Inherit HTMLParser (for unescape).

git-svn-id: file:///home/phd/archive/SVN/bookmarks_db/trunk@107 fdd5c36f-1aea-0310-aeeb-c58d7e2b6c23

diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py
index 4f395a16507e58d5e9a600de00b9056cb2aeb94b..e0129fd1d4cb3c7b34f69f8c772946c04afab645 100644 (file)
--- a/Robots/parse_html_beautifulsoup.py
+++ b/Robots/parse_html_beautifulsoup.py
@@ -4,10 +4,11 @@
    Written by BroytMann. Copyright (C) 2007 PhiloSoft Design
 """
 
+from HTMLParser import HTMLParser
 from BeautifulSoup import BeautifulSoup
 
 
-class DummyParser(object):
+class BSoupParser(HTMLParser):
    def __init__(self, charset, meta, title, refresh, icon):
       object.__init__(self)
       self.charset = charset
@@ -16,6 +17,7 @@ class DummyParser(object):
       self.refresh = refresh
       self.icon = icon
 
+
 def parse_html(filename, charset=None):
    infile = open(filename, 'r')
    root = BeautifulSoup(infile, fromEncoding=charset)
@@ -47,7 +49,7 @@ def parse_html(filename, charset=None):
       else:
          icon = None
 
-   parser = DummyParser(charset, False, title, refresh, icon)
+   parser = BSoupParser(charset, False, title, refresh, icon)
    return parser
 
 def _find_refresh(Tag):