FloorVisualizer/cmd/scrape_logos/main.py

"""
Scrape brand logos from the web.
Tries Clearbit Logo API first, falls back to scraping the homepage.
Outputs brand_logos.json for Go to read.
"""
import json
import os
import sys
import urllib.request
import urllib.error
import ssl
import re

# ── Brand → domain mapping ──────────────────────────────────
BRANDS = {
    "Armstrong":       "armstrongflooring.com",
    "Bruce":           "bruce.com",
    "COREtec":         "coretecfloors.com",
    "Daltile":         "daltile.com",
    "Karndean":        "karndean.com",
    "LifeProof":       "lifeproof.com",
    "Mohawk Flooring": "mohawkflooring.com",
    "MSI Surfaces":    "msisurfaces.com",
    "Pergo":           "pergo.com",
    "Shaw Floors":     "shawfloors.com",
}

OUTPUT_DIR = "static/brand_logos"
OUTPUT_JSON = "brand_logos.json"

ssl_ctx = ssl.create_default_context()
ssl_ctx.check_hostname = False
ssl_ctx.verify_mode = ssl.CERT_NONE


def fetch_url(url, timeout=10):
    """Fetch URL and return response data."""
    try:
        req = urllib.request.Request(url, headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"})
        resp = urllib.request.urlopen(req, timeout=timeout, context=ssl_ctx)
        return resp.read(), resp.getcode()
    except Exception as e:
        print(f"  [!] Failed: {e}")
        return None, 0


def try_clearbit(domain):
    """Try Clearbit Logo API: https://logo.clearbit.com/{domain}"""
    url = f"https://logo.clearbit.com/{domain}"
    print(f"  Trying Clearbit: {url}")
    data, code = fetch_url(url)
    if data and code == 200:
        return data, "png"
    return None, None


def try_homepage_favicon(domain):
    """Try to find logo from homepage HTML (og:image or favicon)."""
    url = f"https://{domain}"
    print(f"  Fetching homepage: {url}")
    html_bytes, code = fetch_url(url)
    if not html_bytes:
        return None, None
    html = html_bytes.decode("utf-8", errors="ignore")

    # Try og:image first
    m = re.search(r'<meta[^>]+property=["\']og:image["\'][^>]+content=["\']([^"\']+)', html)
    if m:
        img_url = m.group(1)
        if img_url.startswith("//"):
            img_url = "https:" + img_url
        elif img_url.startswith("/"):
            img_url = url + img_url
        print(f"  Found og:image: {img_url}")
        data, _ = fetch_url(img_url)
        if data:
            ext = img_url.split(".")[-1].split("?")[0] or "png"
            return data, ext

    # Try favicon
    m = re.search(r'<link[^>]+rel=["\'](?:icon|shortcut icon)["\'][^>]+href=["\']([^"\']+)', html)
    if m:
        favicon_url = m.group(1)
        if favicon_url.startswith("//"):
            favicon_url = "https:" + favicon_url
        elif favicon_url.startswith("/"):
            favicon_url = url + favicon_url
        print(f"  Found favicon: {favicon_url}")
        data, _ = fetch_url(favicon_url)
        if data:
            return data, "ico"

    # Try /favicon.ico
    favicon_url = f"https://{domain}/favicon.ico"
    print(f"  Trying: {favicon_url}")
    data, _ = fetch_url(favicon_url)
    if data:
        return data, "ico"

    return None, None


def try_wikipedia(name):
    """Try to get logo from Wikipedia."""
    search_name = name.replace(" ", "_")
    # Try the Wikipedia REST API
    api_url = f"https://en.wikipedia.org/api/rest_v1/page/summary/{search_name}"
    print(f"  Trying Wikipedia: {api_url}")
    data, code = fetch_url(api_url)
    if data and code == 200:
        try:
            info = json.loads(data)
            thumb = info.get("thumbnail", {}).get("source")
            if thumb:
                print(f"  Found Wikipedia thumbnail: {thumb}")
                img_data, _ = fetch_url(thumb)
                if img_data:
                    return img_data, "png"
        except Exception:
            pass

    # Try infobox image via action=query
    query_url = f"https://en.wikipedia.org/w/api.php?action=query&titles={search_name}&prop=pageimages&format=json&pithumbsize=200"
    print(f"  Trying Wikipedia query: {query_url}")
    data, code = fetch_url(query_url)
    if data and code == 200:
        try:
            result = json.loads(data)
            pages = result.get("query", {}).get("pages", {})
            for page in pages.values():
                thumb = page.get("thumbnail", {}).get("source")
                if thumb:
                    print(f"  Found: {thumb}")
                    img_data, _ = fetch_url(thumb)
                    if img_data:
                        return img_data, "png"
        except Exception:
            pass

    return None, None


def main():
    os.makedirs(OUTPUT_DIR, exist_ok=True)
    results = {}

    for brand, domain in BRANDS.items():
        print(f"\n{'='*60}")
        print(f"Brand: {brand} ({domain})")

        img_data = None
        ext = "png"

        # Strategy 1: Clearbit
        img_data, ext = try_clearbit(domain)

        # Strategy 2: Homepage og:image / favicon
        if not img_data:
            img_data, ext = try_homepage_favicon(domain)

        # Strategy 3: Wikipedia
        if not img_data:
            img_data, ext = try_wikipedia(brand)

        if img_data and len(img_data) > 100:
            filename = f"{brand.lower().replace(' ', '_').replace('.', '')}.{ext}"
            filepath = os.path.join(OUTPUT_DIR, filename)
            with open(filepath, "wb") as f:
                f.write(img_data)
            local_url = f"/static/brand_logos/{filename}"
            print(f"  [OK] Saved: {filepath} ({len(img_data)} bytes)")
            results[brand] = local_url
        else:
            print(f"  [FAIL] No logo found for {brand}")
            results[brand] = ""

    # Write JSON mapping
    json_path = os.path.join(os.path.dirname(__file__) or ".", "..", "..", OUTPUT_JSON)
    # Go binary runs from project root, output to root
    root_json_path = OUTPUT_JSON
    with open(root_json_path, "w", encoding="utf-8") as f:
        json.dump(results, f, indent=2, ensure_ascii=False)
    print(f"\n{'='*60}")
    print(f"Logo mapping saved to {root_json_path}")
    print(f"Logos saved to {OUTPUT_DIR}/")
    print(json.dumps(results, indent=2, ensure_ascii=False))


if __name__ == "__main__":
    main()