mcp-query-table 0.3.2__py3-none-any.whl → 0.3.4__py3-none-any.whl

mcp_query_table/__init__.py

@@ -3,4 +3,5 @@ from ._version import __version__
 from .enums import QueryType, Site, Provider
 from .tool import BrowserManager, query, chat
 
-TIMEOUT = 1000 * 60 * 2  # 2分钟，在抓取EventStream数据时等待数据返回，防止外层30秒超时
+TIMEOUT = 1000 * 60 * 3  # 3分钟，在抓取EventStream数据时等待数据返回，防止外层30秒超时
+TIMEOUT_60 = 1000 * 60  # 1分钟

mcp_query_table/_version.py

@@ -1 +1 @@
-__version__ = "0.3.2"
+__version__ = "0.3.4"

mcp_query_table/enums.py

@@ -26,3 +26,4 @@ class Provider(Enum):
     Nami = '纳米搜索'  # 360 纳米搜索
     YuanBao = '腾讯元宝'  # 腾讯元宝
     BaiDu = '百度AI搜索'  # 百度AI搜索
+    # YiYan = '文心一言'  # 百度文心一言

mcp_query_table/providers/baidu.py

@@ -8,10 +8,11 @@ import json
 from playwright.async_api import Page
 
 import mcp_query_table
-from mcp_query_table.tool import GlobalVars
+from mcp_query_table.tool import GlobalVars, split_images
 
 _PAGE0_ = "https://chat.baidu.com/search"
 _PAGE1_ = "https://chat.baidu.com/aichat/api/conversation"
+_PAGE2_ = "https://chat.baidu.com/aichat/api/file/upload"
 
 G = GlobalVars()
 
@@ -66,13 +67,32 @@ async def on_route(route):
 async def chat(page: Page,
                prompt: str,
                create: bool,
+               files: list[str],
                ) -> str:
+    async def on_file_chooser(file_chooser):
+        # 文件选择对话框
+        await file_chooser.set_files(files)
+
     if not page.url.startswith(_PAGE0_):
         create = True
 
     if create:
         await page.goto(_PAGE0_)
 
+    # 文件上传
+    if len(files) > 0:
+        imgs, docs = split_images(files)
+        assert len(imgs) == 0 or len(docs) == 0, "不能同时包含图片和文档"
+
+        page.on("filechooser", on_file_chooser)
+        async with page.expect_response(f"{_PAGE2_}*", timeout=mcp_query_table.TIMEOUT_60) as response_info:
+            if len(imgs) > 0:
+                await page.locator(".cs-input-upload-icon").last.click()
+            else:
+                await page.locator(".cs-input-upload-icon").first.click()
+        page.remove_listener("filechooser", on_file_chooser)
+
+    # 提交问题
     await page.route(_PAGE1_, on_route)
     async with page.expect_response(_PAGE1_, timeout=mcp_query_table.TIMEOUT) as response_info:
         await page.locator("#chat-input-box").fill(prompt)

mcp_query_table/providers/n.py

@@ -6,11 +6,12 @@ import json
 from playwright.async_api import Page
 
 import mcp_query_table
-from mcp_query_table.tool import GlobalVars
+from mcp_query_table.tool import GlobalVars, is_image
 
 _PAGE0_ = "https://www.n.cn"
 _PAGE1_ = "https://www.n.cn/search"
-_PAGE2_ = "https://www.n.cn/api/common/chat/v2"
+_PAGE2_ = "https://www.n.cn/api/common/chat/v2"  # 对话
+_PAGE3_ = "https://www.n.cn/api/image/upload"  # 上传图片
 
 G = GlobalVars()
 
@@ -48,7 +49,7 @@ def read_event_stream(text):
 
 
 async def on_response(response):
-    if response == _PAGE2_:
+    if response.url == _PAGE2_:
         # print("on_response", response.url)
         text = await response.text()
         G.set_text(read_event_stream(text))
@@ -57,14 +58,43 @@ async def on_response(response):
 async def chat(page: Page,
                prompt: str,
                create: bool,
+               files: list[str],
                ) -> str:
+    """
+
+    Parameters
+    ----------
+    page : playwright.async_api.Page
+        页面
+    prompt : str
+        问题
+    create : bool
+        是否创建新的对话
+    files : list[str] | None
+        上传的文件列表。目前仅支持上传图片
+
+    Returns
+    -------
+    str
+        回答
+    """
     if not create:
         if not page.url.startswith(_PAGE1_):
             create = True
+        if len(files) > 0:
+            create = True
+
+    for file in files:
+        assert is_image(file), f"仅支持上传图片，{file}不是图片"
 
     if create:
-        await page.goto(_PAGE0_)
         name = "输入任何问题"
+
+        await page.goto(_PAGE0_)
+        if len(files) > 0:
+            # 只能在新会话中上传文件
+            async with page.expect_response(_PAGE3_, timeout=mcp_query_table.TIMEOUT_60) as response_info:
+                await page.locator("input[type=\"file\"]").set_input_files(files)
     else:
         name = "提出后续问题，Enter发送，Shift+Enter 换行"
 

mcp_query_table/providers/yuanbao.py

@@ -2,14 +2,16 @@
 腾讯元宝
 """
 import json
+import re
 
 from playwright.async_api import Page
 
 import mcp_query_table
-from mcp_query_table.tool import GlobalVars
+from mcp_query_table.tool import GlobalVars, split_images
 
 _PAGE0_ = "https://yuanbao.tencent.com/"
 _PAGE1_ = "https://yuanbao.tencent.com/api/chat"
+_PAGE2_ = "https://yuanbao.tencent.com/api/resource/genUploadInfo"
 
 G = GlobalVars()
 
@@ -65,6 +67,7 @@ async def on_route(route):
 async def chat(page: Page,
                prompt: str,
                create: bool,
+               files: list[str]
                ) -> str:
     if not page.url.startswith(_PAGE0_):
         create = True
@@ -72,6 +75,21 @@ async def chat(page: Page,
     if create:
         await page.goto(_PAGE0_)
 
+    if len(files) > 0:
+        imgs, docs = split_images(files)
+        assert len(imgs) == 0 or len(docs) == 0, "不能同时包含图片和文档"
+
+        # 点击上传文件按钮，才会出现上传文件的input
+        await page.get_by_role("button").filter(has_text=re.compile(r"^$")).last.click()
+
+        # 上传文件
+        async with page.expect_response(_PAGE2_, timeout=mcp_query_table.TIMEOUT_60) as response_info:
+            if len(imgs) > 0:
+                await page.locator("input[type=\"file\"]").nth(-2).set_input_files(files)
+            else:
+                await page.locator("input[type=\"file\"]").last.set_input_files(files)
+
+    # 提问
     await page.route(f"{_PAGE1_}/*", on_route)
     async with page.expect_response(f"{_PAGE1_}/*", timeout=mcp_query_table.TIMEOUT) as response_info:
         textbox = page.locator(".ql-editor")

mcp_query_table/server.py

@@ -1,4 +1,4 @@
-from typing import Annotated, Optional
+from typing import Annotated, Optional, List
 
 from loguru import logger
 from mcp.server.fastmcp import FastMCP
@@ -29,9 +29,9 @@ class QueryServer:
         if self.format == 'json':
             return df.to_json(force_ascii=False, indent=2)
 
-    async def chat(self, prompt: str, create: bool, provider: Provider):
+    async def chat(self, prompt: str, create: bool, files: List[str], provider: Provider):
         page = await self.browser.get_page()
-        txt = await qt_chat(page, prompt, create, provider)
+        txt = await qt_chat(page, prompt, create, files, provider)
         self.browser.release_page(page)
         return txt
 
@@ -57,10 +57,11 @@ async def query(
 async def chat(
         prompt: Annotated[str, Field(description="提示词。如：`9.9大还是9.11大？`")],
         create: Annotated[bool, Field(default=False, description="是否创建新对话")],
+        files: Annotated[List[str], Field(default=None, description="上传的文件列表。不同网站支持程度不同")],
         provider: Annotated[
             Provider, Field(default=Provider.Nami, description="提供商。支持`纳米搜索`、`腾讯元宝`、`百度AI搜索`")]
 ) -> str:
-    return await qsv.chat(prompt, create, provider)
+    return await qsv.chat(prompt, create, files, provider)
 
 
 def serve(format, cdp_endpoint, executable_path, transport, host, port):

mcp_query_table/tool.py

@@ -2,7 +2,7 @@ import subprocess
 import sys
 import time
 from pathlib import Path
-from typing import Optional
+from typing import Optional, List, Tuple
 
 import pandas as pd
 from loguru import logger
@@ -142,6 +142,12 @@ class BrowserManager:
             # 防止开发者工具被使用
             if page.url.startswith("devtools://"):
                 continue
+            # 防止chrome扩展被使用
+            if page.url.startswith("chrome-extension://"):
+                continue
+            # 防止edge扩展被使用
+            if page.url.startswith("extension://"):
+                continue
             self.pages.append(page)
 
     async def _try_launch(self) -> None:
@@ -230,6 +236,7 @@ async def chat(
         page: Page,
         prompt: str = "9.9大还是9.11大？",
         create: bool = False,
+        files: list[str] | None = None,
         provider: Provider = Provider.Nami) -> str:
     """大语言对话
 
@@ -241,6 +248,8 @@ async def chat(
         对话内容, by default "9.9大还是9.11大？"
     create : bool, optional
         是否创建新对话, by default False
+    files : list[str] | None, optional
+        上传的文件列表。不同网站支持程度不同
     provider : Provider, optional
         提供商, by default Provider.N
 
@@ -250,14 +259,37 @@ async def chat(
         对话结果
 
     """
+    # 空列表转None
+    if files is None:
+        files = []
+
     if provider == Provider.Nami:
         from mcp_query_table.providers.n import chat
-        return await chat(page, prompt, create)
+        return await chat(page, prompt, create, files)
     if provider == Provider.YuanBao:
         from mcp_query_table.providers.yuanbao import chat
-        return await chat(page, prompt, create)
+        return await chat(page, prompt, create, files)
     if provider == Provider.BaiDu:
         from mcp_query_table.providers.baidu import chat
-        return await chat(page, prompt, create)
+        return await chat(page, prompt, create, files)
 
     raise ValueError(f"未支持的提供商:{provider}")
+
+
+def is_image(path: str) -> bool:
+    """判断是否是图片文件"""
+    img_ext = ['.jpg', '.jpeg', '.png', '.gif', '.bmp', '.webp']
+    ext = Path(path).suffix.lower()
+    return ext in img_ext
+
+
+def split_images(files: List[str]) -> Tuple[List[str], List[str]]:
+    """图片列表分成两部分"""
+    imgs = []
+    docs = []
+    for f in files:
+        if is_image(f):
+            imgs.append(f)
+        else:
+            docs.append(f)
+    return imgs, docs

{mcp_query_table-0.3.2.dist-info → mcp_query_table-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mcp_query_table
-Version: 0.3.2
+Version: 0.3.4
 Summary: query table from website, support MCP
 Author-email: wukan <wu-kan@163.com>
 License: MIT License
@@ -132,7 +132,8 @@ if __name__ == '__main__':
 
 确保可以在控制台中执行`python -m mcp_query_table -h`。如果不能，可能要先`pip install mcp_query_table`
 
-在`Cline`中可以配置如下。其中`command`是`python`的绝对路径，`executable_path`是`Chrome`的绝对路径。
+在`Cline`中可以配置如下。其中`command`是`python`的绝对路径，`executable_path`是`Chrome`的绝对路径，`timeout`是超时时间，单位为秒。
+在各`AI`平台中由于返回时间常需1分钟以上，所以需要设置大的超时时间。
 
 ### STDIO方式
 
@@ -140,6 +141,7 @@ if __name__ == '__main__':
 {
   "mcpServers": {
     "mcp_query_table": {
+      "timeout": 300,
       "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
       "args": [
         "-m",
@@ -170,6 +172,7 @@ python -m mcp_query_table --format markdown --transport sse --port 8000
 {
   "mcpServers": {
     "mcp_query_table": {
+      "timeout": 300,
       "url": "http://127.0.0.1:8000/sse"
     }
   }
@@ -182,8 +185,8 @@ python -m mcp_query_table --format markdown --transport sse --port 8000
 npx @modelcontextprotocol/inspector python -m mcp_query_table --format markdown
 ```
 
-打开浏览器并翻页是一个比较耗时的操作，会导致`MCP Inspector`页面超时，可以`http://localhost:5173/?timeout=600000`
-表示超时时间为600秒
+打开浏览器并翻页是一个比较耗时的操作，会导致`MCP Inspector`页面超时，可以`http://localhost:5173/?timeout=300000`
+表示超时时间为300秒
 
 第一次尝试编写`MCP`项目，可能会有各种问题，欢迎大家交流。
 

mcp_query_table-0.3.4.dist-info/RECORD

@@ -0,0 +1,19 @@
+mcp_query_table/__init__.py,sha256=NmnAOKcJjQoeTJMbIY79-JsNNdj-PJpnZ-x8MPjpE4o,272
+mcp_query_table/__main__.py,sha256=W3tMnZZTvkhjlLHmSYHng3CTvYX6-LjyaBDhf-ypH7w,1186
+mcp_query_table/_version.py,sha256=oYLGMpySamd16KLiaBTfRyrAS7_oyp-TOEHmzmeumwg,22
+mcp_query_table/enums.py,sha256=Hen0X1f2of69f08epun6HvYIgbpw_rf8BvoRQ184kS4,679
+mcp_query_table/server.py,sha256=oV8CSi-EW5-xlPn38R1wLu7U-pCHgAJci1W8rJFsXSk,3430
+mcp_query_table/tool.py,sha256=kCnfBNv1T88gNnFLsz-ZjXNuxbzhGvLPcPfNkkJ7Dyg,9096
+mcp_query_table/providers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mcp_query_table/providers/baidu.py,sha256=q0vZxl_UTO8v4LbznwT2b1hM-00jswDR8CqB3tc-X9U,3389
+mcp_query_table/providers/n.py,sha256=J0Xo-BlXveIQdDbwKkuEP4I1mfAr8i1rviD0UTztI9Y,3009
+mcp_query_table/providers/yuanbao.py,sha256=4DzoLfgg7dSP1BhiS_tKyTQ0byc1zHRuZQjyq-2pZfQ,3148
+mcp_query_table/sites/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+mcp_query_table/sites/eastmoney.py,sha256=LImjpYVuM5YnXwnNzB2hkKfHofocZZScetGqMOCHZpk,4477
+mcp_query_table/sites/iwencai.py,sha256=g56pj3pbxu4mXLNnaaS3Hdx-DvEy_9OBrQJe26z4z08,5059
+mcp_query_table/sites/tdx.py,sha256=RIUQaB7Tn4AVyWaevk9SzTKIDwVO2f9erIlI-adXPLY,4126
+mcp_query_table-0.3.4.dist-info/licenses/LICENSE,sha256=rbvv_CTd7biGwT21tvhgQ2zkbPFXOoON7WFQWEdElBA,1063
+mcp_query_table-0.3.4.dist-info/METADATA,sha256=gc0VlBZxpcc_uPxkRA0WXdYNQ0cJeP3K5oTRKx5_4VU,8372
+mcp_query_table-0.3.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+mcp_query_table-0.3.4.dist-info/top_level.txt,sha256=5M_8dkO1USOX7_EWbWS6O_TEsZ5yo-AodFNKeUEgvEQ,16
+mcp_query_table-0.3.4.dist-info/RECORD,,

mcp_query_table-0.3.2.dist-info/RECORD

@@ -1,19 +0,0 @@
-mcp_query_table/__init__.py,sha256=gNXLL6MtH667HEdsUbJ4OAbGqwYO1dLdkqorV3-RtLM,238
-mcp_query_table/__main__.py,sha256=W3tMnZZTvkhjlLHmSYHng3CTvYX6-LjyaBDhf-ypH7w,1186
-mcp_query_table/_version.py,sha256=vNiWJ14r_cw5t_7UDqDQIVZvladKFGyHH2avsLpN7Vg,22
-mcp_query_table/enums.py,sha256=l-6uuGyniMVJGNh4tx9ZtktIjKSqyoHBHCJAdaOvczY,628
-mcp_query_table/server.py,sha256=l8tt-1UNjTc5A8r3jGPt5REyCzU7N1t9_ndNJmThJ9k,3264
-mcp_query_table/tool.py,sha256=X-mopuv0QRiQ2J_VLDcVWkH8ynXVTPgl6vlaYnDKnWA,8143
-mcp_query_table/providers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mcp_query_table/providers/baidu.py,sha256=N7D2mWzVfNJ2dbAMbdHisoBdac17-joyeF7BkFhLKPQ,2560
-mcp_query_table/providers/n.py,sha256=H8hXgai8GDj3KizS2du4ix28PZlDaD6BkoyaheJnYd4,2152
-mcp_query_table/providers/yuanbao.py,sha256=eTcOeV1ERFq7x5EgThBe9zsSodriGy7-eIWJRqcgwYU,2350
-mcp_query_table/sites/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-mcp_query_table/sites/eastmoney.py,sha256=LImjpYVuM5YnXwnNzB2hkKfHofocZZScetGqMOCHZpk,4477
-mcp_query_table/sites/iwencai.py,sha256=g56pj3pbxu4mXLNnaaS3Hdx-DvEy_9OBrQJe26z4z08,5059
-mcp_query_table/sites/tdx.py,sha256=RIUQaB7Tn4AVyWaevk9SzTKIDwVO2f9erIlI-adXPLY,4126
-mcp_query_table-0.3.2.dist-info/licenses/LICENSE,sha256=rbvv_CTd7biGwT21tvhgQ2zkbPFXOoON7WFQWEdElBA,1063
-mcp_query_table-0.3.2.dist-info/METADATA,sha256=D9kCuwRBvBsn1RRc0ysYwSPia_94ferz8UVlye68GwM,8187
-mcp_query_table-0.3.2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-mcp_query_table-0.3.2.dist-info/top_level.txt,sha256=5M_8dkO1USOX7_EWbWS6O_TEsZ5yo-AodFNKeUEgvEQ,16
-mcp_query_table-0.3.2.dist-info/RECORD,,