From 47355b36d9dd9409866fbb4419cb652cb4a8ba9f Mon Sep 17 00:00:00 2001
From: OpenClaw Agent <admin@openclaw.ai>
Date: Tue, 10 Feb 2026 14:53:05 +0800
Subject: [PATCH] feat(kb-bilibili-content): Add article content extraction
 using Playwright
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- Replace API-based article extraction with Playwright scraping
- Support Bilibili article (专栏) content extraction
- Extract full article text using .read-article-holder selector
- Use async Playwright API for proper async/await support
---
 .../kb-bilibili-content/bilibili_content.py   | 55 +++++++++++++------
 1 file changed, 37 insertions(+), 18 deletions(-)

diff --git a/skills/kb-bilibili-content/bilibili_content.py b/skills/kb-bilibili-content/bilibili_content.py
index 9dba074..cc5f790 100644
--- a/skills/kb-bilibili-content/bilibili_content.py
+++ b/skills/kb-bilibili-content/bilibili_content.py
@@ -4,9 +4,9 @@
 Bilibili Content Downloader - B站内容获取工具
 
 功能:
-- download_video(bvid, quality=480) - 下载低分辨率视频
+- download_video(bvid, quality=480) - 下载视频
 - extract_subtitle(bvid) - 提取字幕
-- extract_article(cvid) - 获取专栏全文
+- extract_article(cvid) - 获取专栏全文（使用Playwright）
 - 命令行参数支持
 - JSON 输出
 """
@@ -149,32 +149,51 @@ class BilibiliContent:
         return result
     
     async def extract_article(self, cvid: str) -> Dict[str, Any]:
-        """获取专栏全文"""
+        """获取专栏全文（使用Playwright异步API）"""
         result = {"success": False, "cvid": cvid, "title": "", "content": "", "message": ""}
         
         try:
-            async with aiohttp.ClientSession(headers=self._get_headers()) as session:
-                print(f"获取专栏: {cvid}")
-                async with session.get("https://api.bilibili.com/x/article/viewinfo", params={'id': cvid}) as resp:
-                    data = await resp.json()
+            from playwright.async_api import async_playwright
+            
+            cvid_clean = cvid.replace('cv', '')
+            url = f"https://www.bilibili.com/read/cv{cvid_clean}"
+            print(f"获取专栏: {url}")
+            
+            async with async_playwright() as p:
+                browser = await p.chromium.launch(headless=True)
+                page = await browser.new_page()
                 
-                print(f"状态: {data.get('code')} - {data.get('message')}")
+                await page.goto(url, wait_until="networkidle")
+                await page.wait_for_timeout(3000)
                 
-                if data.get('code') != 0:
-                    result["message"] = f"获取失败: {data.get('message')}"
-                    return result
+                # 提取标题
+                title_elem = await page.query_selector('h1')
+                if title_elem:
+                    result["title"] = (await title_elem.inner_text()).strip()
+                    print(f"标题: {result['title'][:50]}...")
                 
-                article = data.get('data', {})
-                result["title"] = article.get('title', '')
-                result["content"] = article.get('content', '')
-                result["success"] = bool(result["title"] and result["content"])
-                result["message"] = f"获取: {result['title']}" if result["success"] else "获取失败"
+                # 提取正文内容
+                content_elem = await page.query_selector('.read-article-holder')
+                if content_elem:
+                    html_content = await content_elem.inner_html()
+                    text_content = await content_elem.inner_text()
+                    result["content"] = text_content.strip()
+                    result["html_content"] = html_content.strip()
+                    result["success"] = bool(result["title"] and result["content"])
+                    print(f"内容长度: {len(result['content'])} 字符")
+                else:
+                    result["message"] = "未找到专栏内容"
                 
-                if result["success"]:
-                    print(f"✅ {result['title']}")
+                await browser.close()
+            
+            if result["success"]:
+                result["message"] = f"✅ 获取成功: {result['title'][:30]}..."
+            else:
+                result["message"] = f"获取失败: {result.get('message', '未知错误')}"
         
         except Exception as e:
             result["message"] = f"错误: {str(e)}"
+            print(f"错误: {e}")
         
         return result