diff options
author | Bryan Newbold <bnewbold@archive.org> | 2019-10-04 17:59:42 -0700 |
---|---|---|
committer | Bryan Newbold <bnewbold@archive.org> | 2019-10-04 17:59:42 -0700 |
commit | 04e1ae4f903af98ef174be9110aaae5e1ab81360 (patch) | |
tree | 63ec7652c08a48910d2ad8f5e04ef1ab8ad02671 /python/ingest_file.py | |
parent | 84a501f86dc9a6a2e25e58c7380575ed946c9357 (diff) | |
download | sandcrawler-04e1ae4f903af98ef174be9110aaae5e1ab81360.tar.gz sandcrawler-04e1ae4f903af98ef174be9110aaae5e1ab81360.zip |
we do actually want consolidateHeader=2, not 1
Diffstat (limited to 'python/ingest_file.py')
-rwxr-xr-x | python/ingest_file.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/python/ingest_file.py b/python/ingest_file.py index 0699a0c..4daa472 100755 --- a/python/ingest_file.py +++ b/python/ingest_file.py @@ -217,7 +217,7 @@ def file_metadata(blob): def do_grobid(sha1hex, blob): grobid_response = requests.post( GROBID_ENDPOINT + "/api/processFulltextDocument", - files={'input': blob, 'consolidateHeader': '1'}, + files={'input': blob, 'consolidateHeader': '2'}, ) info = dict( |