http://www.mediawiki.org/wiki/Special:Code/pywikipedia/9902

Revision: 9902 Author: drtrigon Date: 2012-02-17 11:34:20 +0000 (Fri, 17 Feb 2012) Log Message: ----------- Adding capabilities of DrTrigonBot 'wikipedia' script; 'getParsedString' and 'getExpandedString'

Modified Paths: -------------- trunk/pywikipedia/wikipedia.py

Modified: trunk/pywikipedia/wikipedia.py =================================================================== --- trunk/pywikipedia/wikipedia.py 2012-02-16 22:44:36 UTC (rev 9901) +++ trunk/pywikipedia/wikipedia.py 2012-02-17 11:34:20 UTC (rev 9902) @@ -4807,8 +4807,11 @@ versionnumber: Return int identifying the MediaWiki version. live_version: Return version number read from Special:Version. checkCharset(charset): Warn if charset doesn't match family file. - server_time : returns server time (currently userclock depending) + server_time: returns server time (currently userclock depending)

+ getParsedString: Parses the string with API and returns html content. + getExpandedString: Expands the string with API and returns wiki content. + linktrail: Return regex for trailing chars displayed as part of a link. disambcategory: Category in which disambiguation pages are listed.

@@ -7581,6 +7584,67 @@ files.append(image) return files

+ def getParsedString(self, string, keeptags = [u'*']): + """Parses the string with API and returns html content. + + @param string: String that should be parsed. + @type string: string + @param keeptags: Defines which tags (wiki, HTML) should NOT be removed. + @type keeptags: list + + Returns the string given, parsed through the wiki parser. + """ + + if not self.has_api(): + raise Exception('parse: no API: not implemented') + + # call the wiki to get info + params = { + u'action' : u'parse', + u'text' : string, + } + + pywikibot.get_throttle() + pywikibot.output(u"Parsing string through the wiki parser via API.") + + result = query.GetData(params, self) + r = result[u'parse'][u'text'][u'*'] + + # disable/remove comments + r = pywikibot.removeDisabledParts(r, tags = ['comments']).strip() + + # disable/remove ALL tags + if not (keeptags == [u'*']): + r = removeHTMLParts(r, keeptags = keeptags).strip() + + return r + + def getExpandedString(self, string): + """Expands the string with API and returns wiki content. + + @param string: String that should be expanded. + @type string: string + + Returns the string given, expanded through the wiki parser. + """ + + if not self.has_api(): + raise Exception('expandtemplates: no API: not implemented') + + # call the wiki to get info + params = { + u'action' : u'expandtemplates', + u'text' : string, + } + + pywikibot.get_throttle() + pywikibot.output(u"Expanding string through the wiki parser via API.") + + result = query.GetData(params, self) + r = result[u'expandtemplates'][u'*'] + + return r + # Caches to provide faster access _sites = {} _namespaceCache = {}