X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=parse_html%2Fbkmk_ph_beautifulsoup4.py;h=1095ebce8d510c22df2c9768baed3c27777e1909;hb=48440e20170112c8a036b0c66c1cbe067ed1d87e;hp=e1662ed9e84b9866fceef5f72c0744b35b870111;hpb=22d567ee3a7eac29b4c83eb1344f7bae4ef0bdb1;p=bookmarks_db.git

diff --git a/parse_html/bkmk_ph_beautifulsoup4.py b/parse_html/bkmk_ph_beautifulsoup4.py
index e1662ed..1095ebc 100644
--- a/parse_html/bkmk_ph_beautifulsoup4.py
+++ b/parse_html/bkmk_ph_beautifulsoup4.py
@@ -12,7 +12,9 @@ __all__ = ['parse_html']
 
 
 from bs4 import BeautifulSoup
+
 from .bkmk_ph_util import HTMLParser
+from compat import string_type
 
 universal_charset = "utf-8"
 DEFAULT_CHARSET = "cp1251"  # Stupid default for Russian Cyrillic
@@ -54,8 +56,8 @@ def parse_html(html_text, charset=None, log=None):
         else:
             parts = []
             for part in title:
-                if not isinstance(part, basestring):
-                    part = unicode(part)
+                if not isinstance(part, string_type):
+                    part = part.decode()
                 parts.append(part.strip())
             title = ''.join(parts)
 
@@ -82,12 +84,12 @@ def parse_html(html_text, charset=None, log=None):
             if meta_content:
                 meta_charset = _charset = meta_content.lower()
 
-    if title and (_charset or meta_charset):
-        try:
-            title = title.encode(_charset or meta_charset)
-        except LookupError:
-            title = title.encode(universal_charset)
-            _charset = universal_charset
+    #if title and (_charset or meta_charset):
+    #    try:
+    #        title = title.encode(_charset or meta_charset)
+    #    except LookupError:
+    #        title = title.encode(universal_charset)
+    #        _charset = universal_charset
 
     meta = head.find(_find_refresh, recursive=False)
     if meta: