import requests
import random, re
import json
import os
from bs4 import BeautifulSoup
from concurrent.futures import ThreadPoolExecutor, as_completed
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry

import warnings
warnings.filterwarnings("ignore")

USER_AGENTS = [
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:137.0) Gecko/20100101 Firefox/137.0",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 14.7; rv:137.0) Gecko/20100101 Firefox/137.0",
    "Mozilla/5.0 (X11; Linux i686; rv:137.0) Gecko/20100101 Firefox/137.0",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 14_7_5) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/18.3 Safari/605.1.15",
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 Edg/135.0.3179.54",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36 Edg/135.0.3179.54"
]

DEFAULT_SEARCH_ENGINES = [
    "http://juhanurmihxlp77nkq76byazcldy2hlmovfu2epvl5ankdibsot4csyd.onion/search/?q={query}", # Ahmia
    "http://3bbad7fauom4d6sgppalyqddsqbf5u5p56b5k5uk2zxsy3d6ey2jobad.onion/search?q={query}", # OnionLand
    "http://iy3544gmoeclh5de6gez2256v6pjh4omhpqdh2wpeeppjtvqmjhkfwad.onion/torgle/?query={query}", # Torgle
    "http://amnesia7u5odx5xbwtpnqk3edybgud5bmiagu75bnqx2crntw5kry7ad.onion/search?query={query}", # Amnesia
    "http://kaizerwfvp5gxu6cppibp7jhcqptavq3iqef66wbxenh6a2fklibdvid.onion/search?q={query}", # Kaizer
    "http://anima4ffe27xmakwnseih3ic2y7y3l6e7fucwk4oerdn4odf7k74tbid.onion/search?q={query}", # Anima
    "http://tornadoxn3viscgz647shlysdy7ea5zqzwda7hierekeuokh5eh5b3qd.onion/search?q={query}", # Tornado
    "http://tornetupfu7gcgidt33ftnungxzyfq2pygui5qdoyss34xbgx2qruzid.onion/search?q={query}", # TorNet
    "http://torlbmqwtudkorme6prgfpmsnile7ug2zm4u3ejpcncxuhpu4k2j4kyd.onion/index.php?a=search&q={query}", # Torland
    "http://findtorroveq5wdnipkaojfpqulxnkhblymc7aramjzajcvpptd4rjqd.onion/search?q={query}", # Find Tor
    "http://2fd6cemt4gmccflhm6imvdfvli3nf7zn6rfrwpsy7uhxrgbypvwf5fad.onion/search?query={query}", # Excavator    
    "http://oniwayzz74cv2puhsgx4dpjwieww4wdphsydqvf5q7eyz4myjvyw26ad.onion/search.php?s={query}", # Onionway
    "http://tor66sewebgixwhcqfnp5inzp5x5uohhdy3kvtnyfxc2e5mxiuh34iid.onion/search?q={query}", # Tor66
    "http://3fzh7yuupdfyjhwt3ugzqqof6ulbcl27ecev33knxe3u7goi3vfn2qqd.onion/oss/index.php?search={query}", # OSS
    "http://torgolnpeouim56dykfob6jh5r2ps2j73enc42s2um4ufob3ny4fcdyd.onion/?q={query}", # Torgol
    "http://searchgf7gdtauh7bhnbyed4ivxqmuoat3nm6zfrg3ymkq6mtnpye3ad.onion/search?q={query}" # The Deep Searches
]

def get_tor_session():
    session = requests.Session()
    retry = Retry(
        total=3,
        read=3,
        connect=3,
        backoff_factor=0.5,
        status_forcelist=[500, 502, 503, 504]
    )
    adapter = HTTPAdapter(max_retries=retry)
    session.mount("http://", adapter)
    session.mount("https://", adapter)
    session.proxies = {
        "http": "socks5h://127.0.0.1:9050",
        "https": "socks5h://127.0.0.1:9050"
    }
    return session

def fetch_search_results(endpoint, query):
    url = endpoint.format(query=query)
    headers = {"User-Agent": random.choice(USER_AGENTS)}
    session = get_tor_session()
    
    try:
        response = session.get(url, headers=headers, timeout=40)
        if response.status_code == 200:
            soup = BeautifulSoup(response.text, "html.parser")
            links = []
            # Generic parsing for standard search engine layouts
            for a in soup.find_all('a'):
                try:
                    href = a['href']
                    title = a.get_text(strip=True)
                    # Extract onion links
                    link = re.findall(r'https?:\/\/[a-z0-9\.]+\.onion.*', href)
                    if len(link) != 0:
                        # Basic filtering to avoid self-referential links
                        if "search" not in link[0] and len(title) > 3:
                            links.append({"title": title, "link": link[0]})
                except:
                    continue
            return links
        else:
            return []
    except:
        return []

def get_search_results(refined_query, max_workers=5):
    results = []
    with ThreadPoolExecutor(max_workers=max_workers) as executor:
        futures = [executor.submit(fetch_search_results, endpoint, refined_query)
                   for endpoint in DEFAULT_SEARCH_ENGINES]
        for future in as_completed(futures):
            result_urls = future.result()
            results.extend(result_urls)

    # Deduplicate results
    seen_links = set()
    unique_results = []
    for res in results:
        link = res.get("link")
        # Remove trailing slashes for better deduplication
        clean_link = link.rstrip('/')
        if clean_link not in seen_links:
            seen_links.add(clean_link)
            unique_results.append(res)
            
    return unique_results