From 44ac994edca503d6b41d04a64fe67d581deb5926 Mon Sep 17 00:00:00 2001
From: Arthur de Jong <arthur@arthurdejong.org>
Date: Tue, 24 Apr 2007 18:53:11 +0000
Subject: handle ID attribute as anchor on any tag

git-svn-id: http://arthurdejong.org/svn/webcheck/webcheck@326 86f53f14-5ff3-0310-afe5-9b438ce3f40c
---
 parsers/html/beautifulsoup.py | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/parsers/html/beautifulsoup.py b/parsers/html/beautifulsoup.py
index a18d1cc..61abb59 100644
--- a/parsers/html/beautifulsoup.py
+++ b/parsers/html/beautifulsoup.py
@@ -91,13 +91,13 @@ def parse(content, link):
             link.add_anchor(crawler.urlescape(htmlunescape(a['id']).strip()))
         # add the anchor
         link.add_anchor(a_name)
-    # <a id="ID">
-    for a in soup.findAll('a', id=True):
-        # skip entries that have a name
-        if a.has_key('name'):
+    # <ANY id="ID">
+    for elem in soup.findAll(id=True):
+        # skip anchor that have a name
+        if elem.name == 'a' and elem.has_key('name'):
             continue
         # add the anchor
-        link.add_anchor(crawler.urlescape(htmlunescape(a['id']).strip()))
+        link.add_anchor(crawler.urlescape(htmlunescape(elem['id']).strip()))
     # <frameset><frame src="URL"...>...</frameset>
     for frame in soup.findAll('frame', src=True):
         embed = crawler.urlescape(htmlunescape(frame['src']).strip())
-- 
cgit v1.2.3