X-Git-Url: https://git.phdru.name/?a=blobdiff_plain;f=Robots%2Fparse_html_beautifulsoup.py;h=47ecbaf459f367a9a80d535af1add172709dcf0d;hb=3bc7824ef023e60e84ba4402e658836304c248e3;hp=db291f9fd46df8607709333dbaa304eaba00007e;hpb=fd325219011aaed865f074275b2270112b5e9732;p=bookmarks_db.git diff --git a/Robots/parse_html_beautifulsoup.py b/Robots/parse_html_beautifulsoup.py index db291f9..47ecbaf 100644 --- a/Robots/parse_html_beautifulsoup.py +++ b/Robots/parse_html_beautifulsoup.py @@ -1,7 +1,7 @@ """ HTML Parser using BeautifulSoup - Written by BroytMann. Copyright (C) 2007, 2008 PhiloSoft Design + Written by Broytman. Copyright (C) 2007, 2008 PhiloSoft Design """ import re @@ -87,17 +87,16 @@ def parse_html(filename, charset=None, log=None): # Lookup TITLE in the root title = root.title - if title is None: - title = '' - elif title.string: - title = title.string.encode(_charset) - else: - parts = [] - for part in title: - if not isinstance(part, basestring): - part = unicode(part) - parts.append(part.strip()) - title = ''.join(parts).encode(_charset) + if title is not None: + if title.string: + title = title.string.encode(_charset) + else: + parts = [] + for part in title: + if not isinstance(part, basestring): + part = unicode(part) + parts.append(part.strip()) + title = ''.join(parts).encode(_charset) meta = head.find(_find_contenttype, recursive=False) if meta: