Mirrors/ArchiveBox
2
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox synced 2024-11-10 06:34:16 +00:00
Code Issues Projects Releases Packages Wiki Activity

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
Show stats Download patch file Download diff file Expand all files Collapse all files

13
archivebox/config/__init__.py
View file

@ -120,7 +120,17 @@ CONFIG_DEFAULTS: Dict[str, ConfigDefaultDict] = {
'--audio-format', 'mp3',
'--audio-quality', '320K',
'--embed-thumbnail',
'--add-metadata']}
'--add-metadata']},
'WGET_ARGS': {'type': list, 'default': ['--no-verbose',
'--adjust-extension',
'--convert-links',
'--force-directories',
'--backup-converted',
'--span-hosts',
'--no-parent',
'-e', 'robots=off',
]}
},
'DEPENDENCY_CONFIG': {
@ -276,6 +286,7 @@ DERIVED_CONFIG_DEFAULTS: ConfigDefaultDict = {
'WGET_USER_AGENT': {'default': lambda c: c['WGET_USER_AGENT'].format(**c)},
'SAVE_WGET': {'default': lambda c: c['USE_WGET'] and c['SAVE_WGET']},
'SAVE_WARC': {'default': lambda c: c['USE_WGET'] and c['SAVE_WARC']},
'WGET_ARGS': {'default': lambda c: c['WGET_ARGS'] or []},
'USE_SINGLEFILE': {'default': lambda c: c['USE_SINGLEFILE'] and c['SAVE_SINGLEFILE']},
'SINGLEFILE_VERSION': {'default': lambda c: bin_version(c['SINGLEFILE_BINARY']) if c['USE_SINGLEFILE'] else None},

1
archivebox/config/stubs.py
View file

@ -95,6 +95,7 @@ class ConfigDict(BaseConfig, total=False):
CHROME_BINARY: Optional[str]
YOUTUBEDL_ARGS: Optional[str]
WGET_ARGS: Optional[str]
ConfigDefaultValueGetter = Callable[[ConfigDict], ConfigValue]

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 []),