X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;ds=sidebyside;f=parse_html%2Fbkmk_ph_etreetidy.py;h=eadcca32605428644b9fa41f1446bafef2386077;hb=3035a4957e210d7a6befcb224f237021b992d285;hp=fc596b18712b460085603e09fcf3ca9a381837ff;hpb=00549b1c0622ee6ed0ac12249097cf4562bc486e;p=bookmarks_db.git

diff --git a/parse_html/bkmk_ph_etreetidy.py b/parse_html/bkmk_ph_etreetidy.py
index fc596b1..eadcca3 100644
--- a/parse_html/bkmk_ph_etreetidy.py
+++ b/parse_html/bkmk_ph_etreetidy.py
@@ -5,7 +5,7 @@ This file is a part of Bookmarks database and Internet robot.
 """
 
 __author__ = "Oleg Broytman <phd@phdru.name>"
-__copyright__ = "Copyright (C) 2010-2014 PhiloSoft Design"
+__copyright__ = "Copyright (C) 2010-2023 PhiloSoft Design"
 __license__ = "GNU GPL"
 
 __all__ = ['parse_html']
@@ -16,6 +16,8 @@ from .bkmk_ph_util import HTMLParser
 
 
 def parse_html(html_text, charset=None, log=None):
+    if not html_text:
+        return None
     try:
         html_tree = TidyHTMLTreeBuilder.parseString(html_text)
     except:
@@ -43,13 +45,13 @@ def parse_html(html_text, 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
 
-    if title and (charset or meta_charset):
-        title = title.encode(charset or meta_charset)
+    #if title and (charset or meta_charset):
+    #    title = title.encode(charset or meta_charset)
 
     for m in meta:
         if m.get('http-equiv', '').lower() == 'refresh':