import requests
import base64
from concurrent.futures import ThreadPoolExecutor, as_completed
from collections import defaultdict
from urllib.parse import quote

# ================== 配置 ==================
URL = "https://serverlist.piaservers.net/shadow_socks"
THREADS = 5
TOTAL_REQUESTS = 400          # 建议 400~800 次，增加获取更多IP概率
TIMEOUT = 10
# =========================================

def fetch_once():
    try:
        r = requests.get(URL, timeout=TIMEOUT, headers={
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
        })
        r.raise_for_status()
        text = r.text.strip()
        
        # 处理 "JSON\nbase64" 这种情况，取第一行（JSON部分）
        if '\n' in text:
            json_part = text.split('\n', 1)[0].strip()
        else:
            json_part = text
        
        data = json.loads(json_part)   # 只解析JSON部分
        if not isinstance(data, list):
            return None
        return data
    except Exception:
        return None

print(f"开始使用 {THREADS} 个线程采集 {TOTAL_REQUESTS} 次...")

servers = defaultdict(set)   # region -> set of hosts

with ThreadPoolExecutor(max_workers=THREADS) as executor:
    futures = [executor.submit(fetch_once) for _ in range(TOTAL_REQUESTS)]
    
    for i, future in enumerate(as_completed(futures), 1):
        data = future.result()
        if data:
            for item in data:
                if isinstance(item, dict):
                    region = str(item.get("region", "")).strip()
                    host = str(item.get("host", "")).strip()
                    if region and host:
                        servers[region].add(host)
        
        if i % 50 == 0 or i == TOTAL_REQUESTS:
            current_count = sum(len(h) for h in servers.values())
            print(f"已完成 {i}/{TOTAL_REQUESTS} 次请求... 当前发现节点数: {current_count}")

print("\n采集完成！")
total = sum(len(hosts) for hosts in servers.values())
print(f"共发现 {total} 个独特节点\n")

# 输出结果
print("地区                Host数量    Hosts")
print("-" * 80)
all_nodes = []
for region in sorted(servers):
    hosts = sorted(servers[region])
    print(f"{region:<20} {len(hosts):<8} {', '.join(hosts)}")
    for host in hosts:
        all_nodes.append({
            "region": region,
            "host": host,
            "port": 443,
            "password": "shadowsocks",
            "cipher": "aes-128-gcm"
        })

if not all_nodes:
    print("还是采集不到节点，请把下面这行贴给我：")
    print("你的网络环境 / 是否用了代理 / 是否在路由器/LEDE/OpenWrt 上运行")
else:
    print(f"\n=== ss:// 节点链接（共 {len(all_nodes)} 个）===")
    ss_links = []
    for node in all_nodes:
        auth = f"{node['cipher']}:{node['password']}@{node['host']}:{node['port']}"
        b64 = base64.urlsafe_b64encode(auth.encode()).decode().rstrip("=")
        name = f"PIA-{node['region']}-{node['host'].split('.')[-1]}"
        ss_url = f"ss://{b64}#{quote(name)}"
        ss_links.append(ss_url)
        print(ss_url)

    print(f"\n=== 一键订阅链接 ===")
    sub_url = "https://api.ss-sub.com/sub?target=ss&url=" + "|".join(ss_links)
    print(sub_url)

    # 保存文件
    with open("pia_shadowsocks_nodes.txt", "w", encoding="utf-8") as f:
        f.write("\n".join(ss_links))
        f.write(f"\n\n订阅链接：\n{sub_url}")

    print("\n节点已保存到 pia_shadowsocks_nodes.txt")