aboutsummaryrefslogtreecommitdiffstats
path: root/python/sandcrawler/fileset_strategies.py
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2021-10-04 13:01:58 -0700
committerBryan Newbold <bnewbold@archive.org>2021-10-15 18:15:20 -0700
commite2e0602114ccdf142b3ef0f30c67d2cb7a58ef7e (patch)
treebee2b4343f30d59fec463dbdcaafafc11d7cd513 /python/sandcrawler/fileset_strategies.py
parent452475df7619f3743eac5ad86e2e1fb8ba9972da (diff)
downloadsandcrawler-e2e0602114ccdf142b3ef0f30c67d2cb7a58ef7e.tar.gz
sandcrawler-e2e0602114ccdf142b3ef0f30c67d2cb7a58ef7e.zip
progress on fileset/dataset ingest
Diffstat (limited to 'python/sandcrawler/fileset_strategies.py')
-rw-r--r--python/sandcrawler/fileset_strategies.py22
1 files changed, 22 insertions, 0 deletions
diff --git a/python/sandcrawler/fileset_strategies.py b/python/sandcrawler/fileset_strategies.py
new file mode 100644
index 0000000..592b475
--- /dev/null
+++ b/python/sandcrawler/fileset_strategies.py
@@ -0,0 +1,22 @@
+
+import sys
+import json
+import gzip
+import time
+from collections import namedtuple
+from typing import Optional, Tuple, Any, Dict, List
+
+from sandcrawler.html_metadata import BiblioMetadata
+from sandcrawler.ia import ResourceResult
+from sandcrawler.fileset_types import IngestStrategy, FilesetManifestFile, DatasetPlatformItem
+
+
+class FilesetIngestStrategy(class):
+
+ def __init__():
+ self.ingest_strategy = 'unknown'
+
+ def check_existing(): # XXX: -> Any:
+ raise NotImplementedError()
+
+ def process(item: DatasetPlatformItem):