X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fparse_html_beautifulsoup.py;h=11db56371b0df277dd957484f782e54624721e40;hb=426a3f8ad53f09372d167c14f3bff8f917a9ea40;hp=c45af2b0221a61f441cf5165fc2a25f6fe978bb5;hpb=8226e19cbea0c03e35a3827929514bf5dc350e92;p=bookmarks_db.git

diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py
index c45af2b..11db563 100644
--- a/Robots/parse_html_beautifulsoup.py
+++ b/Robots/parse_html_beautifulsoup.py
@@ -85,8 +85,12 @@ def parse_html(filename, charset=None):
 
    meta = head.find(_find_contenttype, recursive=False)
    if meta:
-      __charset = meta.get("content").lower().split('charset=')[1].split(';')[0]
-      meta_charset = _charset == __charset
+      try:
+         __charset = meta.get("content").lower().split('charset=')[1].split(';')[0]
+      except IndexError: # No charset in the META Content-Type
+         meta_charset = False
+      else:
+         meta_charset = _charset == __charset
    else:
       meta_charset = False