stock_fundamentals/src/scripts/stock_daily_data_collector.py

# coding:utf-8

import requests
import pandas as pd
from sqlalchemy import create_engine, text
from datetime import datetime, timedelta
from tqdm import tqdm
from src.scripts.config import XUEQIU_HEADERS
import gc

class StockDailyDataCollector:
    """股票日线数据采集器类"""

    def __init__(self, db_url):
        self.engine = create_engine(
            db_url,
            pool_size=5,
            max_overflow=10,
            pool_recycle=3600
        )
        self.headers = XUEQIU_HEADERS

    def fetch_all_stock_codes(self):
        # 从gp_code_all获取股票代码
        query_all = "SELECT gp_code FROM gp_code_all"
        df_all = pd.read_sql(query_all, self.engine)
        codes_all = df_all['gp_code'].tolist()
        
        # 从gp_code_zs获取股票代码
        query_zs = "SELECT gp_code FROM gp_code_zs"
        df_zs = pd.read_sql(query_zs, self.engine)
        codes_zs = df_zs['gp_code'].tolist()

        # 从gp_code_hk获取股票代码
        query_hk = "SELECT gp_code FROM gp_code_hk"
        df_hk = pd.read_sql(query_hk, self.engine)
        codes_hk = df_hk['gp_code'].tolist()
        
        # 合并去重
        all_codes = list(set(codes_all + codes_zs + codes_hk))
        print(f"获取到股票代码: {len(codes_all)}个来自gp_code_all, {len(codes_zs)}个来自gp_code_zs, {len(codes_hk)}个来自gp_code_hk, 去重后共{len(all_codes)}个")
        return all_codes

    def fetch_daily_stock_data(self, symbol, begin, count=-1):
        """获取日线数据，count=-1表示最新一天，-2表示最近两天，-1800表示最近1800天"""
        url = f"https://stock.xueqiu.com/v5/stock/chart/kline.json?symbol={symbol}&begin={begin}&period=day&type=before&count={count}&indicator=kline,pe,pb,ps,pcf,market_capital,agt,ggt,balance"
        try:
            response = requests.get(url, headers=self.headers, timeout=20)
            return response.json()
        except Exception as e:
            print(f"Request error for {symbol}: {e}")
            return {'error_code': -1, 'error_description': str(e)}

    def transform_data(self, data, symbol):
        try:
            items = data['data']['item']
            columns = data['data']['column']
        except KeyError as e:
            print(f"KeyError for {symbol}: {e}")
            return None

        df = pd.DataFrame(items, columns=columns)
        df['symbol'] = symbol

        required_columns = ['timestamp', 'volume', 'open', 'high', 'low', 'close',
                            'chg', 'percent', 'turnoverrate', 'amount', 'symbol', 'pb', 'pe', 'ps']
        existing_columns = [col for col in required_columns if col in df.columns]
        df = df[existing_columns]

        if 'timestamp' in df.columns:
            df['timestamp'] = pd.to_datetime(df['timestamp'], unit='ms', utc=True).dt.tz_convert('Asia/Shanghai')

        return df

    def save_batch_to_database(self, batch):
        if batch:
            df_all = pd.concat(batch, ignore_index=True)
            df_all.to_sql('gp_day_data', self.engine, if_exists='append', index=False)

    def fetch_data_for_date(self, date=None):
        if date is None:
            start_date = datetime.now()
            date_str = start_date.strftime('%Y-%m-%d')
        else:
            start_date = datetime.strptime(date, '%Y-%m-%d')
            date_str = date

        delete_query = text("DELETE FROM gp_day_data WHERE `timestamp` LIKE :date_str")
        with self.engine.begin() as conn:
            conn.execute(delete_query, {"date_str": f"{date_str}%"})

        stock_codes = self.fetch_all_stock_codes()
        begin = int(start_date.replace(hour=0, minute=0, second=0, microsecond=0).timestamp() * 1000)

        batch_data = []
        for idx, symbol in enumerate(tqdm(stock_codes, desc=f"Fetching and saving daily stock data for {date_str}")):
            data = self.fetch_daily_stock_data(symbol, begin)

            if data.get('error_code') == 0:
                df = self.transform_data(data, symbol)
                if df is not None:
                    batch_data.append(df)
            else:
                print(f"Error fetching data for {symbol} on {date_str}: {data.get('error_description')}")

            if len(batch_data) >= 100:
                self.save_batch_to_database(batch_data)
                batch_data.clear()
                gc.collect()

        # Save remaining data
        if batch_data:
            self.save_batch_to_database(batch_data)
            gc.collect()

        self.engine.dispose()
        print(f"Daily data fetching and saving completed for {date_str}.")

    def delete_stock_history(self, symbol):
        """删除指定股票的全部历史数据"""
        delete_query = text("DELETE FROM gp_day_data WHERE symbol = :symbol")
        try:
            with self.engine.begin() as conn:
                conn.execute(delete_query, {"symbol": symbol})
            print(f"Deleted history for {symbol}")
            return True
        except Exception as e:
            print(f"Error deleting history for {symbol}: {e}")
            return False

    def refetch_and_save_history(self, symbol, days=1800):
        """重新获取并保存指定股票的长期历史数据"""
        print(f"Refetching last {days} days for {symbol}...")
        begin = int(datetime.now().timestamp() * 1000)
        data = self.fetch_daily_stock_data(symbol, begin, count=-days)
        if data.get('error_code') == 0:
            df = self.transform_data(data, symbol)
            if df is not None and not df.empty:
                self.save_batch_to_database([df])
                print(f"Successfully refetched and saved history for {symbol}.")
            else:
                print(f"No data transformed for {symbol} after refetch.")
        else:
            print(f"Error refetching history for {symbol}: {data.get('error_description')}")

    def check_and_fix_ex_rights_data(self):
        """
        检查所有股票是否发生除权，如果发生，则删除历史数据并重新获取。
        新逻辑：直接用API返回的上个交易日的时间戳去数据库查询，更稳妥。
        记录：除权日期、股票代码（）、
        """
        all_codes = self.fetch_all_stock_codes()
        ex_rights_log_data = []

        print("--- Step 1: Checking for ex-rights stocks ---")
        for symbol in tqdm(all_codes, desc="Comparing prices"):
            # 1. 从API获取最近两天的日线数据
            begin = int(datetime.now().timestamp() * 1000)
            data = self.fetch_daily_stock_data(symbol, begin, count=-2)

            api_timestamp_str = None
            api_close = None

            if data.get('error_code') == 0 and data.get('data', {}).get('item') and len(data['data']['item']) >= 2:
                try:
                    # API返回的数据是按时间升序的，[-2]是上个交易日
                    prev_day_data = data['data']['item'][-2]
                    columns = data['data']['column']

                    timestamp_index = columns.index('timestamp')
                    close_index = columns.index('close')

                    api_timestamp_ms = prev_day_data[timestamp_index]
                    api_close = prev_day_data[close_index]

                    # 将毫秒时间戳转换为'YYYY-MM-DD'格式，用于数据库查询
                    api_timestamp_str = pd.to_datetime(api_timestamp_ms, unit='ms', utc=True).tz_convert('Asia/Shanghai').strftime('%Y-%m-%d')
                except (ValueError, IndexError, TypeError) as e:
                    print(f"\nError parsing API data for {symbol}: {e}")
                    continue # 处理下一只股票
            else:
                # 获取API数据失败或数据不足，跳过此股票
                continue

            # 如果未能从API解析出上个交易日的数据，则跳过
            if api_timestamp_str is None or api_close is None:
                continue

            # 2. 根据API返回的时间戳，从数据库查询当天的收盘价
            db_close = None
            query = text("SELECT `close` FROM gp_day_data WHERE symbol = :symbol AND `timestamp` LIKE :date_str")
            try:
                with self.engine.connect() as conn:
                    result = conn.execute(query, {"symbol": symbol, "date_str": f"{api_timestamp_str}%"}).fetchone()
                db_close = result[0] if result else None
            except Exception as e:
                print(f"\nError getting DB close for {symbol} on {api_timestamp_str}: {e}")
                continue

            # 3. 比较价格
            if db_close is not None:
                # 注意：数据库中取出的db_close可能是Decimal类型，需要转换
                if not abs(float(db_close) - api_close) < 0.001:
                    print(f"\nEx-rights detected for {symbol} on {api_timestamp_str}: DB_close={db_close}, API_close={api_close}")
                    ex_rights_log_data.append({
                        'symbol': symbol,
                        'date': datetime.now().strftime('%Y-%m-%d'),
                        'db_price': float(db_close),
                        'api_price': api_close,
                        'log_time': datetime.now()
                    })
            # 如果数据库当天没有数据，我们无法比较，所以不处理。
            # 这可能是新股或之前采集失败，不属于除权范畴。

        # 4. 对发生除权的股票进行记录和修复
        if not ex_rights_log_data:
            print("\n--- No ex-rights stocks found. Data is consistent. ---")
            self.engine.dispose()
            return

        # 在修复前，先将日志保存到数据库
        self.save_ex_rights_log(ex_rights_log_data)

        # 从日志数据中提取出需要修复的股票代码列表
        ex_rights_stocks = [item['symbol'] for item in ex_rights_log_data]

        print(f"\n--- Step 2: Found {len(ex_rights_stocks)} stocks to fix: {ex_rights_stocks} ---")
        for symbol in tqdm(ex_rights_stocks, desc="Fixing data"):
            if self.delete_stock_history(symbol):
                self.refetch_and_save_history(symbol, days=1800)
        
        self.engine.dispose()
        print("\n--- Ex-rights data fixing process completed. ---")

    def save_ex_rights_log(self, log_data: list):
        """将除权日志保存到数据库"""
        if not log_data:
            return
        
        print(f"--- Saving {len(log_data)} ex-rights events to log table... ---")
        try:
            df = pd.DataFrame(log_data)
            # 确保列名与数据库字段匹配
            df = df.rename(columns={
                'symbol': 'stock_code',
                'date': 'change_date',
                'db_price': 'before_price',
                'api_price': 'after_price',
                'log_time': 'update_time'
            })
            df.to_sql('gp_ex_rights_log', self.engine, if_exists='append', index=False)
            print("--- Ex-rights log saved successfully. ---")
        except Exception as e:
            print(f"!!! Error saving ex-rights log: {e}")

def collect_stock_daily_data(db_url, date=None):
    collector = StockDailyDataCollector(db_url)
    collector.fetch_data_for_date(date)
    collector.check_and_fix_ex_rights_data()

if __name__ == "__main__":
    db_url = 'mysql+pymysql://root:Chlry#$.8@192.168.18.199:3306/db_gp_cj'
    
    # --- 使用方式 ---
    # 1. 日常采集当天数据
    # collect_stock_daily_data(db_url)

    # 2. 手动执行除权检查和数据修复
    # collector = StockDailyDataCollector(db_url)
    # collector.check_and_fix_ex_rights_data()