Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-22 20:23:12 +00:00
Code Issues Projects Releases Packages Wiki Activity

fix url is too long to be a path error

Browse source
This commit is contained in:
Nick Sweeting 2020-08-18 08:23:57 -04:00
parent e3ac4c2405
commit 2e2b4f8150
1 changed files with 12 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
archivebox/parsers/generic_txt.py
View file

@ -25,6 +25,7 @@ def parse_generic_txt_export(text_file: IO[str]) -> Iterable[Link]:
continue
# if the line is a local file path that resolves, then we can archive it
try:
if Path(line).exists():
yield Link(
url=line,
@ -33,6 +34,9 @@ def parse_generic_txt_export(text_file: IO[str]) -> Iterable[Link]:
tags=None,
sources=[text_file.name],
)
except (OSError, PermissionError):
# nvm, not a valid path...
pass
# otherwise look for anything that looks like a URL in the line
for url in re.findall(URL_REGEX, line):