Update src/streamlit_app.py

src/streamlit_app.py

@@ -3,8 +3,10 @@ import requests
 import pandas as pd
 import io
 import time
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
 
-# Function to fetch WNBA player game log data
+# Function to fetch WNBA player game log data with retry logic
 @st.cache_data
 def fetch_wnba_data():
     url = "https://stats.wnba.com/stats/playergamelogs"
@@ -33,14 +35,14 @@ def fetch_wnba_data():
         "VsDivision": ""
     }
     headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36",
+        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
         "Accept": "application/json, text/plain, */*",
         "x-nba-stats-origin": "stats",
         "x-nba-stats-token": "true",
         "Referer": "https://stats.wnba.com/players/boxscores-traditional/",
         "Accept-Encoding": "gzip, deflate, br",
         "Accept-Language": "en-GB,en-US;q=0.9,en;q=0.8",
-        "sec-ch-ua": '"Not_A Brand";v="99", "Google Chrome";v="109", "Chromium";v="109"',
+        "sec-ch-ua": '"Not/A)Brand";v="99", "Google Chrome";v="126", "Chromium";v="126"',
         "sec-ch-ua-mobile": "?0",
         "sec-ch-ua-platform": '"Windows"',
         "sec-fetch-dest": "empty",
@@ -48,11 +50,18 @@ def fetch_wnba_data():
         "sec-fetch-site": "same-origin"
     }
 
+    # Set up retry strategy
+    session = requests.Session()
+    retries = Retry(total=3, backoff_factor=1, status_forcelist=[429, 500, 502, 503, 504])
+    session.mount("https://", HTTPAdapter(max_retries=retries))
+
     try:
         st.write("Sending API request...")
-        response = requests.get(url, params=params, headers=headers, timeout=10)
-        response.raise_for_status()  # Raises an error for non-200 status codes
-        st.write("API request successful. Processing data...")
+        start_time = time.time()
+        response = session.get(url, params=params, headers=headers, timeout=30)
+        response.raise_for_status()
+        fetch_time = time.time() - start_time
+        st.write(f"API request successful. Fetched in {fetch_time:.2f} seconds.")
         data = response.json()
         game_logs = data.get("resultSets", [])[0].get("rowSet", [])
         if not game_logs:
@@ -60,13 +69,13 @@ def fetch_wnba_data():
             return []
         return game_logs
     except requests.Timeout:
-        st.error("Request timed out after 10 seconds. Try again later or check your network.")
+        st.error("Request timed out after 30 seconds. The API may be slow, or your network is unstable. Try again later.")
         return []
     except requests.HTTPError as e:
-        st.error(f"HTTP error occurred: {e}. Check API headers or rate limits.")
+        st.error(f"HTTP error: {e}. Check if the API requires updated headers or cookies (e.g., cf_clearance).")
         return []
     except requests.RequestException as e:
-        st.error(f"Failed to fetch data: {e}")
+        st.error(f"Request failed: {e}. Possible API or network issue.")
         return []
 
 # Function to convert game logs to a DataFrame
@@ -95,11 +104,7 @@ st.title("WNBA 2025 Player Game Logs")
 
 # Fetch data with progress feedback
 with st.spinner("Fetching WNBA player game log data..."):
-    start_time = time.time()
     game_logs = fetch_wnba_data()
-    fetch_time = time.time() - start_time
-    if game_logs:
-        st.success(f"Data fetched successfully in {fetch_time:.2f} seconds!")
 
 if game_logs:
     # Create DataFrame
@@ -123,13 +128,13 @@ if game_logs:
 
     # Display first 1000 records
     st.subheader("Game Log Data (First 1000 Records)")
-    display_df = filtered_df.iloc[:1000]  # Limit to first 1000 records
+    display_df = filtered_df.iloc[:1000]
     st.write(f"Displaying {len(display_df)} records (out of {len(filtered_df)} after filtering)")
     st.dataframe(display_df, use_container_width=True)
 
     # Download button for all records
     st.subheader("Download Data")
-    csv_data = convert_to_csv(filtered_df)  # Use full filtered DataFrame
+    csv_data = convert_to_csv(filtered_df)
     st.download_button(
         label=f"Download All {len(filtered_df)} Records as CSV",
         data=csv_data,
@@ -137,7 +142,7 @@ if game_logs:
         mime="text/csv"
     )
 
-    # Visualization (Points per Game for selected player)
+    # Visualization
     if player_filter != "All":
         st.subheader(f"Points Scored by {player_filter}")
         player_data = filtered_df[["Game_Date", "PTS"]].copy()