Update app.py

app.py

@@ -1,7 +1,11 @@
+# Standard library imports
 import datetime
 import base64
 import os
+
+# Related third-party imports
 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
@@ -18,25 +22,38 @@ load_dotenv()
 COHERE_API_KEY = os.environ["COHERE_API_KEY"]
 co = cohere.Client(COHERE_API_KEY)
 
+# Configuration: Set to True if running locally, False if running on Streamlit Cloud
+IS_LOCAL = False
+
 # Constants
 SEARCH_TYPES = ["web", "image", "video", "news", "discover", "googleNews"]
 DATE_RANGE_OPTIONS = [
-    "Last 7 Days", "Last 30 Days", "Last 3 Months",
-    "Last 6 Months", "Last 12 Months", "Last 16 Months", "Custom Range"
+    "Last 7 Days",
+    "Last 30 Days",
+    "Last 3 Months",
+    "Last 6 Months",
+    "Last 12 Months",
+    "Last 16 Months",
+    "Custom Range"
 ]
 DEVICE_OPTIONS = ["All Devices", "desktop", "mobile", "tablet"]
 BASE_DIMENSIONS = ["page", "query", "country", "date"]
 MAX_ROWS = 250_000
 DF_PREVIEW_ROWS = 100
 
+# -------------
 # Streamlit App Configuration
+# -------------
+
 def setup_streamlit():
-    st.set_page_config(page_title="✨ Simple Google Search Console Data", layout="wide")
-    st.title("✨ Simple Google Search Console Data")
+    st.set_page_config(page_title="✨ Simple Google Search Console Data | LeeFoot.co.uk", layout="wide")
+    st.title("✨ Simple Google Search Console Data | June 2024")
+    st.markdown(f"### Lightweight GSC Data Extractor. (Max {MAX_ROWS:,} Rows)")
     st.markdown(
         """
-        Created by [LeeFootSEO](https://twitter.com/LeeFootSEO) |
-        [More Apps & Scripts](https://leefoot.co.uk)
+        <p>
+            Created by <a href="https://twitter.com/LeeFootSEO" target="_blank">LeeFootSEO</a> |
+            <a href="https://leefoot.co.uk" target="_blank">More Apps & Scripts on my Website</a>
         """,
         unsafe_allow_html=True
     )
@@ -62,7 +79,10 @@ def init_session_state():
     if 'custom_end_date' not in st.session_state:
         st.session_state.custom_end_date = datetime.date.today()
 
+# -------------
 # Data Processing Functions
+# -------------
+
 def fetch_content(url):
     try:
         response = requests.get(url)
@@ -104,7 +124,10 @@ def process_gsc_data(df):
     result = df_unique[['page', 'query', 'clicks', 'impressions', 'ctr', 'position', 'relevancy_score']]
     return result
 
+# -------------
 # Google Authentication Functions
+# -------------
+
 def load_config():
     client_config = {
         "web": {
@@ -112,7 +135,7 @@ def load_config():
             "client_secret": os.environ["CLIENT_SECRET"],
             "auth_uri": "https://accounts.google.com/o/oauth2/auth",
             "token_uri": "https://oauth2.googleapis.com/token",
-            "redirect_uris": ["https://your-redirect-uri.com/"],
+            "redirect_uris": ["https://poemsforaphrodite-gscpro.hf.space/"],
         }
     }
     return client_config
@@ -143,7 +166,10 @@ def auth_search_console(client_config, credentials):
     }
     return searchconsole.authenticate(client_config=client_config, credentials=token)
 
+# -------------
 # Data Fetching Functions
+# -------------
+
 def list_gsc_properties(credentials):
     service = build('webmasters', 'v3', credentials=credentials)
     site_list = service.sites().list().execute()
@@ -168,7 +194,10 @@ def fetch_data_loading(webproperty, search_type, start_date, end_date, dimension
         processed_df = process_gsc_data(df)
         return processed_df
 
+# -------------
 # Utility Functions
+# -------------
+
 def update_dimensions(selected_search_type):
     return BASE_DIMENSIONS + ['device'] if selected_search_type in SEARCH_TYPES else BASE_DIMENSIONS
 
@@ -195,10 +224,14 @@ def show_error(e):
 def property_change():
     st.session_state.selected_property = st.session_state['selected_property_selector']
 
-def make_clickable(val):
-    return f'<a href="{val}" target="_blank">{val}</a>'
-
+# -------------
 # File & Download Operations
+# -------------
+
+def show_dataframe(report):
+    with st.expander("Preview the First 100 Rows (Unique Pages with Top Query)"):
+        st.dataframe(report.head(DF_PREVIEW_ROWS))
+
 def download_csv_link(report):
     def to_csv(df):
         return df.to_csv(index=False, encoding='utf-8-sig')
@@ -207,44 +240,55 @@ def download_csv_link(report):
     href = f'<a href="data:file/csv;base64,{b64_csv}" download="search_console_data.csv">Download CSV File</a>'
     st.markdown(href, unsafe_allow_html=True)
 
+# -------------
 # Streamlit UI Components
+# -------------
+
 def show_google_sign_in(auth_url):
-    st.info("Please sign in with Google to use the application.")
-    st.markdown(f'<a href="{auth_url}" target="_self">Sign in with Google</a>', 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):
-    default = st.session_state.selected_property
-    if not default and properties:
-        default = properties[0]
-    webproperty = st.selectbox(
-        "Select Web Property",
+    selected_property = st.selectbox(
+        "Select a Search Console Property:",
         properties,
-        index=properties.index(default),
+        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[webproperty]
+    return account[selected_property]
 
 def show_search_type_selector():
-    default = st.session_state.selected_search_type
-    return st.selectbox("Select Search Type", SEARCH_TYPES, index=SEARCH_TYPES.index(default))
+    return st.selectbox(
+        "Select Search Type:",
+        SEARCH_TYPES,
+        index=SEARCH_TYPES.index(st.session_state.selected_search_type),
+        key='search_type_selector'
+    )
 
 def show_date_range_selector():
-    default = st.session_state.selected_date_range
-    return st.selectbox("Select Date Range", DATE_RANGE_OPTIONS, index=DATE_RANGE_OPTIONS.index(default))
+    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():
     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(selected_search_type):
-    available_dimensions = update_dimensions(selected_search_type)
-    default = [dim for dim in st.session_state.selected_dimensions if dim in available_dimensions]
-    return st.multiselect("Select Dimensions", available_dimensions, default=default)
-
-def show_device_selector():
-    default = st.session_state.selected_device
-    return st.selectbox("Select Device Type", DEVICE_OPTIONS, index=DEVICE_OPTIONS.index(default))
+def show_dimensions_selector(search_type):
+    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):
     total_rows = len(report)
@@ -253,7 +297,7 @@ def show_paginated_dataframe(report, rows_per_page=20):
     if 'current_page' not in st.session_state:
         st.session_state.current_page = 1
 
-    col1, col2, col3 = st.columns([1, 3, 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
@@ -265,18 +309,16 @@ def show_paginated_dataframe(report, rows_per_page=20):
 
     start_idx = (st.session_state.current_page - 1) * rows_per_page
     end_idx = start_idx + rows_per_page
+    st.dataframe(report.iloc[start_idx:end_idx])
 
-    paginated_df = report.iloc[start_idx:end_idx].copy()
-    paginated_df['position'] = paginated_df['position'].round(0).astype(int)
-    paginated_df['page'] = paginated_df['page'].apply(make_clickable)
-
-    st.write(paginated_df.to_html(escape=False, index=False), unsafe_allow_html=True)
-
+# -------------
 # Main Streamlit App Function
+# -------------
+
 def main():
     setup_streamlit()
     client_config = load_config()
-
+    
     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)
 
@@ -320,5 +362,6 @@ def main():
             elif st.session_state.report_data is not None:
                 st.warning("No data found for the selected criteria.")
 
+                
 if __name__ == "__main__":
-    main()
+    main()