Log more parsers errors.

[bookmarks_db.git] / Robots / parse_html_beautifulsoup.py

diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py
index c45af2b0221a61f441cf5165fc2a25f6fe978bb5..25719ca9d643ad86e2c2844c572b938d1bf6f792 100644 (file)
--- a/Robots/parse_html_beautifulsoup.py
+++ b/Robots/parse_html_beautifulsoup.py
@@ -49,11 +49,12 @@ class BadDeclParser(BeautifulSoup):
          return j
 
 
-def parse_html(filename, charset=None):
+def parse_html(filename, charset=None, log=None):
    infile = open(filename, 'r')
    try:
       root = BadDeclParser(infile, fromEncoding=charset)
    except TypeError:
+      if log: log("TypeError")
       return None
    finally:
       infile.close()
@@ -61,6 +62,7 @@ def parse_html(filename, charset=None):
    try:
       head = root.html.head
    except AttributeError:
+      if log: log("No HTML in root or no HEAD in HTML")
       return None
 
    if head is None:
@@ -85,8 +87,12 @@ 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