import re
import json
import requests

domain = 'https://fr.wikipedia.org'
page_url = '/w/index.php?title=MediaWiki:Spam-blacklist&action=raw'

response = requests.get(domain + page_url)
spam_text = response.text

spam_entries = re.findall(r'(.*?)\s+#(.*)', spam_text)
spam_list = []

for entry in spam_entries:
    domain, notes = entry
    if domain:
        if notes:
            domain = domain.replace('\\b', '').replace('\\.', '.').replace('\\-', '-')
            special_chars = '()[]{}*\\'
            special_chars_in_domain = [char for char in special_chars if char in domain]
            if not special_chars_in_domain:
                spam_list.append({
                    "domain": domain.strip(),
                    "notes": notes.strip()
                })

print(json.dumps(spam_list, ensure_ascii=False, indent='\t'))