mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-23 11:17:02 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

config fixes

Browse source
This commit is contained in:
Nick Sweeting 2020-10-31 07:55:27 -04:00
parent aa71a231f6
commit ac9e0e356d
8 changed files with 57 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

2
archivebox/extractors/archive_org.py
View file

@ -59,7 +59,7 @@ def save_archive_dot_org(link: Link, out_dir: Optional[Path]=None, timeout: int=
result = run(cmd, cwd=str(out_dir), timeout=timeout)
content_location, errors = parse_archive_dot_org_response(result.stdout)
if content_location:
archive_org_url = 'https://web.archive.org{}'.format(content_location[0])
archive_org_url = content_location[0]
elif len(errors) == 1 and 'RobotAccessControlException' in errors[0]:
archive_org_url = None
# raise ArchiveError('Archive.org denied by {}/robots.txt'.format(domain(link.url)))