fix parsing links from stdin with whitespace

2025-09-01 10:23:38 +02:00 · 2019-02-04 20:03:32 -08:00
parent 794c043fa4
commit 265e1bd830
1 changed files with 1 additions and 0 deletions
--- 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),