From: Oleg Broytman <phd@phdru.name>
Date: Sun, 2 Jan 2011 23:56:53 +0000 (+0000)
Subject: Get favicon before HTML redirect (refresh).
X-Git-Tag: v4.5.3~73
X-Git-Url: https://git.phdru.name/?a=commitdiff_plain;h=c79561dfd3ff2e2a69b542211bfb7c692210776d;p=bookmarks_db.git

Get favicon before HTML redirect (refresh).


git-svn-id: file:///home/phd/archive/SVN/bookmarks_db/trunk@303 fdd5c36f-1aea-0310-aeeb-c58d7e2b6c23
---

diff --git a/Robots/bkmk_rsimple.py b/Robots/bkmk_rsimple.py
index 63f9602..41fa2b3 100644
--- a/Robots/bkmk_rsimple.py
+++ b/Robots/bkmk_rsimple.py
@@ -176,24 +176,6 @@ class robot_simple(Robot):
                   parser = parse_html(fname, charset, self.log)
                   if parser:
                       bookmark.real_title = parser.title
-                      if parser.refresh:
-                         refresh = parser.refresh
-                         try:
-                            url = refresh.split('=', 1)[1]
-                         except IndexError:
-                            url = "self"
-                         try:
-                            timeout = float(refresh.split(';')[0])
-                         except (IndexError, ValueError):
-                            raise RedirectException("html", "Bad redirect to %s (%s)" % (url, refresh))
-                         else:
-                            try:
-                               timeout = int(refresh.split(';')[0])
-                            except ValueError:
-                               pass # float timeout
-                            raise RedirectException("html", "%s (%s sec)" % (url, timeout))
-
-                      # Get favicon.ico
                       icon = parser.icon
                   else:
                      icon = None
@@ -241,6 +223,22 @@ class robot_simple(Robot):
                         else:
                            self.log("   no icon        : bad content type '%s'" % content_type)
                            icons[icon] = None
+                  if parser and parser.refresh:
+                     refresh = parser.refresh
+                     try:
+                        url = refresh.split('=', 1)[1]
+                     except IndexError:
+                        url = "self"
+                     try:
+                        timeout = float(refresh.split(';')[0])
+                     except (IndexError, ValueError):
+                        raise RedirectException("html", "Bad redirect to %s (%s)" % (url, refresh))
+                     else:
+                        try:
+                           timeout = int(refresh.split(';')[0])
+                        except ValueError:
+                           pass # float timeout
+                        raise RedirectException("html", "%s (%s sec)" % (url, timeout))
 
             except KeyError, key:
                self.log("   no header: %s" % key)
diff --git a/doc/ANNOUNCE b/doc/ANNOUNCE
index 8cb06eb..15efd76 100644
--- a/doc/ANNOUNCE
+++ b/doc/ANNOUNCE
@@ -5,11 +5,16 @@ WHAT IS IT
    A set of classes, libraries, programs and plugins I use to manipulate my
 bookmarks.html.
 
+WHAT'S NEW in version 4.3.1 (2011-??-??).
+
+Get favicon before HTML redirect (refresh).
+
+
 WHAT'S NEW in version 4.3.0 (2011-01-01).
 
 Robots no longer have one global temporary file - there are at least two
 (html and favicon), and in the future there will be more for
-asynchronous robot(s) that would test many URLs in parallel.
+asynchronous robot(s) that will test many URLs in parallel.
 
 
 WHERE TO GET