X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_ph_etreetidy.py;h=09aa2a3773642cf08df73e100206d782602e8685;hb=ff958ee854d80253b271de04945a57fafc0363c4;hp=b85ae2ae209c37decf8ebce34e649d25dcc7012b;hpb=1249f2d538e9d679421d7bbb59dfac33fad537f4;p=bookmarks_db.git

diff --git a/parse_html/bkmk_ph_etreetidy.py b/parse_html/bkmk_ph_etreetidy.py
index b85ae2a..09aa2a3 100644
--- 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) 2010-2017 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
 
@@ -42,8 +43,8 @@ def parse_html(filename, charset=None, log=None):
                 except IndexError:
                     meta_charset = False
         elif m.get('charset', ''):
-           meta_charset = m.get('charset').lower()
-           break
+            meta_charset = m.get('charset').lower()
+            break
     else:
         meta_charset = False