From e1e713036bc0dedd5553d62dd10e46af9db79d34 Mon Sep 17 00:00:00 2001
From: calvin <calvin@e7d03fd6-7b0d-0410-9947-9c21f3af8025>
Date: Mon, 7 Mar 2005 13:57:01 +0000
Subject: [PATCH] use noproxyfor config values to ignore proxy settings

git-svn-id: https://linkchecker.svn.sourceforge.net/svnroot/linkchecker/trunk/linkchecker@2360 e7d03fd6-7b0d-0410-9947-9c21f3af8025
---
 ChangeLog                         | 17 ++++++++++---
 linkcheck/checker/httpurl.py      | 13 +++++++---
 linkcheck/checker/proxysupport.py | 42 ++++++++++++++++++++++---------
 3 files changed, 52 insertions(+), 20 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 5e2738e7..fdbf5e4e 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,16 +1,25 @@
 2.6 "" (released xx.xx.xxxx)
 
-  * New option --low-priority to decrease the priority of spawned
-    threads.
+  * New option --low-priority to decrease the priority of spawned threads.
     Type: feature
     Changed: linkchecker, linkcheck/threader.py
     
-  * If GeoIP Python wrapper is installed, log the country name as
-    info.
+  * If GeoIP Python wrapper is installed, log the country name as info.
     Type: feature
     Changed: linkcheck/checker/consumer.py
     Added: linkcheck/checker/geoip.py
 
+  * New option --no-proxy-for that lets linkchecker contact the given
+    hosts directly instead of going through a proxy.
+    Also configurable in linkcheckerrc
+    Type: feature
+    Changed: linkchecker, linkcheck/checker/proxysupport.py,
+      linkcheck/configuration.py
+
+  * Syntax errors in regular expressions give a useful error message.
+    Type: bugfix
+    Changed: linkchecker, linkcheck/configuration.py
+
 2.5 "Spanglish" (released 4.3.2005)
 
   * Added spanish translation, thanks to Servilio Afre Puentes.
diff --git a/linkcheck/checker/httpurl.py b/linkcheck/checker/httpurl.py
index 529d91a6..4a331f72 100644
--- a/linkcheck/checker/httpurl.py
+++ b/linkcheck/checker/httpurl.py
@@ -191,8 +191,6 @@ class HttpUrl (urlbase.UrlBase, proxysupport.ProxySupport):
         """
         # set the proxy, so a 407 status after this is an error
         self.set_proxy(self.consumer.config["proxy"].get(self.scheme))
-        if self.proxy:
-            self.add_info(_("Using Proxy %r.") % self.proxy)
         self.headers = None
         self.auth = None
         self.cookies = []
@@ -232,10 +230,17 @@ class HttpUrl (urlbase.UrlBase, proxysupport.ProxySupport):
             # proxy enforcement (overrides standard proxy)
             if response.status == 305 and self.headers:
                 oldproxy = (self.proxy, self.proxyauth)
-                self.set_proxy(self.headers.getheader("Location"))
-                self.add_info(_("Enforced Proxy %r.") % self.proxy)
+                newproxy = self.headers.getheader("Location")
+                self.add_info(_("Enforced proxy %r.") % newproxy)
+                self.set_proxy(newproxy)
+                if not self.proxy:
+                    self.set_result(
+                         _("Enforced proxy %r ignored, aborting.") % newproxy,
+                         valid=False)
+                    return
                 response = self._get_http_response()
                 self.headers = response.msg
+                # restore old proxy settings
                 self.proxy, self.proxyauth = oldproxy
             try:
                 tries, response = self.follow_redirections(response)
diff --git a/linkcheck/checker/proxysupport.py b/linkcheck/checker/proxysupport.py
index f70387f5..a9d8d7e5 100644
--- a/linkcheck/checker/proxysupport.py
+++ b/linkcheck/checker/proxysupport.py
@@ -28,18 +28,36 @@ class ProxySupport (object):
     def set_proxy (self, proxy):
         """
         Parse given proxy information and store parsed values.
+        Note that only http:// proxies are supported, both for ftp://
+        and http:// urls.
         """
         self.proxy = proxy
         self.proxyauth = None
-        if self.proxy:
-            if self.proxy[:7].lower() != "http://":
-                self.proxy = "http://"+self.proxy
-            self.proxy = urllib.splittype(self.proxy)[1]
-            self.proxy = urllib.splithost(self.proxy)[0]
-            self.proxyauth, self.proxy = urllib.splituser(self.proxy)
-            if self.proxyauth is not None:
-                if ":" not in self.proxyauth:
-                    self.proxyauth += ":"
-                import base64
-                self.proxyauth = base64.encodestring(self.proxyauth).strip()
-                self.proxyauth = "Basic "+self.proxyauth
+        if not self.proxy:
+            self.add_info(_("Ignoring empty proxy setting for %r") % self.url)
+            return
+        if self.proxy[:7].lower() != "http://":
+            self.proxy = "http://"+self.proxy
+        self.proxy = urllib.splittype(self.proxy)[1]
+        self.proxy = urllib.splithost(self.proxy)[0]
+        self.proxyauth, self.proxy = urllib.splituser(self.proxy)
+        if self.ignore_proxy_host():
+            # log proxy without auth info
+            self.add_info(_("Ignoring proxy setting %r") % self.proxy)
+            self.proxy = None
+            self.proxyauth = None
+            return
+        self.add_info(_("Using proxy %r.") % self.proxy)
+        if self.proxyauth is not None:
+            if ":" not in self.proxyauth:
+                self.proxyauth += ":"
+            import base64
+            self.proxyauth = base64.encodestring(self.proxyauth).strip()
+            self.proxyauth = "Basic "+self.proxyauth
+
+
+    def ignore_proxy_host (self):
+        for ro in self.consumer.config["noproxyfor"]:
+            if ro.search(self.host):
+                return True
+        return False