mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-24 03:35:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

Some refinements of the external-link checking code: insert the errors

Browse source 
in the 'bad' dictionary (sanitize them so they are picklable; the
sanitation code is now a subroutine); don't check mailto: URLs; omit
colon in Error message.
This commit is contained in:
Guido van Rossum 1997-01-30 04:26:57 +00:00
parent de66268588
commit 2739cd74b3
1 changed files with 22 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

31
Tools/webchecker/webchecker.py
View file

@ -305,13 +305,18 @@ class Checker:
show("HREF ", url, " from", self.ext[url])
if not checkext:
continue
if url[:7] == 'mailto:':
if verbose > 2: print "Not checking", url
continue
if verbose > 2: print "Checking", url, "..."
try:
f = self.urlopener.open(url)
f.close()
if verbose > 3: print "OK"
except IOError, msg:
print "Error:", msg
msg = sanitize(msg)
print "Error", msg
self.bad[url] = msg
def report_errors(self):
if not self.bad:
@ -327,7 +332,10 @@ class Checker:
try:
origins = self.done[url]
except KeyError:
origins = self.todo[url]
try:
origins = self.todo[url]
except KeyError:
origins = self.ext[url]
for source, rawlink in origins:
triple = url, rawlink, self.bad[url]
try:
@ -406,13 +414,7 @@ class Checker:
try:
f = self.urlopener.open(url)
except IOError, msg:
if (type(msg) == TupleType and
len(msg) >= 4 and
msg[0] == 'http error' and
type(msg[3]) == InstanceType):
# Remove the Message instance -- it may contain
# a file object which prevents pickling.
msg = msg[:3] + msg[4:]
msg = sanitize(msg)
if verbose > 0:
print "Error ", msg
if verbose > 0:
@ -549,5 +551,16 @@ def show(p1, link, p2, origins):
print
def sanitize(msg):
if (type(msg) == TupleType and
len(msg) >= 4 and
msg[0] == 'http error' and
type(msg[3]) == InstanceType):
# Remove the Message instance -- it may contain
# a file object which prevents pickling.
msg = msg[:3] + msg[4:]
return msg
if __name__ == '__main__':
main()