关于moodtx复权问题处理附相关代码

from mootdx.contrib.adjust import get_adjust_year

get_adjust_year(symbol='000001', year='2021', factor='01')

import datetime
import json
import re
import time
import requests
import numpy as np
import pandas as pd
def get_adjust_year(symbol=None, year=None, factor='00'):
    """采集同花顺复权数据
    # http://d.10jqka.com.cn/v2/line/hs_600036/01/2018.js
    # http://d.10jqka.com.cn/v6/line/hs_600000/00/all.js
    :param symbol: 股票代码
    :param factor: 前后复权 before 或 01 为前复权， after 或 02为后复权
    :param year: 年份
    :return: DataFrame
    """
    # 最大重试次数和重试间隔
    max_retries = 5
    retry_delay = 2
    year = datetime.datetime.now().year if not year else year
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/90.0.4430.212 Safari/537.36',
        'Referer': 'http://stockpage.10jqka.com.cn/',
        'DNT': '1',
    }
    if factor == 'before':
        factor = '01'
    if factor == 'after':
        factor = '02'
    if factor not in ['01', '02']:
        print('⚠️ 复权参数错误，factor 的值必须是: before, after, 01, 02')
        return pd.DataFrame()
    # 重试机制
    for attempt in range(max_retries):
        try:
            url = f'http://d.10jqka.com.cn/v2/line/hs_{symbol}/{factor}/{year}.js'
            response = requests.get(url, headers=headers)
            response.raise_for_status()
            # 处理特殊响应情况
            if 'window.location.href' in response.text:
                print('⚠️ 请求频繁，等待后重试...')
                time.sleep(retry_delay)
                continue
            # 提取并解析JSON数据
            text = re.findall(r'\((.*)\)', response.text)
            if not text:
                print('⚠️ 数据格式错误，尝试重新获取...')
                time.sleep(retry_delay)
                continue
            data_json = json.loads(text[0])
            data = data_json['data'].split(';')
            data = [item.split(',')[:8] for item in data]
            # 创建DataFrame
            columns = ['date', 'open', 'high', 'low', 'close', 'volume', 'amount', 'adjust']
            df = pd.DataFrame(data, columns=columns)
            df['date'] = pd.to_datetime(df['date'])
            df = df.set_index('date')
            # 转换数据类型
            for col in ['open', 'high', 'low', 'close', 'volume', 'amount', 'adjust']:
                df[col] = pd.to_numeric(df[col], errors='coerce')
            return df
        except requests.exceptions.RequestException as e:
            print(f'⚠️ 请求失败: {e}，尝试重试 ({attempt + 1}/{max_retries})...')
            time.sleep(retry_delay)
        except (json.JSONDecodeError, KeyError, IndexError) as e:
            print(f'⚠️ 数据解析错误: {e}，尝试重新获取...')
            time.sleep(retry_delay)
        except Exception as e:
            print(f'⚠️ 未知错误: {e}')
            break
    return pd.DataFrame()
# 使用示例
if __name__ == "__main__":
    # 获取前复权数据
    df = get_adjust_year(symbol="600036", year=2023, factor="before")
    if not df.empty:
        print("✅ 数据获取成功！")
        print(f"获取数据量: {len(df)} 条")
        print(f"日期范围: {df.index.min().strftime('%Y-%m-%d')} 至 {df.index.max().strftime('%Y-%m-%d')}")
        print("\n前5行数据预览:")
        print(df.head())
    else:
        print("❌ 数据获取失败，请检查参数或稍后重试")