panchicore · July 27, 2025 00:56
diff --git a/_script.py b/_script.py
 from bs4 import BeautifulSoup
 import quopri
 import json


 def extract_setups_bundle():
    """
    Extract the div with class 'setups-bundle mb-5' from the HTML file
    """
    # Read the HTML file
    with open('Data Packs - Popometer - Short List 2.html', 'r', encoding='utf-8') as file:
        content = file.read()

    # with open('Data Packs - Popometer - Full List 2.html', 'r', encoding='utf-8') as file:
    #     content = file.read()

    # The file is MHTML format, so we need to extract the HTML part
    # Find the start of the HTML content (after the headers)
    html_start = content.find('<!DOCTYPE html>')
    if html_start == -1:
        print("Could not find HTML content in the file")
        return None
    
    # Extract just the HTML part
    html_content = content[html_start:]
    
    # Handle quoted-printable encoding manually for MHTML format
    # Replace common encoded sequences
    decoded_html = html_content.replace('=3D', '=')
    decoded_html = decoded_html.replace('=\n', '')  # Remove soft line breaks
    decoded_html = decoded_html.replace('=20', ' ')  # Space
    decoded_html = decoded_html.replace('=22', '"')  # Quote
    decoded_html = decoded_html.replace('=27', "'")  # Apostrophe
    
    # Parse with BeautifulSoup
    soup = BeautifulSoup(decoded_html, 'html.parser')
    
    # Debug: Check if we can find any divs with "setups" in the class name
    all_divs_with_setups = soup.find_all('div', class_=lambda x: x and 'setups' in x)
    print(f"Found {len(all_divs_with_setups)} divs with 'setups' in class name")
    
    # Debug: Look for the exact text we saw in the file
    setups_div_encoded = soup.find('div', class_='setups-bundle mb-5')
    if not setups_div_encoded:
        # Try searching in the raw content before decoding
        if 'setups-bundle mb-5' in html_content:
            print("Found 'setups-bundle mb-5' in raw content, but not after parsing")
            # Try a different approach - search for the pattern in the original content
            import re
            pattern = r'class=3D"setups-bundle mb-5"'
            if re.search(pattern, html_content):
                print("Found encoded class name in raw content")
                # Replace the encoded version in the content before parsing
                html_content_fixed = html_content.replace('=3D', '=').replace('=\n', '')
                soup = BeautifulSoup(html_content_fixed, 'html.parser')
                setups_div = soup.find('div', class_='setups-bundle mb-5')
            else:
                print("Could not find encoded class name either")
                setups_div = None
        else:
            print("Could not find 'setups-bundle mb-5' in raw content")
            setups_div = None
    else:
        setups_div = setups_div_encoded
    
    if setups_div:
        print("✓ Successfully found the setups-bundle div!")
        print(f"✓ XPath equivalent location (/html/body/main/div[2]/div/div) found")
        
        setup_entries = setups_div.find_all('div', class_='setup-bundle')
        print(f"✓ Number of setup entries: {len(setup_entries)}")
        
        # Verify the structure matches the expected content
        headers = setups_div.find('div', class_='row d-none d-lg-flex')
        if headers:
            header_texts = [span.get_text().strip() for span in headers.find_all('span', class_='text-muted text-uppercase')]
            print(f"✓ Table headers found: {header_texts}")
        
        # Show details of the first setup entry
        if setup_entries:
            first_setup = setup_entries[0]
            car_info = first_setup.find('div', class_='setup-bundle__car')
            if car_info:
                car_name = car_info.find('div', class_='car')
                track_name = car_info.find('div', class_='track')
                if car_name:
                    print(f"✓ First setup car: {car_name.get_text().strip()}")
                if track_name:
                    print(f"✓ First setup track: {track_name.get_text().strip()}")
        
        print(f"\n✓ Extraction successful! The div contains the expected racing setup data.")
        print(f"✓ This corresponds to the XPath: /html/body/main/div[2]/div/div")
        
        return setups_div
    else:
        print("Could not find div with class 'setups-bundle mb-5'")
        # Debug: Show some sample div classes that were found
        sample_divs = soup.find_all('div', class_=True)[:10]
        print("Sample div classes found:")
        for div in sample_divs:
            print(f"  {div.get('class')}")
        return None

 def extract_setups_data():
    """
    Extract setup data including locked status and links from the HTML file
    Returns an array of dictionaries with setup information
    """
    # First get the setups bundle div
    setups_div = extract_setups_bundle()
    if not setups_div:
        return []
    
    # Find all setup entries
    setup_entries = setups_div.find_all('div', class_='setup-bundle')
    setups_data = []
    
    for setup in setup_entries:
        setup_info = {}
        
        # Check if setup is locked or unlocked
        lock_icon = setup.find('i', class_=lambda x: x and ('fa-lock' in x or 'fa-unlock' in x))
        if lock_icon:
            # Check if it contains fa-lock (locked) or fa-unlock (unlocked)
            icon_classes = ' '.join(lock_icon.get('class', []))
            setup_info['locked'] = 'fa-lock' in icon_classes
        else:
            # Default to unlocked if no lock icon found
            setup_info['locked'] = False
        
        # Extract the setup link
        setup_link = setup.find('a', class_='setup-bundle__car-link')
        if setup_link:
            setup_info['link'] = setup_link.get('href', '')
        else:
            setup_info['link'] = ''
        
        # Extract additional info for verification
        car_info = setup.find('div', class_='setup-bundle__car')
        if car_info:
            car_name = car_info.find('div', class_='car')
            track_name = car_info.find('div', class_='track')
            setup_info['car'] = car_name.get_text().strip() if car_name else ''
            setup_info['track'] = track_name.get_text().strip() if track_name else ''
        
        setups_data.append(setup_info)
    
    return setups_data

 if __name__ == '__main__':
    # Extract the basic div structure
    extracted_div = extract_setups_bundle()
    
    # Extract detailed setup data
    setups_data = extract_setups_data()
    
    print(f"\n{'='*50}")
    print("SETUP DATA EXTRACTION RESULTS:")
    print(f"{'='*50}")
    
    # Show the array of dictionaries as requested
    print(f"\nSetups Array (as requested):")
    for i, setup in enumerate(setups_data, 1):
        print(f"Setup {i}: {{'locked': {setup['locked']}, 'link': '{setup['link']}'}}")
    
    print(f"\nDetailed Information:")
    for i, setup in enumerate(setups_data, 1):
        print(f"\nSetup {i}:")
        print(f"  Locked: {setup['locked']}")
        print(f"  Link: {setup['link']}")
        print(f"  Car: {setup['car']}")
        print(f"  Track: {setup['track']}")
    
    print(f"\n{'='*50}")
    print(f"Total setups found: {len(setups_data)}")
    print(f"Locked setups: {sum(1 for s in setups_data if s['locked'])}")
    print(f"Unlocked setups: {sum(1 for s in setups_data if not s['locked'])}")
    print(f"{'='*50}")
    
    # Return the array for programmatic use
    print(f"\nArray of dictionaries with locked boolean and links:")
    # Save setups_data as JSON file
    with open('setups_data.json', 'w', encoding='utf-8') as f:
        json.dump(setups_data, f, indent=4, ensure_ascii=False)
    print(setups_data)
diff --git a/popometer-25-july-2025.md b/popometer-25-july-2025.md
	from bs4 import BeautifulSoup
	import quopri
	import json


	def extract_setups_bundle():
	"""
	Extract the div with class 'setups-bundle mb-5' from the HTML file
	"""
	# Read the HTML file
	with open('Data Packs - Popometer - Short List 2.html', 'r', encoding='utf-8') as file:
	content = file.read()

	# with open('Data Packs - Popometer - Full List 2.html', 'r', encoding='utf-8') as file:
	# content = file.read()

	# The file is MHTML format, so we need to extract the HTML part
	# Find the start of the HTML content (after the headers)
	html_start = content.find('<!DOCTYPE html>')
	if html_start == -1:
	print("Could not find HTML content in the file")
	return None

	# Extract just the HTML part
	html_content = content[html_start:]

	# Handle quoted-printable encoding manually for MHTML format
	# Replace common encoded sequences
	decoded_html = html_content.replace('=3D', '=')
	decoded_html = decoded_html.replace('=\n', '') # Remove soft line breaks
	decoded_html = decoded_html.replace('=20', ' ') # Space
	decoded_html = decoded_html.replace('=22', '"') # Quote
	decoded_html = decoded_html.replace('=27', "'") # Apostrophe

	# Parse with BeautifulSoup
	soup = BeautifulSoup(decoded_html, 'html.parser')

	# Debug: Check if we can find any divs with "setups" in the class name
	all_divs_with_setups = soup.find_all('div', class_=lambda x: x and 'setups' in x)
	print(f"Found {len(all_divs_with_setups)} divs with 'setups' in class name")

	# Debug: Look for the exact text we saw in the file
	setups_div_encoded = soup.find('div', class_='setups-bundle mb-5')
	if not setups_div_encoded:
	# Try searching in the raw content before decoding
	if 'setups-bundle mb-5' in html_content:
	print("Found 'setups-bundle mb-5' in raw content, but not after parsing")
	# Try a different approach - search for the pattern in the original content
	import re
	pattern = r'class=3D"setups-bundle mb-5"'
	if re.search(pattern, html_content):
	print("Found encoded class name in raw content")
	# Replace the encoded version in the content before parsing
	html_content_fixed = html_content.replace('=3D', '=').replace('=\n', '')
	soup = BeautifulSoup(html_content_fixed, 'html.parser')
	setups_div = soup.find('div', class_='setups-bundle mb-5')
	else:
	print("Could not find encoded class name either")
	setups_div = None
	else:
	print("Could not find 'setups-bundle mb-5' in raw content")
	setups_div = None
	else:
	setups_div = setups_div_encoded

	if setups_div:
	print("✓ Successfully found the setups-bundle div!")
	print(f"✓ XPath equivalent location (/html/body/main/div[2]/div/div) found")

	setup_entries = setups_div.find_all('div', class_='setup-bundle')
	print(f"✓ Number of setup entries: {len(setup_entries)}")

	# Verify the structure matches the expected content
	headers = setups_div.find('div', class_='row d-none d-lg-flex')
	if headers:
	header_texts = [span.get_text().strip() for span in headers.find_all('span', class_='text-muted text-uppercase')]
	print(f"✓ Table headers found: {header_texts}")

	# Show details of the first setup entry
	if setup_entries:
	first_setup = setup_entries[0]
	car_info = first_setup.find('div', class_='setup-bundle__car')
	if car_info:
	car_name = car_info.find('div', class_='car')
	track_name = car_info.find('div', class_='track')
	if car_name:
	print(f"✓ First setup car: {car_name.get_text().strip()}")
	if track_name:
	print(f"✓ First setup track: {track_name.get_text().strip()}")

	print(f"\n✓ Extraction successful! The div contains the expected racing setup data.")
	print(f"✓ This corresponds to the XPath: /html/body/main/div[2]/div/div")

	return setups_div
	else:
	print("Could not find div with class 'setups-bundle mb-5'")
	# Debug: Show some sample div classes that were found
	sample_divs = soup.find_all('div', class_=True)[:10]
	print("Sample div classes found:")
	for div in sample_divs:
	print(f" {div.get('class')}")
	return None

	def extract_setups_data():
	"""
	Extract setup data including locked status and links from the HTML file
	Returns an array of dictionaries with setup information
	"""
	# First get the setups bundle div
	setups_div = extract_setups_bundle()
	if not setups_div:
	return []

	# Find all setup entries
	setup_entries = setups_div.find_all('div', class_='setup-bundle')
	setups_data = []

	for setup in setup_entries:
	setup_info = {}

	# Check if setup is locked or unlocked
	lock_icon = setup.find('i', class_=lambda x: x and ('fa-lock' in x or 'fa-unlock' in x))
	if lock_icon:
	# Check if it contains fa-lock (locked) or fa-unlock (unlocked)
	icon_classes = ' '.join(lock_icon.get('class', []))
	setup_info['locked'] = 'fa-lock' in icon_classes
	else:
	# Default to unlocked if no lock icon found
	setup_info['locked'] = False

	# Extract the setup link
	setup_link = setup.find('a', class_='setup-bundle__car-link')
	if setup_link:
	setup_info['link'] = setup_link.get('href', '')
	else:
	setup_info['link'] = ''

	# Extract additional info for verification
	car_info = setup.find('div', class_='setup-bundle__car')
	if car_info:
	car_name = car_info.find('div', class_='car')
	track_name = car_info.find('div', class_='track')
	setup_info['car'] = car_name.get_text().strip() if car_name else ''
	setup_info['track'] = track_name.get_text().strip() if track_name else ''

	setups_data.append(setup_info)

	return setups_data

	if __name__ == '__main__':
	# Extract the basic div structure
	extracted_div = extract_setups_bundle()

	# Extract detailed setup data
	setups_data = extract_setups_data()

	print(f"\n{'='*50}")
	print("SETUP DATA EXTRACTION RESULTS:")
	print(f"{'='*50}")

	# Show the array of dictionaries as requested
	print(f"\nSetups Array (as requested):")
	for i, setup in enumerate(setups_data, 1):
	print(f"Setup {i}: {{'locked': {setup['locked']}, 'link': '{setup['link']}'}}")

	print(f"\nDetailed Information:")
	for i, setup in enumerate(setups_data, 1):
	print(f"\nSetup {i}:")
	print(f" Locked: {setup['locked']}")
	print(f" Link: {setup['link']}")
	print(f" Car: {setup['car']}")
	print(f" Track: {setup['track']}")

	print(f"\n{'='*50}")
	print(f"Total setups found: {len(setups_data)}")
	print(f"Locked setups: {sum(1 for s in setups_data if s['locked'])}")
	print(f"Unlocked setups: {sum(1 for s in setups_data if not s['locked'])}")
	print(f"{'='*50}")

	# Return the array for programmatic use
	print(f"\nArray of dictionaries with locked boolean and links:")
	# Save setups_data as JSON file
	with open('setups_data.json', 'w', encoding='utf-8') as f:
	json.dump(setups_data, f, indent=4, ensure_ascii=False)
	print(setups_data)