baostock下载所有股票的基础数据

PYTHON 2024年1月31日

股票列表格式

股票列表文件

all_stocks-副本下载

代码

  • 2024-1-31更新
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
import baostock as bs
import pandas as pd
 
 
class StockData:
    def __init__(self):
        self.df = pd.read_csv('all_stocks.csv', encoding='gbk', index_col='serial')
        self.code_list = self.df['code'].tolist()
        self.cols = ['name', 'code', 'close', 'peTTM', 'pbMRQ', 'psTTM', 'pcfNcfTTM', 'roeAvg', 'npMargin', 'gpMargin', 'netProfit', 'epsTTM',
                     'MBRevenue', 'totalShare', 'liqaShare', 'NRTurnRatio', 'NRTurnDays', 'INVTurnRatio', 'INVTurnDays', 'CATurnRatio', 'AssetTurnRatio',
                     'YOYEquity', 'YOYAsset', 'YOYNI', 'YOYEPSBasic', 'YOYPNI', 'currentRatio', 'quickRatio', 'cashRatio', 'YOYLiability', 'liabilityToAsset', 'assetToEquity',
                     'CAToAsset','NCAToAsset', 'tangibleAssetToAsset', 'ebitToInterest', 'CFOToOR', 'CFOToNP', 'CFOToGr','dupontROE', 'dupontAssetStoEquity',
                     'dupontAssetTurn', 'dupontPnitoni']
 
    def down_data(self):
        '''下载数据'''
        valuation_df = pd.DataFrame(columns=['code', 'close', 'peTTM', 'pbMRQ', 'psTTM', 'pcfNcfTTM'])
        profit_df = pd.DataFrame(
            columns=['code', 'pubDate', 'statDate', 'roeAvg',
                     'npMargin', 'gpMargin', 'netProfit', 'epsTTM',
                     'MBRevenue', 'totalShare', 'liqaShare']
        )
        operation_df = pd.DataFrame(
            columns=['code', 'pubDate', 'statDate', 'NRTurnRatio', 'NRTurnDays', 'INVTurnRatio', 'INVTurnDays', 'CATurnRatio', 'AssetTurnRatio']
        )
        growth_df = pd.DataFrame(
            columns=['code', 'pubDate', 'statDate', 'YOYEquity', 'YOYAsset', 'YOYNI', 'YOYEPSBasic', 'YOYPNI']
        )
        balance_df = pd.DataFrame(
            columns=['code', 'pubDate', 'statDate', 'currentRatio', 'quickRatio', 'cashRatio', 'YOYLiability', 'liabilityToAsset', 'assetToEquity']
        )
        cash_flow_df = pd.DataFrame(
            columns=['code', 'pubDate', 'statDate', 'CAToAsset','NCAToAsset', 'tangibleAssetToAsset', 'ebitToInterest', 'CFOToOR', 'CFOToNP', 'CFOToGr']
        )
        dupont_df = pd.DataFrame(
            columns=['code', 'pubDate', 'statDate', 'dupontROE', 'dupontAssetStoEquity', 'dupontAssetTurn', 'dupontPnitoni']
        )
        bs.login()
        for code in self.code_list:
            # 下载估值指标
            valuation_df = pd.concat([valuation_df, self.down_valuation(str(code))], ignore_index=True)
            # 下载季频盈利能力
            profit_df = pd.concat([profit_df, self.down_profit(str(code))], ignore_index=True)
            # 下载季频营运能力
            operation_df = pd.concat([operation_df, self.down_operation(str(code))], ignore_index=True)
            # 下载季频成长能力
            growth_df = pd.concat([growth_df, self.down_growth(str(code))], ignore_index=True)
            # 下载季频偿债能力
            balance_df = pd.concat([balance_df, self.down_balance(str(code))], ignore_index=True)
            # 下载季频现金流量
            cash_flow_df = pd.concat([cash_flow_df, self.down_cash_flow(str(code))], ignore_index=True)
            # 下载杜邦指数
            dupont_df = pd.concat([dupont_df, self.down_dupont(str(code))], ignore_index=True)
        bs.logout()
        all_data_list = [valuation_df, profit_df, operation_df, growth_df, balance_df, cash_flow_df, dupont_df]
        for d in all_data_list:
            self.df = self.merge_df(self.df, d)
        return self.df
 
    # 估值指标
    def down_valuation(self, code, start='2023-6-2', end='2023-12-31'):
        results = bs.query_history_k_data_plus(code,
                                               'code,close,peTTM,pbMRQ,psTTM,pcfNcfTTM',
                                               start_date=start, end_date=end,
                                               frequency="d", adjustflag="3")
        result_list = []
        while (results.error_code == '0') & results.next():
            result_list.append(results.get_row_data())
        if result_list:
            print('下载{}估值指标成功！'.format(code), result_list)
            results_valuation = pd.DataFrame([result_list[-1]], columns=results.fields)
            return results_valuation
 
    # 季频盈利能力
    def down_profit(self, code):
        profit_list = []
        rs_profit = bs.query_profit_data(code, year=2023, quarter=1)
        while (rs_profit.error_code == '0') & rs_profit.next():
            profit_list.append(rs_profit.get_row_data())
        if profit_list:
            result_profit = pd.DataFrame([profit_list[-1]], columns=rs_profit.fields)
            print('下载{}季频盈利能力成功！'.format(code), profit_list)
            return result_profit
 
    # 季频营运能力
    def down_operation(self, code):
        operation_list = []
        rs_operation = bs.query_operation_data(code, year=2023, quarter=1)
        while (rs_operation.error_code == '0') & rs_operation.next():
            operation_list.append(rs_operation.get_row_data())
        if operation_list:
            result_operation = pd.DataFrame([operation_list[-1]], columns=rs_operation.fields)
            print('下载{}季频营运能力成功！'.format(code), operation_list)
            return result_operation
 
    # 季频成长能力
    def down_growth(self, code):
        growth_list = []
        rs_growth = bs.query_growth_data(code, year=2023, quarter=1)
        while (rs_growth.error_code == '0') & rs_growth.next():
            growth_list.append(rs_growth.get_row_data())
        if growth_list:
            result_growth = pd.DataFrame([growth_list[-1]], columns=rs_growth.fields)
            print('下载{}季频成长能力成功！'.format(code), growth_list)
            return result_growth
 
    # 季频偿债能力
    def down_balance(self, code):
        balance_list = []
        rs_balance = bs.query_balance_data(code, year=2023, quarter=1)
        while (rs_balance.error_code == '0') & rs_balance.next():
            balance_list.append(rs_balance.get_row_data())
        if balance_list:
            result_balance = pd.DataFrame([balance_list[-1]], columns=rs_balance.fields)
            print('下载{}季频偿债能力成功！'.format(code), balance_list)
            return result_balance
 
    # 季频现金流量
    def down_cash_flow(self, code):
        cash_flow_list = []
        rs_cash_flow = bs.query_cash_flow_data(code, year=2023, quarter=1)
        while (rs_cash_flow.error_code == '0') & rs_cash_flow.next():
            cash_flow_list.append(rs_cash_flow.get_row_data())
        if cash_flow_list:
            result_cash_flow = pd.DataFrame([cash_flow_list[-1]], columns=rs_cash_flow.fields)
            print('下载{}季频现金流量成功！'.format(code), cash_flow_list)
            return result_cash_flow
 
    # 杜邦指数
    def down_dupont(self, code):
        dupont_list = []
        rs_dupont = bs.query_dupont_data(code, year=2023, quarter=1)
        while (rs_dupont.error_code == '0') & rs_dupont.next():
            dupont_list.append(rs_dupont.get_row_data())
        if dupont_list:
            result_profit = pd.DataFrame([dupont_list[-1]], columns=rs_dupont.fields)
            print('下载{}杜邦指数成功！'.format(code), dupont_list)
            return result_profit
 
    # 合并表格
    # 合并表格
    # 合并表格
    def merge_df(self, df1, df2):
        # 先删除可能会冲突的列
        df1 = df1.drop(['pubDate', 'statDate'], axis=1, errors='ignore')
        df2 = df2.drop(['pubDate', 'statDate'], axis=1, errors='ignore')
 
        # 合并数据框，指定suffixes参数
        all_df = pd.merge(df1, df2, on='code', suffixes=('_left', '_right'))
        return all_df
 
    # def merge_df(self, df1, df2):
    #     all_df = pd.merge(df1, df2, on='code')
    #     return all_df
 
    def to_file(self, df):
        df.to_csv('allStockData.csv', index=False)
 
if __name__ == '__main__':
        stockdata = StockData()
        daf = stockdata.down_data()
        daf = daf.loc[:, stockdata.cols]
        stockdata.to_file(daf)
2,031