diff options
Diffstat (limited to 'python/sandcrawler/fileset_strategies.py')
-rw-r--r-- | python/sandcrawler/fileset_strategies.py | 13 |
1 files changed, 7 insertions, 6 deletions
diff --git a/python/sandcrawler/fileset_strategies.py b/python/sandcrawler/fileset_strategies.py index d12fc15..c9f182c 100644 --- a/python/sandcrawler/fileset_strategies.py +++ b/python/sandcrawler/fileset_strategies.py @@ -1,18 +1,19 @@ +import gzip +import json import os +import shutil import sys -import json -import gzip import time -import shutil from collections import namedtuple -from typing import Optional, Tuple, Any, Dict, List +from typing import Any, Dict, List, Optional, Tuple import internetarchive +from sandcrawler.fileset_types import (ArchiveStrategyResult, FilesetManifestFile, FilesetPlatformItem, IngestStrategy, + PlatformScopeError) from sandcrawler.html_metadata import BiblioMetadata -from sandcrawler.ia import ResourceResult, WaybackClient, SavePageNowClient, fix_transfer_encoding -from sandcrawler.fileset_types import IngestStrategy, FilesetManifestFile, FilesetPlatformItem, ArchiveStrategyResult, PlatformScopeError +from sandcrawler.ia import ResourceResult, SavePageNowClient, WaybackClient, fix_transfer_encoding from sandcrawler.misc import gen_file_metadata, gen_file_metadata_path, sanitize_fs_path |