app.py

# Standard library imports
import datetime
import base64
import os

# Related third-party imports
import streamlit as st
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
from apify_client import ApifyClient
import urllib.parse
import openai
from openai import OpenAI
import re
import pycountry


load_dotenv()


# Initialize Cohere client
APIFY_API_TOKEN = os.environ.get('APIFY_API_TOKEN')
COHERE_API_KEY = os.environ["COHERE_API_KEY"]
co = cohere.Client(COHERE_API_KEY)
if not APIFY_API_TOKEN:
    st.error("APIFY_API_TOKEN is not set in the environment variables. Please set it and restart the application.")

# Initialize the ApifyClient with the API token
apify_client = ApifyClient(APIFY_API_TOKEN)

# Initialize OpenAI client
OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY')
if not OPENAI_API_KEY:
    st.error("OPENAI_API_KEY is not set in the environment variables. Please set it and restart the application.")
openai_client = OpenAI(api_key=OPENAI_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"
]
DEVICE_OPTIONS = ["All Devices", "desktop", "mobile", "tablet"]
BASE_DIMENSIONS = ["page", "query", "country", "date"]
MAX_ROWS = 250_000
DF_PREVIEW_ROWS = 100
COUNTRY_OPTIONS = [
    ("", "All Countries"),
    ("af", "Afghanistan"), ("al", "Albania"), ("dz", "Algeria"), ("as", "American Samoa"),
    ("ad", "Andorra"), ("ao", "Angola"), ("ai", "Anguilla"), ("aq", "Antarctica"),
    ("ag", "Antigua and Barbuda"), ("ar", "Argentina"), ("am", "Armenia"), ("aw", "Aruba"),
    ("au", "Australia"), ("at", "Austria"), ("az", "Azerbaijan"), ("bs", "Bahamas"),
    ("bh", "Bahrain"), ("bd", "Bangladesh"), ("bb", "Barbados"), ("by", "Belarus"),
    ("be", "Belgium"), ("bz", "Belize"), ("bj", "Benin"), ("bm", "Bermuda"),
    ("bt", "Bhutan"), ("bo", "Bolivia"), ("ba", "Bosnia and Herzegovina"), ("bw", "Botswana"),
    ("bv", "Bouvet Island"), ("br", "Brazil"), ("io", "British Indian Ocean Territory"),
    ("bn", "Brunei"), ("bg", "Bulgaria"), ("bf", "Burkina Faso"), ("bi", "Burundi"),
    ("kh", "Cambodia"), ("cm", "Cameroon"), ("ca", "Canada"), ("cv", "Cape Verde"),
    ("ky", "Cayman Islands"), ("cf", "Central African Republic"), ("td", "Chad"),
    ("cl", "Chile"), ("cn", "China"), ("cx", "Christmas Island"), ("cc", "Cocos (Keeling) Islands"),
    ("co", "Colombia"), ("km", "Comoros"), ("cg", "Congo"), ("cd", "Congo, Democratic Republic"),
    ("ck", "Cook Islands"), ("cr", "Costa Rica"), ("ci", "Cote D'Ivoire"), ("hr", "Croatia"),
    ("cu", "Cuba"), ("cy", "Cyprus"), ("cz", "Czech Republic"), ("dk", "Denmark"),
    ("dj", "Djibouti"), ("dm", "Dominica"), ("do", "Dominican Republic"), ("ec", "Ecuador"),
    ("eg", "Egypt"), ("sv", "El Salvador"), ("gq", "Equatorial Guinea"), ("er", "Eritrea"),
    ("ee", "Estonia"), ("et", "Ethiopia"), ("fk", "Falkland Islands (Malvinas)"),
    ("fo", "Faroe Islands"), ("fj", "Fiji"), ("fi", "Finland"), ("fr", "France"),
    ("gf", "French Guiana"), ("pf", "French Polynesia"), ("tf", "French Southern Territories"),
    ("ga", "Gabon"), ("gm", "Gambia"), ("ge", "Georgia"), ("de", "Germany"), ("gh", "Ghana"),
    ("gi", "Gibraltar"), ("gr", "Greece"), ("gl", "Greenland"), ("gd", "Grenada"),
    ("gp", "Guadeloupe"), ("gu", "Guam"), ("gt", "Guatemala"), ("gn", "Guinea"),
    ("gw", "Guinea-Bissau"), ("gy", "Guyana"), ("ht", "Haiti"),
    ("hm", "Heard Island and Mcdonald Islands"), ("va", "Holy See (Vatican City State)"),
    ("hn", "Honduras"), ("hk", "Hong Kong"), ("hu", "Hungary"), ("is", "Iceland"),
    ("in", "India"), ("id", "Indonesia"), ("ir", "Iran, Islamic Republic of"), ("iq", "Iraq"),
    ("ie", "Ireland"), ("il", "Israel"),
]

# -------------
# Streamlit App Configuration
# -------------

def setup_streamlit():
    st.set_page_config(page_title="Keyword Relevance Test", layout="wide")
    st.title("Keyword Relevance Test Using Vector Embedding")
    st.divider()
    #logging.info("Streamlit app configured")

def init_session_state():
    if 'selected_property' not in st.session_state:
        st.session_state.selected_property = None
    if 'selected_search_type' not in st.session_state:
        st.session_state.selected_search_type = 'web'
    if 'selected_date_range' not in st.session_state:
        st.session_state.selected_date_range = 'Last 7 Days'
    if 'start_date' not in st.session_state:
        st.session_state.start_date = datetime.date.today() - datetime.timedelta(days=7)
    if 'end_date' not in st.session_state:
        st.session_state.end_date = datetime.date.today()
    if 'selected_dimensions' not in st.session_state:
        st.session_state.selected_dimensions = ['page', 'query']
    if 'selected_device' not in st.session_state:
        st.session_state.selected_device = 'All Devices'
    if 'custom_start_date' not in st.session_state:
        st.session_state.custom_start_date = datetime.date.today() - datetime.timedelta(days=7)
    if 'custom_end_date' not in st.session_state:
        st.session_state.custom_end_date = datetime.date.today()
    if 'relevancy_scores' not in st.session_state:
        st.session_state.relevancy_scores = {}
    #logging.info("Session state initialized")

# -------------
# Data Processing Functions
# -------------
def generate_embeddings(text_list, model_type):
    #logging.debug(f"Generating embeddings for model type: {model_type}")
    if not text_list:
        logging.warning("Text list is empty, returning empty embeddings")
        return []
    model = 'embed-english-v3.0' if model_type == 'english' else 'embed-multilingual-v3.0'
    input_type = 'search_document'
    response = co.embed(model=model, texts=text_list, input_type=input_type)
    embeddings = response.embeddings
   # logging.debug(f"Embeddings generated successfully for model type: {model_type}")
    return embeddings


def get_serp_results(query, country_code):
    if not APIFY_API_TOKEN:
        st.error("Apify API token is not set. Unable to fetch SERP results.")
        return []

    run_input = {
        "queries": query,
        "resultsPerPage": 5,
        "maxPagesPerQuery": 1,
        "languageCode": "",
        "mobileResults": False,
        "includeUnfilteredResults": False,
        "saveHtml": False,
        "saveHtmlToKeyValueStore": False,
        "includeIcons": False,
        "countryCode": country_code,
    }

    try:
        run = apify_client.actor("nFJndFXA5zjCTuudP").call(run_input=run_input)
        results = list(apify_client.dataset(run["defaultDatasetId"]).iterate_items())
        
        if results and 'organicResults' in results[0]:
            serp_data = []
            for position, item in enumerate(results[0]['organicResults'][:5], start=1):
                url = item['url']
                content = fetch_content(url, query)
                serp_data.append({'position': position, 'url': url, 'content': content})
            return serp_data
        else:
            st.warning("No organic results found in the SERP data.")
            return []
    except Exception as e:
        st.error(f"Error fetching SERP results: {str(e)}")
        return []



        
def extract_relevant_content(full_content, query):
    try:
        response = openai_client.chat.completions.create(
            model="gpt-3.5-turbo",
            messages=[
                {"role": "system", "content": "You are a helpful assistant that extracts the most relevant content from web pages."},
                {"role": "user", "content": f"Given the following web page content and search query, extract only the most relevant parts of the content that answer or relate to the query. Limit your response to about 1000 characters. If there's no relevant content, say 'No relevant content found.'\n\nQuery: {query}\n\nContent: {full_content[:4000]}"}  # Limit input to 4000 characters
            ],
            max_tokens=500  # Adjust as needed
        )
        return response.choices[0].message.content.strip()
    except Exception as e:
        st.error(f"Error in GPT content extraction: {str(e)}")
        return "Error in content extraction"

def fetch_content(url, query):
    try:
        decoded_url = urllib.parse.unquote(url)
        response = requests.get(decoded_url, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, 'html.parser')
        
        # Remove unwanted elements
        for unwanted in soup(['nav', 'header', 'footer', 'sidebar', 'menu', 'aside']):
            unwanted.decompose()
        
        # Try to find the main content
        main_content = soup.find('main') or soup.find('article') or soup.find('div', class_=re.compile('content|main|body'))
        
        if main_content:
            content = main_content.get_text(separator=' ', strip=True)
        else:
            # Fallback to body if no main content is found
            content = soup.body.get_text(separator=' ', strip=True)
        
        # Clean up the content
        content = re.sub(r'\s+', ' ', content)  # Replace multiple spaces with single space
        
        # Use GPT to extract relevant content
        relevant_content = extract_relevant_content(content, query)
        return relevant_content
    except requests.RequestException:
        return ""

def calculate_relevance_score(page_content, query, co, model_type='english'):
    try:
        if not page_content.strip():
            st.warning("Page content is empty. Cannot calculate relevance score.")
            return 0
        model = 'embed-english-v3.0' if model_type == 'english' else 'embed-multilingual-v3.0'
        embeddings = co.embed(texts=[page_content, query], model=model, input_type=['search_document', 'search_query'])
        page_embedding = embeddings.embeddings[0]
        query_embedding = embeddings.embeddings[1]
        if not any(page_embedding) or not any(query_embedding):
            st.warning("One of the embeddings is empty. Returning a score of 0.")
            return 0
        score = cosine_similarity([query_embedding], [page_embedding])[0][0]
        return score
    except Exception as e:
        st.error(f"Error calculating relevance score: {str(e)}")
        return 0

def normalize_url(url):
    return url.rstrip('/').lower()

def analyze_competitors(row, co, custom_url=None, country_code=None):
    query = row['query']
    our_url = normalize_url(row['page'])
    model_type = row.get('model_type', 'english')  # Assuming you store model_type per row

    competitor_data = get_serp_results(query, country_code)

    results = []
    our_url_found = False  # Flag to check if our URL is in the results

    for data in competitor_data:
        competitor_url = normalize_url(data['url'])
        score = calculate_relevance_score(data['content'], query, co, model_type=model_type)
        is_our = competitor_url == our_url
        if is_our:
            our_url_found = True
        results.append({
            'Position': data['position'],
            'URL': competitor_url,
            'Score': score,
            'is_our_url': is_our
        })

    # Retrieve "Our Score" from the main data table
    our_score = st.session_state.relevancy_scores.get(our_url, 0)

    if not our_url_found:
        results.append({
            'Position': len(results) + 1,
            'URL': f"{our_url} (Our URL)",
            'Score': our_score,
            'is_our_url': True
        })

    # Sort results by position in ascending order
    results = sorted(results, key=lambda x: x['Position'])

    # Create DataFrame
    results_df = pd.DataFrame(results)
    results_df['Position'] = results_df['Position'].astype(int)

    # Keep only the columns we want to display
    results_df = results_df[['Position', 'URL', 'Score']]

    return results_df

def show_competitor_analysis(row, co, country_code):
    if st.button("Check Competitors", key=f"comp_{row['page']}"):
        st.write(f"Competitor Analysis for: {row['query']}")
        with st.spinner('Analyzing competitors...'):
            results_df = analyze_competitors(row, co, country_code=country_code)
            
            # Display the Markdown table
            st.markdown(results_df.to_markdown(index=False), unsafe_allow_html=True)
            
            # Extract our result for additional insights
            our_result = results_df[results_df['URL'].str.contains('\*\*')]
            
            if not our_result.empty:
                our_rank = our_result['Position'].values[0]
                total_results = len(results_df)
                our_score = our_result['Score'].values[0]
                
                st.write(f"Our page ranks **{our_rank}** out of **{total_results}** in Google search results.")
                st.write(f"Our relevancy score: **{our_score:.4f}**")
                
                if our_rank == 1:
                    st.success("Your page has the highest position in Google search results!")
                elif our_rank <= 3:
                    st.info("Your page is among the top 3 Google search results.")
                elif our_rank > total_results / 2:
                    st.warning("Your page's position is in the lower half of the Google search results. Consider optimizing your content for better visibility.")
            else:
                st.error("Our page was not found in the competitor analysis results.")

def process_gsc_data(df):
    #logging.info("Processing GSC data")
    df_sorted = df.sort_values(['impressions'], ascending=[False])
    df_unique = df_sorted.drop_duplicates(subset='page', keep='first')
    
    if 'relevancy_score' not in df_unique.columns:
        df_unique['relevancy_score'] = 0
    else:
        df_unique['relevancy_score'] = df_sorted.groupby('page')['relevancy_score'].first().values
    
    result = df_unique[['page', 'query', 'clicks', 'impressions', 'ctr', 'position', 'relevancy_score']]
    #logging.info("GSC data processed successfully")
    return result

# -------------
# Google Authentication Functions
# -------------

def load_config():
    #logging.info("Loading Google client configuration")
    client_config = {
        "web": {
            "client_id": os.environ["CLIENT_ID"],
            "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://poemsforaphrodite-gscpro.hf.space/"],
        }
    }
    #logging.info("Google client configuration loaded")
    return client_config

def init_oauth_flow(client_config):
    #logging.info("Initializing OAuth flow")
    scopes = ["https://www.googleapis.com/auth/webmasters.readonly"]
    flow = Flow.from_client_config(
        client_config,
        scopes=scopes,
        redirect_uri=client_config["web"]["redirect_uris"][0]
    )
    #logging.info("OAuth flow initialized")
    return flow

def google_auth(client_config):
   # logging.info("Starting Google authentication")
    flow = init_oauth_flow(client_config)
    auth_url, _ = flow.authorization_url(prompt="consent")
    #logging.info("Google authentication URL generated")
    return flow, auth_url

def auth_search_console(client_config, credentials):
    #logging.info("Authenticating with Google Search Console")
    token = {
        "token": credentials.token,
        "refresh_token": credentials.refresh_token,
        "token_uri": credentials.token_uri,
        "client_id": credentials.client_id,
        "client_secret": credentials.client_secret,
        "scopes": credentials.scopes,
        "id_token": getattr(credentials, "id_token", None),
    }
    #logging.info("Google Search Console authenticated")
    return searchconsole.authenticate(client_config=client_config, credentials=token)

# -------------
# Data Fetching Functions
# -------------

def list_gsc_properties(credentials):
   # logging.info("Listing GSC properties")
    service = build('webmasters', 'v3', credentials=credentials)
    site_list = service.sites().list().execute()
    properties = [site['siteUrl'] for site in site_list.get('siteEntry', [])] or ["No properties found"]
    #logging.info(f"GSC properties listed: {properties}")
    return properties

def fetch_gsc_data(webproperty, search_type, start_date, end_date, dimensions, device_type=None):
    #logging.info(f"Fetching GSC data for property: {webproperty}, search_type: {search_type}, date_range: {start_date} to {end_date}, dimensions: {dimensions}, device_type: {device_type}")
    query = webproperty.query.range(start_date, end_date).search_type(search_type).dimension(*dimensions)
    if 'device' in dimensions and device_type and device_type != 'All Devices':
        query = query.filter('device', 'equals', device_type.lower())
    try:
        df = query.limit(MAX_ROWS).get().to_dataframe()
        #logging.info("GSC data fetched successfully")
        return process_gsc_data(df)
    except Exception as e:
        #logging.error(f"Error fetching GSC data: {e}")
        show_error(e)
        return pd.DataFrame()

    
def calculate_relevancy_scores(df, model_type):
    for index, row in df.iterrows():
        if pd.isna(row['relevancy_score']) or row['relevancy_score'] == 0:
            score = calculate_single_relevancy(row)
            df.at[index, 'relevancy_score'] = score
    return df

# -------------
# Utility Functions
# -------------

def update_dimensions(selected_search_type):
   # logging.debug(f"Updating dimensions for search type: {selected_search_type}")
    return BASE_DIMENSIONS + ['device'] if selected_search_type in SEARCH_TYPES else BASE_DIMENSIONS

def calc_date_range(selection, custom_start=None, custom_end=None):
   # logging.debug(f"Calculating date range for selection: {selection}")
    range_map = {
        'Last 7 Days': 7,
        'Last 30 Days': 30,
        'Last 3 Months': 90,
        'Last 6 Months': 180,
        'Last 12 Months': 365,
        'Last 16 Months': 480
    }
    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}")
            return custom_start, custom_end
        else:
            #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}")
    return date_range

def show_error(e):
    #logging.error(f"An error occurred: {e}")
    st.error(f"An error occurred: {e}")

def property_change():
    #logging.info(f"Property changed to: {st.session_state['selected_property_selector']}")
    st.session_state.selected_property = st.session_state['selected_property_selector']

# -------------
# File & Download Operations
# -------------

def show_dataframe(report):
    #logging.info("Showing dataframe preview")
    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):
    #logging.info("Generating CSV download link")
    def to_csv(df):
        return df.to_csv(index=False, encoding='utf-8-sig')
    csv = to_csv(report)
    b64_csv = base64.b64encode(csv.encode()).decode()
    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)
    #logging.info("CSV download link generated")

# -------------
# Streamlit UI Components
# -------------

def show_google_sign_in(auth_url):
   # logging.info("Showing Google sign-in button")
    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):
  #  logging.info("Showing property selector")
    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():
  #  logging.info("Showing search type selector")
    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():
  #  logging.info("Showing model type selector")
    return st.selectbox(
        "Select the embedding model:",
        ["english", "multilingual"],
        key='model_type_selector'
    )

def calculate_single_relevancy(row):
    page_content = fetch_content(row['page'], row['query'])
    query = row['query']
    model_type = st.session_state.get('model_type_selector', 'english')  # Retrieve from session state
    score = calculate_relevance_score(page_content, query, co, model_type=model_type)
    st.session_state.relevancy_scores[normalize_url(row['page'])] = score  # Ensure score is stored
    return score

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']
    
    # Retrieve "Our Score" from the main data table
    our_score = st.session_state['relevancy_scores'].get(normalize_url(our_url), 0)
    
    # Calculate relevancy scores
    top_score = calculate_relevance_score(top_content, query, co, model_type=row.get('model_type', 'english'))
    
    # 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_tabular_data(df, co, country_code):
    st.write("Data Table with Relevancy Scores")
    
    # Pagination
    rows_per_page = 10
    total_rows = len(df)
    total_pages = (total_rows - 1) // rows_per_page + 1

    if 'current_page' not in st.session_state:
        st.session_state.current_page = 1

    # Pagination controls
    col1, col2, col3 = st.columns([1,3,1])
    with col1:
        if st.button("< Prev", 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
    
    # Initialize or update selected_rows in session state
    if 'selected_rows' not in st.session_state or len(st.session_state.selected_rows) != len(df):
        st.session_state.selected_rows = [False] * len(df)
    
    # Add a "Calculate Relevancy" button at the top with custom styling
    st.markdown(
        """
        <style>
        .stButton > button {
            background-color: #4CAF50;
            color: white;
        }
        </style>
        """,
        unsafe_allow_html=True
    )
    if st.button("Click here to calculate relevancy for selected pages"):
        selected_indices = [i for i, selected in enumerate(st.session_state.selected_rows) if selected]
        with st.spinner('Calculating relevancy scores...'):
            for index in selected_indices:
                if pd.isna(df.iloc[index]['relevancy_score']) or df.iloc[index]['relevancy_score'] == 0:
                    df.iloc[index, df.columns.get_loc('relevancy_score')] = calculate_single_relevancy(df.iloc[index])
        st.success(f"Calculated relevancy scores for {len(selected_indices)} selected rows.")
        st.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']
    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])
        
        # Checkbox for row selection with a label
        cols[0].checkbox("Select", key=f"select_{i}", value=st.session_state.selected_rows[i],
                         on_change=lambda idx=i: setattr(st.session_state, 'selected_rows', 
                                                       [True if j == idx else x for j, x in enumerate(st.session_state.selected_rows)]))
        
        # Truncate and make the URL clickable
        truncated_url = row.page[:30] + '...' if len(row.page) > 30 else row.page
        cols[1].markdown(f"[{truncated_url}]({row.page})")
        
        cols[2].write(row.query)
        cols[3].write(row.clicks)
        cols[4].write(row.impressions)
        cols[5].write(f"{row.ctr:.2%}")
        cols[6].write(f"{row.position:.1f}")
        cols[7].write(f"{row.relevancy_score:.4f}" if not pd.isna(row.relevancy_score) and row.relevancy_score != 0 else "N/A")
        
        # Competitors column
        if not pd.isna(row.relevancy_score) and row.relevancy_score != 0:
            competitor_state_key = f"comp_state_{i}"
            competitor_button_key = f"comp_button_{i}"
            compare_state_key = f"compare_state_{i}"
            compare_button_key = f"compare_button_{i}"
            
            if competitor_state_key not in st.session_state:
                st.session_state[competitor_state_key] = False
            
            if cols[8].button("Show", key=competitor_button_key):
                st.session_state[competitor_state_key] = True
            
            if st.session_state[competitor_state_key]:
                st.write(f"Competitor Analysis for: {row.query}")
                with st.spinner('Analyzing competitors...'):
                    results_df = analyze_competitors(row, co, country_code=country_code)
                    
                    # Sort the results by Position in ascending order
                    results_df = results_df.sort_values('Position', ascending=True).reset_index(drop=True)
                    
                    # Update the Position for our URL
                    our_url_mask = results_df['URL'].str.contains('Our URL')
                    results_df.loc[our_url_mask, 'Position'] = row.position
                    
                    # Create a custom style function to highlight only our URL's row
                    def highlight_our_url(row):
                        if 'Our URL' in row['URL']:
                            return ['background-color: lightgreen'] * len(row)
                        return [''] * len(row)
                    
                    # Apply the custom style and hide the index
                    styled_df = results_df.style.apply(highlight_our_url, axis=1).hide(axis="index")
                    
                    # Display the styled DataFrame
                    st.markdown(styled_df.to_html(), unsafe_allow_html=True)
                    
                    # Extract our result for additional insights
                    our_result = results_df[results_df['URL'].str.contains('Our URL')]
                    
                    if not our_result.empty:
                        our_rank = our_result['Position'].values[0]
                        total_results = len(results_df)
                        our_score = our_result['Score'].values[0]
                        
                        st.write(f"Our page ranks {our_rank} out of {total_results} in terms of relevancy score.")
                        st.write(f"Our relevancy score: {our_score:.4f}")
                        
                        if our_rank == 1:
                            st.success("Your page has the highest relevancy score!")
                        elif our_rank <= 3:
                            st.info("Your page is among the top 3 most relevant results.")
                        elif our_rank > total_results / 2:
                            st.warning("Your page's relevancy score is in the lower half of the results. Consider optimizing your content.")
                    else:
                        st.error(f"Our page '{row.page}' is not in the results. This indicates an error in fetching or processing the page.")
    
                    if compare_state_key not in st.session_state:
                        st.session_state[compare_state_key] = False
                    
                    if cols[8].button("Compare Your Relevancy Score to the Page In First Place", key=compare_button_key):
                        st.session_state[compare_state_key] = True
                    
                    if st.session_state[compare_state_key]:
                        compare_with_top_result(row._asdict(), co, country_code)
        else:
            cols[8].write("N/A")

    return df  # Return the updated dataframe

def show_date_range_selector():
  #  logging.info("Showing date range selector")
    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():
   # logging.info("Showing 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(search_type):
  #  logging.info("Showing dimensions selector")
    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):
  #  logging.info("Showing paginated dataframe")
    report['position'] = report['position'].astype(int)
    report['impressions'] = pd.to_numeric(report['impressions'], errors='coerce')
    
    def format_ctr(x):
        try:
            return f"{float(x):.2%}"
        except ValueError:
            return x
    
    def format_relevancy_score(x):
        try:
            return f"{float(x):.2f}"
        except ValueError:
            return x
    
    report['ctr'] = report['ctr'].apply(format_ctr)
    report['relevancy_score'] = report['relevancy_score'].apply(format_relevancy_score)
    
    def make_clickable(url):
        return f'<a href="{url}" target="_blank">{url}</a>'
    
    report['clickable_url'] = report['page'].apply(make_clickable)
    
    columns = ['clickable_url', 'query', 'impressions', 'clicks', 'ctr', 'position', 'relevancy_score']
    report = report[columns]

    sort_column = st.selectbox("Sort by:", columns[1:], index=columns[1:].index('impressions'))
    sort_order = st.radio("Sort order:", ("Descending", "Ascending"))
    
    ascending = sort_order == "Ascending"
    
    def safe_float_convert(x):
        try:
            return float(x.rstrip('%')) / 100 if isinstance(x, str) and x.endswith('%') else float(x)
        except ValueError:
            return 0
    
    report['ctr_numeric'] = report['ctr'].apply(safe_float_convert)
    report['relevancy_score_numeric'] = report['relevancy_score'].apply(safe_float_convert)
    
    sort_column_numeric = sort_column + '_numeric' if sort_column in ['ctr', 'relevancy_score'] else sort_column
    report = report.sort_values(by=sort_column_numeric, ascending=ascending)
    
    report = report.drop(columns=['ctr_numeric', 'relevancy_score_numeric'])

    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
    
    st.markdown(report.iloc[start_idx:end_idx].to_html(escape=False, index=False), unsafe_allow_html=True)

# -------------
# Main Streamlit App Function
# -------------

def main():
   # logging.info("Starting main function")
    setup_streamlit()
    print("hello")
    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)

    query_params = st.query_params
    auth_code = query_params.get("code", None)
    
    if auth_code and 'credentials' not in st.session_state:
        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:
        init_session_state()
        account = auth_search_console(client_config, st.session_state.credentials)
        properties = list_gsc_properties(st.session_state.credentials)

        if 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 country selector
            selected_country = st.selectbox(
                "Select Country for SERP Results:",
                COUNTRY_OPTIONS,
                format_func=lambda x: x[1],
                key='country_selector'
            )
            country_code = selected_country[0]
            
            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
            else:
                start_date, end_date = calc_date_range(date_range_selection)

            selected_dimensions = show_dimensions_selector(search_type)

            if 'report_data' not in st.session_state:
                st.session_state.report_data = None

            if st.button("Fetch Data"):
                with st.spinner('Fetching data...'):
                    st.session_state.report_data = fetch_gsc_data(webproperty, search_type, start_date, end_date, selected_dimensions)

            if st.session_state.report_data is not None and not st.session_state.report_data.empty:
                st.write("Data fetched successfully.")
                
                st.session_state.report_data = show_tabular_data(st.session_state.report_data, co, country_code)
                
                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.")

if __name__ == "__main__":
   # logging.info("Running main function")
    main()
    #logger.info("Script completed")