mirror of
https://github.com/ArchiveBox/ArchiveBox.git
synced 2026-04-05 15:27:53 +10:00
36 lines
977 B
Python
36 lines
977 B
Python
__package__ = 'abx_plugin_wget'
|
|
|
|
# from pathlib import Path
|
|
|
|
# from pydantic_pkgr import BinName
|
|
|
|
# from .binaries import WGET_BINARY
|
|
# from .wget_util import wget_output_path
|
|
|
|
# class WgetExtractor(BaseExtractor):
|
|
# name: ExtractorName = 'wget'
|
|
# binary: BinName = WGET_BINARY.name
|
|
|
|
# def get_output_path(self, snapshot) -> Path | None:
|
|
# wget_index_path = wget_output_path(snapshot.as_link())
|
|
# if wget_index_path:
|
|
# return Path(wget_index_path)
|
|
# return None
|
|
|
|
# WGET_EXTRACTOR = WgetExtractor()
|
|
|
|
|
|
# class WarcExtractor(BaseExtractor):
|
|
# name: ExtractorName = 'warc'
|
|
# binary: BinName = WGET_BINARY.name
|
|
|
|
# def get_output_path(self, snapshot) -> Path | None:
|
|
# warc_files = list((Path(snapshot.link_dir) / 'warc').glob('*.warc.gz'))
|
|
# if warc_files:
|
|
# return sorted(warc_files, key=lambda x: x.stat().st_size, reverse=True)[0]
|
|
# return None
|
|
|
|
|
|
# WARC_EXTRACTOR = WarcExtractor()
|
|
|