cnks 0.2.5__tar.gz → 0.3.0__tar.gz

cnks-0.3.0/.env

@@ -0,0 +1,2 @@
+SEARCH_URL=https://kns.cnki.net/kns8s/search
+CACHE_FILE=cache.json

cnks-0.3.0/PKG-INFO

@@ -0,0 +1,101 @@
+Metadata-Version: 2.4
+Name: cnks
+Version: 0.3.0
+Summary: 中国知网搜索与引文处理系统
+Author-email: bai-z-l <b@iziliang.com>
+Requires-Python: >=3.12
+Requires-Dist: mcp[cli]>=1.6.0
+Requires-Dist: playwright>=1.40.0
+Requires-Dist: python-dotenv>=1.0.0
+Description-Content-Type: text/markdown
+
+# CNKS - 中国知网搜索与引文处理系统
+
+## 简介
+
+CNKS是一个用于搜索中国知网并提取引文数据的工具。该系统能够自动化搜索过程，提取文献信息，并以结构化的方式返回结果。
+
+## 系统架构
+
+CNKS采用服务器-客户端架构，包含以下主要组件：
+
+1. **服务器 (Server)**: 
+   - 处理来自客户端的请求
+   - 按需调用Worker API处理关键词搜索
+   - 管理搜索结果缓存
+
+2. **工作模块 (Worker)**: 
+   - 提供搜索和数据提取API
+   - 使用Playwright自动浏览网页
+   - 解析和提取引文数据
+   - 不再作为独立进程运行，而是由服务器直接调用
+
+3. **客户端 (Client)**:
+   - 命令行界面，用于发送搜索请求
+   - 接收并显示搜索结果
+
+4. **引文处理器 (Citzer)**:
+   - 解析和格式化引文数据
+   - 支持多种引文格式
+
+## 安装
+
+### 要求
+
+- Python 3.12 或更高版本
+- Playwright
+- MCP
+
+### 安装步骤
+
+1. 克隆仓库：
+   ```
+   git clone https://github.com/your-username/cnks.git
+   cd cnks
+   ```
+
+2. 安装依赖：
+   ```
+   pip install -e .
+   playwright install
+   ```
+
+## 使用方法
+
+### 启动服务器
+
+```
+cnks
+```
+或
+```
+cnks-server
+```
+
+### 使用客户端发送请求
+
+```
+cnks-client "搜索关键词"
+```
+
+选项：
+- `--timeout SECONDS`: 设置响应超时时间（默认为60秒）
+
+### 直接测试Worker模块 (仅用于调试)
+
+```
+cnks-worker-test "搜索关键词"
+```
+
+## 配置
+
+系统可通过以下环境变量进行配置：
+
+- `CACHE_FILE`: 缓存文件路径，默认为 "cache.json"
+- `SEARCH_URL`: 搜索URL，默认为中国知网搜索页面
+
+可以创建`.env`文件设置这些环境变量。
+
+## 许可证
+
+[项目许可证信息]

cnks-0.3.0/README.md

@@ -0,0 +1,90 @@
+# CNKS - 中国知网搜索与引文处理系统
+
+## 简介
+
+CNKS是一个用于搜索中国知网并提取引文数据的工具。该系统能够自动化搜索过程，提取文献信息，并以结构化的方式返回结果。
+
+## 系统架构
+
+CNKS采用服务器-客户端架构，包含以下主要组件：
+
+1. **服务器 (Server)**: 
+   - 处理来自客户端的请求
+   - 按需调用Worker API处理关键词搜索
+   - 管理搜索结果缓存
+
+2. **工作模块 (Worker)**: 
+   - 提供搜索和数据提取API
+   - 使用Playwright自动浏览网页
+   - 解析和提取引文数据
+   - 不再作为独立进程运行，而是由服务器直接调用
+
+3. **客户端 (Client)**:
+   - 命令行界面，用于发送搜索请求
+   - 接收并显示搜索结果
+
+4. **引文处理器 (Citzer)**:
+   - 解析和格式化引文数据
+   - 支持多种引文格式
+
+## 安装
+
+### 要求
+
+- Python 3.12 或更高版本
+- Playwright
+- MCP
+
+### 安装步骤
+
+1. 克隆仓库：
+   ```
+   git clone https://github.com/your-username/cnks.git
+   cd cnks
+   ```
+
+2. 安装依赖：
+   ```
+   pip install -e .
+   playwright install
+   ```
+
+## 使用方法
+
+### 启动服务器
+
+```
+cnks
+```
+或
+```
+cnks-server
+```
+
+### 使用客户端发送请求
+
+```
+cnks-client "搜索关键词"
+```
+
+选项：
+- `--timeout SECONDS`: 设置响应超时时间（默认为60秒）
+
+### 直接测试Worker模块 (仅用于调试)
+
+```
+cnks-worker-test "搜索关键词"
+```
+
+## 配置
+
+系统可通过以下环境变量进行配置：
+
+- `CACHE_FILE`: 缓存文件路径，默认为 "cache.json"
+- `SEARCH_URL`: 搜索URL，默认为中国知网搜索页面
+
+可以创建`.env`文件设置这些环境变量。
+
+## 许可证
+
+[项目许可证信息]

cnks-0.3.0/cache.json

@@ -0,0 +1,37 @@
+{
+  "keyword": "ai幻觉",
+  "links": [
+    "https://kns.cnki.net/kcms2/article/abstract?v=Eh6WGTKUEQTfMYcnIyDlMydu1HABnqq_dsSzg0B5du7XgCN_O9piLwD1K2seLSx_nF3ApA16hsfSiTUdD-WKrcMmzThwhsqozA1bz195HiF6YvUDnQ2LJgcuMLLmBJI0cqJ-1k2WlTuNrFSD6HXQ2hg9nlWWF9qtgRNQrdT5fgmpWeBfviB5zQ==&uniplatform=NZKPT&language=CHS",
+    "https://kns.cnki.net/kcms2/article/abstract?v=Eh6WGTKUEQQfzW3X2aBJ8tSTl6wbxit-K3dXP66Unw2VmqjZe0yGSpxgv_Y3MtW6OxFhNOnWOGfF3Oh3LjPKIdG9cyp1huFXJlcIYLODwrcZa2_5VMWMyoJAbYW9QOQyXC3c8UQrcx0ehtXeph-1l8G-4pYSVyXZGF9rEOnSEZHIgoi_tVxtfg==&uniplatform=NZKPT&language=CHS",
+    "https://kns.cnki.net/kcms2/article/abstract?v=Eh6WGTKUEQQfzW3X2aBJ8tSTl6wbxit-K3dXP66Unw2VmqjZe0yGSkmwSnllxBKNCKC_OTluH6uX6bLabTKn5SVSyAS9rbyPBV28OXmP1_yBkQaPI1Uob6SbAhaO2P4XcgumL8_1Hv_goSbk9-H2twsryMYLFPphwqft1DCXWyLzA6Qj_35biw==&uniplatform=NZKPT&language=CHS",
+    "https://kns.cnki.net/kcms2/article/abstract?v=Eh6WGTKUEQQfzW3X2aBJ8tSTl6wbxit-K3dXP66Unw3r0ukzYcc2MP99ns5pNfsFtfv36V-PrkLgnzDu-ANW9ShcvCdZ8vo2fwDPsTtxQUH6aoSRKSVcSSXH7FEwXUEm0NWohYWeZedQR68YCz1gFtuAvvOmdK1thSLEv7Alo77svvRiXBlSxQ==&uniplatform=NZKPT&language=CHS"
+  ],
+  "results": [
+    {
+      "title": "技术过程论视角下AI幻觉生成的价值负荷与伦理问题探析[J]",
+      "cite_format": "[1]胡泳,王昱昊.技术过程论视角下AI幻觉生成的价值负荷与伦理问题探析[J].南京社会科学,2025,(03):84-94.DOI:10.15937/j.cnki.issn1001-8263.2025.03.009.",
+      "abstract": "AI技术的普及与产业生态的完善在引发智能社会变革的同时，也使得AI幻觉成为社会技术治理过程中新的风险变量。当AI作出不符合其训练数据的自信反应或编造与现实无关的事实时，“幻觉”便会产生。技术过程论主张将技术形态视作一个“动态”的演变过程，可借助技术构思、技术发明与技术产业化三阶段的演化过程框架，分析AI幻觉生成的价值负荷问题。研究发现，随着技术形态的演进，逐步形成了以技术发明者、技术本体、用户个体以及企业组织等多元行动者共同组成的综合性价值负荷过程，而技术本体的自我价值负荷行为也在不断褫夺人的主体性，进而引发网络信息秩序、知识内容生产等方面的价值异化现象。伴随着对AI幻觉价值评判标准的日趋复杂化，我们亟需关注AI幻觉所衍生出的技术伦理问题，秉持怀疑的态度来审慎地开展技术实践，从而在人与技术价值共赋的动态过程中牢牢把握人的主体性价值。"
+    },
+    {
+      "title": "Sora：传媒生态镜像进化与认知变革[J]",
+      "cite_format": "[1]张诗瑶,沈阳.Sora：传媒生态镜像进化与认知变革[J].编辑之友,2024,(06):53-60.DOI:10.13786/j.cnki.cn14-1066/g2.2024.6.007.",
+      "abstract": "Sora作为革命性的“类世界模型”，以镜像进化的逻辑发展，引领“天人智一”认知融合新纪元。在文生视频技术驱动下，文章以三组核心矛盾作为切入点，探讨Sora对未来传媒生态认知的潜在影响。研究发现，Sora引领我们从“真实世界美学”探索到“异世界美学”等，这标志着从标准化资源向个性化创新的转变。同时，其预示着传媒主体将从传统的半人工编辑转向语义智能体，传媒场景将更深层次地打破物理时空区隔，传媒产业价值将朝向AI自动化等方向发展。此外，文章通过对Sora官网发布的48个视频进行案例分析发现，“AI幻觉”问题开始显现。未来传媒从业者在角色方面，需从生产者转变为核查者；在应用方面，需重视编码与解码过程；在治理层面，需从人工治理逻辑转向机器治理逻辑。具体而言，“AI幻觉”的治理包括基于博弈理论的幻觉识别技术，利用多角色、多智能体，进行AI系统间的博弈与碰撞，有效识别和修正幻觉内容。"
+    },
+    {
+      "title": "模拟真实、权力让渡与镜像困境：生成式平台嵌入新闻生产的三重逻辑[J]",
+      "cite_format": "[1]郭栋.模拟真实、权力让渡与镜像困境：生成式平台嵌入新闻生产的三重逻辑[J].中国编辑,2024,(07):36-42.",
+      "abstract": "Sora类生成式大模型拟真化地生成虚拟世界，使人和技术之间由“它异关系”转变为“具身关系”。辅助新闻内容创作是生成式AI在新闻创新中的主要应用，新闻内容的生产从图片视频化发展到文字视频化，过去由文字建构的“影壁真实”转变为“全息真实”，传播者将采访、编辑和核查等权力让渡于新技术，数字在场与肉身在场之间产生张力。人工智能存在技术幻觉和真实性困境，“人在环中”策略在模型开发与运行的各阶段嵌入人的判断和价值观，消弭能力沟、驯化技术和重构编辑力是内在需求。"
+    },
+    {
+      "title": "生成式AI幻象的制造逻辑及其超真实建构的文化后果[J]",
+      "cite_format": "[1]经羽伦,张殿元.生成式AI幻象的制造逻辑及其超真实建构的文化后果[J].山东师范大学学报(社会科学版),2024,69(05):113-126.DOI:10.16456/j.cnki.1001-5973.2024.05.010.",
+      "abstract": "在人类文明史上出现的众多媒介都天然地具有欺骗性。正是媒介的欺骗性特征，使得媒介在中介化现实的过程中不断制造幻象。作为新型媒介的生成式AI,同样具有欺骗性，且在制造幻象方面已超越既往一切媒介，具体表现为“AI幻觉”“模拟影像”和“深度伪造”等形式。基于概率和模拟的自动化生产的软件系统，构成生成式AI复杂且庞大的欺骗机制，具有物质属性的交互界面，将此种欺骗隐匿其下。生成式AI已经建构起一个“超真实”的世界，其幻象正对应着鲍德里亚所预言的“分形文化”。最终的文化后果是，在生成式AI建构的幻象宇宙里，真假与否不再重要，它将我们引入一种“乐此不疲地制造幻象”的媒介环境与新文化形式之中。技术之恶的潜能亦可能被前所未有地激发。"
+    }
+  ],
+  "processed_links": [
+    "https://kns.cnki.net/kcms2/article/abstract?v=Eh6WGTKUEQTfMYcnIyDlMydu1HABnqq_dsSzg0B5du7XgCN_O9piLwD1K2seLSx_nF3ApA16hsfSiTUdD-WKrcMmzThwhsqozA1bz195HiF6YvUDnQ2LJgcuMLLmBJI0cqJ-1k2WlTuNrFSD6HXQ2hg9nlWWF9qtgRNQrdT5fgmpWeBfviB5zQ==&uniplatform=NZKPT&language=CHS",
+    "https://kns.cnki.net/kcms2/article/abstract?v=Eh6WGTKUEQQfzW3X2aBJ8tSTl6wbxit-K3dXP66Unw2VmqjZe0yGSpxgv_Y3MtW6OxFhNOnWOGfF3Oh3LjPKIdG9cyp1huFXJlcIYLODwrcZa2_5VMWMyoJAbYW9QOQyXC3c8UQrcx0ehtXeph-1l8G-4pYSVyXZGF9rEOnSEZHIgoi_tVxtfg==&uniplatform=NZKPT&language=CHS",
+    "https://kns.cnki.net/kcms2/article/abstract?v=Eh6WGTKUEQQfzW3X2aBJ8tSTl6wbxit-K3dXP66Unw2VmqjZe0yGSkmwSnllxBKNCKC_OTluH6uX6bLabTKn5SVSyAS9rbyPBV28OXmP1_yBkQaPI1Uob6SbAhaO2P4XcgumL8_1Hv_goSbk9-H2twsryMYLFPphwqft1DCXWyLzA6Qj_35biw==&uniplatform=NZKPT&language=CHS",
+    "https://kns.cnki.net/kcms2/article/abstract?v=Eh6WGTKUEQQfzW3X2aBJ8tSTl6wbxit-K3dXP66Unw3r0ukzYcc2MP99ns5pNfsFtfv36V-PrkLgnzDu-ANW9ShcvCdZ8vo2fwDPsTtxQUH6aoSRKSVcSSXH7FEwXUEm0NWohYWeZedQR68YCz1gFtuAvvOmdK1thSLEv7Alo77svvRiXBlSxQ==&uniplatform=NZKPT&language=CHS"
+  ]
+}

cnks-0.3.0/pyproject.toml

@@ -0,0 +1,31 @@
+[project]
+name = "cnks"
+version = "0.3.0"
+description = "中国知网搜索与引文处理系统"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "mcp[cli]>=1.6.0",
+    "playwright>=1.40.0",
+    "python-dotenv>=1.0.0",
+]
+
+[[project.authors]]
+name = "bai-z-l"
+email = "b@iziliang.com"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project.scripts]
+cnks = "src.main:main"       # 现在只启动server
+cnks-server = "src.server:main"
+cnks-worker-test = "src.worker:main"  # 仅用于测试目的
+cnks-client = "src.client:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src"]
+
+[tool.setuptools]
+packages = ["src"]

cnks-0.3.0/src/ThisIsAServerSample.py

@@ -0,0 +1,377 @@
+import asyncio
+
+from mcp.server.models import InitializationOptions
+import mcp.types as types
+from mcp.server import NotificationOptions, Server
+from pydantic import AnyUrl
+import mcp.server.stdio
+
+server = Server("playwright-server")
+
+@server.list_resources()
+async def handle_list_resources() -> list[types.Resource]:
+    """
+    List available note resources.
+    Each note is exposed as a resource with a custom note:// URI scheme.
+    """
+    return []
+
+@server.read_resource()
+async def handle_read_resource(uri: AnyUrl) -> str:
+    """
+    Read a specific note's content by its URI.
+    The note name is extracted from the URI host component.
+    """
+    raise ValueError(f"Unsupported URI scheme: {uri.scheme}")
+
+
+@server.list_prompts()
+async def handle_list_prompts() -> list[types.Prompt]:
+    """
+    List available prompts.
+    Each prompt can have optional arguments to customize its behavior.
+    """
+    return []
+
+@server.get_prompt()
+async def handle_get_prompt(
+    name: str, arguments: dict[str, str] | None
+) -> types.GetPromptResult:
+    """
+    Generate a prompt by combining arguments with server state.
+    The prompt includes all current notes and can be customized via arguments.
+    """
+    raise ValueError(f"Unknown prompt: {name}")
+
+
+@server.list_tools()
+async def handle_list_tools() -> list[types.Tool]:
+    """
+    List available tools.
+    Each tool specifies its arguments using JSON Schema validation.
+    """
+    return [
+        # types.Tool(
+        #     name="playwright_new_session",
+        #     description="Create a new browser session",
+        #     inputSchema={
+        #         "type": "object",
+        #         "properties": {
+        #             "url": {"type": "string", "description": "Initial URL to navigate to"}
+        #         }
+        #     }
+        # ),
+        types.Tool(
+            name="playwright_navigate",
+            description="Navigate to a URL,thip op will auto create a session",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "url": {"type": "string"}
+                },
+                "required": ["url"]
+            }
+        ),
+        types.Tool(
+            name="playwright_screenshot",
+            description="Take a screenshot of the current page or a specific element",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "name": {"type": "string"},
+                    "selector": {"type": "string", "description": "CSS selector for element to screenshot,null is full page"},
+                },
+                "required": ["name"]
+            }
+        ),
+        types.Tool(
+            name="playwright_click",
+            description="Click an element on the page using CSS selector",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "selector": {"type": "string", "description": "CSS selector for element to click"}
+                },
+                "required": ["selector"]
+            }
+        ),
+        types.Tool(
+            name="playwright_fill",
+            description="Fill out an input field",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "selector": {"type": "string", "description": "CSS selector for input field"},
+                    "value": {"type": "string", "description": "Value to fill"}
+                },
+                "required": ["selector", "value"]
+            }
+        ),
+        types.Tool(
+            name="playwright_evaluate",
+            description="Execute JavaScript in the browser console",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "script": {"type": "string", "description": "JavaScript code to execute"}
+                },
+                "required": ["script"]
+            }
+        ),
+        types.Tool(
+            name="playwright_click_text",
+            description="Click an element on the page by its text content",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                    "text": {"type": "string", "description": "Text content of the element to click"}
+                },
+                "required": ["text"]
+            }
+        ),
+         types.Tool(
+            name="playwright_get_text_content",
+            description="Get the text content of all elements",
+            inputSchema={
+                "type": "object",
+                "properties": {
+                },
+            }
+        ),
+        types.Tool(
+            name="playwright_get_html_content",
+            description="Get the HTML content of the page",
+             inputSchema={
+                "type": "object",
+                "properties": {
+                    "selector": {"type": "string", "description": "CSS selector for the element"}
+                },
+                "required": ["selector"]
+            }
+        )
+    ]
+
+import uuid
+from playwright.async_api import async_playwright
+import base64
+import os
+
+import asyncio
+
+def update_page_after_click(func):
+    async def wrapper(self, name: str, arguments: dict | None):
+        if not self._sessions:
+            return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        
+        new_page_future = asyncio.ensure_future(page.context.wait_for_event("page", timeout=3000))
+        
+        result = await func(self, name, arguments)
+        try:
+            new_page = await new_page_future
+            await new_page.wait_for_load_state()
+            self._sessions[session_id]["page"] = new_page
+        except:
+            pass
+            # if page.url != self._sessions[session_id]["page"].url:
+            #     await page.wait_for_load_state()
+            #     self._sessions[session_id]["page"] = page
+        
+        return result
+    return wrapper
+
+class ToolHandler:
+    _sessions: dict[str, any] = {}
+    _playwright: any = None
+
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        raise NotImplementedError
+
+class NewSessionToolHandler(ToolHandler):
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        self._playwright = await async_playwright().start()
+        browser = await self._playwright.chromium.launch(headless=False)
+        page = await browser.new_page()
+        session_id = str(uuid.uuid4())
+        self._sessions[session_id] = {"browser": browser, "page": page}
+        url = arguments.get("url")
+        if url:
+            if not url.startswith("http://") and not url.startswith("https://"):
+                url = "https://" + url
+            await page.goto(url)
+        return [types.TextContent(type="text", text="succ")]
+
+class NavigateToolHandler(ToolHandler):
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        if not self._sessions:
+            await NewSessionToolHandler().handle("",{})
+            # return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        url = arguments.get("url")
+        if not url.startswith("http://") and not url.startswith("https://"):
+            url = "https://" + url
+        await page.goto(url)
+        text_content=await GetTextContentToolHandler().handle("",{})
+        return [types.TextContent(type="text", text=f"Navigated to {url}\npage_text_content[:200]:\n\n{text_content[:200]}")]
+
+class ScreenshotToolHandler(ToolHandler):
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        if not self._sessions:
+            return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        name = arguments.get("name")
+        selector = arguments.get("selector")
+        # full_page = arguments.get("fullPage", False)
+        if selector:
+            element = await page.locator(selector)
+            await element.screenshot(path=f"{name}.png")
+        else:
+            await page.screenshot(path=f"{name}.png", full_page=True)
+        with open(f"{name}.png", "rb") as image_file:
+            encoded_string = base64.b64encode(image_file.read()).decode("utf-8")
+        os.remove(f"{name}.png")
+        return [types.ImageContent(type="image", data=encoded_string, mimeType="image/png")]
+
+class ClickToolHandler(ToolHandler):
+    @update_page_after_click
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        if not self._sessions:
+            return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        selector = arguments.get("selector")
+        await page.locator(selector).click()
+        return [types.TextContent(type="text", text=f"Clicked element with selector {selector}")]
+
+class FillToolHandler(ToolHandler):
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        if not self._sessions:
+            return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        selector = arguments.get("selector")
+        value = arguments.get("value")
+        await page.locator(selector).fill(value)
+        return [types.TextContent(type="text", text=f"Filled element with selector {selector} with value {value}")]
+
+class EvaluateToolHandler(ToolHandler):
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        if not self._sessions:
+            return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        script = arguments.get("script")
+        result = await page.evaluate(script)
+        return [types.TextContent(type="text", text=f"Evaluated script, result: {result}")]
+
+class ClickTextToolHandler(ToolHandler):
+    @update_page_after_click
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        if not self._sessions:
+            return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        text = arguments.get("text")
+        await page.locator(f"text={text}").nth(0).click()
+        return [types.TextContent(type="text", text=f"Clicked element with text {text}")]
+
+class GetTextContentToolHandler(ToolHandler):
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        if not self._sessions:
+            return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        # text_contents = await page.locator('body').all_inner_texts()
+
+
+        async def get_unique_texts_js(page):
+            unique_texts = await page.evaluate('''() => {
+            var elements = Array.from(document.querySelectorAll('*')); // 先选择所有元素，再进行过滤
+            var uniqueTexts = new Set();
+
+            for (var element of elements) {
+                if (element.offsetWidth > 0 || element.offsetHeight > 0) { // 判断是否可见
+                    var childrenCount = element.querySelectorAll('*').length;
+                    if (childrenCount <= 3) {
+                        var innerText = element.innerText ? element.innerText.trim() : '';
+                        if (innerText && innerText.length <= 1000) {
+                            uniqueTexts.add(innerText);
+                        }
+                        var value = element.getAttribute('value');
+                        if (value) {
+                            uniqueTexts.add(value);
+                        }
+                    }
+                }
+            }
+            //console.log( Array.from(uniqueTexts));
+            return Array.from(uniqueTexts);
+        }
+        ''')
+            return unique_texts
+
+        # 使用示例
+        text_contents = await get_unique_texts_js(page)
+
+
+
+        return [types.TextContent(type="text", text=f"Text content of all elements: {text_contents}")]
+
+class GetHtmlContentToolHandler(ToolHandler):
+    async def handle(self, name: str, arguments: dict | None) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+        if not self._sessions:
+            return [types.TextContent(type="text", text="No active session. Please create a new session first.")]
+        session_id = list(self._sessions.keys())[-1]
+        page = self._sessions[session_id]["page"]
+        selector = arguments.get("selector")
+        html_content = await page.locator(selector).inner_html()
+        return [types.TextContent(type="text", text=f"HTML content of element with selector {selector}: {html_content}")]
+
+
+tool_handlers = {
+    "playwright_navigate": NavigateToolHandler(),
+    "playwright_screenshot": ScreenshotToolHandler(),
+    "playwright_click": ClickToolHandler(),
+    "playwright_fill": FillToolHandler(),
+    "playwright_evaluate": EvaluateToolHandler(),
+    "playwright_click_text": ClickTextToolHandler(),
+    "playwright_get_text_content": GetTextContentToolHandler(),
+    "playwright_get_html_content": GetHtmlContentToolHandler(),
+    "playwright_new_session":NewSessionToolHandler(),
+}
+
+
+@server.call_tool()
+async def handle_call_tool(
+    name: str, arguments: dict | None
+) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
+    """
+    Handle tool execution requests.
+    Tools can modify server state and notify clients of changes.
+    """
+    if name in tool_handlers:
+        return await tool_handlers[name].handle(name, arguments)
+    else:
+        raise ValueError(f"Unknown tool: {name}")
+
+async def main():
+    # Run the server using stdin/stdout streams
+    async with mcp.server.stdio.stdio_server() as (read_stream, write_stream):
+        await server.run(
+            read_stream,
+            write_stream,
+            InitializationOptions(
+                server_name="playwright-plus-server",
+                server_version="0.1.0",
+                capabilities=server.get_capabilities(
+                    notification_options=NotificationOptions(),
+                    experimental_capabilities={},
+                ),
+            ),
+        )
+
+if __name__ == "__main__":
+    asyncio.run(main())

cnks-0.3.0/src/__init__.py

@@ -0,0 +1,7 @@
+"""
+CNKS - 中国知网搜索与引文处理系统
+
+这是一个基于MCP（模块化通信协议）架构的知网搜索和引文处理系统。
+"""
+
+__version__ = "0.1.0"