Catch UnicodeError for invalid host names.

doc/changelog.txt

@@ -3,9 +3,9 @@
 Features:
 - checking: Support <link rel="dns-prefetch"> URLs.
 - logging: Sending SIGUSR1 signal prints the stack trace of all current
-  running threads. This makes it easier to debug deadlocks.
-- gui: Added support of Drag-and-Drop of local files. If the local file is
-  a LinkChecker project (.lcp) it is loaded automatically, else the check
+  running threads. This makes debugging deadlocks easier.
+- gui: Support Drag-and-Drop of local files. If the local file is
+  a LinkChecker project (.lcp) file it is loaded, else the check
   URL is set to the local file URL.
 
 Changes:
@@ -14,6 +14,8 @@ Changes:
 Fixes:
 - checking: Fix a crash when closing a Word document after scanning failed.
   Closes: GH bug #369
+- checking: Catch UnicodeError from idna.encode() fixing an internal error when
+  trying to connect to certain invalid hostnames.
 
 
 8.3 "Mahna Mahna Killer" (released 6.1.2013)

linkcheck/checker/const.py

@@ -53,6 +53,8 @@ ExcCacheList = [
     ftplib.error_temp,
     ftplib.error_perm,
     ftplib.error_proto,
+    # idna.encode(), called from socket.create_connection()
+    UnicodeError,
 ]
 
 # Exceptions that do not put the URL in the cache so that the URL can

linkcheck/checker/urlbase.py

@@ -526,14 +526,17 @@ class UrlBase (object):
             self.check_connection()
             self.add_size_info()
             self.add_country_info()
-        except tuple(ExcList):
+        except tuple(ExcList) as exc:
             value = self.handle_exception()
             # make nicer error msg for unknown hosts
-            if isinstance(value, socket.error) and value.args[0] == -2:
+            if isinstance(exc, socket.error) and exc.args[0] == -2:
                 value = _('Hostname not found')
             # make nicer error msg for bad status line
-            if isinstance(value, httplib.BadStatusLine):
+            elif isinstance(exc, httplib.BadStatusLine):
                 value = _('Bad HTTP response %(line)r') % {"line": str(value)}
+            elif isinstance(exc, UnicodeError):
+                # idna.encode(host) failed
+                value = _('Bad hostname %(host)r: %(msg)s') % {'host': self.host, 'msg': str(value)}
             self.set_result(unicode_safe(value), valid=False)
         self.checktime = time.time() - check_start
         if self.do_check_content:

tests/checker/data/http.html

@@ -21,3 +21,6 @@
 <object classid="clsid:12345-67890" codebase="http://example.org/foo/ #a=1,2,3">
 
 <!-- <a href=http://nocheckin> no check because of comment -->
+
+<!-- throws UnicodeError from idna.encode() -->
+<a href="http://.example.org/">UnicodeError</a>

tests/checker/data/http.html.result

@@ -1,7 +1,7 @@
 url http://localhost:%(port)d/%(datadir)s/http.html
 cache key http://localhost:%(port)d/%(datadir)s/http.html
 real url http://localhost:%(port)d/%(datadir)s/http.html
-info 13 URLs parsed.
+info 14 URLs parsed.
 valid
 
 url dns://www.example.org
@@ -76,3 +76,9 @@ info Redirected to `http://www.iana.org/domains/example'.
 warning Anchor `a%%3D1%%2C2%%2C3' not found. Available anchors: -.
 valid
 
+url http://.example.org/
+cache key http://.example.org/
+real url http://.example.org/
+name UnicodeError
+warning Access denied by robots.txt, skipping content checks.
+error