pywikibot September 2007

pywikibot@lists.wikimedia.org

24 participants
397 discussions

[Pywikipedia-l] SVN: [4320] trunk/pywikipedia/copyright_put.py

by cosoleto＠svn.wikimedia.org

Revision: 4320 Author: cosoleto Date: 2007-09-17 17:52:44 +0000 (Mon, 17 Sep 2007) Log Message: ----------- code cleanup, -stats command line parameter Modified Paths: -------------- trunk/pywikipedia/copyright_put.py Modified: trunk/pywikipedia/copyright_put.py =================================================================== --- trunk/pywikipedia/copyright_put.py 2007-09-17 17:50:13 UTC (rev 4319) +++ trunk/pywikipedia/copyright_put.py 2007-09-17 17:52:44 UTC (rev 4320) @@ -21,10 +21,6 @@ # Add pubblication date to entries (template:botdate) append_date_to_entries = False -# -# Send statistics -send_stats = False - msg_table = { 'it': {'_default': [u'Pagine nuove', u'Nuove voci'], 'feed': [u'Aggiunte a voci esistenti', u'Testo aggiunto in']}, @@ -50,6 +46,9 @@ template_cat = wikipedia.translate(wikipedia.getSite(), template_cat) stat_wiki_save_path = '%s/%s' % (wiki_save_path, wikipedia.translate(wikipedia.getSite(), stat_msg)[0]) +if append_date_to_wiki_save_path: + wiki_save_path += '_' + date.monthName(wikipedia.getSite().language(), time.localtime()[1]) + '_' + str(time.localtime()[0]) + separatorC = re.compile('(?m)^== +') def set_template(): @@ -154,76 +153,88 @@ return data -if append_date_to_wiki_save_path: - wiki_save_path += '_' + date.monthName(wikipedia.getSite().language(), time.localtime()[1]) + '_' + str(time.localtime()[0]) +def run(send_stats = False): + page = wikipedia.Page(wikipedia.getSite(), wiki_save_path) -page = wikipedia.Page(wikipedia.getSite(), wiki_save_path) + try: + wikitext = page.get() + except wikipedia.NoPage: + wikipedia.output("%s not found." % page.aslink()) + wikitext = '[[%s:%s]]\n' % (wikipedia.getSite().namespace(14), wikipedia.translate(wikipedia.getSite(), reports_cat)) -try: - wikitext = page.get() -except wikipedia.NoPage: - wikipedia.output("%s not found." % page.aslink()) - wikitext = '[[%s:%s]]\n' % (wikipedia.getSite().namespace(14), wikipedia.translate(wikipedia.getSite(), reports_cat)) + final_summary = u'' + output_files = list() -final_summary = u'' -output_files = list() + for f, section, summary in output_files_gen(): + wikipedia.output('File: \'%s\'\nSection: %s\n' % (f, section)) -for f, section, summary in output_files_gen(): - wikipedia.output('File: \'%s\'\nSection: %s\n' % (f, section)) + output_data = read_output_file(f) + output_files.append(f) - output_data = read_output_file(f) - output_files.append(f) + entries = re.findall('=== (.*?) ===', output_data) - entries = re.findall('=== (.*?) ===', output_data) + if not entries: + continue - if not entries: - continue + if append_date_to_entries: + dt = time.strftime('%d-%m-%Y %H:%M', time.localtime()) + output_data = re.sub("(?m)^(=== \[\[.*?\]\] ===\n)", r"\1{{botdate|%s}}\n" % dt, output_data) - if append_date_to_entries: - dt = time.strftime('%d-%m-%Y %H:%M', time.localtime()) - output_data = re.sub("(?m)^(=== \[\[.*?\]\] ===\n)", r"\1{{botdate|%s}}\n" % dt, output_data) - - m = re.search('(?m)^==\s*%s\s*==' % section, wikitext) - if m: - m_end = re.search(separatorC, wikitext[m.end():]) - if m_end: - wikitext = wikitext[:m_end.start() + m.end()] + output_data + wikitext[m_end.start() + m.end():] + m = re.search('(?m)^==\s*%s\s*==' % section, wikitext) + if m: + m_end = re.search(separatorC, wikitext[m.end():]) + if m_end: + wikitext = wikitext[:m_end.start() + m.end()] + output_data + wikitext[m_end.start() + m.end():] + else: + wikitext += '\n' + output_data else: wikitext += '\n' + output_data - else: - wikitext += '\n' + output_data + if final_summary: + final_summary += ' ' + final_summary += u'%s: %s' % (summary, ', '.join(entries)) + if final_summary: - final_summary += ' ' - final_summary += u'%s: %s' % (summary, ', '.join(entries)) + wikipedia.output(final_summary + '\n') -if final_summary: - wikipedia.output(final_summary + '\n') + # if a page in 'Image' or 'Category' namespace is checked then fix + # title section by adding ':' in order to avoid wiki code effects. - # if a page in 'Image' or 'Category' namespace is checked then fix - # title section by adding ':' in order to avoid wiki code effects. + wikitext = re.sub(u'(?i)=== \[\[%s:' % join_family_data('Image', 6), ur'== [[:\1:', wikitext) + wikitext = re.sub(u'(?i)=== \[\[%s:' % join_family_data('Category', 14), ur'== [[:\1:', wikitext) - wikitext = re.sub(u'(?i)=== \[\[%s:' % join_family_data('Image', 6), ur'== [[:\1:', wikitext) - wikitext = re.sub(u'(?i)=== \[\[%s:' % join_family_data('Category', 14), ur'== [[:\1:', wikitext) + # TODO: + # List of frequent rejected address to improve upload process. - # TODO: - # List of frequent rejected address to improve upload process. + wikitext = re.sub('http://(.*?)((forumcommunity|forumfree).net)',r'<blacklist>\1\2', wikitext) - wikitext = re.sub('http://(.*?)((forumcommunity|forumfree).net)',r'<blacklist>\1\2', wikitext) + if len(final_summary)>=200: + final_summary = final_summary[:200] + final_summary = final_summary[:final_summary.rindex("[")-3] + "..." - if len(final_summary)>=200: - final_summary = final_summary[:200] - final_summary = final_summary[:final_summary.rindex("[")-3] + "..." + try: + put(page, wikitext, comment = final_summary) + for f in output_files: + os.remove(f + '_pending') + wikipedia.output("\'%s\' deleted." % f) + except wikipedia.PageNotSaved: + raise - try: - put(page, wikitext, comment = final_summary) - for f in output_files: - os.remove(f + '_pending') - wikipedia.output("\'%s\' deleted." % f) - except wikipedia.PageNotSaved: - raise + if send_stats: + put_stats() -if send_stats: - put_stats() +def main(): + # + # Send statistics + send_stats = False -wikipedia.stopme() + for arg in wikipedia.handleArgs(): + if arg == "-stats": + send_stats = True + run(send_stats = send_stats) + +if __name__ == "__main__": + try: + main() + finally: + wikipedia.stopme() \ No newline at end of file

16 years, 8 months

[Pywikipedia-l] SVN: [4319] trunk/pywikipedia

by cosoleto＠svn.wikimedia.org

Revision: 4319 Author: cosoleto Date: 2007-09-17 17:50:13 +0000 (Mon, 17 Sep 2007) Log Message: ----------- Short path fix. Added shortpath() in wikipedia.py (thank you Russblau). Fix in copyright.put() Modified Paths: -------------- trunk/pywikipedia/copyright.py trunk/pywikipedia/wikipedia.py Modified: trunk/pywikipedia/copyright.py =================================================================== --- trunk/pywikipedia/copyright.py 2007-09-17 15:39:18 UTC (rev 4318) +++ trunk/pywikipedia/copyright.py 2007-09-17 17:50:13 UTC (rev 4319) @@ -251,16 +251,12 @@ for page, path in exclusion_file_list(): try: if not os.path.exists(path): - print 'Creating file \'%s\' (%s)' % (path, page.aslink()) + print 'Creating file \'%s\' (%s)' % (wikipedia.shortpath(path), page.aslink()) force_update = True else: file_age = time.time() - os.path.getmtime(path) if file_age > 24 * 60 * 60: - short_path = path - if path.startswith(wikipedia.config.base_dir): - short_path = path[len(wikipedia.config.base_dir) - +len(os.path.sep) : ] - print 'Updating file \'%s\' (%s)' % (short_path, page.aslink()) + print 'Updating file \'%s\' (%s)' % (wikipedia.shortpath(path), page.aslink()) force_update = True except OSError: raise @@ -901,7 +897,7 @@ break except wikipedia.SpamfilterError, url: print "Spam filter" - text = re.sub(url[0], '<blacklist>' + url[0][7:], text) + text = re.sub(url[0], '<blacklist>' + url[0][url[0].index('://')+3:], text) except wikipedia.EditConflict: print "Edit conflict" raise wikipedia.EditConflict Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2007-09-17 15:39:18 UTC (rev 4318) +++ trunk/pywikipedia/wikipedia.py 2007-09-17 17:50:13 UTC (rev 4319) @@ -4448,6 +4448,15 @@ """ return makepath(os.path.join(config.base_dir, *filename)) +def shortpath(path): + """ + Short an absolute file path removing bot's base directory part if exists. + """ + shortpath = path + if path.startswith(config.base_dir): + shortpath = path[len(config.base_dir) + len(os.path.sep) : ] + return shortpath + ######################### # Interpret configuration ######################### @@ -4963,4 +4972,3 @@ print 'Pywikipediabot %s' % version.getversion() print 'Python %s' % sys.version doctest.testmod() -

16 years, 8 months

[Pywikipedia-l] [ pywikipediabot-Feature Requests-1791272 ] Version management in wikipedia.py

by SourceForge.net

Feature Requests item #1791272, was opened at 2007-09-10 00:32 Message generated for change (Comment added) made by cosoleto You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603141&aid=1791272&group_… Please note that this message will contain a full copy of the comment thread, including the initial issue submission, for this request, not just the latest update. Category: None Group: None Status: Open Priority: 5 Private: No Submitted By: lusum (lusum) Assigned to: Nobody/Anonymous (nobody) Summary: Version management in wikipedia.py Initial Comment: It should be fine for find easly copyright violation to explore the history of a page. It is possible to have the pare with wikipedia.get. It should be possible to have all the history of a page ( or a particular version ) in a list returned by a function wikipedia.getHistory? ---------------------------------------------------------------------- Comment By: Francesco Cosoleto (cosoleto) Date: 2007-09-17 19:04 Message: Logged In: YES user_id=181280 Originator: NO Hey Lusum. You can use fullVersionHistory() to download history of a page with page contents. Do you want bot build diffs data and send related queries to search engine? ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603141&aid=1791272&group_…

16 years, 8 months

[Pywikipedia-l] [ pywikipediabot-Bugs-1795683 ] No error message if download is interrupted

by SourceForge.net

Bugs item #1795683, was opened at 2007-09-16 10:05 Message generated for change (Comment added) made by cosoleto You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603138&aid=1795683&group_… Please note that this message will contain a full copy of the comment thread, including the initial issue submission, for this request, not just the latest update. Category: General Group: None Status: Open Resolution: None Priority: 5 Private: No Submitted By: Jani Patokallio (jpatokal) Assigned to: Nobody/Anonymous (nobody) Summary: No error message if download is interrupted Initial Comment: I'm using imagetransfer.py to download some images off a Mediawiki site, using the following very straightforward code: uo = wikipedia.MyURLopener() img = uo.open(url) file = open(targetFile, "w"); file.write(img.read()) file.close() img.close() However, I found out the hard way that there is no warning of any kind if the download is interrupted halfway through for any reason. Worse yet, there is no practical way to check if the file was downloaded successfully: the MD5 checksum function requires downloading the image and is thus subject to the same bug! The only way to determine even the file's actual size requires hacking through the file version history, and the getFileVersionHistory() command seems to break against the Mediawiki version of Wikitravel anyway. ---------------------------------------------------------------------- Comment By: Francesco Cosoleto (cosoleto) Date: 2007-09-17 18:23 Message: Logged In: YES user_id=181280 Originator: NO Try this: http://sourceforge.net/tracker/index.php?func=detail&aid=1796316&group_id=9…. ---------------------------------------------------------------------- Comment By: Nobody/Anonymous (nobody) Date: 2007-09-17 04:11 Message: Logged In: NO So I managed to fix getFileVersionHistory by borrowing the code from an older version of pywikipediabot that works with Mediawiki 1.10.1, and now I can at least compare sizes. Can you make your patch available? ---------------------------------------------------------------------- Comment By: Francesco Cosoleto (cosoleto) Date: 2007-09-16 19:05 Message: Logged In: YES user_id=181280 Originator: NO I have tried to fix your getVersionHistory() problem. You can read file length in HTTP headers too: f.info().getheader('Content-Length') I have written a improvised and fully untested patch to wikipedia.getUrl() with check length and transfer resume feature, but I am not sure it's useful. ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603138&aid=1795683&group_…

16 years, 8 months

[Pywikipedia-l] [ pywikipediabot-Patches-1796316 ] upload.py, upload_image(), check length and resume feature

by SourceForge.net

Patches item #1796316, was opened at 2007-09-17 18:20 Message generated for change (Tracker Item Submitted) made by Item Submitter You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603140&aid=1796316&group_… Please note that this message will contain a full copy of the comment thread, including the initial issue submission, for this request, not just the latest update. Category: None Group: None Status: Open Resolution: None Priority: 5 Private: No Submitted By: Francesco Cosoleto (cosoleto) Assigned to: Nobody/Anonymous (nobody) Summary: upload.py, upload_image(), check length and resume feature Initial Comment: Untested. ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603140&aid=1796316&group_…

16 years, 8 months

[Pywikipedia-l] SVN: [4318] trunk/pywikipedia

by russblau＠svn.wikimedia.org

Revision: 4318 Author: russblau Date: 2007-09-17 15:39:18 +0000 (Mon, 17 Sep 2007) Log Message: ----------- Additional data file updates Modified Paths: -------------- trunk/pywikipedia/login.py trunk/pywikipedia/watchlist.py Modified: trunk/pywikipedia/login.py =================================================================== --- trunk/pywikipedia/login.py 2007-09-17 15:31:23 UTC (rev 4317) +++ trunk/pywikipedia/login.py 2007-09-17 15:39:18 UTC (rev 4318) @@ -62,26 +62,7 @@ } } -def makepath(path): - """ creates missing directories for the given path and - returns a normalized absolute version of the path. - - if the given path already exists in the filesystem - the filesystem is not modified. - - - otherwise makepath creates directories along the given path - using the dirname() of the path. You may append - a '/' to the path if you want it to be a directory path. - - from holger(a)trillke.net 2002/03/18 - """ - from os import makedirs - from os.path import normpath,dirname,exists,abspath - - dpath = normpath(dirname(path)) - if not exists(dpath): makedirs(dpath) - return normpath(abspath(path)) - class LoginManager: def __init__(self, password = None, sysop = False, site = None): self.site = site or wikipedia.getSite() @@ -177,8 +158,10 @@ The argument data is the raw data, as returned by getCookie(). Returns nothing.""" - filename = 'login-data/%s-%s-%s-login.data' % (self.site.family.name, self.site.lang, self.username) - f = open(makepath(filename), 'w') + filename = wikipedia.datafilepath('login-data', + '%s-%s-%s-login.data' + % (self.site.family.name, self.site.lang, self.username)) + f = open(filename, 'w') f.write(data) f.close() Modified: trunk/pywikipedia/watchlist.py =================================================================== --- trunk/pywikipedia/watchlist.py 2007-09-17 15:31:23 UTC (rev 4317) +++ trunk/pywikipedia/watchlist.py 2007-09-17 15:39:18 UTC (rev 4318) @@ -34,7 +34,8 @@ # Use cached copy if it exists. watchlist = cache[site] else: - fn = 'watchlists/watchlist-%s-%s.dat' % (site.family.name, site.lang) + fn = wikipedia.datafilepath('watchlists', + 'watchlist-%s-%s.dat' % (site.family.name, site.lang)) try: # find out how old our saved dump is (in seconds) file_age = time.time() - os.path.getmtime(fn) @@ -55,26 +56,6 @@ def isWatched(pageName, site=None): watchlist = get(site) return pageName in watchlist - -def makepath(path): - """ creates missing directories for the given path and - returns a normalized absolute version of the path. - - - if the given path already exists in the filesystem - the filesystem is not modified. - - - otherwise makepath creates directories along the given path - using the dirname() of the path. You may append - a '/' to the path if you want it to be a directory path. - - from holger(a)trillke.net 2002/03/18 - """ - from os import makedirs - from os.path import normpath,dirname,exists,abspath - - dpath = normpath(dirname(path)) - if not exists(dpath): makedirs(dpath) - return normpath(abspath(path)) def refresh(site): # get watchlist special page's URL @@ -91,13 +72,14 @@ watchlist.append(pageName) # Save the watchlist to disk # The file is stored in the watchlists subdir. Create if necessary. - f = open(makepath('watchlists/watchlist-%s-%s.dat' % (site.family.name, site.lang)), 'w') + f = open(wikipedia.datafilepath('watchlists', + 'watchlist-%s-%s.dat' % (site.family.name, site.lang)), 'w') pickle.dump(watchlist, f) f.close() def refresh_all(): import dircache, time - filenames = dircache.listdir('watchlists') + filenames = dircache.listdir(wikipedia.datafilepath('watchlists')) watchlist_filenameR = re.compile('watchlist-([a-z\-:]+).dat') for filename in filenames: match = watchlist_filenameR.match(filename)

16 years, 8 months

[Pywikipedia-l] SVN: [4317] trunk/pywikipedia/catlib.py

by russblau＠svn.wikimedia.org

Revision: 4317 Author: russblau Date: 2007-09-17 15:31:23 +0000 (Mon, 17 Sep 2007) Log Message: ----------- capitalization error Modified Paths: -------------- trunk/pywikipedia/catlib.py Modified: trunk/pywikipedia/catlib.py =================================================================== --- trunk/pywikipedia/catlib.py 2007-09-17 14:43:43 UTC (rev 4316) +++ trunk/pywikipedia/catlib.py 2007-09-17 15:31:23 UTC (rev 4317) @@ -432,7 +432,7 @@ wikipedia.output(u'Skipping %s because of edit conflict' % article.title()) except wikipedia.LockedPage: wikipedia.output(u'Skipping locked page %s' % article.title()) - except wikipedia.SpamFilterError, error: + except wikipedia.SpamfilterError, error: wikipedia.output(u'Changing page %s blocked by spam filter (URL=%s)' % (article.title(), error.url)) except wikipedia.NoUsername:

16 years, 8 months

[Pywikipedia-l] SVN: [4316] trunk/pywikipedia/wikipedia.py

by valhallasw＠svn.wikimedia.org

Revision: 4316 Author: valhallasw Date: 2007-09-17 14:43:43 +0000 (Mon, 17 Sep 2007) Log Message: ----------- typo fix: datafiledpath -> datafilepath Modified Paths: -------------- trunk/pywikipedia/wikipedia.py Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2007-09-17 14:29:03 UTC (rev 4315) +++ trunk/pywikipedia/wikipedia.py 2007-09-17 14:43:43 UTC (rev 4316) @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- """ Library to get and put pages on a MediaWiki. @@ -4670,7 +4670,7 @@ if enabled: if not logname: logname = '%s.log' % calledModuleName() - logfn = datafiledpath('logs', logname) + logfn = datafilepath('logs', logname) try: logfile = codecs.open(logfn, 'a', 'utf-8') except IOError:

16 years, 8 months

[Pywikipedia-l] SVN: [4315] trunk/pywikipedia

by russblau＠svn.wikimedia.org

Revision: 4315 Author: russblau Date: 2007-09-17 14:29:03 +0000 (Mon, 17 Sep 2007) Log Message: ----------- Convert more bots to use standardized data file paths Modified Paths: -------------- trunk/pywikipedia/imagecopy.py trunk/pywikipedia/interwiki.py trunk/pywikipedia/makecat.py trunk/pywikipedia/solve_disambiguation.py trunk/pywikipedia/spellcheck.py trunk/pywikipedia/splitwarning.py trunk/pywikipedia/warnfile.py trunk/pywikipedia/weblinkchecker.py trunk/pywikipedia/wikipedia.py Modified: trunk/pywikipedia/imagecopy.py =================================================================== --- trunk/pywikipedia/imagecopy.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/imagecopy.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -393,7 +393,7 @@ imageP.put(imtxt+u'\n\n{{NowCommons}}', u'{{NowCommons}}') #-etiqueta ok skip view #texto -archivo="Uploadbot.localskips.txt" +archivo=wikipedia.datafilepath("Uploadbot.localskips.txt") try: open(archivo, 'r') except IOError: Modified: trunk/pywikipedia/interwiki.py =================================================================== --- trunk/pywikipedia/interwiki.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/interwiki.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -582,7 +582,8 @@ def reportInterwikilessPage(self, page): wikipedia.output(u"NOTE: %s does not have any interwiki links" % self.originPage.aslink(True)) if config.without_interwiki: - f = codecs.open('without_interwiki.txt', 'a', 'utf-8') + f = codecs.open( + wikipedia.datafilepath('without_interwiki.txt'), 'a', 'utf-8') f.write("# %s \n" % page.aslink()) f.close() @@ -728,7 +729,9 @@ self.problemfound = True if globalvar.autonomous: try: - f = codecs.open('autonomous_problem.dat', 'a', 'utf-8') + f = codecs.open( + wikipedia.datafilepath('autonomous_problem.dat'), + 'a', 'utf-8') f.write("* %s {%s}" % (self.originPage.aslink(True), txt)) if config.interwiki_graph and config.interwiki_graph_url: filename = interwiki_graph.getFilename(self.originPage, extension = config.interwiki_graph_formats[0]) Modified: trunk/pywikipedia/makecat.py =================================================================== --- trunk/pywikipedia/makecat.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/makecat.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -220,7 +220,8 @@ mysite = wikipedia.getSite() wikipedia.setAction(wikipedia.translate(mysite,msg) + ' ' + workingcatname) workingcat = catlib.Category(mysite,mysite.category_namespace()+':'+workingcatname) - filename = 'category/' + wikipedia.UnicodeToAsciiHtml(workingcatname) + '_exclude.txt' + filename = wikipedia.datafilepath('category', + wikipedia.UnicodeToAsciiHtml(workingcatname) + '_exclude.txt') try: f = codecs.open(filename, 'r', encoding = mysite.encoding()) for line in f.readlines(): Modified: trunk/pywikipedia/solve_disambiguation.py =================================================================== --- trunk/pywikipedia/solve_disambiguation.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/solve_disambiguation.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -382,10 +382,11 @@ self.enabled = enabled self.ignorelist = [] - filename = 'disambiguations/' + self.disambPage.urlname() + '.txt' + filename = wikipedia.datafilepath('disambiguations', + self.disambPage.urlname() + '.txt') try: # The file is stored in the disambiguation/ subdir. Create if necessary. - f = codecs.open(self.makepath(filename), 'r', 'utf-8') + f = codecs.open(filename, 'r', 'utf-8') for line in f.readlines(): # remove trailing newlines and carriage returns while line[-1] in ['\n', '\r']: @@ -403,36 +404,17 @@ def ignore(self, refPage): if self.enabled: # Skip this occurence next time. - filename = 'disambiguations/' + self.disambPage.urlname() + '.txt' + filename = wikipedia.datafilepath('disambiguations', + self.disambPage.urlname() + '.txt') try: # Open file for appending. If none exists yet, create a new one. # The file is stored in the disambiguation/ subdir. Create if necessary. - f = codecs.open(self.makepath(filename), 'a', 'utf-8') + f = codecs.open(filename, 'a', 'utf-8') f.write(refPage.urlname() + '\n') f.close() except IOError: pass - def makepath(self, path): - """ creates missing directories for the given path and - returns a normalized absolute version of the path. - - - if the given path already exists in the filesystem - the filesystem is not modified. - - - otherwise makepath creates directories along the given path - using the dirname() of the path. You may append - a '/' to the path if you want it to be a directory path. - - from holger(a)trillke.net 2002/03/18 - """ - from os import makedirs - from os.path import normpath,dirname,exists,abspath - - dpath = normpath(dirname(path)) - if not exists(dpath): makedirs(dpath) - return normpath(abspath(path)) - class DisambiguationRobot(object): ignore_contents = { Modified: trunk/pywikipedia/spellcheck.py =================================================================== --- trunk/pywikipedia/spellcheck.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/spellcheck.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -56,9 +56,9 @@ __version__ = '$Id$' -import re,sys +import re, sys import wikipedia, pagegenerators -import string,codecs +import string, codecs msg={ 'en':u'Bot-aided spell checker', @@ -75,25 +75,6 @@ def __init__(self,text): self.style = text -def makepath(path): - """ creates missing directories for the given path and - returns a normalized absolute version of the path. - - - if the given path already exists in the filesystem - the filesystem is not modified. - - - otherwise makepath creates directories along the given path - using the dirname() of the path. You may append - a '/' to the path if you want it to be a directory path. - - from holger(a)trillke.net 2002/03/18 - """ - from os import makedirs - from os.path import normpath,dirname,exists,abspath - - dpath = normpath(dirname(path)) - if not exists(dpath): makedirs(dpath) - return normpath(abspath(path)) def distance(a,b): # Calculates the Levenshtein distance between a and b. @@ -458,10 +439,11 @@ if not checklang: checklang = mysite.language() wikipedia.setAction(wikipedia.translate(mysite,msg)) - filename = 'spelling/spelling-' + checklang + '.txt' + filename = wikipedia.datafilepath('spelling', + 'spelling-' + checklang + '.txt') print "Getting wordlist" try: - f = codecs.open(makepath(filename), 'r', encoding = mysite.encoding()) + f = codecs.open(filename, 'r', encoding = mysite.encoding()) for line in f.readlines(): # remove trailing newlines and carriage returns try: @@ -541,14 +523,15 @@ title = wikipedia.input(u"Which page to check now? (enter to stop)") finally: wikipedia.stopme() - filename = 'spelling/spelling-' + checklang + '.txt' + filename = wikipedia.datafilepath('spelling', + 'spelling-' + checklang + '.txt') if rebuild: list = knownwords.keys() list.sort() - f = codecs.open(makepath(filename), 'w', encoding = mysite.encoding()) + f = codecs.open(filename, 'w', encoding = mysite.encoding()) else: list = newwords - f = codecs.open(makepath(filename), 'a', encoding = mysite.encoding()) + f = codecs.open(filename, 'a', encoding = mysite.encoding()) for word in list: if Word(word).isCorrect(): if word != uncap(word): Modified: trunk/pywikipedia/splitwarning.py =================================================================== --- trunk/pywikipedia/splitwarning.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/splitwarning.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -17,7 +17,8 @@ count={} # TODO: Variable log filename -logFile = codecs.open('logs/interwiki.log', 'r', 'utf-8') +fn = wikipedia.datafilepath("logs", "interwiki.log") +logFile = codecs.open(fn, 'r', 'utf-8') rWarning = re.compile('WARNING: (?P<family>.+?): \[\[(?P<code>.+?):.*') for line in logFile: m = rWarning.match(line) @@ -26,7 +27,10 @@ code = m.group('code') if code in wikipedia.getSite().languages(): if not files.has_key(code): - files[code] = codecs.open('logs/warning-%s-%s.log' % (family, code), 'w', 'utf-8') + files[code] = codecs.open( + wikipedia.datafilepath('logs', + '/warning-%s-%s.log' % (family, code), + 'w', 'utf-8') count[code] = 0 files[code].write(line) count[code] += 1 Modified: trunk/pywikipedia/warnfile.py =================================================================== --- trunk/pywikipedia/warnfile.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/warnfile.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -115,11 +115,15 @@ def main(): filename = None for arg in wikipedia.handleArgs(): - filename = arg + if os.path.isabs(arg): + filename = arg + else: + filename = wikipedia.datafilepath("logs", arg) if not filename: mysite = wikipedia.getSite() - filename = 'logs/warning-%s-%s.log' % (mysite.family.name, mysite.lang) + filename = wikipedia.datafilepath('logs', + 'warning-%s-%s.log' % (mysite.family.name, mysite.lang) reader = WarnfileReader(filename) bot = WarnfileRobot(reader) bot.run() Modified: trunk/pywikipedia/weblinkchecker.py =================================================================== --- trunk/pywikipedia/weblinkchecker.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/weblinkchecker.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -472,7 +472,9 @@ self.reportThread = reportThread site = wikipedia.getSite() self.semaphore = threading.Semaphore() - self.datfilename = 'deadlinks/deadlinks-%s-%s.dat' % (site.family.name, site.lang) + self.datfilename = wikipedia.datafilepath('deadlinks', + 'deadlinks-%s-%s.dat' + % (site.family.name, site.lang)) # Count the number of logged links, so that we can insert captions # from time to time self.logCount = 0 @@ -498,7 +500,8 @@ isoDate = time.strftime('%Y-%m-%d %H:%M:%S', time.gmtime(date)) errorReport += "** In [[%s]] on %s, %s\n" % (pageTitle, isoDate, error) wikipedia.output(u"** Logging link for deletion.") - txtfilename = 'deadlinks/results-%s-%s.txt' % (site.family.name, site.lang) + txtfilename = wikipedia.datafilepath('deadlinks', + 'results-%s-%s.txt' % (site.family.name, site.lang)) txtfile = codecs.open(txtfilename, 'a', 'utf-8') self.logCount += 1 if self.logCount % 30 == 0: Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2007-09-17 10:51:24 UTC (rev 4314) +++ trunk/pywikipedia/wikipedia.py 2007-09-17 14:29:03 UTC (rev 4315) @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +# -*- coding: utf-8 -*- """ Library to get and put pages on a MediaWiki. @@ -4444,8 +4444,9 @@ base directory. Argument(s) are zero or more directory names, followed by a data file name. + Any directories in the path that do not already exist are created. """ - return os.path.join(config.base_dir, *filename) + return makepath(os.path.join(config.base_dir, *filename)) ######################### # Interpret configuration

16 years, 8 months

[Pywikipedia-l] [ pywikipediabot-Feature Requests-1636098 ] -file: option for category.py

by SourceForge.net

Feature Requests item #1636098, was opened at 2007-01-15 09:59 Message generated for change (Comment added) made by nobody You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603141&aid=1636098&group_… Please note that this message will contain a full copy of the comment thread, including the initial issue submission, for this request, not just the latest update. Category: Interface Improvements (example) Group: None Status: Open Priority: 5 Private: No Submitted By: Nobody/Anonymous (nobody) Assigned to: Nobody/Anonymous (nobody) Summary: -file: option for category.py Initial Comment: Similar to that of replace.py's, so that a list of articles to change categories on can be given in a local file. ---------------------------------------------------------------------- Comment By: Nobody/Anonymous (nobody) Date: 2007-09-17 05:26 Message: Logged In: NO I agree, this MUST be implemented! ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=603141&aid=1636098&group_…

16 years, 8 months

← Newer
1
...
13
14
15
16
17
18
19
...
40
Older →

Jump to page:

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

pywikibot September 2007