hf_backend/test_capture_nav.py

#!/usr/bin/env python3
"""
捕获导航事件，获取最终的EPUB URL
"""

from playwright.sync_api import sync_playwright
import time

MD5 = "d94c20d1364af9b484949659398c4062"
SLOW_URL = f"https://annas-archive.gl/slow_download/{MD5}/0/3"

def capture_navigation():
    """捕获所有导航事件"""
    print(f"目标: {SLOW_URL}\n")

    result = {"url": None, "error": None}

    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",
            viewport={"width": 1920, "height": 1080},
        )
        page = context.new_page()

        # 监听所有可能的导航事件
        def on_navigation(frame):
            url = frame.url if frame else page.url
            print(f"  [导航事件] {url}")

        page.on("navigation", on_navigation)
        page.on("framenavigated", on_navigation)

        # 监听下载
        def on_download(download):
            print(f"  [下载事件] {download.url}")
            result["url"] = download.url

        page.on("download", on_download)

        print("访问slow_download...")
        try:
            page.goto(SLOW_URL, timeout=120000, wait_until="domcontentloaded")
        except Exception as e:
            print(f"goto异常: {e}")
            # 可能是导航成功了
            result["url"] = page.url

        print(f"初始URL: {page.url}")

        # 等待60秒
        print("\n等待60秒...")
        for i in range(60):
            time.sleep(1)

            try:
                current_url = page.url
                if current_url.lower().endswith('.epub'):
                    print(f"\n在第{i+1}秒发现EPUB URL: {current_url}")
                    result["url"] = current_url
                    break

                if (i + 1) % 10 == 0:
                    print(f"  {i+1}秒... 当前URL: {current_url[:60]}...")
            except Exception as e:
                # 页面可能在导航中
                print(f"  {i+1}秒... (页面可能正在导航: {str(e)[:30]})")
                continue

        print(f"\n最终URL: {page.url}")

        browser.close()

    return result["url"]

if __name__ == "__main__":
    print("=" * 60)
    print("捕获导航事件")
    print("=" * 60)
    print()

    url = capture_navigation()
    print(f"\n{'='*60}")
    if url:
        print(f"成功获取到: {url}")
    else:
        print("未能获取到EPUB链接")
    print("=" * 60)