add logic to cache data download in get_latest_data()

3 files changed, 40 insertions, 6 deletions

diff --git a/fnme/data.py b/fnme/data.py
index bdec6df..17f30c5 100644
--- a/fnme/data.py
+++ b/fnme/data.py
@@ -1,13 +1,35 @@
-from io import StringIO
+import os
+from pathlib import Path
 from typing import Optional
 
 import pandas as pd
 import requests
+from platformdirs import user_cache_path
 
 from fnme.constants import ENDPOINT, HEADERS
 
 
-def get_latest_data() -> tuple[pd.DataFrame, Optional[str]]:
-    response = requests.get(ENDPOINT, headers=HEADERS, timeout=10)
-    response.raise_for_status()
-    return pd.read_csv(StringIO(response.text)), response.headers.get("Last-Modified")
+def get_latest_data() -> tuple[pd.DataFrame, str | None]:
+    cache_dir = Path(user_cache_path(appname="fnme", appauthor=False))
+    csv_path = cache_dir / "latest_data.csv"
+    timestamp_path = cache_dir / "timestamp.txt"
+
+    cache_dir.mkdir(parents=True, exist_ok=True)
+
+    remote_last_modified = requests.head(
+        ENDPOINT, headers=HEADERS, timeout=10
+    ).headers.get("Last-Modified")
+
+    cached_last_modified = (
+        timestamp_path.read_text() if timestamp_path.exists() else None
+    )
+
+    if not csv_path.exists() or remote_last_modified != cached_last_modified:
+        response = requests.get(ENDPOINT, headers=HEADERS, timeout=10)
+        response.raise_for_status()
+        last_modified = response.headers.get("Last-Modified")
+        csv_path.write_text(response.text, encoding="utf-8")
+        timestamp_path.write_text(last_modified or "")
+        return pd.read_csv(csv_path), last_modified
+
+    return pd.read_csv(csv_path), cached_last_modified
diff --git a/pyproject.toml b/pyproject.toml
index fcf426d..feeed1f 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -9,7 +9,8 @@ dependencies = [
     "pandas>=3.0.2",
     "requests>=2.33.1",
     "numpy>=2.4.4",
-    "tabulate>=0.10.0"
+    "tabulate>=0.10.0",
+    "platformdirs>=4.9.6",
 ]
 
 [project.scripts]
diff --git a/uv.lock b/uv.lock
index 67e5ad6..0f922e3 100644
--- a/uv.lock
+++ b/uv.lock
@@ -116,6 +116,7 @@ dependencies = [
     { name = "geopy" },
     { name = "numpy" },
     { name = "pandas" },
+    { name = "platformdirs" },
     { name = "requests" },
     { name = "tabulate" },
 ]
@@ -125,6 +126,7 @@ requires-dist = [
     { name = "geopy", specifier = ">=2.4.1" },
     { name = "numpy", specifier = ">=2.4.4" },
     { name = "pandas", specifier = ">=3.0.2" },
+    { name = "platformdirs", specifier = ">=4.9.6" },
     { name = "requests", specifier = ">=2.33.1" },
     { name = "tabulate", specifier = ">=0.10.0" },
 ]
@@ -299,6 +301,15 @@ wheels = [
 ]
 
 [[package]]
+name = "platformdirs"
+version = "4.9.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/9f/4a/0883b8e3802965322523f0b200ecf33d31f10991d0401162f4b23c698b42/platformdirs-4.9.6.tar.gz", hash = "sha256:3bfa75b0ad0db84096ae777218481852c0ebc6c727b3168c1b9e0118e458cf0a", size = 29400, upload-time = "2026-04-09T00:04:10.812Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/75/a6/a0a304dc33b49145b21f4808d763822111e67d1c3a32b524a1baf947b6e1/platformdirs-4.9.6-py3-none-any.whl", hash = "sha256:e61adb1d5e5cb3441b4b7710bea7e4c12250ca49439228cc1021c00dcfac0917", size = 21348, upload-time = "2026-04-09T00:04:09.463Z" },
+]
+
+[[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
 source = { registry = "https://pypi.org/simple" }