = pywikibot.inputChoice(u'\nDelete the red lines?', + ['yes', 'no', 'edit'], + ['y', 'N', 'e'], 'n') if answer == "n": continue elif answer == "e": editor = editarticle.TextEditor() - newtext = editor.edit(text, highlight = spamSite, jumpIndex = text.find(spamSite)) + newtext = editor.edit(text, highlight=spamSite, + jumpIndex=text.find(spamSite)) else: newtext = "\n".join(newpage) if newtext != text: - p.put(newtext, wikipedia.translate(mysite, msg) % spamSite) + p.put(newtext, pywikibot.translate(mysite, msg) % spamSite) try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/speedy_delete.py =================================================================== --- trunk/pywikipedia/speedy_delete.py 2010-10-09 16:11:46 UTC (rev 8629) +++ trunk/pywikipedia/speedy_delete.py 2010-10-09 19:32:57 UTC (rev 8630) @@ -19,20 +19,25 @@ NOTE: This script currently only works for the Wikipedia project. """ -__version__ = '$Id$' + # +# (C) Pywikipedia bot team, 2007-2010 +# # Distributed under the terms of the MIT license. # -import wikipedia +__version__ = '$Id$' +# + +import wikipedia as pywikibot import pagegenerators, catlib import time class SpeedyRobot: + """ This robot will load a list of pages from the category of candidates for + speedy deletion on the language's wiki and give the user an interactive + prompt to decide whether each should be deleted or not. + """ - This robot will load a list of pages from the category of candidates for speedy - deletion on the language's wiki and give the user an interactive prompt to decide - whether each should be deleted or not. - """ csd_cat={ 'wikipedia':{ @@ -452,28 +457,32 @@ Arguments: none yet """ - self.mySite = wikipedia.getSite() - self.csdCat = catlib.Category(self.mySite, wikipedia.translate(self.mySite, self.csd_cat)) + self.mySite = pywikibot.getSite() + self.csdCat = catlib.Category(self.mySite, + pywikibot.translate(self.mySite, + self.csd_cat)) self.savedProgress = None self.preloadingGen = None def guessReasonForDeletion(self, page): reason = None - # TODO: The following check loads the page 2 times. Find a better way to do it. - if page.isTalkPage() and (page.toggleTalkPage().isRedirectPage() or not page.toggleTalkPage().exists()): + # TODO: The following check loads the page 2 times. Find a better way to + # do it. + if page.isTalkPage() and (page.toggleTalkPage().isRedirectPage() or + not page.toggleTalkPage().exists()): # This is probably a talk page that is orphaned because we # just deleted the associated article. - reason = wikipedia.translate(self.mySite, self.talk_deletion_msg) + reason = pywikibot.translate(self.mySite, self.talk_deletion_msg) else: # Try to guess reason by the template used templateNames = page.templates() - reasons = wikipedia.translate(self.mySite, self.deletion_messages) + reasons = pywikibot.translate(self.mySite, self.deletion_messages) for templateName in templateNames: if templateName in reasons: if type(reasons[templateName]) is not unicode: #Make alias to delete_reasons - reason = wikipedia.translate(self.mySite, self.delete_reasons)[reasons[templateName]] + reason = pywikibot.translate(self.mySite, self.delete_reasons)[reasons[templateName]] else: reason = reasons[templateName] break @@ -484,26 +493,32 @@ def getReasonForDeletion(self, page): suggestedReason = self.guessReasonForDeletion(page) - wikipedia.output(u'The suggested reason is: \03{lightred}%s\03{default}' % suggestedReason) + pywikibot.output( + u'The suggested reason is: \03{lightred}%s\03{default}' + % suggestedReason) - # We don't use wikipedia.translate() here because for some languages the + # We don't use pywikibot.translate() here because for some languages the # entry is intentionally left out. if self.mySite.family.name in self.delete_reasons: if page.site().lang in self.delete_reasons[self.mySite.family.name]: - localReasons = wikipedia.translate(page.site().lang, self.delete_reasons) - wikipedia.output(u'') + localReasons = pywikibot.translate(page.site().lang, + self.delete_reasons) + pywikibot.output(u'') localReasoneKey = localReasons.keys() localReasoneKey.sort() for key in localReasoneKey: - wikipedia.output((key + ':').ljust(8) + localReasons[key]) - wikipedia.output(u'') - reason = wikipedia.input(u'Please enter the reason for deletion, choose a default reason, or press enter for the suggested message:') + pywikibot.output((key + ':').ljust(8) + localReasons[key]) + pywikibot.output(u'') + reason = pywikibot.input( + u'Please enter the reason for deletion, choose a default reason, or press enter for the suggested message:') if reason.strip() in localReasons: reason = localReasons[reason] else: - reason = wikipedia.input(u'Please enter the reason for deletion, or press enter for the suggested message:') + reason = pywikibot.input( + u'Please enter the reason for deletion, or press enter for the suggested message:') else: - reason = wikipedia.input(u'Please enter the reason for deletion, or press enter for the suggested message:') + reason = pywikibot.input( + u'Please enter the reason for deletion, or press enter for the suggested message:') if not reason: reason = suggestedReason @@ -525,56 +540,69 @@ try: pageText = page.get(get_redirect = True).split("\n") count += 1 - except wikipedia.NoPage: - wikipedia.output(u'Page %s does not exist or has already been deleted, skipping.' % page.aslink()) + except pywikibot.NoPage: + pywikibot.output( + u'Page %s does not exist or has already been deleted, skipping.' + % page.title(asLink=True)) continue # Show the title of the page we're working on. # Highlight the title in purple. - wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title()) - wikipedia.output(u'- - - - - - - - - ') + pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" + % page.title()) + pywikibot.output(u'- - - - - - - - - ') if len(pageText) > 75: - wikipedia.output('The page detail is too many lines, only output first 50 lines:') - wikipedia.output(u'- - - - - - - - - ') - wikipedia.output(u'\n'.join(pageText[:50])) + pywikibot.output( + 'The page detail is too many lines, only output first 50 lines:') + pywikibot.output(u'- - - - - - - - - ') + pywikibot.output(u'\n'.join(pageText[:50])) else: - wikipedia.output(u'\n'.join(pageText)) - wikipedia.output(u'- - - - - - - - - ') - choice = wikipedia.inputChoice(u'Input action?', ['delete', 'skip', 'update', 'quit'], ['d', 'S', 'u', 'q'], 'S') + pywikibot.output(u'\n'.join(pageText)) + pywikibot.output(u'- - - - - - - - - ') + choice = pywikibot.inputChoice(u'Input action?', + ['delete', 'skip', 'update', + 'quit'], + ['d', 'S', 'u', 'q'], 'S') if choice == 'q': keepGoing = False break elif choice == 'u': - wikipedia.output(u'Updating from CSD category.') + pywikibot.output(u'Updating from CSD category.') self.savedProgress = page.title() startFromBeginning = False break elif choice == 'd': reason = self.getReasonForDeletion(page) - wikipedia.output(u'The chosen reason is: \03{lightred}%s\03{default}' % reason) + pywikibot.output( + u'The chosen reason is: \03{lightred}%s\03{default}' + % reason) page.delete(reason, prompt = False) else: - wikipedia.output(u'Skipping page %s' % page.title()) + pywikibot.output(u'Skipping page %s' % page.title()) startFromBeginning = True if count == 0: if startFromBeginning: - wikipedia.output(u'There are no pages to delete.\nWaiting for 30 seconds or press Ctrl+C to quit...') + pywikibot.output( + u'There are no pages to delete.\nWaiting for 30 seconds or press Ctrl+C to quit...') try: time.sleep(30) except KeyboardInterrupt: keepGoing = False else: startFromBeginning = True - wikipedia.output(u'Quitting program.') + pywikibot.output(u'Quitting program.') def refreshGenerator(self): - generator = pagegenerators.CategorizedPageGenerator(self.csdCat, start = self.savedProgress) - # wrap another generator around it so that we won't produce orphaned talk pages. + generator = pagegenerators.CategorizedPageGenerator( + self.csdCat, start=self.savedProgress) + # wrap another generator around it so that we won't produce orphaned + # talk pages. generator2 = pagegenerators.PageWithTalkPageGenerator(generator) - self.preloadingGen = pagegenerators.PreloadingGenerator(generator2, pageNumber = 20) + self.preloadingGen = pagegenerators.PreloadingGenerator(generator2, + pageNumber=20) def main(): # read command line parameters - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): pass #No args yet bot = SpeedyRobot() @@ -584,4 +612,4 @@ try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/spellcheck.py =================================================================== --- trunk/pywikipedia/spellcheck.py 2010-10-09 16:11:46 UTC (rev 8629) +++ trunk/pywikipedia/spellcheck.py 2010-10-09 19:32:57 UTC (rev 8630) @@ -51,15 +51,17 @@ """ # # (C) Andre Engels, 2005 +# (C) Pywikipedia bot team, 2006-2010 # # Distributed under the terms of the MIT license. # - __version__ = '$Id$' +# import re, sys -import wikipedia, pagegenerators import string, codecs +import wikipedia as pywikibot +import pagegenerators msg={ 'ar':u'تدقيق إملائي بمساعدة البوت', @@ -73,8 +75,9 @@ 'pt':u'Bot de correção ortográfica', } + class SpecialTerm(object): - def __init__(self,text): + def __init__(self, text): self.style = text @@ -102,7 +105,8 @@ def getalternatives(string): # Find possible correct words for the incorrect word string - basetext = wikipedia.input(u"Give a text that should occur in the words to be checked.\nYou can choose to give no text, but this will make searching slow:") + basetext = pywikibot.input( + u"Give a text that should occur in the words to be checked.\nYou can choose to give no text, but this will make searching slow:") basetext = basetext.lower() simwords = {} for i in xrange(11): @@ -140,26 +144,28 @@ def askAlternative(word,context=None): correct = None - wikipedia.output(u"="*60) - wikipedia.output(u"Found unknown word '%s'"%word) + pywikibot.output(u"="*60) + pywikibot.output(u"Found unknown word '%s'"%word) if context: - wikipedia.output(u"Context:") - wikipedia.output(u""+context) - wikipedia.output(u"-"*60) + pywikibot.output(u"Context:") + pywikibot.output(u""+context) + pywikibot.output(u"-"*60) while not correct: for i in xrange(len(Word(word).getAlternatives())): - wikipedia.output(u"%s: Replace by '%s'"%(i+1,Word(word).getAlternatives()[i].replace('_',' '))) - wikipedia.output(u"a: Add '%s' as correct"%word) + pywikibot.output(u"%s: Replace by '%s'" + % (i+1, + Word(word).getAlternatives()[i].replace('_',' '))) + pywikibot.output(u"a: Add '%s' as correct"%word) if word[0].isupper(): - wikipedia.output(u"c: Add '%s' as correct"%(uncap(word))) - wikipedia.output(u"i: Ignore once (default)") - wikipedia.output(u"p: Ignore on this page") - wikipedia.output(u"r: Replace text") - wikipedia.output(u"s: Replace text, but do not save as alternative") - wikipedia.output(u"g: Guess (give me a list of similar words)") - wikipedia.output(u"*: Edit by hand") - wikipedia.output(u"x: Do not check the rest of this page") - answer = wikipedia.input(u":") + pywikibot.output(u"c: Add '%s' as correct" % (uncap(word))) + pywikibot.output(u"i: Ignore once (default)") + pywikibot.output(u"p: Ignore on this page") + pywikibot.output(u"r: Replace text") + pywikibot.output(u"s: Replace text, but do not save as alternative") + pywikibot.output(u"g: Guess (give me a list of similar words)") + pywikibot.output(u"*: Edit by hand") + pywikibot.output(u"x: Do not check the rest of this page") + answer = pywikibot.input(u":") if answer == "": answer = "i" if answer in "aAiIpP": correct = word @@ -169,11 +175,13 @@ elif answer in "pP": pageskip.append(word) elif answer in "rRsS": - correct = wikipedia.input(u"What should I replace it by?") + correct = pywikibot.input(u"What should I replace it by?") if answer in "rR": if correct_html_codes: correct = removeHTML(correct) - if correct != cap(word) and correct != uncap(word) and correct != word: + if correct != cap(word) and \ + correct != uncap(word) and \ + correct != word: try: knownwords[word] += [correct.replace(' ','_')] except KeyError: @@ -190,7 +198,7 @@ if possible: print "Found alternatives:" for pos in possible: - wikipedia.output(" %s"%pos) + pywikibot.output(" %s"%pos) else: print "No similar words found." elif answer=="*": @@ -204,7 +212,8 @@ return correct def removeHTML(page): - # TODO: Consider removing this; this stuff can be done by cosmetic_changes.py + # TODO: Consider removing this; this stuff can be done by + # cosmetic_changes.py result = page result = result.replace('Ä',u'Ä') result = result.replace('ä',u'ä') @@ -266,13 +275,15 @@ loc += len(match.group(1)) bigword = Word(match.group(2)) smallword = bigword.derive() - if not Word(smallword).isCorrect(checkalternative = knownonly) and (checknames or not smallword[0].isupper()): - replacement = askAlternative(smallword,context=text[max(0,loc-40):loc+len(match.group(2))+40]) + if not Word(smallword).isCorrect(checkalternative = knownonly) and \ + (checknames or not smallword[0].isupper()): + replacement = askAlternative(smallword, + context=text[max(0,loc-40):loc + len(match.group(2))+40]) if replacement == edit: import editarticle editor = editarticle.TextEditor() # TODO: Don't know to which index to jump - newtxt = editor.edit(text, jumpIndex = 0, highlight = smallword) + newtxt = editor.edit(text, jumpIndex = 0, highlight=smallword) if newtxt: text = newtxt elif replacement == endpage: @@ -291,6 +302,7 @@ pageskip = [] return text + class Word(object): def __init__(self,text): self.word = text @@ -348,13 +360,16 @@ if rep == self.derive(): return self.word if self.derive() not in self.word: - return wikipedia.input(u"Please give the result of replacing %s by %s in %s:"%(self.derive(),rep,self.word)) + return pywikibot.input( + u"Please give the result of replacing %s by %s in %s:" + % (self.derive(), rep, self.word)) return self.word.replace(self.derive(),rep) def isCorrect(self,checkalternative = False): # If checkalternative is True, the word will only be found incorrect if # it is on the spelling list as a spelling error. Otherwise it will - # be found incorrect if it is not on the list as a correctly spelled word. + # be found incorrect if it is not on the list as a correctly spelled + # word. if self.word == "": return True if self.word in pageskip: @@ -367,7 +382,7 @@ except KeyError: pass if self.word != uncap(self.word): - return Word(uncap(self.word)).isCorrect(checkalternative = checkalternative) + return Word(uncap(self.word)).isCorrect(checkalternative=checkalternative) else: if checkalternative: if checklang == 'nl' and self.word.endswith("'s"): @@ -424,7 +439,7 @@ checklang = None knownonly = False - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith("-start:"): start = arg[7:] elif arg.startswith("-newpages"): @@ -446,11 +461,11 @@ else: title.append(arg) - mysite = wikipedia.getSite() + mysite = pywikibot.getSite() if not checklang: checklang = mysite.language() - wikipedia.setAction(wikipedia.translate(mysite,msg)) - filename = wikipedia.config.datafilepath('spelling', + pywikibot.setAction(pywikibot.translate(mysite,msg)) + filename = pywikibot.config.datafilepath('spelling', 'spelling-' + checklang + '.txt') print "Getting wordlist" try: @@ -480,40 +495,43 @@ else: print "Wordlist successfully loaded." # This is a purely interactive bot, we therefore do not want to put-throttle - wikipedia.put_throttle.setDelay(1) + pywikibot.put_throttle.setDelay(1) except: - wikipedia.stopme() + pywikibot.stopme() raise try: if newpages: - for (page, date, length, loggedIn, user, comment) in wikipedia.getSite().newpages(1000): + for (page, date, length, loggedIn, user, comment) in pywikibot.getSite().newpages(1000): try: text = page.get() - except wikipedia.Error: + except pywikibot.Error: pass else: - text = spellcheck(text,checknames=checknames,knownonly=knownonly) + text = spellcheck(text, checknames=checknames, + knownonly=knownonly) if text != page.get(): page.put(text) elif start: for page in pagegenerators.PreloadingGenerator(pagegenerators.AllpagesPageGenerator(start=start,includeredirects=False)): try: text = page.get() - except wikipedia.Error: + except pywikibot.Error: pass else: - text = spellcheck(text,checknames=checknames,knownonly=knownonly) + text = spellcheck(text, checknames=checknames, + knownonly=knownonly) if text != page.get(): page.put(text) if longpages: - for (page, length) in wikipedia.getSite().longpages(500): + for (page, length) in pywikibot.getSite().longpages(500): try: text = page.get() - except wikipedia.Error: + except pywikibot.Error: pass else: - text = spellcheck(text, checknames = checknames,knownonly=knownonly) + text = spellcheck(text, checknames=checknames, + knownonly=knownonly) if text != page.get(): page.put(text) @@ -521,20 +539,20 @@ title = ' '.join(title) while title != '': try: - page = wikipedia.Page(mysite,title) + page = pywikibot.Page(mysite,title) text = page.get() - except wikipedia.NoPage: + except pywikibot.NoPage: print "Page does not exist." - except wikipedia.IsRedirectPage: + except pywikibot.IsRedirectPage: print "Page is a redirect page" else: text = spellcheck(text,knownonly=knownonly) if text != page.get(): page.put(text) - title = wikipedia.input(u"Which page to check now? (enter to stop)") + title = pywikibot.input(u"Which page to check now? (enter to stop)") finally: - wikipedia.stopme() - filename = wikipedia.config.datafilepath('spelling', + pywikibot.stopme() + filename = pywikibot.config.datafilepath('spelling', 'spelling-' + checklang + '.txt') if rebuild: list = knownwords.keys() @@ -547,7 +565,8 @@ if Word(word).isCorrect(): if word != uncap(word): if Word(uncap(word)).isCorrect(): - # Capitalized form of a word that is in the list uncapitalized + # Capitalized form of a word that is in the list + # uncapitalized continue f.write("1 %s\n"%word) else: Modified: trunk/pywikipedia/standardize_interwiki.py =================================================================== --- trunk/pywikipedia/standardize_interwiki.py 2010-10-09 16:11:46 UTC (rev 8629) +++ trunk/pywikipedia/standardize_interwiki.py 2010-10-09 19:32:57 UTC (rev 8630) @@ -9,7 +9,7 @@ """ # # (C) Rob W.W. Hooft, 2003 -# (C) Filnik, 2007 +# (C) Pywikipedia bot team, 2003-2010 # # Distributed under the terms of the MIT license. # @@ -17,8 +17,9 @@ # import os, sys -import wikipedia, config import difflib +import wikipedia as pywikibot +import config # The summary that the Bot will use. comment = { @@ -47,47 +48,48 @@ nothing = False # Load the default parameters and start -for arg in wikipedia.handleArgs(): +for arg in pywikibot.handleArgs(): if arg.startswith('-start'): if len(arg) == 6: - start = unicode(wikipedia.input(u'From what page do you want to start?')) + start = unicode(pywikibot.input( + u'From what page do you want to start?')) else: start = unicode(arg[7:]) -site = wikipedia.getSite() -comm = wikipedia.translate(site, comment) +site = pywikibot.getSite() +comm = pywikibot.translate(site, comment) # What follows is the main part of the code. try: for pl in site.allpages(start): plname = pl.title() - wikipedia.output(u'\nLoading %s...' % plname) + pywikibot.output(u'\nLoading %s...' % plname) try: oldtext = pl.get() - except wikipedia.IsRedirectPage: - wikipedia.output(u"%s is a redirect!" % plname) + except pywikibot.IsRedirectPage: + pywikibot.output(u"%s is a redirect!" % plname) continue old = pl.interwiki() new = {} for pl2 in old: new[pl2.site()] = pl2 - newtext = wikipedia.replaceLanguageLinks(oldtext, new) + newtext = pywikibot.replaceLanguageLinks(oldtext, new) if new: if oldtext != newtext: - wikipedia.showDiff(oldtext, newtext) + pywikibot.showDiff(oldtext, newtext) # Submit changes try: status, reason, data = pl.put(newtext, comment=comm) if str(status) != '302': - wikipedia.output(status, reason) - except wikipedia.LockedPage: - wikipedia.output(u"%s is locked" % plname) + pywikibot.output(status, reason) + except pywikibot.LockedPage: + pywikibot.output(u"%s is locked" % plname) continue else: - wikipedia.output(u'No changes needed.') + pywikibot.output(u'No changes needed.') continue else: - wikipedia.output(u'No interwiki found.') + pywikibot.output(u'No interwiki found.') continue finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/standardize_notes.py =================================================================== --- trunk/pywikipedia/standardize_notes.py 2010-10-09 16:11:46 UTC (rev 8629) +++ trunk/pywikipedia/standardize_notes.py 2010-10-09 19:32:57 UTC (rev 8630) @@ -8,7 +8,7 @@ NOTE: This script is not capable of handling the <ref></ref> syntax. It just handles the {{ref}} syntax, which is still used, but DEPRECATED on the English -Wikipedia. +wikipedia. You can run the bot with the following commandline parameters: @@ -20,7 +20,8 @@ -page - Only edit a single page. Argument can also be given as "-page:pagename". You can give this parameter multiple times to edit multiple pages. --regex - Make replacements using regular expressions. (Obsolete; always True) +-regex - Make replacements using regular expressions. + (Obsolete; always True) -except:XYZ - Ignore pages which contain XYZ. If the -regex argument is given, XYZ will be regarded as a regular expression. -namespace:n - Namespace to process. Works only with a sql dump @@ -41,17 +42,18 @@ # __version__ = '$Id$' # -# 2005-07-15: Find name of section containing citations: doFindRefSection(). (SEWilco) +# 2005-07-15: Find name of section containing citations: doFindRefSection(). +# (SEWilco) # 2005-07-15: Obey robots.txt restrictions. (SEWilco) -# 2005-07-15: Build list of all sections which may contain citations: doFindAllCitationSections(). (SEWilco) +# 2005-07-15: Build list of all sections which may contain citations: +# doFindAllCitationSections(). (SEWilco) # -#from __future__ import generators import subprocess, sys, re, random import socket, urllib, robotparser -import wikipedia, pagegenerators, config - from datetime import date +import wikipedia as pywikibot +import pagegenerators, config # httpcache is optional have_httpcache = True @@ -77,7 +79,8 @@ } fixes = { - # These replacements will convert alternate reference formats to format used by this tool. + # These replacements will convert alternate reference formats to format used + # by this tool. 'ALTREFS': { 'regex': True, # We don't want to mess up pages which discuss HTML tags, so we skip @@ -95,7 +98,8 @@ }, 'replacements': [ # Everything case-insensitive (?i) - # These translate variations of footnote templates to ref|note format. + # These translate variations of footnote templates to ref|note + # format. (r'(?i){{an\|(.*?)}}', r"{{ref|\1}}"), (r'(?i){{anb\|(.*?)}}', r"{{note|\1}}"), (r'(?i){{endnote\|(.*?)}}', r"{{note|\1}}"), @@ -141,50 +145,56 @@ # news sites for which to generate 'news reference' citations, the org name, and prefix to strip newssites = [ - ( 'abcnews.go.com', 'ABC News', 'ABC News: ' ), - ( 'books.guardian.co.uk', 'The Guardian', 'Guardian Unlimited : The Guardian : ' ), - ( 'edition.cnn.com', 'CNN', 'CNN.com - ' ), - ( 'news.bbc.co.uk', 'BBC', 'BBC NEWS : ' ), - ( 'news.scotsman.com', 'The Scotsman', 'Scotsman.com News - ' ), - ( 'nyobserver.com', 'New York Observer', '' ), - ( 'observer.guardian.co.uk', 'The Guardian', 'The Observer : ' ), - ( 'politics.guardian.co.uk', 'The Guardian', 'Guardian Unlimited Politics : ' ), - ( 'seattletimes.nwsource.com', 'The Seattle Times', 'The Seattle Times: ' ), - ( 'service.spiegel.de', 'Der Spiegel', '' ), - ( 'thescotsman.scotsman.com', 'The Scotsman', 'The Scotsman - ' ), - ( 'today.reuters.com', 'Reuters', 'Latest News and Financial Information : ' ), - ( 'today.reuters.co.uk', 'Reuters', 'Latest News and Financial Information : ' ), - ( 'www.boston.com', 'The Boston Globe', 'Boston.com / ' ), - ( 'www.cbsnews.com', 'CBS News', 'CBS News : ' ), - ( 'www.cnn.com', 'CNN', 'CNN.com - ' ), - ( 'www.cnsnews.com', 'Cybercast News Service', '' ), - ( 'www.csmonitor.com', 'Christian Science Monitor', '' ), - ( 'www.dallasnews.com', 'The Dallas Morning News', '' ), - ( 'www.forbes.com', 'Forbes', '' ), - ( 'www.foxnews.com', 'Fox News Channel', 'FOXNews.com - ' ), - ( 'www.gnn.com', 'Government News Network', 'GNN - ' ), - ( 'www.guardian.co.uk', 'The Guardian', 'Guardian Unlimited : The Guardian : ' ), - ( 'www.latimes.com', 'Los Angeles Times', '' ), - ( 'www.msnbc.msn.com', 'MSNBC', '' ), - ( 'www.nationalreview.com', 'National Review', '' ), - ( 'www.nytimes.com', 'The New York Times', '' ), - ( 'www.sfgate.com', 'San Francisco Chronicle', '' ), - ( 'www.socialistworker.co.uk', 'Socialist Worker', '' ), - ( 'www.spectator.org', 'The American Spectator', '' ), - ( 'www.telegraph.co.uk', 'The Daily Telegraph', 'Telegraph newspaper online - ' ), - ( 'www.time.com', 'TIME', '' ), - ( 'www.timesonline.co.uk', 'The Times', 'World news from The Times and the Sunday Times - ' ), - ( 'www.usatoday.com', 'USA Today', 'USATODAY.com - ' ), - ( 'www.washingtonpost.com', 'The Washington Post', '' ), - ( 'www.washtimes.com', 'The Washington Times', '' ), - ( 'www.weeklystandard.com', 'The Weekly Standard', '' ), - ( 'www.wired.com', 'Wired magazine', 'Wired News: ' ), - ( 'wwwimage.cbsnews.com', 'CBS News', 'CBS News : ' ), + ('abcnews.go.com', 'ABC News', 'ABC News: '), + ('books.guardian.co.uk', 'The Guardian', + 'Guardian Unlimited : The Guardian : '), + ('edition.cnn.com', 'CNN', 'CNN.com - '), + ('news.bbc.co.uk', 'BBC', 'BBC NEWS : '), + ('news.scotsman.com', 'The Scotsman', 'Scotsman.com News - '), + ('nyobserver.com', 'New York Observer', ''), + ('observer.guardian.co.uk', 'The Guardian', 'The Observer : '), + ('politics.guardian.co.uk', 'The Guardian', + 'Guardian Unlimited Politics : '), + ('seattletimes.nwsource.com', 'The Seattle Times', 'The Seattle Times: '), + ('service.spiegel.de', 'Der Spiegel', ''), + ('thescotsman.scotsman.com', 'The Scotsman', 'The Scotsman - '), + ('today.reuters.com', 'Reuters', 'Latest News and Financial Information : '), + ('today.reuters.co.uk', 'Reuters', + 'Latest News and Financial Information : '), + ('www.boston.com', 'The Boston Globe', 'Boston.com / '), + ('www.cbsnews.com', 'CBS News', 'CBS News : '), + ('www.cnn.com', 'CNN', 'CNN.com - '), + ('www.cnsnews.com', 'Cybercast News Service', ''), + ('www.csmonitor.com', 'Christian Science Monitor', ''), + ('www.dallasnews.com', 'The Dallas Morning News', ''), + ('www.forbes.com', 'Forbes', ''), + ('www.foxnews.com', 'Fox News Channel', 'FOXNews.com - '), + ('www.gnn.com', 'Government News Network', 'GNN - '), + ('www.guardian.co.uk', 'The Guardian', + 'Guardian Unlimited : The Guardian : '), + ('www.latimes.com', 'Los Angeles Times', ''), + ('www.msnbc.msn.com', 'MSNBC', ''), + ('www.nationalreview.com', 'National Review', ''), + ('www.nytimes.com', 'The New York Times', ''), + ('www.sfgate.com', 'San Francisco Chronicle', ''), + ('www.socialistworker.co.uk', 'Socialist Worker', ''), + ('www.spectator.org', 'The American Spectator', ''), + ('www.telegraph.co.uk', 'The Daily Telegraph', + 'Telegraph newspaper online - '), + ('www.time.com', 'TIME', ''), + ('www.timesonline.co.uk', 'The Times', + 'World news from The Times and the Sunday Times - '), + ('www.usatoday.com', 'USA Today', 'USATODAY.com - '), + ('www.washingtonpost.com', 'The Washington Post', ''), + ('www.washtimes.com', 'The Washington Times', ''), + ('www.weeklystandard.com', 'The Weekly Standard', ''), + ('www.wired.com', 'Wired magazine', 'Wired News: '), + ('wwwimage.cbsnews.com', 'CBS News', 'CBS News : '), ] + class ReplacePageGenerator: - """ - Generator which will yield Pages for pages that might contain text to + """ Generator which will yield Pages for pages that might contain text to replace. These pages might be retrieved from a local SQL dump file or a text file, or as a list of pages entered by the user. @@ -205,7 +215,9 @@ will be used when source is 'sqldump'. * pagenames - a list of pages which will be used when source is 'userinput'. + """ + def __init__(self, source, replacements, exceptions, regex = False, namespace = -1, textfilename = None, sqlfilename = None, categoryname = None, pagenames = None): self.source = source self.replacements = replacements @@ -218,8 +230,7 @@ self.pagenames = pagenames def read_pages_from_sql_dump(self): - """ - Generator which will yield Pages to pages that might contain text to + """ Generator which will yield Pages to pages that might contain text to replace. These pages will be retrieved from a local sql dump file (cur table). @@ -229,12 +240,13 @@ are values * exceptions - a list of strings; pages which contain one of these won't be changed. - * regex - if the entries of replacements and exceptions should - be interpreted as regular expressions + * regex - if the entries of replacements and exceptions + should be interpreted as regular expressions + """ - mysite = wikipedia.getSite() + mysite = pywikibot.getSite() import sqldump - dump = sqldump.SQLdump(self.sqlfilename, wikipedia.getSite().encoding()) + dump = sqldump.SQLdump(self.sqlfilename, pywikibot.getSite().encoding()) for entry in dump.entries(): skip_page = False if self.namespace != -1 and self.namespace != entry.namespace: @@ -255,11 +267,11 @@ if self.regex: old = re.compile(old) if old.search(entry.text): - yield wikipedia.Page(mysite, entry.full_title()) + yield pywikibot.Page(mysite, entry.full_title()) break else: if old in entry.text: - yield wikipedia.Page(mysite, entry.full_title()) + yield pywikibot.Page(mysite, entry.full_title()) break def read_pages_from_category(self): @@ -270,9 +282,10 @@ Arguments: * textfilename - the textfile's path, either absolute or relative + """ import catlib - category = catlib.Category(wikipedia.getSite(), self.categoryname) + category = catlib.Category(pywikibot.getSite(), self.categoryname) for page in category.articles(recurse = False): yield page @@ -284,6 +297,7 @@ Arguments: * textfilename - the textfile's path, either absolute or relative + """ f = open(self.textfilename, 'r') # regular expression which will find [[wiki links]] @@ -294,7 +308,7 @@ # TODO: use findall() instead. m=R.match(line) if m: - yield wikipedia.Page(wikipedia.getSite(), m.group(1)) + yield pywikibot.Page(pywikibot.getSite(), m.group(1)) f.close() def read_pages_from_wiki_page(self): @@ -305,9 +319,10 @@ Arguments: * pagetitle - the title of a page on the home wiki + ''' - listpage = wikipedia.Page(wikipedia.getSite(), self.pagetitle) - list = wikipedia.get(listpage) + listpage = pywikibot.Page(pywikibot.getSite(), self.pagetitle) + list = pywikibot.get(listpage) # TODO - UNFINISHED # TODO: Make MediaWiki's search feature available. @@ -326,7 +341,7 @@ yield pl elif self.source == 'userinput': for pagename in self.pagenames: - yield wikipedia.Page(wikipedia.getSite(), pagename) + yield pywikibot.Page(pywikibot.getSite(), pagename) class ReplaceRobot: def __init__(self, generator, replacements, refsequence, references, @@ -375,36 +390,40 @@ new_text = new_text.replace(old, new) # Find name of Notes section. - refsectionname = self.doFindRefSection( new_text ) + refsectionname = self.doFindRefSection(new_text) # Get list of all sections which may contain citations. - refsectionlist = self.doFindAllCitationSections( new_text, refsectionname ) + refsectionlist = self.doFindAllCitationSections(new_text, + refsectionname) # Read existing Notes section contents into references list - wikipedia.output( u"Reading existing Notes section" ) + pywikibot.output(u"Reading existing Notes section") self.doReadReferencesSection( new_text, refsectionname ) while self.references and self.references[len(self.references)-1] == u'\n': del self.references[len(self.references)-1] # delete trailing empty lines # Convert any external links to footnote references - wikipedia.output( u"Converting external links" ) - new_text = self.doConvertExternalLinks( new_text ) + pywikibot.output(u"Converting external links" ) + new_text = self.doConvertExternalLinks(new_text) # Accumulate ordered list of all references - wikipedia.output( u"Collecting references" ) + pywikibot.output(u"Collecting references") (duplicatefound, self.refusage) = self.doBuildSequenceListOfReferences( new_text ) # Rewrite references, including dealing with duplicates. - wikipedia.output( u"Rewriting references" ) - new_text = self.doRewriteReferences( new_text, self.refusage, refsectionname ) + pywikibot.output(u"Rewriting references") + new_text = self.doRewriteReferences(new_text, self.refusage, + refsectionname) # Reorder Notes to match sequence of ordered list - wikipedia.output( u"Collating references" ) - self.references = self.doReorderReferences( self.references, self.refusage) + pywikibot.output(u"Collating references") + self.references = self.doReorderReferences(self.references, + self.refusage) # Rebuild Notes section - wikipedia.output( u"Rebuilding References section" ) - new_text = self.doUpdateReferencesSection( new_text, self.refusage, refsectionname ) + pywikibot.output(u"Rebuilding References section" ) + new_text = self.doUpdateReferencesSection(new_text, self.refusage, + refsectionname) return new_text def doConvertExternalLinks(self, original_text): + """ Returns the text which is generated by converting external links to + References. Adds References to reference list. + """ - Returns the text which is generated by converting external links to References. - Adds References to reference list. - """ new_text = '' # Default is no text skipsection = False for text_line in original_text.splitlines(True): # Scan all text line by line @@ -422,7 +441,7 @@ # TODO: recognize {{inline}} invisible footnotes when something can be done with them # # Ignore lines within comments - if not text_line.startswith( u'<!--' ): + if not text_line.startswith( u'<!--'): # Fix erroneous external links in double brackets Rextlink = re.compile(r'(?i)\[\[(?P<linkname>http://[^\]]+?)\]\]') # TODO: compiling the regex each time might be inefficient @@ -485,20 +504,17 @@ m = re.search( r'==+(?P<sectionname>[^=]+)==', text_line ) if m: # if in a section, remember section name sectionname = m.group('sectionname').strip() - wikipedia.output( u'Section: %s' % sectionname ) + pywikibot.output( u'Section: %s' % sectionname ) else: # else not a section name so look for reference n = re.search( r'(i?){{(note|ibid)[|]', text_line ) if n: # if reference found refsectionname = sectionname # found reference section - wikipedia.output( u'Ref section: %s' % refsectionname ) + pywikibot.output( u'Ref section: %s' % refsectionname ) break # stop looking return refsectionname def doFindAllCitationSections(self, original_text, refsectionname): - - """ - Returns list of sections which may contain citations. - """ + """ Returns list of sections which may contain citations. """ refsectionlist = [ ( refsectionname) ] sectionname = '' for text_line in original_text.splitlines(True): # Scan all text line by line @@ -523,13 +539,13 @@ if m: # if in a section, check if should skip this section if refsectionname != '': # if a certain section name has been identified m_section = m.group('sectionname') - wikipedia.output( u'Looking for "%s": "%s"' % (refsectionname,unicode(m_section)) ) + pywikibot.output( u'Looking for "%s": "%s"' % (refsectionname,unicode(m_section)) ) if unicode(m_section.strip()) == unicode(refsectionname): - wikipedia.output( u'Found Ref section.' ) + pywikibot.output( u'Found Ref section.') skipsection = True # skipsection left True so no further links converted else: # else grab all possible sections if m.group('sectionname').lower().strip() in referencesectionnames: - wikipedia.output( 'RefSection found by default names: %s' % m.group('sectionname') ) + pywikibot.output('RefSection found by default names: %s' % m.group('sectionname') ) skipsection = True # skipsection left True so no further links converted if skipsection: new_text = new_text + text_line # skip section, so retain text. @@ -543,11 +559,11 @@ m = Rtext_line.search( text_line ) alphabet26 = u'abcdefghijklmnopqrstuvwxyz' while m: # if found a reference - if m.group('reftype').lower() in ( 'ref', 'ref_num', 'ref_label' ): # confirm ref + if m.group('reftype').lower() in ('ref', 'ref_num', 'ref_label'): # confirm ref refkey = m.group('refname').strip() if refkey != '': if refkey in refusage: - # wikipedia.output( u'refusage[%s] = %s' % (refkey,refusage[refkey]) ) + # pywikibot.output( u'refusage[%s] = %s' % (refkey,refusage[refkey]) ) if refusage[refkey][2] == 0: # if first use of reference text_line=text_line[:m.start(0)] + '{{ref|%s}}' % (refkey) + text_line[m.end(0):] refusage[refkey][2] += 1 # count use of reference @@ -574,60 +590,71 @@ urlfile = None urlheaders = None if len(extlink_linkname) > 5: - socket.setdefaulttimeout( 20 ) # timeout in seconds - wikipedia.get_throttle() # throttle down to Wikipedia rate + socket.setdefaulttimeout(20) # timeout in seconds + pywikibot.get_throttle() # throttle down to Wikipedia rate # Obey robots.txt restrictions rp = robotparser.RobotFileParser() rp.set_url( extlink_linkname ) try: rp.read() # read robots.txt except (IOError, socket.timeout): - wikipedia.output( u'Error accessing URL: %s' % unicode(extlink_linkname) ) + pywikibot.output(u'Error accessing URL: %s' + % unicode(extlink_linkname)) else: urlobj = None if not rp.can_fetch( "*", extlink_linkname ): - wikipedia.output( u'Robot prohibited: %s' % unicode(extlink_linkname) ) + pywikibot.output(u'Robot prohibited: %s' + % unicode(extlink_linkname)) else: # else access allowed try: if have_httpcache: - cache = HTTPCache( extlink_linkname ) + cache = HTTPCache(extlink_linkname) urlfile = cache.filename() # filename of cached date urlheaders = cache.info() else: - (urlfile, urlheaders) = urllib.urlretrieve( extlink_linkname ) + (urlfile, urlheaders) = urllib.urlretrieve(extlink_linkname) except IOError: - wikipedia.output( u'Error accessing URL. %s' % unicode(extlink_linkname) ) + pywikibot.output(u'Error accessing URL. %s' + % unicode(extlink_linkname)) except (socket.herror, socket.gaierror), (err, msg): - wikipedia.output( u'Error %i accessing URL, %s. %s' % (err, unicode(msg), unicode(extlink_linkname)) ) + pywikibot.output(u'Error %i accessing URL, %s. %s' + % (err, unicode(msg), + unicode(extlink_linkname))) except socket.timeout, msg: - wikipedia.output( u'Error accessing URL, %s. %s' % (unicode(msg), unicode(extlink_linkname)) ) + pywikibot.output(u'Error accessing URL, %s. %s' + % (unicode(msg), + unicode(extlink_linkname))) except: # Ignore other errors pass if urlfile != None: urlobj = open( urlfile ) if extlink_linkname.lower().endswith('.pdf'): # If file has a PDF suffix - wikipedia.output( u'PDF file.' ) + pywikibot.output( u'PDF file.') try: pdfinfo_out = subprocess.Popen([r"pdfinfo","/dev/stdin"], stdin=urlobj, stdout=subprocess.PIPE, shell=False).communicate()[0] for aline in pdfinfo_out.splitlines(): if aline.lower().startswith('title'): urltitle = aline.split(None)[1:] urltitle = ' '.join(urltitle) - if urltitle != '': wikipedia.output(u'title: ' +urltitle ) + if urltitle: + pywikibot.output(u'title: %s' + % urltitle) else: if aline.lower().startswith('author'): urlauthor = aline.split(None)[1:] urlauthor = ' '.join(urlauthor) - if urlauthor != '': wikipedia.output(u'author: ' +urlauthor ) + if urlauthor: + pywikibot.output(u'author: %s' + % urlauthor ) except ValueError: - wikipedia.output( u'pdfinfo value error.' ) + pywikibot.output( u'pdfinfo value error.') except OSError: - wikipedia.output( u'pdfinfo OS error.' ) + pywikibot.output( u'pdfinfo OS error.') except: # Ignore errors - wikipedia.output( u'PDF processing error.' ) + pywikibot.output( u'PDF processing error.') pass - wikipedia.output( u'PDF done.' ) + pywikibot.output( u'PDF done.') if urlobj: urlobj.close() else: @@ -643,14 +670,16 @@ except: urltitle = u' ' # error, no title urltitle = u' '.join(urltitle.split()) # merge whitespace - wikipedia.output( u'::::Title: %s' % urltitle ) + pywikibot.output( u'::::Title: %s' % urltitle ) break # found a title so stop looking else: if maxalines < 1: - wikipedia.output( u'No title in URL. %s' % unicode(extlink_linkname) ) + pywikibot.output( + u'No title in URL. %s' + % unicode(extlink_linkname) ) else: if urlobj != None: - wikipedia.output( u'::+URL: ' + extlink_linkname ) + pywikibot.output( u'::+URL: ' + extlink_linkname ) # urlinfo = urlobj.info() aline = urlobj.read() full_page = '' @@ -664,7 +693,7 @@ try: urltitle = unicode(titleRE.group('HTMLtitle'), 'utf-8') urltitle = u' '.join(urltitle.split()) # merge whitespace - wikipedia.output( u'::::Title: %s' % urltitle ) + pywikibot.output( u'::::Title: %s' % urltitle ) except: aline = urlobj.read() continue @@ -676,7 +705,7 @@ aline = urlobj.read() else: aline = urlobj.read() - if urltitle != '': wikipedia.output( u'title: ' + urltitle ) + if urltitle != '': pywikibot.output( u'title: ' + urltitle ) # Try a more advanced search ##from nltk.parser.probabilistic import * ##from nltk.tokenizer import * @@ -698,17 +727,17 @@ #for tok in train_tokens: britaggerrules.train(tok, max_rules=200, min_score=2) # brittaggerrul = britaggerrules.train(train_tokens, max_rules=200, min_score=2) #britaggerrul = () - #britagger = BrillTagger(initial_tagger=unitagger, rules=britaggerrul, SUBTOKENS='WORDS' ) + #britagger = BrillTagger(initial_tagger=unitagger, rules=britaggerrul, SUBTOKENS='WORDS') # Training completed # Examine text ##text_token = Token(TEXT=full_page) ##WhitespaceTokenizer(SUBTOKENS='WORDS').tokenize(text_token) #unitagger.tag(text_token) #britagger.tag(text_token) - ### wikipedia.output( unicode(text_token) ) + ### pywikibot.output( unicode(text_token) ) else: - wikipedia.output( u'No data retrieved.' ) - socket.setdefaulttimeout( 200 ) # timeout in seconds + pywikibot.output( u'No data retrieved.') + socket.setdefaulttimeout(200) urltitle = urltitle.replace(u'|',u':') return urltitle.strip() @@ -731,11 +760,11 @@ new_text = u'' now = date.today() if extlink_linktext == None or len(extlink_linktext.strip()) < 20: - wikipedia.output( u'Fetching URL: %s' % unicode(extlink_linkname) ) + pywikibot.output( u'Fetching URL: %s' % unicode(extlink_linkname) ) urltitle = self.doGetTitleFromURL( extlink_linkname ) # try to get title from URL if urltitle == None or urltitle == '': - urltitle = extlink_linkname # Assume linkname for title - wikipedia.output( u'Title is: %s' % urltitle ) + urltitle = extlink_linkname + pywikibot.output( u'Title is: %s' % urltitle ) extlink_linktext = urltitle for newref in self.references: # scan through all references if extlink_linkname in newref: # if undescribed linkname same as a previous entry @@ -750,7 +779,7 @@ for (sitename, newscompany, stripprefix) in newssites: if refname.startswith( sitename ): # If there is a prefix to strip from the title - if stripprefix and extlink_linktext.startswith( stripprefix ): + if stripprefix and extlink_linktext.startswith(stripprefix): extlink_linktext = extlink_linktext[len(stripprefix):] new_text = u'{{news reference | title=%s | url=%s | urldate=%s | org=%s }}' % ( extlink_linktext, extlink_linkname, now.isoformat(), newscompany ) + '\n' break @@ -764,12 +793,14 @@ a format suitable for the Notes section. """ # TODO: look up DOI info and create full reference - urltitle = self.doGetTitleFromURL( 'http://dx.doi.org/' + doi_linktext ) # try to get title from URL + urltitle = self.doGetTitleFromURL('http://dx.doi.org/' + doi_linktext ) # try to get title from URL refname = 'refbot%d' % refsequence if urltitle: - new_text = '# {{note|%s}} %s {{doi|%s}}' % (refname, urltitle, doi_linktext) + '\n' + new_text = '# {{note|%s}} %s {{doi|%s}}\n' \ + % (refname, urltitle, doi_linktext) else: - new_text = '# {{note|%s}} {{doi|%s}}' % (refname, doi_linktext) + '\n' + new_text = '# {{note|%s}} {{doi|%s}}\n' \ + % (refname, doi_linktext) return (refname, new_text) def doBuildSequenceListOfReferences(self, original_text): @@ -777,14 +808,14 @@ Returns a list with all found references and sequence numbers. """ duplicatefound = False - refusage = {} # Nothing found yet + refusage = {} # Data structure: refusage[reference_key] = [ sequence_in_document, count, count_during_dup_handling ] for text_line in original_text.splitlines(True): # Scan all text line by line # Check for various references Rtext_line = re.compile(r'(?i){{(?P<reftype>ref|ref_num|ref_label)\|(?P<refname>[^}|]+?)}}') m = Rtext_line.search( text_line ) while m: # if found a reference - if m.group('reftype').lower() in ( 'ref', 'ref_num', 'ref_label' ): # confirm ref + if m.group('reftype').lower() in ('ref', 'ref_num', 'ref_label'): # confirm ref refkey = m.group('refname').strip() if refkey != '': if refkey in refusage: @@ -793,7 +824,7 @@ else: refusage[refkey] = [len(refusage),0,0] # remember this reference m = Rtext_line.search( text_line, m.end() ) - wikipedia.output( u'Number of refs: %d' % (len(refusage)) ) + pywikibot.output( u'Number of refs: %d' % (len(refusage)) ) return (duplicatefound, refusage) def doReadReferencesSection(self, original_text, refsectionname): @@ -803,7 +834,7 @@ Contents of all Notes sections will be read. """ # TODO: support subsections within Notes - new_text = '' # Default is no text + new_text = '' intargetsection = False for text_line in original_text.splitlines(True): # Scan all text line by line # Check for target section @@ -811,19 +842,20 @@ if m: # if in a section, check if Notes section if refsectionname != '': # if a certain section name has been identified m_section = m.group('sectionname') - wikipedia.output( u'Looking for "%s": "%s"' % (refsectionname,m_section) ) + pywikibot.output(u'Looking for "%s": "%s"' + % (refsectionname,m_section) ) if unicode(m_section.strip()) == unicode(refsectionname): - wikipedia.output( u'Read Ref section.' ) - intargetsection = True # flag as being in section + pywikibot.output(u'Read Ref section.') + intargetsection = True new_text = new_text + text_line else: - intargetsection = False # flag as not being in section + intargetsection = False else: # else grab all possible sections if m.group('sectionname').lower().strip() in referencesectionnames: - intargetsection = True # flag as being in section + intargetsection = True new_text = new_text + text_line else: - intargetsection = False # flag as not being in section + intargetsection = False else: if intargetsection: # if inside target section, remember this reference line if text_line.strip() != '': @@ -837,8 +869,8 @@ if intargetsection: # if still inside target section # Convert any # wiki list to *; will be converted later if a reference if text_line[0] == '#': - text_line = '*' + text_line[1:] # replace # with * wiki - self.references.append( text_line.rstrip() + u'\n' ) # Append line to references + text_line = '*' + text_line[1:] + self.references.append(text_line.rstrip() + u'\n') new_text = new_text + text_line.rstrip() + u'\n' return new_text @@ -891,7 +923,7 @@ Returns the text which is generated by rebuilding the Notes section. Rewrite Notes section from references list. """ - new_text = '' # Default is no text + new_text = '' intargetsection = False for text_line in original_text.splitlines(True): # Scan all text line by line # Check for target section @@ -899,9 +931,9 @@ if m: # if in a section, check if Notes section if refsectionname != '': # if a certain section name has been identified m_section = m.group('sectionname') - wikipedia.output( u'Looking for "%s": "%s"' % (refsectionname,m_section) ) + pywikibot.output( u'Looking for "%s": "%s"' % (refsectionname,m_section) ) if unicode(m_section.strip()) == unicode(refsectionname): - wikipedia.output( u'Updating Ref section.' ) + pywikibot.output( u'Updating Ref section.') intargetsection = True # flag as being in section else: intargetsection = False # flag as not being in section @@ -933,7 +965,7 @@ if not intargetsection: # if not in Notes section, remember line new_text = new_text + text_line # append new line to new text # If references list not emptied, there was no Notes section found - if self.references != []: # empty references + if self.references != []: # New Notes section needs to be created at bottom. text_line_counter = 0 # current line last_text_line_counter_value = 0 # number of last line of possible text @@ -978,26 +1010,29 @@ # Load the page's text from the wiki original_text = pl.get() if pl.editRestriction: - wikipedia.output(u'Skipping locked page %s' % pl.title()) + pywikibot.output(u'Skipping locked page %s' % pl.title()) continue - except wikipedia.NoPage: - wikipedia.output(u'Page %s not found' % pl.title()) + except pywikibot.NoPage: + pywikibot.output(u'Page %s not found' % pl.title()) continue - except wikipedia.IsRedirectPage: + except pywikibot.IsRedirectPage: continue match = self.checkExceptions(original_text) # skip all pages that contain certain texts if match: - wikipedia.output(u'Skipping %s because it contains %s' % (pl.title(), match)) + pywikibot.output(u'Skipping %s because it contains %s' + % (pl.title(), match)) else: new_text = self.doReplacements(original_text) if new_text == original_text: - wikipedia.output('No changes were necessary in %s' % pl.title()) + pywikibot.output('No changes were necessary in %s' + % pl.title()) else: - wikipedia.output(u'>>> %s <<<' % pl.title()) - wikipedia.showDiff(original_text, new_text) + pywikibot.output(u'>>> %s <<<' % pl.title()) + pywikibot.showDiff(original_text, new_text) if not self.acceptall: - choice = wikipedia.input(u'Do you want to accept these changes? [y|n|a(ll)]') + choice = pywikibot.input( + u'Do you want to accept these changes? [y|n|a(ll)]') if choice in ['a', 'A']: self.acceptall = True if self.acceptall or choice in ['y', 'Y']: @@ -1034,7 +1069,7 @@ # default to -1 which means all namespaces will be processed namespace = -1 # Load default summary message. - editSummary = wikipedia.translate(wikipedia.getSite(), msg) + editSummary = pywikibot.translate(pywikibot.getSite(), msg) # List of references in Notes section references = [] # Notes sequence number @@ -1043,31 +1078,33 @@ refusage = {} # Read commandline parameters. - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg == '-regex': regex = True elif arg.startswith('-file'): if len(arg) == 5: - textfilename = wikipedia.input(u'Please enter the filename:') + textfilename = pywikibot.input(u'Please enter the filename:') else: textfilename = arg[6:] source = 'textfile' elif arg.startswith('-cat'): if len(arg) == 4: - categoryname = wikipedia.input(u'Please enter the category name:') + categoryname = pywikibot.input( + u'Please enter the category name:') else: categoryname = arg[5:] source = 'category' elif arg.startswith('-sql'): if len(arg) == 4: - sqlfilename = wikipedia.input(u'Please enter the SQL dump\'s filename:') + sqlfilename = pywikibot.input( + u'Please enter the SQL dump\'s filename:') else: sqlfilename = arg[5:] source = 'sqldump' elif arg.startswith('-page'): if len(arg) == 5: pagenames.append( - wikipedia.input(u'Which page do you want to change?')) + pywikibot.input(u'Which page do you want to change?')) else: pagenames.append(arg[6:]) source = 'userinput' @@ -1085,16 +1122,19 @@ if source == None or len(commandline_replacements) not in [0, 2]: # syntax error, show help text from the top of this file - wikipedia.output(__doc__, 'utf-8') + pywikibot.output(__doc__, 'utf-8') return if (len(commandline_replacements) == 2): replacements[commandline_replacements[0]] = commandline_replacements[1] - editSummary = wikipedia.translate(wikipedia.getSite(), msg ) % ' (-' + commandline_replacements[0] + ' +' + commandline_replacements[1] + ')' + editSummary = pywikibot.translate(pywikibot.getSite(), msg) + % ' (-' + commandline_replacements[0] + ' +' + commandline_replacements[1] + ')' else: change = '' - default_summary_message = wikipedia.translate(wikipedia.getSite(), msg) % change - wikipedia.output(u'The summary message will default to: %s' % default_summary_message) - summary_message = wikipedia.input(u'Press Enter to use this default message, or enter a description of the changes your bot will make:') + default_summary_message = pywikibot.translate(pywikibot.getSite(), msg) % change + pywikibot.output(u'The summary message will default to: %s' + % default_summary_message) + summary_message = pywikibot.input( + u'Press Enter to use this default message, or enter a description of the changes your bot will make:') if summary_message == '': summary_message = default_summary_message editSummary = summary_message @@ -1103,18 +1143,20 @@ try: fix = fixes['ALTREFS'] except KeyError: - wikipedia.output(u'Available predefined fixes are: %s' % fixes.keys()) + pywikibot.output(u'Available predefined fixes are: %s' + % fixes.keys()) return if 'regex' in fix: regex = fix['regex'] if 'msg' in fix: - editSummary = wikipedia.translate(wikipedia.getSite(), fix['msg']) + editSummary = pywikibot.translate(pywikibot.getSite(), fix['msg']) if 'exceptions' in fix: exceptions = fix['exceptions'] replacements = fix['replacements'] - gen = ReplacePageGenerator(source, replacements, exceptions, regex, namespace, - textfilename, sqlfilename, categoryname, pagenames) + gen = ReplacePageGenerator(source, replacements, exceptions, regex, + namespace, textfilename, sqlfilename, + categoryname, pagenames) preloadingGen = pagegenerators.PreloadingGenerator(gen, pageNumber = 20) bot = ReplaceRobot(preloadingGen, replacements, refsequence, references, refusage, exceptions, regex, acceptall, editSummary) @@ -1125,4 +1167,4 @@ try: main() finally: - wikipedia.stopme() + pywikibot.stopme()

13 years, 6 months

SVN: [8629] trunk/pywikipedia

by xqt＠svn.wikimedia.org

Revision: 8629 Author: xqt Date: 2010-10-09 16:11:46 +0000 (Sat, 09 Oct 2010) Log Message: ----------- import wikipedia as pywikibot for merging to rewrite Modified Paths: -------------- trunk/pywikipedia/copyright.py trunk/pywikipedia/lonelypages.py trunk/pywikipedia/makecat.py trunk/pywikipedia/misspelling.py trunk/pywikipedia/movepages.py trunk/pywikipedia/pagefromfile.py trunk/pywikipedia/pageimport.py trunk/pywikipedia/piper.py trunk/pywikipedia/protect.py trunk/pywikipedia/rciw.py trunk/pywikipedia/rcsort.py Modified: trunk/pywikipedia/copyright.py =================================================================== --- trunk/pywikipedia/copyright.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/copyright.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -638,7 +638,7 @@ consecutive = False continue n_query += 1 - #wikipedia.output(search_words) + #pywikibot.output(search_words) if config.copyright_max_query_for_page and n_query > config.copyright_max_query_for_page: warn(u"Max query limit for page reached") return output @@ -845,7 +845,7 @@ def get_results(self, query, numresults = 10): result_list = list() query = re.sub("[()\"<>]", "", query) - # wikipedia.output(query) + # pywikibot.output(query) if config.copyright_google: self.soap('google', query, result_list) if config.copyright_yahoo: Modified: trunk/pywikipedia/lonelypages.py =================================================================== --- trunk/pywikipedia/lonelypages.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/lonelypages.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -46,7 +46,8 @@ __version__ = '$Id: lonelypages.py,v 1.0 2007/12/28 19.16.00 filnik Exp$' # -import wikipedia, pagegenerators +import wikipedia as pywikibot +import pagegenerators import re # This is required for the text that is shown when you run this script @@ -115,20 +116,20 @@ always = False # Check variable for always disambigPage = None # If no disambigPage given, not use it. # Arguments! - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith('-enable'): if len(arg) == 7: - enablePage = wikipedia.input(u'Would you like to check if the bot should run or not?') + enablePage = pywikibot.input(u'Would you like to check if the bot should run or not?') else: enablePage = arg[8:] if arg.startswith('-disambig'): if len(arg) == 9: - disambigPage = wikipedia.input(u'In which page should the bot save the disambig pages?') + disambigPage = pywikibot.input(u'In which page should the bot save the disambig pages?') else: disambigPage = arg[10:] elif arg.startswith('-limit'): if len(arg) == 6: - limit = int(wikipedia.input(u'How many pages do you want to check?')) + limit = int(pywikibot.input(u'How many pages do you want to check?')) else: limit = int(arg[7:]) elif arg.startswith('-newpages'): @@ -136,14 +137,14 @@ nwlimit = 50 # Default: 50 pages else: nwlimit = int(arg[10:]) - generator = wikipedia.getSite().newpages(number = nwlimit) + generator = pywikibot.getSite().newpages(number = nwlimit) nwpages = True elif arg == '-always': always = True else: genFactory.handleArg(arg) # Retrive the site - wikiSite = wikipedia.getSite() + wikiSite = pywikibot.getSite() if not generator: generator = genFactory.getCombinedGenerator() @@ -152,49 +153,49 @@ if not generator: generator = wikiSite.lonelypages(repeat = True, number = limit) # Take the configurations according to our project - comment = wikipedia.translate(wikiSite, commento) - commentdisambig = wikipedia.translate(wikiSite, commenttodisambig) - template = wikipedia.translate(wikiSite, Template) - exception = wikipedia.translate(wikiSite, exception) + comment = pywikibot.translate(wikiSite, commento) + commentdisambig = pywikibot.translate(wikiSite, commenttodisambig) + template = pywikibot.translate(wikiSite, Template) + exception = pywikibot.translate(wikiSite, exception) # EnablePage part if enablePage != None: # Define the Page Object - enable = wikipedia.Page(wikiSite, enablePage) + enable = pywikibot.Page(wikiSite, enablePage) # Loading the page's data try: getenable = enable.get() - except wikipedia.NoPage: - wikipedia.output(u"%s doesn't esist, I use the page as if it was blank!" % enable.title()) + except pywikibot.NoPage: + pywikibot.output(u"%s doesn't esist, I use the page as if it was blank!" % enable.title()) getenable = '' except wikiepedia.IsRedirect: - wikipedia.output(u"%s is a redirect, skip!" % enable.title()) + pywikibot.output(u"%s is a redirect, skip!" % enable.title()) getenable = '' # If the enable page is set to disable, turn off the bot # (useful when the bot is run on a server) if getenable != 'enable': - wikipedia.output('The bot is disabled') + pywikibot.output('The bot is disabled') return # DisambigPage part if disambigPage != None: - disambigpage = wikipedia.Page(wikiSite, disambigPage) + disambigpage = pywikibot.Page(wikiSite, disambigPage) try: disambigtext = disambigpage.get() - except wikipedia.NoPage: - wikipedia.output(u"%s doesn't esist, skip!" % disambigpage.title()) + except pywikibot.NoPage: + pywikibot.output(u"%s doesn't esist, skip!" % disambigpage.title()) disambigtext = '' except wikiepedia.IsRedirect: - wikipedia.output(u"%s is a redirect, don't use it!" % disambigpage.title()) + pywikibot.output(u"%s is a redirect, don't use it!" % disambigpage.title()) disambigPage = None # Main Loop for page in generator: if nwpages == True: page = page[0] # The newpages generator returns a tuple, not a Page object. - wikipedia.output(u"Checking %s..." % page.title()) + pywikibot.output(u"Checking %s..." % page.title()) # Used to skip the first pages in test phase... #if page.title()[0] in ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q']: #continue if page.isRedirectPage(): # If redirect, skip! - wikipedia.output(u'%s is a redirect! Skip...' % page.title()) + pywikibot.output(u'%s is a redirect! Skip...' % page.title()) continue # refs is not a list, it's a generator while resList... is a list, yes. refs = page.getReferences() @@ -202,27 +203,27 @@ for j in refs: if j == None: # We have to find out why the function returns that value - wikipedia.output(u'Error: 1 --> Skip page') + pywikibot.output(u'Error: 1 --> Skip page') continue refsList.append(j) # This isn't possible with a generator if refsList != []: - wikipedia.output(u"%s isn't orphan! Skip..." % page.title()) + pywikibot.output(u"%s isn't orphan! Skip..." % page.title()) continue # Never understood how a list can turn in "None", but it happened :-S elif refsList == None: # We have to find out why the function returns that value - wikipedia.output(u'Error: 2 --> Skip page') + pywikibot.output(u'Error: 2 --> Skip page') continue else: # Ok, no refs, no redirect... let's check if there's already the template try: oldtxt = page.get() - except wikipedia.NoPage: - wikipedia.output(u"%s doesn't exist! Skip..." % page.title()) + except pywikibot.NoPage: + pywikibot.output(u"%s doesn't exist! Skip..." % page.title()) continue - except wikipedia.IsRedirectPage: - wikipedia.output(u"%s is a redirect! Skip..." % page.title()) + except pywikibot.IsRedirectPage: + pywikibot.output(u"%s is a redirect! Skip..." % page.title()) continue # I've used a loop in a loop. If I use continue in the second loop, it won't do anything # in the first. So let's create a variable to avoid this problem. @@ -231,7 +232,7 @@ res = re.findall(regexp, oldtxt.lower()) # Found a template! Let's skip the page! if res != []: - wikipedia.output(u'Your regex has found something in %s, skipping...' % page.title()) + pywikibot.output(u'Your regex has found something in %s, skipping...' % page.title()) Find = True break # Skip the page.. @@ -239,34 +240,34 @@ continue # Is the page a disambig? if page.isDisambig() and disambigPage != None: - wikipedia.output(u'%s is a disambig page, report..' % page.title()) + pywikibot.output(u'%s is a disambig page, report..' % page.title()) if not page.title().lower() in disambigtext.lower(): disambigtext = u"%s\n*[[%s]]" % (disambigtext, page.title()) disambigpage.put(disambigtext, commentdisambig) continue # Is the page a disambig but there's not disambigPage? Skip! elif page.isDisambig(): - wikipedia.output(u'%s is a disambig page, skip...' % page.title()) + pywikibot.output(u'%s is a disambig page, skip...' % page.title()) continue else: # Ok, the page need the template. Let's put it there! newtxt = u"%s\n%s" % (template, oldtxt) # Adding the template in the text - wikipedia.output(u"\t\t>>> %s <<<" % page.title()) # Showing the title - wikipedia.showDiff(oldtxt, newtxt) # Showing the changes + pywikibot.output(u"\t\t>>> %s <<<" % page.title()) # Showing the title + pywikibot.showDiff(oldtxt, newtxt) # Showing the changes choice = 'y' # Default answer if not always: - choice = wikipedia.inputChoice(u'Orphan page found, shall I add the template?', ['Yes', 'No', 'All'], ['y', 'n', 'a']) + choice = pywikibot.inputChoice(u'Orphan page found, shall I add the template?', ['Yes', 'No', 'All'], ['y', 'n', 'a']) if choice == 'a': always = True choice = 'y' if choice == 'y': try: page.put(newtxt, comment) - except wikipedia.EditConflict: - wikipedia.output(u'Edit Conflict! Skip...') + except pywikibot.EditConflict: + pywikibot.output(u'Edit Conflict! Skip...') continue if __name__ == '__main__': try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/makecat.py =================================================================== --- trunk/pywikipedia/makecat.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/makecat.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -32,14 +32,17 @@ """ # (C) Andre Engels, 2004 +# (C) Pywikipedia bot team 2005-2010 # # Distributed under the terms of the MIT license. # - __version__='$Id$' +# import sys, codecs, re -import wikipedia, date, catlib +import date +import wikipedia as pywikibot +import catlib msg={ 'ar':u'إنشاء أو تحديث التصنيف:', @@ -60,12 +63,12 @@ def rawtoclean(c): #Given the 'raw' category, provides the 'clean' category c2 = c.title().split('|')[0] - return wikipedia.Page(mysite,c2) + return pywikibot.Page(mysite,c2) def isdate(s): """returns true iff s is a date or year """ - dict,val = date.getAutoFormat( wikipedia.getSite().language(), s ) + dict,val = date.getAutoFormat( pywikibot.getSite().language(), s ) return dict is not None def needcheck(pl): @@ -82,15 +85,16 @@ def include(pl,checklinks=True,realinclude=True,linkterm=None): cl = checklinks if linkterm: - actualworkingcat = catlib.Category(mysite,workingcat.title(),sortKey=linkterm) + actualworkingcat = catlib.Category(mysite,workingcat.title(), + sortKey=linkterm) else: actualworkingcat = workingcat if realinclude: try: text = pl.get() - except wikipedia.NoPage: + except pywikibot.NoPage: pass - except wikipedia.IsRedirectPage: + except pywikibot.IsRedirectPage: cl = True pass else: @@ -103,7 +107,8 @@ catlib.change_category(pl,c,actualworkingcat) break else: - pl.put(wikipedia.replaceCategoryLinks(text, cats + [actualworkingcat])) + pl.put(pywikibot.replaceCategoryLinks( + text, cats + [actualworkingcat])) if cl: if checkforward: for page2 in pl.linkedPages(): @@ -130,8 +135,8 @@ checked[pl2]=pl2 return ctoshow = 500 - wikipedia.output(u'') - wikipedia.output(u"==%s=="%pl.title()) + pywikibot.output(u'') + pywikibot.output(u"==%s=="%pl.title()) while 1: answer = raw_input("y(es)/n(o)/i(gnore)/(o)ther options? ") if answer=='y': @@ -143,7 +148,8 @@ if answer=='z': if pl.exists(): if not pl.isRedirectPage(): - linkterm = wikipedia.input(u"In what manner should it be alphabetized?") + linkterm = pywikibot.input( + u"In what manner should it be alphabetized?") include(pl,linkterm=linkterm) break include(pl) @@ -155,42 +161,46 @@ exclude(pl,real_exclude=False) break elif answer=='o': - wikipedia.output(u"t: Give the beginning of the text of the page") - wikipedia.output(u"z: Add under another title (as [[Category|Title]])") - wikipedia.output(u"x: Add the page, but do not check links to and from it") - wikipedia.output(u"c: Do not add the page, but do check links") - wikipedia.output(u"a: Add another page") - wikipedia.output(u"l: Give a list of the pages to check") + pywikibot.output(u"t: Give the beginning of the text of the page") + pywikibot.output( + u"z: Add under another title (as [[Category|Title]])") + pywikibot.output( + u"x: Add the page, but do not check links to and from it") + pywikibot.output(u"c: Do not add the page, but do check links") + pywikibot.output(u"a: Add another page") + pywikibot.output(u"l: Give a list of the pages to check") elif answer=='a': pagetitle = raw_input("Specify page to add:") - page=wikipedia.Page(wikipedia.getSite(),pagetitle) + page=pywikibot.Page(pywikibot.getSite(),pagetitle) if not page in checked.keys(): include(page) elif answer=='x': if pl.exists(): if pl.isRedirectPage(): - wikipedia.output(u"Redirect page. Will be included normally.") + pywikibot.output( + u"Redirect page. Will be included normally.") include(pl,realinclude=False) else: include(pl,checklinks=False) else: - wikipedia.output(u"Page does not exist; not added.") + pywikibot.output(u"Page does not exist; not added.") exclude(pl,real_exclude=False) break elif answer=='l': - wikipedia.output(u"Number of pages still to check: %s"%len(tocheck)) - wikipedia.output(u"Pages to be checked:") - wikipedia.output(u" - ".join(page.title() for page in tocheck)) - wikipedia.output(u"==%s=="%pl.title()) + pywikibot.output(u"Number of pages still to check: %s" + % len(tocheck)) + pywikibot.output(u"Pages to be checked:") + pywikibot.output(u" - ".join(page.title() for page in tocheck)) + pywikibot.output(u"==%s=="%pl.title()) elif answer=='t': - wikipedia.output(u"==%s=="%pl.title()) + pywikibot.output(u"==%s=="%pl.title()) try: - wikipedia.output(u''+pl.get(get_redirect=True)[0:ctoshow]) - except wikipedia.NoPage: - wikipedia.output(u"Page does not exist.") + pywikibot.output(u''+pl.get(get_redirect=True)[0:ctoshow]) + except pywikibot.NoPage: + pywikibot.output(u"Page does not exist.") ctoshow += 500 else: - wikipedia.output(u"Not understood.") + pywikibot.output(u"Not understood.") try: checked = {} @@ -202,7 +212,7 @@ main = True workingcatname = [] tocheck = [] - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith('-nodate'): skipdates = True elif arg.startswith('-forward'): @@ -221,11 +231,14 @@ workingcatname = raw_input("Which page to start with? ") else: workingcatname = ' '.join(workingcatname) - mysite = wikipedia.getSite() - wikipedia.setAction(wikipedia.translate(mysite,msg) + ' ' + workingcatname) - workingcat = catlib.Category(mysite,mysite.category_namespace()+':'+workingcatname) - filename = wikipedia.config.datafilepath('category', - wikipedia.UnicodeToAsciiHtml(workingcatname) + '_exclude.txt') + mysite = pywikibot.getSite() + pywikibot.setAction(pywikibot.translate(mysite,msg) + ' ' + workingcatname) + workingcat = catlib.Category(mysite, + u'%s:%s' + % (mysite.category_namespace(), + workingcatname)) + filename = pywikibot.config.datafilepath('category', + pywikibot.UnicodeToAsciiHtml(workingcatname) +'_exclude.txt') try: f = codecs.open(filename, 'r', encoding = mysite.encoding()) for line in f.readlines(): @@ -236,7 +249,7 @@ except IndexError: pass exclude(line,real_exclude=False) - pl = wikipedia.Page(mysite,line) + pl = pywikibot.Page(mysite,line) checked[pl] = pl f.close() excludefile = codecs.open(filename, 'a', encoding = mysite.encoding()) @@ -245,12 +258,12 @@ excludefile = codecs.open(filename, 'w', encoding = mysite.encoding()) try: parentcats = workingcat.categories() - except wikipedia.Error: + except pywikibot.Error: parentcats = [] # Do not include articles already in subcats; only checking direct subcats subcatlist = workingcat.subcategoriesList() if subcatlist: - wikipedia.getall(mysite,subcatlist) + pywikibot.getall(mysite,subcatlist) for cat in subcatlist: list = cat.articlesList() for page in list: @@ -260,16 +273,18 @@ if list: for pl in list: checked[pl]=pl - wikipedia.getall(mysite,list) + pywikibot.getall(mysite,list) for pl in list: include(pl) else: - wikipedia.output(u"Category %s does not exist or is empty. Which page to start with?"%workingcatname) - answer = wikipedia.input(u"(Default is [[%s]]):"%workingcatname) + pywikibot.output( + u"Category %s does not exist or is empty. Which page to start with?" + % workingcatname) + answer = pywikibot.input(u"(Default is [[%s]]):" % workingcatname) if not answer: answer = workingcatname - wikipedia.output(u''+answer) - pl = wikipedia.Page(mysite,answer) + pywikibot.output(u''+answer) + pl = pywikibot.Page(mysite,answer) tocheck = [] checked[pl] = pl include(pl) @@ -280,7 +295,7 @@ loaded = len(tocheck) else: loaded = 50 - wikipedia.getall(mysite,tocheck[:loaded]) + pywikibot.getall(mysite,tocheck[:loaded]) if not checkbroken: if not tocheck[0].exists(): pass @@ -290,8 +305,9 @@ asktoadd(tocheck[0]) tocheck = tocheck[1:] loaded -= 1 + finally: - wikipedia.stopme() + pywikibot.stopme() try: excludefile.close() except: Modified: trunk/pywikipedia/misspelling.py =================================================================== --- trunk/pywikipedia/misspelling.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/misspelling.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -13,9 +13,9 @@ e.g. "l" or "m". -start:XY goes through all misspellings in the category on your wiki - that is defined (to the bot) as the category containing misspelling - pages, starting at XY. If the -start argument is not given, it starts - at the beginning. + that is defined (to the bot) as the category containing + misspelling pages, starting at XY. If the -start argument is not + given, it starts at the beginning. -main only check pages in the main namespace, not in the talk, wikipedia, user, etc. namespaces. @@ -26,7 +26,9 @@ # # Distributed under the terms of the MIT license. -import wikipedia, solve_disambiguation, catlib, pagegenerators +import wikipedia as pywikibot +import catlib, pagegenerators +import solve_disambiguation class MisspellingRobot(solve_disambiguation.DisambiguationRobot): @@ -64,19 +66,27 @@ } def __init__(self, always, firstPageTitle, main_only): - solve_disambiguation.DisambiguationRobot.__init__(self, always, [], True, self.createPageGenerator(firstPageTitle), False, main_only) + solve_disambiguation.DisambiguationRobot.__init__( + self, always, [], True, self.createPageGenerator(firstPageTitle), + False, main_only) def createPageGenerator(self, firstPageTitle): - if wikipedia.getSite().lang in self.misspellingCategory: - misspellingCategoryTitle = self.misspellingCategory[wikipedia.getSite().lang] - misspellingCategory = catlib.Category(wikipedia.getSite(), misspellingCategoryTitle) - generator = pagegenerators.CategorizedPageGenerator(misspellingCategory, recurse = True, start = firstPageTitle) + if pywikibot.getSite().lang in self.misspellingCategory: + misspellingCategoryTitle = self.misspellingCategory[pywikibot.getSite().lang] + misspellingCategory = catlib.Category(pywikibot.getSite(), + misspellingCategoryTitle) + generator = pagegenerators.CategorizedPageGenerator( + misspellingCategory, recurse = True, start=firstPageTitle) else: - misspellingTemplateName = 'Template:%s' % self.misspellingTemplate[wikipedia.getSite().lang] - misspellingTemplate = wikipedia.Page(wikipedia.getSite(), misspellingTemplateName) - generator = pagegenerators.ReferringPageGenerator(misspellingTemplate, onlyTemplateInclusion = True) + misspellingTemplateName = 'Template:%s' \ + % self.misspellingTemplate[pywikibot.getSite().lang] + misspellingTemplate = pywikibot.Page(pywikibot.getSite(), + misspellingTemplateName) + generator = pagegenerators.ReferringPageGenerator( + misspellingTemplate, onlyTemplateInclusion=True) if firstPageTitle: - wikipedia.output(u'-start parameter unsupported on this wiki because there is no category for misspellings.') + pywikibot.output( + u'-start parameter unsupported on this wiki because there is no category for misspellings.') preloadingGen = pagegenerators.PreloadingGenerator(generator) return preloadingGen @@ -87,7 +97,7 @@ return True elif self.misspellingTemplate[disambPage.site().lang] is not None: for templateName, params in disambPage.templatesWithParams(): - if templateName in self.misspellingTemplate[wikipedia.getSite().lang]: + if templateName in self.misspellingTemplate[pywikibot.getSite().lang]: # The correct spelling is in the last paramter. correctSpelling = params[-1] # On de.wikipedia, there are some cases where the @@ -106,8 +116,9 @@ def setSummaryMessage(self, disambPage, new_targets, unlink): # TODO: setSummaryMessage() in solve_disambiguation now has parameters # new_targets and unlink. Make use of these here. - comment = wikipedia.translate(self.mysite, self.msg) % disambPage.title() - wikipedia.setAction(comment) + comment = pywikibot.translate(self.mysite, self.msg) \ + % disambPage.title() + pywikibot.setAction(comment) def main(): # the option that's always selected when the bot wonders what to do with @@ -116,12 +127,13 @@ main_only = False firstPageTitle = None - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith('-always:'): always = arg[8:] elif arg.startswith('-start'): if len(arg) == 6: - firstPageTitle = wikipedia.input(u'At which page do you want to start?') + firstPageTitle = pywikibot.input( + u'At which page do you want to start?') else: firstPageTitle = arg[7:] elif arg == '-main': @@ -135,4 +147,4 @@ try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/movepages.py =================================================================== --- trunk/pywikipedia/movepages.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/movepages.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -13,8 +13,8 @@ -noredirect Leave no redirect behind. --prefix Move pages by adding a namespace prefix to the names of the pages. - (Will remove the old namespace prefix if any) +-prefix Move pages by adding a namespace prefix to the names of the + pages. (Will remove the old namespace prefix if any) Argument can also be given as "-prefix:namespace:". -always Don't prompt to make changes, just do them. @@ -22,11 +22,10 @@ -skipredirects Skip redirect pages (Warning: increases server load) -summary Prompt for a custom summary, bypassing the predefined message - texts. - Argument can also be given as "-summary:XYZ". + texts. Argument can also be given as "-summary:XYZ". --pairs Read pairs of file names from a file. The file must be in a format - [[frompage]] [[topage]] [[frompage]] [[topage]] ... +-pairs Read pairs of file names from a file. The file must be in a + format [[frompage]] [[topage]] [[frompage]] [[topage]] ... Argument can also be given as "-pairs:filename" """ @@ -40,8 +39,9 @@ __version__='$Id$' -import wikipedia, pagegenerators import sys, re +import wikipedia as pywikibot +import pagegenerators # This is required for the text that is shown when you run this script # with the parameter -help. @@ -72,7 +72,8 @@ class MovePagesBot: - def __init__(self, generator, addprefix, noredirect, always, skipredirects, summary): + def __init__(self, generator, addprefix, noredirect, always, skipredirects, + summary): self.generator = generator self.addprefix = addprefix self.noredirect = noredirect @@ -84,30 +85,34 @@ try: msg = self.summary if not msg: - msg = wikipedia.translate(wikipedia.getSite(), summary) - wikipedia.output(u'Moving page %s to [[%s]]' % (page.aslink(), newPageTitle)) - page.move(newPageTitle, msg, throttle=True, leaveRedirect=self.noredirect) - except wikipedia.NoPage: - wikipedia.output(u'Page %s does not exist!' % page.title()) - except wikipedia.IsRedirectPage: - wikipedia.output(u'Page %s is a redirect; skipping.' % page.title()) - except wikipedia.LockedPage: - wikipedia.output(u'Page %s is locked!' % page.title()) - except wikipedia.PageNotSaved, e: + msg = pywikibot.translate(pywikibot.getSite(), summary) + pywikibot.output(u'Moving page %s to [[%s]]' + % (page.title(asLink=True), newPageTitle)) + page.move(newPageTitle, msg, throttle=True, + leaveRedirect=self.noredirect) + except pywikibot.NoPage: + pywikibot.output(u'Page %s does not exist!' % page.title()) + except pywikibot.IsRedirectPage: + pywikibot.output(u'Page %s is a redirect; skipping.' % page.title()) + except pywikibot.LockedPage: + pywikibot.output(u'Page %s is locked!' % page.title()) + except pywikibot.PageNotSaved, e: #target newPageTitle already exists - wikipedia.output(e.message) + pywikibot.output(e.message) def treat(self, page): # Show the title of the page we're working on. # Highlight the title in purple. - wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"% page.title()) + pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" + % page.title()) if self.skipredirects and page.isRedirectPage(): - wikipedia.output(u'Page %s is a redirect; skipping.' % page.title()) + pywikibot.output(u'Page %s is a redirect; skipping.' % page.title()) return pagetitle = page.titleWithoutNamespace() namesp = page.site().namespace(page.namespace()) if self.appendAll: - newPageTitle = (u'%s%s%s' % (self.pagestart, pagetitle, self.pageend)) + newPageTitle = (u'%s%s%s' + % (self.pagestart, pagetitle, self.pageend)) if not self.noNamespace and namesp: newPageTitle = (u'%s:%s' % (namesp, newPageTitle)) elif self.regexAll: @@ -118,7 +123,9 @@ newPageTitle = (u'%s%s' % (self.addprefix, pagetitle)) if self.addprefix or self.appendAll or self.regexAll: if not self.always: - choice2 = wikipedia.inputChoice(u'Change the page title to "%s"?' % newPageTitle, ['yes', 'no', 'all', 'quit'], ['y', 'n', 'a', 'q']) + choice2 = pywikibot.inputChoice( + u'Change the page title to "%s"?' % newPageTitle, + ['yes', 'no', 'all', 'quit'], ['y', 'n', 'a', 'q']) if choice2 == 'y': self.moveOne(page, newPageTitle) elif choice2 == 'a': @@ -133,21 +140,32 @@ else: self.moveOne(page, newPageTitle) else: - choice = wikipedia.inputChoice(u'What do you want to do?', ['change page name', 'append to page name', 'use a regular expression', 'next page', 'quit'], ['c', 'a', 'r', 'n', 'q']) + choice = pywikibot.inputChoice(u'What do you want to do?', + ['change page name', + 'append to page name', + 'use a regular expression', + 'next page', 'quit'], + ['c', 'a', 'r', 'n', 'q']) if choice == 'c': - newPageTitle = wikipedia.input(u'New page name:') + newPageTitle = pywikibot.input(u'New page name:') self.moveOne(page, newPageTitle) elif choice == 'a': - self.pagestart = wikipedia.input(u'Append this to the start:') - self.pageend = wikipedia.input(u'Append this to the end:') - newPageTitle = (u'%s%s%s' % (self.pagestart, pagetitle, self.pageend)) + self.pagestart = pywikibot.input(u'Append this to the start:') + self.pageend = pywikibot.input(u'Append this to the end:') + newPageTitle = (u'%s%s%s' + % (self.pagestart, pagetitle, self.pageend)) if namesp: - choice2 = wikipedia.inputChoice(u'Do you want to remove the namespace prefix "%s:"?' % namesp, ['yes', 'no'], ['y', 'n']) + choice2 = pywikibot.inputChoice( + u'Do you want to remove the namespace prefix "%s:"?' + % namesp, ['yes', 'no'], ['y', 'n']) if choice2 == 'y': noNamespace = True else: newPageTitle = (u'%s:%s' % (namesp, newPageTitle)) - choice2 = wikipedia.inputChoice(u'Change the page title to "%s"?' % newPageTitle, ['yes', 'no', 'all', 'quit'], ['y', 'n', 'a', 'q']) + choice2 = pywikibot.inputChoice( + u'Change the page title to "%s"?' + % newPageTitle, ['yes', 'no', 'all', 'quit'], + ['y', 'n', 'a', 'q']) if choice2 == 'y': self.moveOne(page, newPageTitle) elif choice2 == 'a': @@ -160,19 +178,28 @@ else: self.treat(page) elif choice == 'r': - searchPattern = wikipedia.input(u'Enter the search pattern:') - self.replacePattern = wikipedia.input(u'Enter the replace pattern:') + searchPattern = pywikibot.input(u'Enter the search pattern:') + self.replacePattern = pywikibot.input( + u'Enter the replace pattern:') self.regex=re.compile(searchPattern) if page.title() == page.titleWithoutNamespace(): - newPageTitle = self.regex.sub(self.replacePattern, page.title()) + newPageTitle = self.regex.sub(self.replacePattern, + page.title()) else: - choice2 = wikipedia.inputChoice(u'Do you want to remove the namespace prefix "%s:"?' % namesp, ['yes', 'no'], ['y', 'n']) + choice2 = pywikibot.inputChoice( + u'Do you want to remove the namespace prefix "%s:"?' + % namesp, ['yes', 'no'], ['y', 'n']) if choice2 == 'y': - newPageTitle = self.regex.sub(self.replacePattern, page.titleWithoutNamespace()) + newPageTitle = self.regex.sub( + self.replacePattern, page.titleWithoutNamespace()) noNamespace = True else: - newPageTitle = self.regex.sub(self.replacePattern, page.title()) - choice2 = wikipedia.inputChoice(u'Change the page title to "%s"?' % newPageTitle, ['yes', 'no', 'all', 'quit'], ['y', 'n', 'a', 'q']) + newPageTitle = self.regex.sub(self.replacePattern, + page.title()) + choice2 = pywikibot.inputChoice( + u'Change the page title to "%s"?' + % newPageTitle, ['yes', 'no', 'all', 'quit'], + ['y', 'n', 'a', 'q']) if choice2 == 'y': self.moveOne(page, newPageTitle) elif choice2 == 'a': @@ -215,10 +242,11 @@ # to work on. genFactory = pagegenerators.GeneratorFactory() - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith('-pairs'): if len(arg) == len('-pairs'): - filename = wikipedia.input(u'Enter the name of the file containing pairs:') + filename = pywikibot.input( + u'Enter the name of the file containing pairs:') else: filename = arg[len('-pairs:'):] oldName1 = None @@ -229,7 +257,8 @@ else: oldName1 = page.title() if oldName1: - wikipedia.output(u'WARNING: file %s contains odd number of links' % filename) + pywikibot.output( + u'WARNING: file %s contains odd number of links' % filename) elif arg == '-noredirect': noredirect = False elif arg == '-always': @@ -238,45 +267,47 @@ skipredirects = True elif arg.startswith('-from:'): if oldName: - wikipedia.output(u'WARNING: -from:%s without -to:' % oldName) + pywikibot.output(u'WARNING: -from:%s without -to:' % oldName) oldName = arg[len('-from:'):] elif arg.startswith('-to:'): if oldName: fromToPairs.append([oldName, arg[len('-to:'):]]) oldName = None else: - wikipedia.output(u'WARNING: %s without -from' % arg) + pywikibot.output(u'WARNING: %s without -from' % arg) elif arg.startswith('-prefix'): if len(arg) == len('-prefix'): - prefix = wikipedia.input(u'Enter the prefix:') + prefix = pywikibot.input(u'Enter the prefix:') else: prefix = arg[8:] elif arg.startswith('-summary'): if len(arg) == len('-summary'): - summary = wikipedia.input(u'Enter the summary:') + summary = pywikibot.input(u'Enter the summary:') else: summary = arg[9:] else: genFactory.handleArg(arg) if oldName: - wikipedia.output(u'WARNING: -from:%s without -to:' % oldName) + pywikibot.output(u'WARNING: -from:%s without -to:' % oldName) for pair in fromToPairs: - page = wikipedia.Page(wikipedia.getSite(), pair[0]) - bot = MovePagesBot(None, prefix, noredirect, always, skipredirects, summary) + page = pywikibot.Page(pywikibot.getSite(), pair[0]) + bot = MovePagesBot(None, prefix, noredirect, always, skipredirects, + summary) bot.moveOne(page, pair[1]) if not gen: gen = genFactory.getCombinedGenerator() if gen: preloadingGen = pagegenerators.PreloadingGenerator(gen) - bot = MovePagesBot(preloadingGen, prefix, noredirect, always, skipredirects, summary) + bot = MovePagesBot(preloadingGen, prefix, noredirect, always, + skipredirects, summary) bot.run() elif not fromToPairs: - wikipedia.showHelp('movepages') + pywikibot.showHelp('movepages') if __name__ == '__main__': try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/pagefromfile.py =================================================================== --- trunk/pywikipedia/pagefromfile.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/pagefromfile.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -46,11 +46,12 @@ # # Distributed under the terms of the MIT license. # - __version__='$Id$' +# import re, codecs -import wikipedia, config +import wikipedia as pywikibot +import config class NoTitle(Exception): """No title found""" @@ -138,7 +139,8 @@ 'zh': u'機器人: 覆寫已存在的文字', } - def __init__(self, reader, force, append, summary, minor, autosummary, debug): + def __init__(self, reader, force, append, summary, minor, autosummary, + debug): self.reader = reader self.force = force self.append = append @@ -152,47 +154,54 @@ self.put(title, contents) def put(self, title, contents): - mysite = wikipedia.getSite() + mysite = pywikibot.getSite() - page = wikipedia.Page(mysite, title) + page = pywikibot.Page(mysite, title) # Show the title of the page we're working on. # Highlight the title in purple. - wikipedia.output(u">>> \03{lightpurple}%s\03{default} <<<" % page.title()) + pywikibot.output(u">>> \03{lightpurple}%s\03{default} <<<" + % page.title()) if self.summary: comment = self.summary else: - comment = wikipedia.translate(mysite, self.msg) + comment = pywikibot.translate(mysite, self.msg) - comment_top = comment + " - " + wikipedia.translate(mysite, self.msg_top) - comment_bottom = comment + " - " + wikipedia.translate(mysite, self.msg_bottom) - comment_force = comment + " *** " + wikipedia.translate(mysite, self.msg_force) + " ***" + comment_top = comment + " - " + pywikibot.translate(mysite, + self.msg_top) + comment_bottom = comment + " - " + pywikibot.translate(mysite, + self.msg_bottom) + comment_force = comment + " *** " + pywikibot.translate(mysite, + self.msg_force) + " ***" # Remove trailing newlines (cause troubles when creating redirects) contents = re.sub('^[\r\n]*','', contents) if page.exists(): if self.append == "Top": - wikipedia.output(u"Page %s already exists, appending on top!" % title) + pywikibot.output(u"Page %s already exists, appending on top!" + % title) contents = contents + page.get() comment = comment_top elif self.append == "Bottom": - wikipedia.output(u"Page %s already exists, appending on bottom!" % title) + pywikibot.output(u"Page %s already exists, appending on bottom!" + % title) contents = page.get() + contents comment = comment_bottom elif self.force: - wikipedia.output(u"Page %s already exists, ***overwriting!" % title) + pywikibot.output(u"Page %s already exists, ***overwriting!" + % title) comment = comment_force else: - wikipedia.output(u"Page %s already exists, not adding!" % title) + pywikibot.output(u"Page %s already exists, not adding!" % title) return else: if self.autosummary: comment = '' - wikipedia.setAction('') + pywikibot.setAction('') if self.dry: - wikipedia.output("*** Dry mode ***\n" + \ + pywikibot.output("*** Dry mode ***\n" + \ "\03{lightpurple}title\03{default}: " + title + "\n" + \ "\03{lightpurple}contents\03{default}:\n" + contents + "\n" \ "\03{lightpurple}comment\03{default}: " + comment + "\n") @@ -200,12 +209,14 @@ try: page.put(contents, comment = comment, minorEdit = self.minor) - except wikipedia.LockedPage: - wikipedia.output(u"Page %s is locked; skipping." % title) - except wikipedia.EditConflict: - wikipedia.output(u'Skipping %s because of edit conflict' % title) - except wikipedia.SpamfilterError, error: - wikipedia.output(u'Cannot change %s because of spam blacklist entry %s' % (title, error.url)) + except pywikibot.LockedPage: + pywikibot.output(u"Page %s is locked; skipping." % title) + except pywikibot.EditConflict: + pywikibot.output(u'Skipping %s because of edit conflict' % title) + except pywikibot.SpamfilterError, error: + pywikibot.output( + u'Cannot change %s because of spam blacklist entry %s' + % (title, error.url)) class PageFromFileReader: """ @@ -213,7 +224,8 @@ The run() method yields a (title, contents) tuple for each found page. """ - def __init__(self, filename, pageStartMarker, pageEndMarker, titleStartMarker, titleEndMarker, include, notitle): + def __init__(self, filename, pageStartMarker, pageEndMarker, + titleStartMarker, titleEndMarker, include, notitle): self.filename = filename self.pageStartMarker = pageStartMarker self.pageEndMarker = pageEndMarker @@ -223,9 +235,10 @@ self.notitle = notitle def run(self): - wikipedia.output('Reading \'%s\'...' % self.filename) + pywikibot.output('Reading \'%s\'...' % self.filename) try: - f = codecs.open(self.filename, 'r', encoding = config.textfile_encoding) + f = codecs.open(self.filename, 'r', + encoding=config.textfile_encoding) except IOError, err: print err return @@ -238,12 +251,12 @@ length, title, contents = self.findpage(text[position:]) except AttributeError: if not length: - wikipedia.output(u'\nStart or end marker not found.') + pywikibot.output(u'\nStart or end marker not found.') else: - wikipedia.output(u'End of file.') + pywikibot.output(u'End of file.') break except NoTitle, err: - wikipedia.output(u'\nNo title found - skipping a page.') + pywikibot.output(u'\nNo title found - skipping a page.') position += err.offset continue @@ -270,9 +283,9 @@ return location.end(), title, contents def main(): - # Adapt these to the file you are using. 'pageStartMarker' and 'pageEndMarker' are - # the beginning and end of each entry. Take text that should be included - # and does not occur elsewhere in the text. + # Adapt these to the file you are using. 'pageStartMarker' and + # 'pageEndMarker' are the beginning and end of each entry. Take text that + # should be included and does not occur elsewhere in the text. # TODO: make config variables for these. filename = "dict.txt" @@ -290,7 +303,7 @@ autosummary = False dry = False - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith("-start:"): pageStartMarker = arg[7:] elif arg.startswith("-end:"): @@ -323,10 +336,10 @@ elif arg == '-autosummary': autosummary = True else: - wikipedia.output(u"Disregarding unknown argument %s." % arg) + pywikibot.output(u"Disregarding unknown argument %s." % arg) - reader = PageFromFileReader(filename, pageStartMarker, pageEndMarker, titleStartMarker, titleEndMarker, include, notitle) - + reader = PageFromFileReader(filename, pageStartMarker, pageEndMarker, + titleStartMarker, titleEndMarker, include, notitle) bot = PageFromFileRobot(reader, force, append, summary, minor, autosummary, dry) bot.run() @@ -334,4 +347,4 @@ try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/pageimport.py =================================================================== --- trunk/pywikipedia/pageimport.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/pageimport.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -21,39 +21,41 @@ """ # # (C) Filnik, 2007 +# (C) Pywikipedia bot team, 2008-2010 # # Greetings: # Lorenzo Paulatto and Misza13 # # Distributed under the terms of the MIT license. # - __version__ = '$Id$' +# import urllib -import wikipedia, login, config +import wikipedia as pywikibot, +import login, config -class Importer(wikipedia.Page): +class Importer(pywikibot.Page): def __init__(self, site): self.importsite = site - wikipedia.Page.__init__(self, site, 'Special:Import', None, 0) + pywikibot.Page.__init__(self, site, 'Special:Import', None, 0) def Import(self, target, project = 'w', crono = '1', namespace = '', prompt = True): """Import the page from the wiki. Requires administrator status. If prompt is True, asks the user if he wants to delete the page. """ if project == 'w': - site = wikipedia.getSite(fam = 'wikipedia') + site = pywikibot.getSite(fam = 'wikipedia') elif project == 'b': - site = wikipedia.getSite(fam = 'wikibooks') + site = pywikibot.getSite(fam = 'wikibooks') elif project == 'wikt': - site = wikipedia.getSite(fam = 'wiktionary') + site = pywikibot.getSite(fam = 'wiktionary') elif project == 's': - site = wikipedia.getSite(fam = 'wikisource') + site = pywikibot.getSite(fam = 'wikisource') elif project == 'q': - site = wikipedia.getSite(fam = 'wikiquote') + site = pywikibot.getSite(fam = 'wikiquote') else: - site = wikipedia.getSite() + site = pywikibot.getSite() # Fixing the crono value... if crono == True: crono = '1' @@ -64,7 +66,7 @@ namespace == '' answer = 'y' if prompt: - answer = wikipedia.inputChoice(u'Do you want to import %s?' % target, ['Yes', 'No'], ['y', 'N'], 'N') + answer = pywikibot.inputChoice(u'Do you want to import %s?' % target, ['Yes', 'No'], ['y', 'N'], 'N') if answer == 'y': host = self.site().hostname() address = self.site().path() + '?title=%s&action=submit' % self.urlname() @@ -87,14 +89,14 @@ } response, data = self.site().postForm(address, predata, sysop = True) if data: - wikipedia.output(u'Page imported, checking...') - if wikipedia.Page(self.importsite, target).exists(): - wikipedia.output(u'Import success!') + pywikibot.output(u'Page imported, checking...') + if pywikibot.Page(self.importsite, target).exists(): + pywikibot.output(u'Import success!') return True else: - wikipedia.output(u'Import failed!') + pywikibot.output(u'Import failed!') return False if __name__=='__main__': - wikipedia.output(u'This is just a module! Read the documentation and write your own script!') - wikipedia.stopme() + pywikibot.output(u'This is just a module! Read the documentation and write your own script!') + pywikibot.stopme() Modified: trunk/pywikipedia/piper.py =================================================================== --- trunk/pywikipedia/piper.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/piper.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -40,13 +40,13 @@ # Distributed under the terms of the MIT license. # __version__ = '$Id$' +# -import wikipedia -import pagegenerators - import os import pipes import tempfile +import wikipedia as pywikibot +import pagegenerators # This is required for the text that is shown when you run this script # with the parameter -help. @@ -82,7 +82,8 @@ def run(self): # Set the edit summary message pipes = ', '.join(self.filters) - wikipedia.setAction(wikipedia.translate(wikipedia.getSite(), self.msg) % pipes) + pywikibot.setAction(pywikibot.translate(pywikibot.getSite(), self.msg) + % pipes) for page in self.generator: self.treat(page) @@ -118,11 +119,13 @@ try: # Load the page text = page.get() - except wikipedia.NoPage: - wikipedia.output(u"Page %s does not exist; skipping." % page.aslink()) + except pywikibot.NoPage: + pywikibot.output(u"Page %s does not exist; skipping." + % page.title(asLink=True)) return - except wikipedia.IsRedirectPage: - wikipedia.output(u"Page %s is a redirect; skipping." % page.aslink()) + except pywikibot.IsRedirectPage: + pywikibot.output(u"Page %s is a redirect; skipping." + % page.title(asLink=True)) return # Munge! @@ -133,24 +136,31 @@ if text != page.get(): # Show the title of the page we're working on. # Highlight the title in purple. - wikipedia.output(u"\n\n>>> %s <<<" % page.title()) + pywikibot.output(u"\n\n>>> %s <<<" % page.title()) # show what was changed - wikipedia.showDiff(page.get(), text) + pywikibot.showDiff(page.get(), text) if not self.dry: if not self.always: - choice = wikipedia.inputChoice(u'Do you want to accept these changes?', ['Yes', 'No'], ['y', 'N'], 'N') + choice = pywikibot.inputChoice( + u'Do you want to accept these changes?', + ['Yes', 'No'], ['y', 'N'], 'N') else: choice = 'y' if choice == 'y': try: # Save the page page.put(text) - except wikipedia.LockedPage: - wikipedia.output(u"Page %s is locked; skipping." % page.aslink()) - except wikipedia.EditConflict: - wikipedia.output(u'Skipping %s because of edit conflict' % (page.title())) - except wikipedia.SpamfilterError, error: - wikipedia.output(u'Cannot change %s because of spam blacklist entry %s' % (page.title(), error.url)) + except pywikibot.LockedPage: + pywikibot.output(u"Page %s is locked; skipping." + % page.title(asLink=True)) + except pywikibot.EditConflict: + pywikibot.output( + u'Skipping %s because of edit conflict' + % (page.title())) + except pywikibot.SpamfilterError, error: + pywikibot.output( + u'Cannot change %s because of spam blacklist entry %s' + % (page.title(), error.url)) def main(): @@ -172,7 +182,7 @@ filters = [] # Parse command line arguments - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg.startswith("-dry"): dry = True elif arg.startswith("-filter:"): @@ -189,7 +199,7 @@ if pageTitleParts != []: # We will only work on a single page. pageTitle = ' '.join(pageTitleParts) - page = wikipedia.Page(wikipedia.getSite(), pageTitle) + page = pywikibot.Page(pywikibot.getSite(), pageTitle) gen = iter([page]) if not gen: @@ -201,10 +211,10 @@ bot = PiperBot(gen, dry, filters, always) bot.run() else: - wikipedia.showHelp() + pywikibot.showHelp() if __name__ == "__main__": try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/protect.py =================================================================== --- trunk/pywikipedia/protect.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/protect.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -36,15 +36,19 @@ python protect.py -file:unprotect.txt -unprotect """ +# # Written by http://it.wikisource.org/wiki/Utente:Qualc1 # Created by modifying delete.py -__version__ = '$Id$' - # +# (C) Pywikipedia bot team, 2008-2010 +# # Distributed under the terms of the MIT license. # +__version__ = '$Id$' +# -import wikipedia, catlib +import wikipedia as pywikibot +import catlib import pagegenerators # Summary messages for protecting from a category. @@ -121,7 +125,7 @@ """ #Loop through everything in the page generator and (un)protect it. for page in self.generator: - wikipedia.output(u'Processing page %s' % page.title()) + pywikibot.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, editcreate=self.edit, move=self.move) @@ -131,7 +135,7 @@ def choiceProtectionLevel(operation, default): default = default[0] firstChar = map(lambda level: level[0], protectionLevels) - choiceChar = wikipedia.inputChoice('Choice a protection level to %s:' % operation, + choiceChar = pywikibot.inputChoice('Choice a protection level to %s:' % operation, protectionLevels, firstChar, default = default) for level in protectionLevels: if level.startswith(choiceChar): @@ -157,23 +161,23 @@ defaultProtection = 'sysop' # read command line parameters - for arg in wikipedia.handleArgs(): + for arg in pywikibot.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:') + fileName = pywikibot.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:') + summary = pywikibot.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:') + pageName = pywikibot.input(u'Enter the category to protect from:') else: pageName = arg[len('-cat:'):] elif arg.startswith('-nosubcats'): @@ -181,25 +185,25 @@ elif arg.startswith('-links'): doLinks = True if len(arg) == len('-links'): - pageName = wikipedia.input(u'Enter the page to protect from:') + pageName = pywikibot.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:') + pageName = pywikibot.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:') + pageName = pywikibot.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:') + pageName = pywikibot.input(u'Enter the page with the images to protect:') else: pageName = arg[len('-images:'):] elif arg.startswith('-unprotect'): @@ -217,40 +221,40 @@ if create not in protectionLevels: create = choiceProtectionLevel('create', defaultProtection) - mysite = wikipedia.getSite() + mysite = pywikibot.getSite() if doSinglePage: if not summary: - summary = wikipedia.input(u'Enter a reason for the protection:') - page = wikipedia.Page(mysite, pageName) + summary = pywikibot.input(u'Enter a reason for the protection:') + page = pywikibot.Page(mysite, pageName) gen = iter([page]) elif doCategory: if not summary: - summary = wikipedia.translate(mysite, msg_protect_category) % pageName + summary = pywikibot.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) + summary = pywikibot.translate(mysite, msg_protect_links) % pageName + linksPage = pywikibot.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) + summary = pywikibot.translate(mysite, msg_protect_ref) % pageName + refPage = pywikibot.Page(mysite, pageName) gen = pagegenerators.ReferringPageGenerator(refPage) elif fileName: if not summary: - summary = wikipedia.translate(mysite, msg_simple_protect) + summary = pywikibot.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)) + summary = pywikibot.translate(mysite, msg_protect_images) % pageName + gen = pagegenerators.ImagesPageGenerator(pywikibot.Page(mysite, pageName)) if gen: - wikipedia.setAction(summary) + pywikibot.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 @@ -258,10 +262,10 @@ bot = ProtectionRobot(gen, summary, always, edit=edit, move=move) bot.run() else: - wikipedia.showHelp(u'protect') + pywikibot.showHelp(u'protect') if __name__ == "__main__": try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/rciw.py =================================================================== --- trunk/pywikipedia/rciw.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/rciw.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -16,18 +16,24 @@ Warning: experimental software, use at your own risk """ -__version__ = '$Id$' # Authors: Kisbes # http://hu.wikipedia.org/wiki/User:Kisbes # License : GFDL +# +# (C) Pywikipedia bot team, 2008, 2010 +# +# Distributed under the terms of the MIT license. +# +__version__ = '$Id$' +# -import interwiki import threading import re -import wikipedia import time from Queue import Queue +import wikipedia as pywikibot +import interwiki class IWRCBot(): def __init__(self, site, safe = True): @@ -58,13 +64,13 @@ if name in self.processed: return self.processed.append(name) - page = wikipedia.Page(self.site, name) + page = pywikibot.Page(self.site, name) # the Queue has for now an unlimited size, # it is a simple atomic append(), no need to acquire a semaphore self.queue.put_nowait(page) def main(): - wikipedia.output('Warning: this script can not be run manually/directly, but automatically by maintainer.py') + pywikibot.output('Warning: this script can not be run manually/directly, but automatically by maintainer.py') if __name__ == "__main__": main() Modified: trunk/pywikipedia/rcsort.py =================================================================== --- trunk/pywikipedia/rcsort.py 2010-10-09 05:02:29 UTC (rev 8628) +++ trunk/pywikipedia/rcsort.py 2010-10-09 16:11:46 UTC (rev 8629) @@ -1,17 +1,26 @@ #!/usr/bin/python # -*- coding: utf-8 -*- -# A tool to see the recentchanges ordered by user instead of by date. This -# is meant to be run as a CGI script. -# Apart from the normal options of the recent changes page, you can add an option -# ?newbies=true which will make the bot go over recently registered users only. -# Currently only works on Dutch Wikipedia, I do intend to make it more generally -# usable. -# Permission has been asked to run this on the toolserver. +""" +A tool to see the recentchanges ordered by user instead of by date. This +is meant to be run as a CGI script. +Apart from the normal options of the recent changes page, you can add an option +?newbies=true which will make the bot go over recently registered users only. +Currently only works on Dutch Wikipedia, I do intend to make it more generally +usable. +Permission has been asked to run this on the toolserver. +""" +# (C) Pywikipedia bot team, 2007-2010 +# +# Distributed under the terms of the MIT license. +# __version__ = '$Id$' +# import cgi import cgitb import re +import wikipedia + cgitb.enable() form = cgi.FieldStorage() @@ -21,13 +30,12 @@ print "<html>" print "<head>" print '<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />' -print '<style type="text/css" media="screen,projection">/*<![CDATA[*/ @import "http://nl.wikipedia.org/skins-1.5/monobook/main.css?59"; /*]]>*/</style>' +print '<style type="text/css" media="screen,projection">/*<![CDATA[*/ @import "http://nl.pywikibot.org/skins-1.5/monobook/main.css?59"; /*]]>*/</style>' print "</head>" print "<body>" print "" -mysite = wikipedia.getSite() +mysite = pywikibot.getSite() newbies = 'newbies' in form @@ -63,10 +71,13 @@ count += 1 lines.append((user,count,line)) elif 'rcoptions' in line: - print line.replace(mysite.path() + "?title=Speciaal:RecenteWijzigingen&","rcsort.py?") + print line.replace(mysite.path() + "?title=Speciaal:RecenteWijzigingen&", + "rcsort.py?") rcoptions = True elif newbies and 'Nieuwste' in line: - line = line.replace(mysite.path() + "?title=Speciaal:Bijdragen&","rcsort.py?").replace("target=newbies","newbies=true") + line = line.replace(mysite.path() + "?title=Speciaal:Bijdragen&", + "rcsort.py?").replace("target=newbies", + "newbies=true") if '</fieldset>' in line: line = line[line.find('</fieldset>')+11:] print line @@ -80,10 +91,10 @@ if line[0] == None: print "<h2>Gebruiker onbekend</h2>" else: - wikipedia.output(u"<h2>%s</h2>"%line[0],toStdout=True) + pywikibot.output(u"<h2>%s</h2>"%line[0],toStdout=True) print "<ul>" last = line[0] - wikipedia.output(line[2].replace('href="/w','href="http://nl.wikipedia.org/w'), toStdout = True) + pywikibot.output(line[2].replace('href="/w','href="http://nl.wikipedia.org/w'), toStdout = True) print print "</ul>"

13 years, 6 months

SVN: [8628] trunk/pywikipedia/nowcommons.py

by xqt＠svn.wikimedia.org

Revision: 8628 Author: xqt Date: 2010-10-09 05:02:29 +0000 (Sat, 09 Oct 2010) Log Message: ----------- do not longer find timestamps as filenames (bug #3080059), import urllib forgotten in r8611 Modified Paths: -------------- trunk/pywikipedia/nowcommons.py Modified: trunk/pywikipedia/nowcommons.py =================================================================== --- trunk/pywikipedia/nowcommons.py 2010-10-09 02:57:06 UTC (rev 8627) +++ trunk/pywikipedia/nowcommons.py 2010-10-09 05:02:29 UTC (rev 8628) @@ -54,7 +54,7 @@ __version__ = '$Id$' # -import sys, re, webbrowser +import sys, re, webbrowser, urllib import wikipedia as pywikibot import pagegenerators import image @@ -264,11 +264,25 @@ if params == []: filenameOnCommons = localImagePage.titleWithoutNamespace() elif self.site.lang in namespaceInTemplate: + skip = False + filenameOnCommons = None for par in params: - if ':' in par: + val = par.split('=') + if len(val) == 1 and not skip: filenameOnCommons = par[par.index(':') + 1:] + break + if val[0].strip() == '1': + filenameOnCommons = val[1].strip()[val[1].strip().index(':') + 1:] + break + skip = True + if not filenameOnCommons: + filenameOnCommons = localImagePage.titleWithoutNamespace() else: - filenameOnCommons = params[0] + val = params[0].split('=') + if len(val) == 1: + filenameOnCommons = params[0].strip() + else: + filenameOnCommons = val[1].strip() return filenameOnCommons # Function stolen from wikipedia.py and modified. Really needed?

13 years, 6 months

SVN: [8627] trunk/pywikipedia/interwiki.py

by xqt＠svn.wikimedia.org

Revision: 8627 Author: xqt Date: 2010-10-09 02:57:06 +0000 (Sat, 09 Oct 2010) Log Message: ----------- typo Modified Paths: -------------- trunk/pywikipedia/interwiki.py Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2010-10-09 02:34:35 UTC (rev 8626) +++ trunk/pywikipedia/interwiki.py 2010-10-09 02:57:06 UTC (rev 8627) @@ -2401,7 +2401,7 @@ if not genFactory.handleArg(arg): singlePageTitle.append(arg) - # Do not us additional summary with autonomous mode + # Do not use additional summary with autonomous mode if globalvar.autonomous: globalvar.summary = u'' elif globalvar.summary:

13 years, 6 months

SVN: [8626] branches/rewrite/scripts/interwiki.py

by xqt＠svn.wikimedia.org

Revision: 8626 Author: xqt Date: 2010-10-09 02:34:35 +0000 (Sat, 09 Oct 2010) Log Message: ----------- update from trunk r8625 Modified Paths: -------------- branches/rewrite/scripts/interwiki.py Modified: branches/rewrite/scripts/interwiki.py =================================================================== --- branches/rewrite/scripts/interwiki.py 2010-10-09 01:46:16 UTC (rev 8625) +++ branches/rewrite/scripts/interwiki.py 2010-10-09 02:34:35 UTC (rev 8626) @@ -68,6 +68,10 @@ NOTE: For post-processing it always assumes that saving the the pages was sucessful. + -summary: Set an additional action summary message for the edit. This + could be used for further explainings of the bot action. + This will only be used in non-autonomous mode. + Additionaly, these arguments can be used to restrict the bot to certain pages: -namespace:n Number or name of namespace to process. The parameter can be @@ -634,6 +638,7 @@ quiet = False restoreAll = False async = False + summary = u'' def readOptions(self, arg): """ Read all commandline parameters for the global container """ @@ -732,6 +737,11 @@ self.quiet = True elif arg == '-async': self.async = True + elif arg.startswith('-summary'): + if len(arg) == 8: + self.summary = pywikibot.input(u'What summary do you want to use?') + else: + self.summary = arg[9:] elif arg.startswith('-lack:'): remainder = arg[6:].split(':') self.lacklanguage = remainder[0] @@ -1612,6 +1622,21 @@ bot, just before submitting a page change to the live wiki it is checked whether we will have to wait. If that is the case, the bot will be told to make another get request first.""" + + #from clean_sandbox + def minutesDiff(time1, time2): + if type(time1) is long: + time1 = str(time1) + if type(time2) is long: + time2 = str(time2) + t1 = (((int(time1[0:4]) * 12 + int(time1[4:6])) * 30 + + int(time1[6:8])) * 24 + int(time1[8:10])) * 60 + \ + int(time1[10:12]) + t2 = (((int(time2[0:4]) * 12 + int(time2[4:6])) * 30 + + int(time2[6:8])) * 24 + int(time2[8:10])) * 60 + \ + int(time2[10:12]) + return abs(t2-t1) + if not self.isDone(): raise "Bugcheck: finish called before done" if not self.workonme: @@ -1699,9 +1724,50 @@ break else: for (site, page) in new.iteritems(): + # edit restriction on is-wiki + # http://is.wikipedia.org/wiki/Wikipediaspjall:V%C3%A9lmenni + # allow edits for the same conditions as -whenneeded + # or the last edit wasn't a bot + # or the last edit as 1 month ago + smallWikiAllowed = True + if globalvar.autonomous and page.site.sitename() == 'wikipedia:is': + old={} + try: + for mypage in new[page.site].interwiki(): + old[mypage.site] = mypage + except pywikibot.NoPage: + pywikibot.output(u"BUG>>> %s no longer exists?" + % new[site].aslink(True)) + continue + mods, mcomment, adding, removing, modifying \ + = compareLanguages(old, new, insite=site) + #cannot create userlib.User with IP + smallWikiAllowed = page.isIpEdit() or \ + len(removing) > 0 or len(old) == 0 or \ + len(adding) + len(modifying) > 2 or \ + len(removing) + len(modifying) == 0 and \ + adding == [page.site] + if not smallWikiAllowed: + import userlib + user = userlib.User(page.site, page.userName()) + if not 'bot' in user.groups() \ + and not 'bot' in page.userName().lower(): #erstmal auch keine namen mit bot + smallWikiAllowed = True + else: + diff = minutesDiff(page.editTime(), + time.strftime("%Y%m%d%H%M%S", + time.gmtime())) + if diff > 30*24*60: + smallWikiAllowed = True + else: + pywikibot.output( +u'NOTE: number of edits are restricted at %s' + % page.site.sitename()) + # if we have an account for this site if site.family.name in config.usernames \ - and site.lang in config.usernames[site.family.name]: + and site.lang in config.usernames[site.family.name] \ + and smallWikiAllowed: # Try to do the changes try: if self.replaceLinks(page, new, bot): @@ -2238,7 +2304,8 @@ mcomment = mods = u'' - if len(adding) + len(removing) + len(modifying) <= 3: + if not globalvar.summary and \ + len(adding) + len(removing) + len(modifying) <= 3: # Use an extended format for the string linking to all added pages. fmt = lambda d, site: unicode(d[site]) else: @@ -2260,7 +2327,7 @@ if modifying: mods += (sep + mod + colon + comma.join([fmt(new, x) for x in modifying])) if mods: - mcomment = head + mods + mcomment = head + globalvar.summary + mods return mods, mcomment, adding, removing, modifying def botMayEdit (page): @@ -2371,6 +2438,12 @@ if not genFactory.handleArg(arg): singlePageTitle.append(arg) + # Do not use additional summary with autonomous mode + if globalvar.autonomous: + globalvar.summary = u'' + elif globalvar.summary: + globalvar.summary += u'; ' + # ensure that we don't try to change main page try: site = pywikibot.getSite()

13 years, 6 months

SVN: [8625] trunk/pywikipedia/interwiki.py

by xqt＠svn.wikimedia.org

Revision: 8625 Author: xqt Date: 2010-10-09 01:46:16 +0000 (Sat, 09 Oct 2010) Log Message: ----------- additional summary option for non-autonomous mode to explain manual assistent bot actions. Sets the default summary behind it. Modified Paths: -------------- trunk/pywikipedia/interwiki.py Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2010-10-08 15:39:29 UTC (rev 8624) +++ trunk/pywikipedia/interwiki.py 2010-10-09 01:46:16 UTC (rev 8625) @@ -68,6 +68,10 @@ NOTE: For post-processing it always assumes that saving the the pages was sucessful. + -summary: Set an additional action summary message for the edit. This + could be used for further explainings of the bot action. + This will only be used in non-autonomous mode. + Additionaly, these arguments can be used to restrict the bot to certain pages: -namespace:n Number or name of namespace to process. The parameter can be @@ -607,6 +611,7 @@ quiet = False restoreAll = False async = False + summary = u'' def readOptions(self, arg): """ Read all commandline parameters for the global container """ @@ -705,6 +710,11 @@ self.quiet = True elif arg == '-async': self.async = True + elif arg.startswith('-summary'): + if len(arg) == 8: + self.summary = pywikibot.input(u'What summary do you want to use?') + else: + self.summary = arg[9:] elif arg.startswith('-lack:'): remainder = arg[6:].split(':') self.lacklanguage = remainder[0] @@ -2263,7 +2273,8 @@ mcomment = mods = u'' - if len(adding) + len(removing) + len(modifying) <= 3: + if not globalvar.summary and \ + len(adding) + len(removing) + len(modifying) <= 3: # Use an extended format for the string linking to all added pages. fmt = lambda d, site: d[site].aslink(forceInterwiki=True) else: @@ -2285,7 +2296,7 @@ if modifying: mods += (sep + mod + colon + comma.join([fmt(new, x) for x in modifying])) if mods: - mcomment = head + mods + mcomment = head + globalvar.summary + mods return mods, mcomment, adding, removing, modifying def botMayEdit (page): @@ -2390,6 +2401,12 @@ if not genFactory.handleArg(arg): singlePageTitle.append(arg) + # Do not us additional summary with autonomous mode + if globalvar.autonomous: + globalvar.summary = u'' + elif globalvar.summary: + globalvar.summary += u'; ' + # ensure that we don't try to change main page try: site = pywikibot.getSite()

13 years, 6 months

SVN: [8624] branches/rewrite/pywikibot

by xqt＠svn.wikimedia.org

Revision: 8624 Author: xqt Date: 2010-10-08 15:39:29 +0000 (Fri, 08 Oct 2010) Log Message: ----------- update from trunk r8623 Modified Paths: -------------- branches/rewrite/pywikibot/families/wikipedia_family.py branches/rewrite/pywikibot/families/wiktionary_family.py branches/rewrite/pywikibot/family.py Modified: branches/rewrite/pywikibot/families/wikipedia_family.py =================================================================== --- branches/rewrite/pywikibot/families/wikipedia_family.py 2010-10-08 15:28:12 UTC (rev 8623) +++ branches/rewrite/pywikibot/families/wikipedia_family.py 2010-10-08 15:39:29 UTC (rev 8624) @@ -327,39 +327,6 @@ # but some languages don't use this. self.nocapitalize = ['jbo',] - # A revised sorting order worked out on - # http://meta.wikimedia.org/wiki/Interwiki_sorting_order - self.alphabetic_revised = [ - 'ace', 'af', 'ak', 'als', 'am', 'ang', 'ab', 'ar', 'an', 'arc', - 'roa-rup', 'frp', 'as', 'ast', 'gn', 'av', 'ay', 'az', 'id', 'ms', - 'bm', 'bn', 'zh-min-nan', 'nan', 'map-bms', 'jv', 'su', 'ba', 'be', - 'be-x-old', 'bh', 'bcl', 'bi', 'bar', 'bo', 'bs', 'br', 'bug', 'bg', - 'bxr', 'ca', 'ceb', 'cv', 'cs', 'ch', 'cbk-zam', 'ny', 'sn', 'tum', - 'cho', 'co', 'cy', 'da', 'dk', 'pdc', 'de', 'dv', 'nv', 'dsb', 'na', - 'dz', 'mh', 'et', 'el', 'eml', 'en', 'myv', 'es', 'eo', 'ext', 'eu', - 'ee', 'fa', 'hif', 'fo', 'fr', 'fy', 'ff', 'fur', 'ga', 'gv', 'sm', - 'gd', 'gl', 'gan', 'ki', 'glk', 'gu', 'got', 'hak', 'xal', 'ko', - 'ha', 'haw', 'hy', 'hi', 'ho', 'hsb', 'hr', 'io', 'ig', 'ilo', - 'bpy', 'ia', 'ie', 'iu', 'ik', 'os', 'xh', 'zu', 'is', 'it', 'he', - 'kl', 'kn', 'kr', 'pam', 'ka', 'ks', 'csb', 'kk', 'kw', 'rw', 'ky', - 'rn', 'sw', 'kv', 'kg', 'ht', 'ku', 'kj', 'lad', 'lbe', 'lo', 'la', - 'lv', 'to', 'lb', 'lt', 'lij', 'li', 'ln', 'jbo', 'lg', 'lmo', 'hu', - 'mk', 'mg', 'ml', 'krc', 'mt', 'mi', 'mr', 'arz', 'mzn', 'cdo', - 'mwl', 'mdf', 'mo', 'mn', 'mus', 'my', 'nah', 'fj', 'nl', 'nds-nl', - 'cr', 'ne', 'new', 'ja', 'nap', 'ce', 'frr', 'pih', 'no', 'nb', - 'nn', 'nrm', 'nov', 'ii', 'oc', 'mhr', 'or', 'om', 'ng', 'hz', 'uz', - 'pa', 'pi', 'pag', 'pnb', 'pap', 'ps', 'km', 'pcd', 'pms', 'nds', - 'pl', 'pnt', 'pt', 'aa', 'kaa', 'crh', 'ty', 'ksh', 'ro', 'rmy', - 'rm', 'qu', 'ru', 'sah', 'se', 'sa', 'sg', 'sc', 'sco', 'stq', 'st', - 'tn', 'sq', 'scn', 'si', 'simple', 'sd', 'ss', 'sk', 'sl', 'cu', - 'szl', 'so', 'ckb', 'srn', 'sr', 'sh', 'fi', 'sv', 'tl', 'ta', - 'kab', 'roa-tara', 'tt', 'te', 'tet', 'th', 'vi', 'ti', 'tg', 'tpi', - 'tokipona', 'tp', 'chr', 'chy', 've', 'tr', 'tk', 'tw', 'udm', 'uk', - 'ur', 'ug', 'za', 'vec', 'vo', 'fiu-vro', 'wa', 'zh-classical', - 'vls', 'war', 'wo', 'wuu', 'ts', 'yi', 'yo', 'zh-yue', 'diq', 'zea', - 'bat-smg', 'zh', 'zh-tw', 'zh-cn', - ] - self.alphabetic_latin = [ 'ace', 'af', 'ak', 'als', 'am', 'ang', 'ab', 'ar', 'an', 'arc', 'roa-rup', 'frp', 'arz', 'as', 'ast', 'gn', 'av', 'ay', 'az', 'id', @@ -391,16 +358,6 @@ 'zh-classical', 'zh-yue', 'bat-smg', ] - # Order for fy: alphabetical by code, but y counts as i - - def fycomp(x,y): - x = x.replace("y","i")+x.count("y")*"!" - y = y.replace("y","i")+y.count("y")*"!" - return cmp(x,y) - self.fyinterwiki = self.alphabetic[:] - self.fyinterwiki.remove('nb') - self.fyinterwiki.sort(fycomp) - # 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 Modified: branches/rewrite/pywikibot/families/wiktionary_family.py =================================================================== --- branches/rewrite/pywikibot/families/wiktionary_family.py 2010-10-08 15:28:12 UTC (rev 8623) +++ branches/rewrite/pywikibot/families/wiktionary_family.py 2010-10-08 15:39:29 UTC (rev 8624) @@ -80,15 +80,6 @@ 'zh-cn': 'zh' } - # Order for fy: alphabetical by code, but y counts as i - # TODO: This code is duplicated from wikipedia_family.py - def fycomp(x,y): - x = x.replace("y","i")+x.count("y")*"!" - y = y.replace("y","i")+y.count("y")*"!" - return cmp(x,y) - self.fyinterwiki = self.alphabetic[:] - self.fyinterwiki.sort(fycomp) - # 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 @@ -104,6 +95,7 @@ 'fy': self.fyinterwiki, 'he': ['en'], 'hu': ['en'], + 'ms': self.alphabetic_revised, 'pl': self.alphabetic, 'simple': self.alphabetic } Modified: branches/rewrite/pywikibot/family.py =================================================================== --- branches/rewrite/pywikibot/family.py 2010-10-08 15:28:12 UTC (rev 8623) +++ branches/rewrite/pywikibot/family.py 2010-10-08 15:39:29 UTC (rev 8624) @@ -54,6 +54,49 @@ 'bat-smg', 'zh', 'zh-tw', 'zh-cn', ] + # A revised sorting order worked out on + # http://meta.wikimedia.org/wiki/Interwiki_sorting_order + self.alphabetic_revised = [ + 'ace', 'af', 'ak', 'als', 'am', 'ang', 'ab', 'ar', 'an', 'arc', + 'roa-rup', 'frp', 'as', 'ast', 'gn', 'av', 'ay', 'az', 'id', 'ms', + 'bm', 'bn', 'zh-min-nan', 'nan', 'map-bms', 'jv', 'su', 'ba', 'be', + 'be-x-old', 'bh', 'bcl', 'bi', 'bar', 'bo', 'bs', 'br', 'bug', 'bg', + 'bxr', 'ca', 'ceb', 'cv', 'cs', 'ch', 'cbk-zam', 'ny', 'sn', 'tum', + 'cho', 'co', 'cy', 'da', 'dk', 'pdc', 'de', 'dv', 'nv', 'dsb', 'na', + 'dz', 'mh', 'et', 'el', 'eml', 'en', 'myv', 'es', 'eo', 'ext', 'eu', + 'ee', 'fa', 'hif', 'fo', 'fr', 'fy', 'ff', 'fur', 'ga', 'gv', 'sm', + 'gd', 'gl', 'gan', 'ki', 'glk', 'gu', 'got', 'hak', 'xal', 'ko', + 'ha', 'haw', 'hy', 'hi', 'ho', 'hsb', 'hr', 'io', 'ig', 'ilo', + 'bpy', 'ia', 'ie', 'iu', 'ik', 'os', 'xh', 'zu', 'is', 'it', 'he', + 'kl', 'kn', 'kr', 'pam', 'ka', 'ks', 'csb', 'kk', 'kw', 'rw', 'ky', + 'rn', 'sw', 'kv', 'kg', 'ht', 'ku', 'kj', 'lad', 'lbe', 'lo', 'la', + 'lv', 'to', 'lb', 'lt', 'lij', 'li', 'ln', 'jbo', 'lg', 'lmo', 'hu', + 'mk', 'mg', 'ml', 'krc', 'mt', 'mi', 'mr', 'arz', 'mzn', 'cdo', + 'mwl', 'mdf', 'mo', 'mn', 'mus', 'my', 'nah', 'fj', 'nl', 'nds-nl', + 'cr', 'ne', 'new', 'ja', 'nap', 'ce', 'frr', 'pih', 'no', 'nb', + 'nn', 'nrm', 'nov', 'ii', 'oc', 'mhr', 'or', 'om', 'ng', 'hz', 'uz', + 'pa', 'pi', 'pag', 'pnb', 'pap', 'ps', 'km', 'pcd', 'pms', 'nds', + 'pl', 'pnt', 'pt', 'aa', 'kaa', 'crh', 'ty', 'ksh', 'ro', 'rmy', + 'rm', 'qu', 'ru', 'sah', 'se', 'sa', 'sg', 'sc', 'sco', 'stq', 'st', + 'tn', 'sq', 'scn', 'si', 'simple', 'sd', 'ss', 'sk', 'sl', 'cu', + 'szl', 'so', 'ckb', 'srn', 'sr', 'sh', 'fi', 'sv', 'tl', 'ta', + 'kab', 'roa-tara', 'tt', 'te', 'tet', 'th', 'vi', 'ti', 'tg', 'tpi', + 'tokipona', 'tp', 'chr', 'chy', 've', 'tr', 'tk', 'tw', 'udm', 'uk', + 'ur', 'ug', 'za', 'vec', 'vo', 'fiu-vro', 'wa', 'zh-classical', + 'vls', 'war', 'wo', 'wuu', 'ts', 'yi', 'yo', 'zh-yue', 'diq', 'zea', + 'bat-smg', 'zh', 'zh-tw', 'zh-cn', + ] + + # Order for fy: alphabetical by code, but y counts as i + def fycomp(x,y): + x = x.replace("y","i")+x.count("y")*"!" + y = y.replace("y","i")+y.count("y")*"!" + return cmp(x,y) + self.fyinterwiki = self.alphabetic[:] + self.fyinterwiki.remove('nb') + self.fyinterwiki.sort(fycomp) + + self.langs = {} # letters that can follow a wikilink and are regarded as part of

13 years, 6 months

SVN: [8623] trunk/pywikipedia

by malafaya＠svn.wikimedia.org

Revision: 8623 Author: malafaya Date: 2010-10-08 15:28:12 +0000 (Fri, 08 Oct 2010) Log Message: ----------- * Fixing sort order in ms.wikt (expected to be same as ms.wiki) ** Moved alphabetic_revised and fyinterwiki sort orders to base family.py to allow reuse across projects (Wikipedia, Wiktionary...) * Fixed wrong sort order for 'no' interwikis at fy.wikt (was already fixed on fy.wiki) Modified Paths: -------------- trunk/pywikipedia/families/wikipedia_family.py trunk/pywikipedia/families/wiktionary_family.py trunk/pywikipedia/family.py Modified: trunk/pywikipedia/families/wikipedia_family.py =================================================================== --- trunk/pywikipedia/families/wikipedia_family.py 2010-10-08 06:59:35 UTC (rev 8622) +++ trunk/pywikipedia/families/wikipedia_family.py 2010-10-08 15:28:12 UTC (rev 8623) @@ -938,39 +938,6 @@ # but some languages don't use this. self.nocapitalize = ['jbo',] - # A revised sorting order worked out on - # http://meta.wikimedia.org/wiki/Interwiki_sorting_order - self.alphabetic_revised = [ - 'ace', 'af', 'ak', 'als', 'am', 'ang', 'ab', 'ar', 'an', 'arc', - 'roa-rup', 'frp', 'as', 'ast', 'gn', 'av', 'ay', 'az', 'id', 'ms', - 'bm', 'bn', 'zh-min-nan', 'nan', 'map-bms', 'jv', 'su', 'ba', 'be', - 'be-x-old', 'bh', 'bcl', 'bi', 'bar', 'bo', 'bs', 'br', 'bug', 'bg', - 'bxr', 'ca', 'ceb', 'cv', 'cs', 'ch', 'cbk-zam', 'ny', 'sn', 'tum', - 'cho', 'co', 'cy', 'da', 'dk', 'pdc', 'de', 'dv', 'nv', 'dsb', 'na', - 'dz', 'mh', 'et', 'el', 'eml', 'en', 'myv', 'es', 'eo', 'ext', 'eu', - 'ee', 'fa', 'hif', 'fo', 'fr', 'fy', 'ff', 'fur', 'ga', 'gv', 'sm', - 'gd', 'gl', 'gan', 'ki', 'glk', 'gu', 'got', 'hak', 'xal', 'ko', - 'ha', 'haw', 'hy', 'hi', 'ho', 'hsb', 'hr', 'io', 'ig', 'ilo', - 'bpy', 'ia', 'ie', 'iu', 'ik', 'os', 'xh', 'zu', 'is', 'it', 'he', - 'kl', 'kn', 'kr', 'pam', 'ka', 'ks', 'csb', 'kk', 'kw', 'rw', 'ky', - 'rn', 'sw', 'kv', 'kg', 'ht', 'ku', 'kj', 'lad', 'lbe', 'lo', 'la', - 'lv', 'to', 'lb', 'lt', 'lij', 'li', 'ln', 'jbo', 'lg', 'lmo', 'hu', - 'mk', 'mg', 'ml', 'krc', 'mt', 'mi', 'mr', 'arz', 'mzn', 'cdo', - 'mwl', 'mdf', 'mo', 'mn', 'mus', 'my', 'nah', 'fj', 'nl', 'nds-nl', - 'cr', 'ne', 'new', 'ja', 'nap', 'ce', 'frr', 'pih', 'no', 'nb', - 'nn', 'nrm', 'nov', 'ii', 'oc', 'mhr', 'or', 'om', 'ng', 'hz', 'uz', - 'pa', 'pi', 'pag', 'pnb', 'pap', 'ps', 'km', 'pcd', 'pms', 'nds', - 'pl', 'pnt', 'pt', 'aa', 'kaa', 'crh', 'ty', 'ksh', 'ro', 'rmy', - 'rm', 'qu', 'ru', 'sah', 'se', 'sa', 'sg', 'sc', 'sco', 'stq', 'st', - 'tn', 'sq', 'scn', 'si', 'simple', 'sd', 'ss', 'sk', 'sl', 'cu', - 'szl', 'so', 'ckb', 'srn', 'sr', 'sh', 'fi', 'sv', 'tl', 'ta', - 'kab', 'roa-tara', 'tt', 'te', 'tet', 'th', 'vi', 'ti', 'tg', 'tpi', - 'tokipona', 'tp', 'chr', 'chy', 've', 'tr', 'tk', 'tw', 'udm', 'uk', - 'ur', 'ug', 'za', 'vec', 'vo', 'fiu-vro', 'wa', 'zh-classical', - 'vls', 'war', 'wo', 'wuu', 'ts', 'yi', 'yo', 'zh-yue', 'diq', 'zea', - 'bat-smg', 'zh', 'zh-tw', 'zh-cn', - ] - self.alphabetic_latin = [ 'ace', 'af', 'ak', 'als', 'am', 'ang', 'ab', 'ar', 'an', 'arc', 'roa-rup', 'frp', 'arz', 'as', 'ast', 'gn', 'av', 'ay', 'az', 'id', @@ -1002,16 +969,6 @@ 'zh-classical', 'zh-yue', 'bat-smg', ] - # Order for fy: alphabetical by code, but y counts as i - - def fycomp(x,y): - x = x.replace("y","i")+x.count("y")*"!" - y = y.replace("y","i")+y.count("y")*"!" - return cmp(x,y) - self.fyinterwiki = self.alphabetic[:] - self.fyinterwiki.remove('nb') - self.fyinterwiki.sort(fycomp) - # 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 Modified: trunk/pywikipedia/families/wiktionary_family.py =================================================================== --- trunk/pywikipedia/families/wiktionary_family.py 2010-10-08 06:59:35 UTC (rev 8622) +++ trunk/pywikipedia/families/wiktionary_family.py 2010-10-08 15:28:12 UTC (rev 8623) @@ -472,15 +472,6 @@ 'zh-cn': 'zh' } - # Order for fy: alphabetical by code, but y counts as i - # TODO: This code is duplicated from wikipedia_family.py - def fycomp(x,y): - x = x.replace("y","i")+x.count("y")*"!" - y = y.replace("y","i")+y.count("y")*"!" - return cmp(x,y) - self.fyinterwiki = self.alphabetic[:] - self.fyinterwiki.sort(fycomp) - # 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 @@ -496,6 +487,7 @@ 'fy': self.fyinterwiki, 'he': ['en'], 'hu': ['en'], + 'ms': self.alphabetic_revised, 'pl': self.alphabetic, 'simple': self.alphabetic } Modified: trunk/pywikipedia/family.py =================================================================== --- trunk/pywikipedia/family.py 2010-10-08 06:59:35 UTC (rev 8622) +++ trunk/pywikipedia/family.py 2010-10-08 15:28:12 UTC (rev 8623) @@ -50,6 +50,49 @@ 'bat-smg', 'zh', 'zh-tw', 'zh-cn', ] + # A revised sorting order worked out on + # http://meta.wikimedia.org/wiki/Interwiki_sorting_order + self.alphabetic_revised = [ + 'ace', 'af', 'ak', 'als', 'am', 'ang', 'ab', 'ar', 'an', 'arc', + 'roa-rup', 'frp', 'as', 'ast', 'gn', 'av', 'ay', 'az', 'id', 'ms', + 'bm', 'bn', 'zh-min-nan', 'nan', 'map-bms', 'jv', 'su', 'ba', 'be', + 'be-x-old', 'bh', 'bcl', 'bi', 'bar', 'bo', 'bs', 'br', 'bug', 'bg', + 'bxr', 'ca', 'ceb', 'cv', 'cs', 'ch', 'cbk-zam', 'ny', 'sn', 'tum', + 'cho', 'co', 'cy', 'da', 'dk', 'pdc', 'de', 'dv', 'nv', 'dsb', 'na', + 'dz', 'mh', 'et', 'el', 'eml', 'en', 'myv', 'es', 'eo', 'ext', 'eu', + 'ee', 'fa', 'hif', 'fo', 'fr', 'fy', 'ff', 'fur', 'ga', 'gv', 'sm', + 'gd', 'gl', 'gan', 'ki', 'glk', 'gu', 'got', 'hak', 'xal', 'ko', + 'ha', 'haw', 'hy', 'hi', 'ho', 'hsb', 'hr', 'io', 'ig', 'ilo', + 'bpy', 'ia', 'ie', 'iu', 'ik', 'os', 'xh', 'zu', 'is', 'it', 'he', + 'kl', 'kn', 'kr', 'pam', 'ka', 'ks', 'csb', 'kk', 'kw', 'rw', 'ky', + 'rn', 'sw', 'kv', 'kg', 'ht', 'ku', 'kj', 'lad', 'lbe', 'lo', 'la', + 'lv', 'to', 'lb', 'lt', 'lij', 'li', 'ln', 'jbo', 'lg', 'lmo', 'hu', + 'mk', 'mg', 'ml', 'krc', 'mt', 'mi', 'mr', 'arz', 'mzn', 'cdo', + 'mwl', 'mdf', 'mo', 'mn', 'mus', 'my', 'nah', 'fj', 'nl', 'nds-nl', + 'cr', 'ne', 'new', 'ja', 'nap', 'ce', 'frr', 'pih', 'no', 'nb', + 'nn', 'nrm', 'nov', 'ii', 'oc', 'mhr', 'or', 'om', 'ng', 'hz', 'uz', + 'pa', 'pi', 'pag', 'pnb', 'pap', 'ps', 'km', 'pcd', 'pms', 'nds', + 'pl', 'pnt', 'pt', 'aa', 'kaa', 'crh', 'ty', 'ksh', 'ro', 'rmy', + 'rm', 'qu', 'ru', 'sah', 'se', 'sa', 'sg', 'sc', 'sco', 'stq', 'st', + 'tn', 'sq', 'scn', 'si', 'simple', 'sd', 'ss', 'sk', 'sl', 'cu', + 'szl', 'so', 'ckb', 'srn', 'sr', 'sh', 'fi', 'sv', 'tl', 'ta', + 'kab', 'roa-tara', 'tt', 'te', 'tet', 'th', 'vi', 'ti', 'tg', 'tpi', + 'tokipona', 'tp', 'chr', 'chy', 've', 'tr', 'tk', 'tw', 'udm', 'uk', + 'ur', 'ug', 'za', 'vec', 'vo', 'fiu-vro', 'wa', 'zh-classical', + 'vls', 'war', 'wo', 'wuu', 'ts', 'yi', 'yo', 'zh-yue', 'diq', 'zea', + 'bat-smg', 'zh', 'zh-tw', 'zh-cn', + ] + + # Order for fy: alphabetical by code, but y counts as i + def fycomp(x,y): + x = x.replace("y","i")+x.count("y")*"!" + y = y.replace("y","i")+y.count("y")*"!" + return cmp(x,y) + self.fyinterwiki = self.alphabetic[:] + self.fyinterwiki.remove('nb') + self.fyinterwiki.sort(fycomp) + + self.langs = {} # The timedelta to GMT of the server.

13 years, 6 months

SVN: [8622] branches/rewrite/pywikibot/families

by xqt＠svn.wikimedia.org

Revision: 8622 Author: xqt Date: 2010-10-08 06:59:35 +0000 (Fri, 08 Oct 2010) Log Message: ----------- update family files from trunk r8621 Modified Paths: -------------- branches/rewrite/pywikibot/families/wikibooks_family.py branches/rewrite/pywikibot/families/wikipedia_family.py branches/rewrite/pywikibot/families/wikiquote_family.py branches/rewrite/pywikibot/families/wiktionary_family.py Modified: branches/rewrite/pywikibot/families/wikibooks_family.py =================================================================== --- branches/rewrite/pywikibot/families/wikibooks_family.py 2010-10-08 06:56:59 UTC (rev 8621) +++ branches/rewrite/pywikibot/families/wikibooks_family.py 2010-10-08 06:59:35 UTC (rev 8622) @@ -11,15 +11,14 @@ self.name = 'wikibooks' self.languages_by_size = [ - 'en', 'de', 'fr', 'ja', 'hu', 'pt', 'nl', 'es', 'pl', 'it', 'he', + 'en', 'de', 'fr', 'ja', 'pt', 'hu', 'nl', 'es', 'pl', 'it', 'he', 'sq', 'fi', 'ca', 'ru', 'vi', 'cs', 'hr', 'zh', 'sv', 'tr', 'da', - 'th', 'id', 'mk', 'ko', 'sr', 'fa', 'tl', 'ar', 'gl', 'is', 'no', + 'th', 'id', 'mk', 'ko', 'fa', 'sr', 'tl', 'ar', 'gl', 'is', 'no', 'ta', 'ka', 'lt', 'eo', 'bg', 'ro', 'sk', 'el', 'si', 'la', 'uk', - 'ang', 'ia', 'cv', 'sl', 'mr', 'et', 'az', 'ur', 'ml', 'oc', 'ms', + 'ang', 'ia', 'cv', 'sl', 'mr', 'et', 'az', 'ur', 'oc', 'ml', 'ms', 'eu', 'hi', 'fy', 'ie', 'tt', 'af', 'tg', 'bn', 'hy', 'pa', 'te', 'sa', 'bs', 'ky', 'be', 'ne', 'ast', 'zh-min-nan', 'cy', 'mg', 'ku', - 'co', 'tk', 'su', 'als', 'vo', 'uz', 'na', 'kk', 'mn', 'nds', 'zu', - 'my', + 'co', 'tk', 'su', 'als', 'vo', 'uz', 'na', 'kk', 'mn', 'nds', 'my', ] for lang in self.languages_by_size: @@ -83,7 +82,8 @@ 'yo': None, # http://meta.wikimedia.org/wiki/Proposals_for_closing_projects/Closure_of_Yo… 'za': None, # https://bugzilla.wikimedia.org/show_bug.cgi?id=20325 'zh-tw': 'zh', - 'zh-cn': 'zh' + 'zh-cn': 'zh', + 'zu': None, # https://bugzilla.wikimedia.org/show_bug.cgi?id=25425 } self.interwiki_putfirst = { Modified: branches/rewrite/pywikibot/families/wikipedia_family.py =================================================================== --- branches/rewrite/pywikibot/families/wikipedia_family.py 2010-10-08 06:56:59 UTC (rev 8621) +++ branches/rewrite/pywikibot/families/wikipedia_family.py 2010-10-08 06:59:35 UTC (rev 8622) @@ -11,28 +11,28 @@ self.name = 'wikipedia' self.languages_by_size = [ - 'en', 'de', 'fr', 'it', 'pl', 'ja', 'es', 'nl', 'pt', 'ru', 'sv', + 'en', 'de', 'fr', 'pl', 'it', 'ja', 'es', 'nl', 'pt', 'ru', 'sv', 'zh', 'ca', 'no', 'fi', 'uk', 'hu', 'cs', 'ro', 'tr', 'ko', 'da', 'ar', 'eo', 'id', 'vi', 'sr', 'vo', 'lt', 'sk', 'he', 'bg', 'fa', 'sl', 'war', 'hr', 'et', 'ms', 'new', 'simple', 'gl', 'th', 'roa-rup', 'nn', 'eu', 'hi', 'el', 'ht', 'te', 'la', 'ka', 'mk', 'ceb', 'az', 'tl', 'br', 'sh', 'mr', 'lb', 'jv', 'lv', 'bs', 'is', 'cy', 'pms', 'be-x-old', 'sq', 'ta', 'bpy', 'be', 'an', 'oc', 'bn', - 'sw', 'io', 'ksh', 'fy', 'gu', 'lmo', 'nds', 'af', 'scn', 'qu', + 'sw', 'io', 'ksh', 'fy', 'lmo', 'gu', 'nds', 'af', 'scn', 'qu', 'ku', 'ur', 'su', 'ml', 'zh-yue', 'ast', 'nap', 'bat-smg', 'wa', 'ga', 'cv', 'hy', 'yo', 'kn', 'tg', 'roa-tara', 'vec', 'pnb', 'gd', 'yi', 'zh-min-nan', 'uz', 'tt', 'pam', 'os', 'ne', 'sah', 'als', 'mi', 'arz', 'kk', 'nah', 'li', 'hsb', 'glk', 'co', 'gan', 'am', - 'ia', 'mn', 'bcl', 'fiu-vro', 'nds-nl', 'fo', 'tk', 'vls', 'si', - 'sa', 'sco', 'bar', 'gv', 'dv', 'nrm', 'pag', 'rm', 'my', 'map-bms', + 'ia', 'mn', 'bcl', 'fiu-vro', 'nds-nl', 'fo', 'tk', 'vls', 'sa', + 'si', 'sco', 'bar', 'gv', 'dv', 'nrm', 'pag', 'rm', 'my', 'map-bms', 'diq', 'ckb', 'se', 'wuu', 'mzn', 'ug', 'fur', 'lij', 'mt', 'bh', 'nov', 'mg', 'csb', 'ilo', 'sc', 'km', 'zh-classical', 'lad', 'pi', 'ang', 'cbk-zam', 'bo', 'frp', 'hif', 'hak', 'kw', 'pa', 'ps', 'xal', 'pdc', 'szl', 'haw', 'ie', 'stq', 'crh', 'fj', 'kv', 'to', - 'ace', 'so', 'nv', 'myv', 'gn', 'krc', 'ln', 'ext', 'ky', 'mhr', - 'arc', 'eml', 'jbo', 'wo', 'ay', 'pcd', 'kab', 'frr', 'ty', 'tpi', - 'ba', 'pap', 'zea', 'srn', 'kl', 'udm', 'ce', 'ig', 'or', 'dsb', - 'kg', 'lo', 'ab', 'rmy', 'tum', 'mwl', 'cu', 'mdf', 'kaa', 'sm', + 'ace', 'nv', 'so', 'myv', 'gn', 'krc', 'ln', 'ext', 'ky', 'mhr', + 'arc', 'eml', 'jbo', 'wo', 'ay', 'pcd', 'kab', 'frr', 'ty', 'ba', + 'tpi', 'pap', 'zea', 'srn', 'kl', 'udm', 'ce', 'ig', 'tum', 'or', + 'dsb', 'kg', 'lo', 'ab', 'rmy', 'mwl', 'cu', 'mdf', 'kaa', 'sm', 'av', 'tet', 'sn', 'ks', 'got', 'sd', 'na', 'bm', 'pih', 'pnt', 'iu', 'chr', 'ik', 'bi', 'as', 'cdo', 'ee', 'ss', 'om', 'za', 'ti', 'ts', 've', 'zu', 'ha', 'dz', 'sg', 'ch', 'cr', 'ak', 'xh', 'rw', Modified: branches/rewrite/pywikibot/families/wikiquote_family.py =================================================================== --- branches/rewrite/pywikibot/families/wikiquote_family.py 2010-10-08 06:56:59 UTC (rev 8621) +++ branches/rewrite/pywikibot/families/wikiquote_family.py 2010-10-08 06:59:35 UTC (rev 8622) @@ -13,7 +13,7 @@ self.languages_by_size = [ 'en', 'pl', 'it', 'de', 'pt', 'ru', 'sk', 'es', 'bg', 'bs', 'tr', 'sl', 'fr', 'cs', 'he', 'lt', 'el', 'id', 'zh', 'hu', 'fa', 'uk', - 'eo', 'sv', 'nl', 'no', 'fi', 'ja', 'nn', 'hy', 'et', 'ca', 'li', + 'eo', 'sv', 'nl', 'fi', 'no', 'ja', 'nn', 'hy', 'et', 'ca', 'li', 'ar', 'ka', 'hr', 'ko', 'ku', 'gl', 'ro', 'sr', 'cy', 'ml', 'az', 'is', 'th', 'te', 'af', 'da', 'eu', 'sq', 'vi', 'la', 'br', 'hi', 'mr', 'be', 'ast', 'ta', 'uz', 'ang', 'zh-min-nan', 'ur', 'lb', Modified: branches/rewrite/pywikibot/families/wiktionary_family.py =================================================================== --- branches/rewrite/pywikibot/families/wiktionary_family.py 2010-10-08 06:56:59 UTC (rev 8621) +++ branches/rewrite/pywikibot/families/wiktionary_family.py 2010-10-08 06:59:35 UTC (rev 8622) @@ -12,15 +12,15 @@ self.languages_by_size = [ 'en', 'fr', 'lt', 'zh', 'tr', 'ru', 'vi', 'pl', 'io', 'pt', 'fi', - 'hu', 'ko', 'el', 'no', 'de', 'ta', 'sv', 'it', 'nl', 'my', 'kn', - 'li', 'mg', 'lo', 'ml', 'ja', 'es', 'ku', 'ar', 'et', 'ro', 'id', + 'hu', 'ko', 'el', 'no', 'de', 'ta', 'sv', 'it', 'nl', 'mg', 'my', + 'kn', 'li', 'lo', 'ml', 'ja', 'es', 'ku', 'ar', 'et', 'ro', 'id', 'te', 'gl', 'uk', 'bg', 'ca', 'vo', 'fa', 'is', 'scn', 'cs', 'hr', 'simple', 'sr', 'af', 'th', 'oc', 'fy', 'sw', 'br', 'he', 'la', 'sq', 'sl', 'hy', 'tt', 'zh-min-nan', 'da', 'cy', 'wa', 'ne', 'tk', 'lv', 'ast', 'ur', 'hsb', 'ka', 'kk', 'eo', 'ky', 'wo', 'eu', 'ang', 'hi', 'co', 'az', 'mr', 'ga', 'gn', 'ia', 'sk', 'be', 'tl', 'ms', 'csb', 'st', 'nn', 'nds', 'kl', 'sd', 'ug', 'ps', 'ti', 'sh', 'mk', - 'bn', 'an', 'si', 'zu', 'gu', 'km', 'ss', 'qu', 'ts', 'bs', 'fo', + 'bn', 'si', 'an', 'zu', 'gu', 'km', 'ss', 'qu', 'ts', 'bs', 'fo', 'am', 'rw', 'chr', 'om', 'su', 'kw', 'iu', 'mn', 'gv', 'nah', 'lb', 'yi', 'ie', 'pa', 'mt', 'gd', 'tg', 'tpi', 'dv', 'za', 'ik', 'sg', 'so', 'mi', 'roa-rup', 'uz', 'jv', 'ln', 'sm', 'ha', 'ay', 'sa',

13 years, 6 months

SVN: [8621] trunk/pywikipedia/families

by xqt＠svn.wikimedia.org

Revision: 8621 Author: xqt Date: 2010-10-08 06:56:59 +0000 (Fri, 08 Oct 2010) Log Message: ----------- Portal namespace for az-wiki; remove obsolete zu-wikibooks; update language_by_size Modified Paths: -------------- trunk/pywikipedia/families/wikibooks_family.py trunk/pywikipedia/families/wikipedia_family.py trunk/pywikipedia/families/wikiquote_family.py trunk/pywikipedia/families/wiktionary_family.py Modified: trunk/pywikipedia/families/wikibooks_family.py =================================================================== --- trunk/pywikipedia/families/wikibooks_family.py 2010-10-07 11:56:18 UTC (rev 8620) +++ trunk/pywikipedia/families/wikibooks_family.py 2010-10-08 06:56:59 UTC (rev 8621) @@ -11,15 +11,14 @@ self.name = 'wikibooks' self.languages_by_size = [ - 'en', 'de', 'fr', 'ja', 'hu', 'pt', 'nl', 'es', 'pl', 'it', 'he', + 'en', 'de', 'fr', 'ja', 'pt', 'hu', 'nl', 'es', 'pl', 'it', 'he', 'sq', 'fi', 'ca', 'ru', 'vi', 'cs', 'hr', 'zh', 'sv', 'tr', 'da', - 'th', 'id', 'mk', 'ko', 'sr', 'fa', 'tl', 'ar', 'gl', 'is', 'no', + 'th', 'id', 'mk', 'ko', 'fa', 'sr', 'tl', 'ar', 'gl', 'is', 'no', 'ta', 'ka', 'lt', 'eo', 'bg', 'ro', 'sk', 'el', 'si', 'la', 'uk', - 'ang', 'ia', 'cv', 'sl', 'mr', 'et', 'az', 'ur', 'ml', 'oc', 'ms', + 'ang', 'ia', 'cv', 'sl', 'mr', 'et', 'az', 'ur', 'oc', 'ml', 'ms', 'eu', 'hi', 'fy', 'ie', 'tt', 'af', 'tg', 'bn', 'hy', 'pa', 'te', 'sa', 'bs', 'ky', 'be', 'ne', 'ast', 'zh-min-nan', 'cy', 'mg', 'ku', - 'co', 'tk', 'su', 'als', 'vo', 'uz', 'na', 'kk', 'mn', 'nds', 'zu', - 'my', + 'co', 'tk', 'su', 'als', 'vo', 'uz', 'na', 'kk', 'mn', 'nds', 'my', ] if family.config.SSL_connection: @@ -367,7 +366,8 @@ 'yo': None, # http://meta.wikimedia.org/wiki/Proposals_for_closing_projects/Closure_of_Yo… 'za': None, # https://bugzilla.wikimedia.org/show_bug.cgi?id=20325 'zh-tw': 'zh', - 'zh-cn': 'zh' + 'zh-cn': 'zh', + 'zu': None, # https://bugzilla.wikimedia.org/show_bug.cgi?id=25425 } self.interwiki_putfirst = { Modified: trunk/pywikipedia/families/wikipedia_family.py =================================================================== --- trunk/pywikipedia/families/wikipedia_family.py 2010-10-07 11:56:18 UTC (rev 8620) +++ trunk/pywikipedia/families/wikipedia_family.py 2010-10-08 06:56:59 UTC (rev 8621) @@ -11,28 +11,28 @@ self.name = 'wikipedia' self.languages_by_size = [ - 'en', 'de', 'fr', 'it', 'pl', 'ja', 'es', 'nl', 'pt', 'ru', 'sv', + 'en', 'de', 'fr', 'pl', 'it', 'ja', 'es', 'nl', 'pt', 'ru', 'sv', 'zh', 'ca', 'no', 'fi', 'uk', 'hu', 'cs', 'ro', 'tr', 'ko', 'da', 'ar', 'eo', 'id', 'vi', 'sr', 'vo', 'lt', 'sk', 'he', 'bg', 'fa', 'sl', 'war', 'hr', 'et', 'ms', 'new', 'simple', 'gl', 'th', 'roa-rup', 'nn', 'eu', 'hi', 'el', 'ht', 'te', 'la', 'ka', 'mk', 'ceb', 'az', 'tl', 'br', 'sh', 'mr', 'lb', 'jv', 'lv', 'bs', 'is', 'cy', 'pms', 'be-x-old', 'sq', 'ta', 'bpy', 'be', 'an', 'oc', 'bn', - 'sw', 'io', 'ksh', 'fy', 'gu', 'lmo', 'nds', 'af', 'scn', 'qu', + 'sw', 'io', 'ksh', 'fy', 'lmo', 'gu', 'nds', 'af', 'scn', 'qu', 'ku', 'ur', 'su', 'ml', 'zh-yue', 'ast', 'nap', 'bat-smg', 'wa', 'ga', 'cv', 'hy', 'yo', 'kn', 'tg', 'roa-tara', 'vec', 'pnb', 'gd', 'yi', 'zh-min-nan', 'uz', 'tt', 'pam', 'os', 'ne', 'sah', 'als', 'mi', 'arz', 'kk', 'nah', 'li', 'hsb', 'glk', 'co', 'gan', 'am', - 'ia', 'mn', 'bcl', 'fiu-vro', 'nds-nl', 'fo', 'tk', 'vls', 'si', - 'sa', 'sco', 'bar', 'gv', 'dv', 'nrm', 'pag', 'rm', 'my', 'map-bms', + 'ia', 'mn', 'bcl', 'fiu-vro', 'nds-nl', 'fo', 'tk', 'vls', 'sa', + 'si', 'sco', 'bar', 'gv', 'dv', 'nrm', 'pag', 'rm', 'my', 'map-bms', 'diq', 'ckb', 'se', 'wuu', 'mzn', 'ug', 'fur', 'lij', 'mt', 'bh', 'nov', 'mg', 'csb', 'ilo', 'sc', 'km', 'zh-classical', 'lad', 'pi', 'ang', 'cbk-zam', 'bo', 'frp', 'hif', 'hak', 'kw', 'pa', 'ps', 'xal', 'pdc', 'szl', 'haw', 'ie', 'stq', 'crh', 'fj', 'kv', 'to', - 'ace', 'so', 'nv', 'myv', 'gn', 'krc', 'ln', 'ext', 'ky', 'mhr', - 'arc', 'eml', 'jbo', 'wo', 'ay', 'pcd', 'kab', 'frr', 'ty', 'tpi', - 'ba', 'pap', 'zea', 'srn', 'kl', 'udm', 'ce', 'ig', 'or', 'dsb', - 'kg', 'lo', 'ab', 'rmy', 'tum', 'mwl', 'cu', 'mdf', 'kaa', 'sm', + 'ace', 'nv', 'so', 'myv', 'gn', 'krc', 'ln', 'ext', 'ky', 'mhr', + 'arc', 'eml', 'jbo', 'wo', 'ay', 'pcd', 'kab', 'frr', 'ty', 'ba', + 'tpi', 'pap', 'zea', 'srn', 'kl', 'udm', 'ce', 'ig', 'tum', 'or', + 'dsb', 'kg', 'lo', 'ab', 'rmy', 'mwl', 'cu', 'mdf', 'kaa', 'sm', 'av', 'tet', 'sn', 'ks', 'got', 'sd', 'na', 'bm', 'pih', 'pnt', 'iu', 'chr', 'ik', 'bi', 'as', 'cdo', 'ee', 'ss', 'om', 'za', 'ti', 'ts', 've', 'zu', 'ha', 'dz', 'sg', 'ch', 'cr', 'ak', 'xh', 'rw', @@ -385,6 +385,7 @@ 'an': u'Portal', 'ar': u'بوابة', 'arz': u'بوابة', + 'az': u'Portal', 'bar': u'Portal', 'be-x-old': u'Партал', 'bg': u'Портал', @@ -472,6 +473,7 @@ 'an': u'Descusión Portal', 'ar': u'نقاش البوابة', 'arz': u'مناقشة بوابة', + 'az': u'Portal müzakirəsi', 'bar': u'Portal Diskussion', 'be-x-old': u'Абмеркаваньне парталу', 'bg': u'Портал беседа', Modified: trunk/pywikipedia/families/wikiquote_family.py =================================================================== --- trunk/pywikipedia/families/wikiquote_family.py 2010-10-07 11:56:18 UTC (rev 8620) +++ trunk/pywikipedia/families/wikiquote_family.py 2010-10-08 06:56:59 UTC (rev 8621) @@ -13,7 +13,7 @@ self.languages_by_size = [ 'en', 'pl', 'it', 'de', 'pt', 'ru', 'sk', 'es', 'bg', 'bs', 'tr', 'sl', 'fr', 'cs', 'he', 'lt', 'el', 'id', 'zh', 'hu', 'fa', 'uk', - 'eo', 'sv', 'nl', 'no', 'fi', 'ja', 'nn', 'hy', 'et', 'ca', 'li', + 'eo', 'sv', 'nl', 'fi', 'no', 'ja', 'nn', 'hy', 'et', 'ca', 'li', 'ar', 'ka', 'hr', 'ko', 'ku', 'gl', 'ro', 'sr', 'cy', 'ml', 'az', 'is', 'th', 'te', 'af', 'da', 'eu', 'sq', 'vi', 'la', 'br', 'hi', 'mr', 'be', 'ast', 'ta', 'uz', 'ang', 'zh-min-nan', 'ur', 'lb', Modified: trunk/pywikipedia/families/wiktionary_family.py =================================================================== --- trunk/pywikipedia/families/wiktionary_family.py 2010-10-07 11:56:18 UTC (rev 8620) +++ trunk/pywikipedia/families/wiktionary_family.py 2010-10-08 06:56:59 UTC (rev 8621) @@ -12,15 +12,15 @@ self.languages_by_size = [ 'en', 'fr', 'lt', 'zh', 'tr', 'ru', 'vi', 'pl', 'io', 'pt', 'fi', - 'hu', 'ko', 'el', 'no', 'de', 'ta', 'sv', 'it', 'nl', 'my', 'kn', - 'li', 'mg', 'lo', 'ml', 'ja', 'es', 'ku', 'ar', 'et', 'ro', 'id', + 'hu', 'ko', 'el', 'no', 'de', 'ta', 'sv', 'it', 'nl', 'mg', 'my', + 'kn', 'li', 'lo', 'ml', 'ja', 'es', 'ku', 'ar', 'et', 'ro', 'id', 'te', 'gl', 'uk', 'bg', 'ca', 'vo', 'fa', 'is', 'scn', 'cs', 'hr', 'simple', 'sr', 'af', 'th', 'oc', 'fy', 'sw', 'br', 'he', 'la', 'sq', 'sl', 'hy', 'tt', 'zh-min-nan', 'da', 'cy', 'wa', 'ne', 'tk', 'lv', 'ast', 'ur', 'hsb', 'ka', 'kk', 'eo', 'ky', 'wo', 'eu', 'ang', 'hi', 'co', 'az', 'mr', 'ga', 'gn', 'ia', 'sk', 'be', 'tl', 'ms', 'csb', 'st', 'nn', 'nds', 'kl', 'sd', 'ug', 'ps', 'ti', 'sh', 'mk', - 'bn', 'an', 'si', 'zu', 'gu', 'km', 'ss', 'qu', 'ts', 'bs', 'fo', + 'bn', 'si', 'an', 'zu', 'gu', 'km', 'ss', 'qu', 'ts', 'bs', 'fo', 'am', 'rw', 'chr', 'om', 'su', 'kw', 'iu', 'mn', 'gv', 'nah', 'lb', 'yi', 'ie', 'pa', 'mt', 'gd', 'tg', 'tpi', 'dv', 'za', 'ik', 'sg', 'so', 'mi', 'roa-rup', 'uz', 'jv', 'ln', 'sm', 'ha', 'ay', 'sa',

13 years, 6 months

← Newer
1
2
3
4
5
6
7
8
9
Older →

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

Pywikipedia-svn October 2010