import requests
import json


nft_addresses = [
         # PASTE HASH LIST HERE  
]

apikey = "INSERT YOUR API KEY BETWEEN THESE QUOTATION MARKS"

url = f"https://api.helius.xyz/v0/token-metadata?api-key={apikey}"

def get_metadata(nft_addresses):
    batch_size = 80
    all_data = []

    for i in range(0, len(nft_addresses), batch_size):
        batch_addresses = nft_addresses[i:i + batch_size]
        payload = {
            "mintAccounts": batch_addresses,
            "includeOffChain": True,
            "disableCache": False
        }
        headers = {
            'Content-Type': 'application/json',
        }
        response = requests.post(url, headers=headers, json=payload)
        if response.status_code == 200:
            batch_data = response.json()
            all_data.extend(batch_data)
            print(f"Batch {i // batch_size + 1} successfully retrieved.")
        else:
            print(f"Failed to retrieve metadata for batch {i // batch_size + 1}: {response.status_code}")
            print("Error message:", response.text)

    with open('nft_metadata.json', 'w') as file:
        json.dump(all_data, file, indent=4)
        print("All metadata written to nft_metadata.json")

get_metadata(nft_addresses)

import json
import pandas as pd

def calculate_rarity_score(attributes, trait_counts_df):
    score = sum(1 / trait_counts_df[(trait_counts_df['trait_type'] == attr['trait_type']) &
                                    (trait_counts_df['value'] == attr['value'])]['count'].values[0]
                for attr in attributes if len(trait_counts_df[(trait_counts_df['trait_type'] == attr['trait_type']) &
                                                              (trait_counts_df['value'] == attr['value'])]) > 0)
    return score

file_path = 'nft_metadata.json'
with open(file_path, 'r') as file:
    nft_metadata = json.load(file)

nft_df = pd.json_normalize(nft_metadata)

attributes_list = nft_df.dropna(subset=['offChainMetadata.metadata.attributes'])['offChainMetadata.metadata.attributes'].tolist()
attributes_flat_list = [attr for sublist in attributes_list for attr in sublist]
attributes_df = pd.DataFrame(attributes_flat_list)

trait_counts = attributes_df.groupby(['trait_type', 'value']).size().reset_index(name='count')

nft_df['rarity_score'] = nft_df['offChainMetadata.metadata.attributes'].apply(
    lambda attrs: calculate_rarity_score(attrs, trait_counts) if isinstance(attrs, list) else None
)

for i, record in enumerate(nft_metadata):
    rarity_score = nft_df.loc[i, 'rarity_score']
    record['rarity_score'] = rarity_score if pd.notnull(rarity_score) else 0

updated_file_path = 'nft_metadata_with_rarity.json'
with open(updated_file_path, 'w') as file:
    json.dump(nft_metadata, file, indent=4)

print(f"Awesome! The updated JSON file with rarity scores is saved to {updated_file_path}.")

import json

file_path_nft_metadata = 'nft_metadata.json'
file_path_howrare = 'howrare.json'

with open(file_path_nft_metadata, 'r') as file:
    nft_metadata = json.load(file)

with open(file_path_howrare, 'r') as file:
    howrare_data = json.load(file)['result']['data']['items']

howrare_dict = {item['mint']: item for item in howrare_data}

accounts_without_rarity = []

max_rank = max(item.get('rank', 0) for item in howrare_data)

for item in nft_metadata:
    account = item.get('account')
    if account in howrare_dict:
        normalized_rank = 1 - (howrare_dict[account].get('rank') / max_rank)
        item['rarity_score'] = max(normalized_rank, 0.001) 
    else:
        accounts_without_rarity.append(account)

new_file = 'with-HowRare.json'
with open(new_file, 'w') as file:
    json.dump(nft_metadata, file, indent=4)

if not accounts_without_rarity:
    print("Success, all items received a HowRare value")
else:
    print("The following accounts did not receive a HowRare value:")
    for account in accounts_without_rarity:
        print(account)

import json
import random
import time
import logging
import sys
import os
from datetime import datetime
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException, ElementClickInterceptedException
from selenium.webdriver.common.action_chains import ActionChains
import psutil


LOG_FILE = 'logfile.log'
FILE_ADDRESS = 'address.html'
FILE_TIME = 'time.html'


def setup_logger(log_file_path, logger_name='MyAppLogger'):
    logger = logging.getLogger(logger_name)
    logger.handlers = []
    logger.setLevel(logging.INFO)
    logger.setLevel(logging.DEBUG)

    formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')

    file_handler = logging.FileHandler(log_file_path)
    file_handler.setLevel(logging.INFO)
    file_handler.setFormatter(formatter)

    stream_handler = logging.StreamHandler(sys.stdout)
    stream_handler.setLevel(logging.INFO)
    stream_handler.setFormatter(formatter)

    logger.addHandler(file_handler)
    logger.addHandler(stream_handler)

    return logger


def kill_chrome_and_chromedriver(logger):
    for proc in psutil.process_iter():
        if 'chrome' in proc.name().lower() or 'chromedriver' in proc.name().lower():
            try:
                proc.kill()
            except (psutil.NoSuchProcess, psutil.AccessDenied, psutil.ZombieProcess):
                pass


def driversetup(logger):
    options = webdriver.ChromeOptions()
    options.add_argument("user-data-dir=selenium")
    options.add_argument('--headless')
    options.add_argument('--no-sandbox')
    options.add_argument('--disable-dev-shm-usage')
    options.add_argument("--disable-gpu")
    options.add_argument("--remote-debugging-port=9222")
    options.add_argument("lang=en-US")
    options.add_argument("location=US")
    options.add_argument(f"--window-size={1920},{1080}")
    options.add_argument("disable-infobars")
    options.add_argument("--disable-extensions")
    options.add_argument("--incognito")
    options.add_argument("--disable-blink-features=AutomationControlled")
    options.page_load_strategy = 'normal'

    user_agents = [
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"
    ]
    selected_user_agent = random.choice(user_agents)
    options.add_argument(f"user-agent={selected_user_agent}")

    caps = webdriver.DesiredCapabilities.CHROME
    caps['goog:loggingPrefs'] = {'browser': 'ALL'}
    service = webdriver.chrome.service.Service('/usr/bin/chromedriver')
    driver = webdriver.Chrome(options=options)
    driver.execute_cdp_cmd("Network.clearBrowserCookies", {})
    driver.execute_cdp_cmd("Network.setExtraHTTPHeaders", {"headers": {"Referer": "https://www.google.com/"}})
    driver.execute_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined});")
    return driver

def random_sleep(min_seconds, max_seconds):
    time.sleep(random.uniform(min_seconds, max_seconds))

def simulate_human_interaction(driver, logger):
    action = ActionChains(driver)
    body_element = driver.find_element(By.TAG_NAME, 'body')
    for _ in range(random.randint(1, 3)):
        action.send_keys_to_element(body_element, Keys.PAGE_DOWN).perform()
        random_sleep(0.5, 1.0)
        action.send_keys_to_element(body_element, Keys.PAGE_UP).perform()
        random_sleep(0.5, 1.0)
    action.move_to_element(body_element).perform()
    random_sleep(0.5, 1.0)
    action.move_by_offset(random.randint(0, 100), random.randint(0, 100)).perform()
    random_sleep(0.5, 1.0)


def extract_owner_address_from_file(file_path, logger):
    try:
        with open(FILE_ADDRESS, 'r') as file:
            html_content = file.read()
        soup = BeautifulSoup(html_content, 'html.parser')
        tables = soup.find_all("table")

        for table in tables:
            if table.find("th", {"title": "Owner"}):
                visible_rows = table.select("tbody tr:not(.ant-table-measure-row)")
                if visible_rows:
                    owner_address_element = visible_rows[0].select_one("td:nth-of-type(2) a")
                    if owner_address_element:
                        address = owner_address_element.text.strip()
                        logger.info(f"Owner address found: {address}")
                        return address
                    else:
                        logger.info("Owner address not found in the table.")
                        return "Address not found"
                else:
                    logger.info("No visible rows found in the owner table.")
                    return "No rows in table"
    except Exception as e:
        logger.info(f"Error while extracting owner address: {e}")
        return f"Error: {e}"


def extract_time_from_file(file_path, logger):
    try:
        with open(file_path, 'r') as file:
            html_content = file.read()
        logger.info(f"Successfully read HTML content from '{file_path}'.")

        soup = BeautifulSoup(html_content, 'html.parser')
        time_column_index = 4

        table = soup.select_one("#rc-tabs-0-panel-txs table")
        if not table:
            logger.info("The specific table with ID 'rc-tabs-0-panel-txs' was not found.")
            return "Table not found"

        time_cell = table.select_one("tbody tr:nth-of-type(2) td:nth-of-type(4)")
        if not time_cell:
            logger.info("Time cell not found in the specified row and column.")
            return "Time cell not found"

        hold_time = time_cell.text.strip()
        logger.info(f"Time successfully extracted: {hold_time}")
        return hold_time

    except Exception as e:
        logger.info(f"An unexpected error occurred while extracting time from '{file_path}': {e}")
        return f"Error: {e}"


def getholderaddress(url_holder, driver, logger):

    try:

        driver.get(url_holder)

        wait = WebDriverWait(driver, timeout=30)
        root = driver.find_element(By.ID, 'root')
        body = driver.find_element(By.TAG_NAME, 'body')

        wait.until(lambda d: driver.execute_script('return document.readyState') == 'complete')
        wait.until(lambda d: root.is_displayed())
        wait.until(lambda d: body.is_displayed())

        random_sleep(7, 8)

        simulate_human_interaction(driver, logger)

        root_html = driver.find_element(By.ID, 'root').get_attribute('outerHTML')
        with open(FILE_ADDRESS, 'w') as file:
            file.write(root_html)

        solana_address = extract_owner_address_from_file(FILE_ADDRESS, logger)
        logger.info(f"Holder Address: {solana_address}")

    except TimeoutException:
        logger.error("Timed out waiting for page to load")
        solana_address = "Error: Page did not load properly"
    except Exception as e:
        logger.error(f"An error occurred: {e}")
        solana_address = "Error: Unexpected issue occurred"
    return solana_address


def get_hold_time(url_time, driver, logger):
    try:

        driver.get(url_time)

        wait = WebDriverWait(driver, timeout=30)
        root = driver.find_element(By.ID, 'root')
        body = driver.find_element(By.TAG_NAME, 'body')

        wait.until(lambda d: driver.execute_script('return document.readyState') == 'complete')
        wait.until(lambda d: root.is_displayed())
        wait.until(lambda d: body.is_displayed())

        random_sleep(8, 9)

        simulate_human_interaction(driver, logger)

        javascript = """
        const clickAndCheck = async () => {
          const clockIconElement = document.querySelector(".ant-space.ant-space-vertical.sc-cwSeag.jTZqgO > div > div > div > div > div > div > div > table > thead > tr > th:nth-child(4) > span");
          if (!clockIconElement) {
            console.warn('Unable to find clock icon element');
            return;
          }
          let retries = 5;
          while (clockIconElement.querySelector('svg') && retries > 0) {
            await clockIconElement.click();
            console.log('Clicking clock icon, remaining retries:', retries);
            retries--;
            await new Promise(resolve => setTimeout(resolve, 1000));
          }
          if (retries === 0) {
            console.warn('Max retries reached for clock icon click');
          } else {
            console.log('Clicking successful - clock icon disappeared');
          }
        };
        clickAndCheck();
        """

        try:
            driver.execute_script(javascript)
        except Exception as e:
            logger.error(f"An error occurred: {e}")

        time.sleep(2)

        body_html = driver.find_element(By.TAG_NAME, 'body').get_attribute('outerHTML')

        with open(FILE_TIME, 'w') as file:
            file.write(body_html)

        hold_time = extract_time_from_file(FILE_TIME, logger)
        logger.info(f"Hold time extracted: {hold_time}")

    except TimeoutException as e:
        logger.info(f"TimeoutException encountered: {e}. The website might be unresponsive or the element locators might be incorrect.")
        hold_time = "Error: Timed out"
    except Exception as e:
        logger.info(f"Unexpected error encountered: {e}. Review the stack trace for details and check the website's structure.")
        hold_time = "Error: Unexpected issue occurred"
    finally:
        logger.info("Closing the web driver...")
        driver.close()
        logger.info("Web driver closed for time.")

    return hold_time


def process_item(item, driver, logger):
    account = item.get('account')
    if not account:
        logger.info("Account information not found in the item.")
        return

    time.sleep(1)
    url_holder = f"https://solscan.io/token/{account}#holders"
    logger.info(f"https://solscan.io/token/{account}#holders")
    time.sleep(1)
    url_time = f"https://solscan.io/token/{account}#txs"
    logger.info(f"https://solscan.io/token/{account}#txs")
    time.sleep(1)

    try:
        solana_address = getholderaddress(url_holder, driver, logger)
        hold_time = get_hold_time(url_time, driver, logger)
        update_json_data(item, solana_address, hold_time, logger)
        logger.info(f"Successfully processed account {account}.")
    except Exception as e:
        logger.error(f"Error processing {account}: {e}")


def update_json_data(item, solana_address, hold_time_str, logger):

    hold_time_format = "%m-%d-%Y %H:%M:%S"
    hold_time = datetime.strptime(hold_time_str, hold_time_format)

    current_time = datetime.now()
    hold_time_unix = int(hold_time.timestamp())
    current_time_unix = int(current_time.timestamp())

    item['holder data'] = [
        {"holder": solana_address},
        {"when acquired": hold_time_unix},
        {"time checked": current_time_unix}
    ]


def find_start_index(nft_metadata, processed_indices, logger):
    for index, item in enumerate(nft_metadata):
        if index in processed_indices:
            continue
        if 'holder data' not in item:
            logger.info(f"Starting from index {index}: No 'holder data' field found.")
            return index

    logger.info("All items have 'holder data'. Moving to the next priority.")

    for index, item in enumerate(nft_metadata):
        if index in processed_indices:
            continue
        if 'holder data' in item:
            holder = item['holder data'][0]['holder']
            if holder is None:
                logger.info(f"Starting from index {index}: Found invalid 'holder' value.")
                return index
            if len(holder) not in range(32, 45) and holder != "Magic Eden V2 Authority":
                logger.info(f"Starting from index {index}: Found invalid 'holder' value.")
                return index

    logger.info("All items have valid 'holder' values. Moving to the next priority.")

    for index, item in enumerate(nft_metadata):
        if index in processed_indices:
            continue
        if 'holder data' in item:
            when_acquired = item['holder data'][1]['when acquired']
            if not isinstance(when_acquired, int):
                logger.info(f"Starting from index {index}: 'when acquired' is not a Unix epoch timestamp.")
                return index

    logger.info("All items have valid 'when acquired' timestamps. Moving to the next priority.")

    oldest_index = None
    oldest_time = float('inf')
    for index, item in enumerate(nft_metadata):
        if index in processed_indices:
            continue
        if 'holder data' in item:
            time_checked = item['holder data'][2]['time checked']
            if time_checked < oldest_time:
                oldest_time = time_checked
                oldest_index = index

    if oldest_index is not None:
        logger.info(f"Starting from index {oldest_index}: It has the oldest 'time checked'.")
        return oldest_index
    else:
        logger.info("No items to prioritize based on 'time checked'.")
        return len(nft_metadata)


def get_next_item_index(nft_metadata, logger):
    return find_start_index(nft_metadata, logger)

def main():
    logger = setup_logger(LOG_FILE)

    logger.info("Starting new run. Appending to the existing logfile.")

    kill_chrome_and_chromedriver(logger)

    processed_data_file = 'nft_metadata_with_rarity_and_holder_data.json'
    if os.path.exists(processed_data_file):
        try:
            with open(processed_data_file, 'r') as file:
                nft_metadata = json.load(file)
            logger.info("Continuing from previously saved progress.")
        except Exception as e:
            logger.error(f"Error loading processed data: {e}")
            return
    else:
        try:
            with open('nft_metadata_with_rarity.json', 'r') as file:
                nft_metadata = json.load(file)
                logger.info("Starting from the beginning as no progress file found.")
        except Exception as e:
            logger.error(f"Error loading initial data: {e}")
            return

    processed_count = 0
    processed_indices = set()
    while processed_count < 100:
        next_index = find_start_index(nft_metadata, processed_indices, logger)
        if next_index >= len(nft_metadata):
            logger.info("All items have been processed or no more items to prioritize.")
            break

        item = nft_metadata[next_index]
        logger.info(f"Processing item {processed_count + 1}/100 with account: {item.get('account', 'Unknown')} (Global index: {next_index + 1}/{len(nft_metadata)})")
        driver = driversetup(logger)

        try:
            process_item(item, driver, logger)
            processed_count += 1
            processed_indices.add(next_index)
        except Exception as e:
            logger.error(f"Error processing item with account {item.get('account', 'Unknown')}: {e}")
        finally:
            driver.quit()
            logger.info(f"WebDriver closed for item {next_index + 1}")

    try:
        with open(processed_data_file, 'w') as file:
            json.dump(nft_metadata, file, indent=4)
            logger.info("Progress saved after processing 100 items.")
    except Exception as e:
        logger.error(f"An error occurred while saving the progress: {e}")

if __name__ == '__main__':
    main()

# In the root of the repository

import json
import random
import time
import logging
import sys
import os
from datetime import datetime
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.webdriver.chrome.service import Service as ChromeService
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException, ElementClickInterceptedException
from selenium.webdriver.common.action_chains import ActionChains
import psutil


LOG_FILE = 'collection/logfile.log'
FILE_ADDRESS = 'collection/address.html'
FILE_TIME = 'collection/time.html'


def setup_logger(log_file_path, logger_name='MyAppLogger'):
    logger = logging.getLogger(logger_name)
    logger.handlers = []
    logger.setLevel(logging.INFO)
    logger.setLevel(logging.DEBUG)

    formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')

    file_handler = logging.FileHandler(log_file_path)
    file_handler.setLevel(logging.INFO)
    file_handler.setFormatter(formatter)

    stream_handler = logging.StreamHandler(sys.stdout)
    stream_handler.setLevel(logging.INFO)
    stream_handler.setFormatter(formatter)

    logger.addHandler(file_handler)
    logger.addHandler(stream_handler)

    return logger


def kill_chrome_and_chromedriver(logger):
    for proc in psutil.process_iter():
        if 'chrome' in proc.name().lower() or 'chromedriver' in proc.name().lower():
            try:
                proc.kill()
            except (psutil.NoSuchProcess, psutil.AccessDenied, psutil.ZombieProcess):
                pass


def driversetup(logger):
    options = webdriver.ChromeOptions()
    options.add_argument("user-data-dir=selenium")
    options.add_argument('--headless')
    options.add_argument('--no-sandbox')
    options.add_argument('--disable-dev-shm-usage')
    options.add_argument("--disable-gpu")
    options.add_argument("--remote-debugging-port=9222")
    options.add_argument("lang=en-US")
    options.add_argument("location=US")
    options.add_argument(f"--window-size={1920},{1080}")
    options.add_argument("disable-infobars")
    options.add_argument("--disable-extensions")
    options.add_argument("--incognito")
    options.add_argument("--disable-blink-features=AutomationControlled")
    options.page_load_strategy = 'normal'
    # options.binary_location = '/usr/bin/google-chrome'

    user_agents = [
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36",
        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36"
    ]
    selected_user_agent = random.choice(user_agents)
    options.add_argument(f"user-agent={selected_user_agent}")

    caps = webdriver.DesiredCapabilities.CHROME
    caps['goog:loggingPrefs'] = {'browser': 'ALL'}
    service = ChromeService(ChromeDriverManager().install())
    driver = webdriver.Chrome(service=service, options=options)
    driver.execute_cdp_cmd("Network.clearBrowserCookies", {})
    driver.execute_cdp_cmd("Network.setExtraHTTPHeaders", {"headers": {"Referer": "https://www.google.com/"}})
    driver.execute_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined});")
    return driver

def random_sleep(min_seconds, max_seconds):
    time.sleep(random.uniform(min_seconds, max_seconds))

def simulate_human_interaction(driver, logger):
    action = ActionChains(driver)
    body_element = driver.find_element(By.TAG_NAME, 'body')
    for _ in range(random.randint(1, 3)):
        action.send_keys_to_element(body_element, Keys.PAGE_DOWN).perform()
        random_sleep(0.5, 1.0)
        action.send_keys_to_element(body_element, Keys.PAGE_UP).perform()
        random_sleep(0.5, 1.0)
    action.move_to_element(body_element).perform()
    random_sleep(0.5, 1.0)
    action.move_by_offset(random.randint(0, 100), random.randint(0, 100)).perform()
    random_sleep(0.5, 1.0)


def extract_owner_address_from_file(file_path, logger):
    try:
        with open(FILE_ADDRESS, 'r') as file:
            html_content = file.read()
        soup = BeautifulSoup(html_content, 'html.parser')
        tables = soup.find_all("table")

        for table in tables:
            if table.find("th", {"title": "Owner"}):
                visible_rows = table.select("tbody tr:not(.ant-table-measure-row)")
                if visible_rows:
                    owner_address_element = visible_rows[0].select_one("td:nth-of-type(2) a")
                    if owner_address_element:
                        address = owner_address_element.text.strip()
                        logger.info(f"Owner address found: {address}")
                        return address
                    else:
                        logger.info("Owner address not found in the table.")
                        return "Address not found"
                else:
                    logger.info("No visible rows found in the owner table.")
                    return "No rows in table"
    except Exception as e:
        logger.info(f"Error while extracting owner address: {e}")
        return f"Error: {e}"


def extract_time_from_file(file_path, logger):
    try:
        with open(file_path, 'r') as file:
            html_content = file.read()
        logger.info(f"Successfully read HTML content from '{file_path}'.")

        soup = BeautifulSoup(html_content, 'html.parser')
        time_column_index = 4

        table = soup.select_one("#rc-tabs-0-panel-txs table")
        if not table:
            logger.info("The specific table with ID 'rc-tabs-0-panel-txs' was not found.")
            return "Table not found"

        time_cell = table.select_one("tbody tr:nth-of-type(2) td:nth-of-type(4)")
        if not time_cell:
            logger.info("Time cell not found in the specified row and column.")
            return "Time cell not found"

        hold_time = time_cell.text.strip()
        logger.info(f"Time successfully extracted: {hold_time}")
        return hold_time

    except Exception as e:
        logger.info(f"An unexpected error occurred while extracting time from '{file_path}': {e}")
        return f"Error: {e}"


def getholderaddress(url_holder, driver, logger):

    try:

        driver.get(url_holder)

        wait = WebDriverWait(driver, timeout=30)
        root = driver.find_element(By.ID, 'root')
        body = driver.find_element(By.TAG_NAME, 'body')

        wait.until(lambda d: driver.execute_script('return document.readyState') == 'complete')
        wait.until(lambda d: root.is_displayed())
        wait.until(lambda d: body.is_displayed())

        random_sleep(7, 8)

        simulate_human_interaction(driver, logger)

        root_html = driver.find_element(By.ID, 'root').get_attribute('outerHTML')
        with open(FILE_ADDRESS, 'w') as file:
            file.write(root_html)

        solana_address = extract_owner_address_from_file(FILE_ADDRESS, logger)
        logger.info(f"Holder Address: {solana_address}")

    except TimeoutException:
        logger.error("Timed out waiting for page to load")
        solana_address = "Error: Page did not load properly"
    except Exception as e:
        logger.error(f"An error occurred: {e}")
        solana_address = "Error: Unexpected issue occurred"
    return solana_address


def get_hold_time(url_time, driver, logger):
    try:

        driver.get(url_time)

        wait = WebDriverWait(driver, timeout=30)
        root = driver.find_element(By.ID, 'root')
        body = driver.find_element(By.TAG_NAME, 'body')

        wait.until(lambda d: driver.execute_script('return document.readyState') == 'complete')
        wait.until(lambda d: root.is_displayed())
        wait.until(lambda d: body.is_displayed())

        random_sleep(8, 9)

        simulate_human_interaction(driver, logger)

        javascript = """
        const clickAndCheck = async () => {
          const clockIconElement = document.querySelector(".ant-space.ant-space-vertical.sc-cwSeag.jTZqgO > div > div > div > div > div > div > div > table > thead > tr > th:nth-child(4) > span");
          if (!clockIconElement) {
            console.warn('Unable to find clock icon element');
            return;
          }
          let retries = 5;
          while (clockIconElement.querySelector('svg') && retries > 0) {
            await clockIconElement.click();
            console.log('Clicking clock icon, remaining retries:', retries);
            retries--;
            await new Promise(resolve => setTimeout(resolve, 1000));
          }
          if (retries === 0) {
            console.warn('Max retries reached for clock icon click');
          } else {
            console.log('Clicking successful - clock icon disappeared');
          }
        };
        clickAndCheck();
        """

        try:
            driver.execute_script(javascript)
        except Exception as e:
            logger.error(f"An error occurred: {e}")

        time.sleep(2)

        body_html = driver.find_element(By.TAG_NAME, 'body').get_attribute('outerHTML')

        with open(FILE_TIME, 'w') as file:
            file.write(body_html)

        hold_time = extract_time_from_file(FILE_TIME, logger)
        logger.info(f"Hold time extracted: {hold_time}")

    except TimeoutException as e:
        logger.info(f"TimeoutException encountered: {e}. The website might be unresponsive or the element locators might be incorrect.")
        hold_time = "Error: Timed out"
    except Exception as e:
        logger.info(f"Unexpected error encountered: {e}. Review the stack trace for details and check the website's structure.")
        hold_time = "Error: Unexpected issue occurred"
    finally:
        logger.info("Closing the web driver...")
        driver.close()
        logger.info("Web driver closed for time.")

    return hold_time


def process_item(item, driver, logger):
    account = item.get('account')
    if not account:
        logger.info("Account information not found in the item.")
        return

    time.sleep(1)
    url_holder = f"https://solscan.io/token/{account}#holders"
    logger.info(f"https://solscan.io/token/{account}#holders")
    time.sleep(1)
    url_time = f"https://solscan.io/token/{account}#txs"
    logger.info(f"https://solscan.io/token/{account}#txs")
    time.sleep(1)

    try:
        solana_address = getholderaddress(url_holder, driver, logger)
        hold_time = get_hold_time(url_time, driver, logger)
        update_json_data(item, solana_address, hold_time, logger)
        logger.info(f"Successfully processed account {account}.")
    except Exception as e:
        logger.error(f"Error processing {account}: {e}")


def update_json_data(item, solana_address, hold_time_str, logger):

    hold_time_format = "%m-%d-%Y %H:%M:%S"
    hold_time = datetime.strptime(hold_time_str, hold_time_format)

    current_time = datetime.now()
    hold_time_unix = int(hold_time.timestamp())
    current_time_unix = int(current_time.timestamp())

    item['holder data'] = [
        {"holder": solana_address},
        {"when acquired": hold_time_unix},
        {"time checked": current_time_unix}
    ]


def find_start_index(nft_metadata, processed_indices, logger):
    for index, item in enumerate(nft_metadata):
        if index in processed_indices:
            continue
        if 'holder data' not in item:
            logger.info(f"Starting from index {index}: No 'holder data' field found.")
            return index

    logger.info("All items have 'holder data'. Moving to the next priority.")

    for index, item in enumerate(nft_metadata):
        if index in processed_indices:
            continue
        if 'holder data' in item:
            holder = item['holder data'][0]['holder']
            if holder is None:
                logger.info(f"Starting from index {index}: Found invalid 'holder' value.")
                return index
            if len(holder) not in range(32, 45) and holder != "Magic Eden V2 Authority":
                logger.info(f"Starting from index {index}: Found invalid 'holder' value.")
                return index

    logger.info("All items have valid 'holder' values. Moving to the next priority.")

    for index, item in enumerate(nft_metadata):
        if index in processed_indices:
            continue
        if 'holder data' in item:
            when_acquired = item['holder data'][1]['when acquired']
            if not isinstance(when_acquired, int):
                logger.info(f"Starting from index {index}: 'when acquired' is not a Unix epoch timestamp.")
                return index

    logger.info("All items have valid 'when acquired' timestamps. Moving to the next priority.")

    oldest_index = None
    oldest_time = float('inf')
    for index, item in enumerate(nft_metadata):
        if index in processed_indices:
            continue
        if 'holder data' in item:
            time_checked = item['holder data'][2]['time checked']
            if time_checked < oldest_time:
                oldest_time = time_checked
                oldest_index = index

    if oldest_index is not None:
        logger.info(f"Starting from index {oldest_index}: It has the oldest 'time checked'.")
        return oldest_index
    else:
        logger.info("No items to prioritize based on 'time checked'.")
        return len(nft_metadata)


def get_next_item_index(nft_metadata, logger):
    return find_start_index(nft_metadata, logger)

def main():
    logger = setup_logger(LOG_FILE)

    logger.info("Starting new run. Appending to the existing logfile.")

    kill_chrome_and_chromedriver(logger)

    processed_data_file = 'collection/with-rarity-and-holder-data.json'
    if os.path.exists(processed_data_file):
        try:
            with open(processed_data_file, 'r') as file:
                nft_metadata = json.load(file)
            logger.info("Continuing from previously saved progress.")
        except Exception as e:
            logger.error(f"Error loading processed data: {e}")
            return
    else:
        try:
            with open('collection/with-rarity.json', 'r') as file:
                nft_metadata = json.load(file)
                logger.info("Starting from the beginning as no progress file found.")
        except Exception as e:
            logger.error(f"Error loading initial data: {e}")
            return

    processed_count = 0
    processed_indices = set()
    while processed_count < 100:
        next_index = find_start_index(nft_metadata, processed_indices, logger)
        if next_index >= len(nft_metadata):
            logger.info("All items have been processed or no more items to prioritize.")
            break

        item = nft_metadata[next_index]
        logger.info(f"Processing item {processed_count + 1}/100 with account: {item.get('account', 'Unknown')} (Global index: {next_index + 1}/{len(nft_metadata)})")
        driver = driversetup(logger)

        try:
            process_item(item, driver, logger)
            processed_count += 1
            processed_indices.add(next_index)
        except Exception as e:
            logger.error(f"Error processing item with account {item.get('account', 'Unknown')}: {e}")
        finally:
            driver.quit()
            logger.info(f"WebDriver closed for item {next_index + 1}")

    try:
        with open(processed_data_file, 'w') as file:
            json.dump(nft_metadata, file, indent=4)
            logger.info("Progress saved after processing 100 items.")
    except Exception as e:
        logger.error(f"An error occurred while saving the progress: {e}")

if __name__ == '__main__':
    main()

import json
import re

def get_name(nft_name):
    try:
        return nft_name.rsplit(' ', 1)[0]
    except IndexError:
        return nft_name.split(' ', 1)[0]

def get_nft_number(nft_name):
    match = re.search(r'#(\d+)', nft_name)
    if match:
        return int(match.group(1))
    return 0

def rewrite_data(data):
  rewritten_data = []
  for item in data:
    nft_name = item["onChainMetadata"]["metadata"]["data"]["name"]
    nft_address = item["account"]
    rarity_score = item["rarity_score"]
    holder_data = {}
    if "holder data" in item:
        holder_data = {
            "holderAddress": item["holder data"][0]["holder"],
            "whenAcquired": item["holder data"][1]["when acquired"],
            "timeChecked": item["holder data"][2]["time checked"]
        }
    rewritten_data.append({
      "nftName": nft_name,
      "nftAddress": nft_address,
      "rarityScore": rarity_score,
      "holderData": holder_data,
    })
  return rewritten_data

with open("collection/with-rarity-and-holder-data.json") as f:
  data = json.load(f)

naming = set([get_name(x["onChainMetadata"]["metadata"]["data"]["name"]) for x in data])
naming_order = sorted(list(naming))

rewritten_data = rewrite_data(data)
rewritten_data = sorted(rewritten_data, key=lambda x: (naming_order.index(get_name(x["nftName"])), get_nft_number(x["nftName"])))

with open("collection/by-NFT.json", "w") as f:
  json.dump(rewritten_data, f, indent=4)

import json
import re
from datetime import datetime

with open('collection/by-NFT.json') as f:
    data = json.load(f)

holders = {}
for nft in data:
    holder_data = nft['holderData']
    if holder_data is None:
      continue
    holder_address = holder_data.get('holderAddress')  # Get the holderAddress
    if holder_address in ["Magic Eden V2 Authority", "4zdNGgAtFsW1cQgHqkiWyRsxaAgxrSRRynnuunxzjxue", "1BWutmTvYPwDtmw9abTkS4Ssr8no61spGAvW1X6NDix"]:
        continue
    if holder_data:
        holder_address = holder_data['holderAddress']
        if isinstance(holder_address, str): 
            if not re.match(r'^[123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz]{32,44}$', holder_address):
                continue
        if holder_address not in holders:
            holders[holder_address] = {
                "holderAddress": holder_address,
                "quantityNfts": 1,
                "holdingNfts": [{
                    "nftAddress": nft['nftAddress'],
                    "rarityScore": nft['rarityScore'],
                    "daysHeld": (datetime.utcnow() - datetime.utcfromtimestamp(holder_data['whenAcquired'])).days
                }]
            }
        else:
            holders[holder_address]['quantityNfts'] += 1
            holders[holder_address]['holdingNfts'].append({
                "nftAddress": nft['nftAddress'],
                "rarityScore": nft['rarityScore'],
                "daysHeld": (datetime.utcnow() - datetime.utcfromtimestamp(holder_data['whenAcquired'])).days
            })

result = sorted(holders.values(), key=lambda x: x["quantityNfts"], reverse=True)

with open('collection/by-holder.json', 'w') as f:
    json.dump(result, f, indent=4)

import json
from datetime import date
import traceback
from math import exp
import numpy as np

try:
    with open('collection/by-holder.json') as f:
        data = json.load(f)

    quantityNfts_weight = 1
    rarityScore_weight = 0.1
    daysHeld_weight = 1

    daysHeld_decay_factor = 0.1

    max_nfts = max([holder["quantityNfts"] for holder in data])
    # print(f"The total number of NFTs owned by the individual with the largest NFT collection: {max_nfts}")

    avg_rarity_per_holder = [(holder["holderAddress"], sum(subnft["rarityScore"] for subnft in holder["holdingNfts"]) / holder["quantityNfts"]) for holder in data]
    rarity_sniper = max(avg_rarity_per_holder, key=lambda x: x[1])
    highest_rarity_average = rarity_sniper[1]
    # print(f"The average rarity score of the owner who possesses the highest average rarity score: {highest_rarity_average}")

    days_held_per_holder = [(holder["holderAddress"], sum(subnft["daysHeld"] for subnft in holder["holdingNfts"])) for holder in data]
    diamond_hands = max(days_held_per_holder, key=lambda x: x[1])
    hold_door = diamond_hands[1]
    # print(f"Th total duration held by the owner possessing the maximum cumulative duration of all NFTs they own : {hold_door}")

    today = date.today()

    def score_address(addr):
        holder_data = [holder for holder in data if holder["holderAddress"] == addr]
        if not holder_data:
            return 0

        holder_data = holder_data[0]

        nfts = holder_data["quantityNfts"]
        nfts_normalized = nfts / max_nfts
        nfts_weighted = nfts_normalized * quantityNfts_weight

        rarity_scores = [subnft["rarityScore"] for subnft in holder_data["holdingNfts"]]
        rarity_scores_log = [np.log(score + 1) for score in rarity_scores]
        rarity_score_average = sum(rarity_scores_log) / len(rarity_scores_log)
        rarity_score_normalized = rarity_score_average / np.log(highest_rarity_average + 1)
        rarity_score_weighted = rarity_score_normalized * rarityScore_weight

        days_held = sum([subnft["daysHeld"] for subnft in holder_data["holdingNfts"]])
        days_held_normalized = days_held / hold_door
        decay_factor = exp(-days_held_normalized * daysHeld_decay_factor)
        days_held_with_decay = days_held_normalized * decay_factor
        days_held_weighted = days_held_with_decay * daysHeld_weight
        # print(f"Address: {addr}, NFTs Weighted: {nfts_weighted}, Rarity Score Weighted: {rarity_score_weighted}, Days Held Weighted: {days_held_weighted}")
        scoreHold = (nfts_weighted + rarity_score_weighted + days_held_weighted)
        return scoreHold, # nfts_weighted, rarity_score_weighted, days_held_weighted

    # Review the calculated averages to consider adjustments to the weights assigned to the number
    # of NFTs (`quantityNfts_weight`), rarity score (`rarityScore_weight`), and holding duration
    # (`daysHeld_weight`). This evaluation will help in fine-tuning the scoring system for more
    # accurate assessments.

    """
    sum_nfts_weighted = 0
    sum_nfts_weighted = 0
    sum_rarity_score_weighted = 0
    sum_days_held_weighted = 0
    for holder in data:
        _, nfts_weighted, rarity_score_weighted, days_held_weighted = score_address(holder["holderAddress"])
        sum_nfts_weighted += nfts_weighted
        sum_rarity_score_weighted += rarity_score_weighted
        sum_days_held_weighted += days_held_weighted
    average_nfts_weighted = sum_nfts_weighted / len(data)
    average_rarity_score_weighted = sum_rarity_score_weighted / len(data)
    average_days_held_weighted = sum_days_held_weighted / len(data)
    print(f"Average Score of Holder's NFTs Owned: {average_nfts_weighted}")
    print(f"Average Score of Holder's Rarity: {average_rarity_score_weighted}")
    print(f"Average Score of Holder's Days Held: {average_days_held_weighted}")
    """

    scored = []
    for holder in data:
        score = score_address(holder["holderAddress"])
        holder["holderScore"] = score
        scored.append(holder)

    ranked = sorted(scored, key=lambda x: x["holderScore"], reverse=True)

    with open('collection/ranked-holders.json', 'w') as f:
      json.dump(ranked, f, indent=4)

except Exception as e:
    print(f"Error: {e}")
    traceback.print_exc()

import json
import matplotlib.pyplot as plt
from matplotlib import ticker
import matplotlib.font_manager as fm
import numpy as np
import math
from datetime import datetime

def custom_formatter(x, pos):
    if x >= 100:
        exponent = int(math.log10(x))
        mantissa = x / 10**exponent
        return f"{mantissa:.0f}e{exponent}"
    else:
        return "%d" % x

with open('collection/ranked-holders.json') as f:
    data = json.load(f)[:20]

data = [d for d in data if d is not None]

holders = []
for d in data:
    address = d.get('holderAddress')
    if address:
        holders.append(address[:4] + "..." + address[-4:])
    else:
        holders.append("Unknown")

metrics = [
    (d['quantityNfts'],
     sum(nft['rarityScore'] for nft in d['holdingNfts']),
     sum(nft['daysHeld'] for nft in d['holdingNfts']))
    for d in data
]
font1 = fm.FontProperties(size=12)
plt.style.use('dark_background')
fig, ax = plt.subplots(figsize=(7, 8.4))
x = np.arange(len(holders))
width = 0.2
ticks = x + 0.9 * width
locator = ticker.FixedLocator(ticks)

ax.yaxis.set_major_locator(locator)
ax.set_yticklabels(holders, color='#ffffff', fontsize=10)
ax.set_ylabel('Holders', color='#E0E0E0', fontsize=16, fontweight=5)
ax.set_title('Collection Name\nTop Holders', fontsize=20, fontweight=5, color='#E0E0E0')
ax.tick_params(axis='y', color='#E0E0E0')
ax.tick_params(axis='x', which='both', bottom=False, top=False, labelbottom=False)
ax.invert_yaxis()
ax.text(0.5, 0.5, 'Arctic Frenz', fontsize=70, color='gray', alpha=0.2,
          ha='center', va='center', rotation=30, transform=ax.transAxes)

ax1 = ax.twiny()
ax1.set_xscale('linear')
ax1.barh(x, [m[0] for m in metrics], width, color='#00e0ff', label='Quantity of NFTs Owned', edgecolor='#E0E0E0', alpha=0.8)
ax1.set_ylabel('Quantity of NFTs Owned', color='#00e0ff')
ax1.set_autoscalex_on(True)
ax1.xaxis.set_major_formatter(ticker.FormatStrFormatter('%d'))
ax1.tick_params(axis='y', labelcolor='#00e0ff')
ax1.tick_params(axis='x', which='both', labelcolor='#00e0ff', tickdir='in', direction='out', length=4, width=1, colors='#00e0ff', grid_color='#00e0ff', grid_alpha=0.5)
ax1.grid(axis='x', linestyle='--', alpha=0.5, color='#00e0ff')
ax1.yaxis.label.set_color('#00e0ff')

ax2 = ax.twiny()
ax2.set_xscale('linear')
ax2.barh(x + 1*width, [m[1] for m in metrics], width, color='#ff00a8', label='Cumulative Rarity Score\nAcross NFTs Owned', edgecolor='#E0E0E0', alpha=0.8)
ax2.set_ylabel('Cumulative Rarity Score\nAcross NFTs Owned', color='#ff00a8')
ax2.set_autoscalex_on(True)
ax2.xaxis.set_major_formatter(ticker.FormatStrFormatter('%d'))
ax2.tick_params(axis='y', labelcolor='#ff00a8')
ax2.tick_params(axis='x', labelcolor='#ff00a8', tickdir='out', direction='out', length=15, width=1, colors='#ff00a8', grid_color='#ff00a8', grid_alpha=0.5)
ax2.grid(axis='x', linestyle='--', alpha=0.5, color='#ff00a8')
ax2.yaxis.label.set_color('#ff00a8')

ax3 = ax.twiny()
ax3.set_xscale('log')
ax3.barh(x + 2*width, [m[2] for m in metrics], width, color='#fdff00', label='Cumulative Hold Duration\nin Days Across NFTs Owned', edgecolor='#E0E0E0', alpha=0.8)
ax3.set_ylabel('Cumulative Hold Duration\nin Days Across NFTs Owned', color='#fdff00')
ax3.set_autoscalex_on(True)
ax3.xaxis.set_major_formatter(custom_formatter)
ax3.tick_params(axis='y', labelcolor='#fdff00')
ax3.tick_params(axis='x', labelcolor='#fdff00', tickdir='out', direction='out', length=35, width=1, colors='#fdff00', grid_color='#fdff00', grid_alpha=0.5)
ax3.grid(axis='x', linestyle='--', alpha=0.5, color='#fdff00')
ax3.yaxis.label.set_color('#fdff00')

legend_handles = []
legend_labels = []
for ax in [ax1, ax2, ax3]:
    handles, labels = ax.get_legend_handles_labels()
    legend_handles.extend(handles)
    legend_labels.extend(labels)
fig.legend(legend_handles, legend_labels, bbox_to_anchor=(0.98, 0.02), loc='lower right', title='Holders\' Stats', fontsize=10)

generation_time = datetime.utcnow().strftime("%Y-%m-%d %H:%M:%S UTC")
footnote_text = f"Chart generated on:\n{generation_time}"
fig.text(-0.16, 1.17, footnote_text, fontsize=9, color='#E0E0E0', ha="left", va="top", transform=ax.transAxes, alpha=0.7)

fig.tight_layout()
plt.savefig('collection/top-holders.png', format='png', bbox_inches='tight')