Update app.py

app.py

@@ -113,13 +113,14 @@ def get_serp_results(query):
     }
 
     try:
-        logger.debug(f"Calling Apify Actor with input: {run_input}")
+        #logger.debug(f"Calling Apify Actor with input: {run_input}")
         # Run the Actor and wait for it to finish
         run = client.actor("nFJndFXA5zjCTuudP").call(run_input=run_input)
         logger.info(f"Apify Actor run completed. Run ID: {run.get('id')}")
         
         # Fetch results from the run's dataset
-        logger.debug(f"Fetching results from dataset ID: {run.get('defaultDatasetId')}")
+        
+        #logger.debug(f"Fetching results from dataset ID: {run.get('defaultDatasetId')}")
         results = list(client.dataset(run["defaultDatasetId"]).iterate_items())
         logger.info(f"Fetched {len(results)} results from Apify dataset")
         
@@ -183,6 +184,8 @@ def analyze_competitors(row, co):
     
     # Calculate score for our page first
     our_content = fetch_content(our_url)
+    print(out_url)
+    print(our_content)
     if our_content:
         our_score = calculate_relevance_score(our_content, query, co)
         results.append({'url': our_url, 'relevancy_score': our_score})
@@ -193,7 +196,7 @@ def analyze_competitors(row, co):
     # Calculate scores for competitor pages
     for url in competitor_urls:
         try:
-            logger.debug(f"Processing competitor URL: {url}")
+           # logger.debug(f"Processing competitor URL: {url}")
             content = fetch_content(url)
             if not content:
                 logger.warning(f"No content fetched for competitor URL: {url}")
@@ -245,13 +248,13 @@ def show_competitor_analysis(row, co):
                 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']
-                    })
+                    # 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:
@@ -366,22 +369,6 @@ def fetch_gsc_data(webproperty, search_type, start_date, end_date, dimensions, d
         show_error(e)
         return pd.DataFrame()
 
-def calculate_relevance_score(page_content, query, co):
-    logger.info(f"Calculating relevance score for query: {query}")
-    try:
-        if not page_content:
-            logger.warning("Empty page content. Returning score 0.")
-            return 0
-        
-        page_embedding = co.embed(texts=[page_content], model='embed-english-v3.0', input_type='search_document').embeddings[0]
-        query_embedding = co.embed(texts=[query], model='embed-english-v3.0', input_type='search_query').embeddings[0]
-        score = cosine_similarity([query_embedding], [page_embedding])[0][0]
-        logger.debug(f"Relevance score calculated: {score}")
-        return score
-    except Exception as e:
-        logger.exception(f"Error calculating relevance score: {str(e)}")
-        st.error(f"Error calculating relevance score: {str(e)}")
-        return 0
     
 def calculate_relevancy_scores(df, model_type):
     logging.info("Calculating relevancy scores")
@@ -420,10 +407,10 @@ def calc_date_range(selection, custom_start=None, custom_end=None):
     today = datetime.date.today()
     if selection == 'Custom Range':
         if custom_start and custom_end:
-            logging.debug(f"Custom date range: {custom_start} to {custom_end}")
+            #logging.debug(f"Custom date range: {custom_start} to {custom_end}")
             return custom_start, custom_end
         else:
-            logging.debug("Defaulting custom date range to last 7 days")
+            #logging.debug("Defaulting custom date range to last 7 days")
             return today - datetime.timedelta(days=7), today
     date_range = today - datetime.timedelta(days=range_map.get(selection, 0)), today
     #logging.debug(f"Date range calculated: {date_range}")