Upload hf_backend/test_show_external.py with huggingface_hub

hf_backend/test_show_external.py

@@ -0,0 +1,94 @@
+#!/usr/bin/env python3
+"""
+查找 "show external downloads" 选项并尝试通过其他方式获取文件
+"""
+
+from playwright.sync_api import sync_playwright
+import time
+import re
+
+MD5 = "d94c20d1364af9b484949659398c4062"
+MD5_URL = f"https://annas-archive.gl/md5/{MD5}"
+
+def find_external_downloads():
+    """查找外部下载选项"""
+    print(f"目标: {MD5_URL}\n")
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=True)
+        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()
+
+        print("访问 md5 页面...")
+        page.goto(MD5_URL, timeout=60000, wait_until="domcontentloaded")
+        page.wait_for_timeout(3000)
+
+        # 查找 "show external downloads" 按钮或链接
+        print("\n查找 'show external downloads' 链接...")
+
+        # 方法1: 通过文本查找
+        show_external = None
+        try:
+            # 尝试查找包含 "external" 的元素
+            elements = page.query_selector_all("button, a, span, div")
+            for el in elements:
+                text = el.inner_text().strip().lower()
+                if 'external' in text or 'show' in text:
+                    print(f"  发现元素: '{el.inner_text().strip()}' - tag: {el.evaluate('el => el.tagName')}")
+                    if 'external' in text:
+                        show_external = el
+        except Exception as e:
+            print(f"  查找错误: {e}")
+
+        # 方法2: 直接点击 "show external downloads" 文本
+        try:
+            # 尝试点击包含 "show external" 的链接
+            link = page.locator("text=show external").first
+            if link:
+                print(f"\n找到 'show external' 链接!")
+                link.click()
+                page.wait_for_timeout(2000)
+
+                # 查找新出现的下载选项
+                print("点击后查找下载链接...")
+                links = page.query_selector_all("a[href]")
+                for l in links:
+                    href = l.get_attribute("href")
+                    if href and any(k in href.lower() for k in ['zlib', 'tor', 'onion', 'libgen']):
+                        print(f"  外部链接: {href}")
+        except Exception as e:
+            print(f"点击错误: {e}")
+
+        # 方法3: 直接访问 Z-Library 的 Tor URL
+        print("\n尝试访问 Z-Library Tor URL...")
+        tor_url = f"http://bookszlibb74ugqojhzhg2a63w5i2atv5bqarulgczawnbmsb6s6qead.onion/md5/{MD5}"
+        try:
+            # 这个可能会失败因为没有 Tor 代理
+            page.goto(tor_url, timeout=15000)
+            print(f"  Tor URL 标题: {page.title()}")
+        except Exception as e:
+            print(f"  Tor URL 访问失败: {str(e)[:50]}")
+
+        # 方法4: 尝试用 requests 访问 Z-Library 的 clearnet 版本
+        print("\n尝试 Z-Library clearnet...")
+        import requests
+        try:
+            # Z-Library 的 API 或搜索
+            resp = requests.get(
+                "https://z-lib.org",
+                headers={"User-Agent": "Mozilla/5.0"},
+                timeout=10
+            )
+            print(f"  Z-Library 状态: {resp.status_code}")
+        except Exception as e:
+            print(f"  Z-Library 访问失败: {str(e)[:50]}")
+
+        browser.close()
+
+if __name__ == "__main__":
+    print("=" * 60)
+    print("查找外部下载选项")
+    print("=" * 60)
+    find_external_downloads()