akshare-one 0.1.0__py3-none-any.whl

akshare_one/__init__.py

@@ -0,0 +1,32 @@
+"""Akshare One - Unified interface for Chinese market data
+
+Provides standardized access to various financial data sources with:
+- Consistent symbol formats
+- Unified data schemas
+- Cleaned and normalized outputs
+
+Example:
+    >>> from akshare_one import get_hist_data, get_realtime_data
+    >>> df = get_hist_data("600000", interval="day")
+    >>> print(df.head())
+    >>> # 获取单只股票实时数据
+    >>> df = get_realtime_data(symbol="600000")
+    >>> # 获取所有股票实时数据
+    >>> df = get_realtime_data()
+"""
+
+from .stock import get_hist_data, get_realtime_data
+from .news import get_news_data
+from .insider import get_inner_trade_data
+from .financial import get_balance_sheet, get_income_statement, get_cash_flow
+
+
+__all__ = [
+    "get_hist_data",
+    "get_realtime_data",
+    "get_news_data",
+    "get_inner_trade_data",
+    "get_balance_sheet",
+    "get_income_statement",
+    "get_cash_flow",
+]

akshare_one/adapters/__init__.py

@@ -0,0 +1,7 @@
+# Initialize adapters package
+from .eastmoney import EastMoneyAdapter
+from .sina import SinaAdapter
+from .xueqiu import XueQiuAdapter
+from .cache.cache import CACHE_CONFIG
+
+__all__ = ['EastMoneyAdapter', 'SinaAdapter', 'XueQiuAdapter', 'CACHE_CONFIG']

akshare_one/adapters/cache/cache.py

@@ -0,0 +1,9 @@
+from cachetools import TTLCache
+
+# 缓存配置
+CACHE_CONFIG = {
+    'hist_data_cache': TTLCache(maxsize=1000, ttl=3600),  # 历史数据缓存1小时
+    'realtime_cache': TTLCache(maxsize=500, ttl=60),      # 实时数据缓存1分钟 
+    'news_cache': TTLCache(maxsize=500, ttl=3600),
+    'financial_cache': TTLCache(maxsize=500, ttl=86400),  # 财务数据缓存24小时
+}

akshare_one/adapters/eastmoney.py

@@ -0,0 +1,344 @@
+from typing import Optional
+import pandas as pd
+import akshare as ak
+from cachetools import cached
+from .cache.cache import CACHE_CONFIG
+
+
+class EastMoneyAdapter:
+    """Adapter for EastMoney historical stock data API"""
+
+    @cached(
+        CACHE_CONFIG["hist_data_cache"],
+        key=lambda self,
+        symbol,
+        interval,
+        interval_multiplier,
+        start_date,
+        end_date,
+        adjust: ("eastmoney", symbol, interval, interval_multiplier, start_date, end_date, adjust),
+    )
+    def get_hist_data(
+        self,
+        symbol: str,
+        interval: str = "day",
+        interval_multiplier: int = 1,
+        start_date: str = "1970-01-01",
+        end_date: str = "2030-12-31",
+        adjust: str = "none",
+    ) -> pd.DataFrame:
+        """获取东方财富历史行情数据
+
+        Args:
+            symbol: Unified symbol format (e.g. '600000')
+            interval: Time granularity ('second','minute','hour','day','week','month','year')
+            interval_multiplier: Interval multiplier (e.g. 5 for 5 minutes)
+            start_date: Start date in YYYY-MM-DD format (will be converted to YYYYMMDD)
+            end_date: End date in YYYY-MM-DD format (will be converted to YYYYMMDD)
+            adjust: Adjustment type ('none','qfq','hfq')
+
+        Returns:
+           Standardized DataFrame with OHLCV data
+        """
+        # Map standard interval to akshare supported periods
+        interval = interval.lower()
+        if interval == "second":
+            raise ValueError("EastMoney does not support second-level data")
+        elif interval == "minute":
+            if interval_multiplier < 1:
+                raise ValueError("Minute interval multiplier must be >= 1")
+
+            start_date = (
+                f"{start_date} 09:30:00" if " " not in start_date else start_date
+            )
+            end_date = f"{end_date} 15:00:00" if " " not in end_date else end_date
+
+            raw_df = ak.stock_zh_a_hist_min_em(
+                symbol=symbol,
+                period="1",
+                start_date=start_date,
+                end_date=end_date,
+                adjust=adjust if adjust != "none" else "",
+            )
+            # Resample the data to the desired minute interval
+            raw_df["时间"] = pd.to_datetime(raw_df["时间"])
+            raw_df = raw_df.set_index("时间")
+            resampled = raw_df.resample(f"{interval_multiplier}min").agg(
+                {
+                    "开盘": "first",
+                    "最高": "max",
+                    "最低": "min",
+                    "收盘": "last",
+                    "成交量": "sum",
+                    "成交额": "sum",
+                }
+            )
+            raw_df = resampled.reset_index()
+            return self._clean_minute_data(raw_df, str(interval_multiplier))
+        elif interval == "hour":
+            if interval_multiplier < 1:
+                raise ValueError("Hour interval multiplier must be >= 1")
+
+            start_date = (
+                f"{start_date} 09:30:00" if " " not in start_date else start_date
+            )
+            end_date = f"{end_date} 15:00:00" if " " not in end_date else end_date
+
+            raw_df = ak.stock_zh_a_hist_min_em(
+                symbol=symbol,
+                period="60",
+                start_date=start_date,
+                end_date=end_date,
+                adjust=adjust if adjust != "none" else "",
+            )
+
+            # Resample the data to the desired hour interval
+            raw_df["时间"] = pd.to_datetime(raw_df["时间"])
+            raw_df = raw_df.set_index("时间")
+            resampled = raw_df.resample(f"{interval_multiplier}h").agg(
+                {
+                    "开盘": "first",
+                    "最高": "max",
+                    "最低": "min",
+                    "收盘": "last",
+                    "成交量": "sum",
+                    "成交额": "sum",
+                }
+            )
+            raw_df = resampled.reset_index()
+
+            return self._clean_minute_data(raw_df, f"{interval_multiplier}H")
+        elif interval == "day":
+            period = "daily"
+        elif interval == "week":
+            period = "weekly"
+        elif interval == "month":
+            period = "monthly"
+        elif interval == "year":
+            period = "monthly"  # use monthly for yearly data
+            interval_multiplier = 12 * interval_multiplier
+        else:
+            raise ValueError(f"Unsupported interval: {interval}")
+
+        # Convert date format from YYYY-MM-DD to YYYYMMDD if needed
+        start_date = start_date.replace("-", "") if "-" in start_date else start_date
+        end_date = end_date.replace("-", "") if "-" in end_date else end_date
+
+        # Fetch raw data from akshare
+        raw_df = ak.stock_zh_a_hist(
+            symbol=symbol,
+            period=period,  # daily/weekly/monthly
+            start_date=start_date,
+            end_date=end_date,
+            adjust=adjust if adjust != "none" else "",
+        )
+
+        if interval_multiplier > 1:
+            raw_df = self._resample_data(raw_df, interval, interval_multiplier)
+
+        # Standardize the data format
+        return self._clean_data(raw_df)
+
+    @cached(CACHE_CONFIG["realtime_cache"], key=lambda self, symbol=None: f"eastmoney_{symbol if symbol else 'all'}")
+    def get_realtime_data(self, symbol: Optional[str] = None) -> pd.DataFrame:
+        """获取沪深京A股实时行情数据"""
+        raw_df = ak.stock_zh_a_spot_em()
+        df = self._clean_spot_data(raw_df)
+        if symbol:
+            df = df[df["symbol"] == symbol].reset_index(drop=True)
+        return df
+
+    def _resample_data(
+        self, df: pd.DataFrame, interval: str, multiplier: int
+    ) -> pd.DataFrame:
+        """Resample the data based on the given interval and multiplier"""
+        if interval == "day":
+            freq = f"{multiplier}D"
+        elif interval == "week":
+            freq = f"{multiplier}W-MON"
+        elif interval == "month":
+            freq = f"{multiplier}MS"
+        elif interval == "year":
+            freq = f"{multiplier}AS-JAN"
+
+        df["日期"] = pd.to_datetime(df["日期"])
+        df = df.set_index("日期")
+        resampled = df.resample(freq).agg(
+            {
+                "开盘": "first",
+                "最高": "max",
+                "最低": "min",
+                "收盘": "last",
+                "成交量": "sum",
+            }
+        )
+        return resampled.reset_index()
+
+    def _clean_minute_data(self, raw_df: pd.DataFrame, period: str) -> pd.DataFrame:
+        if period == "1":
+            column_mapping = {
+                "时间": "timestamp",
+                "开盘": "open",
+                "收盘": "close",
+                "最高": "high",
+                "最低": "low",
+                "成交量": "volume",
+                "成交额": "amount",
+                "均价": "vwap",
+            }
+        else:
+            column_mapping = {
+                "时间": "timestamp",
+                "开盘": "open",
+                "收盘": "close",
+                "最高": "high",
+                "最低": "low",
+                "涨跌幅": "pct_change",
+                "涨跌额": "change",
+                "成交量": "volume",
+                "成交额": "amount",
+                "振幅": "amplitude",
+                "换手率": "turnover",
+            }
+
+        df = raw_df.rename(columns=column_mapping)
+
+        if "timestamp" in df.columns:
+            df["timestamp"] = (
+                pd.to_datetime(df["timestamp"])
+                .dt.tz_localize("Asia/Shanghai")
+                .dt.tz_convert("UTC")
+            )
+        standard_columns = [
+            "timestamp",
+            "open",
+            "high",
+            "low",
+            "close",
+            "volume",
+        ]
+        return df[[col for col in standard_columns if col in df.columns]]
+
+    def _clean_data(self, raw_df: pd.DataFrame, adjust: str = "none") -> pd.DataFrame:
+        """清理和标准化历史数据格式
+
+        Args:
+            raw_df: Raw DataFrame from EastMoney API
+            adjust: Adjustment type ('none','qfq','hfq')
+
+        Returns:
+            Standardized DataFrame with consistent columns
+        """
+        # Check if required columns exist in raw data
+        required_columns = {
+            "日期": "timestamp",
+            "开盘": "open",
+            "收盘": "close",
+            "最高": "high",
+            "最低": "low",
+            "成交量": "volume",
+        }
+
+        # Find available columns in raw data
+        available_columns = {}
+        for src_col, target_col in required_columns.items():
+            if src_col in raw_df.columns:
+                available_columns[src_col] = target_col
+
+        if not available_columns:
+            raise ValueError("Raw data does not contain any expected columns")
+
+        # Rename available columns
+        df = raw_df.rename(columns=available_columns)
+
+        # Process timestamp if available
+        if "timestamp" in df.columns:
+            df = df.assign(
+                timestamp=lambda x: pd.to_datetime(x["timestamp"])
+                .dt.tz_localize("Asia/Shanghai")
+                .dt.tz_convert("UTC")
+            )
+
+        # Process volume if available
+        if "volume" in df.columns:
+            df = df.assign(volume=lambda x: x["volume"].astype("int64"))
+
+        # Process adjustment flag
+        if adjust != "none":
+            df = df.assign(is_adjusted=lambda x: x["adjust"] != "none")
+        else:
+            df = df.assign(is_adjusted=False)
+
+        # Select available standardized columns
+        standard_columns = [
+            "timestamp",
+            "open",
+            "high",
+            "low",
+            "close",
+            "volume",
+        ]
+        return df[[col for col in standard_columns if col in df.columns]]
+
+    @cached(CACHE_CONFIG["news_cache"], key=lambda self, symbol: f"eastmoney_{symbol}")
+    def get_news_data(self, symbol: str) -> pd.DataFrame:
+        """获取东方财富个股新闻数据"""
+        raw_df = ak.stock_news_em(symbol=symbol)
+
+        column_mapping = {
+            "关键词": "keyword",
+            "新闻标题": "title",
+            "新闻内容": "content",
+            "发布时间": "publish_time",
+            "文章来源": "source",
+            "新闻链接": "url",
+        }
+
+        df = raw_df.rename(columns=column_mapping)
+
+        if "publish_time" in df.columns:
+            df = df.assign(
+                publish_time=lambda x: pd.to_datetime(x["publish_time"])
+                .dt.tz_localize("Asia/Shanghai")
+                .dt.tz_convert("UTC")
+            )
+
+        return df
+
+    def _clean_spot_data(self, raw_df: pd.DataFrame) -> pd.DataFrame:
+        """清理和标准化实时行情数据"""
+
+        column_mapping = {
+            "代码": "symbol",
+            "最新价": "price",
+            "涨跌额": "change",
+            "涨跌幅": "pct_change",
+            "成交量": "volume",
+            "成交额": "amount",
+            "今开": "open",
+            "最高": "high",
+            "最低": "low",
+            "昨收": "prev_close",
+        }
+
+        df = raw_df.rename(columns=column_mapping)
+
+        # Change time to UTC
+        df = df.assign(
+            timestamp=lambda x: pd.Timestamp.now(tz="Asia/Shanghai").tz_convert("UTC")
+        )
+
+        required_columns = [
+            "symbol",
+            "price",
+            "change",
+            "pct_change",
+            "timestamp",
+            "volume",
+            "amount",
+            "open",
+            "high",
+            "low",
+            "prev_close",
+        ]
+        return df[required_columns]

akshare_one/adapters/sina.py

@@ -0,0 +1,463 @@
+import pandas as pd
+import akshare as ak
+from cachetools import cached
+from .cache.cache import CACHE_CONFIG
+
+
+class SinaAdapter:
+    """Adapter for Sina financial data API
+
+    Includes:
+    - Financial reports (balance sheet, income statement, cash flow)
+    - Historical market data
+    """
+
+    @cached(CACHE_CONFIG["financial_cache"], key=lambda self, symbol: f"sina_{symbol}")
+    def get_balance_sheet(self, symbol: str) -> pd.DataFrame:
+        """获取资产负债表数据
+
+        Args:
+            symbol: 股票代码 (如 "600600")
+
+        Returns:
+            Standardized DataFrame with balance sheet data
+        """
+        stock = f"sh{symbol}" if not symbol.startswith(("sh", "sz", "bj")) else symbol
+        raw_df = ak.stock_financial_report_sina(stock=stock, symbol="资产负债表")
+        return self._clean_balance_data(raw_df)
+
+    @cached(CACHE_CONFIG["financial_cache"], key=lambda self, symbol: f"sina_{symbol}")
+    def get_income_statement(self, symbol: str) -> pd.DataFrame:
+        """获取利润表数据
+
+        Args:
+            symbol: 股票代码 (如 "600600")
+
+        Returns:
+            Standardized DataFrame with income statement data
+        """
+        stock = f"sh{symbol}" if not symbol.startswith(("sh", "sz", "bj")) else symbol
+        raw_df = ak.stock_financial_report_sina(stock=stock, symbol="利润表")
+        return self._clean_income_data(raw_df)
+
+    @cached(CACHE_CONFIG["financial_cache"], key=lambda self, symbol: f"sina_{symbol}")
+    def get_cash_flow(self, symbol: str) -> pd.DataFrame:
+        """获取现金流量表数据
+
+        Args:
+            symbol: 股票代码 (如 "600600")
+
+        Returns:
+            Standardized DataFrame with cash flow data
+        """
+        stock = f"sh{symbol}" if not symbol.startswith(("sh", "sz", "bj")) else symbol
+        raw_df = ak.stock_financial_report_sina(stock=stock, symbol="现金流量表")
+        return self._clean_cash_data(raw_df)
+
+    def _clean_cash_data(self, raw_df: pd.DataFrame) -> pd.DataFrame:
+        """清理和标准化现金流量表数据
+
+        Args:
+            raw_df: Raw DataFrame from Sina API
+
+        Returns:
+            Standardized DataFrame with consistent columns
+        """
+        # Convert timestamp columns if exists
+        if "报告日" in raw_df.columns:
+            raw_df = raw_df.rename(columns={"报告日": "report_date"})
+            raw_df["report_date"] = pd.to_datetime(
+                raw_df["report_date"], format="%Y%m%d"
+            )
+
+        if "更新日期" in raw_df.columns:
+            raw_df = raw_df.rename(columns={"更新日期": "update_time"})
+            raw_df["update_time"] = pd.to_datetime(raw_df["update_time"])
+
+        # Standardize column names
+        column_mapping = {
+            "类型": "report_type",
+            "币种": "currency",
+            "净利润": "net_income",
+            "固定资产折旧、油气资产折耗、生产性生物资产折旧": "depreciation_and_amortization",
+            "无形资产摊销": "share_based_compensation",
+            "经营活动产生的现金流量净额": "net_cash_flow_from_operations",
+            "购建固定资产、无形资产和其他长期资产支付的现金": "capital_expenditure",
+            "取得子公司及其他营业单位支付的现金净额": "business_acquisitions_and_disposals",
+            "投资支付的现金": "investment_acquisitions_and_disposals",
+            "投资活动产生的现金流量净额": "net_cash_flow_from_investing",
+            "取得借款收到的现金": "issuance_or_repayment_of_debt_securities",
+            "吸收投资收到的现金": "issuance_or_purchase_of_equity_shares",
+            "分配股利、利润或偿付利息支付的现金": "dividends_and_other_cash_distributions",
+            "筹资活动产生的现金流量净额": "net_cash_flow_from_financing",
+            "现金及现金等价物净增加额": "change_in_cash_and_equivalents",
+            "汇率变动对现金及现金等价物的影响": "effect_of_exchange_rate_changes",
+            "期末现金及现金等价物余额": "ending_cash_balance",
+            "自由现金流": "free_cash_flow",
+        }
+        raw_df = raw_df.rename(columns=column_mapping)
+
+        # Select only required columns
+        required_columns = [
+            "report_date",
+            "report_period",
+            "period",
+            "currency",
+            "net_income",
+            "depreciation_and_amortization",
+            "share_based_compensation",
+            "net_cash_flow_from_operations",
+            "capital_expenditure",
+            "business_acquisitions_and_disposals",
+            "investment_acquisitions_and_disposals",
+            "net_cash_flow_from_investing",
+            "issuance_or_repayment_of_debt_securities",
+            "issuance_or_purchase_of_equity_shares",
+            "dividends_and_other_cash_distributions",
+            "net_cash_flow_from_financing",
+            "change_in_cash_and_equivalents",
+            "effect_of_exchange_rate_changes",
+            "ending_cash_balance",
+            "free_cash_flow",
+        ]
+
+        # Filter columns
+        available_columns = [col for col in required_columns if col in raw_df.columns]
+        return raw_df[available_columns]
+
+    def _clean_balance_data(self, raw_df: pd.DataFrame) -> pd.DataFrame:
+        """清理和标准化资产负债表数据
+
+        Args:
+            raw_df: Raw DataFrame from Sina API
+
+        Returns:
+            Standardized DataFrame with consistent columns
+        """
+        # Convert timestamp columns if exists
+        if "报告日" in raw_df.columns:
+            raw_df = raw_df.rename(columns={"报告日": "report_date"})
+            raw_df["report_date"] = pd.to_datetime(
+                raw_df["report_date"], format="%Y%m%d"
+            )
+
+        if "更新日期" in raw_df.columns:
+            raw_df = raw_df.rename(columns={"更新日期": "update_time"})
+            raw_df["update_time"] = pd.to_datetime(raw_df["update_time"])
+
+        # Standardize column names
+        column_mapping = {
+            "类型": "report_type",
+            "币种": "currency",
+            "资产总计": "total_assets",
+            "流动资产合计": "current_assets",
+            "货币资金": "cash_and_equivalents",
+            "存货": "inventory",
+            "交易性金融资产": "current_investments",
+            "应收票据及应收账款": "trade_and_non_trade_receivables",
+            "非流动资产合计": "non_current_assets",
+            "固定资产": "property_plant_and_equipment",
+            "商誉": "goodwill_and_intangible_assets",
+            "长期股权投资": "investments",
+            "其他非流动金融资产": "non_current_investments",
+            "实收资本(或股本)": "outstanding_shares",
+            "递延所得税资产": "tax_assets",
+            "负债合计": "total_liabilities",
+            "流动负债合计": "current_liabilities",
+            "短期借款": "current_debt",
+            "应付票据及应付账款": "trade_and_non_trade_payables",
+            "合同负债": "deferred_revenue",
+            "吸收存款及同业存放": "deposit_liabilities",
+            "非流动负债合计": "non_current_liabilities",
+            "长期借款": "non_current_debt",
+            "递延所得税负债": "tax_liabilities",
+            "所有者权益(或股东权益)合计": "shareholders_equity",
+            "未分配利润": "retained_earnings",
+            "其他综合收益": "accumulated_other_comprehensive_income",
+        }
+        raw_df = raw_df.rename(columns=column_mapping)
+
+        # Select only required columns
+        required_columns = [
+            "report_date",
+            "report_period",
+            "period",
+            "currency",
+            "total_assets",
+            "current_assets",
+            "cash_and_equivalents",
+            "inventory",
+            "current_investments",
+            "trade_and_non_trade_receivables",
+            "non_current_assets",
+            "property_plant_and_equipment",
+            "goodwill_and_intangible_assets",
+            "investments",
+            "non_current_investments",
+            "outstanding_shares",
+            "tax_assets",
+            "total_liabilities",
+            "current_liabilities",
+            "current_debt",
+            "trade_and_non_trade_payables",
+            "deferred_revenue",
+            "deposit_liabilities",
+            "non_current_liabilities",
+            "non_current_debt",
+            "tax_liabilities",
+            "shareholders_equity",
+            "retained_earnings",
+            "accumulated_other_comprehensive_income",
+        ]
+
+        # Calculate total_debt
+        if "current_debt" in raw_df.columns and "non_current_debt" in raw_df.columns:
+            raw_df["total_debt"] = raw_df["current_debt"] + raw_df["non_current_debt"]
+            required_columns.append("total_debt")
+
+        # Filter columns
+        available_columns = [col for col in required_columns if col in raw_df.columns]
+        return raw_df[available_columns]
+
+    @cached(
+        CACHE_CONFIG["hist_data_cache"],
+        key=lambda self,
+        symbol,
+        interval,
+        interval_multiplier,
+        start_date,
+        end_date,
+        adjust: ("sina", symbol, interval, interval_multiplier, start_date, end_date, adjust),
+    )
+    def get_hist_data(
+        self,
+        symbol: str,
+        interval: str = "day",
+        interval_multiplier: int = 1,
+        start_date: str = "1970-01-01",
+        end_date: str = "2030-12-31",
+        adjust: str = "none",
+    ) -> pd.DataFrame:
+        """获取新浪历史行情数据
+
+        Args:
+            symbol: 股票代码 (如 "600000")
+            interval: 时间粒度 (支持: "minute", "hour", "day", "week", "month", "year")
+            interval_multiplier: 时间间隔倍数 (如: 5分钟数据设为5)
+            start_date: 开始日期 (YYYY-MM-DD)
+            end_date: 结束日期 (YYYY-MM-DD)
+            adjust: 复权类型 ('none','qfq','hfq','qfq-factor','hfq-factor')
+
+        Returns:
+            Standardized DataFrame with OHLCV data
+        """
+        interval = interval.lower()
+        stock = f"sh{symbol}" if not symbol.startswith(("sh", "sz", "bj")) else symbol
+
+        if interval == "minute":
+            raw_df = ak.stock_zh_a_minute(
+                symbol=stock,
+                period="1",
+                adjust=adjust if adjust != "none" else "",
+            )
+            raw_df = raw_df.rename(columns={"day": "date"})
+            raw_df["date"] = pd.to_datetime(raw_df["date"])
+            raw_df = raw_df.set_index("date")
+            raw_df = (
+                raw_df.resample(f"{interval_multiplier}min")
+                .agg(
+                    {
+                        "open": "first",
+                        "high": "max",
+                        "low": "min",
+                        "close": "last",
+                        "volume": "sum",
+                    }
+                )
+                .reset_index()
+            )
+
+        elif interval == "hour":
+            if interval_multiplier < 1:
+                raise ValueError("Hour interval multiplier must be >= 1")
+
+            raw_df = ak.stock_zh_a_minute(
+                symbol=stock,
+                period="60",
+                adjust=adjust if adjust != "none" else "",
+            )
+            raw_df = raw_df.rename(columns={"day": "date"})
+            raw_df["date"] = pd.to_datetime(raw_df["date"])
+            raw_df = raw_df.set_index("date")
+            raw_df = (
+                raw_df.resample(f"{interval_multiplier}h")
+                .agg(
+                    {
+                        "open": "first",
+                        "high": "max",
+                        "low": "min",
+                        "close": "last",
+                        "volume": "sum",
+                    }
+                )
+                .reset_index()
+            )
+
+        elif interval in ["day", "week", "month", "year"]:
+            # Convert date format from YYYY-MM-DD to YYYYMMDD
+            start_date = (
+                start_date.replace("-", "") if "-" in start_date else start_date
+            )
+            end_date = end_date.replace("-", "") if "-" in end_date else end_date
+
+            raw_df = ak.stock_zh_a_daily(
+                symbol=stock,
+                start_date=start_date,
+                end_date=end_date,
+                adjust=adjust if adjust != "none" else "",
+            )
+
+            if interval_multiplier > 1:
+                raw_df = self._resample_data(raw_df, interval, interval_multiplier)
+        else:
+            raise ValueError(f"Unsupported interval: {interval}")
+
+        return self._clean_hist_data(raw_df, adjust)
+
+    def _resample_data(
+        self, df: pd.DataFrame, interval: str, multiplier: int
+    ) -> pd.DataFrame:
+        if interval == "day":
+            freq = f"{multiplier}D"
+        elif interval == "week":
+            freq = f"{multiplier}W-MON"
+        elif interval == "month":
+            freq = f"{multiplier}MS"
+        elif interval == "year":
+            freq = f"{multiplier}AS-JAN"
+
+        df["date"] = pd.to_datetime(df["date"])
+        df = df.set_index("date")
+        resampled = df.resample(freq).agg(
+            {
+                "open": "first",
+                "high": "max",
+                "low": "min",
+                "close": "last",
+                "volume": "sum",
+            }
+        )
+        return resampled.reset_index()
+
+    def _clean_hist_data(self, raw_df: pd.DataFrame, adjust: str) -> pd.DataFrame:
+        """清理和标准化历史行情数据
+
+        Args:
+            raw_df: 原始数据DataFrame
+            adjust: 复权类型
+
+        Returns:
+            标准化后的DataFrame
+        """
+        column_mapping = {
+            "date": "timestamp",
+            "open": "open",
+            "high": "high",
+            "low": "low",
+            "close": "close",
+            "volume": "volume",
+        }
+
+        df = raw_df.rename(columns=column_mapping)
+
+        # Process timestamp
+        if "timestamp" in df.columns:
+            df["timestamp"] = (
+                pd.to_datetime(df["timestamp"])
+                .dt.tz_localize("Asia/Shanghai")
+                .dt.tz_convert("UTC")
+            )
+
+        # Process volume
+        if "volume" in df.columns:
+            df["volume"] = df["volume"].astype("int64")
+
+        # Select and order columns
+        standard_columns = [
+            "timestamp",
+            "open",
+            "high",
+            "low",
+            "close",
+            "volume",
+        ]
+
+        return df[[col for col in standard_columns if col in df.columns]]
+
+    def _clean_income_data(self, raw_df: pd.DataFrame) -> pd.DataFrame:
+        """清理和标准化利润表数据
+
+        Args:
+            raw_df: Raw DataFrame from Sina API
+
+        Returns:
+            Standardized DataFrame with consistent columns
+        """
+        # Convert timestamp columns if exists
+        if "报告日" in raw_df.columns:
+            raw_df = raw_df.rename(columns={"报告日": "report_date"})
+            raw_df["report_date"] = pd.to_datetime(
+                raw_df["report_date"], format="%Y%m%d"
+            )
+
+        if "更新日期" in raw_df.columns:
+            raw_df = raw_df.rename(columns={"更新日期": "update_time"})
+            raw_df["update_time"] = pd.to_datetime(raw_df["update_time"])
+
+        # Standardize column names
+        column_mapping = {
+            "类型": "report_type",
+            "币种": "currency",
+            "营业总收入": "revenue",
+            "营业成本": "cost_of_revenue",
+            "营业利润": "gross_profit",
+            "销售费用": "selling_general_and_administrative_expenses",
+            "管理费用": "operating_expense",
+            "研发费用": "research_and_development",
+            "利息支出": "interest_expense",
+            "利润总额": "ebit",
+            "所得税费用": "income_tax_expense",
+            "净利润": "net_income",
+            "归属于母公司所有者的净利润": "net_income_common_stock",
+            "少数股东损益": "net_income_non_controlling_interests",
+            "基本每股收益": "earnings_per_share",
+            "稀释每股收益": "earnings_per_share_diluted",
+        }
+        raw_df = raw_df.rename(columns=column_mapping)
+
+        # Select only required columns
+        required_columns = [
+            "report_date",
+            "report_period",
+            "period",
+            "currency",
+            "revenue",
+            "cost_of_revenue",
+            "gross_profit",
+            "operating_expense",
+            "selling_general_and_administrative_expenses",
+            "research_and_development",
+            "operating_income",
+            "interest_expense",
+            "ebit",
+            "income_tax_expense",
+            "net_income",
+            "net_income_common_stock",
+            "net_income_non_controlling_interests",
+            "earnings_per_share",
+            "earnings_per_share_diluted",
+        ]
+
+        # Filter columns
+        available_columns = [col for col in required_columns if col in raw_df.columns]
+        return raw_df[available_columns]

akshare_one/adapters/xueqiu.py

@@ -0,0 +1,106 @@
+from typing import Optional
+import pandas as pd
+import akshare as ak
+from cachetools import cached
+from .cache.cache import CACHE_CONFIG
+
+
+class XueQiuAdapter:
+    """Adapter for XueQiu insider trading data API"""
+
+    @cached(CACHE_CONFIG["hist_data_cache"], key=lambda self, symbol=None: f"inner_trade_{symbol if symbol else 'all'}")
+    def get_inner_trade_data(self, symbol: Optional[str] = None) -> pd.DataFrame:
+        """获取雪球内部交易数据
+
+        Args:
+            symbol: 可选股票代码，如"600000"，不传则返回所有数据
+
+        Returns:
+            Standardized DataFrame with insider trading data:
+            - symbol: 股票代码
+            - name: 股票名称
+            - change_date: 变动日期
+            - insider: 变动人
+            - shares_changed: 变动股数
+            - avg_price: 成交均价
+            - shares_after: 变动后持股数
+            - relationship: 与董监高关系
+            - position: 董监高职务
+        """
+        raw_df = ak.stock_inner_trade_xq()
+        if symbol:
+            raw_df = raw_df[raw_df["股票代码"] == symbol]
+        return self._clean_data(raw_df)
+
+    def _clean_data(self, raw_df: pd.DataFrame) -> pd.DataFrame:
+        """清理和标准化内部交易数据
+
+        Args:
+            raw_df: Raw DataFrame from XueQiu API
+
+        Returns:
+            Standardized DataFrame with consistent columns
+        """
+        column_mapping = {
+            "股票代码": "symbol",
+            "股票名称": "issuer",
+            "变动人": "name",
+            "董监高职务": "title",
+            "变动日期": "transaction_date",
+            "变动股数": "transaction_shares",
+            "成交均价": "transaction_price_per_share",
+            "变动后持股数": "shares_owned_after_transaction",
+            "与董监高关系": "relationship",
+        }
+
+        df = raw_df.rename(columns=column_mapping)
+
+        # Add is_board_director column
+        df["is_board_director"] = df["title"].str.contains("董事")
+
+        # Calculate transaction_value
+        if (
+            "transaction_shares" in df.columns
+            and "transaction_price_per_share" in df.columns
+        ):
+            df["transaction_value"] = (
+                df["transaction_shares"] * df["transaction_price_per_share"]
+            )
+
+        # Add shares_owned_before_transaction if possible
+        if (
+            "shares_owned_after_transaction" in df.columns
+            and "transaction_shares" in df.columns
+        ):
+            df["shares_owned_before_transaction"] = (
+                df["shares_owned_after_transaction"] - df["transaction_shares"]
+            )
+
+        # Convert date format
+        if "transaction_date" in df.columns:
+            df["transaction_date"] = (
+                pd.to_datetime(df["transaction_date"])
+                .dt.tz_localize("Asia/Shanghai")
+                .dt.tz_convert("UTC")
+            )
+
+        if "filing_date" in df.columns:
+            df["filing_date"] = (
+                pd.to_datetime(df["filing_date"])
+                .dt.tz_localize("Asia/Shanghai")
+                .dt.tz_convert("UTC")
+            )
+
+        # Convert numeric columns
+        numeric_cols = [
+            "transaction_shares",
+            "transaction_price_per_share",
+            "transaction_value",
+            "shares_owned_before_transaction",
+            "shares_owned_after_transaction",
+        ]
+        for col in numeric_cols:
+            if col in df.columns:
+                df[col] = pd.to_numeric(df[col], errors="coerce")
+
+        return df

akshare_one/financial.py

@@ -0,0 +1,121 @@
+"""财务报表数据模块
+
+包含资产负债表、利润表和现金流量表相关功能
+"""
+
+import pandas as pd
+from .adapters import SinaAdapter
+
+
+def get_balance_sheet(symbol: str, source: str = "sina") -> "pd.DataFrame":
+    """获取资产负债表数据
+
+    Args:
+        symbol: 股票代码 (如 "600600")
+        source: 数据源 ("sina")
+
+    Returns:
+        pd.DataFrame:
+        - report_date: 报告日期
+        - report_period: 报告期
+        - period: 期间
+        - currency: 币种
+        - total_assets: 资产总计
+        - current_assets: 流动资产合计
+        - cash_and_equivalents: 货币资金
+        - inventory: 存货
+        - current_investments: 交易性金融资产
+        - trade_and_non_trade_receivables: 应收票据及应收账款
+        - non_current_assets: 非流动资产合计
+        - property_plant_and_equipment: 固定资产
+        - goodwill_and_intangible_assets: 商誉
+        - investments: 长期股权投资
+        - non_current_investments: 其他非流动金融资产
+        - outstanding_shares: 实收资本(或股本)
+        - tax_assets: 递延所得税资产
+        - total_liabilities: 负债合计
+        - current_liabilities: 流动负债合计
+        - current_debt: 短期借款
+        - trade_and_non_trade_payables: 应付票据及应付账款
+        - deferred_revenue: 合同负债
+        - deposit_liabilities: 吸收存款及同业存放
+        - non_current_liabilities: 非流动负债合计
+        - non_current_debt: 长期借款
+        - tax_liabilities: 递延所得税负债
+        - shareholders_equity: 所有者权益(或股东权益)合计
+        - retained_earnings: 未分配利润
+        - accumulated_other_comprehensive_income: 其他综合收益
+        - total_debt: 总债务(短期借款+长期借款)
+    """
+    if source == "sina":
+        return SinaAdapter().get_balance_sheet(symbol=symbol)
+    raise ValueError(f"Unsupported data source: {source}")
+
+
+def get_income_statement(symbol: str, source: str = "sina") -> "pd.DataFrame":
+    """获取利润表数据
+
+    Args:
+        symbol: 股票代码 (如 "600600")
+        source: 数据源 (目前支持 "sina")
+
+    Returns:
+        pd.DataFrame:
+        - report_date: 报告日期
+        - report_period: 报告期
+        - period: 期间
+        - currency: 币种
+        - revenue: 营业总收入
+        - cost_of_revenue: 营业成本
+        - gross_profit: 营业利润
+        - operating_expense: 管理费用
+        - selling_general_and_administrative_expenses: 销售费用
+        - research_and_development: 研发费用
+        - operating_income: 营业利润
+        - interest_expense: 利息支出
+        - ebit: 利润总额
+        - income_tax_expense: 所得税费用
+        - net_income: 净利润
+        - net_income_common_stock: 归属于母公司所有者的净利润
+        - net_income_non_controlling_interests: 少数股东损益
+        - earnings_per_share: 基本每股收益
+        - earnings_per_share_diluted: 稀释每股收益
+    """
+    if source == "sina":
+        return SinaAdapter().get_income_statement(symbol=symbol)
+    raise ValueError(f"Unsupported data source: {source}")
+
+
+def get_cash_flow(symbol: str, source: str = "sina") -> "pd.DataFrame":
+    """获取现金流量表数据
+
+    Args:
+        symbol: 股票代码 (如 "600600")
+        source: 数据源 (目前支持 "sina")
+
+    Returns:
+        pd.DataFrame:
+        - report_date: 报告日期
+        - report_period: 报告期
+        - period: 期间
+        - currency: 币种
+        - net_income: 净利润
+        - depreciation_and_amortization: 固定资产折旧、油气资产折耗、生产性生物资产折旧
+        - share_based_compensation: 无形资产摊销
+        - net_cash_flow_from_operations: 经营活动产生的现金流量净额
+        - capital_expenditure: 购建固定资产、无形资产和其他长期资产支付的现金
+        - business_acquisitions_and_disposals: 取得子公司及其他营业单位支付的现金净额
+        - investment_acquisitions_and_disposals: 投资支付的现金
+        - net_cash_flow_from_investing: 投资活动产生的现金流量净额
+        - issuance_or_repayment_of_debt_securities: 取得借款收到的现金
+        - issuance_or_purchase_of_equity_shares: 吸收投资收到的现金
+        - dividends_and_other_cash_distributions: 分配股利、利润或偿付利息支付的现金
+        - net_cash_flow_from_financing: 筹资活动产生的现金流量净额
+        - change_in_cash_and_equivalents: 现金及现金等价物净增加额
+        - effect_of_exchange_rate_changes: 汇率变动对现金及现金等价物的影响
+        - ending_cash_balance: 期末现金及现金等价物余额
+        - free_cash_flow: 自由现金流
+    """
+    if source == "sina":
+        return SinaAdapter().get_cash_flow(symbol=symbol)
+    raise ValueError(f"Unsupported data source: {source}")

akshare_one/insider.py

@@ -0,0 +1,35 @@
+"""内部交易数据模块
+
+包含上市公司内部交易相关功能
+"""
+
+from typing import Optional
+import pandas as pd
+from .adapters import XueQiuAdapter
+
+
+def get_inner_trade_data(source: str = "xueqiu", symbol: Optional[str] = None) -> "pd.DataFrame":
+    """获取雪球内部交易数据
+
+    Args:
+        source: 数据源 (目前支持 "xueqiu")
+        symbol: 可选股票代码，如"600000"，不传则返回所有数据
+
+    Returns:
+        pd.DataFrame:
+        - symbol: 股票代码
+        - issuer: 股票名称
+        - name: 变动人
+        - title: 董监高职务
+        - transaction_date: 变动日期(UTC时区)
+        - transaction_shares: 变动股数
+        - transaction_price_per_share: 成交均价
+        - shares_owned_after_transaction: 变动后持股数
+        - relationship: 与董监高关系
+        - is_board_director: 是否为董事会成员
+        - transaction_value: 交易金额(变动股数*成交均价)
+        - shares_owned_before_transaction: 变动前持股数
+    """
+    if source == "xueqiu":
+        return XueQiuAdapter().get_inner_trade_data(symbol=symbol)
+    raise ValueError(f"Unsupported data source: {source}")

akshare_one/news.py

@@ -0,0 +1,28 @@
+"""新闻数据模块
+
+包含股票新闻相关功能
+"""
+
+import pandas as pd
+from .adapters import EastMoneyAdapter
+
+
+def get_news_data(symbol: str, source: str = "eastmoney") -> "pd.DataFrame":
+    """获取个股新闻数据
+
+    Args:
+        symbol: 股票代码 (如 "300059")
+        source: 数据源 ('eastmoney')
+
+    Returns:
+        pd.DataFrame:
+        - keyword: 关键词
+        - title: 新闻标题
+        - content: 新闻内容
+        - publish_time: 发布时间
+        - source: 文章来源
+        - url: 新闻链接
+    """
+    if source == "eastmoney":
+        return EastMoneyAdapter().get_news_data(symbol=symbol)
+    raise ValueError(f"Unsupported data source: {source}")

akshare_one/stock.py

@@ -0,0 +1,86 @@
+"""股票市场数据模块
+
+包含股票历史数据和实时数据相关功能
+"""
+
+from typing import Optional
+import pandas as pd
+from .adapters import EastMoneyAdapter, SinaAdapter
+
+
+def get_hist_data(
+    symbol: str,
+    interval: str,
+    interval_multiplier: int = 1,
+    start_date: str = "1970-01-01",
+    end_date: str = "2030-12-31",
+    adjust: str = "none",
+    source: str = "eastmoney",
+) -> "pd.DataFrame":
+    """Get historical market data
+
+    Args:
+        symbol: 股票代码 (e.g. '600000')
+        interval: 时间间隔 ('second','minute','hour','day','week','month','year')
+        interval_multiplier: 时间间隔倍数 (e.g. 5 for 5 minutes)
+        start_date: 开始日期 (YYYY-MM-DD)
+        end_date: 结束日期 (YYYY-MM-DD)
+        adjust: 复权类型 ('none','qfq','hfq')
+        source: 数据源 ('eastmoney', 'sina')
+
+    Returns:
+        pd.DataFrame:
+        - timestamp: 时间戳(UTC时区)
+        - open: 开盘价
+        - high: 最高价
+        - low: 最低价
+        - close: 收盘价
+        - volume: 成交量
+    """
+    if source == "eastmoney":
+        return EastMoneyAdapter().get_hist_data(
+            symbol=symbol,
+            interval=interval,
+            interval_multiplier=interval_multiplier,
+            start_date=start_date,
+            end_date=end_date,
+            adjust=adjust,
+        )
+    elif source == "sina":
+        return SinaAdapter().get_hist_data(
+            symbol=symbol,
+            interval=interval,
+            interval_multiplier=interval_multiplier,
+            start_date=start_date,
+            end_date=end_date,
+            adjust=adjust,
+        )
+    raise ValueError(f"Unsupported data source: {source}")
+
+
+def get_realtime_data(
+    source: str = "eastmoney", symbol: Optional[str] = None
+) -> "pd.DataFrame":
+    """Get real-time market quotes
+
+    Args:
+        symbol: 股票代码 (如 "600000")
+        source: 数据源 ('eastmoney')
+
+    Returns:
+        pd.DataFrame:
+        - symbol: 股票代码
+        - price: 最新价
+        - change: 涨跌额
+        - pct_change: 涨跌幅(%)
+        - timestamp: 时间戳
+        - volume: 成交量(手)
+        - amount: 成交额(元)
+        - open: 今开
+        - high: 最高
+        - low: 最低
+        - prev_close: 昨收
+    """
+    if source == "eastmoney":
+        return EastMoneyAdapter().get_realtime_data(symbol=symbol)
+    raise ValueError(f"Unsupported data source: {source}")

akshare_one-0.1.0.dist-info/METADATA

@@ -0,0 +1,61 @@
+Metadata-Version: 2.4
+Name: akshare-one
+Version: 0.1.0
+Summary: Add your description here
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: akshare>=1.16.64
+Requires-Dist: cachetools>=5.5.2
+Dynamic: license-file
+
+# AKShare One
+
+**AKShare One** 是一个标准化中国金融市场数据接口，基于 [AKShare](https://github.com/akfamily/akshare) 二次封装，解决AKShare多数据源输入输出不统一的问题。
+
+## 项目背景
+
+AKShare提供了丰富的中国金融市场数据，但不同数据源的：
+- 股票代码格式不统一（如东方财富和新浪使用不同格式）
+- 返回数据结构不一致
+- 参数命名和用法有差异
+
+AKShare One希望通过统一封装，提供：
+- 标准化的股票代码格式
+- 一致的数据返回结构
+- 简化的API参数
+
+## 核心功能
+
+### 目前仅实现了以下功能：
+- 历史数据 (`get_hist_data`)
+- 实时行情 (`get_realtime_data`) 
+- 个股新闻 (`get_news_data`)
+- 财务数据 (资产负债表/利润表/现金流量表)
+- 内部交易 (`get_inner_trade_data`)
+
+### 标准化处理
+- 统一时间戳为UTC
+- 自动处理复权数据
+- 清理异常值和缺失数据
+- 统一列名和数据类型
+
+## 快速开始
+
+使用示例：
+```python
+from akshare_one import get_hist_data, get_realtime_data
+
+# 获取历史数据
+df_hist = get_hist_data(
+    symbol="600000",
+    interval="day",
+    adjust="hfq"
+)
+
+# 获取实时数据
+df_realtime = get_realtime_data(symbol="600000")
+```
+
+## API文档
+详细API说明请参考 [docs/api.md](docs/api.md)

akshare_one-0.1.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+akshare_one/__init__.py,sha256=xWUyTnh1Tv-2mEPxDmk5giUPwhrsoAuZcyoW6mAbX4k,923
+akshare_one/financial.py,sha256=0vPm8LYzV-UIaPIk5GeEJuuCXYYXtWp5h1AYo-9ms38,5005
+akshare_one/insider.py,sha256=hy1eM0Fa2J4uHU3vl-VDm4uB8zYTSUTbonnxOxbBuGc,1193
+akshare_one/news.py,sha256=qUeX_1SnViDXBAb4Gcl28ow1qvMugEEPL75JgJhLbCA,707
+akshare_one/stock.py,sha256=oGd432iZ6_hr63L4VG2iT36wOQ2q8RI8QUOflFY-OPg,2466
+akshare_one/adapters/__init__.py,sha256=JrpGJ80drrU9Imc3L_gZ5Z90zyMd3PiJ5dG86VAEnmA,252
+akshare_one/adapters/eastmoney.py,sha256=OP5zNbSRVEKfKX0ikC6onABuifxoWEAbBNYbk_GO3lU,11783
+akshare_one/adapters/sina.py,sha256=jcpddoEJI7hEIRkxlZl7Ee1PAyDglhsOZGXFOgdnpGs,17412
+akshare_one/adapters/xueqiu.py,sha256=bwRNTDnXrXJxp4cFG0Uj5LVLBvCxFyxKOHAJS1nnKaM,3624
+akshare_one/adapters/cache/cache.py,sha256=GhADIdLuh_IFpPXrkhTLv-joTcuh_vC12kRdqT-cpvI,378
+akshare_one-0.1.0.dist-info/licenses/LICENSE,sha256=Gg6A1GNSJCZWQ73aHJ7TXOa0i8RQ3FejZCTZ6Db07cU,1066
+akshare_one-0.1.0.dist-info/METADATA,sha256=oHAPghYP-c2rNCZGcqxEYacIxV9pOwuK0eTpnk0l-oQ,1586
+akshare_one-0.1.0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+akshare_one-0.1.0.dist-info/top_level.txt,sha256=kNiucyLVAGa89wmUSpXbBLWD7pF_RuahuiaOfLHZSyw,12
+akshare_one-0.1.0.dist-info/RECORD,,

akshare_one-0.1.0.dist-info/WHEEL

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

akshare_one-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 zwldarren
+
+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.

akshare_one-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+akshare_one