Last active
November 5, 2025 14:59
-
-
Save davidaknowles/b315ec42602de9b8230b2171054b2709 to your computer and use it in GitHub Desktop.
Get COA coauthor list for NSF including affiliations from PUBMED
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from Bio import Entrez | |
| import csv | |
| from collections import defaultdict | |
| from datetime import datetime | |
| AUTHOR_NAME = "Knowles DA" | |
| START_YEAR = datetime.now().year - 4 | |
| EMAIL = "[email protected]" | |
| OUTFILE = "nsf_coauthors.csv" | |
| Entrez.email = EMAIL | |
| term = f'"{AUTHOR_NAME}[Author]" AND ("{START_YEAR}"[dp] : "3000"[dp])' | |
| search = Entrez.esearch(db="pubmed", term=term, retmax=1000) | |
| ids = Entrez.read(search)["IdList"] | |
| handle = Entrez.efetch(db="pubmed", id=",".join(ids), retmode="xml") | |
| records = Entrez.read(handle) | |
| coauthors = {} | |
| last_active = defaultdict(int) | |
| for r in records["PubmedArticle"]: | |
| year = r["MedlineCitation"]["Article"]["Journal"]["JournalIssue"]["PubDate"].get("Year", "") | |
| for a in r["MedlineCitation"]["Article"].get("AuthorList", []): | |
| if "ForeName" in a and "LastName" in a: | |
| # Format as "LastName, FirstName MiddleInitial" | |
| name = f"{a['LastName']}, {a['ForeName']}".strip() | |
| if AUTHOR_NAME.split()[0] in name and AUTHOR_NAME.split()[1] in name: | |
| continue | |
| affs = a.get("AffiliationInfo", []) | |
| aff = affs[0]["Affiliation"] if affs else "" | |
| if name not in coauthors: | |
| coauthors[name] = aff | |
| if year: | |
| last_active[name] = max(last_active[name], int(year)) | |
| with open(OUTFILE, "w", newline="", encoding="utf-8-sig") as f: | |
| w = csv.writer(f) | |
| w.writerow(["Name", "Institution", "Last Active"]) | |
| for name in sorted(coauthors): | |
| w.writerow([name, coauthors[name], last_active.get(name, "")]) | |
| print(f"Wrote {len(coauthors)} coauthors to {OUTFILE}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment