Arcade Highscore Scraper

arcadehighscores.py

import argparse
import json
import re
import requests
from bs4 import BeautifulSoup

parser = argparse.ArgumentParser(description='Extract data from arcadehighscores.com tables and save as JSON.')
parser.add_argument('url', help='URL to extract data from')
parser.add_argument('output_file', help='File name to save JSON output to')
args = parser.parse_args()

response = requests.get(args.url)
html = response.content

soup = BeautifulSoup(html, 'html.parser')
tables = soup.find_all('table')

results = []

for i, table in enumerate(tables):
    inner_tables = table.find_all('table')
    if not inner_tables:
        header = ''
        img = table.find_previous('img', {'src': re.compile(r'^pic\.php\?.*n=.*')})
        if img:
            header = img['src'].split('n=')[-1].split('&')[0]
        table_data = []
        rows = table.find_all('tr')
        for row in rows:
            cols = row.find_all('td')
            row_data = [col.text.strip() for col in cols]
            if len(row_data) == 4:
                table_data.append(row_data)
        if table_data:
            table_json = {
                'header': header,
                'rows': table_data
            }
            results.append(table_json)

output = {
    'tables': results
}

with open(args.output_file, 'w') as f:
    json.dump(output, f, indent=2)

print('JSON output saved to', args.output_file)