diff --git a/src/Admin/sitemap_gen.py b/src/Admin/sitemap_gen.py index 9c984424b2d3ec5ca640497d4c49f112aa1105dd..fe3dce2ddcbcbc1a94874353416cda4198a68ca3 100755 --- a/src/Admin/sitemap_gen.py +++ b/src/Admin/sitemap_gen.py @@ -88,7 +88,7 @@ def getPage(url): for i in f.readlines(): page += i date = f.info().getdate('Last-Modified') - if date == None: + if date is None: date = (0, 0, 0) else: date = date[:3] @@ -112,7 +112,7 @@ def getRobotParser(startUrl): robotUrl = urlparse.urljoin(startUrl, "/robots.txt") page, date, url = getPage(robotUrl) - if page == None: + if page is None: print "Could not read ROBOTS.TXT at:", robotUrl return None # end if @@ -205,11 +205,11 @@ def parsePages(startUrl, maxUrls, blockExtensions): while True: url = getUrlToProcess(pageMap) - if url == None: + if url is None: break print " ", url page, date, newUrl = getPage(url) - if page == None: + if page is None: del pageMap[url] elif url != newUrl: print "Redirect -> " + newUrl