import requests
from fastapi import FastAPI, HTTPException, BackgroundTasks
from fastapi.responses import HTMLResponse, FileResponse
from faker import Faker
import fake_useragent
import json
import logging
import os
import asyncio
from concurrent.futures import ThreadPoolExecutor, as_completed
from threading import Lock, Thread
from typing import List

# Initialize the FastAPI app
app = FastAPI()

# Configure logging
logging.basicConfig(level=logging.INFO)

# Create instances of Faker and fake_useragent
fake = Faker()
user_agent_generator = fake_useragent.UserAgent()

# Global dictionaries to store valid and invalid proxies
global_proxies = {
    "valid": set(),
    "invalid": set()
}

# Lock to synchronize access to global proxies
proxies_lock = Lock()

def get_random_user_agent():
    """Generate a random fake user agent."""
    return user_agent_generator.random

def get_random_ip():
    """Generate a random fake IP address."""
    return fake.ipv4()

def fetch_response(url, headers=None):
    """Fetches the URL and returns the raw response text."""
    try:
        response = requests.get(url, headers=headers)
        response.raise_for_status()  # Raise HTTPError for bad responses
        return response.text
    except requests.RequestException as e:
        logging.error(f"Request failed for URL {url}: {e}")
        return None

async def verify_proxy(proxy: str):
    """Verify if a proxy is working by making a test request."""
    if proxy in global_proxies["invalid"]:
        # Skip already verified invalid proxies
        return proxy, False

    test_url = "http://httpbin.org/ip"  # Simple URL to test proxy
    proxy_dict = {
        "http": f"http://{proxy}",
        "https": f"http://{proxy}"
    }
    try:
        response = requests.get(test_url, proxies=proxy_dict, timeout=5)
        response.raise_for_status()
        with proxies_lock:
            global_proxies["valid"].add(proxy)
        return proxy, True
    except requests.RequestException:
        with proxies_lock:
            global_proxies["invalid"].add(proxy)
        return proxy, False

async def background_verification(proxies_to_verify: List[str]):
    """Background task to verify proxies."""
    with ThreadPoolExecutor() as executor:
        futures = [executor.submit(asyncio.run, verify_proxy(proxy)) for proxy in proxies_to_verify]
        for future in as_completed(futures):
            proxy, is_valid = future.result()
            if is_valid:
                logging.info(f"Proxy {proxy} is valid.")
            else:
                logging.info(f"Proxy {proxy} is invalid and will be excluded.")

@app.get("/", response_class=HTMLResponse)
async def rotate_ip(background_tasks: BackgroundTasks):
    proxies = set()  # Use a set to avoid duplicate proxies

    # URLs for fetching proxies
    proxy_urls = [
        os.getenv("PROXY_API_URL", "http://pubproxy.com/api/proxy?format=txt&level=anonymous,elite&type=http,socks4,socks5&last_check=60&speed=25&limit=1&post=true&user_agent=true&cookies=true&referer=true"),
        'https://raw.githubusercontent.com/clarketm/proxy-list/master/proxy-list-raw.txt',
        'https://raw.githubusercontent.com/TheSpeedX/PROXY-List/master/http.txt',
        'https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/socks4.txt',
        'https://raw.githubusercontent.com/TheSpeedX/SOCKS-List/master/socks5.txt',
        'https://raw.githubusercontent.com/ShiftyTR/Proxy-List/master/proxy.txt',
        'https://raw.githubusercontent.com/sunny9577/proxy-scraper/master/proxies.txt',
        "https://storage.googleapis.com/river-treat-249913.appspot.com/p.txt",
        "https://storage.googleapis.com/river-treat-249913.appspot.com/proxy.txt",
        "https://storage.googleapis.com/river-treat-249913.appspot.com/ultimate.txt",
        # Additional proxy sources
        'https://raw.githubusercontent.com/proxylist/proxylist/master/proxy.txt',
        'https://raw.githubusercontent.com/scrapfly/proxy-list/main/proxies.txt',
        'https://raw.githubusercontent.com/roosterkid/openproxylist/main/HTTP.txt',
        'https://raw.githubusercontent.com/roosterkid/openproxylist/main/SOCKS4.txt',
        'https://raw.githubusercontent.com/roosterkid/openproxylist/main/SOCKS5.txt',
        'https://raw.githubusercontent.com/roosterkid/openproxylist/main/HTTPS.txt',
        'https://raw.githubusercontent.com/roosterkid/openproxylist/main/ALL.txt',
        'https://raw.githubusercontent.com/proxylist/proxylist/master/https.txt',
        'https://raw.githubusercontent.com/proxylist/proxylist/master/socks4.txt',
        'https://raw.githubusercontent.com/proxylist/proxylist/master/socks5.txt',
        'https://raw.githubusercontent.com/proxylist/proxylist/master/http.txt',
        'https://raw.githubusercontent.com/proxylist/proxylist/master/all.txt',
        'https://raw.githubusercontent.com/jetlore/proxies/master/proxy-list.txt',
        'https://raw.githubusercontent.com/hookzof/proxy-list/main/proxy.txt',
        'https://raw.githubusercontent.com/zzlol123/proxy-list/main/proxies.txt',
        'https://raw.githubusercontent.com/sqSfg/Proxy-List/master/http.txt',
        'https://raw.githubusercontent.com/sqSfg/Proxy-List/master/https.txt',
        'https://raw.githubusercontent.com/sqSfg/Proxy-List/master/socks4.txt',
        'https://raw.githubusercontent.com/sqSfg/Proxy-List/master/socks5.txt',
        'https://raw.githubusercontent.com/sqSfg/Proxy-List/master/all.txt',
        'https://www.proxy-list.download/api/v1/get?type=https',
        'https://www.proxy-list.download/api/v1/get?type=http',
        'https://www.proxy-list.download/api/v1/get?type=socks4',
        'https://www.proxy-list.download/api/v1/get?type=socks5',
        'https://www.proxy-list.download/api/v1/get?type=all',
        'https://www.sslproxies.org/',
        'https://www.us-proxy.org/',
        'https://free-proxy-list.net/',
        'https://www.proxy-list.download/',
        'https://www.proxyscan.io/api/proxies?type=http',
        # New additional proxy sources
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.download/api/v1/get?type=all',
        'https://www.proxynova.com/proxy-server-list/',
        'https://www.proxy-list.download/api/v1/get?type=http',
        'https://www.proxy-list.download/api/v1/get?type=https',
        'https://www.proxy-list.download/api/v1/get?type=socks4',
        'https://www.proxy-list.download/api/v1/get?type=socks5',
        'https://www.proxy-list.download/api/v1/get?type=all',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt',
        'https://www.proxy-list.org/eng/proxylist.txt'
    ]
    
    # Fetch proxies from all URLs concurrently using ThreadPoolExecutor
    with ThreadPoolExecutor(max_workers=None) as executor:
        futures = [executor.submit(fetch_response, url, headers={
            "User-Agent": get_random_user_agent(),
            "X-Forwarded-For": get_random_ip(),
            "Client-IP": get_random_ip(),
            "X-Real-IP": get_random_ip()
        }) for url in proxy_urls]
        
        for future in as_completed(futures):
            response_text = future.result()
            if response_text is None:
                continue  # Skip URLs that failed

            # Determine the response format and process accordingly
            if response_text.startswith('{') and response_text.endswith('}'):
                # Try to parse JSON response
                try:
                    data = json.loads(response_text)  # Parse JSON
                    if isinstance(data, dict) and 'data' in data:
                        # Extract only IP and port from JSON data
                        new_proxies = {f"{proxy_data['ip']}:{proxy_data['port']}" for proxy_data in data['data'] if 'ip' in proxy_data and 'port' in proxy_data}
                        proxies.update(new_proxies)
                    else:
                        raise ValueError("Expected 'data' key in JSON response")
                except ValueError as e:
                    logging.error(f"Invalid JSON format: {e}")
                    continue
            else:
                # Treat response as plain text and extract IP and port if present
                lines = response_text.splitlines()
                new_proxies = {line.strip() for line in lines if line.strip()}  # Extract IP:port pairs
                proxies.update(new_proxies)

    # Convert to list and start background verification
    proxies_list = list(proxies)
    background_tasks.add_task(background_verification, proxies_list)

    # Write valid proxies to a text file
    with open("proxy.txt", "w") as file:
        file.write("\n".join(global_proxies["valid"]))

    # Generate HTML content to display the response data
    html_content = "<ul>" + "".join(f"<li>{proxy}</li>" for proxy in global_proxies["valid"]) + "</ul>"
    html_content += '<p><a href="/proxy-file">Download proxy.txt</a></p>'

    return HTMLResponse(content=html_content, status_code=200)

@app.get("/proxy-file")
def get_proxy_file():
    """Endpoint to download the proxy.txt file."""
    file_path = "proxy.txt"
    if os.path.exists(file_path):
        return FileResponse(path=file_path, filename=file_path, media_type='text/plain')
    else:
        raise HTTPException(status_code=404, detail="File not found")

if __name__ == "__main__":
    # Start background proxy verification
    verification_thread = Thread(target=lambda: asyncio.run(verify_valid_proxies()), daemon=True)
    verification_thread.start()

    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=7860)