diff --git a/archivebox/extractors/title.py b/archivebox/extractors/title.py index 19a78591..dc496c4e 100644 --- a/archivebox/extractors/title.py +++ b/archivebox/extractors/title.py @@ -26,7 +26,7 @@ from ..logging_util import TimedProgress HTML_TITLE_REGEX = re.compile( r'' # start matching text after tag - r'(.[^<>]+)', # get everything up to these symbols + r'([^<>]+)', # get everything up to these symbols re.IGNORECASE | re.MULTILINE | re.DOTALL | re.UNICODE, )