media-center/sites/yunpan1/v1/yunpan1_search.py

#!python
# -*- coding: utf-8 -*-
"""
yunpan1 搜索工具 — 搜索云盘资源分享社区并提取夸克链接

用法：
  py -X utf8 yunpan1_search.py <关键词>
  py -X utf8 yunpan1_search.py 遮天

说明：
  - 优先搜索，30 秒超时后自动降级到浏览动漫板块最新帖子
  - Cookie 文件: tmp/yunpan1_cookies.txt（格式：key=value 一行一个 或 Netscape 格式均可）
  - 依赖: Python 标准库（无需额外安装）
"""

import re
import os
import sys
import urllib.request
import urllib.parse
import time

# ── 配置 ──────────────────────────────────────────────────────────
BASE_URL = 'https://yunpan1.cc'
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
COOKIE_FILE = os.path.abspath(os.path.join(SCRIPT_DIR, '..', '..', '..', 'tmp', 'yunpan1_cookies.txt'))
OUTPUT_FILE = os.path.abspath(os.path.join(SCRIPT_DIR, '..', '..', '..', 'tmp', 'quark_links.txt'))

SEARCH_URL = BASE_URL + '/search.php?mod=forum&srchtxt={keyword}&searchsubmit=yes'
FORUM_URL = BASE_URL + '/forum.php?mod=forumdisplay&fid=3&orderby=dateline'

SEARCH_TIMEOUT = 30     # 搜索超时（秒），超时后降级到浏览板块
FORUM_TIMEOUT = 15      # 板块页面超时

_opener = urllib.request.build_opener()
_opener.timeout = SEARCH_TIMEOUT


# ── Cookie 加载（兼容两种格式） ──────────────────────────────────

def load_cookie():
    """加载 Cookie，兼容 key=value 一行一个 和 Netscape 格式"""
    path = COOKIE_FILE
    if not os.path.exists(path):
        print(f'❌ Cookie 文件不存在: {path}')
        print(f'请通过 Playwright 登录 yunpan1.cc 后，将 Cookie 保存到该文件')
        sys.exit(1)

    with open(path, 'r', encoding='utf-8') as f:
        raw = f.read()

    # 如果是 Netscape 格式（含 tab、domain、TRUE/FALSE 等字段）
    if '\t' in raw and ('TRUE' in raw or 'FALSE' in raw):
        parts = []
        for line in raw.strip().splitlines():
            line = line.strip()
            if not line or line.startswith('#'):
                continue
            cols = line.split('\t')
            if len(cols) >= 7:
                parts.append(f'{cols[5]}={cols[6]}')
        if parts:
            return '; '.join(parts)

    # 否则按 key=value 一行一个处理
    return raw.strip().replace('\n', '; ').replace('\r', '')


# ── HTTP 请求 ─────────────────────────────────────────────────────

def request(url, cookie, timeout=SEARCH_TIMEOUT):
    req = urllib.request.Request(url, headers={
        'Cookie': cookie,
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
    })
    _opener.timeout = timeout
    t0 = time.time()
    try:
        resp = _opener.open(req)
        html = resp.read().decode('utf-8', errors='replace')
        return resp.status, html, resp.url, time.time() - t0, None
    except Exception as e:
        return None, '', '', time.time() - t0, str(e)


# ── 提取函数 ──────────────────────────────────────────────────────

def extract_quark_links(html):
    raw = re.findall(r'https?://pan\.quark\.cn/s/[a-zA-Z0-9]{12,}', html)
    return sorted(set(l for l in raw if not l.endswith('https')))


def extract_truncated_links(html):
    raw = re.findall(r'https?://pan\.quark\.cn/s/[a-zA-Z0-9]{1,11}', html)
    return sorted(set(raw))


def extract_threads(html):
    """提取帖子标题，兼容 viewthread 和 thread 格式"""
    patterns = [
        r'<a[^>]+href="forum\.php\?mod=viewthread[^>]+>([^<]+)</a>',
        r'<a[^>]+href="thread\.php\?tid=\d+[^>]*>([^<]+)</a>',
        r'class="s xst"[^>]*>([^<]+)</a>',
        r'<a[^>]+class="xst"[^>]*>([^<]+)</a>',
    ]
    all_titles = []
    for p in patterns:
        all_titles.extend(re.findall(p, html))

    seen = set()
    result = []
    for t in all_titles:
        t = t.strip()
        if t and len(t) > 5 and t not in seen:
            seen.add(t)
            result.append(t)
    return result


# ── 主流程 ────────────────────────────────────────────────────────

def search(keyword, cookie):
    """搜索，超时则返回 None"""
    url = SEARCH_URL.format(keyword=urllib.parse.quote(keyword))
    print(f'🔍 搜索 "{keyword}"（{SEARCH_TIMEOUT}s 超时）...')
    sys.stdout.flush()
    return request(url, cookie, timeout=SEARCH_TIMEOUT)


def browse_forum(cookie):
    """浏览动漫板块最新帖子作为降级方案"""
    print(f'⏩ 降级到浏览动漫板块最新帖子...')
    sys.stdout.flush()
    return request(FORUM_URL, cookie, timeout=FORUM_TIMEOUT)


def print_results(links, truncated, threads, source, elapsed):
    print(f'\n✅ 完成（来源: {source}，耗时 {elapsed:.0f}s）')

    if links:
        print(f'\n{"=" * 50}')
        print(f'✅ 完整夸克链接（可直接转存）: {len(links)}')
        print(f'{"=" * 50}')
        for l in links:
            print(f'   {l}')

        os.makedirs(os.path.dirname(OUTPUT_FILE), exist_ok=True)
        with open(OUTPUT_FILE, 'w', encoding='utf-8') as f:
            f.write('\n'.join(links) + '\n')
        print(f'\n💾 链接已保存: {os.path.relpath(OUTPUT_FILE)}')
    else:
        print('\n⚠️  未找到完整夸克链接')

    if truncated:
        print(f'\n⚠️  被截断的链接（{len(truncated)} 个，需点进帖子）:')
        for l in truncated[:5]:
            print(f'   {l}')

    if threads:
        print(f'\n📌 帖子预览（前 10 条）:')
        for t in threads[:10]:
            print(f'   • {t[:60]}')


def main():
    if len(sys.argv) < 2:
        print('用法: py -X utf8 yunpan1_search.py <关键词>')
        print('示例: py -X utf8 yunpan1_search.py 遮天')
        sys.exit(1)

    keyword = sys.argv[1]
    cookie = load_cookie()

    # 尝试搜索
    status, html, _, elapsed, err = search(keyword, cookie)

    if err and 'timeout' in err.lower():
        print(f'⏱  搜索超时（{elapsed:.0f}s），机器配置较低时首次建索引可能卡死')
        # 降级到浏览板块
        status, html, _, elapsed, err2 = browse_forum(cookie)
        if err2:
            print(f'❌ 降级也失败了: {err2}')
            sys.exit(1)
        source = '板块浏览（搜索超时降级）'
    elif err:
        print(f'❌ 搜索失败: {err}')
        # 尝试降级
        status, html, _, elapsed, _ = browse_forum(cookie)
        source = '板块浏览（搜索失败降级）'
    else:
        source = '搜索'

    links = extract_quark_links(html)
    truncated = extract_truncated_links(html)
    threads = extract_threads(html)
    print_results(links, truncated, threads, source, elapsed)


if __name__ == '__main__':
    main()