#!/usr/bin/env python3
"""
Email Extractor for HTML Files
Extract emails from HTML using BeautifulSoup4
"""
from bs4 import BeautifulSoup
import re
import requests

EMAIL_PATTERN = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'

def extract_from_html(html_content):
    """Extract emails from HTML content"""
    soup = BeautifulSoup(html_content, 'html.parser')

    # Remove script and style tags
    for tag in soup(['script', 'style']):
        tag.decompose()

    text = soup.get_text()
    emails = set(re.findall(EMAIL_PATTERN, text))

    # Also check href attributes
    for link in soup.find_all('a', href=True):
        href = link['href']
        if href.startswith('mailto:'):
            email = href[7:].split('?')[0]
            emails.add(email)

    return list(emails)

def extract_from_url(url):
    """Extract emails from a web page"""
    response = requests.get(url, timeout=10)
    return extract_from_html(response.text)

def extract_from_file(filepath):
    """Extract emails from HTML file"""
    with open(filepath, 'r', encoding='utf-8') as f:
        return extract_from_html(f.read())

if __name__ == '__main__':
    import sys
    if len(sys.argv) > 1:
        emails = extract_from_file(sys.argv[1])
        for email in sorted(emails):
            print(email)