mirror of
https://github.com/ArchiveBox/ArchiveBox.git
synced 2025-05-25 04:04:25 -04:00
fix parsing links from stdin with whitespace
This commit is contained in:
parent
794c043fa4
commit
265e1bd830
1 changed files with 1 additions and 0 deletions
|
@ -262,6 +262,7 @@ def parse_plain_text(text_file):
|
||||||
urls = re.findall(URL_REGEX, line)
|
urls = re.findall(URL_REGEX, line)
|
||||||
|
|
||||||
for url in urls:
|
for url in urls:
|
||||||
|
url = url.strip()
|
||||||
info = {
|
info = {
|
||||||
'url': url,
|
'url': url,
|
||||||
'domain': domain(url),
|
'domain': domain(url),
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue