Strip embedded whitespace from URLs given at the commandline or the GUI.

doc/changelog.txt

@@ -9,6 +9,8 @@ Changes:
   sending false positive status codes for HEAD requests.
 - checking: Strip leading and trailing whitespace from URLs and print
   a warning instead of having errors.
+  Also all embedded whitespace is stripped from URLs given at the
+  commandline or the GUI.
   Closes: SF bug #3196918
 
 

linkcheck/gui/__init__.py

@@ -262,7 +262,7 @@ Version 2 or later.
 
     def get_url (self):
         """Return URL to check from the urlinput widget."""
-        url = unicode(self.urlinput.text()).strip()
+        url = strformat.stripall(unicode(self.urlinput.text()))
         if url.startswith(u"www."):
             url = u"http://%s" % url
         elif url.startswith(u"ftp."):

linkcheck/lc_cgi.py

@@ -77,7 +77,7 @@ def checklink (out=sys.stdout, form=None, env=os.environ):
     # start checking
     aggregate = director.get_aggregate(config)
     get_url_from = checker.get_url_from
-    url = form["url"].value
+    url = strformat.stripall(form["url"].value)
     url_data = get_url_from(url, 0, aggregate)
     try:
         add_intern_pattern(url_data, config)

linkchecker

@@ -761,7 +761,7 @@ if options.stdin:
     args.extend(read_stdin_urls())
 if args:
     for url in args:
-        aggregate_url(aggregate, config, url)
+        aggregate_url(aggregate, config, strformat.stripall(url))
 else:
     log.warn(LOG_CMDLINE, _("no files or URLs given"))
 # set up profiling