X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fparse_html_beautifulsoup.py;h=209486c4054f015a179d4469ccaa5adc3f8bbe8f;hb=7f4662c68c41b4dfff5b134d3762591acecba656;hp=d73e4c313a62a67570eb190dac14d5198499ef1b;hpb=9ce15336f7969a5a32eb8fe7e8996a953eaa4eb2;p=bookmarks_db.git

diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py
index d73e4c3..209486c 100644
--- a/Robots/parse_html_beautifulsoup.py
+++ b/Robots/parse_html_beautifulsoup.py
@@ -58,19 +58,27 @@ def parse_html(filename, charset=None):
    finally:
       infile.close()
 
-   _charset = root.originalEncoding
    try:
-      title = root.html.head.title.string.encode(_charset)
+      head = root.html.head
    except AttributeError:
       return None
 
-   meta = root.html.head.find(_find_refresh, recursive=False)
+   if head is None:
+      head = root.html # Some sites put TITLE in HTML without HEAD
+
+   _charset = root.originalEncoding
+   try:
+      title = head.title.string.encode(_charset)
+   except AttributeError:
+      title = '' # HEAD but no TITLE
+
+   meta = head.find(_find_refresh, recursive=False)
    if meta:
       refresh = meta.get("content")
    else:
       refresh = None
 
-   meta = root.html.head.find(_find_icon, recursive=False)
+   meta = head.find(_find_icon, recursive=False)
    if meta:
       icon = meta.get("href")
    else: