Orcid

CHANGES.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## [5.3.0] - 26 June 2025
+- update format expected for jlist.csv dates
+
+## [5.3a0] - 21 May 2025
+- add API to get name from ORCID
+- add ORCID Person
+
 ## [5.2] - 16 May 2025
 - add search by author_ids
 

pub/tools/__init__.py

@@ -2,4 +2,4 @@
 
 __all__ = [journals]
 
-__version__ = "5.2"
+__version__ = "5.3.0"

pub/tools/entrez.py

@@ -13,6 +13,7 @@
 from .schema import Abstract
 from .schema import BookRecord
 from .schema import ChapterRecord
+from .schema import EntrezRecord
 from .schema import Grant
 from .schema import JournalRecord
 from .schema import Person
@@ -173,13 +174,15 @@ def _parse_author_name(author: dict, investigator: bool = False) -> Person:
     # strip excess spaces like in
     # https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=22606070&retmode=xml
     fname = " ".join([part for part in fname.split(" ") if part])
+    identifiers = {source.attributes.get("Source", ""): str(source) for source in author.get("Identifier", [])}
     return Person(
         last_name=author.get("LastName", ""),
         first_name=fname,
         initial=author.get("Initials", ""),
         collective_name=author.get("CollectiveName", ""),
         suffix=author.get("Suffix", ""),
         investigator=investigator,
+        identifiers=identifiers,
         affiliations=author.get("affiliations", []),
     )
 
@@ -583,7 +586,7 @@ def find_publications(
     affl=None,
     doi="",
     inclusive=False,
-):
+) -> list[EntrezRecord]:
     """
     You can use the resulting WebEnv and QueryKey values to call get_searched_publications
     https://www.ncbi.nlm.nih.gov/books/NBK3827/#_pubmedhelp_Search_Field_Descriptions_and_

pub/tools/journals.py

@@ -79,8 +79,8 @@ def _parse_journals(text):
                     deposit,
                     url,
                 ) = row
-                latest = latest.split(";")[-1]
-                earliest = earliest.split(";")[-1]
+                latest = latest.split(" ")[-1]
+                earliest = earliest.split(" ")[-1]
                 _atoj[abbr.lower()] = title
                 _jtoa[title.lower()] = abbr
                 dates[abbr.lower()] = (earliest, latest)

pub/tools/orcid.py

@@ -0,0 +1,17 @@
+import requests
+
+PUBLIC_API = "https://pub.orcid.org/v3.0/"
+
+
+def get_author(orcid: str, full: bool = False) -> dict:
+    response = requests.get(f"{PUBLIC_API}{orcid}", headers={"Accept": "application/json"}, timeout=2.0)
+    if response.status_code != 200:
+        raise requests.exceptions.HTTPError(f"REST API returned: {response.status_code}")
+
+    data = response.json()
+    if full:
+        return data
+    given_name = data["person"].get("name", {}).get("given-names", {}).get("value")
+    family_name = data["person"].get("name", {}).get("family-name", {}).get("value")
+
+    return {"given_name": given_name, "family_name": family_name}

pub/tools/schema.py

@@ -16,6 +16,7 @@ class Person:
     suffix: str = ""
     investigator: bool = False
     affiliations: list[str] = dataclasses.field(default_factory=list)
+    identifiers: dict[str, str] = dataclasses.field(default_factory=dict)
 
     def asdict(self):
         base = dataclasses.asdict(self)
@@ -24,6 +25,7 @@ def asdict(self):
             "fname": self.fname,
             "cname": self.cname,
             "iname": self.iname,
+            "orcid": self.orcid,
         })
         return base
 
@@ -47,6 +49,11 @@ def cname(self):
         """backwards compatibility"""
         return self.collective_name
 
+    @property
+    def orcid(self):
+        """Derivative from identifiers"""
+        return self.identifiers.get("ORCID", "")
+
 
 @dataclasses.dataclass
 class Abstract:

tests/test_entrez.py

@@ -4,6 +4,7 @@
 
 from pub.tools import citations
 from pub.tools import entrez
+from pub.tools import orcid
 from pub.tools.schema import Abstract
 from pub.tools.schema import Grant
 from pub.tools.schema import JournalRecord
@@ -447,6 +448,20 @@ def test_find_and_fetch(self):
         record = entrez.get_searched_publications(record["WebEnv"], record["QueryKey"])
         self.check_pub_data(record[0])
 
-    def test_orcid(self):
+    def test_orcid_search(self):
         record = entrez.find_publications(author_ids=["0000-0002-8953-3940"])
         assert int(record["Count"]) > 0
+
+    def test_pubmed_orcid_author(self):
+        record = entrez.get_publication(pmid="32570285")
+        assert record.authors[0].orcid == "0000-0002-1771-9287"
+        assert record.authors[0].asdict()["orcid"] == "0000-0002-1771-9287"
+
+    def test_full_identifiers(self):
+        record = entrez.get_publication(pmid="32570285")
+        assert record.authors[0].identifiers == {"ORCID": "0000-0002-1771-9287"}
+
+    def test_get_orcid(self):
+        record = orcid.get_author(orcid="0000-0002-1771-9287")
+        assert record["given_name"] == "Rachel"
+        assert record["family_name"] == "Altshuler"