diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2021-10-26 12:22:38 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2021-10-26 12:22:38 -0700 |
| commit | 3cdf4af9be4c762ff2ed79a57b5ad30637909f1e (patch) | |
| tree | b7e7e27ff2032c99fd782b3ea40daf1d12f9164e /python/scripts/grobid_affiliations.py | |
| parent | f67d870ba4ca9cecd0b75f106335997c813e9df4 (diff) | |
| download | sandcrawler-3cdf4af9be4c762ff2ed79a57b5ad30637909f1e.tar.gz sandcrawler-3cdf4af9be4c762ff2ed79a57b5ad30637909f1e.zip | |
python: isort all imports
Diffstat (limited to 'python/scripts/grobid_affiliations.py')
| -rwxr-xr-x | python/scripts/grobid_affiliations.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/python/scripts/grobid_affiliations.py b/python/scripts/grobid_affiliations.py index 79feac1..d391f60 100755 --- a/python/scripts/grobid_affiliations.py +++ b/python/scripts/grobid_affiliations.py @@ -10,11 +10,12 @@ Run in bulk like: ls /bigger/unpaywall-transfer/2019-07-17-1741.30-dumpgrobidxml/part*gz | parallel --progress -j8 'zcat {} | ./grobid_affiliations.py > {}.affiliations' """ -import sys import json +import sys from grobid2json import teixml2json + def parse_hbase(line): line = line.split('\t') assert len(line) == 2 |