Fetch Hong Kong market financial data to csv

hong_kong_market.py

@@ -0,0 +1,306 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+香港市场财报数据获取脚本 V2
+"""
+
+import akshare as ak
+import pandas as pd
+import numpy as np
+from datetime import datetime
+import warnings
+import time
+from tqdm import tqdm
+import os
+
+warnings.filterwarnings("ignore")
+
+# 导入工具函数
+from src.utils import *
+
+
+def get_hk_stock_list():
+    """获取香港股票列表"""
+    try:
+        # 获取港股现货行情
+        print("正在获取香港股票列表...")
+        hk_spot = ak.stock_hk_spot_em()
+
+        # 筛选主板股票（排除创业板等）
+        # 港股代码规则：主板股票代码一般是5位数，00001-09999
+        hk_spot = hk_spot[hk_spot['代码'].str.len() == 5]
+        hk_spot = hk_spot[hk_spot['代码'].str.startswith('0')]
+
+        # 过滤掉没有价格的股票
+        hk_spot = hk_spot[hk_spot['最新价'] > 0]
+        hk_spot = hk_spot[~hk_spot['最新价'].isna()]
+
+        print(f"获取到 {len(hk_spot)} 只有效香港股票")
+        return hk_spot
+    except Exception as e:
+        print(f"获取香港股票列表失败: {e}")
+        return pd.DataFrame()
+
+
+def get_hk_financial_indicators(code):
+    """获取港股财务指标数据"""
+    try:
+        # 获取财务指标
+        financial_data = ak.stock_financial_hk_analysis_indicator_em(
+            symbol=code, 
+            indicator="按报告期"
+        )
+        return financial_data
+    except Exception as e:
+        return pd.DataFrame()
+
+
+def safe_float(value, default=0):
+    """安全转换为浮点数"""
+    try:
+        if pd.isna(value) or value is None or value == '-':
+            return default
+        return float(value)
+    except:
+        return default
+
+
+def calculate_growth_rate(current, previous):
+    """计算增长率"""
+    if previous == 0 or pd.isna(previous):
+        return 0
+    return (current - previous) / abs(previous)
+
+
+def process_hk_stock(code, hk_spot_info):
+    """处理单只港股数据"""
+    try:
+        # 获取实时行情信息
+        stock_info = hk_spot_info[hk_spot_info['代码'] == code]
+        if stock_info.empty:
+            print(f"{code} 未找到实时信息")
+            return None
+
+        # 基础信息
+        name = stock_info['名称'].values[0]
+        current_price = stock_info['最新价'].values[0]
+        volume = stock_info['成交量'].values[0] if '成交量' in stock_info.columns else 0
+
+        # 跳过无效数据
+        if pd.isna(current_price) or current_price == 0:
+            print(f"{code} 无有效价格")
+            return None
+
+        # 获取财务指标数据
+        financial_data = get_hk_financial_indicators(code)
+
+        if financial_data.empty:
+            print(f"{code} 无财务数据")
+            return None
+
+        # 获取最新一期数据
+        latest_data = financial_data.iloc[0]
+
+        # 构建基础结果
+        result = {
+            "股票名称": name,
+            "代码": code,
+            "行业": "港股",  # 暂时使用固定值
+            "总市值": 0,  # 需要计算
+            "当前价格": current_price,
+            "总股本": 0,  # 需要从其他数据源获取
+        }
+
+        # 从财务指标中提取数据
+        # 每股收益
+        eps = safe_float(latest_data.get('BASIC_EPS', 0))
+        # 每股净资产
+        bps = safe_float(latest_data.get('BPS', 0))
+        # 每股经营现金流
+        cfps = safe_float(latest_data.get('PER_NETCASH_OPERATE', 0))
+
+        # 计算市盈率、市净率等
+        if eps > 0:
+            pe_ratio = current_price / eps
+        else:
+            pe_ratio = 0
+
+        if bps > 0:
+            pb_ratio = current_price / bps
+        else:
+            pb_ratio = 0
+
+        # 获取营业收入和净利润相关数据
+        revenue = safe_float(latest_data.get('TOTAL_OPERATE_INCOME', 0))
+        net_profit = safe_float(latest_data.get('NETPROFIT', 0))
+        deducted_profit = safe_float(latest_data.get('DEDUCTNP', 0))
+
+        # 获取总资产和总负债
+        total_assets = safe_float(latest_data.get('TOT_ASSETS', 0))
+        total_liabilities = safe_float(latest_data.get('TOT_LIAB', 0))
+
+        # 填充财务数据
+        result.update({
+            "扣非净利润-TTM": to_yi_round2(deducted_profit) if deducted_profit else 0,
+            "扣非净利润同比-TTM": 0,  # 需要历史数据计算
+            "扣非利润年复合同比": 0,
+            "扣非净利润增速-TTM": 0,
+            "当季扣非净利润同比": 0,
+            "当季扣非净利润增速": 0,
+            "营业总收入-TTM": to_yi_round2(revenue) if revenue else 0,
+            "营业总收入同比-TTM": 0,
+            "营业总收入年复合同比": 0,
+            "营业总收入增速-TTM": 0,
+            "当季营业总收入同比": 0,
+            "当季营业总收入增速": 0,
+            "当季毛利率": 0,
+            "当季毛利率同比": 0,
+            "当季毛利率同比增速": 0,
+            "自由现金流": to_yi_round2(cfps * bps) if cfps and bps else 0,
+            "自由现金流复合增长率": 0,
+            "总负债": to_yi_round2(total_liabilities),
+            "总资产": to_yi_round2(total_assets),
+            "少数股东损益": 0,
+            "当季三费同比": 0,
+            "商誉": 0,
+            "商誉占比": 0,
+            "市净率": pb_ratio,
+            "市销率": current_price * volume / revenue if revenue > 0 else 0,
+            "市盈率-TTM": pe_ratio,
+            "市盈率-TTM(财报)": pe_ratio,
+            "ROE": safe_float(latest_data.get('AVG_ROE', 0)),
+            "ROE_qualified-TTM": safe_float(latest_data.get('DILUTED_ROE', 0)),
+            "每股分红": 0,
+            "股息率": 0,
+            "分红率": 0,
+            "每股收益": eps,
+            "每股收益-占比": eps / current_price if current_price > 0 else 0,
+            "每股FCF": cfps,
+            "每股FCF-占比": cfps / current_price if current_price > 0 else 0,
+            "每股资产": bps,
+            "每股资产-占比": bps / current_price if current_price > 0 else 0,
+            "每股负债": bps * (total_liabilities / total_assets) if total_assets > 0 else 0,
+            "每股负债-占比": (bps * (total_liabilities / total_assets)) / current_price if total_assets > 0 and current_price > 0 else 0,
+        })
+
+        # 如果有多期数据，计算同比增长
+        if len(financial_data) > 4:
+            try:
+                # 获取去年同期数据
+                last_year_data = financial_data.iloc[4]
+
+                # 计算扣非净利润同比
+                last_deducted_profit = safe_float(last_year_data.get('DEDUCTNP', 0))
+                if last_deducted_profit != 0:
+                    result["扣非净利润同比-TTM"] = calculate_growth_rate(deducted_profit, last_deducted_profit)
+                    result["扣非净利润增速-TTM"] = result["扣非净利润同比-TTM"]
+
+                # 计算营业收入同比
+                last_revenue = safe_float(last_year_data.get('TOTAL_OPERATE_INCOME', 0))
+                if last_revenue != 0:
+                    result["营业总收入同比-TTM"] = calculate_growth_rate(revenue, last_revenue)
+                    result["营业总收入增速-TTM"] = result["营业总收入同比-TTM"]
+            except:
+                pass
+
+        return result
+
+    except Exception as e:
+        print(f"处理 {code} 时出错: {e}")
+        return None
+
+
+def main():
+    """主函数"""
+    try:
+        # 创建输出目录
+        os.makedirs("./daily_report", exist_ok=True)
+
+        # 获取港股列表
+        hk_stocks = get_hk_stock_list()
+        if hk_stocks.empty:
+            print("无法获取港股列表")
+            return
+
+        # 限制处理数量（测试时可以减少）
+        # hk_stocks = hk_stocks.head(50)  # 测试时只处理前50只
+
+        results = []
+        failed_count = 0
+
+        # 处理每只股票
+        for idx, row in tqdm(hk_stocks.iterrows(), total=len(hk_stocks), desc="处理港股数据"):
+            code = row['代码']
+            result = process_hk_stock(code, hk_stocks)
+
+            if result:
+                results.append(result)
+            else:
+                failed_count += 1
+
+            # 每处理10只股票暂停一下，避免请求过快
+            if (idx + 1) % 10 == 0:
+                time.sleep(1)
+
+        # 保存结果
+        if results:
+            df_results = pd.DataFrame(results)
+
+            # 确保所有必需的列都存在
+            required_columns = [
+                "股票名称", "代码", "行业", "总市值", "当前价格", "总股本",
+                "扣非净利润-TTM", "扣非净利润同比-TTM", "扣非利润年复合同比",
+                "扣非净利润增速-TTM", "当季扣非净利润同比", "当季扣非净利润增速",
+                "营业总收入-TTM", "营业总收入同比-TTM", "营业总收入年复合同比",
+                "营业总收入增速-TTM", "当季营业总收入同比", "当季营业总收入增速",
+                "当季毛利率", "当季毛利率同比", "当季毛利率同比增速",
+                "自由现金流", "自由现金流复合增长率", "总负债", "总资产",
+                "少数股东损益", "当季三费同比", "商誉", "商誉占比",
+                "市净率", "市销率", "市盈率-TTM", "市盈率-TTM(财报)",
+                "ROE", "ROE_qualified-TTM", "每股分红", "股息率", "分红率",
+                "每股收益", "每股收益-占比", "每股FCF", "每股FCF-占比",
+                "每股资产", "每股资产-占比", "每股负债", "每股负债-占比"
+            ]
+
+            # 确保所有列都存在
+            for col in required_columns:
+                if col not in df_results.columns:
+                    df_results[col] = 0
+
+            # 按照要求的列顺序排列
+            df_results = df_results[required_columns]
+
+            # 格式化百分比列
+            percentage_columns = [
+                "扣非净利润同比-TTM", "扣非利润年复合同比", "扣非净利润增速-TTM",
+                "当季扣非净利润同比", "当季扣非净利润增速", "营业总收入同比-TTM",
+                "营业总收入年复合同比", "营业总收入增速-TTM", "当季营业总收入同比",
+                "当季营业总收入增速", "当季毛利率", "当季毛利率同比",
+                "当季毛利率同比增速", "自由现金流复合增长率", "当季三费同比",
+                "商誉占比", "股息率", "分红率", "每股收益-占比", "每股FCF-占比",
+                "每股资产-占比", "每股负债-占比"
+            ]
+
+            for col in percentage_columns:
+                df_results[col] = df_results[col].apply(lambda x: f"{x*100:.2f}%" if pd.notna(x) else "0.00%")
+
+            # 保存文件
+            save_path = f"./daily_report/hk_stock_data_{current_date}.csv"
+            df_results.to_csv(save_path, index=False, encoding='utf-8-sig')
+
+            print(f"\n处理完成！")
+            print(f"成功处理: {len(results)} 只股票")
+            print(f"失败处理: {failed_count} 只股票")
+            print(f"数据已保存到: {save_path}")
+
+        else:
+            print("没有成功处理任何股票数据")
+
+    except Exception as e:
+        print(f"程序执行出错: {e}")
+        import traceback
+        traceback.print_exc()
+
+
+if __name__ == "__main__":
+    main()