diff options
Diffstat (limited to 'python')
-rwxr-xr-x | python/grobid_tool.py | 2 | ||||
-rwxr-xr-x | python/pdftrio_tool.py | 2 |
2 files changed, 2 insertions, 2 deletions
diff --git a/python/grobid_tool.py b/python/grobid_tool.py index 029cbf1..3ffac98 100755 --- a/python/grobid_tool.py +++ b/python/grobid_tool.py @@ -5,7 +5,7 @@ might go to stdout, or might go to Kafka topic. Example of large parallel run, locally: - cat /srv/sandcrawler/tasks/ungrobided.2019-09-23.json | pv -l | parallel -j30 --pipe ./grobid_tool.py --kafka-env prod --kafka-hosts wbgrp-svc263.us.archive.org:9092,wbgrp-svc284.us.archive.org:9092,wbgrp-svc285.us.archive.org:9092 --kafka-mode --grobid-host http://localhost:8070 -j0 extract-json - + cat /srv/sandcrawler/tasks/ungrobided.2019-09-23.json | pv -l | parallel -j30 --pipe ./grobid_tool.py --kafka-env prod --kafka-hosts wbgrp-svc350.us.archive.org:9092,wbgrp-svc284.us.archive.org:9092,wbgrp-svc285.us.archive.org:9092 --kafka-mode --grobid-host http://localhost:8070 -j0 extract-json - """ import argparse diff --git a/python/pdftrio_tool.py b/python/pdftrio_tool.py index 9d3010e..24b749d 100755 --- a/python/pdftrio_tool.py +++ b/python/pdftrio_tool.py @@ -5,7 +5,7 @@ text extraction. Example of large parallel run, locally: -cat /srv/sandcrawler/tasks/something.cdx | pv -l | parallel -j30 --pipe ./pdftrio_tool.py --kafka-env prod --kafka-hosts wbgrp-svc263.us.archive.org:9092,wbgrp-svc284.us.archive.org:9092,wbgrp-svc285.us.archive.org:9092 --kafka-mode --pdftrio-host http://localhost:3939 -j0 classify-pdf-json - +cat /srv/sandcrawler/tasks/something.cdx | pv -l | parallel -j30 --pipe ./pdftrio_tool.py --kafka-env prod --kafka-hosts wbgrp-svc350.us.archive.org:9092,wbgrp-svc284.us.archive.org:9092,wbgrp-svc285.us.archive.org:9092 --kafka-mode --pdftrio-host http://localhost:3939 -j0 classify-pdf-json - """ import argparse |