hf_backend/test_zlibrary_func.py

#!/usr/bin/env python3
"""
测试 Z-Library 搜索功能，验证能否获取 EPUB 直链
"""

from playwright.sync_api import sync_playwright
import time
import re
from urllib.parse import quote
import requests

def test_zlibrary_search(query):
    """测试 Z-Library 搜索"""
    print(f"搜索: {query}\n")

    with sync_playwright() as p:
        browser = p.chromium.launch(headless=False)
        context = browser.new_context(
            user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36",
        )
        page = context.new_page()

        # 访问搜索页
        search_url = f"https://z-library.sk/s/{quote(query)}"
        page.goto(search_url, timeout=60000, wait_until="domcontentloaded")
        page.wait_for_timeout(5000)

        print(f"页面标题: {page.title()}")

        # 获取页面内容
        content = page.content()

        # 查找书籍详情页链接
        book_pattern = r'/book/([a-zA-Z0-9]+)/([^"]+\.html)'
        book_matches = re.findall(book_pattern, content)

        print(f"找到书籍数量: {len(book_matches)}")

        # 获取第一本书的下载页 URL
        if book_matches:
            first_book_id, first_book_title = book_matches[0]
            book_url = f"https://z-library.sk/book/{first_book_id}/{first_book_title}"
            print(f"\n访问第一本书详情页: {book_url}")

            page2 = context.new_page()
            page2.goto(book_url, timeout=60000, wait_until="domcontentloaded")
            page2.wait_for_timeout(3000)

            # 获取下载链接
            detail_content = page2.content()

            # 查找 dl/ 链接
            dl_matches = re.findall(r'/dl/([a-zA-Z0-9]+)', detail_content)
            if dl_matches:
                dl_id = dl_matches[0]
                dl_url = f"https://z-library.sk/dl/{dl_id}"
                print(f"下载页 URL: {dl_url}")

                # 尝试用 Playwright 访问下载页
                print("\n用 Playwright 访问下载页...")
                page3 = context.new_page()
                page3.goto(dl_url, timeout=60000, wait_until="domcontentloaded")

                # 等待 Cloudflare 检查
                for i in range(30):
                    time.sleep(1)
                    title = page3.title()
                    print(f"  {i+1}秒: {title}")

                    if 'Checking' not in title and 'browser' not in title.lower():
                        break

                final_url = page3.url
                print(f"\n最终 URL: {final_url}")

                if final_url.lower().endswith('.epub'):
                    print("[成功] 获取到 EPUB 直链!")

                page3.close()

            page2.close()

        input("按回车键关闭浏览器...")
        browser.close()

if __name__ == "__main__":
    test_zlibrary_search("Capitalism: A Global History")