mcp-query-table 0.2.6__py3-none-any.whl

mcp_query_table/__init__.py

@@ -0,0 +1,4 @@
+from ._version import __version__
+
+from .enums import QueryType, Site
+from .tool import BrowserManager, query

mcp_query_table/__main__.py

@@ -0,0 +1,29 @@
+from mcp_query_table.server import serve
+
+
+def main():
+    import argparse
+
+    parser = argparse.ArgumentParser(
+        description="query table from website",
+    )
+
+    parser.add_argument("--format", type=str, help="输出格式",
+                        default='markdown', choices=['markdown', 'csv', 'json'])
+    parser.add_argument("--cdp_port", type=int, help="浏览器远程调试端口",
+                        default=9222)
+    parser.add_argument("--browser_path", type=str, help="浏览器类型",
+                        default=r'C:\Program Files\Google\Chrome\Application\chrome.exe')
+
+    parser.add_argument("--transport", type=str, help="传输类型",
+                        default='stdio', choices=['stdio', 'sse'])
+    parser.add_argument("--mcp_host", type=str, help="MCP服务端地址",
+                        default='0.0.0.0')
+    parser.add_argument("--mcp_port", type=int, help="MCP服务端端口",
+                        default='8000')
+    args = parser.parse_args()
+    serve(args.format, args.cdp_port, args.browser_path, args.transport, args.mcp_host, args.mcp_port)
+
+
+if __name__ == "__main__":
+    main()

mcp_query_table/_version.py

@@ -0,0 +1 @@
+__version__ = "0.2.6"

mcp_query_table/enums.py

@@ -0,0 +1,21 @@
+from enum import Enum
+
+
+class QueryType(Enum):
+    """查询类型"""
+    CNStock = 'A股'
+    HKStock = '港股'
+    USStock = '美股'
+    Index = '指数'
+    Fund = '基金'
+    ETF = 'ETF'
+    ConBond = '可转债'
+    Board = '板块'
+    Info = '资讯'
+
+
+class Site(Enum):
+    """站点"""
+    EastMoney = '东方财富'  # 东方财富 条件选股
+    TDX = '通达信'  # 通达信 问小达
+    THS = '同花顺'  # 同花顺 i问财

mcp_query_table/server.py

@@ -0,0 +1,56 @@
+from typing import Annotated, Optional
+
+from loguru import logger
+from mcp.server.fastmcp import FastMCP
+from pydantic import Field
+
+from mcp_query_table import QueryType, Site, query as query_table_query
+from mcp_query_table.tool import BrowserManager
+
+
+class QueryServer:
+    def __init__(self, format: str = 'markdown', port: int = 9222, browser_path: Optional[str] = None) -> None:
+        self.format: str = format
+        self.browser = BrowserManager(port=port, browser_path=browser_path, debug=False)
+
+    async def query(self, query_input: str, query_type: QueryType, max_page: int, site: Site):
+        page = await self.browser.get_page()
+        df = await query_table_query(page, query_input, query_type, max_page, site)
+        self.browser.release_page(page)
+
+        if self.format == 'csv':
+            return df.to_csv()
+        if self.format == 'markdown':
+            return df.to_markdown()
+        if self.format == 'json':
+            return df.to_json(force_ascii=False, indent=2)
+
+
+# !!!log_level这一句非常重要，否则Cline/MCP Server/Tools工作不正常
+mcp = FastMCP("query_table_mcp", log_level="ERROR")
+qsv = QueryServer()
+
+
+@mcp.tool(description="查询金融表格数据")
+async def query(
+        query_input: Annotated[
+            str, Field(description="查询条件。支持复杂查询，如：`2024年涨幅最大的100只股票按市值排名`")],
+        query_type: Annotated[QueryType, Field(default=QueryType.CNStock,
+                                               description="查询类型。支持`A股`、`指数`、`基金`、`港股`、`美股`等")],
+        max_page: Annotated[int, Field(default=1, ge=1, le=10, description="最大页数。只查第一页即可")],
+        site: Annotated[Site, Field(default=Site.THS, description="站点。支持`东方财富`、`通达信`、`同花顺`")]
+) -> str:
+    return await qsv.query(query_input, query_type, max_page, site)
+
+
+def serve(format, cdp_port, browser_path, transport, mcp_host, mcp_port):
+    qsv.format = format
+    qsv.port = cdp_port
+    qsv.browser_path = browser_path
+    logger.info("serve:{},{},{},{}", qsv.format, qsv.port, qsv.browser_path, transport)
+    if transport == 'sse':
+        logger.info("mcp:{},{}:{}", transport, mcp_host, mcp_port)
+
+    mcp.settings.host = mcp_host
+    mcp.settings.port = mcp_port
+    mcp.run(transport=transport)

mcp_query_table/sites/eastmoney.py

@@ -0,0 +1,144 @@
+"""
+东方财富 条件选股
+https://xuangu.eastmoney.com/
+
+1. 部分数据中包含中文单位，如万亿等，导致无法转换为数字，如VOLUME
+2. 东财翻页需要提前手工登录
+3. 东财翻页是页面已经翻了，然后等数据来更新，懒加载
+"""
+import re
+
+import pandas as pd
+from loguru import logger
+from playwright.async_api import Page
+
+from mcp_query_table.enums import QueryType
+
+# 查询结果
+# 'https://np-pick-b.eastmoney.com/api/smart-tag/stock/v3/pw/search-code'
+# 'https://np-pick-b.eastmoney.com/api/smart-tag/fund/v3/pw/search-code'
+# 'https://np-pick-b.eastmoney.com/api/smart-tag/hk/v3/pw/search-code'
+# 'https://np-pick-b.eastmoney.com/api/smart-tag/cb/v3/pw/search-code'
+# 'https://np-pick-b.eastmoney.com/api/smart-tag/etf/v3/pw/search-code'
+# 'https://np-pick-b.eastmoney.com/api/smart-tag/bkc/v3/pw/search-code'
+# 'https://np-tjxg-b.eastmoney.com/api/smart-tag/bkc/v3/pw/search-code'
+_PAGE1_ = 'https://*.eastmoney.com/api/smart-tag/*/v3/pw/search-code'
+
+_type_ = {
+    QueryType.CNStock: 'stock',
+    QueryType.Fund: 'fund',
+    QueryType.HKStock: 'hk',
+    QueryType.ConBond: 'cb',
+    QueryType.ETF: 'etf',
+    QueryType.Board: 'bk',  # 比较坑，bkc和bkc的区别
+}
+
+
+def convert_type(type):
+    if type == 'Double':
+        return float
+    if type == 'String':
+        return str
+    if type == 'Long':
+        return int
+    if type == 'Boolean':
+        return bool
+    if type == 'INT':  # TODO 好像未出现过
+        return int
+    return type
+
+
+class Pagination:
+    def __init__(self):
+        self.datas = {}
+        self.pageNo = 1
+        self.pageSize = 100
+        self.total = 1024
+        self.columns = []
+        self.datas = {}
+
+    def reset(self):
+        self.datas = {}
+
+    def update(self, pageNo, pageSize, total, columns, dataList):
+        self.pageNo = pageNo
+        self.pageSize = pageSize
+        self.total = total
+        self.columns = columns
+        self.datas[self.pageNo] = dataList
+
+    def has_next(self, max_page):
+        c1 = self.pageNo * self.pageSize < self.total
+        c2 = self.pageNo < max_page
+        return c1 & c2
+
+    def current(self):
+        return self.pageNo
+
+    def get_list(self):
+        datas = []
+        for k, v in self.datas.items():
+            datas.extend(v)
+        return datas
+
+    def get_dataframe(self):
+        columns = {x['key']: x['title'] for x in self.columns}
+        dtypes = {x['key']: convert_type(x['dataType']) for x in self.columns}
+
+        df = pd.DataFrame(self.get_list())
+        for k, v in dtypes.items():
+            if k == 'SERIAL':
+                df[k] = df[k].astype(int)
+                continue
+            if isinstance(v, str):
+                logger.info("未识别的数据类型 {}:{}", k, v)
+                continue
+            try:
+                df[k] = df[k].astype(v)
+            except ValueError:
+                logger.info("转换失败 {}:{}", k, v)
+
+        return df.rename(columns=columns)
+
+
+P = Pagination()
+
+
+def search_code(json_data):
+    total = json_data['data']['result']['total']
+    columns = json_data['data']['result']['columns']
+    dataList = json_data['data']['result']['dataList']
+    return total, columns, dataList
+
+
+async def on_response(response):
+    post_data_json = response.request.post_data_json
+    pageNo = post_data_json['pageNo']
+    pageSize = post_data_json['pageSize']
+    P.update(pageNo, pageSize, *search_code(await response.json()))
+
+
+async def query(page: Page,
+                q: str = "收盘价>100元",
+                type_: QueryType = 'stock',
+                max_page: int = 5) -> pd.DataFrame:
+    type = _type_.get(type_, None)
+    assert type is not None, f"不支持的类型:{type_}"
+
+    await page.route(re.compile(r'.*\.(?:jpg|jpeg|png|gif|webp)(?:$|\?)'), lambda route: route.abort())
+
+    P.reset()
+    async with page.expect_response(_PAGE1_) as response_info:
+        # 这里不用处理输入编码问题
+        await page.goto(f"https://xuangu.eastmoney.com/Result?q={q}&type={type}", wait_until="load")
+    await on_response(await response_info.value)
+
+    while P.has_next(max_page):
+        logger.info("当前页为:{}, 点击`下一页`", P.current())
+
+        # 这种写法解决了懒加载问题
+        async with page.expect_response(_PAGE1_) as response_info:
+            await page.get_by_role("button", name="下一页").click()
+        await on_response(await response_info.value)
+
+    return P.get_dataframe()

mcp_query_table/sites/iwencai.py

@@ -0,0 +1,171 @@
+"""
+同花顺 i问财
+https://www.iwencai.com/
+
+1. 一定要保证浏览器宽度>768，防止界面变成适应手机
+
+"""
+import re
+
+import pandas as pd
+from loguru import logger
+from playwright.async_api import Page
+
+from mcp_query_table.enums import QueryType
+
+# 初次查询页面
+_PAGE1_ = 'https://www.iwencai.com/customized/chart/get-robot-data'
+# 翻页
+_PAGE2_ = 'https://www.iwencai.com/gateway/urp/v7/landing/getDataList'
+
+_querytype_ = {
+    QueryType.CNStock: 'stock',
+    QueryType.Index: 'zhishu',
+    QueryType.Fund: 'fund',
+    QueryType.HKStock: 'hkstock',
+    QueryType.USStock: 'usstock',
+    '新三板': 'threeboard',
+    QueryType.ConBond: 'conbond',
+    '保险': 'insurance',
+    '期货': 'futures',
+    '理财': 'lccp',
+    '外汇': 'foreign_exchange',
+    '宏观': 'macro',
+    #
+    QueryType.ETF: 'fund',  # 查ETF定位到基金
+}
+
+
+def convert_type(type):
+    if type == 'LONG':
+        return int
+    if type == 'DOUBLE':
+        return float
+    if type == 'STR':
+        return str
+    if type == 'INT':  # TODO 好像未出现过
+        return int
+    return type
+
+
+class Pagination:
+    def __init__(self):
+        self.datas = {}
+        self.limit = 100
+        self.page = 1
+        self.row_count = 1024
+        self.columns = []
+
+    def reset(self):
+        self.datas = {}
+
+    def update(self, datas, columns, page, limit, row_count):
+        self.datas[page] = datas
+        self.columns = columns
+        self.limit = limit
+        self.page = page
+        self.row_count = row_count
+
+    def has_next(self, max_page):
+        c1 = self.page * self.limit < self.row_count
+        c2 = self.page < max_page
+        return c1 & c2
+
+    def current(self):
+        return self.page
+
+    def get_list(self):
+        datas = []
+        for k, v in self.datas.items():
+            datas.extend(v)
+        return datas
+
+    def get_dataframe(self):
+        columns = {x['key']: x['index_name'] for x in self.columns}
+        dtypes = {x['key']: convert_type(x['type']) for x in self.columns}
+
+        df = pd.DataFrame(self.get_list())
+        for k, v in dtypes.items():
+            if isinstance(v, str):
+                logger.info("未识别的数据类型 {}:{}", k, v)
+                continue
+            try:
+                df[k] = df[k].astype(v)
+            except ValueError:
+                logger.info("转换失败 {}:{}", k, v)
+
+        return df.rename(columns=columns)
+
+
+P = Pagination()
+
+
+def get_robot_data(json_data):
+    """
+json_data['data']['answer'][0]['txt'][0]['content']['components'][0]['data']['datas']
+json_data['data']['answer'][0]['txt'][0]['content']['components'][0]['data']['meta']['limit'] 100
+json_data['data']['answer'][0]['txt'][0]['content']['components'][0]['data']['meta']['page'] 1
+json_data['data']['answer'][0]['txt'][0]['content']['components'][0]['data']['meta']['extra']['row_count'] 1364
+    """
+    _1 = json_data['data']['answer'][0]['txt'][0]['content']['components'][0]['data']
+    _2 = _1['meta']
+
+    datas = _1['datas']
+    columns = _1['columns']
+    page = _2['page']
+    limit = _2['limit']
+    row_count = _2['extra']['row_count']
+
+    return datas, columns, page, limit, row_count
+
+
+def getDataList(json_data):
+    """
+json_data['answer']['components'][0]['data']['datas']
+json_data['answer']['components'][0]['data']['meta']['page']
+json_data['answer']['components'][0]['data']['meta']['limit']
+json_data['answer']['components'][0]['data']['meta']['extra']['row_count']
+    """
+    _1 = json_data['answer']['components'][0]['data']
+    _2 = _1['meta']
+
+    datas = _1['datas']
+    columns = _1['columns']
+    page = _2['page']
+    limit = _2['limit']
+    row_count = _2['extra']['row_count']
+
+    return datas, columns, int(page), int(limit), row_count
+
+
+async def on_response(response):
+    if response.url == _PAGE1_:
+        P.update(*get_robot_data(await response.json()))
+    if response.url == _PAGE2_:
+        P.update(*getDataList(await response.json()))
+
+
+async def query(page: Page,
+                w: str = "收盘价>1000元",
+                type_: QueryType = 'stock',
+                max_page: int = 5) -> pd.DataFrame:
+    querytype = _querytype_.get(type_, None)
+    assert querytype is not None, f"不支持的类型:{type_}"
+
+    await page.route(re.compile(r'.*\.(?:jpg|jpeg|png|gif|webp)(?:$|\?)'), lambda route: route.abort())
+
+    P.reset()
+    # page.viewport_size # 取出来是None
+    # 宽度<=768会认为是手机,>768是PC
+    await page.set_viewport_size({"width": 1280, "height": 800})
+    async with page.expect_response(_PAGE1_) as response_info:
+        await page.goto(f"https://www.iwencai.com/unifiedwap/result?w={w}&querytype={querytype}", wait_until="load")
+    await on_response(await response_info.value)
+
+    while P.has_next(max_page):
+        logger.info("当前页为:{}, 点击`下页`", P.current())
+        async with page.expect_response(_PAGE2_) as response_info:
+            await page.get_by_text("下页").click()
+        await on_response(await response_info.value)
+
+    return P.get_dataframe()

mcp_query_table/sites/tdx.py

@@ -0,0 +1,150 @@
+"""
+通达信 小达
+https://wenda.tdx.com.cn/
+"""
+import math
+import re
+
+import pandas as pd
+from loguru import logger
+from playwright.async_api import Page
+
+from mcp_query_table.enums import QueryType
+
+# 查询结果
+_PAGE1_ = 'https://wenda.tdx.com.cn/TQL?Entry=NLPSE.NLPQuery'
+# 代码数量
+_PAGE2_ = 'https://wenda.tdx.com.cn/TQL?Entry=JNLPSE.getAllCode'
+
+_queryType_ = {
+    QueryType.CNStock: 'AG',
+    QueryType.Fund: 'JJ',
+    QueryType.Index: 'ZS',
+    QueryType.Info: 'ZX',
+    QueryType.Board: 'ZX',  # 板块也走指数
+}
+
+
+def convert_type(type):
+    if type == '':
+        return str
+    if type == '0|0|0':
+        return str
+    if type == '2|0|0':
+        return float
+    if type == '0|9|1':
+        return float
+    if type == '1|9|1':
+        return float
+    if type == '2|9|1':
+        return float
+    return type
+
+
+class Pagination:
+    def __init__(self):
+        self.datas = {}
+        self.last_count = 1
+        self.limit = 100
+        self.row_count = 1024
+        self.dtypes = []
+        self.columns = []
+
+    def reset(self):
+        self.datas = {}
+
+    def update_row_count(self, row_count):
+        self.row_count = row_count
+
+    def update_last_count(self, limit, last_count, columns, dtypes, datas):
+        self.limit = limit
+        self.last_count = last_count
+        self.columns = columns
+        self.dtypes = dtypes
+        self.datas[last_count] = datas
+
+    def has_next(self, max_page):
+        page = math.ceil(self.last_count / self.limit)
+        c1 = self.last_count < self.row_count
+        c2 = page < max_page
+        return c1 & c2
+
+    def current(self):
+        return self.last_count
+
+    def get_list(self):
+        datas = []
+        for k, v in self.datas.items():
+            datas.extend(v)
+        return datas
+
+    def get_dataframe(self):
+        dtypes = [convert_type(x) for x in self.dtypes]
+        df = pd.DataFrame(self.get_list(), columns=self.columns)
+        for i, v in enumerate(dtypes):
+            k = self.columns[i]
+            if k == 'POS':
+                df[k] = df[k].astype(int)
+                continue
+            if isinstance(v, str):
+                logger.info("未识别的数据类型 {}:{}", k, v)
+                continue
+            try:
+                df[k] = df[k].astype(v)
+            except ValueError:
+                logger.info("转换失败 {}:{}", k, v)
+        return df
+
+
+P = Pagination()
+
+
+def NLPQuery(json_data):
+    limit = json_data[0][2]
+    last_count = int(json_data[0][4])
+    columns = json_data[1]
+    dtypes = json_data[2]
+    datas = json_data[3:]
+
+    return limit, last_count, columns, dtypes, datas
+
+
+def getAllCode(json_data):
+    row_count = json_data[0][2]
+
+    return row_count
+
+
+async def on_response1(response):
+    if response.url.startswith(_PAGE1_):
+        P.update_last_count(*NLPQuery(await response.json()))
+
+
+async def on_response2(response):
+    if response.url.startswith(_PAGE2_):
+        P.update_row_count(getAllCode(await response.json()))
+
+
+async def query(page: Page,
+                message: str = "收盘价>100元",
+                type_: QueryType = 'AG',
+                max_page: int = 5) -> pd.DataFrame:
+    queryType = _queryType_.get(type_, None)
+    assert queryType is not None, f"不支持的类型:{type_}"
+
+    await page.route(re.compile(r'.*\.(?:jpg|jpeg|png|gif|webp)(?:$|\?)'), lambda route: route.abort())
+    page.on("response", on_response2)
+
+    P.reset()
+    async with page.expect_response(lambda response: response.url.startswith(_PAGE1_)) as response_info:
+        await page.goto(f"https://wenda.tdx.com.cn/site/wenda/stock_index.html?message={message}&queryType={queryType}",
+                        wait_until="load")
+    await on_response1(await response_info.value)
+
+    while P.has_next(max_page):
+        logger.info("当前序号为:{}, 点击`下一页`", P.current())
+        async with page.expect_response(lambda response: response.url.startswith(_PAGE1_)) as response_info:
+            await page.get_by_role("button", name="下一页").click()
+        await on_response1(await response_info.value)
+
+    return P.get_dataframe()

mcp_query_table/tool.py

@@ -0,0 +1,165 @@
+import subprocess
+import time
+from pathlib import Path
+from typing import Optional
+
+import pandas as pd
+from loguru import logger
+from playwright.async_api import async_playwright, Playwright, Page
+
+from mcp_query_table.enums import QueryType, Site
+
+
+class BrowserManager:
+    async def __aenter__(self):
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        await self.cleanup()
+
+    def __init__(self, port: int = 9222, browser_path: Optional[str] = None, debug: bool = False):
+        """
+
+        Parameters
+        ----------
+        port:int
+            浏览器调试端口
+        browser_path
+            浏览器可执行路径。推荐使用chrome，因为Microsoft Edge必须在任务管理器中完全退出才能启动调试端口
+        debug:bool
+            是否显示开发者工具
+
+        """
+        if browser_path is None:
+            browser_path = r'C:\Program Files\Google\Chrome\Application\chrome.exe'
+            if not Path(browser_path).exists():
+                # Microsoft Edge必须在任务管理器中完全退出才能启动调试端口
+                browser_path = r'C:\Program Files (x86)\Microsoft\Edge\Application\msedge.exe'
+                if not Path(browser_path).exists():
+                    raise ValueError("未找到浏览器可执行文件")
+
+        self.port = port
+        self.browser_path = browser_path
+        self.debug = debug
+
+        self.playwright: Optional[Playwright] = None
+        self.browser = None
+        self.context = None
+        # 空闲page池
+        self.pages = []
+
+    async def cleanup(self):
+        if self.browser:
+            await self.browser.close()
+        if self.playwright:
+            await self.playwright.stop()
+
+    async def _launch(self) -> None:
+        """启动浏览器，并连接CDP协议
+
+        References
+        ----------
+        https://blog.csdn.net/qq_30576521/article/details/142370538
+
+        """
+        self.playwright = await async_playwright().start()
+
+        try:
+            # 尝试连接已打开的浏览器
+            self.browser = await self.playwright.chromium.connect_over_cdp(f"http://127.0.0.1:{self.port}",
+                                                                           slow_mo=1000,
+                                                                           timeout=5000)
+        except:
+
+            # 执行完成后不会关闭浏览器
+            if self.debug:
+                command = f'"{self.browser_path}" --remote-debugging-port={self.port} --start-maximized --auto-open-devtools-for-tabs'
+            else:
+                command = f'"{self.browser_path}" --remote-debugging-port={self.port} --start-maximized'
+            logger.info(f"start browser:{command}")
+            subprocess.Popen(command, shell=True)
+            time.sleep(3)
+
+            try:
+                self.browser = await self.playwright.chromium.connect_over_cdp(f"http://127.0.0.1:{self.port}",
+                                                                               slow_mo=1000,
+                                                                               timeout=5000)
+            except:
+                logger.warning("是否提前打开了浏览器，但未开启远程调试端口？请关闭浏览器全部进程后重试")
+                raise
+
+        self.context = self.browser.contexts[0]
+        # 复用打开的page
+        for page in self.context.pages:
+            # 防止开发者工具被使用
+            if page.url.startswith("devtools://"):
+                continue
+            self.pages.append(page)
+
+    async def _try_launch(self) -> None:
+        if self.browser is None:
+            await self._launch()
+        if not self.browser.is_connected():
+            await self._launch()
+
+    async def get_page(self) -> Page:
+        """获取可用Page。无空闲标签时会打开新标签"""
+        await self._try_launch()
+
+        # 反复取第一个tab
+        while len(self.pages) > 0:
+            page = self.pages.pop()
+            if page.is_closed():
+                continue
+            return page
+
+        # 不够，新建一个
+        return await self.context.new_page()
+
+    def release_page(self, page) -> None:
+        """用完的Page释放到池中。如果用完不放回，get_page会一直打开新标签"""
+        if page.is_closed():
+            return
+        # 放回
+        self.pages.append(page)
+
+
+async def query(
+        page: Page,
+        query_input: str = "收盘价>100元",
+        query_type: QueryType = QueryType.CNStock,
+        max_page: int = 5,
+        site: Site = Site.THS) -> pd.DataFrame:
+    """查询表格
+
+    Parameters
+    ----------
+    page : playwright.sync_api.Page
+        页面
+    query_input : str, optional
+        查询条件, by default "收盘价>100元"
+    query_type : QueryType, optional
+        查询类型, by default QueryType.astock
+    max_page : int, optional
+        最大页数, by default 5
+    site : Site, optional
+        站点, by default Site.iwencai
+
+    Returns
+    -------
+    pd.DataFrame
+        查询结果
+
+    """
+
+    if site == Site.EastMoney:
+        from mcp_query_table.sites.eastmoney import query
+        return await query(page, query_input, query_type, max_page)
+    if site == Site.THS:
+        from mcp_query_table.sites.iwencai import query
+        return await query(page, query_input, query_type, max_page)
+    if site == Site.TDX:
+        from mcp_query_table.sites.tdx import query
+        return await query(page, query_input, query_type, max_page)
+
+    raise ValueError(f"未支持的站点:{site}")

mcp_query_table-0.2.6.dist-info/METADATA

@@ -0,0 +1,183 @@
+Metadata-Version: 2.4
+Name: mcp_query_table
+Version: 0.2.6
+Summary: query table from website, support MCP
+Author-email: wukan <wu-kan@163.com>
+License: MIT License
+        
+        Copyright (c) 2025 伍侃
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Keywords: playwright,mcp,table,iwencai,tdx,eastmoney
+Classifier: Development Status :: 4 - Beta
+Classifier: Programming Language :: Python
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: loguru
+Requires-Dist: playwright
+Requires-Dist: mcp
+Dynamic: license-file
+
+# mcp_query_table
+
+基于`playwright`实现的财经网页表格爬虫，支持`Model Context Protocol (MCP) `。目前可查询来源为
+
+- [同花顺i问财](http://iwencai.com/)
+- [通达信问小达](https://wenda.tdx.com.cn/)
+- [东方财富条件选股](https://xuangu.eastmoney.com/)
+
+实盘时，如果某网站宕机或改版，可以立即切换到其他网站。(注意：不同网站的表格结构不同，需要提前做适配)
+
+## 安装
+
+```commandline
+pip install -i https://pypi.org/simple --upgrade mcp_query_table
+pip install -i https://pypi.tuna.tsinghua.edu.cn/simple --upgrade mcp_query_table
+```
+
+## 使用
+
+```python
+import asyncio
+
+from mcp_query_table import *
+
+
+async def main() -> None:
+    async with BrowserManager(port=9222, browser_path=None, debug=True) as bm:
+        # 问财需要保证浏览器宽度>768，防止界面变成适应手机
+        page = await bm.get_page()
+        df = await query(page, '收益最好的200只ETF', query_type=QueryType.ETF, max_page=1, site=Site.THS)
+        print(df.to_markdown())
+        df = await query(page, '年初至今收益率前50', query_type=QueryType.Fund, max_page=1, site=Site.TDX)
+        print(df.to_csv())
+        df = await query(page, '流通市值前10的行业板块', query_type=QueryType.Index, max_page=1, site=Site.TDX)
+        print(df.to_csv())
+        # TODO 东财翻页要提前登录
+        df = await query(page, '今日涨幅前5的概念板块;', query_type=QueryType.Board, max_page=3, site=Site.EastMoney)
+        print(df)
+        bm.release_page(page)
+        print('done')
+        await page.wait_for_timeout(2000)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())
+
+```
+
+## 注意事项
+
+1. 浏览器最好是`Chrome`。如一定要使用`Edge`,除了关闭`Edge`所有窗口外，还要在任务管理器关闭`Microsoft Edge`
+   的所有进程，即`taskkill /f /im msedge.exe`
+2. 浏览器要保证窗口宽度，防止部分网站自动适配成手机版，导致表格查询失败
+3. 如有网站账号，请提前登录。此工具无自动登录功能
+4. 不同网站的表格结构不同，同条件返回股票数量也不同。需要查询后做适配
+
+## 工作原理
+
+不同于`requests`，`playwright`是基于浏览器的，模拟用户在浏览器中的操作。
+
+1. 不需要解决登录问题
+2. 不需要解决请求构造、响应解析
+3. 可以直接获取表格数据，所见即所得
+4. 运行速度慢于`requests`，但开发效率高
+
+数据的获取有：
+
+1. 直接解析HTML表格
+    1. 数字文本化了，不利于后期研究
+    2. 适用性最强
+2. 截获请求，获取返回的`json`数据
+    1. 类似于`requests`，需要做响应解析
+    2. 灵活性差点，网站改版后，需要重新做适配
+
+此项目采用的是模拟点击浏览器来发送请求，使用截获响应并解析的方法来获取数据。
+
+后期会根据不同的网站改版情况，使用更适合的方法。
+
+## MCP支持
+
+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，`browser_path`是`Chrome`的绝对路径。
+
+### STDIO方式
+
+```json
+{
+  "mcpServers": {
+    "mcp_query_table": {
+      "command": "D:\\Users\\Kan\\miniconda3\\envs\\py312\\python.exe",
+      "args": [
+        "-m",
+        "mcp_query_table",
+        "--format",
+        "markdown",
+        "--browser_path",
+        "C:\\Program Files\\Google\\Chrome\\Application\\chrome.exe"
+      ]
+    }
+  }
+}
+```
+
+### SSE方式
+
+先在控制台中执行如下命令，启动`MCP`服务
+
+```commandline
+python -m mcp_query_table --format markdown --browser_path "C:\Program Files\Google\Chrome\Application\chrome.exe" --transport sse --mcp_port 8000
+```
+
+然后就可以连接到`MCP`服务了
+http://localhost:8000/sse
+
+## 使用`MCP Inspector`进行调试
+
+```commandline
+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=60000` 表示超时时间为60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`使用技巧
+
+1. 2024年涨幅最大的100只股票按2024年12月31日总市值排名。三个网站的结果都不一样
+    - 同花顺：显示了2201只股票。前5个是工商银行、农业银行、中国移动、中国石油、建设银行
+    - 通达信：显示了100只股票，前5个是寒武纪、正丹股份，汇金科技、万丰奥威、艾融软件
+    - 东方财富：显示了100只股票，前5个是海光信息、寒武纪、光启技术、润泽科技、新易盛
+
+2. 大语言模型对问题拆分能力弱，所以要能合理的提问，保证查询条件不会被改动。以下推荐第2、3种
+    - 2024年涨幅最大的100只股票按2024年12月31日总市值排名
+      > 大语言模型非常有可能拆分这句，导致一步查询被分成了多步查询
+    - 向东方财富查询“2024年涨幅最大的100只股票按2024年12月31日总市值排名”
+      > 用引号括起来，避免被拆分
+    - 向东方财富板块查询 “去年涨的最差的行业板块”，再查询此板块中去年涨的最好的5只股票
+      > 分成两步查询，先查询板块，再查询股票。但最好不要全自动，因为第一步的结果它不理解“今日涨幅”和“区间涨幅”,需要交互修正
+
+## 参考
+
+- [Playwright](https://playwright.dev/python/docs/intro)
+- [Selenium webdriver无法附加到edge实例，edge的--remote-debugging-port选项无效](https://blog.csdn.net/qq_30576521/article/details/142370538)

mcp_query_table-0.2.6.dist-info/RECORD

@@ -0,0 +1,15 @@
+mcp_query_table/__init__.py,sha256=nHQOsX_pO9mwyq4a77irNpgvIXmc8NArQnj5-nEMW6k,110
+mcp_query_table/__main__.py,sha256=SmOaVfIDX4dcF-SV_xcn-Sfn3io-XunsdwKPnGfzwAU,1150
+mcp_query_table/_version.py,sha256=Oz5HbwHMyE87nmwV80AZzpkJPf-wBg7eDuJr_BXZkhU,22
+mcp_query_table/enums.py,sha256=gVioM6lyI6lGfBBS9KY2IxCh4QKdLVAqXAgo19aAg6U,446
+mcp_query_table/server.py,sha256=Hi9qUMH9vvhLwcgsnCGORjQB9Ac_N-SM0a-hcC2QB8w,2375
+mcp_query_table/tool.py,sha256=_PjyjsgjDvwAGKVFv4W-Olim_qB7jGpg4CZxnsXzNDk,5641
+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-0.2.6.dist-info/licenses/LICENSE,sha256=rbvv_CTd7biGwT21tvhgQ2zkbPFXOoON7WFQWEdElBA,1063
+mcp_query_table-0.2.6.dist-info/METADATA,sha256=gmVXsQZi17_AAJi9StVSPpIpcrrdNwj51OOVFdne7Ww,7490
+mcp_query_table-0.2.6.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+mcp_query_table-0.2.6.dist-info/top_level.txt,sha256=5M_8dkO1USOX7_EWbWS6O_TEsZ5yo-AodFNKeUEgvEQ,16
+mcp_query_table-0.2.6.dist-info/RECORD,,

mcp_query_table-0.2.6.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (78.1.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

mcp_query_table-0.2.6.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 伍侃
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

mcp_query_table-0.2.6.dist-info/top_level.txt

@@ -0,0 +1 @@
+mcp_query_table