import re
with open('main_extracted.html', 'r', encoding='utf-8') as f:
html = f.read()
# Clean up unwanted tags
html = re.sub(r'', '', html, flags=re.DOTALL)
html = re.sub(r'', '', html, flags=re.DOTALL)
html = re.sub(r'', '', html, flags=re.DOTALL) # simple regex might fail on nested divs, but let's try
# better to just strip specific known script tags
html = re.sub(r'', '', html, flags=re.DOTALL)
# replace _next/image paths
html = re.sub(r'/_next/image\?url=(.*?)&.*?(?: |"|\')', r'\1"', html)
# URL decode the paths (simple replacement)
html = html.replace('%2F', '/')
# wrap in Thymeleaf
template = f"""
Đội ngũ bác sĩ | UMC
{html}
"""
with open('src/main/resources/templates/doctor.html', 'w', encoding='utf-8') as f:
f.write(template)
print("Generated src/main/resources/templates/doctor.html")