Change parse_html to parse strings, not files

[bookmarks_db.git] / parse_html / bkmk_ph_etreetidy.py

diff --git a/parse_html/bkmk_ph_etreetidy.py b/parse_html/bkmk_ph_etreetidy.py
index b85ae2ae209c37decf8ebce34e649d25dcc7012b..fc596b18712b460085603e09fcf3ca9a381837ff 100644 (file)
--- a/parse_html/bkmk_ph_etreetidy.py
+++ b/parse_html/bkmk_ph_etreetidy.py
@@ -1,10 +1,11 @@
 """HTML Parser using ElementTree+TidyLib.
 
 This file is a part of Bookmarks database and Internet robot.
+
 """
 
 __author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 2010-2013 PhiloSoft Design"
+__copyright__ = "Copyright (C) 2010-2014 PhiloSoft Design"
 __license__ = "GNU GPL"
 
 __all__ = ['parse_html']
@@ -14,9 +15,9 @@ from elementtidy import TidyHTMLTreeBuilder
 from .bkmk_ph_util import HTMLParser
 
 
-def parse_html(filename, charset=None, log=None):
+def parse_html(html_text, charset=None, log=None):
     try:
-        html_tree = TidyHTMLTreeBuilder.parse(filename)
+        html_tree = TidyHTMLTreeBuilder.parseString(html_text)
     except:
         return None