Update app.py

app.py

@@ -5,15 +5,14 @@ from pathlib import Path
 from zipfile import ZipFile
 
 # ------------------
-# Download Resources
+# Data prep
 # ------------------
 def download_file(url: str, output_path: Path):
     if output_path.exists():
         print(f"Skipping {output_path.name}, already exists.")
         return
     print(f"Downloading {url}")
-    headers = {"User-Agent": "Mozilla/5.0"}  # Bypass basic bot protections
-    response = requests.get(url, headers=headers)
+    response = requests.get(url)
     response.raise_for_status()
     output_path.write_bytes(response.content)
     print(f"Saved to {output_path}")
@@ -21,18 +20,22 @@ def download_file(url: str, output_path: Path):
 
 # Download files
 download_file("https://raw.githubusercontent.com/BradyStephenson/bible-data/refs/heads/main/BibleData-Person.csv", Path("BibleData-Person.csv"))
-download_file("https://www.ssa.gov/oact/babynames/names.zip", Path("names.zip"))
 download_file("https://raw.githubusercontent.com/BradyStephenson/bible-data/refs/heads/main/BibleData-PersonLabel.csv", Path("BibleData-PersonLabel.csv"))
 
-# Unzip names.zip
-with ZipFile("names.zip", 'r') as zip_ref:
-    zip_ref.extractall(".")
-    print("Unzipped names.zip")
+# Assume `names.zip` is already in the repo
+if not Path("names").exists():
+    print("Unzipping local names.zip...")
+    with ZipFile("names.zip", 'r') as zip_ref:
+        zip_ref.extractall("names")
+else:
+    print("SSA name files already extracted.")
+
+# Define where to find SSA name files
+ssa_name_txt_files = list(Path("names").glob("yob*.txt"))
 
 # ------------------
 # Load Data
 # ------------------
-ssa_name_txt_files = list(Path(".").glob("yob*.txt"))
 
 def load_ssa_names():
     ssa_dfs = []
@@ -60,7 +63,7 @@ def load_bible_names():
     )
     return bible_names_df
 
-# Load on startup
+# Load data on startup
 ssa_names_df, ssa_names_aggregated_df = load_ssa_names()
 bible_names_df = load_bible_names()