Calculate if the charset came from HTTP or from HTML meta.

[bookmarks_db.git] / Robots / parse_html_beautifulsoup.py

diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py
index 4f395a16507e58d5e9a600de00b9056cb2aeb94b..130b20a7ca8f53a472526125be0390b029251c78 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
@@ -16,14 +17,15 @@ class DummyParser(object):
       self.refresh = refresh
       self.icon = icon
 
+
 def parse_html(filename, charset=None):
    infile = open(filename, 'r')
    root = BeautifulSoup(infile, fromEncoding=charset)
    infile.close()
 
-   charset = root.originalEncoding
+   _charset = root.originalEncoding
    try:
-      title = root.html.head.title.string.encode(charset)
+      title = root.html.head.title.string.encode(_charset)
    except AttributeError:
       title = ''
 
@@ -47,7 +49,7 @@ def parse_html(filename, charset=None):
       else:
          icon = None
 
-   parser = DummyParser(charset, False, title, refresh, icon)
+   parser = BSoupParser(_charset, _charset == charset, title, refresh, icon)
    return parser
 
 def _find_refresh(Tag):