import requests
from bs4 import BeautifulSoup

URL = "https://futureoffestivals.com/ausstellerinnen-2026/"
PREFIX = "https://futureoffestivals.com/exhibitors/"
OUTPUT_FILE = "aussteller_urls.txt"

def extract_urls():
    print(f"Lade Seite: {URL}")

    headers = {"User-Agent": "Mozilla/5.0"}
    r = requests.get(URL, headers=headers, timeout=10)
    r.raise_for_status()

    soup = BeautifulSoup(r.text, "html.parser")

    urls = set()

    for a in soup.find_all("a", href=True):
        href = a["href"].strip()
        if href.startswith(PREFIX):
            urls.add(href)

    urls = sorted(urls)

    print(f"{len(urls)} URLs gefunden. Speichere in {OUTPUT_FILE} ...")

    with open(OUTPUT_FILE, "w", encoding="utf-8") as f:
        for u in urls:
            f.write(u + "\n")

    print("Fertig!")

if __name__ == "__main__":
    extract_urls()