Update app.py

app.py

@@ -17,7 +17,8 @@ import requests
 from bs4 import BeautifulSoup
 
 load_dotenv()
-#test
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
 
 # Initialize Cohere client
 COHERE_API_KEY = os.environ["COHERE_API_KEY"]
@@ -287,33 +288,7 @@ def show_dimensions_selector(search_type):
         key='dimensions_selector'
     )
 
-import datetime
-import base64
-import os
-
-import streamlit as st
-from streamlit_elements import elements
-from google_auth_oauthlib.flow import Flow
-from googleapiclient.discovery import build
-from dotenv import load_dotenv
-import pandas as pd
-import searchconsole
-import cohere
-from sklearn.metrics.pairwise import cosine_similarity
-import requests
-from bs4 import BeautifulSoup
-
-# ... (keep the existing imports and configuration)
 
-# -------------
-# Data Processing Functions
-# -------------
-
-# ... (keep existing functions)
-
-# -------------
-# Streamlit UI Components
-# -------------
 
 def show_paginated_dataframe(report, rows_per_page=20, model_type='english'):
     # Check if required columns are present
@@ -403,7 +378,7 @@ def show_paginated_dataframe(report, rows_per_page=20, model_type='english'):
             '.calculate-btn { cursor: pointer; padding: 5px 10px; background-color: #4CAF50; color: white; border: none; border-radius: 4px; }',
             '.calculate-btn:hover { background-color: #45a049; }',
             '</style>',
-            *[f'<script>document.getElementsByTagName("table")[0].rows[{i+1}].cells[6].onclick = function(e) {{ if(e.target.classList.contains("calculate-btn")) calculate_relevancy({start_idx + i}) }}</script>'
+            *[f'<script>document.getElementsByTagName("table")[0].rows[{i+1}].cells[6].onclick = function(e) {{ if(e.target.classList.contains("calculate-btn")) {{ Streamlit.setComponentValue("calculate_relevancy", {start_idx + i}); }} }}</script>'
               for i in range(min(rows_per_page, len(report) - start_idx))]
         ]) + '</table>')
         dataframe_placeholder.markdown(df_html, unsafe_allow_html=True)
@@ -411,37 +386,37 @@ def show_paginated_dataframe(report, rows_per_page=20, model_type='english'):
     # Initial dataframe display
     update_dataframe()
     
-    # JavaScript to handle button clicks
-    st.markdown("""
-    <script>
-    function calculate_relevancy(row_index) {
-        Streamlit.setComponentValue('calculate_relevancy', row_index);
-    }
-    </script>
-    """, unsafe_allow_html=True)
-    
     # Handle relevancy calculation
     if st.session_state.get('calculate_relevancy') is not None:
         row_index = st.session_state.calculate_relevancy
-        page_content = fetch_content(report.iloc[row_index]['page'])
-        query = report.iloc[row_index]['query']
-        relevancy_score = calculate_single_relevancy_score(page_content, query, model_type)
-        report.at[row_index, 'relevancy_score'] = relevancy_score
-        st.session_state.calculate_relevancy = None  # Reset the state
-        update_dataframe()  # Update the dataframe display
+        logger.info(f"Calculating relevancy for row index: {row_index}")
+        try:
+            page_content = fetch_content(report.iloc[row_index]['page'])
+            query = report.iloc[row_index]['query']
+            relevancy_score = calculate_single_relevancy_score(page_content, query, model_type)
+            logger.info(f"Relevancy score calculated: {relevancy_score}")
+            report.at[row_index, 'relevancy_score'] = f"{relevancy_score:.2f}"
+            st.session_state.calculate_relevancy = None  # Reset the state
+            update_dataframe()  # Update the dataframe display
+            st.success(f"Relevancy score calculated for row {row_index + 1}")
+        except Exception as e:
+            logger.error(f"Error calculating relevancy score: {str(e)}")
+            st.error(f"Error calculating relevancy score: {str(e)}")
 
     return report
 
-
 # -------------
 # Main Streamlit App Function
 # -------------
 
+
 def main():
+    logger.info("Starting the Streamlit app")
     setup_streamlit()
     client_config = load_config()
     
     if 'auth_flow' not in st.session_state or 'auth_url' not in st.session_state:
+        logger.info("Initializing Google auth flow")
         st.session_state.auth_flow, st.session_state.auth_url = google_auth(client_config)
 
     # Directly access query parameters using st.query_params
@@ -450,23 +425,27 @@ def main():
     # Retrieve the 'code' parameter
     auth_code = query_params.get("code", None)
     
-
     if auth_code and 'credentials' not in st.session_state:
+        logger.info("Fetching token with auth code")
         st.session_state.auth_flow.fetch_token(code=auth_code)
         st.session_state.credentials = st.session_state.auth_flow.credentials
+        logger.info("Credentials stored in session state")
 
     if 'credentials' not in st.session_state:
+        logger.info("No credentials found, showing Google sign-in")
         show_google_sign_in(st.session_state.auth_url)
     else:
+        logger.info("Credentials found, initializing session state")
         init_session_state()
         account = auth_search_console(client_config, st.session_state.credentials)
         properties = list_gsc_properties(st.session_state.credentials)
 
         if properties:
+            logger.info(f"Found {len(properties)} properties")
             webproperty = show_property_selector(properties, account)
             search_type = show_search_type_selector()
             date_range_selection = show_date_range_selector()
-            model_type = show_model_type_selector()  # Add this line
+            model_type = show_model_type_selector()
             if date_range_selection == 'Custom Range':
                 show_custom_date_inputs()
                 start_date, end_date = st.session_state.custom_start_date, st.session_state.custom_end_date
@@ -480,15 +459,22 @@ def main():
 
             if st.button("Fetch Data"):
                 with st.spinner('Fetching data...'):
+                    logger.info(f"Fetching GSC data for {webproperty} from {start_date} to {end_date}")
                     st.session_state.report_data = fetch_gsc_data(webproperty, search_type, start_date, end_date, selected_dimensions)
+                    logger.info(f"Data fetched: {len(st.session_state.report_data)} rows")
 
             if st.session_state.report_data is not None and not st.session_state.report_data.empty:
+                logger.info("Displaying fetched data")
                 st.write("Data fetched successfully. Click the 'Calculate' button in the Relevancy Score column to calculate the score for each row.")
                 st.session_state.report_data = show_paginated_dataframe(st.session_state.report_data, model_type=model_type)
                 download_csv_link(st.session_state.report_data)
             elif st.session_state.report_data is not None:
+                logger.warning("No data found for the selected criteria")
                 st.warning("No data found for the selected criteria.")
+        else:
+            logger.warning("No properties found for the account")
+            st.warning("No properties found for your Google Search Console account.")
 
-                
 if __name__ == "__main__":
+    logger.info("Application started")
     main()