diff options
author | Martin Czygan <martin.czygan@gmail.com> | 2020-03-09 20:07:30 +0100 |
---|---|---|
committer | Martin Czygan <martin.czygan@gmail.com> | 2020-03-09 20:07:30 +0100 |
commit | c6b29c17eeea4c067dcc391fe6d9bdaec3f657b3 (patch) | |
tree | a1291744ed067c5423016cee2de5259df8464cb8 /python/fatcat_tools | |
parent | 0ec71d1b47dffe0d976554a76efa636cbe025e08 (diff) | |
download | fatcat-c6b29c17eeea4c067dcc391fe6d9bdaec3f657b3.tar.gz fatcat-c6b29c17eeea4c067dcc391fe6d9bdaec3f657b3.zip |
oaipmh: HarvestPubmedWorker obsoleted by PubmedFTPWorker
Diffstat (limited to 'python/fatcat_tools')
-rw-r--r-- | python/fatcat_tools/harvest/oaipmh.py | 34 |
1 files changed, 0 insertions, 34 deletions
diff --git a/python/fatcat_tools/harvest/oaipmh.py b/python/fatcat_tools/harvest/oaipmh.py index 8e9efea8..c95f3445 100644 --- a/python/fatcat_tools/harvest/oaipmh.py +++ b/python/fatcat_tools/harvest/oaipmh.py @@ -132,40 +132,6 @@ class HarvestArxivWorker(HarvestOaiPmhWorker): 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 - - https://github.com/titipata/pubmed_parser - - TODO(martin): OAI does not seem to support the format we already have an - importer for. Maybe we can use "Daily Update Files" -- - - Daily Update Files - ------------------ - Each day, NLM produces update files that include new, revised and deleted - citations. The first Update file to be loaded after loading the complete - set of 2019 MEDLINE/PubMed Baseline files is pubmed20n1016.xml. - ftp://ftp.ncbi.nlm.nih.gov/pubmed/updatefiles - - NOTES: - - * OAI: https://dtd.nlm.nih.gov/archiving/2.3/xsd/archivearticle.xsd - * FTP: https://dtd.nlm.nih.gov/ncbi/pubmed/out/pubmed_190101.dtd - """ - - def __init__(self, **kwargs): - super().__init__(**kwargs) - self.endpoint_url = "https://www.ncbi.nlm.nih.gov/pmc/oai/oai.cgi" - self.metadata_prefix = "pmc_fm" - self.name = "pubmed" - - class HarvestDoajJournalWorker(HarvestOaiPmhWorker): """ WARNING: DOAJ OAI-PMH doesn't seem to respect 'from' and 'until' params |