Clash of Clans API에서 플레이어 데이터 다운로드

pip install requests pandas tqdm ratelimit

import time
import math
import json
import requests
import logging
import pandas as pd
from concurrent.futures import ThreadPoolExecutor, as_completed
from ratelimit import limits, sleep_and_retry
from tqdm import tqdm

file_path = 'others/clans.json'

# Function to open the file and extract tags, specifying the encoding
def extract_tags_from_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as file:  # Specifying the encoding here
        data = json.load(file)
        return [item.get("tag") for item in data.get("items", [])]

# Extract tags from the specified file
try:
    extracted_tags = extract_tags_from_file(file_path)
    print(extracted_tags)

except UnicodeDecodeError as e:
    print(f"Error reading the file: {e}")

# the extracted clan tags have '#' in beigning we have to replace it with URL encode '%23'
def update_tags(extracted_tags):
    # Replace '#' with '%23' for each tag in the list
    updated_tags = [tag.replace('#', '%23') for tag in extracted_tags]
    return updated_tags

# Get the updated list of tags
updated_extracted_tags = update_tags(extracted_tags)

# Print or return the updated list
print(updated_extracted_tags)

# Replace your API_KEY
api_key = 'your_api_key_here'  

# Base URL for the Clash of Clans API clans endpoint
base_url = 'https://api.clashofclans.com/v1/clans/'

# Header to include in the request
headers = {
   'Authorization': f'Bearer {api_key}',
   'Accept': 'application/json'
}

# Function to get clan member list for each clan tag
def get_clan_members(clan_tags):
    clan_members = {}  # Dictionary to store clan members list by clan tag

    for tag in clan_tags:
        # Constructing the full URL for the clan members endpoint
        full_url = f'{base_url}{tag}/members'
        response = requests.get(full_url, headers=headers)

        if response.status_code == 200:
            # Successful response
            data = response.json()
            # Assuming the API returns a list of clan members directly
            clan_members[tag] = data.get('items', [])

        else:
            # Handle errors or unsuccessful responses
            print(f'Failed to fetch clan members for {tag}: HTTP {response.status_code}')

    return clan_members

# Get clan members for each tag
clan_members_lists = get_clan_members(updated_extracted_tags)

# Example: print the result for the first clan
first_tag = updated_extracted_tags[0]
print(f'Clan members for {first_tag}:', clan_members_lists[first_tag])

# Assuming clan_members_lists is your dictionary from the modified get_clan_members function
def convert_to_dataframe(clan_members_lists):
# Create a list of tuples (clan_tag, player_tag) for all clans
    data = [(clan_tag, player_tag) for clan_tag, player_tags in clan_members_lists.items() for player_tag in player_tags]

# Convert the list of tuples into a DataFrame
    df = pd.DataFrame(data, columns=['Clan Tag', 'Player Tag'])

    return df

# Convert the dictionary to a DataFrame
df_clan_members = convert_to_dataframe(clan_members_lists)
print(df_clan_members)

def convert_to_dataframe(clan_members_lists):
    # Initialize an empty list to store the data
    data = []

    # Loop through each clan tag and its corresponding list of members
    for clan_tag, members in clan_members_lists.items():
        for member in members:
            # For each member, extract the clan tag and the player tag, ensuring the player tag is a string
            player_tag = member['tag']  # Assuming 'tag' key exists and its value is the player's tag
            data.append((clan_tag, player_tag))

    # Convert the list of tuples into a DataFrame
    df = pd.DataFrame(data, columns=['Clan Tag', 'Player Tag'])

    # Optional: Convert clan and player tags to ensure they are URL-friendly
    # This step is optional and depends on whether you need to use these tags in URLs
    df['Clan Tag'] = df['Clan Tag'].apply(lambda x: x.replace('%23', '#'))
    # df['Player Tag'] = df['Player Tag'].apply(lambda x: x.replace('#', '%23'))

    return df

# Example usage with your clan_members_lists dictionary
# Make sure to replace 'clan_members_lists' with your actual dictionary variable
df_clan_members = convert_to_dataframe(clan_members_lists)
print(df_clan_members)

df_clan_members.to_csv('datasets/clan_and_player_tags.csv', index=False)

# Set up logging to file
logging.basicConfig(filename='others/error_log.log', level=logging.ERROR, 
                    format='%(asctime)s - %(levelname)s - %(message)s')

# Load the CSV file into a DataFrame
df = pd.read_csv('datasets/clan_and_player_tags.csv')  # Update this path to your actual CSV file location

# API details
api_key = 'your_api_key_here'
headers = {'Authorization': 'Bearer ' + api_key}

# Rate limit: 10 requests per second (adjust as needed)
@sleep_and_retry
@limits(calls=10, period=1)
def call_api(url):
    response = requests.get(url, headers=headers)
    response.raise_for_status()
    return response.json()

def fetch_player_details(tag):
    url = f'https://api.clashofclans.com/v1/players/{tag.replace("#", "%23")}'
    try:
        data = call_api(url)
        return {
            'name': data.get('name', ''),
            'role': data.get('role', ''),
            'league': data.get('league', {}).get('name', ''),
            'builderBaseLeague': data.get('builderBaseLeague', {}).get('name', ''),
            'townHallLevel': data.get('townHallLevel', 0),
            'builderHallLevel': data.get('builderHallLevel', 0),
            'expLevel': data.get('expLevel', 0),
            'trophies': data.get('trophies', 0),
            'bestTrophies': data.get('bestTrophies', 0),
            'builderBaseTrophies': data.get('builderBaseTrophies', 0),
            'bestBuilderBaseTrophies': data.get('bestBuilderBaseTrophies', 0),
            'attackWins': data.get('attackWins', 0),
            'defenseWins': data.get('defenseWins', 0),
            'warStars': data.get('warStars', 0),
            'clanCapitalContributions': data.get('clanCapitalContributions', 0),
            'donations': data.get('donations', 0),
            'donationsReceived': data.get('donationsReceived', 0),
        }
    except requests.exceptions.RequestException as e:
        logging.error(f'Error fetching data for {tag}: {e}')

def process_batch(batch):
    player_details = []
    with ThreadPoolExecutor(max_workers=20) as executor:
        future_to_tag = {executor.submit(fetch_player_details, tag): tag for tag in batch}
        for future in as_completed(future_to_tag):
            tag = future_to_tag[future]
            try:
                details = future.result()
                player_details.append(details)
            except Exception as exc:
                logging.error(f'{tag} generated an exception: {exc}')

    return player_details

def save_checkpoint(data, filename):
    with open(filename, 'w') as f:
        json.dump(data, f)

def load_checkpoint(filename):
    try:
        with open(filename, 'r') as f:
            return json.load(f)
    except FileNotFoundError:
        return []

def main():
    batch_size = 1000
    checkpoint_file = 'others/player_details_checkpoint.json'

    # Load checkpoint if it exists
    player_details = load_checkpoint(checkpoint_file)
    start_index = len(player_details)

    num_batches = math.ceil((len(df) - start_index) / batch_size)

    for i in tqdm(range(start_index, len(df), batch_size), total=num_batches, desc="Processing batches"):
        batch = df['Player Tag'].iloc[i:i+batch_size].tolist()
        batch_details = process_batch(batch)
        player_details.extend(batch_details)

        # Save checkpoint after each batch
        save_checkpoint(player_details, checkpoint_file)

     # Filter out None values from player_details
    player_details = [detail for detail in player_details if detail is not None]

    # Create a new DataFrame with the player details
    details_df = pd.DataFrame(player_details)

    # Merge the original DataFrame with the new details DataFrame
    final_df = pd.concat([df, details_df], axis=1)

    # Save the final DataFrame to a new CSV file
    final_df.to_csv('datasets/player_details.csv', index=False)
    print("Data fetching and processing complete. Results saved to 'Clan_and_Player_Details.csv'")

if __name__ == "__main__":
    start_time = time.time()
    main()
    end_time = time.time()
    print(f"Total execution time: {end_time - start_time:.2f} seconds")