diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-06-17 18:04:37 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-06-17 18:04:37 -0700 |
| commit | 55fca256e26ef53c4a9f59d074a835f87ee5b79f (patch) | |
| tree | c33106e854aef088b841647cb32b15dbe7ca54e8 /python/persist_tool.py | |
| parent | e03f4eda875f4a36a3d3e62eac467b3f2b1e0fbe (diff) | |
| download | sandcrawler-55fca256e26ef53c4a9f59d074a835f87ee5b79f.tar.gz sandcrawler-55fca256e26ef53c4a9f59d074a835f87ee5b79f.zip | |
lint fixes
Diffstat (limited to 'python/persist_tool.py')
| -rwxr-xr-x | python/persist_tool.py | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/python/persist_tool.py b/python/persist_tool.py index 4d78314..66e02aa 100755 --- a/python/persist_tool.py +++ b/python/persist_tool.py @@ -10,7 +10,6 @@ Kafka feeds, but sometimes we have bulk processing output we want to backfill. import os import sys import argparse -import datetime from sandcrawler import * from sandcrawler.persist import * @@ -158,7 +157,7 @@ def main(): help="only write status to sandcrawler-db (don't save TEI-XML to S3)") sub_pdftext = subparsers.add_parser('pdftext', - help="backfill a pdftext JSON ('pg') dump into postgresql and s3 (minio)") + help="backfill a pdftext JSON ('pg') dump into postgresql and s3 (seaweedfs)") sub_pdftext.set_defaults(func=run_pdftext) sub_pdftext.add_argument('json_file', help="pdftext file to import from (or '-' for stdin)", |