import requests
import time
from bs4 import BeautifulSoup
from ddgs import DDGS

SKIP_DOMAINS = [
    "tripadvisor", "tiktok", "facebook", "instagram",
    "twitter", "yelp", "google", "wikipedia", "youtube",
    "infoguidenigeria", "nairaland"
]

def search_leads(query, max_results=10):
    try:
        time.sleep(2)
        with DDGS() as ddgs:
            results = list(ddgs.text(query, max_results=max_results))
        return results
    except Exception as e:
        print(f"Search error: {e}")
        return []

def scrape_website(url):
    try:
        response = requests.get(url, timeout=5)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, "html.parser")
        paragraphs = soup.find_all("p")
        content = " ".join([p.get_text() for p in paragraphs[:15]])
        return content[:800]
    except Exception:
        return ""

def gather_leads(target_audience):
    results = search_leads(target_audience)
    leads = []
    for r in results:
        url = r.get("href", "")
        title = r.get("title", "")
        body = r.get("body", "")

        # skip directories and social media
        if url and any(domain in url.lower() for domain in SKIP_DOMAINS):
            continue

        if url:
            extra_info = scrape_website(url)
            leads.append({
                "name": title,
                "website": url,
                "summary": body,
                "details": extra_info
            })
    return leads