Pywikipedia-svn September 2010

pywikipedia-svn@lists.wikimedia.org

5 participants
127 discussions

SVN: [8530] trunk/pywikipedia/imagerecat.py
by xqt＠svn.wikimedia.org 12 Sep '10

12 Sep '10

Revision: 8530 Author: xqt Date: 2010-09-12 12:19:44 +0000 (Sun, 12 Sep 2010) Log Message: ----------- import wikipedia as pywikibot for merging to rewrite branch; use wikipedia lib for categoryRedirects; some speedup fixes Modified Paths: -------------- trunk/pywikipedia/imagerecat.py Modified: trunk/pywikipedia/imagerecat.py =================================================================== --- trunk/pywikipedia/imagerecat.py 2010-09-12 11:41:43 UTC (rev 8529) +++ trunk/pywikipedia/imagerecat.py 2010-09-12 12:19:44 UTC (rev 8530) @@ -3,13 +3,16 @@ Program to (re)categorize images at commons. The program uses commonshelper for category suggestions. -It takes the suggestions and the current categories. Put the categories through some filters and adds the result. +It takes the suggestions and the current categories. Put the categories through +some filters and adds the result. The following command line parameters are supported: --onlyfilter Don't use Commonsense to get categories, just filter the current categories +-onlyfilter Don't use Commonsense to get categories, just filter the current + categories --onlyuncat Only work on uncategorized images. Will prevent the bot from working on an image multiple times. +-onlyuncat Only work on uncategorized images. Will prevent the bot from + working on an image multiple times. -hint Give Commonsense a hint. For example -hint:li.wikipedia.org @@ -32,9 +35,11 @@ import urllib, httplib, urllib2 import catlib import time -import wikipedia, config -import pagegenerators, StringIO import socket +import StringIO +import wikipedia as pywikibot +import config +import pagegenerators category_blacklist = [] countries = [] @@ -49,29 +54,33 @@ global category_blacklist global countries - blacklistPage = wikipedia.Page(wikipedia.getSite(u'commons', u'commons'), u'User:Multichill/Category_blacklist') + blacklistPage = pywikibot.Page(pywikibot.getSite(u'commons', u'commons'), + u'User:Multichill/Category_blacklist') for cat in blacklistPage.linkedPages(): category_blacklist.append(cat.titleWithoutNamespace()) - countryPage = wikipedia.Page(wikipedia.getSite(u'commons', u'commons'), u'User:Multichill/Countries') + countryPage = pywikibot.Page(pywikibot.getSite(u'commons', u'commons'), + u'User:Multichill/Countries') for country in countryPage.linkedPages(): countries.append(country.titleWithoutNamespace()) return def categorizeImages(generator, onlyFilter, onlyUncat): + ''' Loop over all images in generator and try to categorize them. Get + category suggestions from CommonSense. + ''' - Loop over all images in generator and try to categorize them. Get category suggestions from CommonSense. - ''' for page in generator: - if page.exists() and (page.namespace() == 6) and (not page.isRedirectPage()): - imagepage = wikipedia.ImagePage(page.site(), page.title()) - wikipedia.output(u'Working on ' + imagepage.title()) + if page.exists() and (page.namespace() == 6) and \ + (not page.isRedirectPage()): + imagepage = pywikibot.ImagePage(page.site(), page.title()) + pywikibot.output(u'Working on ' + imagepage.title()) - if(onlyUncat and not(u'Uncategorized' in imagepage.templates())): - wikipedia.output(u'No Uncategorized template found') + if (onlyUncat and not(u'Uncategorized' in imagepage.templates())): + pywikibot.output(u'No Uncategorized template found') else: currentCats = getCurrentCats(imagepage) - if(onlyFilter): + if onlyFilter: commonshelperCats = [] usage = [] galleries = [] @@ -81,25 +90,22 @@ if (len(newcats) > 0 and not(set(currentCats)==set(newcats))): for cat in newcats: - wikipedia.output(u' Found new cat: ' + cat); - saveImagePage(imagepage, newcats, usage, galleries, onlyFilter) + pywikibot.output(u' Found new cat: ' + cat); + saveImagePage(imagepage, newcats, usage, galleries, + onlyFilter) - - def getCurrentCats(imagepage): - ''' - Get the categories currently on the image - ''' + ''' Get the categories currently on the image ''' result = [] for cat in imagepage.categories(): result.append(cat.titleWithoutNamespace()) return list(set(result)) - def getCommonshelperCats(imagepage): + ''' Get category suggestions from CommonSense. Parse them and return a list + of suggestions. + ''' - Get category suggestions from CommonSense. Parse them and return a list of suggestions. - ''' commonshelperCats = [] usage = [] galleries = [] @@ -116,82 +122,76 @@ else: #Cant handle other sites atm return ([], [], []) - + commonsenseRe = re.compile('^#COMMONSENSE(.*)#USAGE(\s)+$(?P<usagenum>(\d)+)$\s(?P<usage>(.*))\s#KEYWORDS(\s)+$(?P<keywords>(\d)+)$(.*)#CATEGORIES(\s)+$(?P<catnum>(\d)+)$\s(?P<cats>(.*))\s#GALLERIES(\s)+$(?P<galnum>(\d)+)$\s(?P<gals>(.*))\s(.*)#EOF$', re.MULTILINE + re.DOTALL) gotInfo = False matches = None maxtries = 10 tries = 0 - while(not gotInfo): try: if ( tries < maxtries ): tries = tries + 1 - commonsHelperPage = urllib.urlopen("http://toolserver.org/~daniel/WikiSense/CommonSense.php?%s" % parameters) - matches = commonsenseRe.search(commonsHelperPage.read().decode('utf-8')) + commonsHelperPage = urllib.urlopen( + "http://toolserver.org/~daniel/WikiSense/CommonSense.php?%s" % parameters) + matches = commonsenseRe.search( + commonsHelperPage.read().decode('utf-8')) gotInfo = True else: break except IOError: - wikipedia.output(u'Got an IOError, let\'s try again') + pywikibot.output(u'Got an IOError, let\'s try again') except socket.timeout: - wikipedia.output(u'Got a timeout, let\'s try again') + pywikibot.output(u'Got a timeout, let\'s try again') if (matches and gotInfo): - if(matches.group('usagenum') > 0): + if (matches.group('usagenum') > 0): used = matches.group('usage').splitlines() for use in used: usage= usage + getUsage(use) - #wikipedia.output(use) - if(matches.group('catnum') > 0): + #pywikibot.output(use) + if (matches.group('catnum') > 0): cats = matches.group('cats').splitlines() for cat in cats: commonshelperCats.append(cat.replace('_',' ')) - wikipedia.output(u'category : ' + cat) - if(matches.group('galnum') > 0): + pywikibot.output(u'category : ' + cat) + if (matches.group('galnum') > 0): gals = matches.group('gals').splitlines() for gal in gals: galleries.append(gal.replace('_',' ')) - wikipedia.output(u'gallery : ' + gal) + pywikibot.output(u'gallery : ' + gal) commonshelperCats = list(set(commonshelperCats)) galleries = list(set(galleries)) for (lang, project, article) in usage: - wikipedia.output(lang + project + article) - + pywikibot.output(lang + project + article) return (commonshelperCats, usage, galleries) def getUsage(use): - ''' - Parse the Commonsense output to get the usage - ''' + ''' Parse the Commonsense output to get the usage ''' result = [] lang = '' project = '' article = '' - usageRe = re.compile('^(?P<lang>([\w]+))\.(?P<project>([\w]+))\.org:(?P<articles>\s(.*))') + usageRe = re.compile( + '^(?P<lang>([\w]+))\.(?P<project>([\w]+))\.org:(?P<articles>\s(.*))') matches = usageRe.search(use) if matches: - if(matches.group('lang')): + if (matches.group('lang')): lang = matches.group('lang') - #wikipedia.output(lang) - if(matches.group('project')): + #pywikibot.output(lang) + if (matches.group('project')): project = matches.group('project') - #wikipedia.output(project) - if(matches.group('articles')): + #pywikibot.output(project) + if (matches.group('articles')): articles = matches.group('articles') - #wikipedia.output(articles) + #pywikibot.output(articles) for article in articles.split(): result.append((lang, project, article)) - return result - - def applyAllFilters(categories): - ''' - Apply all filters on categories. - ''' + ''' Apply all filters on categories. ''' result = [] result = filterBlacklist(categories) result = filterDisambiguation(result) @@ -200,11 +200,8 @@ result = filterParents(result) return result - def filterBlacklist(categories): - ''' - Filter out categories which are on the blacklist. - ''' + ''' Filter out categories which are on the blacklist. ''' result = [] for cat in categories: cat = cat.replace('_', ' ') @@ -212,40 +209,36 @@ result.append(cat) return list(set(result)) - def filterDisambiguation(categories): - ''' - Filter out disambiguation categories. - ''' + ''' Filter out disambiguation categories. ''' result = [] for cat in categories: - if(not wikipedia.Page(wikipedia.getSite(u'commons', u'commons'), u'Category:' + cat).isDisambig()): + if (not pywikibot.Page(pywikibot.getSite(u'commons', u'commons'), + cat, defaultNamespace=14).isDisambig()): result.append(cat) return result def followRedirects(categories): - ''' - If a category is a redirect, replace the category with the target. - ''' + ''' If a category is a redirect, replace the category with the target. ''' result = [] for cat in categories: - categoryPage = wikipedia.Page(wikipedia.getSite(u'commons', u'commons'), u'Category:' + cat) - if u'Category redirect' in categoryPage.templates() or u'Seecat' in categoryPage.templates(): - for template in categoryPage.templatesWithParams(): - if ((template[0]==u'Category redirect' or template[0]==u'Seecat') and (len(template[1]) > 0)): - result.append(template[1][0]) + categoryPage = pywikibot.Page(pywikibot.getSite(u'commons', u'commons'), + cat, defaultNamespace=14) + if categoryPage.isCategoryRedirect(): + result.append(getCategoryRedirectTarget(), + categoryPage.titleWithoutNamespace()) else: result.append(cat) return result - def filterCountries(categories): + ''' Try to filter out ...by country categories. + First make a list of any ...by country categories and try to find some + countries. If a by country category has a subcategoy containing one of the + countries found, add it. The ...by country categories remain in the set and + should be filtered out by filterParents. + ''' - Try to filter out ...by country categories. - First make a list of any ...by country categories and try to find some countries. - If a by country category has a subcategoy containing one of the countries found, add it. - The ...by country categories remain in the set and should be filtered out by filterParents. - ''' result = categories listByCountry = [] listCountries = [] @@ -259,76 +252,70 @@ for country in countries: if country in cat: listCountries.append(country) - if(len(listByCountry) > 0): for bc in listByCountry: - category = catlib.Category(wikipedia.getSite(u'commons', u'commons'), u'Category:' + bc) + category = catlib.Category( + pywikibot.getSite(u'commons', u'commons'), u'Category:' + bc) for subcategory in category.subcategories(): for country in listCountries: if (subcategory.titleWithoutNamespace().endswith(country)): result.append(subcategory.titleWithoutNamespace()) - return list(set(result)) def filterParents(categories): + ''' Remove all parent categories from the set to prevent overcategorization. + ''' - Remove all parent categories from the set to prevent overcategorization. - ''' result = [] toFilter = u'' - for cat in categories: cat = cat.replace('_',' ') toFilter = toFilter + "[[Category:" + cat + "]]\n" - #try: - parameters = urllib.urlencode({'source' : toFilter.encode('utf-8'), 'bot' : '1'}) + parameters = urllib.urlencode({'source' : toFilter.encode('utf-8'), + 'bot' : '1'}) filterCategoriesRe = re.compile('\[\[Category:([^\]]*)\]\]') try: - filterCategoriesPage = urllib.urlopen("http://toolserver.org/~multichill/filtercats.php?%s" % parameters) - result = filterCategoriesRe.findall(filterCategoriesPage.read().decode('utf-8')) + filterCategoriesPage = urllib.urlopen( + "http://toolserver.org/~multichill/filtercats.php?%s" % parameters) + result = filterCategoriesRe.findall( + filterCategoriesPage.read().decode('utf-8')) except IOError: #Something is wrong, forget about this filter and just return the input return categories - + if not result: #Is empty, dont want to remove all categories return categories return result - def saveImagePage(imagepage, newcats, usage, galleries, onlyFilter): - ''' - Remove the old categories and add the new categories to the image. - ''' - newtext = wikipedia.removeCategoryLinks(imagepage.get(), imagepage.site()) - + ''' Remove the old categories and add the new categories to the image. ''' + newtext = pywikibot.removeCategoryLinks(imagepage.get(), imagepage.site()) if not(onlyFilter): newtext = removeTemplates(newtext) - newtext = newtext + getCheckCategoriesTemplate(usage, galleries, len(newcats)) - + newtext = newtext + getCheckCategoriesTemplate(usage, galleries, + len(newcats)) newtext = newtext + u'\n' - for category in newcats: newtext = newtext + u'[[Category:' + category + u']]\n' - if(onlyFilter): comment = u'Filtering categories' else: comment = u'Image is categorized by a bot using data from [[Commons:Tools#CommonSense|CommonSense]]' - - wikipedia.showDiff(imagepage.get(), newtext) + pywikibot.showDiff(imagepage.get(), newtext) imagepage.put(newtext, comment) return - def removeTemplates(oldtext = u''): ''' Remove {{Uncategorized}} and {{Check categories}} templates ''' result = u'' - result = re.sub(u'\{\{\s*([Uu]ncat(egori[sz]ed( image)?)?|[Nn]ocat|[Nn]eedscategory)[^}]*\}\}', u'', oldtext) - result = re.sub(u'', u'', result) + result = re.sub( + u'\{\{\s*([Uu]ncat(egori[sz]ed( image)?)?|[Nn]ocat|[Nn]eedscategory)[^}]*\}\}', u'', oldtext) + result = re.sub(u'', + u'', result) result = re.sub(u'\{\{\s*[Cc]heck categories[^}]*\}\}', u'', result) return result @@ -337,25 +324,21 @@ Build the check categories template with all parameters ''' result = u'{{Check categories|year={{subst:CURRENTYEAR}}|month={{subst:CURRENTMONTHNAME}}|day={{subst:CURRENTDAY}}\n' - usageCounter = 1 for (lang, project, article) in usage: - result = result + u'|lang' + str(usageCounter) + u'=' + lang - result = result + u'|wiki' + str(usageCounter) + u'=' + project - result = result + u'|article' + str(usageCounter) + u'=' + article - result = result + u'\n' + result += u'|lang%d=' % (usageCounter, lang) + result += u'|wiki%d=' % (usageCounter, project) + result += u'|article%d=' % (usageCounter, article) + result += u'\n' usageCounter = usageCounter + 1 - galleryCounter = 1 for gallery in galleries: - result = result + u'|gallery' + str(galleryCounter) + u'=' + gallery.replace('_', ' ') + u'\n' + result += u'|gallery%d=%s' % (galleryCounter, gallery.replace('_', ' ')) + u'\n' galleryCounter = galleryCounter + 1 - - result = result + u'|ncats='+ str(ncats) + u'\n' - result = result + u'}}\n' + result += u'|ncats=%d\n' % ncats + result += u'}}\n' return result - def main(args): ''' Main loop. Get a generator and options. Work on all images in the generator. @@ -368,9 +351,9 @@ global search_wikis global hint_wiki - site = wikipedia.getSite(u'commons', u'commons') - wikipedia.setSite(site) - for arg in wikipedia.handleArgs(): + site = pywikibot.getSite(u'commons', u'commons') + pywikibot.setSite(site) + for arg in pywikibot.handleArgs(): if arg == '-onlyfilter': onlyFilter = True elif arg == '-onlyuncat': @@ -384,15 +367,15 @@ generator = genFactory.getCombinedGenerator() if not generator: - generator = pagegenerators.CategorizedPageGenerator(catlib.Category(site, u'Category:Media needing categories'), recurse=True) - + generator = pagegenerators.CategorizedPageGenerator( + catlib.Category(site, u'Category:Media needing categories'), + recurse=True) initLists() categorizeImages(generator, onlyFilter, onlyUncat) + pywikibot.output(u'All done') - wikipedia.output(u'All done') - if __name__ == "__main__": try: main(sys.argv[1:]) finally: - wikipedia.stopme() + pywikibot.stopme()

1 0

SVN: [8529] trunk/pywikipedia/families
by xqt＠svn.wikimedia.org 12 Sep '10

12 Sep '10

Revision: 8529 Author: xqt Date: 2010-09-12 11:41:43 +0000 (Sun, 12 Sep 2010) Log Message: ----------- update language_by_size Modified Paths: -------------- trunk/pywikipedia/families/wikipedia_family.py trunk/pywikipedia/families/wiktionary_family.py Modified: trunk/pywikipedia/families/wikipedia_family.py =================================================================== --- trunk/pywikipedia/families/wikipedia_family.py 2010-09-12 11:41:06 UTC (rev 8528) +++ trunk/pywikipedia/families/wikipedia_family.py 2010-09-12 11:41:43 UTC (rev 8529) @@ -16,7 +16,7 @@ 'eo', 'ar', 'id', 'vi', 'sr', 'vo', 'sk', 'lt', 'he', 'bg', 'fa', 'sl', 'war', 'hr', 'et', 'ms', 'new', 'simple', 'th', 'gl', 'roa-rup', 'nn', 'eu', 'hi', 'el', 'ht', 'te', 'la', 'ka', 'mk', - 'ceb', 'az', 'br', 'tl', 'sh', 'mr', 'lb', 'jv', 'lv', 'bs', 'is', + 'ceb', 'az', 'tl', 'br', 'sh', 'mr', 'lb', 'jv', 'lv', 'bs', 'is', 'cy', 'pms', 'be-x-old', 'sq', 'bpy', 'ta', 'be', 'an', 'oc', 'bn', 'sw', 'io', 'fy', 'gu', 'nds', 'lmo', 'af', 'scn', 'qu', 'ku', 'su', 'zh-yue', 'ur', 'ml', 'ast', 'nap', 'bat-smg', 'wa', 'ga', 'cv', @@ -25,7 +25,7 @@ 'kk', 'arz', 'nah', 'li', 'hsb', 'glk', 'co', 'gan', 'ia', 'mn', 'bcl', 'am', 'fiu-vro', 'nds-nl', 'tk', 'fo', 'vls', 'si', 'sa', 'bar', 'dv', 'gv', 'nrm', 'pag', 'rm', 'sco', 'my', 'map-bms', - 'diq', 'ckb', 'se', 'wuu', 'fur', 'mzn', 'lij', 'ug', 'mt', 'bh', + 'diq', 'ckb', 'se', 'wuu', 'fur', 'mzn', 'ug', 'lij', 'mt', 'bh', 'nov', 'csb', 'mg', 'sc', 'ilo', 'zh-classical', 'km', 'lad', 'pi', 'ang', 'cbk-zam', 'frp', 'bo', 'hif', 'hak', 'pa', 'kw', 'ps', 'xal', 'pdc', 'szl', 'haw', 'stq', 'ie', 'crh', 'fj', 'ee', 'kv', Modified: trunk/pywikipedia/families/wiktionary_family.py =================================================================== --- trunk/pywikipedia/families/wiktionary_family.py 2010-09-12 11:41:06 UTC (rev 8528) +++ trunk/pywikipedia/families/wiktionary_family.py 2010-09-12 11:41:43 UTC (rev 8529) @@ -13,17 +13,17 @@ self.languages_by_size = [ 'en', 'fr', 'lt', 'zh', 'tr', 'ru', 'vi', 'io', 'pl', 'pt', 'fi', 'hu', 'el', 'ko', 'no', 'ta', 'de', 'sv', 'it', 'nl', 'my', 'kn', - 'li', 'lo', 'ml', 'ja', 'es', 'ku', 'ar', 'et', 'mg', 'ro', 'id', + 'li', 'lo', 'ml', 'ja', 'es', 'ku', 'ar', 'mg', 'et', 'ro', 'id', 'te', 'gl', 'uk', 'bg', 'ca', 'vo', 'fa', 'is', 'scn', 'cs', 'sr', 'simple', 'hr', 'af', 'th', 'oc', 'fy', 'sw', 'br', 'he', 'la', 'sq', 'sl', 'hy', 'tt', 'zh-min-nan', 'da', 'wa', 'cy', 'ne', 'tk', 'ast', 'lv', 'ur', 'hsb', 'ka', 'kk', 'eo', 'ky', 'wo', 'ang', 'co', - 'hi', 'mr', 'eu', 'az', 'ga', 'gn', 'ia', 'sk', 'ms', 'csb', 'tl', + 'hi', 'eu', 'mr', 'az', 'ga', 'gn', 'ia', 'sk', 'ms', 'csb', 'tl', 'st', 'be', 'nn', 'nds', 'kl', 'sd', 'ug', 'ps', 'ti', 'mk', 'sh', - 'bn', 'an', 'si', 'gu', 'zu', 'km', 'ss', 'qu', 'ts', 'bs', 'fo', + 'bn', 'an', 'zu', 'si', 'gu', 'km', 'ss', 'qu', 'ts', 'bs', 'fo', 'am', 'rw', 'chr', 'om', 'su', 'kw', 'iu', 'mn', 'nah', 'gv', 'yi', 'ie', 'lb', 'pa', 'mt', 'gd', 'tg', 'tpi', 'dv', 'ik', 'za', 'sg', - 'so', 'roa-rup', 'uz', 'jv', 'mi', 'ln', 'sm', 'ha', 'ay', 'sa', + 'so', 'roa-rup', 'uz', 'mi', 'jv', 'ln', 'sm', 'ha', 'ay', 'sa', 'na', 'jbo', 'tn', 'fj', 'ks', 'dz', 'als', ]

1 0

SVN: [8528] branches/rewrite/pywikibot/families
by xqt＠svn.wikimedia.org 12 Sep '10

12 Sep '10

Revision: 8528 Author: xqt Date: 2010-09-12 11:41:06 +0000 (Sun, 12 Sep 2010) Log Message: ----------- update language_by_size Modified Paths: -------------- branches/rewrite/pywikibot/families/wikinews_family.py branches/rewrite/pywikibot/families/wikipedia_family.py branches/rewrite/pywikibot/families/wiktionary_family.py Modified: branches/rewrite/pywikibot/families/wikinews_family.py =================================================================== --- branches/rewrite/pywikibot/families/wikinews_family.py 2010-09-11 22:50:52 UTC (rev 8527) +++ branches/rewrite/pywikibot/families/wikinews_family.py 2010-09-12 11:41:06 UTC (rev 8528) @@ -12,7 +12,7 @@ self.languages_by_size = [ 'sr', 'en', 'pl', 'de', 'fr', 'it', 'pt', 'es', 'zh', 'ja', 'sv', - 'ru', 'fi', 'he', 'cs', 'ta', 'bg', 'ro', 'ar', 'sd', 'hu', 'no', + 'ru', 'fi', 'he', 'ta', 'cs', 'bg', 'ro', 'ar', 'sd', 'hu', 'no', 'uk', 'tr', 'ca', 'bs', 'th', 'ko', ] Modified: branches/rewrite/pywikibot/families/wikipedia_family.py =================================================================== --- branches/rewrite/pywikibot/families/wikipedia_family.py 2010-09-11 22:50:52 UTC (rev 8527) +++ branches/rewrite/pywikibot/families/wikipedia_family.py 2010-09-12 11:41:06 UTC (rev 8528) @@ -16,20 +16,20 @@ 'eo', 'ar', 'id', 'vi', 'sr', 'vo', 'sk', 'lt', 'he', 'bg', 'fa', 'sl', 'war', 'hr', 'et', 'ms', 'new', 'simple', 'th', 'gl', 'roa-rup', 'nn', 'eu', 'hi', 'el', 'ht', 'te', 'la', 'ka', 'mk', - 'ceb', 'az', 'br', 'tl', 'sh', 'mr', 'jv', 'lb', 'lv', 'bs', 'is', + 'ceb', 'az', 'tl', 'br', 'sh', 'mr', 'lb', 'jv', 'lv', 'bs', 'is', 'cy', 'pms', 'be-x-old', 'sq', 'bpy', 'ta', 'be', 'an', 'oc', 'bn', 'sw', 'io', 'fy', 'gu', 'nds', 'lmo', 'af', 'scn', 'qu', 'ku', 'su', 'zh-yue', 'ur', 'ml', 'ast', 'nap', 'bat-smg', 'wa', 'ga', 'cv', - 'ksh', 'hy', 'yo', 'kn', 'tg', 'roa-tara', 'vec', 'gd', 'yi', - 'zh-min-nan', 'uz', 'pam', 'tt', 'os', 'sah', 'pnb', 'ne', 'als', - 'mi', 'kk', 'arz', 'nah', 'li', 'hsb', 'glk', 'co', 'gan', 'ia', - 'mn', 'bcl', 'am', 'fiu-vro', 'nds-nl', 'tk', 'fo', 'vls', 'si', - 'sa', 'bar', 'dv', 'gv', 'nrm', 'pag', 'rm', 'my', 'sco', 'map-bms', - 'diq', 'ckb', 'se', 'wuu', 'fur', 'mzn', 'lij', 'ug', 'mt', 'bh', + 'ksh', 'hy', 'yo', 'kn', 'tg', 'roa-tara', 'vec', 'gd', 'yi', 'pnb', + 'zh-min-nan', 'uz', 'pam', 'tt', 'os', 'sah', 'ne', 'als', 'mi', + 'kk', 'arz', 'nah', 'li', 'hsb', 'glk', 'co', 'gan', 'ia', 'mn', + 'bcl', 'am', 'fiu-vro', 'nds-nl', 'tk', 'fo', 'vls', 'si', 'sa', + 'bar', 'dv', 'gv', 'nrm', 'pag', 'rm', 'sco', 'my', 'map-bms', + 'diq', 'ckb', 'se', 'wuu', 'fur', 'mzn', 'ug', 'lij', 'mt', 'bh', 'nov', 'csb', 'mg', 'sc', 'ilo', 'zh-classical', 'km', 'lad', 'pi', 'ang', 'cbk-zam', 'frp', 'bo', 'hif', 'hak', 'pa', 'kw', 'ps', - 'xal', 'pdc', 'szl', 'haw', 'ie', 'stq', 'crh', 'fj', 'kv', 'ee', - 'to', 'ace', 'nv', 'so', 'myv', 'gn', 'ky', 'ln', 'krc', 'ext', + 'xal', 'pdc', 'szl', 'haw', 'stq', 'ie', 'crh', 'fj', 'ee', 'kv', + 'to', 'ace', 'so', 'nv', 'myv', 'gn', 'ky', 'ln', 'krc', 'ext', 'mhr', 'arc', 'jbo', 'wo', 'eml', 'pcd', 'ay', 'kab', 'ty', 'tpi', 'pap', 'ba', 'frr', 'zea', 'srn', 'kl', 'udm', 'ig', 'ce', 'or', 'dsb', 'kg', 'lo', 'ab', 'rmy', 'cu', 'mwl', 'mdf', 'kaa', 'sm', Modified: branches/rewrite/pywikibot/families/wiktionary_family.py =================================================================== --- branches/rewrite/pywikibot/families/wiktionary_family.py 2010-09-11 22:50:52 UTC (rev 8527) +++ branches/rewrite/pywikibot/families/wiktionary_family.py 2010-09-12 11:41:06 UTC (rev 8528) @@ -13,17 +13,17 @@ self.languages_by_size = [ 'en', 'fr', 'lt', 'zh', 'tr', 'ru', 'vi', 'io', 'pl', 'pt', 'fi', 'hu', 'el', 'ko', 'no', 'ta', 'de', 'sv', 'it', 'nl', 'my', 'kn', - 'li', 'lo', 'ml', 'ja', 'es', 'ku', 'ar', 'et', 'mg', 'ro', 'id', + 'li', 'lo', 'ml', 'ja', 'es', 'ku', 'ar', 'mg', 'et', 'ro', 'id', 'te', 'gl', 'uk', 'bg', 'ca', 'vo', 'fa', 'is', 'scn', 'cs', 'sr', 'simple', 'hr', 'af', 'th', 'oc', 'fy', 'sw', 'br', 'he', 'la', 'sq', 'sl', 'hy', 'tt', 'zh-min-nan', 'da', 'wa', 'cy', 'ne', 'tk', 'ast', 'lv', 'ur', 'hsb', 'ka', 'kk', 'eo', 'ky', 'wo', 'ang', 'co', - 'hi', 'mr', 'eu', 'az', 'ga', 'gn', 'ia', 'sk', 'ms', 'csb', 'tl', + 'hi', 'eu', 'mr', 'az', 'ga', 'gn', 'ia', 'sk', 'ms', 'csb', 'tl', 'st', 'be', 'nn', 'nds', 'kl', 'sd', 'ug', 'ps', 'ti', 'mk', 'sh', - 'bn', 'an', 'si', 'gu', 'zu', 'km', 'ss', 'qu', 'ts', 'bs', 'fo', + 'bn', 'an', 'zu', 'si', 'gu', 'km', 'ss', 'qu', 'ts', 'bs', 'fo', 'am', 'rw', 'chr', 'om', 'su', 'kw', 'iu', 'mn', 'nah', 'gv', 'yi', 'ie', 'lb', 'pa', 'mt', 'gd', 'tg', 'tpi', 'dv', 'ik', 'za', 'sg', - 'so', 'roa-rup', 'uz', 'jv', 'mi', 'ln', 'sm', 'ha', 'ay', 'sa', + 'so', 'roa-rup', 'uz', 'mi', 'jv', 'ln', 'sm', 'ha', 'ay', 'sa', 'na', 'jbo', 'tn', 'fj', 'ks', 'dz', 'als', ]

1 0

SVN: [8527] trunk/pywikipedia/userlib.py
by xqt＠svn.wikimedia.org 11 Sep '10

11 Sep '10

Revision: 8527 Author: xqt Date: 2010-09-11 22:50:52 +0000 (Sat, 11 Sep 2010) Log Message: ----------- fix old sendMailOld() stuff r7479, submitted by Dr. Trigon. Thanks Modified Paths: -------------- trunk/pywikipedia/userlib.py Modified: trunk/pywikipedia/userlib.py =================================================================== --- trunk/pywikipedia/userlib.py 2010-09-11 16:45:50 UTC (rev 8526) +++ trunk/pywikipedia/userlib.py 2010-09-11 22:50:52 UTC (rev 8527) @@ -217,7 +217,7 @@ return False def sendMailOld(self, subject = u'', text = u'', ccMe = False): - addr = self.site().put_address('Special:EmailUser') + address = self.site().put_address('Special:EmailUser') predata = { "wpSubject" : subject, "wpText" : text,

1 0

SVN: [8526] trunk/pywikipedia
by xqt＠svn.wikimedia.org 11 Sep '10

11 Sep '10

Revision: 8526 Author: xqt Date: 2010-09-11 16:45:50 +0000 (Sat, 11 Sep 2010) Log Message: ----------- import wikipedia as pywikibot for merging to rewrite branch Modified Paths: -------------- trunk/pywikipedia/imagecopy.py trunk/pywikipedia/imagecopy_enwp.py trunk/pywikipedia/imagecopy_self.py Modified: trunk/pywikipedia/imagecopy.py =================================================================== --- trunk/pywikipedia/imagecopy.py 2010-09-11 16:21:58 UTC (rev 8525) +++ trunk/pywikipedia/imagecopy.py 2010-09-11 16:45:50 UTC (rev 8526) @@ -72,11 +72,13 @@ # (C) Wikipedian, Keichwa, Leogregianin, Rikwade, Misza13 2003-2007 # # New bot by: -# (C) Kyle/Orgullomoore, Siebrand Mazeland 2007 +# (C) Kyle/Orgullomoore, Siebrand Mazeland 2007-2008 # # Another rewrite by: -# (C) Multichill 2008 +# (C) Multichill 2008-2010 # +# (C) Pywikipedia bot team, 2003-2010 +# # Distributed under the terms of the MIT license. # __version__='$Id$' @@ -87,7 +89,8 @@ import urllib, httplib, urllib2 import webbrowser import time, threading -import wikipedia, config, socket +import wikipedia as pywikibot +import config, socket import pagegenerators, add_text from upload import * from image import * @@ -242,9 +245,9 @@ data = commonsHelperPage.read().decode('utf-8') gotInfo = True; except IOError: - wikipedia.output(u'Got an IOError, let\'s try again') + pywikibot.output(u'Got an IOError, let\'s try again') except socket.timeout: - wikipedia.output(u'Got a timeout, let\'s try again') + pywikibot.output(u'Got a timeout, let\'s try again') return data class imageTransfer (threading.Thread): @@ -276,7 +279,7 @@ CH=CH.split('<textarea '+tablock+'>')[1].split('</textarea>')[0] CH=CH.replace(u'×', u'×') CH = self.fixAuthor(CH) - wikipedia.output(CH); + pywikibot.output(CH); # I want every picture to be tagged with the bottemplate so i can check my contributions later. CH=u'\n\n{{BotMoveToCommons|'+ self.imagePage.site().language() + '.' + self.imagePage.site().family.name +'|year={{subst:CURRENTYEAR}}|month={{subst:CURRENTMONTHNAME}}|day={{subst:CURRENTDAY}}}}' + CH @@ -285,11 +288,11 @@ CH = CH.replace(u'{{subst:Unc}} ', u'') CH = CH + u'[[Category:' + self.category + u']]' - bot = UploadRobot(url=self.imagePage.fileUrl(), description=CH, useFilename=self.newname, keepFilename=True, verifyDescription=False, ignoreWarning = True, targetSite = wikipedia.getSite('commons', 'commons')) + bot = UploadRobot(url=self.imagePage.fileUrl(), description=CH, useFilename=self.newname, keepFilename=True, verifyDescription=False, ignoreWarning = True, targetSite = pywikibot.getSite('commons', 'commons')) bot.run() #Should check if the image actually was uploaded - if wikipedia.Page(wikipedia.getSite('commons', 'commons'), u'Image:' + self.newname).exists(): + if pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'Image:' + self.newname).exists(): #Get a fresh copy, force to get the page so we dont run into edit conflicts imtxt=self.imagePage.get(force=True) @@ -309,7 +312,7 @@ else: commentText = nowCommonsMessage['_default'] - wikipedia.showDiff(self.imagePage.get(), imtxt+addTemplate) + pywikibot.showDiff(self.imagePage.get(), imtxt+addTemplate) self.imagePage.put(imtxt + addTemplate, comment = commentText) self.gen = pagegenerators.FileLinksGenerator(self.imagePage) @@ -349,7 +352,7 @@ #-label ok skip view #textarea -archivo=wikipedia.config.datafilepath("Uploadbot.localskips.txt") +archivo=pywikibot.config.datafilepath("Uploadbot.localskips.txt") try: open(archivo, 'r') except IOError: @@ -476,7 +479,7 @@ # Load a lot of default generators genFactory = pagegenerators.GeneratorFactory() - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg == '-always': always = True elif arg.startswith('-cc:'): @@ -493,11 +496,11 @@ for page in pregenerator: skip = False if page.exists() and (page.namespace() == 6) and (not page.isRedirectPage()) : - imagepage = wikipedia.ImagePage(page.site(), page.title()) + imagepage = pywikibot.ImagePage(page.site(), page.title()) #First do autoskip. if doiskip(imagepage.get()): - wikipedia.output("Skipping " + page.title()) + pywikibot.output("Skipping " + page.title()) skip = True else: # The first upload is last in the list. @@ -508,7 +511,7 @@ (datetime, username, resolution, size, comment) = imagepage.getFileVersionHistory().pop() if always: newname=imagepage.titleWithoutNamespace() - CommonsPage=wikipedia.Page(wikipedia.getSite('commons', 'commons'), u'File:'+newname) + CommonsPage=pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:'+newname) if CommonsPage.exists(): skip = True else: @@ -518,7 +521,7 @@ (newname, skip)=Tkdialog(imagepage.titleWithoutNamespace(), imagepage.get(), username, imagepage.permalink(), imagepage.templates()).getnewname() if skip: - wikipedia.output('Skipping this image') + pywikibot.output('Skipping this image') break # Did we enter a new name? @@ -529,26 +532,26 @@ newname = newname.decode('utf-8') # Check if the image already exists - CommonsPage=wikipedia.Page( - wikipedia.getSite('commons', 'commons'), + CommonsPage=pywikibot.Page( + pywikibot.getSite('commons', 'commons'), u'File:'+newname) if not CommonsPage.exists(): break else: - wikipedia.output('Image already exists, pick another name or skip this image') + pywikibot.output('Image already exists, pick another name or skip this image') # We dont overwrite images, pick another name, go to the start of the loop if not skip: imageTransfer(imagepage, newname, category).start() - wikipedia.output(u'Still ' + str(threading.activeCount()) + u' active threads, lets wait') + pywikibot.output(u'Still ' + str(threading.activeCount()) + u' active threads, lets wait') for openthread in threading.enumerate(): if openthread != threading.currentThread(): openthread.join() - wikipedia.output(u'All threads are done') + pywikibot.output(u'All threads are done') if __name__ == "__main__": try: main(sys.argv[1:]) finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/imagecopy_enwp.py =================================================================== --- trunk/pywikipedia/imagecopy_enwp.py 2010-09-11 16:21:58 UTC (rev 8525) +++ trunk/pywikipedia/imagecopy_enwp.py 2010-09-11 16:45:50 UTC (rev 8526) @@ -42,6 +42,8 @@ # English Wikipedia specific bot by: # (C) Multichill 2010 # +# (C) Pywikipedia bot team, 2003-2010 +# # Distributed under the terms of the MIT license. # __version__='$Id$' @@ -53,7 +55,8 @@ import webbrowser from Queue import Queue import time, threading -import wikipedia, config, socket +import wikipedia as pywikibot +import config, socket import pagegenerators, add_text import imagerecat from datetime import datetime @@ -127,7 +130,8 @@ ] class Tkdialog: - def __init__(self, imagepage, description, date, source, author, licensetemplate, categories): + def __init__(self, imagepage, description, date, source, author, + licensetemplate, categories): self.root=Tk() #"%dx%d%+d%+d" % (width, height, xoffset, yoffset) #Always appear the same size and in the bottom-left corner @@ -140,7 +144,9 @@ self.old_description=Text(self.root) self.old_description.insert(END, imagepage.get().encode('utf-8')) - self.old_description.config(state=DISABLED, height=8, width=140, padx=0, pady=0, wrap=WORD, yscrollcommand=self.scrollbar.set) + self.old_description.config(state=DISABLED, height=8, width=140, padx=0, + pady=0, wrap=WORD, + yscrollcommand=self.scrollbar.set) self.scrollbar.config(command=self.old_description.yview) @@ -154,23 +160,28 @@ self.categories = categories self.skip = False - self.old_description_label=Label(self.root,text=u'The old description was : ') - self.new_description_label=Label(self.root,text=u'The new fields are : ') - self.filename_label=Label(self.root,text=u'Filename : ') - self.information_description_label=Label(self.root,text=u'Description : ') - self.information_date_label=Label(self.root,text=u'Date : ') - self.information_source_label=Label(self.root,text=u'Source : ') - self.information_author_label=Label(self.root,text=u'Author : ') - self.information_licensetemplate_label=Label(self.root,text=u'License : ') - self.information_categories_label=Label(self.root,text=u'Categories : ') + self.old_description_label = Label(self.root, + text=u'The old description was : ') + self.new_description_label = Label(self.root, + text=u'The new fields are : ') + self.filename_label = Label(self.root, text=u'Filename : ') + self.information_description_label = Label(self.root, + text=u'Description : ') + self.information_date_label = Label(self.root, text=u'Date : ') + self.information_source_label = Label(self.root, text=u'Source : ') + self.information_author_label = Label(self.root, text=u'Author : ') + self.information_licensetemplate_label = Label(self.root, + text=u'License : ') + self.information_categories_label = Label(self.root, + text=u'Categories : ') - self.filename_field=Entry(self.root) - self.information_description=Entry(self.root) - self.information_date=Entry(self.root) - self.information_source=Entry(self.root) - self.information_author=Entry(self.root) - self.information_licensetemplate=Entry(self.root) - self.information_categories=Entry(self.root) + self.filename_field = Entry(self.root) + self.information_description = Entry(self.root) + self.information_date = Entry(self.root) + self.information_source = Entry(self.root) + self.information_author = Entry(self.root) + self.information_licensetemplate = Entry(self.root) + self.information_categories = Entry(self.root) self.field_width=120 @@ -282,7 +293,7 @@ for page in self.pagegenerator: self.processImage(page) self.prefetchQueue.put(None) - wikipedia.output(u'Fetched all images.') + pywikibot.output(u'Fetched all images.') return True def processImage(self, page): @@ -290,11 +301,11 @@ Work on a single image ''' if page.exists() and (page.namespace() == 6) and (not page.isRedirectPage()): - imagepage = wikipedia.ImagePage(page.site(), page.title()) + imagepage = pywikibot.ImagePage(page.site(), page.title()) #First do autoskip. if self.doiskip(imagepage): - wikipedia.output(u'Skipping %s : Got a template on the skip list.' % page.title()) + pywikibot.output(u'Skipping %s : Got a template on the skip list.' % page.title()) return False text = imagepage.get() @@ -304,7 +315,7 @@ if match: foundMatch = True if not foundMatch: - wikipedia.output(u'Skipping %s : No suitable license template was found.' % page.title()) + pywikibot.output(u'Skipping %s : No suitable license template was found.' % page.title()) return False self.prefetchQueue.put(self.getNewFields(imagepage)) @@ -315,7 +326,7 @@ ''' for template in imagepage.templates(): if template in skipTemplates: - wikipedia.output(u'Found ' + template + u' which is on the template skip list') + pywikibot.output(u'Found ' + template + u' which is on the template skip list') return True return False @@ -333,9 +344,10 @@ return (imagepage, description, date, source, author, licensetemplate, categories) def getNewFieldsFromInformation(self, imagepage): + ''' Try to extract fields from the current information template for the + newinformation template. + ''' - Try to extract fields from the current information template for the new information template. - ''' description = u'' date = u'' source = u'' @@ -352,22 +364,29 @@ for regex in regexes: match =re.search(regex, text, re.IGNORECASE|re.DOTALL) if match: - description = self.convertLinks(match.group(u'description').strip(), imagepage.site()) + description = self.convertLinks( + match.group(u'description').strip(), imagepage.site()) date = match.group(u'date').strip() if date == u'': date = self.getUploadDate(imagepage) - source = self.getSource(imagepage, source=self.convertLinks(match.group(u'source').strip(), imagepage.site())) + source = self.getSource(imagepage, + source=self.convertLinks( + match.group(u'source').strip(), + imagepage.site())) - author = self.convertLinks(match.group(u'author').strip(), imagepage.site()) + author = self.convertLinks(match.group(u'author').strip(), + imagepage.site()) if author == u'': author = self.getAuthorText(imagepage) if u'permission' in match.groupdict(): - permission = self.convertLinks(match.group(u'permission').strip(), imagepage.site()) + permission = self.convertLinks( + match.group(u'permission').strip(), imagepage.site()) if u'other_versions' in match.groupdict(): - other_versions = self.convertLinks(match.group(u'other_versions').strip(), imagepage.site()) + other_versions = self.convertLinks( + match.group(u'other_versions').strip(), imagepage.site()) # Return the stuff we found return (description, date, source, author) @@ -389,7 +408,7 @@ for (regex, repl) in licenseTemplates: text = re.sub(regex, u'', text, re.IGNORECASE) - text = wikipedia.removeCategoryLinks(text, imagepage.site()).strip() + text = pywikibot.removeCategoryLinks(text, imagepage.site()).strip() description = self.convertLinks(text.strip(), imagepage.site()) date = self.getUploadDate(imagepage) @@ -398,9 +417,10 @@ return (description, date, source, author) def getUploadDate(self, imagepage): + ''' Get the original upload date to put in the date field of the new + information template. If we really have nothing better. + ''' - Get the original upload date to put in the date field of the new information template. If we really have nothing better. - ''' uploadtime = imagepage.getFileVersionHistory()[-1][0] uploadDatetime = datetime.strptime(uploadtime, u'%Y-%m-%dT%H:%M:%SZ') return u'{{Date|' + str(uploadDatetime.year) + u'|' + str(uploadDatetime.month) + u'|' + str(uploadDatetime.day) + u'}} (original upload date)' @@ -414,19 +434,23 @@ family = site.family.name if source==u'': source=u'{{Own}}' - - return source.strip() + u'<BR />Transferred from [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]' % {u'lang' : lang, u'family' : family} + return source.strip() + \ + u'<BR />Transferred from [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]' \ + % {u'lang' : lang, u'family' : family} def getAuthorText(self, imagepage): + ''' Get the original uploader to put in the author field of the new + information template. + ''' - Get the original uploader to put in the author field of the new information template. - ''' site = imagepage.site() lang = site.language() family = site.family.name firstuploader = self.getAuthor(imagepage) - return u'[[:%(lang)s:User:%(firstuploader)s|%(firstuploader)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]' % {u'lang' : lang, u'family' : family , u'firstuploader' : firstuploader} + return u'[[:%(lang)s:User:%(firstuploader)s|%(firstuploader)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]' \ + % {u'lang' : lang, u'family' : family , + u'firstuploader' : firstuploader} def getAuthor(self, imagepage): ''' @@ -440,13 +464,14 @@ ''' lang = sourceSite.language() family = sourceSite.family.name - conversions =[(u'\[\[([^\[\]\|]+)\|([^\[\]\|]+)\]\]', u'[[:%(lang)s:\\1|\\2]]'), + conversions =[(u'\[\[([^\[\]\|]+)\|([^\[\]\|]+)\]\]', + u'[[:%(lang)s:\\1|\\2]]'), (u'\[\[([^\[\]\|]+)\]\]', u'[[:%(lang)s:\\1|\\1]]'), ] for (regex, replacement) in conversions: - text = re.sub(regex, replacement % {u'lang' : lang, u'family' : family}, text) - + text = re.sub(regex, replacement + % {u'lang' : lang, u'family' : family}, text) return text def getNewLicensetemplate(self, imagepage): @@ -454,21 +479,18 @@ Get a license template to put on the image to be uploaded ''' text = imagepage.get() - site = imagepage.site() lang = site.language() family = site.family.name - result = u'' - for (regex, replacement) in licenseTemplates: match = re.search(regex, text, re.IGNORECASE) if match: - result = re.sub(regex, replacement, match.group(0), re.IGNORECASE) + result = re.sub(regex, replacement, match.group(0), + re.IGNORECASE) return result % {u'author' : self.getAuthor(imagepage), u'lang' : lang, u'family' : family} - return result def getNewCategories(self, imagepage): @@ -477,10 +499,11 @@ Dont forget to filter ''' result = u'' - (commonshelperCats, usage, galleries) = imagerecat.getCommonshelperCats(imagepage) + (commonshelperCats, usage, galleries) = \ + imagerecat.getCommonshelperCats(imagepage) newcats = imagerecat.applyAllFilters(commonshelperCats) for newcat in newcats: - result = result + u'[[Category:' + newcat + u']] ' + result += u'[[Category:' + newcat + u']] ' return result class userInteraction(threading.Thread): @@ -500,28 +523,32 @@ else: break self.uploadQueue.put(None) - wikipedia.output(u'User worked on all images.') + pywikibot.output(u'User worked on all images.') return True def processImage(self, fields): ''' Work on a single image ''' - (imagepage, description, date, source, author, licensetemplate, categories) = fields + (imagepage, description, date, source, author, licensetemplate, + categories) = fields while True: # Do the Tkdialog to accept/reject and change te name - (filename, description, date, source, author, licensetemplate, categories, skip)=Tkdialog(imagepage, description, date, source, author, licensetemplate, categories).getnewmetadata() + (filename, description, date, source, author, licensetemplate, + categories, skip) = Tkdialog(imagepage, description, date, source, + author, licensetemplate, categories).getnewmetadata() if skip: - wikipedia.output(u'Skipping %s : User pressed skip.' % imagepage.title()) + pywikibot.output(u'Skipping %s : User pressed skip.' + % imagepage.title()) return False # Check if the image already exists - CommonsPage=wikipedia.Page(wikipedia.getSite('commons', 'commons'), u'File:' + filename) + CommonsPage = pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:' + filename) if not CommonsPage.exists(): break else: - wikipedia.output('Image already exists, pick another name or skip this image') + pywikibot.output('Image already exists, pick another name or skip this image') # We dont overwrite images, pick another name, go to the start of the loop self.uploadQueue.put((imagepage, filename, description, date, source, author, licensetemplate, categories)) @@ -558,8 +585,8 @@ ''' (imagepage, filename, description, date, source, author, licensetemplate, categories) = fields cid = self.buildNewImageDescription(imagepage, description, date, source, author, licensetemplate, categories) - wikipedia.output(cid) - bot = UploadRobot(url=imagepage.fileUrl(), description=cid, useFilename=filename, keepFilename=True, verifyDescription=False, ignoreWarning = True, targetSite = wikipedia.getSite('commons', 'commons')) + pywikibot.output(cid) + bot = UploadRobot(url=imagepage.fileUrl(), description=cid, useFilename=filename, keepFilename=True, verifyDescription=False, ignoreWarning = True, targetSite = pywikibot.getSite('commons', 'commons')) bot.run() self.tagNowcommons(imagepage, filename) @@ -631,7 +658,7 @@ ''' Tagged the imag which has been moved to Commons for deletion. ''' - if wikipedia.Page(wikipedia.getSite('commons', 'commons'), u'File:' + filename).exists(): + if pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:' + filename).exists(): #Get a fresh copy, force to get the page so we dont run into edit conflicts imtxt=imagepage.get(force=True) @@ -651,7 +678,7 @@ else: commentText = nowCommonsMessage['_default'] - wikipedia.showDiff(imagepage.get(), imtxt + addTemplate) + pywikibot.showDiff(imagepage.get(), imtxt + addTemplate) imagepage.put(imtxt + addTemplate, comment = commentText) def replaceUsage(self, imagepage, filename): @@ -671,10 +698,10 @@ def main(args): - wikipedia.output(u'WARNING: This is an experimental bot') - wikipedia.output(u'WARNING: It will only work on self published work images') - wikipedia.output(u'WARNING: This bot is still full of bugs') - wikipedia.output(u'WARNING: Use at your own risk!') + pywikibot.output(u'WARNING: This is an experimental bot') + pywikibot.output(u'WARNING: It will only work on self published work images') + pywikibot.output(u'WARNING: This bot is still full of bugs') + pywikibot.output(u'WARNING: Use at your own risk!') generator = None; always = False @@ -683,7 +710,7 @@ # Load a lot of default generators genFactory = pagegenerators.GeneratorFactory() - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg == '-nochecktemplate': checkTemplate = False else: @@ -718,4 +745,4 @@ try: main(sys.argv[1:]) finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/imagecopy_self.py =================================================================== --- trunk/pywikipedia/imagecopy_self.py 2010-09-11 16:21:58 UTC (rev 8525) +++ trunk/pywikipedia/imagecopy_self.py 2010-09-11 16:45:50 UTC (rev 8526) @@ -1,8 +1,10 @@ # -*- coding: utf-8 -*- """ -Script to copy self published files from the English Wikipedia to Wikimedia Commons. +Script to copy self published files from the English Wikipedia to Wikimedia +Commons. -This bot is based on imagecopy.py and intended to be used to empty out http://en.wikipedia.org/wiki/Category:Self-published_work +This bot is based on imagecopy.py and intended to be used to empty out +http://en.wikipedia.org/wiki/Category:Self-published_work This bot uses a graphical interface and may not work from commandline only environment. @@ -21,10 +23,12 @@ This is a first test version and should be used with care. -Use -nochecktemplate if you don't want to add the check template. Be sure to check it yourself. +Use -nochecktemplate if you don't want to add the check template. Be sure to +check it yourself. Todo: -*Queues with threads have to be implemented for the information collecting part and for the upload part. +*Queues with threads have to be implemented for the information collecting part + and for the upload part. *Categories are now on a single line. Something like hotcat would be nice. """ @@ -42,6 +46,8 @@ # English Wikipedia specific bot by: # (C) Multichill 2010 # +# (C) Pywikipedia bot team, 2003-2010 +# # Distributed under the terms of the MIT license. # __version__='$Id$' @@ -53,7 +59,8 @@ import webbrowser from Queue import Queue import time, threading -import wikipedia, config, socket +import wikipedia as pywikibot +import config, socket import pagegenerators, add_text import imagerecat from datetime import datetime @@ -154,23 +161,28 @@ self.categories = categories self.skip = False - self.old_description_label=Label(self.root,text=u'The old description was : ') - self.new_description_label=Label(self.root,text=u'The new fields are : ') - self.filename_label=Label(self.root,text=u'Filename : ') - self.information_description_label=Label(self.root,text=u'Description : ') - self.information_date_label=Label(self.root,text=u'Date : ') - self.information_source_label=Label(self.root,text=u'Source : ') - self.information_author_label=Label(self.root,text=u'Author : ') - self.information_licensetemplate_label=Label(self.root,text=u'License : ') - self.information_categories_label=Label(self.root,text=u'Categories : ') + self.old_description_label = Label(self.root, + text=u'The old description was : ') + self.new_description_label = Label(self.root, + text=u'The new fields are : ') + self.filename_label = Label(self.root, text=u'Filename : ') + self.information_description_label = Label(self.root, + text=u'Description : ') + self.information_date_label = Label(self.root, text=u'Date : ') + self.information_source_label = Label(self.root, text=u'Source : ') + self.information_author_label = Label(self.root, text=u'Author : ') + self.information_licensetemplate_label = Label(self.root, + text=u'License : ') + self.information_categories_label = Label(self.root, + text=u'Categories : ') - self.filename_field=Entry(self.root) - self.information_description=Entry(self.root) - self.information_date=Entry(self.root) - self.information_source=Entry(self.root) - self.information_author=Entry(self.root) - self.information_licensetemplate=Entry(self.root) - self.information_categories=Entry(self.root) + self.filename_field = Entry(self.root) + self.information_description = Entry(self.root) + self.information_date = Entry(self.root) + self.information_source = Entry(self.root) + self.information_author = Entry(self.root) + self.information_licensetemplate = Entry(self.root) + self.information_categories = Entry(self.root) self.field_width=120 @@ -191,7 +203,8 @@ self.information_licensetemplate.insert(0, self.licensetemplate) self.information_categories.insert(0, self.categories) - self.browserButton=Button(self.root, text='View in browser', command=self.openInBrowser) + self.browserButton=Button(self.root, text='View in browser', + command=self.openInBrowser) self.skipButton=Button(self.root, text="Skip", command=self.skipFile) self.okButton=Button(self.root, text="OK", command=self.okFile) @@ -265,7 +278,8 @@ Activate the dialog and return the new name and if the image is skipped. ''' self.root.mainloop() - return (self.filename, self.description, self.date, self.source, self.author, self.licensetemplate, self.categories, self.skip) + return (self.filename, self.description, self.date, self.source, + self.author, self.licensetemplate, self.categories, self.skip) class imageFetcher(threading.Thread): @@ -282,19 +296,22 @@ for page in self.pagegenerator: self.processImage(page) self.prefetchQueue.put(None) - wikipedia.output(u'Fetched all images.') + pywikibot.output(u'Fetched all images.') return True def processImage(self, page): ''' Work on a single image ''' - if page.exists() and (page.namespace() == 6) and (not page.isRedirectPage()): - imagepage = wikipedia.ImagePage(page.site(), page.title()) + if page.exists() and (page.namespace() == 6) and \ + (not page.isRedirectPage()): + imagepage = pywikibot.ImagePage(page.site(), page.title()) #First do autoskip. if self.doiskip(imagepage): - wikipedia.output(u'Skipping %s : Got a template on the skip list.' % page.title()) + pywikibot.output( + u'Skipping %s : Got a template on the skip list.' + % page.title()) return False text = imagepage.get() @@ -304,7 +321,9 @@ if match: foundMatch = True if not foundMatch: - wikipedia.output(u'Skipping %s : No suitable license template was found.' % page.title()) + pywikibot.output( + u'Skipping %s : No suitable license template was found.' + % page.title()) return False self.prefetchQueue.put(self.getNewFields(imagepage)) @@ -315,7 +334,8 @@ ''' for template in imagepage.templates(): if template in skipTemplates: - wikipedia.output(u'Found ' + template + u' which is on the template skip list') + pywikibot.output( + u'Found %s which is on the template skip list' % template) return True return False @@ -345,7 +365,6 @@ author = u'' permission = u'' other_versions = u'' - contents = {} for field in fields: @@ -414,7 +433,7 @@ for (regex, repl) in licenseTemplates: text = re.sub(regex, u'', text, re.IGNORECASE) - text = wikipedia.removeCategoryLinks(text, imagepage.site()).strip() + text = pywikibot.removeCategoryLinks(text, imagepage.site()).strip() description = self.convertLinks(text.strip(), imagepage.site()) date = self.getUploadDate(imagepage) @@ -525,7 +544,7 @@ else: break self.uploadQueue.put(None) - wikipedia.output(u'User worked on all images.') + pywikibot.output(u'User worked on all images.') return True def processImage(self, fields): @@ -538,15 +557,15 @@ (filename, description, date, source, author, licensetemplate, categories, skip)=Tkdialog(imagepage, description, date, source, author, licensetemplate, categories).getnewmetadata() if skip: - wikipedia.output(u'Skipping %s : User pressed skip.' % imagepage.title()) + pywikibot.output(u'Skipping %s : User pressed skip.' % imagepage.title()) return False # Check if the image already exists - CommonsPage=wikipedia.Page(wikipedia.getSite('commons', 'commons'), u'File:' + filename) + CommonsPage=pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:' + filename) if not CommonsPage.exists(): break else: - wikipedia.output('Image already exists, pick another name or skip this image') + pywikibot.output('Image already exists, pick another name or skip this image') # We dont overwrite images, pick another name, go to the start of the loop self.uploadQueue.put((imagepage, filename, description, date, source, author, licensetemplate, categories)) @@ -583,8 +602,8 @@ ''' (imagepage, filename, description, date, source, author, licensetemplate, categories) = fields cid = self.buildNewImageDescription(imagepage, description, date, source, author, licensetemplate, categories) - wikipedia.output(cid) - bot = UploadRobot(url=imagepage.fileUrl(), description=cid, useFilename=filename, keepFilename=True, verifyDescription=False, ignoreWarning = True, targetSite = wikipedia.getSite('commons', 'commons')) + pywikibot.output(cid) + bot = UploadRobot(url=imagepage.fileUrl(), description=cid, useFilename=filename, keepFilename=True, verifyDescription=False, ignoreWarning = True, targetSite = pywikibot.getSite('commons', 'commons')) bot.run() self.tagNowcommons(imagepage, filename) @@ -656,7 +675,7 @@ ''' Tagged the imag which has been moved to Commons for deletion. ''' - if wikipedia.Page(wikipedia.getSite('commons', 'commons'), u'File:' + filename).exists(): + if pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:' + filename).exists(): #Get a fresh copy, force to get the page so we dont run into edit conflicts imtxt=imagepage.get(force=True) @@ -676,7 +695,7 @@ else: commentText = nowCommonsMessage['_default'] - wikipedia.showDiff(imagepage.get(), imtxt + addTemplate) + pywikibot.showDiff(imagepage.get(), imtxt + addTemplate) imagepage.put(imtxt + addTemplate, comment = commentText) def replaceUsage(self, imagepage, filename): @@ -696,10 +715,10 @@ def main(args): - wikipedia.output(u'WARNING: This is an experimental bot') - wikipedia.output(u'WARNING: It will only work on self published work images') - wikipedia.output(u'WARNING: This bot is still full of bugs') - wikipedia.output(u'WARNING: Use at your own risk!') + pywikibot.output(u'WARNING: This is an experimental bot') + pywikibot.output(u'WARNING: It will only work on self published work images') + pywikibot.output(u'WARNING: This bot is still full of bugs') + pywikibot.output(u'WARNING: Use at your own risk!') generator = None; always = False @@ -708,7 +727,7 @@ # Load a lot of default generators genFactory = pagegenerators.GeneratorFactory() - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg == '-nochecktemplate': checkTemplate = False else: @@ -743,4 +762,4 @@ try: main(sys.argv[1:]) finally: - wikipedia.stopme() + pywikibot.stopme()

1 0

SVN: [8525] trunk/pywikipedia
by xqt＠svn.wikimedia.org 11 Sep '10

11 Sep '10

Revision: 8525 Author: xqt Date: 2010-09-11 16:21:58 +0000 (Sat, 11 Sep 2010) Log Message: ----------- import wikipedia as pywikibot for merging to rewrite branch Modified Paths: -------------- trunk/pywikipedia/get.py trunk/pywikipedia/gui.py trunk/pywikipedia/image.py Modified: trunk/pywikipedia/get.py =================================================================== --- trunk/pywikipedia/get.py 2010-09-11 16:11:14 UTC (rev 8524) +++ trunk/pywikipedia/get.py 2010-09-11 16:21:58 UTC (rev 8525) @@ -15,22 +15,22 @@ __version__='$Id$' -import wikipedia +import wikipedia as pywikibot def main(): singlePageTitleParts = [] - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): singlePageTitleParts.append(arg) pageTitle = " ".join(singlePageTitleParts) - page = wikipedia.Page(wikipedia.getSite(), pageTitle) + page = pywikibot.Page(pywikibot.getSite(), pageTitle) # TODO: catch exceptions - wikipedia.output(page.get(), toStdout = True) + pywikibot.output(page.get(), toStdout = True) if __name__ == "__main__": try: main() finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/gui.py =================================================================== --- trunk/pywikipedia/gui.py 2010-09-11 16:11:14 UTC (rev 8524) +++ trunk/pywikipedia/gui.py 2010-09-11 16:21:58 UTC (rev 8525) @@ -7,7 +7,7 @@ # (C) Rob W.W. Hooft, 2003 # (C) Daniel Herding, 2004 # Wikiwichtel -# (C) the PyWikipediabot team, 2008 +# (C) the PyWikipediabot team, 2008-2010 # # Distributed under the terms of the MIT license. # @@ -413,15 +413,15 @@ if __name__=="__main__": - import wikipedia + import wikipedia as pywikibot try: root = Tk() root.resizable(width=FALSE, height=FALSE) root.title("Pywikipediabot GUI") - page = wikipedia.Page(wikipedia.getSite(), u'Wiki') + page = pywikibot.Page(pywikibot.getSite(), u'Wiki') content = page.get() myapp = EditBoxWindow(root) myapp.bind("<Control-d>", myapp.debug) v = myapp.edit(content, highlight = page.title()) finally: - wikipedia.stopme() + pywikibot.stopme() Modified: trunk/pywikipedia/image.py =================================================================== --- trunk/pywikipedia/image.py 2010-09-11 16:11:14 UTC (rev 8524) +++ trunk/pywikipedia/image.py 2010-09-11 16:21:58 UTC (rev 8525) @@ -1,27 +1,31 @@ # -*- coding: utf-8 -*- """ -This script can be used to change one image to another or remove an image entirely. +This script can be used to change one image to another or remove an image +entirely. Syntax: python image.py image_name [new_image_name] -If only one command-line parameter is provided then that image will be removed; if -two are provided, then the first image will be replaced by the second one on all pages. +If only one command-line parameter is provided then that image will be removed; +if two are provided, then the first image will be replaced by the second one on +all pages. Command line options: --summary: Provide a custom edit summary. If the summary includes spaces, surround - it with single quotes, such as: -summary:'My edit summary' +-summary: Provide a custom edit summary. If the summary includes spaces, + surround it with single quotes, such as: + -summary:'My edit summary' -always Don't prompt to make changes, just do them. --loose Do loose replacements. This will replace all occurences of the name of the - image (and not just explicit image syntax). This should work to catch all - instances of the image, including where it is used as a template parameter - or in image galleries. However, it can also make more mistakes. This only - works with image replacement, not image removal. +-loose Do loose replacements. This will replace all occurences of the name + of the image (and not just explicit image syntax). This should work + to catch all instances of the image, including where it is used as a + template parameter or in image galleries. However, it can also make + more mistakes. This only works with image replacement, not image + removal. Examples: -The image "FlagrantCopyvio.jpg" is about to be deleted, so let's first remove it from -everything that displays it: +The image "FlagrantCopyvio.jpg" is about to be deleted, so let's first remove it +from everything that displays it: python image.py FlagrantCopyvio.jpg @@ -34,10 +38,11 @@ # # Distributed under the terms of the MIT license. # -import wikipedia +import wikipedia as pywikibot import replace, pagegenerators import re + class ImageRobot: """ This robot will load all pages yielded by a file links image page generator and @@ -87,7 +92,8 @@ 'zh': u'機器人：移除圖像 %s', } - def __init__(self, generator, oldImage, newImage = None, summary = '', always = False, loose = False): + def __init__(self, generator, oldImage, newImage=None, summary='', + always=False, loose=False): """ Arguments: * generator - A page generator. @@ -104,13 +110,15 @@ self.loose = loose # get edit summary message - mysite = wikipedia.getSite() + mysite = pywikibot.getSite() if summary: self.editSummary = summary elif self.newImage: - self.editSummary = wikipedia.translate(mysite, self.msg_replace) % (self.oldImage, self.newImage) + self.editSummary = pywikibot.translate(mysite, self.msg_replace) \ + % (self.oldImage, self.newImage) else: - self.editSummary = wikipedia.translate(mysite, self.msg_remove) % self.oldImage + self.editSummary = pywikibot.translate(mysite, self.msg_remove) \ + % self.oldImage def run(self): """ @@ -123,13 +131,14 @@ # empty string if there are none. replacements = [] - site = wikipedia.getSite() + site = pywikibot.getSite() if not site.nocapitalize: - case = re.escape( self.oldImage[0].upper() + self.oldImage[0].lower() ) + case = re.escape(self.oldImage[0].upper() + \ + self.oldImage[0].lower()) escaped = '[' + case + ']' + re.escape(self.oldImage[1:]) else: - escaped = re.escape( self.oldImage ) + escaped = re.escape(self.oldImage) # Be careful, spaces and _ have been converted to '\ ' and '\_' escaped = re.sub('\\\\[_ ]', '[_ ]', escaped) @@ -146,9 +155,12 @@ else: replacements.append((ImageRegex, '')) - replaceBot = replace.ReplaceRobot(self.generator, replacements, acceptall = self.always, editSummary = self.editSummary) + replaceBot = replace.ReplaceRobot(self.generator, replacements, + acceptall=self.always, + editSummary=self.editSummary) replaceBot.run() + def main(): oldImage = None newImage = None @@ -156,14 +168,14 @@ always = False loose = False # read command line parameters - for arg in wikipedia.handleArgs(): + for arg in pywikibot.handleArgs(): if arg == '-always': always = True elif arg == '-loose': loose = True elif arg.startswith('-summary'): if len(arg) == len('-summary'): - summary = wikipedia.input(u'Choose an edit summary: ') + summary = pywikibot.input(u'Choose an edit summary: ') else: summary = arg[len('-summary:'):] else: @@ -171,23 +183,20 @@ newImage = arg else: oldImage = arg - if not oldImage: - wikipedia.showHelp('image') + pywikibot.showHelp('image') else: - mysite = wikipedia.getSite() + mysite = pywikibot.getSite() ns = mysite.image_namespace() - - oldImagePage = wikipedia.ImagePage(mysite, ns + ':' + oldImage) - + oldImagePage = pywikibot.ImagePage(mysite, ns + ':' + oldImage) gen = pagegenerators.FileLinksGenerator(oldImagePage) preloadingGen = pagegenerators.PreloadingGenerator(gen) - - bot = ImageRobot(preloadingGen, oldImage, newImage, summary, always, loose) + bot = ImageRobot(preloadingGen, oldImage, newImage, summary, always, + loose) bot.run() if __name__ == "__main__": try: main() finally: - wikipedia.stopme() + pywikibot.stopme()

1 0

SVN: [8524] trunk/pywikipedia/followlive.py
by xqt＠svn.wikimedia.org 11 Sep '10

11 Sep '10

Revision: 8524 Author: xqt Date: 2010-09-11 16:11:14 +0000 (Sat, 11 Sep 2010) Log Message: ----------- import wikipedia as pywikibot for merging to rewrite branch; use instance for site object in CleaningBot class Modified Paths: -------------- trunk/pywikipedia/followlive.py Modified: trunk/pywikipedia/followlive.py =================================================================== --- trunk/pywikipedia/followlive.py 2010-09-11 13:16:56 UTC (rev 8523) +++ trunk/pywikipedia/followlive.py 2010-09-11 16:11:14 UTC (rev 8524) @@ -12,7 +12,8 @@ __version__='$Id$' import sys, datetime, time, traceback -import wikipedia, editarticle +import wikipedia as pywikibot +import editarticle __metaclass__ = type @@ -325,27 +326,43 @@ # do nothing if this is in it done = { 'ar':(u'{{شطب}}', u'{{حذف}}', u'{{خرق}}'), - 'en':('{{VfD}}', '{{AfD}}', '{{AfD1}}', '{{cleanup}}', '{{nonsense}}', '{{deletedpage}}', - '{{db-reason}}', '{{notability}}', '{{not verified}}', '{{unreferenced}}', '{{db-empty}}', - '{{db-nocontext}}', '{{db-foreign}}', '{{db-notenglish}}', '{{db-nocontent}}', '{{db-blankcsd}}', - '{{db-transwiki}}', '{{db-attack}}', '{{db-band}}', '{{db-club}}', '{{db-bio}}', '{{db-bio-notenglish}}', - '{{db-inc}}', '{{db-bio-photo}}', '{{db-catempty}}', '{{db-c2}}', '{{db-catfd}}', '{{badname}}', '{{db-pagemove}}', - '{{db-nonsense}}', '{{db-spam}}', '{{db-copyvio}}', '{{db-test}}', '{{db-vandalism}}', '{{db-repost}}', '{{db-banned}}', - '{{db-histmerge}}', '{{db-move}}', '{{db-g6}}', '{{db-afd}}', '{{db-disambig}}', '{{db-authora}}', '{{db-author}}', - '{{db-blanked}}', '{{csd:g7}}', '{{db-talk}}', '{{db-botnomain}}', '{{db-redundantimage}}', '{{db-noimage}}', '{{db-noncom}}', - '{{db-ccnoncom}}', '{{db-unksource}}', '{{db-norat}}', '{{db-badfairuse}}', '{{duplicate}}', '{{db-meta}}', - '{{db-emptyportal}}', '{{db-redirnone}}', '{{db-rediruser}}', '{{db-redirtypo}}', '{{csd-c3}}', '{{cc-by-nc-sa}}', - '{{cc-nd-nc}}', '{{cc-nc}}', '{{cc-by-nc-2.0}}', '{{cc-by-nc-sa-2.0}}', '{{cc-by-nd-nc-2.0}}', '{{cc-by-2.0-nc-nd}}', - '{{cc-by-nc-nd-2.0}}', '{{db-contact}}', '{{db-i2}}', '{{db-i1}}', '{{communityuseonly}}', '{{db-disparage}}', '{{db-web}}', - '{{db-userreq}}', '{{db-nouser}}', '{{db-u3}}', '{{db-unfree}}'), + 'en':('{{VfD}}', '{{AfD}}', '{{AfD1}}', '{{cleanup}}', '{{nonsense}}', + '{{deletedpage}}', '{{db-reason}}', '{{notability}}', + '{{not verified}}', '{{unreferenced}}', '{{db-empty}}', + '{{db-nocontext}}', '{{db-foreign}}', '{{db-notenglish}}', + '{{db-nocontent}}', '{{db-blankcsd}}', '{{db-transwiki}}', + '{{db-attack}}', '{{db-band}}', '{{db-club}}', '{{db-bio}}', + '{{db-bio-notenglish}}', '{{db-inc}}', '{{db-bio-photo}}', + '{{db-catempty}}', '{{db-c2}}', '{{db-catfd}}', '{{badname}}', + '{{db-pagemove}}', '{{db-nonsense}}', '{{db-spam}}', '{{db-copyvio}}', + '{{db-test}}', '{{db-vandalism}}', '{{db-repost}}', '{{db-banned}}', + '{{db-histmerge}}', '{{db-move}}', '{{db-g6}}', '{{db-afd}}', + '{{db-disambig}}', '{{db-authora}}', '{{db-author}}', + '{{db-blanked}}', '{{csd:g7}}', '{{db-talk}}', '{{db-botnomain}}', + '{{db-redundantimage}}', '{{db-noimage}}', '{{db-noncom}}', + '{{db-ccnoncom}}', '{{db-unksource}}', '{{db-norat}}', + '{{db-badfairuse}}', '{{duplicate}}', '{{db-meta}}', + '{{db-emptyportal}}', '{{db-redirnone}}', '{{db-rediruser}}', + '{{db-redirtypo}}', '{{csd-c3}}', '{{cc-by-nc-sa}}', '{{cc-nd-nc}}', + '{{cc-nc}}', '{{cc-by-nc-2.0}}', '{{cc-by-nc-sa-2.0}}', + '{{cc-by-nd-nc-2.0}}', '{{cc-by-2.0-nc-nd}}', '{{cc-by-nc-nd-2.0}}', + '{{db-contact}}', '{{db-i2}}', '{{db-i1}}', '{{communityuseonly}}', + '{{db-disparage}}', '{{db-web}}', '{{db-userreq}}', '{{db-nouser}}', + '{{db-u3}}', '{{db-unfree}}'), 'fr':(u'{{suppression}}', u'{{à vérifier}}', u'{{ébauche}}'), 'ia':(u'{{Eliminar}}', u'{{Revision}}', u'{{Stub}}'), 'he':(u'{{מחק}}', u'{{פירושונים}}', u'{{הצבעת מחיקה}}'), 'nl':('{{nuweg}}', '{{weg}}', '{{wb}}', '{{wiu}}', '{{nocat}}'), 'pl':('{{ek}}', u'{{dopracować}}', '{{linki}}', u'{{źródła}}', u'{{stub}}'), - 'pt':('{{wikificar}}', '{{reciclar}}', '{{lixo}}', u'{{revisão}}', u'{{impróprio}}', u'{{apagar vaidade}}'), - 'sv':(u'{{radera', u'{{Radera', u'{{städa}}', u'{{stub}}', u'{{verifieras}}', u'{{språkvård}}', u'{{Källor', u'{{källor', u'{{wikify}}', u'{{Ickewiki}}', u'{{ickewiki}}', u'{{Wikify}}'), - 'zh':(u'{{VfD}}',u'{{AfD}}',u'{{unreferenced}}',u'{{db-reason}}',u'{{cleanup}}',u'{{stub}}',u'{{uncategorized}}',u'{{notability}}',u'{{copyedit}}',u'{{unreferenced}}',u'{{wikify}}',u'{{Translating}}',u'{{copyvio}}',u'{{Notchinese}}'), + 'pt':('{{wikificar}}', '{{reciclar}}', '{{lixo}}', u'{{revisão}}', + u'{{impróprio}}', u'{{apagar vaidade}}'), + 'sv':(u'{{radera', u'{{Radera', u'{{städa}}', u'{{stub}}', + u'{{verifieras}}', u'{{språkvård}}', u'{{Källor', u'{{källor', + u'{{wikify}}', u'{{Ickewiki}}', u'{{ickewiki}}', u'{{Wikify}}'), + 'zh':(u'{{VfD}}', u'{{AfD}}', u'{{unreferenced}}', u'{{db-reason}}', + u'{{cleanup}}', u'{{stub}}', u'{{uncategorized}}', u'{{notability}}', + u'{{copyedit}}', u'{{unreferenced}}', u'{{wikify}}', + u'{{Translating}}',u'{{copyvio}}',u'{{Notchinese}}'), } # TODO: merge 'done' with 'templates' above @@ -362,9 +379,9 @@ # Display informations about an article def showpageinfo(self): - wikipedia.output(u'[[%s]] %s ' % (self.page.title(), self.date)) + pywikibot.output(u'[[%s]] %s ' % (self.page.title(), self.date)) print 'Length: %i bytes' % self.length - wikipedia.output(u'User : %s' % self.user) + pywikibot.output(u'User : %s' % self.user) def couldbebad(self): return self.length < 250 or not self.loggedIn @@ -372,30 +389,32 @@ def handlebadpage(self): try: self.content = self.page.get() - except wikipedia.IsRedirectPage: - wikipedia.output(u'Already redirected, skipping.') + except pywikibot.IsRedirectPage: + pywikibot.output(u'Already redirected, skipping.') return - except wikipedia.NoPage: - wikipedia.output(u'Already deleted') + except pywikibot.NoPage: + pywikibot.output(u'Already deleted') return - for d in wikipedia.translate(wikipedia.getSite(), done): + for d in pywikibot.translate(pywikibot.getSite(), done): if d in self.content: - wikipedia.output(u'Found: "%s" in content, nothing necessary'%d) + pywikibot.output( + u'Found: "%s" in content, nothing necessary' % d) return print "---- Start content ----------------" - wikipedia.output(u""+self.content) + pywikibot.output(u"%s" % self.content) print "---- End of content ---------------" # Loop other user answer answered = False while not answered: - answer = wikipedia.input(question) + answer = pywikibot.input(question) if answer == 'q': sys.exit("Exiting") if answer == 'd': - wikipedia.output(u'Trying to delete page [[%s]].' % self.page.title()) + pywikibot.output(u'Trying to delete page [[%s]].' + % self.page.title()) self.page.delete() return if answer == 'e': @@ -404,14 +423,17 @@ editor = editarticle.TextEditor() text = editor.edit(self.page.get()) if oldText != text: - wikipedia.showDiff(oldText, text) - msg = wikipedia.input(u'Summary message:') + pywikibot.showDiff(oldText, text) + msg = pywikibot.input(u'Summary message:') self.page.put(text, msg) return if answer == 'b': - wikipedia.output(u'Blanking page [[%s]].' % self.page.title()) + pywikibot.output(u'Blanking page [[%s]].' % self.page.title()) try: - self.page.put('', comment = wikipedia.translate(wikipedia.getSite(), blanking) % self.content ) + self.page.put('', + comment=pywikibot.translate( + pywikibot.getSite(), blanking) + % self.content) except EditConflict: print "An edit conflict occured ! Automatically retrying" handlebadpage(self) @@ -426,14 +448,14 @@ choices=answer[1:].split(',') except ValueError: # User entered wrong value - wikipedia.output(u'ERROR: "%s" is not valid' % answer) + pywikibot.output(u'ERROR: "%s" is not valid' % answer) continue else: try: choices=answer.split(',') except ValueError: # User entered wrong value - wikipedia.output(u'ERROR: "%s" is not valid' % answer) + pywikibot.output(u'ERROR: "%s" is not valid' % answer) continue #test input for choice in choices: @@ -444,27 +466,30 @@ else: answered=x in range(1,len(questionlist)+1) if not answered: - wikipedia.output(u'ERROR: "%s" is not valid' % answer) + pywikibot.output(u'ERROR: "%s" is not valid' % answer) continue summary = u'' for choice in choices: answer = int(choice) # grab the template parameters - tpl = wikipedia.translate(wikipedia.getSite(), templates)[questionlist[answer]] + tpl = pywikibot.translate(pywikibot.getSite(), templates) \ + [questionlist[answer]] if tpl['pos'] == 'top': - wikipedia.output(u'prepending %s...' % questionlist[answer]) + pywikibot.output(u'prepending %s...' % questionlist[answer]) self.content = questionlist[answer] + '\n' + self.content elif tpl['pos'] == 'bottom': - wikipedia.output(u'appending %s...' % questionlist[answer]) + pywikibot.output(u'appending %s...' % questionlist[answer]) self.content += '\n' + questionlist[answer] else: - wikipedia.output(u'ERROR: "pos" should be "top" or "bottom" for template %s. Contact a developer.' % questionlist[answer]) + pywikibot.output( + u'ERROR: "pos" should be "top" or "bottom" for template %s. Contact a developer.' + % questionlist[answer]) sys.exit("Exiting") summary += tpl['msg']+' ' - wikipedia.output(u'Probably added %s' % questionlist[answer]) -# wikipedia.output(newcontent) bug #2986247 + pywikibot.output(u'Probably added %s' % questionlist[answer]) +# pywikibot.output(newcontent) bug #2986247 self.page.put(self.content, comment = summary) - wikipedia.output(u'with comment %s\n' % summary) + pywikibot.output(u'with comment %s\n' % summary) def run(self): self.showpageinfo() @@ -472,7 +497,7 @@ print 'Integrity of page doubtful...' try: self.handlebadpage() - except wikipedia.NoPage: + except pywikibot.NoPage: print 'seems already gone' print '----- Current time:', datetime.datetime.now() @@ -480,19 +505,21 @@ class CleaningBot: def __init__(self, site=None): if site is None: - site = wikipedia.getSite() + site = pywikibot.getSite() self.site = site def run(self): - for (page, date, length, loggedIn, username, comment) in wikipedia.getSite().newpages(100, repeat = True): - handler = PageHandler(page, date, length, loggedIn, username, comment) + for (page, date, length, loggedIn, username, comment) in \ + self.site.newpages(100, repeat=True): + handler = PageHandler(page, date, length, loggedIn, username, + comment) handler.run() # Generate the question text i = 0 questions = '\n' questionlist = {} -for t in wikipedia.translate(wikipedia.getSite(), templates): +for t in pywikibot.translate(pywikibot.getSite(), templates): i+=1 questions += ( u'%s) %s\n' % (i,t) ) questionlist[i] = t @@ -501,10 +528,11 @@ # MAIN if __name__ == "__main__": try: - for arg in wikipedia.handleArgs(): - wikipedia.output(u'Warning: argument "%s" not understood; ignoring.' % arg) + for arg in pywikibot.handleArgs(): + pywikibot.output( + u'Warning: argument "%s" not understood; ignoring.' % arg) bot = CleaningBot() bot.run() except: - wikipedia.stopme() + pywikibot.stopme() raise

1 0

SVN: [8523] trunk/pywikipedia/families
by xqt＠svn.wikimedia.org 11 Sep '10

11 Sep '10

Revision: 8523 Author: xqt Date: 2010-09-11 13:16:56 +0000 (Sat, 11 Sep 2010) Log Message: ----------- update namespace alias Modified Paths: -------------- trunk/pywikipedia/families/wikinews_family.py trunk/pywikipedia/families/wikipedia_family.py Modified: trunk/pywikipedia/families/wikinews_family.py =================================================================== --- trunk/pywikipedia/families/wikinews_family.py 2010-09-11 10:55:00 UTC (rev 8522) +++ trunk/pywikipedia/families/wikinews_family.py 2010-09-11 13:16:56 UTC (rev 8523) @@ -12,7 +12,7 @@ self.languages_by_size = [ 'sr', 'en', 'pl', 'de', 'fr', 'it', 'pt', 'es', 'zh', 'ja', 'sv', - 'ru', 'fi', 'he', 'cs', 'ta', 'bg', 'ro', 'ar', 'sd', 'hu', 'no', + 'ru', 'fi', 'he', 'ta', 'cs', 'bg', 'ro', 'ar', 'sd', 'hu', 'no', 'uk', 'tr', 'ca', 'bs', 'th', 'ko', ] @@ -51,6 +51,7 @@ 'ro': u'Wikiştiri', 'ru': u'Викиновости', 'sr': u'Викивести', + 'ta': u'விக்கிசெய்தி', 'th': u'วิกิข่าว', 'tr': u'Vikihaber', 'uk': u'ВікіНовини', @@ -81,7 +82,7 @@ 'sd': u'Wikinews بحث', 'sr': u'Разговор о Викивестима', 'sv': u'Wikinewsdiskussion', - 'ta': u'Wikinews பேச்சு', + 'ta': u'விக்கிசெய்தி பேச்சு', 'th': u'คุยเรื่องวิกิข่าว', 'tr': u'Vikihaber tartışma', 'uk': u'Обговорення ВікіНовини', Modified: trunk/pywikipedia/families/wikipedia_family.py =================================================================== --- trunk/pywikipedia/families/wikipedia_family.py 2010-09-11 10:55:00 UTC (rev 8522) +++ trunk/pywikipedia/families/wikipedia_family.py 2010-09-11 13:16:56 UTC (rev 8523) @@ -16,20 +16,20 @@ 'eo', 'ar', 'id', 'vi', 'sr', 'vo', 'sk', 'lt', 'he', 'bg', 'fa', 'sl', 'war', 'hr', 'et', 'ms', 'new', 'simple', 'th', 'gl', 'roa-rup', 'nn', 'eu', 'hi', 'el', 'ht', 'te', 'la', 'ka', 'mk', - 'ceb', 'az', 'br', 'tl', 'sh', 'mr', 'jv', 'lb', 'lv', 'bs', 'is', + 'ceb', 'az', 'br', 'tl', 'sh', 'mr', 'lb', 'jv', 'lv', 'bs', 'is', 'cy', 'pms', 'be-x-old', 'sq', 'bpy', 'ta', 'be', 'an', 'oc', 'bn', 'sw', 'io', 'fy', 'gu', 'nds', 'lmo', 'af', 'scn', 'qu', 'ku', 'su', 'zh-yue', 'ur', 'ml', 'ast', 'nap', 'bat-smg', 'wa', 'ga', 'cv', - 'ksh', 'hy', 'yo', 'kn', 'tg', 'roa-tara', 'vec', 'gd', 'yi', - 'zh-min-nan', 'uz', 'pam', 'tt', 'os', 'sah', 'pnb', 'ne', 'als', - 'mi', 'kk', 'arz', 'nah', 'li', 'hsb', 'glk', 'co', 'gan', 'ia', - 'mn', 'bcl', 'am', 'fiu-vro', 'nds-nl', 'tk', 'fo', 'vls', 'si', - 'sa', 'bar', 'dv', 'gv', 'nrm', 'pag', 'rm', 'my', 'sco', 'map-bms', + 'ksh', 'hy', 'yo', 'kn', 'tg', 'roa-tara', 'vec', 'gd', 'yi', 'pnb', + 'zh-min-nan', 'uz', 'pam', 'tt', 'os', 'sah', 'ne', 'als', 'mi', + 'kk', 'arz', 'nah', 'li', 'hsb', 'glk', 'co', 'gan', 'ia', 'mn', + 'bcl', 'am', 'fiu-vro', 'nds-nl', 'tk', 'fo', 'vls', 'si', 'sa', + 'bar', 'dv', 'gv', 'nrm', 'pag', 'rm', 'sco', 'my', 'map-bms', 'diq', 'ckb', 'se', 'wuu', 'fur', 'mzn', 'lij', 'ug', 'mt', 'bh', 'nov', 'csb', 'mg', 'sc', 'ilo', 'zh-classical', 'km', 'lad', 'pi', 'ang', 'cbk-zam', 'frp', 'bo', 'hif', 'hak', 'pa', 'kw', 'ps', - 'xal', 'pdc', 'szl', 'haw', 'ie', 'stq', 'crh', 'fj', 'kv', 'ee', - 'to', 'ace', 'nv', 'so', 'myv', 'gn', 'ky', 'ln', 'krc', 'ext', + 'xal', 'pdc', 'szl', 'haw', 'stq', 'ie', 'crh', 'fj', 'ee', 'kv', + 'to', 'ace', 'so', 'nv', 'myv', 'gn', 'ky', 'ln', 'krc', 'ext', 'mhr', 'arc', 'jbo', 'wo', 'eml', 'pcd', 'ay', 'kab', 'ty', 'tpi', 'pap', 'ba', 'frr', 'zea', 'srn', 'kl', 'udm', 'ig', 'ce', 'or', 'dsb', 'kg', 'lo', 'ab', 'rmy', 'cu', 'mwl', 'mdf', 'kaa', 'sm', @@ -592,7 +592,7 @@ 'hr': u'Razgovor o dodatku', 'ia': u'Discussion Appendice', 'it': u'Discussioni progetto', - 'ja': u'ノート‐プロジェクト', + 'ja': u'プロジェクト‐ノート', 'lmo': u'Descüssiun Purtaal', 'lt': u'Vikiprojekto aptarimas', 'lv': u'Vikiprojekta diskusija',

1 0

SVN: [8522] trunk/pywikipedia/
by xqt＠svn.wikimedia.org 11 Sep '10

11 Sep '10

Revision: 8522 Author: xqt Date: 2010-09-11 10:55:00 +0000 (Sat, 11 Sep 2010) Log Message: ----------- ignore *.bak Property Changed: ---------------- trunk/pywikipedia/ Property changes on: trunk/pywikipedia ___________________________________________________________________ Modified: svn:ignore - *.pyc *.pyo *.log *.dump *.dump.bz2 *.txt user-config.py autonomous_problems.dat sax_parse_bug.dat login-data password-file user-fixes.py + *.pyc *.pyo *.log *.dump *.dump.bz2 *.txt *.bak user-config.py autonomous_problems.dat sax_parse_bug.dat login-data password-file user-fixes.py

1 0

SVN: [8521] trunk/pywikipedia/commonscat.py
by xqt＠svn.wikimedia.org 11 Sep '10

11 Sep '10

Revision: 8521 Author: xqt Date: 2010-09-11 10:49:44 +0000 (Sat, 11 Sep 2010) Log Message: ----------- be-x-old ignore template submitted by zedlik (patch bug #3064024). Thanks Modified Paths: -------------- trunk/pywikipedia/commonscat.py Modified: trunk/pywikipedia/commonscat.py =================================================================== --- trunk/pywikipedia/commonscat.py 2010-09-11 10:40:05 UTC (rev 8520) +++ trunk/pywikipedia/commonscat.py 2010-09-11 10:49:44 UTC (rev 8521) @@ -121,6 +121,7 @@ ignoreTemplates = { 'af' : [u'commons'], 'ar' : [u'تحويلة تصنيف', u'كومنز', u'كومونز', u'Commons'], + 'be-x-old' : [u'Commons'], 'cs' : [u'Commons', u'Sestřičky', u'Sisterlinks'], 'da' : [u'Commons', u'Commons left', u'Commons2', u'Commonsbilleder', u'Commonscat left', u'Commonscat2', u'GalleriCommons',

1 0

← Newer
1
...
5
6
7
8
9
10
11
12
13
Older →

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

Pywikipedia-svn September 2010