diff --git a/newspaper/parsers.py b/newspaper/parsers.py index be10f37c..2f9ad45a 100644 --- a/newspaper/parsers.py +++ b/newspaper/parsers.py @@ -163,7 +163,7 @@ def clean_article_html(cls, node): article_cleaner = Cleaner() article_cleaner.javascript = True article_cleaner.style = True - article_cleaner.allow_tags = ['a', 'span', 'p', 'br', 'strong', 'b', 'em'] + article_cleaner.allow_tags = ['a', 'span', 'p', 'br', 'strong', 'b', 'em', 'i', 'tt', 'code', 'pre', 'blockquote', 'img', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6'] article_cleaner.remove_unknown_tags = False return article_cleaner.clean_html(node)