Here's a pyparsing program that reads my personal web page, and spits out HTML with all of the HREF's reversed.
-- Paul (Download pyparsing at http://pyparsing.sourceforge.net.) from pyparsing import Literal, quotedString import urllib LT = Literal("<") GT = Literal(">") EQUALS = Literal("=") htmlAnchor = LT + "A" + "HREF" + EQUALS + quotedString.setResultsName("href") + GT def convertHREF(s,l,toks): # do HREF conversion here - for demonstration, we will just reverse them print toks.href return "<A HREF=%s>" % toks.href[::-1] htmlAnchor.setParseAction( convertHREF ) inputURL = "http://www.geocities.com/ptmcg"; inputPage = urllib.urlopen(inputURL) inputHTML = inputPage.read() inputPage.close() print htmlAnchor.transformString( inputHTML ) -- http://mail.python.org/mailman/listinfo/python-list
