Upload hf_backend/test_curl_cookies.py with huggingface_hub

hf_backend/test_curl_cookies.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+"""
+使用curl来访问slow_download，保存和使用cookies
+"""
+
+import subprocess
+import time
+import os
+
+MD5 = "d94c20d1364af9b484949659398c4062"
+SLOW_URL = f"https://annas-archive.gl/slow_download/{MD5}/0/3"
+COOKIE_FILE = "cookies.txt"
+
+def curl_get(url, cookies=None, follow_redirect=True):
+    """使用curl发送请求"""
+    cmd = ["curl", "-s", "-L"]
+
+    if cookies:
+        cmd.extend(["-b", cookies, "-c", cookies])
+
+    cmd.extend([
+        "-A", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36",
+        "-H", "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
+        "-H", "Accept-Language: zh-CN,zh;q=0.9,en;q=0.8",
+        url
+    ])
+
+    result = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
+    return result.stdout, result.stderr, result.returncode
+
+def test_curl_approach():
+    print(f"目标: {SLOW_URL}\n")
+
+    # 首先访问主页获取cookies
+    print("步骤1: 访问主页获取cookies...")
+    stdout, stderr, code = curl_get("https://annas-archive.gl", cookies=None)
+
+    # 保存cookies
+    if os.path.exists(COOKIE_FILE):
+        print(f"Cookies文件已存在: {COOKIE_FILE}")
+    else:
+        print(f"创建cookies文件: {COOKIE_FILE}")
+
+    print(f"\n步骤2: 用cookies访问slow_download...")
+    stdout, stderr, code = curl_get(SLOW_URL, cookies=COOKIE_FILE)
+
+    print(f"响应长度: {len(stdout)} 字节")
+    print(f"前500字符:\n{stdout[:500]}")
+
+    # 检查是否是DDoS-Guard
+    if 'ddos' in stdout.lower() or 'DDoS' in stdout:
+        print("\n被DDoS-Guard阻止")
+    elif '.epub' in stdout.lower():
+        print("\n可能包含EPUB!")
+        import re
+        epub_links = re.findall(r'href=["\']([^"\']*\.epub[^"\']*)["\']', stdout)
+        if epub_links:
+            print(f"找到EPUB链接: {epub_links[0]}")
+    else:
+        # 检查最终URL
+        print("\n内容不包含.epub或ddos")
+
+if __name__ == "__main__":
+    print("=" * 60)
+    print("Curl方式访问Anna's Archive")
+    print("=" * 60)
+    test_curl_approach()