Author: pfrields
Update of /cvs/docs/release-notes/devel/xmlbeats In directory cvs-int.fedora.redhat.com:/tmp/cvs-serv28686
Modified Files: beatconvert Log Message: Add default behavior to ignore page names with embedded slashes
Index: beatconvert =================================================================== RCS file: /cvs/docs/release-notes/devel/xmlbeats/beatconvert,v retrieving revision 1.6 retrieving revision 1.7 diff -u -r1.6 -r1.7 --- beatconvert 3 Apr 2007 03:17:25 -0000 1.6 +++ beatconvert 3 Apr 2007 03:36:10 -0000 1.7 @@ -5,7 +5,7 @@
import os, sys import urllib -import httplib +import re from time import sleep from optparse import OptionParser
@@ -24,6 +24,9 @@ help="Use URL as base for pages to fetch", metavar="URL") parser.add_option("-p", "--pause", dest="pausetime", default=0.5, help="Wait SEC seconds between fetches", metavar="SEC") +parser.add_option("-s", "--slashes", dest="ignoreSlashes", + action="store_false", default=True, + help="Don't ignore page names with embedded slashes") (opts, args) = parser.parse_args()
try: @@ -41,12 +44,15 @@ if opts.verbose: print "Read", len(pageList), "pages"
for page in pageList: - sleep(opts.pausetime) - if opts.verbose: print "Retrieving", page - data = ''.join(urllib.urlopen(opts.urlbase + page + - "?action=RenderAsDocbook").readlines()) - outXml = open(os.path.join(opts.outdir, page.replace("/", "")), "w") - outXml.write(data) - outXml.close() + if opts.ignoreSlashes and len(re.findall("/", page)) > 0: + continue + else: + sleep(opts.pausetime) + if opts.verbose: print "Retrieving", page + data = ''.join(urllib.urlopen(opts.urlbase + page + + "?action=RenderAsDocbook").readlines()) + outXml = open(os.path.join(opts.outdir, page.replace("/", "")), "w") + outXml.write(data) + outXml.close()
if opts.verbose: print "Finished"