Pywikipedia-svn June 2010

pywikipedia-svn@lists.wikimedia.org

8 participants
109 discussions

SVN: [8290] trunk/pywikipedia/interwiki.py
by xqt＠svn.wikimedia.org 14 Jun '10

14 Jun '10

Revision: 8290 Author: xqt Date: 2010-06-14 11:23:38 +0000 (Mon, 14 Jun 2010) Log Message: ----------- edit restrictions for is-wiki Modified Paths: -------------- trunk/pywikipedia/interwiki.py Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2010-06-14 09:34:19 UTC (rev 8289) +++ trunk/pywikipedia/interwiki.py 2010-06-14 11:23:38 UTC (rev 8290) @@ -1064,13 +1064,12 @@ if page == self.originPage: try: pywikibot.output(u"%s has a backlink from %s." - % (page, linkingPage)) + % (page.aslink(), linkingPage.aslink())) except UnicodeDecodeError: pywikibot.output(u"Found a backlink for a page.") self.makeForcedStop(counter) return False - if page in self.foundIn: # not new self.foundIn[page].append(linkingPage) @@ -1574,6 +1573,17 @@ 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: @@ -1618,7 +1628,8 @@ for siteCode in lclSite.family.languages_by_size: site = pywikibot.getSite(code = siteCode) - if (not lclSiteDone and site == lclSite) or (not frgnSiteDone and site != lclSite and site in new): + if (not lclSiteDone and site == lclSite) or \ + (not frgnSiteDone and site != lclSite and site in new): if site == lclSite: lclSiteDone = True # even if we fail the update if site.family.name in config.usernames and site.lang in config.usernames[site.family.name]: @@ -1631,16 +1642,23 @@ notUpdatedSites.append(site) except GiveUpOnPage: break - elif not globalvar.strictlimittwo and site in new and site != lclSite: + elif not globalvar.strictlimittwo and site in new \ + and site != lclSite: old={} try: for page in new[site].interwiki(): old[page.site()] = page except pywikibot.NoPage: - pywikibot.output(u"BUG>>> %s no longer exists?" % new[site].aslink(True)) + pywikibot.output(u"BUG>>> %s no longer exists?" + % new[site].aslink(True)) continue - mods, mcomment, adding, removing, modifying = compareLanguages(old, new, insite = lclSite) - if (len(removing) > 0 and not globalvar.autonomous) or (len(modifying) > 0 and self.problemfound) or len(old) == 0 or (globalvar.needlimit and len(adding) + len(modifying) >= globalvar.needlimit +1): + mods, mcomment, adding, removing, modifying \ + = compareLanguages(old, new, insite = lclSite) + if (len(removing) > 0 and not globalvar.autonomous) or \ + (len(modifying) > 0 and self.problemfound) or \ + len(old) == 0 or \ + (globalvar.needlimit and \ + len(adding) + len(modifying) >= globalvar.needlimit +1): try: if self.replaceLinks(new[site], new, bot): updatedSites.append(site) @@ -1652,8 +1670,48 @@ 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 self.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) + smallWikiAllowed = 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]: + if site.family.name in config.usernames \ + and site.lang in config.usernames[site.family.name] \ + and smallWikiAllowed: # Try to do the changes try: if self.replaceLinks(page, new, bot):

1 0

SVN: [8289] trunk/pywikipedia/copyright_clean.py
by xqt＠svn.wikimedia.org 14 Jun '10

14 Jun '10

Revision: 8289 Author: xqt Date: 2010-06-14 09:34:19 +0000 (Mon, 14 Jun 2010) Log Message: ----------- bugfix for #3015645 (2nd Part) coming with r7131 Modified Paths: -------------- trunk/pywikipedia/copyright_clean.py Modified: trunk/pywikipedia/copyright_clean.py =================================================================== --- trunk/pywikipedia/copyright_clean.py 2010-06-14 09:24:42 UTC (rev 8288) +++ trunk/pywikipedia/copyright_clean.py 2010-06-14 09:34:19 UTC (rev 8289) @@ -120,7 +120,7 @@ for s in mysplit(query.ListToParam(titles), 50, "|"): query_results_titles.append(query_api({'titles': s,})) for s in mysplit(query.ListToParam(revids), 50, "|"): - query_results_revids.append(query_api({'revids': ,})) + query_results_revids.append(query_api({'revids': s,})) comment_entry = list() add_separator = False

1 0

SVN: [8288] branches/rewrite/scripts/template.py
by xqt＠svn.wikimedia.org 14 Jun '10

14 Jun '10

Revision: 8288 Author: xqt Date: 2010-06-14 09:24:42 +0000 (Mon, 14 Jun 2010) Log Message: ----------- update fa-translations from trunk r8212 Modified Paths: -------------- branches/rewrite/scripts/template.py Modified: branches/rewrite/scripts/template.py =================================================================== --- branches/rewrite/scripts/template.py 2010-06-14 09:13:58 UTC (rev 8287) +++ branches/rewrite/scripts/template.py 2010-06-14 09:24:42 UTC (rev 8288) @@ -149,6 +149,7 @@ 'de':u'Bot: Ändere Vorlage: %s', 'en':u'Robot: Changing template: %s', 'es':u'Robot: Cambiada la plantilla: %s', + 'fa':u'ربات:تعییر تلگو: %s', 'fi':u'Botti korvasi mallineen: %s', 'fr':u'Robot : Change modèle: %s', 'he':u'בוט: משנה תבנית: %s', @@ -175,6 +176,7 @@ 'de':u'Bot: Ändere Vorlagen: %s', 'en':u'Robot: Changing templates: %s', 'es':u'Robot: Cambiando las plantillas: %s', + 'fa':u'ربات:تغییر الگوها: %s', 'fi':u'Botti korvasi mallineet: %s', 'fr':u'Robot : Modifie modèles %s', 'he':u'בוט: משנה תבניות: %s', @@ -198,6 +200,7 @@ 'de':u'Bot: Entferne Vorlage: %s', 'en':u'Robot: Removing template: %s', 'es':u'Robot: Retirando la plantilla: %s', + 'fa':u'ربات:حذف الگو: %s', 'fi':u'Botti poisti mallineen: %s', 'fr':u'Robot : Enlève le modèle: %s', 'he':u'בוט: מסיר תבנית: %s', @@ -224,6 +227,7 @@ 'de':u'Bot: Entferne Vorlagen: %s', 'en':u'Robot: Removing templates: %s', 'es':u'Robot: Retirando las plantillas: %s', + 'fa':u'ربات:حذف الگوها: %s', 'fi':u'Botti poisti mallineet: %s', 'he':u'בוט: מסיר תבניות: %s', 'fr':u'Robot : Enlève modèles : %s', @@ -248,6 +252,7 @@ 'de':u'Bot: Umgehe Vorlage: %s', 'en':u'Robot: Substituting template: %s', 'es':u'Robot: Sustituyendo la plantilla: %s', + 'fa':u'ربات:استفاده از دستور جا: برای الگو: %s', 'fi':u'Botti substasi mallineen: %s', 'fr':u'Robot : Remplace modèle : %s', 'he':u'בוט: מכליל תבנית בקוד הדף: %s', @@ -270,6 +275,7 @@ 'de':u'Bot: Umgehe Vorlagen: %s', 'en':u'Robot: Substituting templates: %s', 'es':u'Robot: Sustituyendo las plantillas: %s', + 'fa':u'ربات:استفاده از دستور جا: برای الگوهای : %s', 'fi':u'Botti substasi mallineet: %s', 'fr':u'Robot : Remplace modèles : %s', 'he':u'בוט: מכליל תבניות בקוד הדף: %s',

1 0

SVN: [8287] branches/rewrite/pywikibot/families/wikipedia_family.py
by xqt＠svn.wikimedia.org 14 Jun '10

14 Jun '10

Revision: 8287 Author: xqt Date: 2010-06-14 09:13:58 +0000 (Mon, 14 Jun 2010) Log Message: ----------- update family file from trunk r8286 Modified Paths: -------------- branches/rewrite/pywikibot/families/wikipedia_family.py Modified: branches/rewrite/pywikibot/families/wikipedia_family.py =================================================================== --- branches/rewrite/pywikibot/families/wikipedia_family.py 2010-06-14 09:11:12 UTC (rev 8286) +++ branches/rewrite/pywikibot/families/wikipedia_family.py 2010-06-14 09:13:58 UTC (rev 8287) @@ -15,27 +15,27 @@ 'zh', 'no', 'ca', 'fi', 'uk', 'cs', 'hu', 'tr', 'ro', 'ko', 'eo', 'da', 'ar', 'id', 'vi', 'vo', 'sr', 'sk', 'lt', 'he', 'bg', 'fa', 'sl', 'hr', 'et', 'war', 'new', 'ms', 'simple', 'th', 'gl', 'nn', - 'eu', 'hi', 'el', 'ht', 'te', 'ka', 'ceb', 'roa-rup', 'mk', 'la', - 'az', 'br', 'sh', 'lb', 'bs', 'jv', 'mr', 'is', 'lv', 'tl', 'cy', + 'eu', 'hi', 'el', 'ht', 'te', 'ka', 'roa-rup', 'ceb', 'mk', 'la', + 'az', 'br', 'sh', 'lb', 'bs', 'mr', 'jv', 'is', 'lv', 'tl', 'cy', 'pms', 'sq', 'be-x-old', 'bpy', 'ta', 'oc', 'bn', 'an', 'be', 'io', 'sw', 'fy', 'nds', 'scn', 'af', 'qu', 'gu', 'lmo', 'su', 'zh-yue', 'ast', 'ur', 'nap', 'ku', 'ml', 'bat-smg', 'wa', 'cv', 'ksh', 'ga', 'hy', 'tg', 'yo', 'roa-tara', 'vec', 'kn', 'gd', 'yi', 'uz', 'pam', - 'os', 'zh-min-nan', 'sah', 'mi', 'tt', 'als', 'kk', 'nah', 'li', - 'arz', 'hsb', 'glk', 'co', 'gan', 'ia', 'bcl', 'ne', 'mn', 'pnb', + 'os', 'zh-min-nan', 'sah', 'mi', 'tt', 'als', 'kk', 'arz', 'nah', + 'li', 'hsb', 'glk', 'co', 'gan', 'ia', 'ne', 'bcl', 'mn', 'pnb', 'fiu-vro', 'nds-nl', 'vls', 'am', 'fo', 'tk', 'sa', 'si', 'dv', - 'bar', 'nrm', 'pag', 'rm', 'gv', 'map-bms', 'my', 'sco', 'diq', + 'bar', 'nrm', 'pag', 'gv', 'rm', 'map-bms', 'my', 'sco', 'diq', 'se', 'wuu', 'fur', 'lij', 'ug', 'bh', 'mt', 'nov', 'mzn', 'csb', - 'ilo', 'zh-classical', 'km', 'pi', 'lad', 'mg', 'sc', 'ang', 'frp', - 'hif', 'bo', 'kw', 'ckb', 'hak', 'pdc', 'haw', 'szl', 'ps', 'pa', - 'xal', 'ie', 'fj', 'kv', 'crh', 'to', 'stq', 'myv', 'ace', 'gn', - 'ln', 'cbk-zam', 'krc', 'nv', 'ky', 'mhr', 'ext', 'arc', 'jbo', - 'wo', 'ty', 'so', 'eml', 'kab', 'tpi', 'pap', 'zea', 'srn', 'ay', - 'ba', 'or', 'ig', 'dsb', 'kl', 'ce', 'kg', 'udm', 'lo', 'rmy', 'cu', - 'ab', 'mwl', 'pcd', 'kaa', 'sm', 'av', 'ks', 'tet', 'got', 'mdf', + 'mg', 'ilo', 'zh-classical', 'km', 'pi', 'lad', 'sc', 'ang', 'frp', + 'bo', 'hif', 'kw', 'ckb', 'hak', 'pdc', 'haw', 'szl', 'xal', 'ps', + 'pa', 'ie', 'fj', 'kv', 'crh', 'to', 'stq', 'myv', 'ace', 'gn', + 'ln', 'cbk-zam', 'krc', 'nv', 'ky', 'mhr', 'ext', 'ty', 'arc', + 'jbo', 'wo', 'so', 'eml', 'kab', 'tpi', 'pap', 'zea', 'srn', 'ay', + 'ba', 'or', 'ig', 'dsb', 'kl', 'ce', 'udm', 'kg', 'lo', 'rmy', 'cu', + 'ab', 'pcd', 'mwl', 'kaa', 'sm', 'av', 'ks', 'tet', 'mdf', 'got', 'sd', 'na', 'bm', 'pnt', 'pih', 'iu', 'cdo', 'as', 'bug', 'ee', - 'chr', 'om', 'bi', 'zu', 'za', 'ti', 'ts', 'ss', 've', 'ha', 'sg', - 'dz', 'ch', 'cr', 'xh', 'ak', 'ik', 'lbe', 'ki', 'tn', 'bxr', 'rw', + 'chr', 'bi', 'om', 'zu', 'za', 'ti', 'ts', 'ss', 've', 'ha', 'dz', + 'sg', 'ch', 'bxr', 'cr', 'xh', 'ak', 'ik', 'lbe', 'ki', 'tn', 'rw', 'st', 'tw', 'ny', 'sn', 'chy', 'ff', 'lg', 'rn', 'tum', ]

1 0

SVN: [8286] trunk/pywikipedia/families/wikipedia_family.py
by xqt＠svn.wikimedia.org 14 Jun '10

14 Jun '10

Revision: 8286 Author: xqt Date: 2010-06-14 09:11:12 +0000 (Mon, 14 Jun 2010) Log Message: ----------- portal namespace for af-wiki; update language_by_size Modified Paths: -------------- trunk/pywikipedia/families/wikipedia_family.py Modified: trunk/pywikipedia/families/wikipedia_family.py =================================================================== --- trunk/pywikipedia/families/wikipedia_family.py 2010-06-14 08:58:08 UTC (rev 8285) +++ trunk/pywikipedia/families/wikipedia_family.py 2010-06-14 09:11:12 UTC (rev 8286) @@ -15,27 +15,27 @@ 'zh', 'no', 'ca', 'fi', 'uk', 'cs', 'hu', 'tr', 'ro', 'ko', 'eo', 'da', 'ar', 'id', 'vi', 'vo', 'sr', 'sk', 'lt', 'he', 'bg', 'fa', 'sl', 'hr', 'et', 'war', 'new', 'ms', 'simple', 'th', 'gl', 'nn', - 'eu', 'hi', 'el', 'ht', 'te', 'ka', 'ceb', 'roa-rup', 'mk', 'la', - 'az', 'br', 'sh', 'lb', 'bs', 'jv', 'mr', 'is', 'lv', 'tl', 'cy', + 'eu', 'hi', 'el', 'ht', 'te', 'ka', 'roa-rup', 'ceb', 'mk', 'la', + 'az', 'br', 'sh', 'lb', 'bs', 'mr', 'jv', 'is', 'lv', 'tl', 'cy', 'pms', 'sq', 'be-x-old', 'bpy', 'ta', 'oc', 'bn', 'an', 'be', 'io', 'sw', 'fy', 'nds', 'scn', 'af', 'qu', 'gu', 'lmo', 'su', 'zh-yue', 'ast', 'ur', 'nap', 'ku', 'ml', 'bat-smg', 'wa', 'cv', 'ksh', 'ga', 'hy', 'tg', 'yo', 'roa-tara', 'vec', 'kn', 'gd', 'yi', 'uz', 'pam', - 'os', 'zh-min-nan', 'sah', 'mi', 'tt', 'als', 'kk', 'nah', 'li', - 'arz', 'hsb', 'glk', 'co', 'gan', 'ia', 'bcl', 'ne', 'mn', 'pnb', + 'os', 'zh-min-nan', 'sah', 'mi', 'tt', 'als', 'kk', 'arz', 'nah', + 'li', 'hsb', 'glk', 'co', 'gan', 'ia', 'ne', 'bcl', 'mn', 'pnb', 'fiu-vro', 'nds-nl', 'vls', 'am', 'fo', 'tk', 'sa', 'si', 'dv', - 'bar', 'nrm', 'pag', 'rm', 'gv', 'map-bms', 'my', 'sco', 'diq', + 'bar', 'nrm', 'pag', 'gv', 'rm', 'map-bms', 'my', 'sco', 'diq', 'se', 'wuu', 'fur', 'lij', 'ug', 'bh', 'mt', 'nov', 'mzn', 'csb', - 'ilo', 'zh-classical', 'km', 'pi', 'lad', 'mg', 'sc', 'ang', 'frp', - 'hif', 'bo', 'kw', 'ckb', 'hak', 'pdc', 'haw', 'szl', 'ps', 'pa', - 'xal', 'ie', 'fj', 'kv', 'crh', 'to', 'stq', 'myv', 'ace', 'gn', - 'ln', 'cbk-zam', 'krc', 'nv', 'ky', 'mhr', 'ext', 'arc', 'jbo', - 'wo', 'ty', 'so', 'eml', 'kab', 'tpi', 'pap', 'zea', 'srn', 'ay', - 'ba', 'or', 'ig', 'dsb', 'kl', 'ce', 'kg', 'udm', 'lo', 'rmy', 'cu', - 'ab', 'mwl', 'pcd', 'kaa', 'sm', 'av', 'ks', 'tet', 'got', 'mdf', + 'mg', 'ilo', 'zh-classical', 'km', 'pi', 'lad', 'sc', 'ang', 'frp', + 'bo', 'hif', 'kw', 'ckb', 'hak', 'pdc', 'haw', 'szl', 'xal', 'ps', + 'pa', 'ie', 'fj', 'kv', 'crh', 'to', 'stq', 'myv', 'ace', 'gn', + 'ln', 'cbk-zam', 'krc', 'nv', 'ky', 'mhr', 'ext', 'ty', 'arc', + 'jbo', 'wo', 'so', 'eml', 'kab', 'tpi', 'pap', 'zea', 'srn', 'ay', + 'ba', 'or', 'ig', 'dsb', 'kl', 'ce', 'udm', 'kg', 'lo', 'rmy', 'cu', + 'ab', 'pcd', 'mwl', 'kaa', 'sm', 'av', 'ks', 'tet', 'mdf', 'got', 'sd', 'na', 'bm', 'pnt', 'pih', 'iu', 'cdo', 'as', 'bug', 'ee', - 'chr', 'om', 'bi', 'zu', 'za', 'ti', 'ts', 'ss', 've', 'ha', 'sg', - 'dz', 'ch', 'cr', 'xh', 'ak', 'ik', 'lbe', 'ki', 'tn', 'bxr', 'rw', + 'chr', 'bi', 'om', 'zu', 'za', 'ti', 'ts', 'ss', 've', 'ha', 'dz', + 'sg', 'ch', 'bxr', 'cr', 'xh', 'ak', 'ik', 'lbe', 'ki', 'tn', 'rw', 'st', 'tw', 'ny', 'sn', 'chy', 'ff', 'lg', 'rn', 'tum', ] @@ -355,6 +355,7 @@ } self.namespaces[100] = { + 'af': u'Portaal', 'als': u'Portal', 'an': u'Portal', 'ar': u'بوابة', @@ -440,6 +441,7 @@ } self.namespaces[101] = { + 'af': u'Portaalbespreking', 'als': u'Portal Diskussion', 'an': u'Descusión Portal', 'ar': u'نقاش البوابة',

1 0

SVN: [8285] trunk/pywikipedia/template.py
by xqt＠svn.wikimedia.org 14 Jun '10

14 Jun '10

Revision: 8285 Author: xqt Date: 2010-06-14 08:58:08 +0000 (Mon, 14 Jun 2010) Log Message: ----------- recognize preleading template namespaces (bug 3015627) Modified Paths: -------------- trunk/pywikipedia/template.py Modified: trunk/pywikipedia/template.py =================================================================== --- trunk/pywikipedia/template.py 2010-06-14 08:14:29 UTC (rev 8284) +++ trunk/pywikipedia/template.py 2010-06-14 08:58:08 UTC (rev 8285) @@ -345,14 +345,18 @@ replacements = [] exceptions = {} - + site = pywikibot.getSite() for old, new in self.templates.iteritems(): - if not pywikibot.getSite().nocapitalize: + namespaces = list(site.namespace(10, all=True)) + if not site.nocapitalize: pattern = '[' + re.escape(old[0].upper()) + re.escape(old[0].lower()) + ']' + re.escape(old[1:]) else: pattern = re.escape(old) pattern = re.sub(r'_|\\ ', r'[_ ]', pattern) - templateRegex = re.compile(r'\{\{ *([Tt]emplate:|[mM][sS][gG]:)?' + pattern + r'(?P<parameters>\s*\|.+?|) *}}', re.DOTALL) + templateRegex = re.compile(r'\{\{ *(' + ':|'.join(namespaces) + \ + r':|[mM][sS][gG]:)?' + pattern + \ + r'(?P<parameters>\s*\|.+?|) *}}', + re.DOTALL) if self.remove: replacements.append((templateRegex, ''))

1 0

SVN: [8284] trunk/pywikipedia/noreferences.py
by xqt＠svn.wikimedia.org 14 Jun '10

14 Jun '10

Revision: 8284 Author: xqt Date: 2010-06-14 08:14:29 +0000 (Mon, 14 Jun 2010) Log Message: ----------- pl update for noreferences.py (patch tracker bug #3015596 by masti) Modified Paths: -------------- trunk/pywikipedia/noreferences.py Modified: trunk/pywikipedia/noreferences.py =================================================================== --- trunk/pywikipedia/noreferences.py 2010-06-12 22:36:27 UTC (rev 8283) +++ trunk/pywikipedia/noreferences.py 2010-06-14 08:14:29 UTC (rev 8284) @@ -319,6 +319,7 @@ 'wikipedia': { 'fi': u'{{viitteet}}', 'hu': u'{{Források}}', + 'pl': u'{{Przypisy}}', }, }

1 0

SVN: [8283] trunk/pywikipedia/imagecopy_enwp.py
by multichill＠svn.wikimedia.org 13 Jun '10

13 Jun '10

Revision: 8283 Author: multichill Date: 2010-06-12 22:36:27 +0000 (Sat, 12 Jun 2010) Log Message: ----------- * Added a templates skip list * Fixed Licensing header detection * Improved the {{information}} detection. Modified Paths: -------------- trunk/pywikipedia/imagecopy_enwp.py Modified: trunk/pywikipedia/imagecopy_enwp.py =================================================================== --- trunk/pywikipedia/imagecopy_enwp.py 2010-06-12 13:39:27 UTC (rev 8282) +++ trunk/pywikipedia/imagecopy_enwp.py 2010-06-12 22:36:27 UTC (rev 8283) @@ -73,6 +73,41 @@ 'en': u'[[:File:%s|File]] moved to [[:commons:File:%s|commons]].', } +skipTemplates = [u'Db-f1', + u'Db-f2', + u'Db-f3', + u'Db-f7', + u'Db-f8', + u'Db-f9', + u'Db-f10', + u'NowCommons', + u'CommonsNow', + u'Nowcommons', + u'NowCommonsThis', + u'Nowcommons2', + u'NCT', + u'Nowcommonsthis', + u'Moved to commons', + u'Now Commons', + u'Now at commons', + u'Db-nowcommons', + u'WikimediaCommons', + u'Now commons', + u'Di-no source', + u'Di-no license', + u'Di-no permission', + u'Di-orphaned fair use', + u'Di-no source no license', + u'Di-replaceable fair use', + u'Di-no fair use rationale', + u'Di-disputed fair use rationale', + u'Puf', + u'PUI', + u'Pui', + u'Ffd', + ] + + licenseTemplates = [(u'\{\{(self|self2)\|([^\}]+)\}\}', u'{{Self|\\2|author=[[:%(lang)s:User:%(author)s|%(author)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]}}'), (u'\{\{(GFDL-self|GFDL-self-no-disclaimers)\|([^\}]+)\}\}', u'{{Self|GFDL|\\2|author=[[:%(lang)s:User:%(author)s|%(author)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]}}'), (u'\{\{GFDL-self-with-disclaimers\|([^\}]+)\}\}', u'{{Self|GFDL-with-disclaimers|\\1|author=[[:%(lang)s:User:%(author)s|%(author)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]}}'), @@ -82,7 +117,7 @@ ] sourceGarbage = [u'== Summary ==', - u'== Licensing ==', + u'== Licensing:? ==', ] class Tkdialog: @@ -227,19 +262,15 @@ return (self.filename, self.description, self.date, self.source, self.author, self.licensetemplate, self.categories, self.skip) -def doiskip(pagetext): +def doiskip(imagepage): ''' Skip this image or not. Returns True if the image is on the skip list, otherwise False - - saltos=getautoskip() - #print saltos - for salto in saltos: - rex=ur'\{\{\s*['+salto[0].upper()+salto[0].lower()+']'+salto[1:]+'(\}\}|\|)' - #print rex - if re.search(rex, pagetext): + ''' + for template in imagepage.templates(): + if template in skipTemplates: + wikipedia.output(u'Found ' + template + u' which is on the template skip list') return True - ''' return False def getNewFields(imagepage): @@ -266,20 +297,26 @@ other_versions = u'' text = imagepage.get() # Need to add the permission field - regex =u'\{\{Information[\s\r\n]*\|[\s\r\n]*description[\s\r\n]*=(?P<description>.*)\|[\s\r\n]*source[\s\r\n]*=(?P<source>.*)\|[\s\r\n]*date[\s\r\n]*=(?P<date>.*)\|[\s\r\n]*author[\s\r\n]*=(?P<author>.*)(\|[\s\r\n]*permission.*=(?P<permission>[^\}]*))?(\|[\s\r\n]*other_versions.*=(?P<other_versions>[^\}]*))?\}\}' + regexes =[u'\{\{Information[\s\r\n]*\|[\s\r\n]*description[\s\r\n]*=(?P<description>.*)\|[\s\r\n]*source[\s\r\n]*=(?P<source>.*)\|[\s\r\n]*date[\s\r\n]*=(?P<date>.*)\|[\s\r\n]*author[\s\r\n]*=(?P<author>.*)\|[\s\r\n]*permission.*=(?P<permission>[^\}]*)\|[\s\r\n]*other_versions.*=(?P<other_versions>[^\}]*)\}\}', + u'\{\{Information[\s\r\n]*\|[\s\r\n]*description[\s\r\n]*=(?P<description>.*)\|[\s\r\n]*source[\s\r\n]*=(?P<source>.*)\|[\s\r\n]*date[\s\r\n]*=(?P<date>.*)\|[\s\r\n]*author[\s\r\n]*=(?P<author>.*)\|[\s\r\n]*other_versions.*=(?P<other_versions>[^\}]*)\}\}', + ] + - match =re.search(regex, text, re.IGNORECASE|re.DOTALL) - if match: - description = convertLinks(match.group(u'description').strip(), imagepage.site()) - date = match.group(u'date').strip() - source = getSource(imagepage, source=convertLinks(match.group(u'source').strip(), imagepage.site())) - author = convertLinks(match.group(u'author').strip(), imagepage.site()) - if match.group(u'permission'): - print u'permission' - permission = convertLinks(match.group(u'permission').strip(), imagepage.site()) - if match.group(u'other_versions'): - print u'other_versions' - other_versions = convertLinks(match.group(u'other_versions').strip(), imagepage.site()) + for regex in regexes: + match =re.search(regex, text, re.IGNORECASE|re.DOTALL) + if match: + description = convertLinks(match.group(u'description').strip(), imagepage.site()) + date = match.group(u'date').strip() + source = getSource(imagepage, source=convertLinks(match.group(u'source').strip(), imagepage.site())) + author = convertLinks(match.group(u'author').strip(), imagepage.site()) + if u'permission' in match.groupdict(): + permission = convertLinks(match.group(u'permission').strip(), imagepage.site()) + if u'other_versions' in match.groupdict(): + other_versions = convertLinks(match.group(u'other_versions').strip(), imagepage.site()) + # Return the stuff we found + return (description, date, source, author) + + #We didn't find anything, return the empty strings return (description, date, source, author) def getNewFieldsFromFreetext(imagepage): @@ -417,7 +454,7 @@ imagepage = wikipedia.ImagePage(page.site(), page.title()) #First do autoskip. - if doiskip(imagepage.get()): + if doiskip(imagepage): wikipedia.output("Skipping " + page.title()) skip = True else:

1 0

SVN: [8282] trunk/pywikipedia/imagerecat.py
by multichill＠svn.wikimedia.org 12 Jun '10

12 Jun '10

Revision: 8282 Author: multichill Date: 2010-06-12 13:39:27 +0000 (Sat, 12 Jun 2010) Log Message: ----------- Modified the lib so it can also be used for files which are being moved from some Wikipedia to Commons Modified Paths: -------------- trunk/pywikipedia/imagerecat.py Modified: trunk/pywikipedia/imagerecat.py =================================================================== --- trunk/pywikipedia/imagerecat.py 2010-06-12 13:20:46 UTC (rev 8281) +++ trunk/pywikipedia/imagerecat.py 2010-06-12 13:39:27 UTC (rev 8282) @@ -49,11 +49,11 @@ global category_blacklist global countries - blacklistPage = wikipedia.Page(wikipedia.getSite(), u'User:Multichill/Category_blacklist') + blacklistPage = wikipedia.Page(wikipedia.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'User:Multichill/Countries') + countryPage = wikipedia.Page(wikipedia.getSite(u'commons', u'commons'), u'User:Multichill/Countries') for country in countryPage.linkedPages(): countries.append(country.titleWithoutNamespace()) return @@ -106,8 +106,17 @@ global search_wikis global hint_wiki + site = imagepage.site() + lang = site.language() + family = site.family.name + if lang==u'commons' and family==u'commons': + parameters = urllib.urlencode({'i' : imagepage.titleWithoutNamespace().encode('utf-8'), 'r' : 'on', 'go-clean' : 'Find+Categories', 'p' : search_wikis, 'cl' : hint_wiki}) + elif family==u'wikipedia': + parameters = urllib.urlencode({'i' : imagepage.titleWithoutNamespace().encode('utf-8'), 'r' : 'on', 'go-move' : 'Find+Categories', 'p' : search_wikis, 'cl' : hint_wiki, 'w' : lang}) + else: + #Cant handle other sites atm + return ([], [], []) - parameters = urllib.urlencode({'i' : imagepage.titleWithoutNamespace().encode('utf-8'), 'r' : 'on', 'go-clean' : 'Find+Categories', 'p' : search_wikis, 'cl' : hint_wiki}) 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 @@ -210,7 +219,7 @@ ''' result = [] for cat in categories: - if(not wikipedia.Page(wikipedia.getSite(), u'Category:' + cat).isDisambig()): + if(not wikipedia.Page(wikipedia.getSite(u'commons', u'commons'), u'Category:' + cat).isDisambig()): result.append(cat) return result @@ -220,7 +229,7 @@ ''' result = [] for cat in categories: - categoryPage = wikipedia.Page(wikipedia.getSite(), u'Category:' + cat) + 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)): @@ -253,7 +262,7 @@ if(len(listByCountry) > 0): for bc in listByCountry: - category = catlib.Category(wikipedia.getSite(), u'Category:' + bc) + category = catlib.Category(wikipedia.getSite(u'commons', u'commons'), u'Category:' + bc) for subcategory in category.subcategories(): for country in listCountries: if (subcategory.titleWithoutNamespace().endswith(country)):

1 0

SVN: [8281] trunk/pywikipedia/imagecopy_enwp.py
by multichill＠svn.wikimedia.org 12 Jun '10

12 Jun '10

Revision: 8281 Author: multichill Date: 2010-06-12 13:20:46 +0000 (Sat, 12 Jun 2010) Log Message: ----------- First version of a bot to empty out http://en.wikipedia.org/wiki/Category:Self-published_work Still needs a lot of work. Added Paths: ----------- trunk/pywikipedia/imagecopy_enwp.py Copied: trunk/pywikipedia/imagecopy_enwp.py (from rev 8268, trunk/pywikipedia/imagecopy.py) =================================================================== --- trunk/pywikipedia/imagecopy_enwp.py (rev 0) +++ trunk/pywikipedia/imagecopy_enwp.py 2010-06-12 13:20:46 UTC (rev 8281) @@ -0,0 +1,523 @@ +# -*- coding: utf-8 -*- +""" +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 uses a graphical interface and may not work from commandline +only environment. + +Examples + +Work on a single image + python imagecopy.py -page:Image:<imagename> +Work on the 100 newest images: + python imagecopy.py -newimages:100 +Work on all images in a category:<cat> + python imagecopy.py -cat:<cat> +Work on all images which transclude a template + python imagecopy.py -transcludes:<template> + +See pagegenerators.py for more ways to get a list of images. +By default the bot works on your home wiki (set in user-config) + +This is a first test version and should be used with care. + + +""" +# +# Based on upload.py by: +# (C) Rob W.W. Hooft, Andre Engels 2003-2007 +# (C) Wikipedian, Keichwa, Leogregianin, Rikwade, Misza13 2003-2007 +# +# New bot by: +# (C) Kyle/Orgullomoore, Siebrand Mazeland 2007 +# +# Another rewrite by: +# (C) Multichill 2008 +# +# English Wikipedia specific bot by: +# (C) Multichill 2010 +# +# Distributed under the terms of the MIT license. +# +__version__='$Id$' +# + +from Tkinter import * +import os, sys, re, codecs +import urllib, httplib, urllib2 +import webbrowser +import time, threading +import wikipedia, config, socket +import pagegenerators, add_text +import imagerecat +from datetime import datetime +from upload import * +from image import * +NL='' + +nowCommonsTemplate = { + 'en': u'{{subst:ncd|%s}}', +} + +nowCommonsMessage = { + 'en': u'File is now available on Wikimedia Commons.', +} + +moveToCommonsTemplate = { + 'en': [u'Commons ok', u'Copy to Wikimedia Commons', u'Move to commons', u'Movetocommons', u'To commons', u'Copy to Wikimedia Commons by BotMultichill'], +} + +imageMoveMessage = { + 'en': u'[[:File:%s|File]] moved to [[:commons:File:%s|commons]].', +} + +licenseTemplates = [(u'\{\{(self|self2)\|([^\}]+)\}\}', u'{{Self|\\2|author=[[:%(lang)s:User:%(author)s|%(author)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]}}'), + (u'\{\{(GFDL-self|GFDL-self-no-disclaimers)\|([^\}]+)\}\}', u'{{Self|GFDL|\\2|author=[[:%(lang)s:User:%(author)s|%(author)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]}}'), + (u'\{\{GFDL-self-with-disclaimers\|([^\}]+)\}\}', u'{{Self|GFDL-with-disclaimers|\\1|author=[[:%(lang)s:User:%(author)s|%(author)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]}}'), + (u'\{\{PD-self(\|date=[^\}]+)\}\}', u'{{PD-user-w|%(lang)s|%(family)s|%(author)s}}'), + #Multilicense replacing placeholder + (u'\{\{Multilicense replacing placeholder new(\|class=[^\}]+)\}\}', u'{{Self|GFDL|Cc-by-sa-3.0,2.5,2.0,1.0|author=[[:%(lang)s:User:%(author)s|%(author)s]] at [http://%(lang)s.%(family)s.org %(lang)s.%(family)s]}}'), + ] + +sourceGarbage = [u'== Summary ==', + u'== Licensing ==', + ] + +class Tkdialog: + def __init__(self, imagepage, currentcontent): + self.root=Tk() + #"%dx%d%+d%+d" % (width, height, xoffset, yoffset) + #Always appear the same size and in the bottom-left corner + self.root.geometry("1000x400+100-100") + self.root.title(imagepage.titleWithoutNamespace()) + + + self.url=imagepage.permalink() + self.scrollbar=Scrollbar(self.root, orient=VERTICAL) + + 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.scrollbar.config(command=self.old_description.yview) + + self.filename = imagepage.titleWithoutNamespace() + + (self.description, + self.date, + self.source, + self.author, + self.licensetemplate, + self.categories) = currentcontent + 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.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 + + self.filename_field.config(width=self.field_width) + self.information_description.config(width=self.field_width) + self.information_date.config(width=self.field_width) + self.information_source.config(width=self.field_width) + self.information_author.config(width=self.field_width) + self.information_licensetemplate.config(width=self.field_width) + self.information_categories.config(width=self.field_width) + + + self.filename_field.insert(0, self.filename) + self.information_description.insert(0, self.description) + self.information_date.insert(0, self.date) + self.information_source.insert(0, self.source) + self.information_author.insert(0, self.author) + 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.skipButton=Button(self.root, text="Skip", command=self.skipFile) + self.okButton=Button(self.root, text="OK", command=self.okFile) + + ##Start grid + self.old_description_label.grid(row=0, column=0, columnspan=3) + + self.old_description.grid(row=1, column=0, columnspan=3) + self.scrollbar.grid(row=1, column=3) + self.new_description_label.grid(row=2, column=0, columnspan=3) + + self.filename_label.grid(row=3, column=0) + self.information_description_label.grid(row=4, column=0) + self.information_date_label.grid(row=5, column=0) + self.information_source_label.grid(row=6, column=0) + self.information_author_label.grid(row=7, column=0) + self.information_licensetemplate_label.grid(row=8, column=0) + self.information_categories_label.grid(row=9, column=0) + + self.filename_field.grid(row=3, column=1, columnspan=3) + self.information_description.grid(row=4, column=1, columnspan=3) + self.information_date.grid(row=5, column=1, columnspan=3) + self.information_source.grid(row=6, column=1, columnspan=3) + self.information_author.grid(row=7, column=1, columnspan=3) + self.information_licensetemplate.grid(row=8, column=1, columnspan=3) + self.information_categories.grid(row=9, column=1, columnspan=3) + + self.okButton.grid(row=10, column=3, rowspan=2) + self.skipButton.grid(row=10, column=2, rowspan=2) + self.browserButton.grid(row=10, column=1, rowspan=2) + + def okFile(self): + ''' + The user pressed the OK button. + ''' + self.filename=self.filename_field.get().decode('utf-8') + self.description=self.information_description.get().decode('utf-8') + self.date=self.information_date.get().decode('utf-8') + self.source=self.information_source.get().decode('utf-8') + self.author=self.information_author.get().decode('utf-8') + self.licensetemplate=self.information_licensetemplate.get().decode('utf-8') + self.categories=self.information_categories.get().decode('utf-8') + + self.root.destroy() + + def skipFile(self): + ''' + The user pressed the Skip button. + ''' + self.skip=1 + self.root.destroy() + + def openInBrowser(self): + ''' + The user pressed the View in browser button. + ''' + webbrowser.open(self.url) + + def add2autoskip(self): + ''' + The user pressed the Add to AutoSkip button. + ''' + templateid=int(self.templatelist.curselection()[0]) + template=self.templatelist.get(templateid) + toadd=codecs.open(archivo, 'a', 'utf-8') + toadd.write('{{'+template) + toadd.close() + self.skipFile() + + def getnewmetadata(self): + ''' + 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) + + +def doiskip(pagetext): + ''' + Skip this image or not. + Returns True if the image is on the skip list, otherwise False + + saltos=getautoskip() + #print saltos + for salto in saltos: + rex=ur'\{\{\s*['+salto[0].upper()+salto[0].lower()+']'+salto[1:]+'(\}\}|\|)' + #print rex + if re.search(rex, pagetext): + return True + ''' + return False + +def getNewFields(imagepage): + ''' + Build a new description based on the imagepage + ''' + if u'{{Information' in imagepage.get() or u'{{information' in imagepage.get(): + (description, date, source, author) = getNewFieldsFromInformation(imagepage) + else: + (description, date, source, author) = getNewFieldsFromFreetext(imagepage) + + licensetemplate = getNewLicensetemplate(imagepage) + categories = getNewCategories(imagepage) + return (description, date, source, author, licensetemplate, categories) + +def getNewFieldsFromInformation(imagepage): + ''' + ''' + description = u'' + date = u'' + source = u'' + author = u'' + permission = u'' + other_versions = u'' + text = imagepage.get() + # Need to add the permission field + regex =u'\{\{Information[\s\r\n]*\|[\s\r\n]*description[\s\r\n]*=(?P<description>.*)\|[\s\r\n]*source[\s\r\n]*=(?P<source>.*)\|[\s\r\n]*date[\s\r\n]*=(?P<date>.*)\|[\s\r\n]*author[\s\r\n]*=(?P<author>.*)(\|[\s\r\n]*permission.*=(?P<permission>[^\}]*))?(\|[\s\r\n]*other_versions.*=(?P<other_versions>[^\}]*))?\}\}' + + match =re.search(regex, text, re.IGNORECASE|re.DOTALL) + if match: + description = convertLinks(match.group(u'description').strip(), imagepage.site()) + date = match.group(u'date').strip() + source = getSource(imagepage, source=convertLinks(match.group(u'source').strip(), imagepage.site())) + author = convertLinks(match.group(u'author').strip(), imagepage.site()) + if match.group(u'permission'): + print u'permission' + permission = convertLinks(match.group(u'permission').strip(), imagepage.site()) + if match.group(u'other_versions'): + print u'other_versions' + other_versions = convertLinks(match.group(u'other_versions').strip(), imagepage.site()) + return (description, date, source, author) + +def getNewFieldsFromFreetext(imagepage): + ''' + ''' + text = imagepage.get() + #text = re.sub(u'== Summary ==', u'', text, re.IGNORECASE) + #text = re.sub(u'== Licensing ==', u'', text, re.IGNORECASE) + #text = re.sub(u'\{\{(self|self2)\|[^\}]+\}\}', u'', text, re.IGNORECASE) + + for toRemove in sourceGarbage: + text = re.sub(toRemove, u'', text, re.IGNORECASE) + + for (regex, repl) in licenseTemplates: + text = re.sub(regex, u'', text, re.IGNORECASE) + + text = wikipedia.removeCategoryLinks(text, imagepage.site()).strip() + + description = convertLinks(text.strip(), imagepage.site()) + date = getUploadDate(imagepage) + source = getSource(imagepage) + author = getAuthorText(imagepage) + return (description, date, source, author) + +def getUploadDate(imagepage): + # Get the original upload date + 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)' + +def getSource(imagepage, source=u''): + site = imagepage.site() + lang = site.language() + 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} + +def getAuthorText(imagepage): + firstuploader = getAuthor(imagepage) + return u'[[:en:User:' + firstuploader + u'|' + firstuploader + u']] at [http://en.wikipedia.org en.wikipedia]' + +def getAuthor(imagepage): + return imagepage.getFileVersionHistory()[-1][1].strip() + +def convertLinks(text, sourceSite): + lang = sourceSite.language() + family = sourceSite.family.name + conversions =[(u'\[\[([^\[\]\|]+)\|([^\[\]\|]+)\]\]', u'[[:%(lang)s:\\1|\\2]]'), + (u'\[\[([^\[\]\|]+)\]\]', u'[[:%(lang)s:\\1|\\1]]'), + ] + + for (regex, replacement) in conversions: + text = re.sub(regex, replacement, text) + + return text % {u'lang' : lang, u'family' : family} + +def getNewLicensetemplate(imagepage): + ''' + ''' + 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) + return result % {u'author' : getAuthor(imagepage), + u'lang' : lang, + u'family' : family} + + return result + +def getNewCategories(imagepage): + ''' + Get a categories for the image + Dont forget to filter + ''' + result = u'' + (commonshelperCats, usage, galleries) = imagerecat.getCommonshelperCats(imagepage) + newcats = imagerecat.applyAllFilters(commonshelperCats) + for newcat in newcats: + result = result + u'[[Category:' + newcat + u']] ' + return result + +def getOriginalUploadLog(imagepage): + filehistory = imagepage.getFileVersionHistory() + filehistory.reverse() + + result = u'== Original upload log ==\n' + result = result + u'The original description page is/was [http://en.wikipedia.org%s here]. All following user names refer to en.wikipedia.\n' % (imagepage.site().get_address(imagepage.title()).replace(u'&redirect=no&useskin=monobook', u'')) + for (timestamp, username, resolution, size, comment) in filehistory: + result = result + u'* %s [[:en:user:%s|%s]] %s (%s bytes) \'\'<nowiki>%s</nowiki>\'\'\n' % (datetime.strptime(timestamp, u'%Y-%m-%dT%H:%M:%SZ').strftime('%Y-%m-%d %H:%M'), username, username, resolution, size, comment) + + return result + + + +def buildNewImageDescription(imagepage, description, date, source, author, licensetemplate, categories): + ''' + Build a new information template + ''' + cid = u'' + cid = cid + u'\n{{BotMoveToCommons|'+ imagepage.site().language() + '.' + imagepage.site().family.name +'|year={{subst:CURRENTYEAR}}|month={{subst:CURRENTMONTHNAME}}|day={{subst:CURRENTDAY}}}}\n' + cid = cid + u'== {{int:filedesc}} ==\n' + cid = cid + u'{{Information\n' + cid = cid + u'|description={{en|1=' + description + u'}}\n' + cid = cid + u'|date=' + date + u'\n' + cid = cid + u'|source=' + source + u'\n' + cid = cid + u'|author=' + author + u'\n' + cid = cid + u'|permission=\n' + cid = cid + u'|other_versions=\n' + cid = cid + u'}}\n' + cid = cid + u'== {{int:license}} ==\n' + cid = cid + licensetemplate + u'\n' + cid = cid + u'\n' + cid = cid + getOriginalUploadLog(imagepage) + cid = cid + u'__NOTOC__\n' + if categories.strip()==u'': + cid = cid + u'{{Subst:Unc}}' + else: + cid = cid + categories + return cid + + +def processImage(page): + skip = False + if page.exists() and (page.namespace() == 6) and (not page.isRedirectPage()): + imagepage = wikipedia.ImagePage(page.site(), page.title()) + + #First do autoskip. + if doiskip(imagepage.get()): + wikipedia.output("Skipping " + page.title()) + skip = True + else: + currentcontent = getNewFields(imagepage) + + while True: + # Do the Tkdialog to accept/reject and change te name + (filename, description, date, source, author, licensetemplate, categories, skip)=Tkdialog(imagepage, currentcontent).getnewmetadata() + + if skip: + wikipedia.output('Skipping this image') + break + + # Check if the image already exists + CommonsPage=wikipedia.Page(wikipedia.getSite('commons', 'commons'), u'File:' + filename) + if not CommonsPage.exists(): + break + else: + wikipedia.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: + cid = 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')) + bot.run() + + if wikipedia.Page(wikipedia.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) + + #Remove the move to commons templates + if imagepage.site().language() in moveToCommonsTemplate: + for moveTemplate in moveToCommonsTemplate[imagepage.site().language()]: + imtxt = re.sub(u'(?i)\{\{' + moveTemplate + u'[^\}]*\}\}', u'', imtxt) + + #add {{NowCommons}} + if imagepage.site().language() in nowCommonsTemplate: + addTemplate = nowCommonsTemplate[imagepage.site().language()] % filename + else: + addTemplate = nowCommonsTemplate['_default'] % filename + + if imagepage.site().language() in nowCommonsMessage: + commentText = nowCommonsMessage[imagepage.site().language()] + else: + commentText = nowCommonsMessage['_default'] + + wikipedia.showDiff(imagepage.get(), imtxt + addTemplate) + imagepage.put(imtxt + addTemplate, comment = commentText) + + gen = pagegenerators.FileLinksGenerator(imagepage) + preloadingGen = pagegenerators.PreloadingGenerator(gen) + + #If the image is uploaded under a different name, replace all instances + if imagepage.titleWithoutNamespace() != filename: + if imagepage.site().language() in imageMoveMessage: + moveSummary = imageMoveMessage[imagepage.site().language()] % (imagepage.titleWithoutNamespace(), filename) + else: + moveSummary = imageMoveMessage['_default'] % (imagepage.titleWithoutNamespace(), filename) + imagebot = ImageRobot(generator = preloadingGen, oldImage = imagepage.titleWithoutNamespace(), newImage = filename, summary = moveSummary, always = True, loose = True) + imagebot.run() + + + +def main(args): + generator = None; + #newname = ""; + imagepage = None; + always = False + category = u'' + imagerecat.initLists() + # Load a lot of default generators + genFactory = pagegenerators.GeneratorFactory() + + for arg in wikipedia.handleArgs(): + if arg == '-always': + always = True + elif arg.startswith('-cc:'): + category = arg [len('-cc:'):] + else: + genFactory.handleArg(arg) + + generator = genFactory.getCombinedGenerator() + if not generator: + raise add_text.NoEnoughData('You have to specify the generator you want to use for the script!') + + pregenerator = pagegenerators.PreloadingGenerator(generator) + + for page in pregenerator: + processImage(page) + + + wikipedia.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') + +if __name__ == "__main__": + try: + main(sys.argv[1:]) + finally: + wikipedia.stopme()

1 0

← Newer
1
2
3
4
5
6
7
8
9
10
11
Older →

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

Pywikipedia-svn June 2010