Update app.py

app.py

@@ -565,14 +565,14 @@ def show_tabular_data(df, co, country_code):
         st.experimental_rerun()
     
     # Display column headers
-    cols = st.columns([0.5, 3, 2, 1, 1, 1, 1, 1, 1])
-    headers = ['Select', 'Page', 'Query', 'Clicks', 'Impressions', 'CTR', 'Position', 'Relevancy Score', 'Competitors']
+    cols = st.columns([0.5, 3, 2, 1, 1, 1, 1, 1, 1, 1])  # Added an extra column
+    headers = ['Select', 'Page', 'Query', 'Clicks', 'Impressions', 'CTR', 'Position', 'Relevancy Score', 'Competitors', 'Compare']
     for col, header in zip(cols, headers):
         col.write(f"**{header}**")
 
     # Display each row
     for i, row in enumerate(df.iloc[start_idx:end_idx].itertuples(), start=start_idx):
-        cols = st.columns([0.5, 3, 2, 1, 1, 1, 1, 1, 1])
+        cols = st.columns([0.5, 3, 2, 1, 1, 1, 1, 1, 1, 1])  # Added an extra column
         
         # Checkbox for row selection
         cols[0].checkbox("", key=f"select_{i}", value=st.session_state.selected_rows[i],
@@ -631,8 +631,74 @@ def show_tabular_data(df, co, country_code):
                 else:
                     st.error(f"Our page '{row.page}' is not in the results. This indicates an error in fetching or processing the page.")
 
+        # New button for content comparison
+        compare_button = cols[9].button("Compare", key=f"compare_{i}")
+        if compare_button:
+            compare_with_top_result(row._asdict(), co, country_code)
+
     return df  # Return the updated dataframe
 
+def compare_with_top_result(row, co, country_code):
+    query = row['query']
+    our_url = row['page']
+    
+    # Fetch SERP results
+    serp_results = get_serp_results(query, country_code)
+    
+    if not serp_results:
+        st.error("Unable to fetch SERP results.")
+        return
+    
+    top_result = serp_results[0]
+    top_url = top_result['url']
+    
+    # Fetch content
+    our_content = fetch_content(our_url, query)
+    top_content = top_result['content']
+    
+    # Calculate relevancy scores
+    our_score = calculate_relevance_score(our_content, query, co)
+    top_score = calculate_relevance_score(top_content, query, co)
+    
+    # Prepare prompt for GPT-4
+    prompt = f"""
+    Compare the following two pieces of content for the query "{query}":
+
+    1. Top-ranking page (score: {top_score:.4f}):
+    {top_content[:1000]}...
+
+    2. Our page (score: {our_score:.4f}):
+    {our_content[:1000]}...
+
+    Explain the difference in cosine similarity scores between the top-ranking page and our page. 
+    What can we do to improve our score and make our content more relevant to the query?
+    Provide specific, actionable recommendations.
+    """
+
+    # Call GPT-4
+    try:
+        response = openai_client.chat.completions.create(
+            model="gpt-4o-mini",
+            messages=[
+                {"role": "system", "content": "You are an SEO expert analyzing content relevance."},
+                {"role": "user", "content": prompt}
+            ],
+            max_tokens=1000
+        )
+        analysis = response.choices[0].message.content.strip()
+        
+        # Display results
+        st.subheader("Content Comparison Analysis")
+        st.write(f"Query: {query}")
+        st.write(f"Top-ranking URL: {top_url}")
+        st.write(f"Our URL: {our_url}")
+        st.write(f"Top-ranking score: {top_score:.4f}")
+        st.write(f"Our score: {our_score:.4f}")
+        st.write("Analysis:")
+        st.write(analysis)
+    except Exception as e:
+        st.error(f"Error in GPT-4 analysis: {str(e)}")
+
 def show_date_range_selector():
   #  logging.info("Showing date range selector")
     return st.selectbox(