Update app.py

app.py

@@ -17,6 +17,7 @@ import requests
 from bs4 import BeautifulSoup
 
 load_dotenv()
+#test
 
 # Initialize Cohere client
 COHERE_API_KEY = os.environ["COHERE_API_KEY"]
@@ -47,7 +48,8 @@ DF_PREVIEW_ROWS = 100
 
 def setup_streamlit():
     st.set_page_config(page_title="Simple Google Search Console Data", layout="wide")
-    st.title("GSC Relevancy Score Calculator")
+    st.title("✨ Simple Google Search Console Data | June 2024")
+    st.markdown(f"### Lightweight GSC Data Extractor. (Max {MAX_ROWS:,} Rows)")
     st.divider()
 
 def init_session_state():
@@ -244,67 +246,95 @@ def download_csv_link(report):
 # -------------
 
 def show_google_sign_in(auth_url):
-    with elements("sign_in"):
-        st.markdown(
-            f"""
-            <div style="text-align: center;">
-                <h3>Google Search Console Sign-In</h3>
-                <a href="{auth_url}">
-                    <button>Sign in with Google</button>
-                </a>
-            </div>
-            """,
-            unsafe_allow_html=True
-        )
+    with st.sidebar:
+        if st.button("Sign in with Google"):
+            st.write('Please click the link below to sign in:')
+            st.markdown(f'[Google Sign-In]({auth_url})', unsafe_allow_html=True)
 
 def show_property_selector(properties, account):
-    with st.sidebar:
-        st.subheader("Select a Search Console Property")
-        property_selector = st.selectbox("Available Properties", properties, key='selected_property_selector', on_change=property_change)
-        selected_property = next(prop for prop in account if prop.url == property_selector)
-    return selected_property
+    selected_property = st.selectbox(
+        "Select a Search Console Property:",
+        properties,
+        index=properties.index(
+            st.session_state.selected_property) if st.session_state.selected_property in properties else 0,
+        key='selected_property_selector',
+        on_change=property_change
+    )
+    return account[selected_property]
 
 def show_search_type_selector():
-    with st.sidebar:
-        st.subheader("Select Search Type")
-        return st.radio("Search Type", SEARCH_TYPES, key='selected_search_type')
+    return st.selectbox(
+        "Select Search Type:",
+        SEARCH_TYPES,
+        index=SEARCH_TYPES.index(st.session_state.selected_search_type),
+        key='search_type_selector'
+    )
+
+def show_model_type_selector():
+    return st.selectbox(
+        "Select the embedding model:",
+        ["english", "multilingual"],
+        key='model_type_selector'
+    )
 
 def show_date_range_selector():
-    with st.sidebar:
-        st.subheader("Select Date Range")
-        return st.radio("Date Range", DATE_RANGE_OPTIONS, key='selected_date_range')
+    return st.selectbox(
+        "Select Date Range:",
+        DATE_RANGE_OPTIONS,
+        index=DATE_RANGE_OPTIONS.index(st.session_state.selected_date_range),
+        key='date_range_selector'
+    )
 
 def show_custom_date_inputs():
-    with st.sidebar:
-        st.subheader("Select Custom Date Range")
-        st.session_state.custom_start_date = st.date_input("Start Date", value=st.session_state.start_date)
-        st.session_state.custom_end_date = st.date_input("End Date", value=st.session_state.end_date)
-
-def show_model_type_selector():
-    with st.sidebar:
-        st.subheader("Select the Embedding Model")
-        return st.radio("Embedding Model", ["english", "multilingual"])
+    st.session_state.custom_start_date = st.date_input("Start Date", st.session_state.custom_start_date)
+    st.session_state.custom_end_date = st.date_input("End Date", st.session_state.custom_end_date)
 
 def show_dimensions_selector(search_type):
-    dimensions = update_dimensions(search_type)
-    with st.sidebar:
-        st.subheader("Select Dimensions")
-        selected_dimensions = st.multiselect("Dimensions", dimensions, default=['page', 'query'])
-    return selected_dimensions
-
-def show_device_selector():
-    with st.sidebar:
-        st.subheader("Select Device Type")
-        return st.selectbox("Device Type", DEVICE_OPTIONS, key='selected_device')
-
-def show_paginated_dataframe(df):
-    if df.empty:
-        st.warning("No data available to display.")
-    else:
-        show_dataframe(df)
+    available_dimensions = update_dimensions(search_type)
+    return st.multiselect(
+        "Select Dimensions:",
+        available_dimensions,
+        default=st.session_state.selected_dimensions,
+        key='dimensions_selector'
+    )
 
+def show_paginated_dataframe(report, rows_per_page=20):
+    # Convert 'position' column to integer
+    report['position'] = report['position'].astype(int)
+    
+    # Create a clickable URL column
+    def make_clickable(url):
+        return f'<a href="{url}" target="_blank">{url}</a>'
+    
+    report['clickable_url'] = report['page'].apply(make_clickable)
+    
+    # Reorder columns to put clickable_url first and sort by impressions
+    columns = ['clickable_url', 'query', 'impressions', 'clicks', 'ctr', 'position', 'relevancy_score']
+    report = report[columns].sort_values('impressions', ascending=False)
+
+    total_rows = len(report)
+    total_pages = (total_rows - 1) // rows_per_page + 1
+
+    if 'current_page' not in st.session_state:
+        st.session_state.current_page = 1
+
+    col1, col2, col3 = st.columns([1,3,1])
+    with col1:
+        if st.button("Previous", disabled=st.session_state.current_page == 1):
+            st.session_state.current_page -= 1
+    with col2:
+        st.write(f"Page {st.session_state.current_page} of {total_pages}")
+    with col3:
+        if st.button("Next", disabled=st.session_state.current_page == total_pages):
+            st.session_state.current_page += 1
+
+    start_idx = (st.session_state.current_page - 1) * rows_per_page
+    end_idx = start_idx + rows_per_page
+    
+    # Use st.markdown to display the dataframe with clickable links
+    st.markdown(report.iloc[start_idx:end_idx].to_html(escape=False, index=False), unsafe_allow_html=True)
 # -------------
-# Main Function
+# Main Streamlit App Function
 # -------------
 
 def main():
@@ -314,19 +344,14 @@ def main():
     if 'auth_flow' not in st.session_state or 'auth_url' not in st.session_state:
         st.session_state.auth_flow, st.session_state.auth_url = google_auth(client_config)
 
-    # Retrieve query parameters
-    query_params = st.experimental_get_query_params() if IS_LOCAL else st.query_params
-    st.write("Query Parameters:", query_params)  # Debugging
-    auth_code = query_params.get('code', [None])[0]
-    st.write("Authorization Code:", auth_code)  # Debugging
-    
+    query_params = st.experimental_get_query_params()
+    print(query_params)
+    auth_code = query_params.get("code", [None])[0]
+
     if auth_code and 'credentials' not in st.session_state:
-        try:
-            st.session_state.auth_flow.fetch_token(code=auth_code)
-            st.session_state.credentials = st.session_state.auth_flow.credentials
-        except Exception as e:
-            st.error(f"Error fetching token: {e}")
-    
+        st.session_state.auth_flow.fetch_token(code=auth_code)
+        st.session_state.credentials = st.session_state.auth_flow.credentials
+
     if 'credentials' not in st.session_state:
         show_google_sign_in(st.session_state.auth_url)
     else:
@@ -338,7 +363,7 @@ def main():
             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()
+            model_type = show_model_type_selector()  # Add this line
             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
@@ -352,13 +377,14 @@ def main():
 
             if st.button("Fetch Data"):
                 with st.spinner('Fetching data...'):
-                    st.session_state.report_data = fetch_data_loading(webproperty, search_type, start_date, end_date, selected_dimensions, model_type=model_type)
+                    st.session_state.report_data = fetch_data_loading(webproperty, search_type, start_date, end_date, selected_dimensions, model_type=model_type)  # Update this line
 
             if st.session_state.report_data is not None and not st.session_state.report_data.empty:
                 show_paginated_dataframe(st.session_state.report_data)
                 download_csv_link(st.session_state.report_data)
             elif st.session_state.report_data is not None:
                 st.warning("No data found for the selected criteria.")
+
                 
 if __name__ == "__main__":
-    main()
+    main()