mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-23 03:06:55 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Add WGET_ARGS to control wget arguments

Browse source
This commit is contained in:
Cristian 2020-10-15 08:31:49 -05:00 • committed by Cristian Vargas
parent 65530e1e5b
commit 24e7a74855
3 changed files with 15 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

10
archivebox/extractors/wget.py
View file

@ -19,6 +19,7 @@ from ..util import (
urldecode,
)
from ..config import (
WGET_ARGS,
TIMEOUT,
SAVE_WGET,
SAVE_WARC,
@ -59,14 +60,7 @@ def save_wget(link: Link, out_dir: Optional[Path]=None, timeout: int=TIMEOUT) ->
cmd = [
WGET_BINARY,
# '--server-response', # print headers for better error parsing
'--no-verbose',
'--adjust-extension',
'--convert-links',
'--force-directories',
'--backup-converted',
'--span-hosts',
'--no-parent',
'-e', 'robots=off',
*WGET_ARGS,
'--timeout={}'.format(timeout),
*(['--restrict-file-names={}'.format(RESTRICT_FILE_NAMES)] if RESTRICT_FILE_NAMES else []),
*(['--warc-file={}'.format(str(warc_path))] if SAVE_WARC else []),