From 7e2b6f942f174aa1942e189d45be07f16a20e616 Mon Sep 17 00:00:00 2001
From: AndrewVFranco <129307231+AndrewVFranco@users.noreply.github.com>
Date: Sat, 4 Apr 2026 02:36:36 -0700
Subject: [PATCH 1/3] Add pubmed data retrieval function

---
 .idea/.gitignore        | 10 ----------
 requirements.txt        |  6 +++++-
 src/core/config.py      |  4 +++-
 src/retrieval/pubmed.py | 35 +++++++++++++++++++++++++++++++++++
 4 files changed, 43 insertions(+), 12 deletions(-)
 delete mode 100644 .idea/.gitignore
 create mode 100644 src/retrieval/pubmed.py

diff --git a/.idea/.gitignore b/.idea/.gitignore
deleted file mode 100644
index ab1f416..0000000
--- a/.idea/.gitignore
+++ /dev/null
@@ -1,10 +0,0 @@
-# Default ignored files
-/shelf/
-/workspace.xml
-# Ignored default folder with query files
-/queries/
-# Datasource local storage ignored files
-/dataSources/
-/dataSources.local.xml
-# Editor-based HTTP Client requests
-/httpRequests/
diff --git a/requirements.txt b/requirements.txt
index f1fa448..109cd41 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -9,4 +9,8 @@ python-json-logger>=2.0.0
 ruff>=0.4.0
 
 # Pytest
-pytest>=9.0.0
\ No newline at end of file
+pytest>=9.0.0
+
+# Pubmed requests
+requests>=2.33.0
+lxml>=6.0.2
\ No newline at end of file
diff --git a/src/core/config.py b/src/core/config.py
index 98fc734..1a1084f 100644
--- a/src/core/config.py
+++ b/src/core/config.py
@@ -27,4 +27,6 @@ class Settings(BaseSettings):
     DEBUG: bool = True
 
     class Config:
-        env_file = ".env"
\ No newline at end of file
+        env_file = ".env"
+
+settings = Settings()
\ No newline at end of file
diff --git a/src/retrieval/pubmed.py b/src/retrieval/pubmed.py
new file mode 100644
index 0000000..ed418c1
--- /dev/null
+++ b/src/retrieval/pubmed.py
@@ -0,0 +1,35 @@
+import requests
+from src.core.config import settings
+
+def search_pubmed(query: str, max_results: int = 10) -> list[dict]:
+    base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
+
+    esearch_params = {
+        "db": "pubmed",
+        "term": query,
+        "retmax": max_results,
+        "retmode": "json",
+        "api_key": settings.NCBI_API_KEY
+    }
+
+    try:
+        response = requests.get(f"{base_url}esearch.fcgi", params=esearch_params)
+        response.raise_for_status()
+        pmids = response.json()["esearchresult"]["idlist"]
+
+        pmids = ",".join(pmids)
+
+        efetch_params = {
+            "db": "pubmed",
+            "id": pmids,
+            "retmode": "XML",
+            "api_key": settings.NCBI_API_KEY
+        }
+
+        raw_data = requests.get(f"{base_url}efetch.fcgi", params=efetch_params)
+        raw_data.raise_for_status()
+
+        return raw_data.text
+    except Exception as e:
+        print(f"Error: {e}")
+

From 47a0e7a7c336fe74cf65fda25391d9b2f3235994 Mon Sep 17 00:00:00 2001
From: AndrewVFranco <129307231+AndrewVFranco@users.noreply.github.com>
Date: Sat, 4 Apr 2026 02:49:02 -0700
Subject: [PATCH 2/3] Add xml parsing helper function

---
 .gitignore              |  1 +
 src/retrieval/pubmed.py | 25 ++++++++++++++++++++++++-
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index 5316331..5a2e476 100644
--- a/.gitignore
+++ b/.gitignore
@@ -209,3 +209,4 @@ __marimo__/
 # General
 *.DS_Store
 **.DS_Store
+.idea/
diff --git a/src/retrieval/pubmed.py b/src/retrieval/pubmed.py
index ed418c1..a79a6e2 100644
--- a/src/retrieval/pubmed.py
+++ b/src/retrieval/pubmed.py
@@ -1,8 +1,28 @@
 import requests
+from lxml import etree
 from src.core.config import settings
 
+def parse_data(xml_text: str) -> list[dict]:
+    article_list = []
+    root = etree.fromstring(xml_text.encode("utf-8"))
+
+    articles = root.findall(".//PubmedArticle")
+
+    # For each article, extract fields using findtext
+    for article in articles:
+        pmid = article.findtext(".//PMID")
+        title = article.findtext(".//ArticleTitle")
+        abstract = article.findtext(".//AbstractText")
+        article_data = {"pmid": pmid, "title": title, "abstract": abstract}
+        if article_data["abstract"] is not None:
+            article_list.append(article_data)
+
+    return article_list
+
+
 def search_pubmed(query: str, max_results: int = 10) -> list[dict]:
     base_url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/"
+    article_list = []
 
     esearch_params = {
         "db": "pubmed",
@@ -29,7 +49,10 @@ def search_pubmed(query: str, max_results: int = 10) -> list[dict]:
         raw_data = requests.get(f"{base_url}efetch.fcgi", params=efetch_params)
         raw_data.raise_for_status()
 
-        return raw_data.text
+        article_list = parse_data(raw_data.text)
+
+        return article_list
     except Exception as e:
         print(f"Error: {e}")
 
+

From 5f25b347d7029c17b95da5a285a5b11ad80ea30f Mon Sep 17 00:00:00 2001
From: AndrewVFranco <129307231+AndrewVFranco@users.noreply.github.com>
Date: Sat, 4 Apr 2026 02:54:34 -0700
Subject: [PATCH 3/3] Fix path to key in config

---
 src/core/config.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/core/config.py b/src/core/config.py
index 1a1084f..f03c7e6 100644
--- a/src/core/config.py
+++ b/src/core/config.py
@@ -1,5 +1,5 @@
 from pydantic_settings import BaseSettings
-
+from pathlib import Path
 
 class Settings(BaseSettings):
     # NCBI
@@ -27,6 +27,6 @@ class Settings(BaseSettings):
     DEBUG: bool = True
 
     class Config:
-        env_file = ".env"
+        env_file = Path(__file__).resolve().parent.parent.parent / ".env"
 
 settings = Settings()
\ No newline at end of file