X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_ph_etreetidy.py;h=09aa2a3773642cf08df73e100206d782602e8685;hb=11632b7623b2b2e01995f013bc6d8ba01c20cf74;hp=c823dfac4a9929524e2388b3015716f98791c6a7;hpb=80054d3bdcbde67d3b941e0b69b55ca4998f4673;p=bookmarks_db.git

diff --git a/parse_html/bkmk_ph_etreetidy.py b/parse_html/bkmk_ph_etreetidy.py
index c823dfa..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) 2010-2012 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
 
@@ -41,6 +42,9 @@ def parse_html(filename, charset=None, log=None):
                     break
                 except IndexError:
                     meta_charset = False
+        elif m.get('charset', ''):
+            meta_charset = m.get('charset').lower()
+            break
     else:
         meta_charset = False