Update app.py

app.py

@@ -238,33 +238,49 @@ def calculate_relevance_score(page_content, query, co):
         st.error(f"Error calculating relevance score: {str(e)}")
         return 0
 
+def normalize_url(url):
+    return url.rstrip('/').lower()
+
+@st.cache_data(ttl=3600)  # Cache the results for 1 hour
 def analyze_competitors(row, co, custom_url=None, country_code=None):
     query = row['query']
-    our_url = row['page']
+    our_url = normalize_url(row['page'])
     
     competitor_data = get_serp_results(query, country_code)
     
     results = []
     for data in competitor_data:
+        competitor_url = normalize_url(data['url'])
         score = calculate_relevance_score(data['content'], query, co)
-        results.append({'position': data['position'], 'url': data['url'], 'relevancy_score': score})
+        results.append({
+            'position': data['position'],
+            'url': competitor_url,
+            'relevancy_score': score,
+            'is_our_url': competitor_url == our_url
+        })
     
     our_content = fetch_content(our_url, query)
     our_score = calculate_relevance_score(our_content, query, co)
-    our_position = next((r['position'] for r in results if r['url'] == our_url), len(results) + 1)
-    results.append({'position': our_position, 'url': our_url, 'relevancy_score': our_score})
     
-    # Sort results by the original position
-    results = sorted(results, key=lambda x: x['position'])
+    if not any(r['is_our_url'] for r in results):
+        results.append({
+            'position': len(results) + 1,
+            'url': our_url,
+            'relevancy_score': our_score,
+            'is_our_url': True
+        })
     
-    # Re-number positions starting from 1 and format URLs
-    for idx, item in enumerate(results, start=1):
-        item['position'] = idx
-        if item['url'] == our_url:
-            item['url'] = f"**{item['url']}**"  # Mark our URL in bold
+    # Sort results by position
+    results = sorted(results, key=lambda x: x['position'])
     
-    # Keep only 'position', 'url', and 'relevancy_score' columns
-    results_df = pd.DataFrame(results)[['position', 'url', 'relevancy_score']]
+    # Create DataFrame and format
+    results_df = pd.DataFrame(results)[['position', 'url', 'relevancy_score', 'is_our_url']]
+    results_df['position'] = results_df['position'].astype(int)
+    results_df['url'] = results_df.apply(
+        lambda x: f"**{x['url']}**" if x['is_our_url'] else x['url'], axis=1
+    )
+    results_df = results_df[['position', 'url', 'relevancy_score']]
+    results_df.columns = ['Position', 'URL', 'Score']
     
     return results_df
 
@@ -274,20 +290,12 @@ def show_competitor_analysis(row, co, country_code):
         with st.spinner('Analyzing competitors...'):
             results_df = analyze_competitors(row, co, country_code=country_code)
             
-            # Rename columns to have a proper header
-            results_df.columns = ['Position', 'URL', 'Score']
-            
-            # Convert 'Position' to integer for proper sorting and display
-            results_df['Position'] = results_df['Position'].astype(int)
-            
-            # Convert the DataFrame to Markdown with bold URLs where applicable
-            markdown_table = results_df.to_markdown(index=False)
-            
             # Display the Markdown table
-            st.markdown(markdown_table, unsafe_allow_html=True)
+            st.markdown(results_df.to_markdown(index=False), unsafe_allow_html=True)
             
             # Extract our result for additional insights
-            our_result = results_df[results_df['URL'].str.contains("**" + row['page'] + "**")]
+            our_result = results_df[results_df['URL'].str.contains('\*\*')]
+            
             if not our_result.empty:
                 our_rank = our_result['Position'].values[0]
                 total_results = len(results_df)
@@ -586,7 +594,7 @@ def show_tabular_data(df, co, country_code):
             st.write(f"Competitor Analysis for: {row.query}")
             with st.spinner('Analyzing competitors...'):
                 results_df = analyze_competitors(row._asdict(), co, country_code=country_code)
-                
+                print(results_df)
                 # Sort the results by relevancy score in descending order
                 results_df = results_df.sort_values('relevancy_score', ascending=False).reset_index(drop=True)