Spin off checking of external page in a subroutine.

Increase MAXPAGE to 150K.
Add back printing of __doc__ for usage message.

Tools/webchecker/webchecker.py

@@ -121,7 +121,7 @@ import robotparser
 
 # Tunable parameters
 DEFROOT = "file:/usr/local/etc/httpd/htdocs/"	# Default root URL
-MAXPAGE = 50000				# Ignore files bigger than this
+MAXPAGE = 150000			# Ignore files bigger than this
 ROUNDSIZE = 50				# Number of links processed per round
 DUMPFILE = "@webchecker.pickle"		# Pickled checkpoint
 AGENTNAME = "webchecker"		# Agent name for robots.txt parser
@@ -145,6 +145,7 @@ def main():
     except getopt.error, msg:
 	sys.stdout = sys.stderr
 	print msg
+	print __doc__%globals()
 	sys.exit(2)
     for o, a in opts:
 	if o == '-R':
@@ -314,11 +315,13 @@ class Checker:
 	for url in urls:
 	    if verbose > 0:
 		show("HREF ", url, " from", self.ext[url])
-	    if not checkext:
-		continue
-	    if url[:7] == 'mailto:':
+	    if checkext:
+		self.checkextpage(url)
+
+    def checkextpage(self, url):
+	if url[:7] == 'mailto:' or url[:5] == 'news:':
 	    if verbose > 2: print "Not checking", url
-		continue
+	    return
 	if verbose > 2: print "Checking", url, "..."
 	try:
 	    f = self.urlopener.open(url)