Upload hf_backend/test_zlibrary_v2.py with huggingface_hub

hf_backend/test_zlibrary_v2.py

@@ -0,0 +1,107 @@
+#!/usr/bin/env python3
+"""
+测试 Z-Library 不同的访问方式
+"""
+
+from playwright.sync_api import sync_playwright
+import requests
+import time
+import re
+
+def test_zlibrary_domains():
+    """测试不同的 Z-Library 域名"""
+    domains = [
+        "https://z-library.sk",
+        "https://zlibrary.to",
+        "https://zlibrary.is",
+        "https://singlelogin.re",
+        "https://bookszlibb74ugqojhzhg2a63w5i2atv5bqarulgczawnbmsb6s6qead.onion",  # Tor
+    ]
+
+    query = "Capitalism A Global History"
+    print("测试不同的 Z-Library 域名...\n")
+
+    for domain in domains:
+        print(f"测试: {domain}")
+        try:
+            if ".onion" in domain:
+                print("   [跳过] Tor 需要特殊配置")
+                continue
+
+            resp = requests.get(f"{domain}/search?q={query}&languages=1",
+                             timeout=10,
+                             headers={"User-Agent": "Mozilla/5.0"})
+            print(f"   状态: {resp.status_code}")
+            if resp.status_code == 200:
+                if "not found" in resp.text.lower() or "404" in resp.text[:500]:
+                    print("   [无效] 页面不存在")
+                else:
+                    print(f"   [有效] 内容长度: {len(resp.text)}")
+        except Exception as e:
+            print(f"   错误: {str(e)[:50]}")
+        print()
+
+def test_with_playwright():
+    """用 Playwright 测试"""
+    print("\n用 Playwright 测试 Z-Library...")
+
+    domains = [
+        ("https://z-library.sk", "Z-Library SK"),
+        ("https://singlelogin.re", "SingleLogin"),
+    ]
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=True)
+
+        for domain, name in domains:
+            print(f"\n测试 {name}: {domain}")
+            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()
+
+            try:
+                page.goto(f"{domain}/search?q=Capitalism+A+Global+History&languages=1",
+                         timeout=15000, wait_until="domcontentloaded")
+                page.wait_for_timeout(2000)
+                print(f"   标题: {page.title()}")
+
+                # 查找书籍链接
+                links = page.query_selector_all("a[href*='/book/'], a[href*='/b/']")
+                print(f"   找到书籍链接: {len(links)}")
+                for link in links[:5]:
+                    href = link.get_attribute("href")
+                    text = link.inner_text().strip()[:50]
+                    print(f"      {href[:60]} - {text}")
+
+            except Exception as e:
+                print(f"   错误: {e}")
+
+            context.close()
+
+        browser.close()
+
+def test_zlib_api():
+    """测试 Z-Library API"""
+    print("\n\n测试 Z-Library API...")
+
+    # Z-Library 有一些公共 API 端点
+    api_urls = [
+        "https://z-library.sk/suggest_json.php?term=capitalism",
+        "https://api.zlibrary.org/v1/book/search",
+    ]
+
+    for url in api_urls:
+        print(f"\n测试: {url}")
+        try:
+            resp = requests.get(url, timeout=10, headers={"User-Agent": "Mozilla/5.0"})
+            print(f"   状态: {resp.status_code}")
+            if resp.status_code == 200:
+                print(f"   内容: {resp.text[:200]}")
+        except Exception as e:
+            print(f"   错误: {e}")
+
+if __name__ == "__main__":
+    test_zlibrary_domains()
+    test_with_playwright()
+    test_zlib_api()