From 265e1bd8305afd9b9b541ca53948ba4118ea50ff Mon Sep 17 00:00:00 2001 From: Nick Sweeting Date: Mon, 4 Feb 2019 20:03:32 -0800 Subject: [PATCH] fix parsing links from stdin with whitespace --- archivebox/parse.py | 1 + 1 file changed, 1 insertion(+) diff --git a/archivebox/parse.py b/archivebox/parse.py index a66b7c59..7314a543 100644 --- a/archivebox/parse.py +++ b/archivebox/parse.py @@ -262,6 +262,7 @@ def parse_plain_text(text_file): urls = re.findall(URL_REGEX, line) for url in urls: + url = url.strip() info = { 'url': url, 'domain': domain(url),