Update src/streamlit_app.py

src/streamlit_app.py

@@ -36,9 +36,6 @@ if 'chat_history' not in st.session_state:
 # Basketball-Reference Data Fetching Utilities
 # —————————————————————————————————————————————————————————————————————————————
 
-# Basketball-Reference Data Fetching Utilities
-# —————————————————————————————————————————————————————————————————————————————
-
 import requests
 import pandas as pd
 import streamlit as st
@@ -76,7 +73,7 @@ def parse_table(html, table_id=None):
     """
     if not html:
         return pd.DataFrame()
-    
+
     soup = BeautifulSoup(html, "html.parser")
     tbl_html = ""
 
@@ -87,22 +84,14 @@ def parse_table(html, table_id=None):
             tbl_html = str(tbl)
         else:
             # If not found directly, search for it within HTML comments
-            # Basketball-Reference often comments out tables
-            comment_pattern = re.compile(
-                r'<!--.*?<table[^>]*?id=["\']' + re.escape(table_id) + r'["\'][^>]*?>.*?</table>.*?-->', 
-                re.DOTALL | re.IGNORECASE
-            )
-            comment_match = comment_pattern.search(html)
-            if comment_match:
-                # Extract the content of the comment
-                comment_content = comment_match.group(0)
-                # Remove the comment tags
-                comment_content = comment_content.replace('<!--', '').replace('-->', '')
-                # Parse the comment content as new HTML
-                comment_soup = BeautifulSoup(comment_content, 'html.parser')
-                tbl = comment_soup.find('table', {'id': table_id})
-                if tbl:
-                    tbl_html = str(tbl)
+            comments = soup.find_all(string=lambda text: isinstance(text, Comment))
+            for comment in comments:
+                if table_id in comment:
+                    comment_soup = BeautifulSoup(comment, 'html.parser')
+                    tbl = comment_soup.find('table', {'id': table_id})
+                    if tbl:
+                        tbl_html = str(tbl)
+                        break
     else:
         # fallback: first table on page (only if no table_id specified)
         first = soup.find("table")