import re
import requests

EXTRACT_RULES = {
    "mailto_links": {
        "selector": "a[href^='mailto:']",
        "type": "obj",
        "multiple": True,
        "children": {
            "email": {"selector": "", "type": "attr", "attribute": "href"}
        }
    },
    "page_content": {"selector": "body", "type": "text"}
}

response = requests.post("https://api.ujeebu.com/scrape",
    headers={"ApiKey": "YOUR_API_KEY", "Content-Type": "application/json"},
    json={
        "url": "https://example.com/contact",
        "extract_rules": EXTRACT_RULES
    })

data = response.json()["result"]

# Regex for email addresses
email_pattern = r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'

# From mailto links
mailto_emails = [
    link["email"].replace("mailto:", "").split("?")[0]
    for link in data.get("mailto_links", [])
]

# From page content using regex
content_emails = re.findall(email_pattern, data.get("page_content", ""))

# Combine and deduplicate
all_emails = list(set(mailto_emails + content_emails))
print(f"Found {len(all_emails)} unique emails: {all_emails}")