aboutsummaryrefslogtreecommitdiffstats
path: root/python/fatcat_tools/harvest
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@robocracy.org>2019-03-15 15:16:50 -0700
committerBryan Newbold <bnewbold@robocracy.org>2019-03-15 15:16:57 -0700
commitd0772cc01462d532d0cd82cb0c6dd859f4c4e74d (patch)
tree0f1739a3ae16d4181be59e5e511fda97fb5bb2a0 /python/fatcat_tools/harvest
parent9f7f6f9446a431564b3d7e12e117f16cbf41a9fd (diff)
downloadfatcat-d0772cc01462d532d0cd82cb0c6dd859f4c4e74d.tar.gz
fatcat-d0772cc01462d532d0cd82cb0c6dd859f4c4e74d.zip
MEDLINE/Pubmed note
Also, arXivRaw, not arXiv (though see WIP on more-importers branch)
Diffstat (limited to 'python/fatcat_tools/harvest')
-rw-r--r--python/fatcat_tools/harvest/oaipmh.py8
1 files changed, 6 insertions, 2 deletions
diff --git a/python/fatcat_tools/harvest/oaipmh.py b/python/fatcat_tools/harvest/oaipmh.py
index 923500fc..0b482924 100644
--- a/python/fatcat_tools/harvest/oaipmh.py
+++ b/python/fatcat_tools/harvest/oaipmh.py
@@ -98,18 +98,22 @@ class HarvestArxivWorker(HarvestOaiPmhWorker):
- http://export.arxiv.org/oai2?verb=GetRecord&identifier=oai:arXiv.org:0804.2273&metadataPrefix=arXivRaw
All records are work-level. Some metadata formats have internal info about
- specific versions. The 'arXiv' format does, so i'm using that.
+ specific versions. The 'arXivRaw' format does, so i'm using that.
"""
def __init__(self, **kwargs):
super().__init__(**kwargs)
self.endpoint_url = "https://export.arxiv.org/oai2"
- self.metadata_prefix = "arXiv"
+ self.metadata_prefix = "arXivRaw"
self.name = "arxiv"
class HarvestPubmedWorker(HarvestOaiPmhWorker):
"""
+ Will likely be doing MEDLINE daily batch imports for primary metadata, but
+ might also want to run a PMC importer to update fulltext and assign OA
+ licenses (when appropriate).
+
Pubmed refs:
- https://www.ncbi.nlm.nih.gov/pmc/tools/oai/
- https://www.ncbi.nlm.nih.gov/pmc/oai/oai.cgi?verb=GetRecord&identifier=oai:pubmedcentral.nih.gov:152494&metadataPrefix=pmc_fm