diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2019-07-07 19:40:59 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2019-07-07 19:40:59 -0700 |
| commit | 626d85a693bef8dd8af85906f089d300e45d9f09 (patch) | |
| tree | b4bc02e2f34475a919e59f0e83cd3a2e026ac0ba | |
| parent | 4298e1f9c7a092602e1cbe46add13936cb6169e7 (diff) | |
| download | sandcrawler-626d85a693bef8dd8af85906f089d300e45d9f09.tar.gz sandcrawler-626d85a693bef8dd8af85906f089d300e45d9f09.zip | |
ia_pdf_match.py bugfix
| -rwxr-xr-x | python/ia_pdf_match.py | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/python/ia_pdf_match.py b/python/ia_pdf_match.py index 60b7843..bc814de 100755 --- a/python/ia_pdf_match.py +++ b/python/ia_pdf_match.py @@ -13,8 +13,8 @@ Ouput is insertable fatcat "match" JSON - dois (list) - pmcid -- jstor_id -- arxiv_id +- jstor +- arxiv When invoking import matched, be sure to: @@ -33,7 +33,7 @@ def parse(obj): extid_type = None extid = None if obj['metadata']['identifier'].startswith('arxiv-'): - extid_type = 'arxiv_id' + extid_type = 'arxiv' extid = obj['metadata'].get('source') if not extid: sys.stderr.write('skip: no source\n') @@ -55,7 +55,7 @@ def parse(obj): assert extid.startswith("PMC") int(extid[3:]) elif obj['metadata']['identifier'].startswith('jstor-'): - extid_type = 'jstor_id' + extid_type = 'jstor' extid = obj['metadata']['identifier'].replace('jstor-', '') int(extid) else: |