File size: 21,119 Bytes
66111ac
 
7b55067
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4cfdb9d
7b55067
66111ac
 
 
7b55067
66111ac
3a8e960
7b55067
 
 
66111ac
4cfdb9d
 
 
 
 
7b55067
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82b97bd
a1f9248
7b55067
66111ac
7b55067
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66111ac
7b55067
 
 
 
 
4cfdb9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b55067
 
 
 
 
4cfdb9d
7b55067
4cfdb9d
 
7b55067
 
66111ac
7b55067
66111ac
7b55067
 
 
 
 
66111ac
7b55067
 
4cfdb9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b55067
4cfdb9d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b55067
66111ac
a1f9248
7b55067
3a8e960
 
 
 
 
 
 
66111ac
7b55067
 
 
 
 
 
 
66111ac
7b55067
 
 
 
 
 
 
 
 
66111ac
7b55067
 
 
66111ac
7b55067
 
 
 
 
 
66111ac
7b55067
 
 
66111ac
7b55067
 
66111ac
7b55067
 
 
66111ac
7b55067
 
 
 
 
 
 
 
 
66111ac
7b55067
 
 
 
 
 
 
66111ac
7b55067
 
66111ac
 
 
7b55067
 
66111ac
7b55067
 
 
 
 
66111ac
7b55067
 
66111ac
7b55067
 
 
1f18d28
66111ac
1f18d28
 
 
 
 
 
 
66111ac
1f18d28
66111ac
1f18d28
 
 
 
7b55067
 
 
 
 
66111ac
7b55067
 
 
66111ac
7b55067
 
 
 
 
 
 
 
 
 
 
66111ac
7b55067
 
66111ac
7b55067
66111ac
 
 
7b55067
 
66111ac
7b55067
 
 
66111ac
7b55067
 
 
 
 
 
 
66111ac
7b55067
 
 
 
66111ac
7b55067
 
 
 
 
 
66111ac
7b55067
 
 
 
 
 
66111ac
fd6bb51
 
 
82b97bd
 
 
66111ac
82b97bd
 
 
 
 
 
 
 
 
 
 
66111ac
82b97bd
 
 
 
 
 
7b55067
82b97bd
66111ac
82b97bd
 
 
 
 
7b55067
82b97bd
66111ac
82b97bd
 
 
 
 
 
a1f9248
82b97bd
66111ac
82b97bd
 
 
 
66111ac
82b97bd
 
 
 
 
 
 
a1f9248
3a8e960
66111ac
82b97bd
230aabc
82b97bd
230aabc
 
 
 
66111ac
3a8e960
 
 
 
 
66111ac
230aabc
 
3a8e960
 
 
 
fde6668
3a8e960
 
 
3250b31
a1f9248
66111ac
82b97bd
 
 
3a8e960
 
 
 
 
66111ac
3a8e960
 
 
 
 
 
 
 
82b97bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3a8e960
66111ac
82b97bd
 
 
7b55067
82b97bd
66111ac
3d7a954
 
f52f788
82b97bd
 
 
 
 
ee5283f
82b97bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
66111ac
82b97bd
 
 
 
 
 
 
 
 
9ae1da2
82b97bd
 
 
fbb8761
82b97bd
 
3a8e960
4cfdb9d
3a8e960
 
4cfdb9d
 
 
 
 
 
 
 
82b97bd
 
 
66111ac
82b97bd
4cfdb9d
3d7a954
66111ac
82b97bd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
import logging

# 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
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

# Configure logging
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s - %(levelname)s - %(message)s')

load_dotenv()
logging.info("Environment variables loaded")

# Initialize Cohere client
COHERE_API_KEY = os.environ["COHERE_API_KEY"]
co = cohere.Client(COHERE_API_KEY)
logging.info("Cohere client initialized")
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
client = ApifyClient(APIFY_API_TOKEN)

# 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

# -------------
# 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()
    logging.info("Session state initialized")

# -------------
# Data Processing Functions
# -------------

def get_serp_results(query):
    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,
    }

    try:
        # Run the Actor and wait for it to finish
        run = client.actor("nFJndFXA5zjCTuudP").call(run_input=run_input)
        
        # Fetch results from the run's dataset
        results = list(client.dataset(run["defaultDatasetId"]).iterate_items())
        
        if results and 'organicResults' in results[0]:
            return [item['url'] for item in results[0]['organicResults']]
        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 fetch_content(url):
    try:
        response = requests.get(url)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, 'html.parser')
        return soup.get_text(separator=' ', strip=True)
    except requests.RequestException as e:
        st.warning(f"Error fetching content from {url}: {e}")
        return ""

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 calculate_relevance_score(page_content, query, co):
    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]
    return cosine_similarity([query_embedding], [page_embedding])[0][0]

def show_competitor_analysis(row, co):
    if st.button("Check Competitors", key=f"comp_{row['page']}"):
        with st.spinner('Analyzing competitors...'):
            results_df = analyze_competitors(row, co)
            st.write("Relevancy Score Comparison:")
            st.dataframe(results_df)
            
            our_rank = results_df.index[results_df['url'] == row['page']].tolist()[0] + 1
            st.write(f"Our page ranks {our_rank} out of {len(results_df)} in terms of relevancy score.")


def analyze_competitors(row, co):
    query = row['query']
    our_url = row['page']
    our_score = row['relevancy_score']
    
    competitor_urls = get_serp_results(query)
    
    results = []
    for url in competitor_urls:
        content = fetch_content(url)
        score = calculate_relevance_score(content, query, co)
        results.append({'url': url, 'relevancy_score': score})
    
    results.append({'url': our_url, 'relevancy_score': our_score})
    results_df = pd.DataFrame(results).sort_values('relevancy_score', ascending=False)
    
    return results_df
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):
    logging.info("Calculating relevancy scores")
    with st.spinner('Calculating relevancy scores...'):
        try:
            page_contents = [fetch_content(url) for url in df['page']]
            page_embeddings = generate_embeddings(page_contents, model_type)
            query_embeddings = generate_embeddings(df['query'].tolist(), model_type)
            relevancy_scores = cosine_similarity(query_embeddings, page_embeddings).diagonal()
            df = df.assign(relevancy_score=relevancy_scores)
            logging.info("Relevancy scores calculated successfully")
        except Exception as e:
            logging.error(f"Error calculating relevancy scores: {e}")
            st.warning(f"Error calculating relevancy scores: {e}")
            df = df.assign(relevancy_score=0)
    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 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()
    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()
            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. Click the button below to calculate relevancy scores.")
                
                if st.button("Calculate Relevancy Scores"):
                    st.session_state.report_data = calculate_relevancy_scores(st.session_state.report_data, model_type)
                
                for index, row in st.session_state.report_data.iterrows():
                    st.write(f"Query: {row['query']}")
                    st.write(f"Page: {row['page']}")
                    st.write(f"Relevancy Score: {row['relevancy_score']:.4f}")
                    show_competitor_analysis(row, co)
                    st.divider()
                
                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.")
                logging.warning("No data found for the selected criteria")


if __name__ == "__main__":
    logging.info("Running main function")
    main()