diff --git a/html2md.py b/html2md.py index 9cd7991..b81dbdd 100644 --- a/html2md.py +++ b/html2md.py @@ -62,8 +62,9 @@ class SmartMarkdownConverter: tag.decompose() # Remove common navigation/chrome elements - single combined selector + # Note: aside:not(.quote) preserves Discourse quote blocks noise_selector = ', '.join([ - 'nav', 'header', 'footer', 'aside', + 'nav', 'header', 'footer', 'aside:not(.quote)', '.sidebar', '.nav', '.navigation', '.menu', '.breadcrumb', '.header', '.footer', '.logo', '.site-logo', '#header', '#footer', '#nav', '#sidebar',