Update app.py

app.py

@@ -242,7 +242,6 @@ def calculate_relevance_score(page_content, query, co):
         return 0
 
 def analyze_competitors(row, co, custom_url=None, country_code=None):
-    # logger.info(f"Analyzing competitors for query: {row['query']}")
     query = row['query']
     our_url = row['page']
     
@@ -267,50 +266,44 @@ def analyze_competitors(row, co, custom_url=None, country_code=None):
 
 def show_competitor_analysis(row, co, country_code):
     if st.button("Check Competitors", key=f"comp_{row['page']}"):
-        # logger.info(f"Competitor analysis requested for page: {row['page']}")
+        st.write(f"Competitor Analysis for: {row['query']}")
         with st.spinner('Analyzing competitors...'):
             results_df = analyze_competitors(row, co, country_code=country_code)
+            
+            # Remove duplicates and our site from the results
+            results_df = results_df.drop_duplicates(subset='url', keep='first')
+            our_result = results_df[results_df['url'] == row['page']]
+            competitor_results = results_df[results_df['url'] != row['page']]
+            
+            # Combine results, with our result at its actual position
+            combined_results = pd.concat([competitor_results.iloc[:row['position']-1], our_result, competitor_results.iloc[row['position']-1:]])
+            combined_results = combined_results.reset_index(drop=True)
+            
+            # Add position column, starting from 1
+            combined_results.insert(0, 'Position', range(1, len(combined_results) + 1))
+            
+            # Format our result in bold
+            combined_results['URL'] = combined_results.apply(
+                lambda x: f"**{x['url']}**" if x['url'] == row['page'] else x['url'], axis=1
+            )
+            
+            # Display the results
             st.write("Relevancy Score Comparison:")
-            st.dataframe(results_df)
+            st.markdown(combined_results[['Position', 'URL', 'relevancy_score']].to_markdown(index=False), unsafe_allow_html=True)
             
-            our_data = results_df[results_df['url'] == row['page']]
-            if our_data.empty:
-                st.error(f"Our page '{row['page']}' is not in the results. This indicates an error in fetching or processing the page.")
-               # logger.error(f"Our page '{row['page']}' is missing from the results.")
-                
-                # Additional debugging information
-                # st.write("Debugging Information:")
-                # st.json({
-                #     "our_url": row['page'],
-                #     "query": row['query'],
-                #     "content_fetched": fetch_content(row['page']),
-                #     "urls_processed": results_df['url'].tolist()
-                # })
-            else:
-                our_rank = our_data.index[0] + 1
-                total_results = len(results_df)
-                our_score = our_data['relevancy_score'].values[0]
-                
-               # logger.info(f"Our page ranks {our_rank} out of {total_results} in terms of relevancy score.")
-                st.write(f"Our page ('{row['page']}') ranks {our_rank} out of {total_results} in terms of relevancy score.")
-                st.write(f"Our relevancy score: {our_score:.4f}")
-                
-                if our_score == 0:
-                    st.warning("Our page's relevancy score is 0. This might indicate an issue with content fetching or score calculation.")
-                    # Additional debugging information
-                    # st.write("Debugging Information:")
-                    # content = fetch_content(row['page'])
-                    # st.json({
-                    #     "content_length": len(content),
-                    #     "content_preview": content[:500] if content else "No content fetched",
-                    #     "query": row['query']
-                    # })
-                elif our_rank == 1:
-                    st.success("Your page has the highest relevancy score!")
-                elif our_rank <= 3:
-                    st.info("Your page is among the top 3 most relevant results.")
-                elif our_rank > total_results / 2:
-                    st.warning("Your page's relevancy score is in the lower half of the results. Consider optimizing your content.")
+            our_rank = combined_results.index[combined_results['url'] == row['page']].tolist()[0] + 1
+            total_results = len(combined_results)
+            our_score = our_result['relevancy_score'].values[0]
+            
+            st.write(f"Our page ranks {our_rank} out of {total_results} in terms of relevancy score.")
+            st.write(f"Our relevancy score: {our_score:.4f}")
+            
+            if our_rank == 1:
+                st.success("Your page has the highest relevancy score!")
+            elif our_rank <= 3:
+                st.info("Your page is among the top 3 most relevant results.")
+            elif our_rank > total_results / 2:
+                st.warning("Your page's relevancy score is in the lower half of the results. Consider optimizing your content.")
 
 def process_gsc_data(df):
     #logging.info("Processing GSC data")