X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fparse_html.py;h=a83585df318afb1602a916a1a17768485a099138;hb=8ce74f839238093d7278aa041ff55dbcb7abd3a0;hp=bc9a8d4950fc2ae430a111c423c78c3a5c5755b9;hpb=f8c96fe94544f486e9e76640d16fc355daa4db70;p=bookmarks_db.git

diff --git a/Robots/parse_html.py b/Robots/parse_html.py
index bc9a8d4..a83585d 100755
--- a/Robots/parse_html.py
+++ b/Robots/parse_html.py
@@ -20,6 +20,13 @@ except ImportError:
 else:
    parsers.append(parse_html_beautifulsoup.parse_html)
 
+try:
+   from parse_html_lxml import parse_html
+except ImportError:
+   pass
+else:
+    parsers.append(parse_html)
+
 try:
    from parse_html_htmlparser import parse_html
 except ImportError:
@@ -136,6 +143,14 @@ def parse_html(filename, charset=None, log=None):
       final_title = ' '.join([s for s in parts if s])
       if log and (final_title <> converted_title): log("   final title    : %s" % final_title)
       parser.title = final_title
+
+   icon = parser.icon
+   if isinstance(icon, unicode):
+       try:
+           parser.icon = icon.encode('ascii')
+       except UnicodeEncodeError:
+           if parser.charset:
+               parser.icon = icon.encode(parser.charset)
    return parser