From 905ad4fc433d3a026649645311aa08492db1226e Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 19 Jul 2022 12:26:41 -0700 Subject: dblp: more skip patterns, and rename variable --- python/fatcat_tools/importers/dblp_release.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'python') diff --git a/python/fatcat_tools/importers/dblp_release.py b/python/fatcat_tools/importers/dblp_release.py index 5f78ca3a..b97c3976 100644 --- a/python/fatcat_tools/importers/dblp_release.py +++ b/python/fatcat_tools/importers/dblp_release.py @@ -542,18 +542,21 @@ class DblpReleaseImporter(EntityImporter): Used only in JSON dump mode, with the intent of transforming into sandcrawler ingest requests. """ - EXTID_PATTERNS = [ + SKIP_PATTERNS = [ "://doi.acm.org/", "://doi.ieeecomputersociety.org/", "doi.org/10.", "wikidata.org/entity/Q", "://arxiv.org/abs/", + "://hdl.handle.net/", + "://d-nb.info/", + "://www.base-search.net/", ] urls = [] for ee in xml_elem.find_all("ee"): url = ee.text skip = False - for pattern in EXTID_PATTERNS: + for pattern in SKIP_PATTERNS: if pattern in url: skip = True break -- cgit v1.2.3 From 94cce3ebe325f7601feee7dbe7ab8b24aa2492ee Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 19 Jul 2022 12:27:01 -0700 Subject: ingest: generate URLs for hdl (handle.net) --- python/fatcat_tools/transforms/ingest.py | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'python') diff --git a/python/fatcat_tools/transforms/ingest.py b/python/fatcat_tools/transforms/ingest.py index d60f9467..1a19a651 100644 --- a/python/fatcat_tools/transforms/ingest.py +++ b/python/fatcat_tools/transforms/ingest.py @@ -89,6 +89,10 @@ def release_ingest_request( url = "https://doaj.org/article/{}".format(release.ext_ids.doaj.lower()) link_source = "doaj" link_source_id = release.ext_ids.doaj.lower() + elif release.ext_ids.hdl: + url = "https://hdl.handle.net/{}".format(release.ext_ids.hdl.lower()) + link_source = "hdl" + link_source_id = release.ext_ids.hdl.lower() if not url: return None -- cgit v1.2.3