python金融数据分析和可视化--03利用Akshare获取股票数据

02利用Akshare获取股票数据

1. AKShare 的介绍

AKShare 是基于 Python 的财经数据接口库，目的是实现对股票、期货、期权、基金、外汇、债券、指数、加密货币等金融产品的基本面数据、实时和历史行情数据、衍生数据从数据采集、数据清洗到数据落地的一套工具，主要用于学术研究目的。

AKShare 的特点是获取的是相对权威的财经数据网站公布的原始数据，通过利用原始数据进行各数据源之间的交叉验证，进而再加工，从而得出科学的结论。

2. 安装 AKShare

pip install akshare

3. 获取股票数据

AKShare 股票数据
AKShare github

1. # 股票市场总貌
2. import akshare as ak
5. # 上海证券交易所
6. # http://www.sse.com.cn/market/stockdata/statistic/
7. def sh_df():
8. stock_sse_summary_df = ak.stock_sse_summary()
9. print(stock_sse_summary_df)
12. # 深圳证券交易所
13. # 证券类别统计
14. # http://www.szse.cn/market/overview/index.html
15. def sz_df():
16. stock_szse_summary_df = ak.stock_szse_summary()
17. print(stock_szse_summary_df)
20. # 深圳证券交易所
21. # 地区交易排序
22. # http://www.szse.cn/market/overview/index.html
23. def sz_area():
24. stock_szse_area_summary_df = ak.stock_szse_area_summary(date="202203")
25. print(stock_szse_area_summary_df)
28. # 深圳证券交易所
29. # 股票行业成交
30. # http://docs.static.szse.cn/www/market/periodical/month/W020220511355248518608.html
31. def sz_sector():
32. stock_szse_sector_summary_df = ak.stock_szse_sector_summary(symbol="当年", date="202204")
33. print(stock_szse_sector_summary_df)
35. # 上海证券交易所
36. # 每日概况
37. # http://www.sse.com.cn/market/stockdata/overview/day/
38. def sh_day():
39. stock_sse_deal_daily_df = ak.stock_sse_deal_daily(date="20201111")
40. print(stock_sse_deal_daily_df)
43. def get_account_statistics():
44. # 股票账户统计月度
45. """
46. 输出参数
47. 名称 类型 描述
48. 数据日期 object -
49. 新增投资者-数量 float64 注意单位: 万户
50. 新增投资者-环比 float64 -
51. 新增投资者-同比 float64 -
52. 期末投资者-总量 float64 注意单位: 万户
53. 期末投资者-A股账户 float64 注意单位: 万户
54. 期末投资者-B股账户 float64 注意单位: 万户
55. 沪深总市值 float64 -
56. 沪深户均市值 float64 注意单位: 万
57. 上证指数-收盘 float64 -
58. 上证指数-涨跌幅 float64 -
59. """
60. account = ak.stock_account_statistics_em()
61. account.set_index("数据日期", inplace=True) # 设置索引值
62. account.to_csv("I:\\bianchengxx\\pythonxx\\backtrader_001\\datas\\stock_account_statistics.csv")
63. print(account)
67. if __name__ == '__main__':
68. # sh_df()
69. # sz_df()
70. # sz_area()
71. # sz_sector()
72. # sh_day()
73. get_account_statistics()

1. # 个股信息查询
2. # http://quote.eastmoney.com/concept/sh603777.html?from=classic
4. import akshare as ak
6. df = ak.stock_individual_info_em(symbol="002624")
7. print(df)

1. # 实时行情数据-东财
2. # 沪深京 A 股
3. # http://quote.eastmoney.com/center/gridlist.html#hs_a_board
4. import akshare as ak
6. # 实时行情数据-东财
7. # 沪深京 A 股
8. # 单次返回所有沪深京 A 股上市公司的实时行情数据
9. def em_spot():
10. stock_zh_a_spot_em_df = ak.stock_zh_a_spot_em()
11. print(stock_zh_a_spot_em_df)
14. # 实时行情数据-东财
15. # 沪 A 股
16. # http://quote.eastmoney.com/center/gridlist.html#sh_a_board
17. def em_sha_spot():
18. stock_sh_a_spot_em_df = ak.stock_sh_a_spot_em()
19. print(stock_sh_a_spot_em_df)
22. # 实时行情数据-东财
23. # 深 A 股
24. # http://quote.eastmoney.com/center/gridlist.html#sz_a_board
25. def em_sza_spot():
26. stock_sz_a_spot_em_df = ak.stock_sz_a_spot_em()
27. print(stock_sz_a_spot_em_df)
30. # 实时行情数据-东财
31. # 京 A 股
32. # http://quote.eastmoney.com/center/gridlist.html#bj_a_board
33. def em_bja_spot():
34. stock_bj_a_spot_em_df = ak.stock_bj_a_spot_em()
35. print(stock_bj_a_spot_em_df)
38. # 实时行情数据-东财
39. # 新股
40. # http://quote.eastmoney.com/center/gridlist.html#newshares
41. def em_new_spot():
42. stock_new_a_spot_em_df = ak.stock_new_a_spot_em()
43. print(stock_new_a_spot_em_df)
46. # 实时行情数据-东财
47. # 科创板
48. # http://quote.eastmoney.com/center/gridlist.html#hs_a_board
49. def em_kc_spot():
50. stock_kc_a_spot_em_em_df = ak.stock_kc_a_spot_em()
51. print(stock_kc_a_spot_em_em_df)
54. # 实时行情数据-新浪
55. # http://vip.stock.finance.sina.com.cn/mkt/#hs_a
56. def xl_a_spot():
57. stock_zh_a_spot_df = ak.stock_zh_a_spot()
58. print(stock_zh_a_spot_df)
61. if __name__ == "__main__":
62. em_spot()
63. # em_sha_spot()
64. # em_sza_spot()

1. # 历史行情数据-东财
2. # https://quote.eastmoney.com/concept/sh603777.html?from=classic
3. import akshare as ak
4. import pandas as pd
6. pd.set_option('expand_frame_repr', False) # True就是可以换行显示。设置成False的时候不允许换行
7. pd.set_option('display.max_columns', None) # 显示所有列
8. # pd.set_option('display.max_rows', None) # 显示所有行
9. pd.set_option('colheader_justify', 'centre') # 显示居中
12. def a_hist():
13. # period
14. # str
15. # choice of {'daily', 'weekly', 'monthly'}
16. # start_date
17. # str
18. # 开始查询的日期
19. # end_date
20. # str
21. # 结束查询的日期
22. # adjust
23. # str
24. # 默认返回不复权的数据;
25. # qfq: 返回前复权后的数据;
26. # hfq: 返回后复权后的数据
27. stock_zh_a_hist_df = ak.stock_zh_a_hist(symbol="002624", period="weekly", start_date="20190301", end_date='20230907',
28. adjust="qfq")
29. print(stock_zh_a_hist_df)
33. # 分时数据-东财
34. # http://quote.eastmoney.com/concept/sh603777.html?from=classic
35. # period str choice of {'1', '5', '15', '30', '60'};
36. # adjust str choice of {'', 'qfq', 'hfq'}; '': 不复权, 'qfq': 前复权, 'hfq': 后复权,
37. # 其中 1 分钟数据返回近 5 个交易日数据且不复权
38. def a_hist_min():
39. stock_zh_a_hist_min_em_df = ak.stock_zh_a_hist_min_em(symbol="002624", start_date="2023-01-01 09:30:00", end_date="2023-02-03 15:00:00", period='30', adjust='')
40. print(stock_zh_a_hist_min_em_df)
43. if __name__ == "__main__":
44. a_hist()
45. # a_hist_min()

4. 获取股票数据本地存储

1. import akshare as ak
2. import pandas as pd
4. pd.set_option('expand_frame_repr', False) # True就是可以换行显示。设置成False的时候不允许换行
5. pd.set_option('display.max_columns', None) # 显示所有列
6. pd.set_option('display.max_rows', None) # 显示所有行
7. pd.set_option('colheader_justify', 'centre') # 显示居中
10. def download_hist(symbol="002624", period="daily", start="1990101", end="20230318", adjust="qfq"):
11. stock_zh_a_hist_df = ak.stock_zh_a_hist(symbol=symbol, period=period, start_date=start, end_date=end,
12. adjust=adjust)
13. stock_zh_a_hist_df.sort_values("日期", inplace=True)
14. stock_zh_a_hist_df.set_index("日期", inplace=True)
15. if period=="daily":
16. stock_zh_a_hist_df.to_csv("I:\\akshare_stock\\stock_datas\\day\\{}.csv".format(symbol))
17. elif period=="weekly":
18. stock_zh_a_hist_df.to_csv("I:\\akshare_stock\\stock_datas\\week\\{}.csv".format(symbol))
19. elif period=="monthly":
20. stock_zh_a_hist_df.to_csv("I:\\akshare_stock\\stock_datas\\month\\{}.csv".format(symbol))
21. else:
22. print("period错误")
25. def download_hist_min(symbol="002624", start="1990-01-01 09:30:00", end="2023-02-03 15:00:00", period='30', adjust='qfq'):
26. stock_zh_a_hist_min_em_df = ak.stock_zh_a_hist_min_em(symbol=symbol, start_date=start, end_date=end, period=period, adjust=adjust)
27. stock_zh_a_hist_min_em_df.set_index("时间", inplace=True)
28. stock_zh_a_hist_min_em_df.to_csv("I:\\akshare_stock\\stock_datas\\minute\\"+symbol+"_{}.csv".format(period))
30. if __name__ == "__main__":
31. df = pd.read_csv("I:\\akshare_stock\\stock_datas\\stock_list.csv")
32. df.sort_values("symbol", inplace=True)
33. code = list(df["ts_code"])
34. print(len(code))
35. for period in ['daily', 'weekly', 'monthly']:
36. for i in range(0, len(code)):
37. symbol = code[i].rstrip('.SZHBJ')
38. download_hist(symbol=symbol, period=period)
39. print(symbol)
41. for period in ['1', '5', '15', '30', '60']:
42. for i in range(0, len(code)):
43. symbol = code[i].rstrip('.SZHBJ')
44. download_hist_min(symbol=symbol, period=period)
45. print(symbol)

5.将股票数据存到mysql数据库中

1. """
2. date:20210918
3. 将CSV文件写入到MySQL中
4. """
5. import pandas as pd
6. from sqlalchemy import create_engine
9. def connect_db(db):
10. engine = create_engine('mysql+pymysql://hao:671010@localhost:3306/{}?charset=utf8'.format(db))
11. return engine
14. def create_stock(akcode, db, date):
15. # 读取本地CSV文件
16. df = pd.read_csv(
17. 'I:\\akshare_stock\\stock_datas\\' + date + '\\{}.csv'.format(akcode))
18. engine = connect_db(db)
19. # name='stocklist'全部小写否则会报错
20. df.to_sql(name='ak_' + date + '_{}'.format(akcode), con=engine, index=False, if_exists='replace')
22. def create_min_stock(akcode, db, date):
23. # 读取本地CSV文件
24. df = pd.read_csv(
25. 'I:\\akshare_stock\\stock_datas\\minute\\'+akcode+'_{}.csv'.format(date))
26. engine = connect_db(db)
27. # name='stocklist'全部小写否则会报错
28. df.to_sql(name='ak_' + akcode + '_{}'.format(date), con=engine, index=False, if_exists='replace')
31. def read_csv(code):
32. df = pd.read_csv('I:\\akshare_stock\\stock_datas\\{}.csv'.format(code))
33. return df
36. stockDB = 'akshare_stock'
37. stockList = 'stock_list'
38. create_stock(akcode=stockList, db=stockDB, date="day")
39. df1 = read_csv(stockList)
40. df1.sort_values("ts_code", inplace=True)
41. li1 = list(df1['ts_code'])
42. for date in ["day", "week", "month"]:
43. for i in range(0, len(li1)):
44. codeStock = li1[i].rstrip('.SHZBJ')
45. create_stock(akcode=codeStock, db=stockDB, date=date)
46. print(codeStock)
48. for date in ['1', '5', '15', '30', '60']:
49. for i in range(0, len(li1)):
50. codeStock = li1[i].rstrip('.SHZBJ')
51. create_min_stock(akcode=codeStock, db=stockDB, date=date)
52. print(codeStock)