Pywikipedia-svn November 2009

pywikipedia-svn@lists.wikimedia.org

9 participants
146 discussions

SVN: [7582] trunk/pywikipedia/interwiki.py
by xqt＠svn.wikimedia.org 02 Nov '09

02 Nov '09

Revision: 7582 Author: xqt Date: 2009-11-02 18:43:03 +0000 (Mon, 02 Nov 2009) Log Message: ----------- IOError exception handling when reading from dump Modified Paths: -------------- trunk/pywikipedia/interwiki.py Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2009-11-02 18:34:37 UTC (rev 7581) +++ trunk/pywikipedia/interwiki.py 2009-11-02 18:43:03 UTC (rev 7582) @@ -1735,7 +1735,11 @@ for i in range(number): try: while True: - page = self.pageGenerator.next() + try: + page = self.pageGenerator.next() + except IOError: + pywikibot.output(u'IOError occured; skipping') + continue if page in globalvar.skip: pywikibot.output(u'Skipping: %s is in the skip list' % page.title()) continue

1 0

SVN: [7581] trunk/pywikipedia/interwiki.py
by a_engels＠svn.wikimedia.org 02 Nov '09

02 Nov '09

Revision: 7581 Author: a_engels Date: 2009-11-02 18:34:37 +0000 (Mon, 02 Nov 2009) Log Message: ----------- I got an error here; throwing a try...catch around it Modified Paths: -------------- trunk/pywikipedia/interwiki.py Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2009-11-02 17:38:54 UTC (rev 7580) +++ trunk/pywikipedia/interwiki.py 2009-11-02 18:34:37 UTC (rev 7581) @@ -870,7 +870,10 @@ return False if globalvar.nobackonly: if page == self.originPage: - pywikibot.output(u"%s has a backlink from %s."%(page,linkingPage)) + try: + pywikibot.output(u"%s has a backlink from %s."%(page,linkingPage)) + except UnicodeDecodeError: + pywikibot.output(u"Found a backlink for a page.") self.makeForcedStop(counter) return False

1 0

SVN: [7580] trunk/pywikipedia/clean_sandbox.py
by xqt＠svn.wikimedia.org 02 Nov '09

02 Nov '09

Revision: 7580 Author: xqt Date: 2009-11-02 17:38:54 +0000 (Mon, 02 Nov 2009) Log Message: ----------- parameter for delay time after the last edit has beend made; bugfix for list object. Modified Paths: -------------- trunk/pywikipedia/clean_sandbox.py Modified: trunk/pywikipedia/clean_sandbox.py =================================================================== --- trunk/pywikipedia/clean_sandbox.py 2009-11-02 14:38:10 UTC (rev 7579) +++ trunk/pywikipedia/clean_sandbox.py 2009-11-02 17:38:54 UTC (rev 7580) @@ -9,6 +9,11 @@ after # hours. Hours can be defined as a decimal. 0.01 hours are 36 seconds; 0.1 are 6 minutes. + -delay:# Use this parameter for a wait time after the last edit + was made. If no parameter is given it takes it from + hours and limits it between 5 and 15 minutes. + The minimum delay time is 5 minutes. + """ # # (C) Leonardo Gregianin, 2006 @@ -99,13 +104,28 @@ } class SandboxBot: - def __init__(self, hours, no_repeat): + def __init__(self, hours, no_repeat, delay): self.hours = hours self.no_repeat = no_repeat + if delay == None: + self.delay = min(15, max(5, int(self.hours *60))) + else: + self.delay = max(5, delay) def run(self): + + 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) + mySite = wikipedia.getSite() while True: + wait = False now = time.strftime("%d %b %Y %H:%M:%S (UTC)", time.gmtime()) localSandboxTitle = wikipedia.translate(mySite, sandboxTitle) if type(localSandboxTitle) is list: @@ -113,36 +133,52 @@ else: titles = [localSandboxTitle,] for title in titles: - sandboxPage = wikipedia.Page(mySite, localSandboxTitle) + sandboxPage = wikipedia.Page(mySite, title) try: text = sandboxPage.get() translatedContent = wikipedia.translate(mySite, content) + translatedMsg = wikipedia.translate(mySite, msg) if text.strip() == translatedContent.strip(): wikipedia.output(u'The sandbox is still clean, no change necessary.') + elif text.find(translatedContent.strip()) <> 0: + sandboxPage.put(translatedContent, translatedMsg) + wikipedia.output(u'Standard content was changed, sandbox cleaned.') else: - translatedMsg = wikipedia.translate(mySite, msg) - sandboxPage.put(translatedContent, translatedMsg) + diff = minutesDiff(sandboxPage.editTime(), time.strftime("%Y%m%d%H%M%S", time.gmtime())) + #Is the last edit more than 5 minutes ago? + if diff >= self.delay: + sandboxPage.put(translatedContent, translatedMsg) + else: #wait for the rest + wikipedia.output(u'Sleeping for %d minutes.' % (self.delay-diff)) + time.sleep((self.delay-diff)*60) + wait = True except wikipedia.EditConflict: wikipedia.output(u'*** Loading again because of edit conflict.\n') if self.no_repeat: wikipedia.output(u'\nDone.') return - else: - wikipedia.output('\nSleeping %s hours, now %s' % (self.hours, now) ) + elif not wait: + if self.hours < 1.0: + wikipedia.output('\nSleeping %s minutes, now %s' % ((self.hours*60), now) ) + else: + wikipedia.output('\nSleeping %s hours, now %s' % (self.hours, now) ) time.sleep(self.hours * 60 * 60) def main(): hours = 1 + delay = None no_repeat = True for arg in wikipedia.handleArgs(): if arg.startswith('-hours:'): hours = float(arg[7:]) no_repeat = False + elif arg.startswith('-delay:'): + delay = int(arg[7:]) else: wikipedia.showHelp('clean_sandbox') return - bot = SandboxBot(hours, no_repeat) + bot = SandboxBot(hours, no_repeat, delay) bot.run() if __name__ == "__main__":

1 0

SVN: [7579] trunk/pywikipedia/clean_sandbox.py
by xqt＠svn.wikimedia.org 02 Nov '09

02 Nov '09

Revision: 7579 Author: xqt Date: 2009-11-02 14:38:10 +0000 (Mon, 02 Nov 2009) Log Message: ----------- correcting usage of decimals in hours-option Modified Paths: -------------- trunk/pywikipedia/clean_sandbox.py Modified: trunk/pywikipedia/clean_sandbox.py =================================================================== --- trunk/pywikipedia/clean_sandbox.py 2009-11-01 10:21:50 UTC (rev 7578) +++ trunk/pywikipedia/clean_sandbox.py 2009-11-02 14:38:10 UTC (rev 7579) @@ -6,8 +6,8 @@ This script understands the following command-line arguments: -hours:# Use this parameter if to make the script repeat itself - after # hours. Hours can be defined as a decimal. 0.001 - hours is one second. + after # hours. Hours can be defined as a decimal. 0.01 + hours are 36 seconds; 0.1 are 6 minutes. """ # @@ -53,7 +53,7 @@ 'ar': u'روبوت: هذه الصفحة سيتم تفريغها تلقائيا', 'cs': u'Uhrabání pískoviště', 'da': u'Bot: Nyt sand (fra[[Skabelon:Sandkasse tekst]])', - 'de': u'Bot: Setze Seite zurück.', + 'de': u'Bot: Setze Spielwiese zurück.', 'en': u'Robot: Automatically cleaned', 'fi': u'Botti siivosi hiekkalaatikon.', 'he': u'בוט: דף זה ינוקה אוטומטית.',

1 0

SVN: [7578] trunk/pywikipedia/families/wikipedia_family.py
by a_engels＠svn.wikimedia.org 01 Nov '09

01 Nov '09

Revision: 7578 Author: a_engels Date: 2009-11-01 10:21:50 +0000 (Sun, 01 Nov 2009) Log Message: ----------- some disambiguation templates in Japanese and other languages Modified Paths: -------------- trunk/pywikipedia/families/wikipedia_family.py Modified: trunk/pywikipedia/families/wikipedia_family.py =================================================================== --- trunk/pywikipedia/families/wikipedia_family.py 2009-11-01 09:52:00 UTC (rev 7577) +++ trunk/pywikipedia/families/wikipedia_family.py 2009-11-01 10:21:50 UTC (rev 7578) @@ -674,10 +674,11 @@ 'be-x-old': [u'Неадназначнасць', u'Неадназначнасьць', u'Disambig'], 'bg': [u'Пояснение', u'Disambig'], 'bn': [u'দ্ব্যর্থতা নিরসন', u'Disambig'], - 'br': [u'Hvlstumm', u'Digejañ', u'Digejañ anvioù-badez'], + 'br': [u'Hvlstumm', u'Digejañ', u'Digejañ anvioù-badez', + u"Digejañ lec'hanvioù"], 'bs': [u'Čvor'], 'ca': [u'Desambiguació', u'Disambig', u'Desambigua', - u'acrònim', u'onomàstica'], + u'acrònim', u'onomàstica', u'DesambigCurta'], 'ceb': [u'Giklaro'], 'cdo': [u'Gì-ngiê'], 'crh': [u'Çoq manalı', u'Disambig'], @@ -722,7 +723,8 @@ 'io': [u'Homonimo', u'Disambig'], 'is': None, 'it': [u'Disambigua', u'Sigla2', u'Sigla3', u'Sigla4', u'Cogni'], - 'ja': [u'Aimai', u'Dab', u'曖昧さ回避', u'Disambig'], + 'ja': [u'Aimai', u'Dab', u'曖昧さ回避', u'Disambig', u'地名の曖昧さ回避|あはていん', + u'地名の曖昧さ回避', u'人名の曖昧さ回避', u'人名の曖昧さ回避|あたるへると'], 'ka': [u'მრავალმნიშვნელოვანი', u'მრავმნიშ'], 'kab': [u'Asefham'], 'kg': [u'Bisongidila'], @@ -732,7 +734,7 @@ 'kw': [u'Klerheans'], 'ksh': [u'Disambig'], 'la': [u'Discretiva', u'Disnomen'], - 'lb': [u'Homonymie', u'Disambig'], + 'lb': [u'Homonymie', u'Disambig', u'Homonymie Ofkierzungen'], 'li': [u'Verdudeliking', u'Verdudelikingpazjena', u'Vp'], 'lmo': [u'Desambiguació'], 'ln': [u'Bokokani'], @@ -747,7 +749,7 @@ 'nds': [u'Mehrdüdig Begreep', 'Disambig'], 'nds-nl': [u'Dv'], 'nl': [u'Dp', u'DP', u'Dp2', u'Dpintro', u'Cognomen'], - 'nn': [u'Fleirtyding'], + 'nn': [u'Fleirtyding', u'Tobokstavforkorting'], 'no': [u'Peker', u'Etternavn', u'Disambig', u'Tobokstavsforkortelse', u'Trebokstavsforkortelse', u'Flertydig', u'Pekerside'], 'nov': [u'Desambig'], @@ -771,7 +773,7 @@ 'sl': None, 'sq': [u'Kthjellim', u'Disambig'], 'sr': [u'Вишезначна одредница', u'Disambig', u'Вишезначна', - u'Višeznačna odrednica'], + u'Višeznačna odrednica', u'Взо'], 'srn': [u'Dp'], 'stq': [u'Begriepskläärenge'], 'su': [u'Disambig'], @@ -797,7 +799,7 @@ 'wo': [u'Bokktekki'], 'yi': [u'באדייטען'], 'zea': [u'dp', u'Deurverwiespagina'], - 'zh': [u'Disambig', u'消歧义', u'消歧义页', u'消歧義'], + 'zh': [u'Disambig', u'消歧义', u'消歧义页', u'消歧義', u'Letter disambig'], 'zh-classical': [u'Disambig', u'釋義', u'消歧義'], 'zh-min-nan': [u'Khu-pia̍t-ia̍h', 'KhPI', u'Disambig'], 'zh-yue': [u'搞清楚', u'Disambig'],

1 0

SVN: [7577] trunk/pywikipedia/pagegenerators.py
by a_engels＠svn.wikimedia.org 01 Nov '09

01 Nov '09

Revision: 7577 Author: a_engels Date: 2009-11-01 09:52:00 +0000 (Sun, 01 Nov 2009) Log Message: ----------- When using the -cat (and similar) command-line arguments, if one wants to start the category somewhere in the middle, allow usage of # instead of |. I prefer # because | already has a meaning on the command line, and thus can only be used with quotation marks as escape. Modified Paths: -------------- trunk/pywikipedia/pagegenerators.py Modified: trunk/pywikipedia/pagegenerators.py =================================================================== --- trunk/pywikipedia/pagegenerators.py 2009-10-31 00:35:16 UTC (rev 7576) +++ trunk/pywikipedia/pagegenerators.py 2009-11-01 09:52:00 UTC (rev 7577) @@ -18,22 +18,23 @@ parameterHelp = """\ -cat Work on all pages which are in a specific category. Argument can also be given as "-cat:categoryname" or - as "-cat:categoryname|fromtitle". + as "-cat:categoryname#fromtitle" (using | instead of # + is also allowed in this one and the following) -catr Like -cat, but also recursively includes pages in subcategories, sub-subcategories etc. of the given category. Argument can also be given as "-catr:categoryname" or - as "-catr:categoryname|fromtitle". + as "-catr:categoryname#fromtitle". -subcats Work on all subcategories of a specific category. Argument can also be given as "-subcats:categoryname" or - as "-subcats:categoryname|fromtitle". + as "-subcats:categoryname#fromtitle". -subcatsr Like -subcats, but also includes sub-subcategories etc. of the given category. Argument can also be given as "-subcatsr:categoryname" or - as "-subcatsr:categoryname|fromtitle". + as "-subcatsr:categoryname#fromtitle". -uncat Work on all pages which are not categorised. @@ -925,7 +926,7 @@ categoryname = wikipedia.input(u'Please enter the category name:') else: categoryname = arg[length + 1:] - + categoryname = categoryname.replace('#', '|') ind = categoryname.find('|') startfrom = None if ind > 0:

1 0

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

Pywikipedia-svn November 2009