Upload hf_backend/test_monitor_network.py with huggingface_hub

hf_backend/test_monitor_network.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""
+监控网络请求，看是否能捕获到 EPUB 下载请求
+"""
+
+from playwright.sync_api import sync_playwright
+import time
+
+MD5 = "d94c20d1364af9b484949659398c4062"
+SLOW_URL = f"https://annas-archive.gl/slow_download/{MD5}/0/3"
+
+def monitor_network():
+    """监控网络请求"""
+    print(f"目标: {SLOW_URL}\n")
+
+    epub_requests = []
+    all_requests = []
+
+    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()
+
+        # 监控请求
+        def on_request(request):
+            url = request.url
+            if '.epub' in url.lower():
+                print(f"  [EPUB请求] {url}")
+                epub_requests.append(url)
+            elif 'download' in url.lower() or 'file' in url.lower():
+                all_requests.append(url)
+
+        def on_response(response):
+            url = response.url
+            content_type = response.headers.get('content-type', '')
+            if '.epub' in url.lower():
+                print(f"  [EPUB响应] {url} - {content_type}")
+                epub_requests.append(url)
+
+        page.on("request", on_request)
+        page.on("response", on_response)
+
+        print("访问 slow_download...")
+        page.goto(SLOW_URL, timeout=120000, wait_until="domcontentloaded")
+        print(f"初始标题: {page.title()}")
+
+        # 等待最多60秒
+        for i in range(60):
+            time.sleep(1)
+            try:
+                title = page.title()
+                url = page.url
+
+                if url.lower().endswith('.epub'):
+                    print(f"\n在第{i+1}秒发现EPUB URL: {url}")
+                    browser.close()
+                    return url
+
+                if title != "DDoS-Guard":
+                    print(f"\n在第{i+1}秒: 标题={title}, URL={url}")
+
+                if (i + 1) % 15 == 0:
+                    print(f"  {i+1}秒... 标题={title}")
+            except Exception as e:
+                print(f"  {i+1}秒... (导航中)")
+                continue
+
+        print(f"\n最终URL: {page.url}")
+        print(f"\n捕获到的EPUB相关请求: {epub_requests}")
+        print(f"捕获到的下载相关请求: {all_requests[:5]}")
+
+        browser.close()
+        return epub_requests[0] if epub_requests else None
+
+if __name__ == "__main__":
+    print("=" * 60)
+    print("监控网络请求")
+    print("=" * 60)
+    result = monitor_network()
+    if result:
+        print(f"\n成功: {result}")
+    else:
+        print("\n未捕获到EPUB请求")