diff options
| author | Martin Czygan <martin@archive.org> | 2020-11-19 22:36:55 +0000 |
|---|---|---|
| committer | Martin Czygan <martin@archive.org> | 2020-11-19 22:36:55 +0000 |
| commit | 03eadfc7e2bee4213345f6464378e87b8f741d20 (patch) | |
| tree | 3e5b13af8ba46b240f9ae53d5f522fb7ee02c219 /python/fatcat_tools/transforms | |
| parent | 5afde4690a4653db53fe4962af5da3eb9188d9a2 (diff) | |
| parent | a73b73c2944b3df2a62886c4e6b69c93f5e74222 (diff) | |
| download | fatcat-03eadfc7e2bee4213345f6464378e87b8f741d20.tar.gz fatcat-03eadfc7e2bee4213345f6464378e87b8f741d20.zip | |
Merge branch 'bnewbold-xml-html-ingest' into 'master'
HTML webcapture ingest (and XML file ingest)
See merge request webgroup/fatcat!88
Diffstat (limited to 'python/fatcat_tools/transforms')
| -rw-r--r-- | python/fatcat_tools/transforms/ingest.py | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/python/fatcat_tools/transforms/ingest.py b/python/fatcat_tools/transforms/ingest.py index 2f4e2271..59831017 100644 --- a/python/fatcat_tools/transforms/ingest.py +++ b/python/fatcat_tools/transforms/ingest.py @@ -15,15 +15,19 @@ def release_ingest_request(release, ingest_request_source='fatcat', ingest_type= if release.state != 'active': return None + # TODO: infer ingest type based on release_type or container metadata? + if not ingest_type: + ingest_type = 'pdf' + # generate a URL where we expect to find fulltext url = None link_source = None link_source_id = None - if release.ext_ids.arxiv: + if release.ext_ids.arxiv and ingest_type == "pdf": url = "https://arxiv.org/pdf/{}.pdf".format(release.ext_ids.arxiv) link_source = "arxiv" link_source_id = release.ext_ids.arxiv - elif release.ext_ids.pmcid: + elif release.ext_ids.pmcid and ingest_type == "pdf": # TODO: how to tell if an author manuscript in PMC vs. published? #url = "https://www.ncbi.nlm.nih.gov/pmc/articles/{}/pdf/".format(release.ext_ids.pmcid) url = "http://europepmc.org/backend/ptpmcrender.fcgi?accid={}&blobtype=pdf".format(release.ext_ids.pmcid) @@ -40,10 +44,6 @@ def release_ingest_request(release, ingest_request_source='fatcat', ingest_type= ext_ids = release.ext_ids.to_dict() ext_ids = dict([(k, v) for (k, v) in ext_ids.items() if v]) - # TODO: infer ingest type based on release_type or container metadata? - if not ingest_type: - ingest_type = 'pdf' - ingest_request = { 'ingest_type': ingest_type, 'ingest_request_source': ingest_request_source, |