research/stock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

modify src dir.

Browse Source
This commit is contained in:
oscar
2024-10-23 12:11:11 +08:00
parent a746b323aa
commit 593c6ce419
28 changed files with 4626 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
stockapp/src/crawling/__init__.py Normal file
View File

360
stockapp/src/crawling/fund_etf_em.py Normal file
View File

@ -0,0 +1,360 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
Date: 2023/1/4 12:18
Desc: 东方财富-ETF 行情
https://quote.eastmoney.com/sh513500.html
"""
from functools import lru_cache
import pandas as pd
import requests
def fund_etf_spot_em() -> pd.DataFrame:
"""
东方财富-ETF 实时行情
https://quote.eastmoney.com/center/gridlist.html#fund_etf
:return: ETF 实时行情
:rtype: pandas.DataFrame
"""
url = "http://88.push2.eastmoney.com/api/qt/clist/get"
params = {
"pn": "1",
"pz": "2000",
"po": "1",
"np": "1",
"ut": "bd1d9ddb04089700cf9c27f6f7426281",
"fltt": "2",
"invt": "2",
"wbp2u": "|0|0|0|web",
"fid": "f3",
"fs": "b:MK0021,b:MK0022,b:MK0023,b:MK0024",
"fields": "f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f12,f13,f14,f15,f16,f17,f18,f20,f21,f23,f24,f25,f22,f11,f62,f128,f136,f115,f152",
"_": "1672806290972",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["data"]["diff"])
temp_df.rename(
columns={
"f12": "代码",
"f14": "名称",
"f2": "最新价",
"f3": "涨跌幅",
"f4": "涨跌额",
"f5": "成交量",
"f6": "成交额",
"f17": "开盘价",
"f15": "最高价",
"f16": "最低价",
"f18": "昨收",
"f8": "换手率",
"f21": "流通市值",
"f20": "总市值",
},
inplace=True,
)
temp_df = temp_df[
[
"代码",
"名称",
"最新价",
"涨跌幅",
"涨跌额",
"成交量",
"成交额",
"开盘价",
"最高价",
"最低价",
"昨收",
"换手率",
"流通市值",
"总市值",
]
]
temp_df["最新价"] = pd.to_numeric(temp_df["最新价"], errors="coerce")
temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"], errors="coerce")
temp_df["涨跌额"] = pd.to_numeric(temp_df["涨跌额"], errors="coerce")
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"], errors="coerce")
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"], errors="coerce")
temp_df["开盘价"] = pd.to_numeric(temp_df["开盘价"], errors="coerce")
temp_df["最高价"] = pd.to_numeric(temp_df["最高价"], errors="coerce")
temp_df["最低价"] = pd.to_numeric(temp_df["最低价"], errors="coerce")
temp_df["昨收"] = pd.to_numeric(temp_df["昨收"], errors="coerce")
temp_df["换手率"] = pd.to_numeric(temp_df["换手率"], errors="coerce")
temp_df["流通市值"] = pd.to_numeric(temp_df["流通市值"], errors="coerce")
temp_df["总市值"] = pd.to_numeric(temp_df["总市值"], errors="coerce")
return temp_df
@lru_cache()
def _fund_etf_code_id_map_em() -> dict:
"""
东方财富-ETF 代码和市场标识映射
https://quote.eastmoney.com/center/gridlist.html#fund_etf
:return: ETF 代码和市场标识映射
:rtype: pandas.DataFrame
"""
url = "http://88.push2.eastmoney.com/api/qt/clist/get"
params = {
"pn": "1",
"pz": "5000",
"po": "1",
"np": "1",
"ut": "bd1d9ddb04089700cf9c27f6f7426281",
"fltt": "2",
"invt": "2",
"wbp2u": "|0|0|0|web",
"fid": "f3",
"fs": "b:MK0021,b:MK0022,b:MK0023,b:MK0024",
"fields": "f12,f13",
"_": "1672806290972",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["data"]["diff"])
temp_dict = dict(zip(temp_df["f12"], temp_df["f13"]))
return temp_dict
def fund_etf_hist_em(
symbol: str = "159707",
period: str = "daily",
start_date: str = "19700101",
end_date: str = "20500101",
adjust: str = "",
) -> pd.DataFrame:
"""
东方财富-ETF 行情
https://quote.eastmoney.com/sz159707.html
:param symbol: ETF 代码
:type symbol: str
:param period: choice of {'daily', 'weekly', 'monthly'}
:type period: str
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:param adjust: choice of {"qfq": "前复权", "hfq": "后复权", "": "不复权"}
:type adjust: str
:return: 每日行情
:rtype: pandas.DataFrame
"""
code_id_dict = _fund_etf_code_id_map_em()
adjust_dict = {"qfq": "1", "hfq": "2", "": "0"}
period_dict = {"daily": "101", "weekly": "102", "monthly": "103"}
url = "http://push2his.eastmoney.com/api/qt/stock/kline/get"
params = {
"fields1": "f1,f2,f3,f4,f5,f6",
"fields2": "f51,f52,f53,f54,f55,f56,f57,f58,f59,f60,f61,f116",
"ut": "7eea3edcaed734bea9cbfc24409ed989",
"klt": period_dict[period],
"fqt": adjust_dict[adjust],
"secid": f"{code_id_dict[symbol]}.{symbol}",
"beg": start_date,
"end": end_date,
"_": "1623766962675",
}
r = requests.get(url, params=params)
data_json = r.json()
if not (data_json["data"] and data_json["data"]["klines"]):
return pd.DataFrame()
temp_df = pd.DataFrame([item.split(",") for item in data_json["data"]["klines"]])
temp_df.columns = [
"日期",
"开盘",
"收盘",
"最高",
"最低",
"成交量",
"成交额",
"振幅",
"涨跌幅",
"涨跌额",
"换手率",
]
temp_df.index = pd.to_datetime(temp_df["日期"])
temp_df.reset_index(inplace=True, drop=True)
temp_df["开盘"] = pd.to_numeric(temp_df["开盘"])
temp_df["收盘"] = pd.to_numeric(temp_df["收盘"])
temp_df["最高"] = pd.to_numeric(temp_df["最高"])
temp_df["最低"] = pd.to_numeric(temp_df["最低"])
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"])
temp_df["振幅"] = pd.to_numeric(temp_df["振幅"])
temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"])
temp_df["涨跌额"] = pd.to_numeric(temp_df["涨跌额"])
temp_df["换手率"] = pd.to_numeric(temp_df["换手率"])
return temp_df
def fund_etf_hist_min_em(
symbol: str = "159707",
start_date: str = "1979-09-01 09:32:00",
end_date: str = "2222-01-01 09:32:00",
period: str = "5",
adjust: str = "",
) -> pd.DataFrame:
"""
东方财富-ETF 行情
https://quote.eastmoney.com/sz159707.html
:param symbol: ETF 代码
:type symbol: str
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:param period: choice of {'1', '5', '15', '30', '60'}
:type period: str
:param adjust: choice of {'', 'qfq', 'hfq'}
:type adjust: str
:return: 每日分时行情
:rtype: pandas.DataFrame
"""
code_id_dict = _fund_etf_code_id_map_em()
adjust_map = {
"": "0",
"qfq": "1",
"hfq": "2",
}
if period == "1":
url = "https://push2his.eastmoney.com/api/qt/stock/trends2/get"
params = {
"fields1": "f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13",
"fields2": "f51,f52,f53,f54,f55,f56,f57,f58",
"ut": "7eea3edcaed734bea9cbfc24409ed989",
"ndays": "5",
"iscr": "0",
"secid": f"{code_id_dict[symbol]}.{symbol}",
"_": "1623766962675",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(
[item.split(",") for item in data_json["data"]["trends"]]
)
temp_df.columns = [
"时间",
"开盘",
"收盘",
"最高",
"最低",
"成交量",
"成交额",
"最新价",
]
temp_df.index = pd.to_datetime(temp_df["时间"])
temp_df = temp_df[start_date:end_date]
temp_df.reset_index(drop=True, inplace=True)
temp_df["开盘"] = pd.to_numeric(temp_df["开盘"])
temp_df["收盘"] = pd.to_numeric(temp_df["收盘"])
temp_df["最高"] = pd.to_numeric(temp_df["最高"])
temp_df["最低"] = pd.to_numeric(temp_df["最低"])
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"])
temp_df["最新价"] = pd.to_numeric(temp_df["最新价"])
temp_df["时间"] = pd.to_datetime(temp_df["时间"]).astype(str)
return temp_df
else:
url = "http://push2his.eastmoney.com/api/qt/stock/kline/get"
params = {
"fields1": "f1,f2,f3,f4,f5,f6",
"fields2": "f51,f52,f53,f54,f55,f56,f57,f58,f59,f60,f61",
"ut": "7eea3edcaed734bea9cbfc24409ed989",
"klt": period,
"fqt": adjust_map[adjust],
"secid": f"{code_id_dict[symbol]}.{symbol}",
"beg": "0",
"end": "20500000",
"_": "1630930917857",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(
[item.split(",") for item in data_json["data"]["klines"]]
)
temp_df.columns = [
"时间",
"开盘",
"收盘",
"最高",
"最低",
"成交量",
"成交额",
"振幅",
"涨跌幅",
"涨跌额",
"换手率",
]
temp_df.index = pd.to_datetime(temp_df["时间"])
temp_df = temp_df[start_date:end_date]
temp_df.reset_index(drop=True, inplace=True)
temp_df["开盘"] = pd.to_numeric(temp_df["开盘"])
temp_df["收盘"] = pd.to_numeric(temp_df["收盘"])
temp_df["最高"] = pd.to_numeric(temp_df["最高"])
temp_df["最低"] = pd.to_numeric(temp_df["最低"])
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"])
temp_df["振幅"] = pd.to_numeric(temp_df["振幅"])
temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"])
temp_df["涨跌额"] = pd.to_numeric(temp_df["涨跌额"])
temp_df["换手率"] = pd.to_numeric(temp_df["换手率"])
temp_df["时间"] = pd.to_datetime(temp_df["时间"]).astype(str)
temp_df = temp_df[
[
"时间",
"开盘",
"收盘",
"最高",
"最低",
"涨跌幅",
"涨跌额",
"成交量",
"成交额",
"振幅",
"换手率",
]
]
return temp_df
if __name__ == "__main__":
fund_etf_spot_em_df = fund_etf_spot_em()
print(fund_etf_spot_em_df)
fund_etf_hist_hfq_em_df = fund_etf_hist_em(
symbol="513500",
period="daily",
start_date="20000101",
end_date="20230201",
adjust="hfq",
)
print(fund_etf_hist_hfq_em_df)
fund_etf_hist_qfq_em_df = fund_etf_hist_em(
symbol="513500",
period="daily",
start_date="20000101",
end_date="20230201",
adjust="qfq",
)
print(fund_etf_hist_qfq_em_df)
fund_etf_hist_em_df = fund_etf_hist_em(
symbol="513500",
period="daily",
start_date="20000101",
end_date="20230201",
adjust="",
)
print(fund_etf_hist_em_df)
fund_etf_hist_min_em_df = fund_etf_hist_min_em(
symbol="513500",
period="5",
adjust="hfq",
start_date="2023-01-01 09:32:00",
end_date="2023-01-04 14:40:00",
)
print(fund_etf_hist_min_em_df)

139
stockapp/src/crawling/stock_cpbd.py Normal file
View File

@ -0,0 +1,139 @@
# -*- coding:utf-8 -*-
# !/usr/bin/env python
import pandas as pd
import requests
import instock.core.tablestructure as tbs
__author__ = 'myh '
__date__ = '2023/5/7 '
def stock_cpbd_em(symbol: str = "688041") -> pd.DataFrame:
"""
东方财富网-个股-操盘必读
https://emweb.securities.eastmoney.com/PC_HSF10/OperationsRequired/Index?type=web&code=SH688041#
:param symbol: 带市场标识的股票代码
:type symbol: str
:return: 操盘必读
:rtype: pandas.DataFrame
"""
url = "https://emweb.securities.eastmoney.com/PC_HSF10/OperationsRequired/PageAjax"
if symbol.startswith("6"):
symbol = f"SH{symbol}"
else:
symbol = f"SZ{symbol}"
params = {"code": symbol}
r = requests.get(url, params=params)
data_json = r.json()
zxzb = data_json["zxzb"] # 主要指标
if len(zxzb) < 1:
return None
data_dict = zxzb[0]
zxzbOther = data_json["zxzbOther"] # 其它指标,计算出来
if len(zxzbOther) > 0:
zxzbOther = zxzbOther[0]
data_dict = {**data_dict, **zxzbOther}
# zxzbhq = data_json["zxzbhq"] # 其它指标,计算出来
# if len(zxzbhq) > 0:
# data_dict = {**data_dict, **zxzbhq}
_ssbks = data_json["ssbk"] # 所属板块
ssbk = None
for s in _ssbks:
_v = s.get('BOARD_NAME')
if _v is not None:
if ssbk is None:
ssbk = f"{_v}"
else:
ssbk = f"{ssbk}、{_v}"
data_dict["BOARD_NAME"] = ssbk
gdrs = data_json["gdrs"] # 股东分析
if len(gdrs) > 0:
gdrs = gdrs[0]
data_dict = {**data_dict, **gdrs}
lhbd = data_json["lhbd"] # 龙虎榜单
if len(lhbd) > 0:
lhbd = lhbd[0]
lhbd["LHBD_DATE"] = lhbd.pop("TRADE_DATE")
data_dict = {**data_dict, **lhbd}
dzjy = data_json["dzjy"] # 大宗交易
if len(dzjy) > 0:
dzjy = dzjy[0]
dzjy["DZJY_DATE"] = dzjy.pop("TRADE_DATE")
data_dict = {**data_dict, **dzjy}
rzrq = data_json["rzrq"] # 融资融券
if len(rzrq) > 0:
rzrq = rzrq[0]
rzrq["RZRQ_DATE"] = rzrq.pop("TRADE_DATE")
data_dict = {**data_dict, **rzrq}
tbs.CN_STOCK_CPBD
# temp_df["报告期"] = pd.to_datetime(temp_df["报告期"], errors="coerce").dt.date
# temp_df["每股收益"] = pd.to_numeric(temp_df["每股收益"], errors="coerce")
# temp_df["每股净资产"] = pd.to_numeric(temp_df["每股净资产"], errors="coerce")
# temp_df["每股经营现金流"] = pd.to_numeric(temp_df["每股经营现金流"], errors="coerce")
# temp_df["每股公积金"] = pd.to_numeric(temp_df["每股公积金"], errors="coerce")
# temp_df["每股未分配利润"] = pd.to_numeric(temp_df["每股未分配利润"], errors="coerce")
# temp_df["加权净资产收益率"] = pd.to_numeric(temp_df["加权净资产收益率"], errors="coerce")
# temp_df["毛利率"] = pd.to_numeric(temp_df["毛利率"], errors="coerce")
# temp_df["资产负债率"] = pd.to_numeric(temp_df["资产负债率"], errors="coerce")
# temp_df["营业收入"] = pd.to_numeric(temp_df["营业收入"], errors="coerce")
# temp_df["营业收入滚动环比增长"] = pd.to_numeric(temp_df["营业收入同比增长"], errors="coerce")
# temp_df["营业收入同比增长"] = pd.to_numeric(temp_df["营业收入同比增长"], errors="coerce")
# temp_df["归属净利润"] = pd.to_numeric(temp_df["归属净利润"], errors="coerce")
# temp_df["归属净利润滚动环比增长"] = pd.to_numeric(temp_df["归属净利润滚动环比增长"], errors="coerce")
# temp_df["归属净利润同比增长"] = pd.to_numeric(temp_df["归属净利润同比增长"], errors="coerce")
# temp_df["扣非净利润"] = pd.to_numeric(temp_df["归属净利润"], errors="coerce")
# temp_df["扣非净利润滚动环比增长"] = pd.to_numeric(temp_df["扣非净利润滚动环比增长"], errors="coerce")
# temp_df["扣非净利润同比增长"] = pd.to_numeric(temp_df["扣非净利润同比增长"], errors="coerce")
# temp_df["总股本"] = pd.to_numeric(temp_df["总股本"], errors="coerce")
# temp_df["已流通股份"] = pd.to_numeric(temp_df["已流通股份"], errors="coerce")
def stock_zjlx_em(symbol: str = "688041") -> pd.DataFrame:
"""
东方财富网-个股-资金流向
https://data.eastmoney.com/zjlx/688041.html
:param symbol: 带市场标识的股票代码
:type symbol: str
:return: 操盘必读
:rtype: pandas.DataFrame
"""
url = "https://push2his.eastmoney.com/api/qt/stock/fflow/daykline/get"
if symbol.startswith("6"):
symbol = f"1.{symbol}"
else:
symbol = f"0.{symbol}"
params = {
"lmt": "0",
"klt": "1",
"fields1": "f1,f2,f3,f7",
"fields2": "f51,f52,f53,f54,f55,f56,f57,f58,f59,f60,f61,f62,f63,f64,f65",
"ut": "b2884a393a59ad64002292a3e90d46a5",
"secid": symbol
}
r = requests.get(url, params=params)
data_json = r.json()
klines = data_json["klines"] # 主要指标
"日期","主力净流入额","小单净流入额","中单净流入额","大单净流入额","超大单净流入额","主力净流入占比", "小单净流入占比", "中单净流入占比", "大单净流入占比", "超大单净流入占比"
"收盘价","涨跌幅"
if len(klines) < 1:
return None
if __name__ == "__main__":
stock_cpbd_em_df = stock_cpbd_em(symbol="688041")
print(stock_cpbd_em_df)

535
stockapp/src/crawling/stock_dzjy_em.py Normal file
View File

@ -0,0 +1,535 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
Date: 2022/5/16 15:31
Desc: 东方财富网-数据中心-大宗交易-市场统计
http://data.eastmoney.com/dzjy/dzjy_sctj.aspx
"""
import pandas as pd
import requests
def stock_dzjy_sctj() -> pd.DataFrame:
"""
东方财富网-数据中心-大宗交易-市场统计
http://data.eastmoney.com/dzjy/dzjy_sctj.aspx
:return: 市场统计表
:rtype: pandas.DataFrame
"""
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
'sortColumns': 'TRADE_DATE',
'sortTypes': '-1',
'pageSize': '500',
'pageNumber': '1',
'reportName': 'PRT_BLOCKTRADE_MARKET_STA',
'columns': 'TRADE_DATE,SZ_INDEX,SZ_CHANGE_RATE,BLOCKTRADE_DEAL_AMT,PREMIUM_DEAL_AMT,PREMIUM_RATIO,DISCOUNT_DEAL_AMT,DISCOUNT_RATIO',
'source': 'WEB',
'client': 'WEB',
}
r = requests.get(url, params=params)
data_json = r.json()
total_page = int(data_json['result']["pages"])
big_df = pd.DataFrame()
for page in range(1, total_page+1):
params.update({'pageNumber': page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json['result']["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df['index'] = big_df['index'] + 1
big_df.columns = [
"序号",
"交易日期",
"上证指数",
"上证指数涨跌幅",
"大宗交易成交总额",
"溢价成交总额",
"溢价成交总额占比",
"折价成交总额",
"折价成交总额占比",
]
big_df["交易日期"] = pd.to_datetime(big_df["交易日期"]).dt.date
big_df["上证指数"] = pd.to_numeric(big_df["上证指数"])
big_df["上证指数涨跌幅"] = pd.to_numeric(big_df["上证指数涨跌幅"])
big_df["大宗交易成交总额"] = pd.to_numeric(big_df["大宗交易成交总额"])
big_df["溢价成交总额"] = pd.to_numeric(big_df["溢价成交总额"])
big_df["溢价成交总额占比"] = pd.to_numeric(big_df["溢价成交总额占比"])
big_df["折价成交总额"] = pd.to_numeric(big_df["折价成交总额"])
big_df["折价成交总额占比"] = pd.to_numeric(big_df["折价成交总额占比"])
return big_df
def stock_dzjy_mrmx(symbol: str = '基金', start_date: str = '20220104', end_date: str = '20220104') -> pd.DataFrame:
"""
东方财富网-数据中心-大宗交易-每日明细
http://data.eastmoney.com/dzjy/dzjy_mrmxa.aspx
:param symbol: choice of {'A股', 'B股', '基金', '债券'}
:type symbol: str
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:return: 每日明细
:rtype: pandas.DataFrame
"""
symbol_map = {
'A股': '1',
'B股': '2',
'基金': '3',
'债券': '4',
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
'sortColumns': 'SECURITY_CODE',
'sortTypes': '1',
'pageSize': '5000',
'pageNumber': '1',
'reportName': 'RPT_DATA_BLOCKTRADE',
'columns': 'TRADE_DATE,SECURITY_CODE,SECUCODE,SECURITY_NAME_ABBR,CHANGE_RATE,CLOSE_PRICE,DEAL_PRICE,PREMIUM_RATIO,DEAL_VOLUME,DEAL_AMT,TURNOVER_RATE,BUYER_NAME,SELLER_NAME,CHANGE_RATE_1DAYS,CHANGE_RATE_5DAYS,CHANGE_RATE_10DAYS,CHANGE_RATE_20DAYS,BUYER_CODE,SELLER_CODE',
'source': 'WEB',
'client': 'WEB',
'filter': f"""(SECURITY_TYPE_WEB={symbol_map[symbol]})(TRADE_DATE>='{'-'.join([start_date[:4], start_date[4:6], start_date[6:]])}')(TRADE_DATE<='{'-'.join([end_date[:4], end_date[4:6], end_date[6:]])}')"""
}
r = requests.get(url, params=params)
data_json = r.json()
if not data_json['result']["data"]:
return pd.DataFrame()
temp_df = pd.DataFrame(data_json['result']["data"])
temp_df.reset_index(inplace=True)
temp_df['index'] = temp_df.index + 1
if symbol in {'A股'}:
temp_df.columns = [
"序号",
"交易日期",
"证券代码",
"-",
"证券简称",
"涨跌幅",
"收盘价",
"成交价",
"折溢率",
"成交量",
"成交额",
"成交额/流通市值",
"买方营业部",
"卖方营业部",
"_",
"_",
"_",
"_",
"_",
"_",
]
temp_df["交易日期"] = pd.to_datetime(temp_df["交易日期"]).dt.date
temp_df = temp_df[[
"序号",
"交易日期",
"证券代码",
"证券简称",
"涨跌幅",
"收盘价",
"成交价",
"折溢率",
"成交量",
"成交额",
"成交额/流通市值",
"买方营业部",
"卖方营业部",
]]
temp_df['涨跌幅'] = pd.to_numeric(temp_df['涨跌幅'])
temp_df['收盘价'] = pd.to_numeric(temp_df['收盘价'])
temp_df['成交价'] = pd.to_numeric(temp_df['成交价'])
temp_df['折溢率'] = pd.to_numeric(temp_df['折溢率'])
temp_df['成交量'] = pd.to_numeric(temp_df['成交量'])
temp_df['成交额'] = pd.to_numeric(temp_df['成交额'])
temp_df['成交额/流通市值'] = pd.to_numeric(temp_df['成交额/流通市值'])
if symbol in {'B股', '基金', '债券'}:
temp_df.columns = [
"序号",
"交易日期",
"证券代码",
"-",
"证券简称",
"-",
"-",
"成交价",
"-",
"成交量",
"成交额",
"-",
"买方营业部",
"卖方营业部",
"_",
"_",
"_",
"_",
"_",
"_",
]
temp_df["交易日期"] = pd.to_datetime(temp_df["交易日期"]).dt.date
temp_df = temp_df[[
"序号",
"交易日期",
"证券代码",
"证券简称",
"成交价",
"成交量",
"成交额",
"买方营业部",
"卖方营业部",
]]
temp_df['成交价'] = pd.to_numeric(temp_df['成交价'])
temp_df['成交量'] = pd.to_numeric(temp_df['成交量'])
temp_df['成交额'] = pd.to_numeric(temp_df['成交额'])
return temp_df
def stock_dzjy_mrtj(start_date: str = '20220105', end_date: str = '20220105') -> pd.DataFrame:
"""
东方财富网-数据中心-大宗交易-每日统计
http://data.eastmoney.com/dzjy/dzjy_mrtj.aspx
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:return: 每日统计
:rtype: pandas.DataFrame
"""
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
'sortColumns': 'TURNOVERRATE',
'sortTypes': '-1',
'pageSize': '5000',
'pageNumber': '1',
'reportName': 'RPT_BLOCKTRADE_STA',
'columns': 'TRADE_DATE,SECURITY_CODE,SECUCODE,SECURITY_NAME_ABBR,CHANGE_RATE,CLOSE_PRICE,AVERAGE_PRICE,PREMIUM_RATIO,DEAL_NUM,VOLUME,DEAL_AMT,TURNOVERRATE,D1_CLOSE_ADJCHRATE,D5_CLOSE_ADJCHRATE,D10_CLOSE_ADJCHRATE,D20_CLOSE_ADJCHRATE',
'source': 'WEB',
'client': 'WEB',
'filter': f"(TRADE_DATE>='{'-'.join([start_date[:4], start_date[4:6], start_date[6:]])}')(TRADE_DATE<='{'-'.join([end_date[:4], end_date[4:6], end_date[6:]])}')"
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json['result']["data"])
temp_df.reset_index(inplace=True)
temp_df['index'] = temp_df.index + 1
temp_df.columns = [
"序号",
"交易日期",
"证券代码",
"-",
"证券简称",
"涨跌幅",
"收盘价",
"成交价",
"折溢率",
"成交笔数",
"成交总量",
"成交总额",
"成交总额/流通市值",
"_",
"_",
"_",
"_",
]
temp_df["交易日期"] = pd.to_datetime(temp_df["交易日期"]).dt.date
temp_df = temp_df[[
"序号",
"交易日期",
"证券代码",
"证券简称",
"收盘价",
"涨跌幅",
"成交价",
"折溢率",
"成交笔数",
"成交总量",
"成交总额",
"成交总额/流通市值",
]]
temp_df['涨跌幅'] = pd.to_numeric(temp_df['涨跌幅'])
temp_df['收盘价'] = pd.to_numeric(temp_df['收盘价'])
temp_df['成交价'] = pd.to_numeric(temp_df['成交价'])
temp_df['折溢率'] = pd.to_numeric(temp_df['折溢率'])
temp_df['成交笔数'] = pd.to_numeric(temp_df['成交笔数'])
temp_df['成交总量'] = pd.to_numeric(temp_df['成交总量'])
temp_df['成交总额'] = pd.to_numeric(temp_df['成交总额'])
temp_df['成交总额/流通市值'] = pd.to_numeric(temp_df['成交总额/流通市值'])
return temp_df
def stock_dzjy_hygtj(symbol: str = '近三月') -> pd.DataFrame:
"""
东方财富网-数据中心-大宗交易-活跃 A 股统计
http://data.eastmoney.com/dzjy/dzjy_hygtj.aspx
:param symbol: choice of {'近一月', '近三月', '近六月', '近一年'}
:type symbol: str
:return: 活跃 A 股统计
:rtype: pandas.DataFrame
"""
period_map = {
'近一月': '1',
'近三月': '3',
'近六月': '6',
'近一年': '12',
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
'sortColumns': 'DEAL_NUM,SECURITY_CODE',
'sortTypes': '-1,-1',
'pageSize': '5000',
'pageNumber': '1',
'reportName': 'RPT_BLOCKTRADE_ACSTA',
'columns': 'SECURITY_CODE,SECUCODE,SECURITY_NAME_ABBR,CLOSE_PRICE,CHANGE_RATE,TRADE_DATE,DEAL_AMT,PREMIUM_RATIO,SUM_TURNOVERRATE,DEAL_NUM,PREMIUM_TIMES,DISCOUNT_TIMES,D1_AVG_ADJCHRATE,D5_AVG_ADJCHRATE,D10_AVG_ADJCHRATE,D20_AVG_ADJCHRATE,DATE_TYPE_CODE',
'source': 'WEB',
'client': 'WEB',
'filter': f'(DATE_TYPE_CODE={period_map[symbol]})',
}
r = requests.get(url, params=params)
data_json = r.json()
total_page = data_json['result']["pages"]
big_df = pd.DataFrame()
for page in range(1, int(total_page)+1):
params.update({"pageNumber": page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json['result']["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df['index'] = big_df.index + 1
big_df.columns = [
"序号",
"证券代码",
"_",
"证券简称",
"最新价",
"涨跌幅",
"最近上榜日",
"总成交额",
"折溢率",
"成交总额/流通市值",
"上榜次数-总计",
"上榜次数-溢价",
"上榜次数-折价",
"上榜日后平均涨跌幅-1日",
"上榜日后平均涨跌幅-5日",
"上榜日后平均涨跌幅-10日",
"上榜日后平均涨跌幅-20日",
"_",
]
big_df = big_df[[
"序号",
"证券代码",
"证券简称",
"最新价",
"涨跌幅",
"最近上榜日",
"上榜次数-总计",
"上榜次数-溢价",
"上榜次数-折价",
"总成交额",
"折溢率",
"成交总额/流通市值",
"上榜日后平均涨跌幅-1日",
"上榜日后平均涨跌幅-5日",
"上榜日后平均涨跌幅-10日",
"上榜日后平均涨跌幅-20日",
]]
big_df["最近上榜日"] = pd.to_datetime(big_df["最近上榜日"]).dt.date
big_df["最新价"] = pd.to_numeric(big_df["最新价"])
big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"])
big_df["上榜次数-总计"] = pd.to_numeric(big_df["上榜次数-总计"])
big_df["上榜次数-溢价"] = pd.to_numeric(big_df["上榜次数-溢价"])
big_df["上榜次数-折价"] = pd.to_numeric(big_df["上榜次数-折价"])
big_df["总成交额"] = pd.to_numeric(big_df["总成交额"])
big_df["折溢率"] = pd.to_numeric(big_df["折溢率"])
big_df["成交总额/流通市值"] = pd.to_numeric(big_df["成交总额/流通市值"])
big_df["上榜日后平均涨跌幅-1日"] = pd.to_numeric(big_df["上榜日后平均涨跌幅-1日"])
big_df["上榜日后平均涨跌幅-5日"] = pd.to_numeric(big_df["上榜日后平均涨跌幅-5日"])
big_df["上榜日后平均涨跌幅-10日"] = pd.to_numeric(big_df["上榜日后平均涨跌幅-10日"])
big_df["上榜日后平均涨跌幅-20日"] = pd.to_numeric(big_df["上榜日后平均涨跌幅-20日"])
return big_df
def stock_dzjy_hyyybtj(symbol: str = '近3日') -> pd.DataFrame:
"""
东方财富网-数据中心-大宗交易-活跃营业部统计
https://data.eastmoney.com/dzjy/dzjy_hyyybtj.html
:param symbol: choice of {'当前交易日', '近3日', '近5日', '近10日', '近30日'}
:type symbol: str
:return: 活跃营业部统计
:rtype: pandas.DataFrame
"""
period_map = {
'当前交易日': '1',
'近3日': '3',
'近5日': '5',
'近10日': '10',
'近30日': '30',
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
'sortColumns': 'BUYER_NUM,TOTAL_BUYAMT',
'sortTypes': '-1,-1',
'pageSize': '5000',
'pageNumber': '1',
'reportName': 'RPT_BLOCKTRADE_OPERATEDEPTSTATISTICS',
'columns': 'OPERATEDEPT_CODE,OPERATEDEPT_NAME,ONLIST_DATE,STOCK_DETAILS,BUYER_NUM,SELLER_NUM,TOTAL_BUYAMT,TOTAL_SELLAMT,TOTAL_NETAMT,N_DATE',
'source': 'WEB',
'client': 'WEB',
'filter': f'(N_DATE=-{period_map[symbol]})',
}
r = requests.get(url, params=params)
data_json = r.json()
total_page = data_json['result']["pages"]
big_df = pd.DataFrame()
for page in range(1, int(total_page)+1):
params.update({"pageNumber": page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json['result']["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df['index'] = big_df.index + 1
big_df.columns = [
"序号",
"_",
"营业部名称",
"最近上榜日",
"买入的股票",
"次数总计-买入",
"次数总计-卖出",
"成交金额统计-买入",
"成交金额统计-卖出",
"成交金额统计-净买入额",
"_",
]
big_df = big_df[[
"序号",
"最近上榜日",
"营业部名称",
"次数总计-买入",
"次数总计-卖出",
"成交金额统计-买入",
"成交金额统计-卖出",
"成交金额统计-净买入额",
"买入的股票",
]]
big_df["最近上榜日"] = pd.to_datetime(big_df["最近上榜日"]).dt.date
big_df["次数总计-买入"] = pd.to_numeric(big_df["次数总计-买入"])
big_df["次数总计-卖出"] = pd.to_numeric(big_df["次数总计-卖出"])
big_df["成交金额统计-买入"] = pd.to_numeric(big_df["成交金额统计-买入"])
big_df["成交金额统计-卖出"] = pd.to_numeric(big_df["成交金额统计-卖出"])
big_df["成交金额统计-净买入额"] = pd.to_numeric(big_df["成交金额统计-净买入额"])
return big_df
def stock_dzjy_yybph(symbol: str = '近三月') -> pd.DataFrame:
"""
东方财富网-数据中心-大宗交易-营业部排行
http://data.eastmoney.com/dzjy/dzjy_yybph.aspx
:param symbol: choice of {'近一月', '近三月', '近六月', '近一年'}
:type symbol: str
:return: 营业部排行
:rtype: pandas.DataFrame
"""
period_map = {
'近一月': '30',
'近三月': '90',
'近六月': '120',
'近一年': '360',
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
'sortColumns': 'D5_BUYER_NUM,D1_AVERAGE_INCREASE',
'sortTypes': '-1,-1',
'pageSize': '5000',
'pageNumber': '1',
'reportName': 'RPT_BLOCKTRADE_OPERATEDEPT_RANK',
'columns': 'OPERATEDEPT_CODE,OPERATEDEPT_NAME,D1_BUYER_NUM,D1_AVERAGE_INCREASE,D1_RISE_PROBABILITY,D5_BUYER_NUM,D5_AVERAGE_INCREASE,D5_RISE_PROBABILITY,D10_BUYER_NUM,D10_AVERAGE_INCREASE,D10_RISE_PROBABILITY,D20_BUYER_NUM,D20_AVERAGE_INCREASE,D20_RISE_PROBABILITY,N_DATE,RELATED_ORG_CODE',
'source': 'WEB',
'client': 'WEB',
'filter': f'(N_DATE=-{period_map[symbol]})',
}
r = requests.get(url, params=params)
data_json = r.json()
total_page = data_json['result']["pages"]
big_df = pd.DataFrame()
for page in range(1, int(total_page)+1):
params.update({"pageNumber": page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json['result']["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df['index'] = big_df.index + 1
big_df.columns = [
"序号",
"_",
"营业部名称",
"上榜后1天-买入次数",
"上榜后1天-平均涨幅",
"上榜后1天-上涨概率",
"上榜后5天-买入次数",
"上榜后5天-平均涨幅",
"上榜后5天-上涨概率",
"上榜后10天-买入次数",
"上榜后10天-平均涨幅",
"上榜后10天-上涨概率",
"上榜后20天-买入次数",
"上榜后20天-平均涨幅",
"上榜后20天-上涨概率",
"_",
"_",
]
big_df = big_df[[
"序号",
"营业部名称",
"上榜后1天-买入次数",
"上榜后1天-平均涨幅",
"上榜后1天-上涨概率",
"上榜后5天-买入次数",
"上榜后5天-平均涨幅",
"上榜后5天-上涨概率",
"上榜后10天-买入次数",
"上榜后10天-平均涨幅",
"上榜后10天-上涨概率",
"上榜后20天-买入次数",
"上榜后20天-平均涨幅",
"上榜后20天-上涨概率",
]]
big_df['上榜后1天-买入次数'] = pd.to_numeric(big_df['上榜后1天-买入次数'])
big_df['上榜后1天-平均涨幅'] = pd.to_numeric(big_df['上榜后1天-平均涨幅'])
big_df['上榜后1天-上涨概率'] = pd.to_numeric(big_df['上榜后1天-上涨概率'])
big_df['上榜后5天-买入次数'] = pd.to_numeric(big_df['上榜后5天-买入次数'])
big_df['上榜后5天-平均涨幅'] = pd.to_numeric(big_df['上榜后5天-平均涨幅'])
big_df['上榜后5天-上涨概率'] = pd.to_numeric(big_df['上榜后5天-上涨概率'])
big_df['上榜后10天-买入次数'] = pd.to_numeric(big_df['上榜后10天-买入次数'])
big_df['上榜后10天-平均涨幅'] = pd.to_numeric(big_df['上榜后10天-平均涨幅'])
big_df['上榜后10天-上涨概率'] = pd.to_numeric(big_df['上榜后10天-上涨概率'])
big_df['上榜后20天-买入次数'] = pd.to_numeric(big_df['上榜后20天-买入次数'])
big_df['上榜后20天-平均涨幅'] = pd.to_numeric(big_df['上榜后20天-平均涨幅'])
big_df['上榜后20天-上涨概率'] = pd.to_numeric(big_df['上榜后20天-上涨概率'])
return big_df
if __name__ == "__main__":
stock_dzjy_sctj_df = stock_dzjy_sctj()
print(stock_dzjy_sctj_df)
stock_dzjy_mrmx_df = stock_dzjy_mrmx(symbol='债券', start_date='20201204', end_date='20201204')
print(stock_dzjy_mrmx_df)
stock_dzjy_mrtj_df = stock_dzjy_mrtj(start_date='20201204', end_date='20201204')
print(stock_dzjy_mrtj_df)
stock_dzjy_hygtj_df = stock_dzjy_hygtj(symbol='近三月')
print(stock_dzjy_hygtj_df)
stock_dzjy_hyyybtj_df = stock_dzjy_hyyybtj(symbol='近3日')
print(stock_dzjy_hyyybtj_df)
stock_dzjy_yybph_df = stock_dzjy_yybph(symbol='近三月')
print(stock_dzjy_yybph_df)

126
stockapp/src/crawling/stock_fhps_em.py Normal file
View File

@ -0,0 +1,126 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
Date: 2023/4/7 15:22
Desc: 东方财富网-数据中心-年报季报-分红送配
https://data.eastmoney.com/yjfp/
"""
import pandas as pd
import requests
from tqdm import tqdm
__author__ = 'myh '
__date__ = '2023/6/27 '
def stock_fhps_em(date: str = "20210630") -> pd.DataFrame:
"""
东方财富网-数据中心-年报季报-分红送配
https://data.eastmoney.com/yjfp/
:param date: 分红送配报告期
:type date: str
:return: 分红送配
:rtype: pandas.DataFrame
"""
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"sortColumns": "PLAN_NOTICE_DATE",
"sortTypes": "-1",
"pageSize": "500",
"pageNumber": "1",
"reportName": "RPT_SHAREBONUS_DET",
"columns": "ALL",
"quoteColumns": "",
"js": '{"data":(x),"pages":(tp)}',
"source": "WEB",
"client": "WEB",
"filter": f"""(REPORT_DATE='{"-".join([date[:4], date[4:6], date[6:]])}')""",
}
r = requests.get(url, params=params)
data_json = r.json()
total_pages = int(data_json["result"]["pages"])
big_df = pd.DataFrame()
for page in tqdm(range(1, total_pages + 1), leave=False):
params.update({"pageNumber": page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.columns = [
"_",
"名称",
"_",
"_",
"代码",
"送转股份-送转总比例",
"送转股份-送转比例",
"送转股份-转股比例",
"现金分红-现金分红比例",
"预案公告日",
"股权登记日",
"除权除息日",
"_",
"方案进度",
"_",
"最新公告日期",
"_",
"_",
"_",
"每股收益",
"每股净资产",
"每股公积金",
"每股未分配利润",
"净利润同比增长",
"总股本",
"_",
"现金分红-股息率",
"-",
"-",
"-",
]
big_df = big_df[
[
"代码",
"名称",
"送转股份-送转总比例",
"送转股份-送转比例",
"送转股份-转股比例",
"现金分红-现金分红比例",
"现金分红-股息率",
"每股收益",
"每股净资产",
"每股公积金",
"每股未分配利润",
"净利润同比增长",
"总股本",
"预案公告日",
"股权登记日",
"除权除息日",
"方案进度",
"最新公告日期",
]
]
big_df["送转股份-送转总比例"] = pd.to_numeric(big_df["送转股份-送转总比例"])
big_df["送转股份-送转比例"] = pd.to_numeric(big_df["送转股份-送转比例"])
big_df["送转股份-转股比例"] = pd.to_numeric(big_df["送转股份-转股比例"])
big_df["现金分红-现金分红比例"] = pd.to_numeric(big_df["现金分红-现金分红比例"])
big_df["现金分红-股息率"] = pd.to_numeric(big_df["现金分红-股息率"])
big_df["每股收益"] = pd.to_numeric(big_df["每股收益"])
big_df["每股净资产"] = pd.to_numeric(big_df["每股净资产"])
big_df["每股公积金"] = pd.to_numeric(big_df["每股公积金"])
big_df["每股未分配利润"] = pd.to_numeric(big_df["每股未分配利润"])
big_df["净利润同比增长"] = pd.to_numeric(big_df["净利润同比增长"])
big_df["总股本"] = pd.to_numeric(big_df["总股本"])
big_df["预案公告日"] = pd.to_datetime(big_df["预案公告日"], errors="coerce").dt.date
big_df["股权登记日"] = pd.to_datetime(big_df["股权登记日"], errors="coerce").dt.date
big_df["除权除息日"] = pd.to_datetime(big_df["除权除息日"], errors="coerce").dt.date
big_df["最新公告日期"] = pd.to_datetime(big_df["最新公告日期"], errors="coerce").dt.date
return big_df
if __name__ == "__main__":
stock_fhps_em_df = stock_fhps_em(date="20221231")
print(stock_fhps_em_df)

419
stockapp/src/crawling/stock_fund_em.py Normal file
View File

@ -0,0 +1,419 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
Date: 2023/5/16 15:30
Desc: 东方财富网-数据中心-资金流向
https://data.eastmoney.com/zjlx/detail.html
"""
import json
import time
from functools import lru_cache
import pandas as pd
import requests
__author__ = 'myh '
__date__ = '2023/6/12 '
def stock_individual_fund_flow_rank(indicator: str = "5日") -> pd.DataFrame:
"""
东方财富网-数据中心-资金流向-排名
https://data.eastmoney.com/zjlx/detail.html
:param indicator: choice of {"今日", "3日", "5日", "10日"}
:type indicator: str
:return: 指定 indicator 资金流向排行
:rtype: pandas.DataFrame
"""
indicator_map = {
"今日": [
"f62",
"f12,f14,f2,f3,f62,f184,f66,f69,f72,f75,f78,f81,f84,f87,f204,f205,f124",
],
"3日": [
"f267",
"f12,f14,f2,f127,f267,f268,f269,f270,f271,f272,f273,f274,f275,f276,f257,f258,f124",
],
"5日": [
"f164",
"f12,f14,f2,f109,f164,f165,f166,f167,f168,f169,f170,f171,f172,f173,f257,f258,f124",
],
"10日": [
"f174",
"f12,f14,f2,f160,f174,f175,f176,f177,f178,f179,f180,f181,f182,f183,f260,f261,f124",
],
}
url = "http://push2.eastmoney.com/api/qt/clist/get"
params = {
"fid": indicator_map[indicator][0],
"po": "1",
"pz": "10000",
"pn": "1",
"np": "1",
"fltt": "2",
"invt": "2",
"ut": "b2884a393a59ad64002292a3e90d46a5",
"fs": "m:0+t:6+f:!2,m:0+t:13+f:!2,m:0+t:80+f:!2,m:1+t:2+f:!2,m:1+t:23+f:!2,m:0+t:7+f:!2,m:1+t:3+f:!2",
"fields": indicator_map[indicator][1],
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["data"]["diff"])
if indicator == "今日":
temp_df.columns = [
"最新价",
"今日涨跌幅",
"代码",
"名称",
"今日主力净流入-净额",
"今日超大单净流入-净额",
"今日超大单净流入-净占比",
"今日大单净流入-净额",
"今日大单净流入-净占比",
"今日中单净流入-净额",
"今日中单净流入-净占比",
"今日小单净流入-净额",
"今日小单净流入-净占比",
"_",
"今日主力净流入-净占比",
"_",
"_",
"_",
]
temp_df = temp_df[
[
"代码",
"名称",
"最新价",
"今日涨跌幅",
"今日主力净流入-净额",
"今日主力净流入-净占比",
"今日超大单净流入-净额",
"今日超大单净流入-净占比",
"今日大单净流入-净额",
"今日大单净流入-净占比",
"今日中单净流入-净额",
"今日中单净流入-净占比",
"今日小单净流入-净额",
"今日小单净流入-净占比",
]
]
elif indicator == "3日":
temp_df.columns = [
"最新价",
"代码",
"名称",
"_",
"3日涨跌幅",
"_",
"_",
"_",
"3日主力净流入-净额",
"3日主力净流入-净占比",
"3日超大单净流入-净额",
"3日超大单净流入-净占比",
"3日大单净流入-净额",
"3日大单净流入-净占比",
"3日中单净流入-净额",
"3日中单净流入-净占比",
"3日小单净流入-净额",
"3日小单净流入-净占比",
]
temp_df = temp_df[
[
"代码",
"名称",
"最新价",
"3日涨跌幅",
"3日主力净流入-净额",
"3日主力净流入-净占比",
"3日超大单净流入-净额",
"3日超大单净流入-净占比",
"3日大单净流入-净额",
"3日大单净流入-净占比",
"3日中单净流入-净额",
"3日中单净流入-净占比",
"3日小单净流入-净额",
"3日小单净流入-净占比",
]
]
elif indicator == "5日":
temp_df.columns = [
"最新价",
"代码",
"名称",
"5日涨跌幅",
"_",
"5日主力净流入-净额",
"5日主力净流入-净占比",
"5日超大单净流入-净额",
"5日超大单净流入-净占比",
"5日大单净流入-净额",
"5日大单净流入-净占比",
"5日中单净流入-净额",
"5日中单净流入-净占比",
"5日小单净流入-净额",
"5日小单净流入-净占比",
"_",
"_",
"_",
]
temp_df = temp_df[
[
"代码",
"名称",
"最新价",
"5日涨跌幅",
"5日主力净流入-净额",
"5日主力净流入-净占比",
"5日超大单净流入-净额",
"5日超大单净流入-净占比",
"5日大单净流入-净额",
"5日大单净流入-净占比",
"5日中单净流入-净额",
"5日中单净流入-净占比",
"5日小单净流入-净额",
"5日小单净流入-净占比",
]
]
elif indicator == "10日":
temp_df.columns = [
"最新价",
"代码",
"名称",
"_",
"10日涨跌幅",
"10日主力净流入-净额",
"10日主力净流入-净占比",
"10日超大单净流入-净额",
"10日超大单净流入-净占比",
"10日大单净流入-净额",
"10日大单净流入-净占比",
"10日中单净流入-净额",
"10日中单净流入-净占比",
"10日小单净流入-净额",
"10日小单净流入-净占比",
"_",
"_",
"_",
]
temp_df = temp_df[
[
"代码",
"名称",
"最新价",
"10日涨跌幅",
"10日主力净流入-净额",
"10日主力净流入-净占比",
"10日超大单净流入-净额",
"10日超大单净流入-净占比",
"10日大单净流入-净额",
"10日大单净流入-净占比",
"10日中单净流入-净额",
"10日中单净流入-净占比",
"10日小单净流入-净额",
"10日小单净流入-净占比",
]
]
return temp_df
def stock_sector_fund_flow_rank(
indicator: str = "10日", sector_type: str = "行业资金流"
) -> pd.DataFrame:
"""
东方财富网-数据中心-资金流向-板块资金流-排名
https://data.eastmoney.com/bkzj/hy.html
:param indicator: choice of {"今日", "5日", "10日"}
:type indicator: str
:param sector_type: choice of {"行业资金流", "概念资金流", "地域资金流"}
:type sector_type: str
:return: 指定参数的资金流排名数据
:rtype: pandas.DataFrame
"""
sector_type_map = {"行业资金流": "2", "概念资金流": "3", "地域资金流": "1"}
indicator_map = {
"今日": [
"f62",
"1",
"f12,f14,f2,f3,f62,f184,f66,f69,f72,f75,f78,f81,f84,f87,f204,f205,f124",
],
"5日": [
"f164",
"5",
"f12,f14,f2,f109,f164,f165,f166,f167,f168,f169,f170,f171,f172,f173,f257,f258,f124",
],
"10日": [
"f174",
"10",
"f12,f14,f2,f160,f174,f175,f176,f177,f178,f179,f180,f181,f182,f183,f260,f261,f124",
],
}
url = "http://push2.eastmoney.com/api/qt/clist/get"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36",
}
params = {
"pn": "1",
"pz": "5000",
"po": "1",
"np": "1",
"ut": "b2884a393a59ad64002292a3e90d46a5",
"fltt": "2",
"invt": "2",
"fid0": indicator_map[indicator][0],
"fs": f"m:90 t:{sector_type_map[sector_type]}",
"stat": indicator_map[indicator][1],
"fields": indicator_map[indicator][2],
"rt": "52975239",
"cb": "jQuery18308357908311220152_1589256588824",
"_": int(time.time() * 1000),
}
r = requests.get(url, params=params, headers=headers)
text_data = r.text
json_data = json.loads(text_data[text_data.find("{") : -2])
temp_df = pd.DataFrame(json_data["data"]["diff"])
if indicator == "今日":
temp_df.columns = [
"-",
"今日涨跌幅",
"_",
"名称",
"今日主力净流入-净额",
"今日超大单净流入-净额",
"今日超大单净流入-净占比",
"今日大单净流入-净额",
"今日大单净流入-净占比",
"今日中单净流入-净额",
"今日中单净流入-净占比",
"今日小单净流入-净额",
"今日小单净流入-净占比",
"-",
"今日主力净流入-净占比",
"今日主力净流入最大股",
"今日主力净流入最大股代码",
"是否净流入",
]
temp_df = temp_df[
[
"名称",
"今日涨跌幅",
"今日主力净流入-净额",
"今日主力净流入-净占比",
"今日超大单净流入-净额",
"今日超大单净流入-净占比",
"今日大单净流入-净额",
"今日大单净流入-净占比",
"今日中单净流入-净额",
"今日中单净流入-净占比",
"今日小单净流入-净额",
"今日小单净流入-净占比",
"今日主力净流入最大股",
]
]
elif indicator == "5日":
temp_df.columns = [
"-",
"_",
"名称",
"5日涨跌幅",
"_",
"5日主力净流入-净额",
"5日主力净流入-净占比",
"5日超大单净流入-净额",
"5日超大单净流入-净占比",
"5日大单净流入-净额",
"5日大单净流入-净占比",
"5日中单净流入-净额",
"5日中单净流入-净占比",
"5日小单净流入-净额",
"5日小单净流入-净占比",
"5日主力净流入最大股",
"_",
"_",
]
temp_df = temp_df[
[
"名称",
"5日涨跌幅",
"5日主力净流入-净额",
"5日主力净流入-净占比",
"5日超大单净流入-净额",
"5日超大单净流入-净占比",
"5日大单净流入-净额",
"5日大单净流入-净占比",
"5日中单净流入-净额",
"5日中单净流入-净占比",
"5日小单净流入-净额",
"5日小单净流入-净占比",
"5日主力净流入最大股",
]
]
elif indicator == "10日":
temp_df.columns = [
"-",
"_",
"名称",
"_",
"10日涨跌幅",
"10日主力净流入-净额",
"10日主力净流入-净占比",
"10日超大单净流入-净额",
"10日超大单净流入-净占比",
"10日大单净流入-净额",
"10日大单净流入-净占比",
"10日中单净流入-净额",
"10日中单净流入-净占比",
"10日小单净流入-净额",
"10日小单净流入-净占比",
"10日主力净流入最大股",
"_",
"_",
]
temp_df = temp_df[
[
"名称",
"10日涨跌幅",
"10日主力净流入-净额",
"10日主力净流入-净占比",
"10日超大单净流入-净额",
"10日超大单净流入-净占比",
"10日大单净流入-净额",
"10日大单净流入-净占比",
"10日中单净流入-净额",
"10日中单净流入-净占比",
"10日小单净流入-净额",
"10日小单净流入-净占比",
"10日主力净流入最大股",
]
]
return temp_df
if __name__ == "__main__":
stock_individual_fund_flow_rank_df = stock_individual_fund_flow_rank(indicator="今日")
print(stock_individual_fund_flow_rank_df)
stock_individual_fund_flow_rank_df = stock_individual_fund_flow_rank(indicator="3日")
print(stock_individual_fund_flow_rank_df)
stock_individual_fund_flow_rank_df = stock_individual_fund_flow_rank(indicator="5日")
print(stock_individual_fund_flow_rank_df)
stock_individual_fund_flow_rank_df = stock_individual_fund_flow_rank(
indicator="10日"
)
print(stock_individual_fund_flow_rank_df)
stock_sector_fund_flow_rank_df = stock_sector_fund_flow_rank(
indicator="5日", sector_type="概念资金流"
)
print(stock_sector_fund_flow_rank_df)
stock_sector_fund_flow_rank_df = stock_sector_fund_flow_rank(
indicator="今日", sector_type="行业资金流"
)
print(stock_sector_fund_flow_rank_df)

554
stockapp/src/crawling/stock_hist_em.py Normal file
View File

@ -0,0 +1,554 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
Date: 2022/6/19 15:26
Desc: 东方财富网-行情首页-沪深京 A 股
"""
import requests
import pandas as pd
from functools import lru_cache
def stock_zh_a_spot_em() -> pd.DataFrame:
"""
东方财富网-沪深京 A 股-实时行情
https://quote.eastmoney.com/center/gridlist.html#hs_a_board
:return: 实时行情
:rtype: pandas.DataFrame
"""
url = "http://82.push2.eastmoney.com/api/qt/clist/get"
params = {
"pn": "1",
"pz": "50000",
"po": "1",
"np": "1",
"ut": "bd1d9ddb04089700cf9c27f6f7426281",
"fltt": "2",
"invt": "2",
"fid": "f3",
"fs": "m:0 t:6,m:0 t:80,m:1 t:2,m:1 t:23,m:0 t:81 s:2048",
"fields": "f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f14,f15,f16,f17,f18,f20,f21,f22,f23,f24,f25,f26,f37,f38,f39,f40,f41,f45,f46,f48,f49,f57,f61,f100,f112,f113,f114,f115,f221",
"_": "1623833739532",
}
r = requests.get(url, params=params)
data_json = r.json()
if not data_json["data"]["diff"]:
return pd.DataFrame()
temp_df = pd.DataFrame(data_json["data"]["diff"])
temp_df.columns = [
"最新价",
"涨跌幅",
"涨跌额",
"成交量",
"成交额",
"振幅",
"换手率",
"市盈率动",
"量比",
"5分钟涨跌",
"代码",
"名称",
"最高",
"最低",
"今开",
"昨收",
"总市值",
"流通市值",
"涨速",
"市净率",
"60日涨跌幅",
"年初至今涨跌幅",
"上市时间",
"加权净资产收益率",
"总股本",
"已流通股份",
"营业收入",
"营业收入同比增长",
"归属净利润",
"归属净利润同比增长",
"每股未分配利润",
"毛利率",
"资产负债率",
"每股公积金",
"所处行业",
"每股收益",
"每股净资产",
"市盈率静",
"市盈率TTM",
"报告期"
]
temp_df = temp_df[
[
"代码",
"名称",
"最新价",
"涨跌幅",
"涨跌额",
"成交量",
"成交额",
"振幅",
"换手率",
"量比",
"今开",
"最高",
"最低",
"昨收",
"涨速",
"5分钟涨跌",
"60日涨跌幅",
"年初至今涨跌幅",
"市盈率动",
"市盈率TTM",
"市盈率静",
"市净率",
"每股收益",
"每股净资产",
"每股公积金",
"每股未分配利润",
"加权净资产收益率",
"毛利率",
"资产负债率",
"营业收入",
"营业收入同比增长",
"归属净利润",
"归属净利润同比增长",
"报告期",
"总股本",
"已流通股份",
"总市值",
"流通市值",
"所处行业",
"上市时间"
]
]
temp_df["最新价"] = pd.to_numeric(temp_df["最新价"], errors="coerce")
temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"], errors="coerce")
temp_df["涨跌额"] = pd.to_numeric(temp_df["涨跌额"], errors="coerce")
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"], errors="coerce")
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"], errors="coerce")
temp_df["振幅"] = pd.to_numeric(temp_df["振幅"], errors="coerce")
temp_df["量比"] = pd.to_numeric(temp_df["量比"], errors="coerce")
temp_df["换手率"] = pd.to_numeric(temp_df["换手率"], errors="coerce")
temp_df["最高"] = pd.to_numeric(temp_df["最高"], errors="coerce")
temp_df["最低"] = pd.to_numeric(temp_df["最低"], errors="coerce")
temp_df["今开"] = pd.to_numeric(temp_df["今开"], errors="coerce")
temp_df["昨收"] = pd.to_numeric(temp_df["昨收"], errors="coerce")
temp_df["涨速"] = pd.to_numeric(temp_df["涨速"], errors="coerce")
temp_df["5分钟涨跌"] = pd.to_numeric(temp_df["5分钟涨跌"], errors="coerce")
temp_df["60日涨跌幅"] = pd.to_numeric(temp_df["60日涨跌幅"], errors="coerce")
temp_df["年初至今涨跌幅"] = pd.to_numeric(temp_df["年初至今涨跌幅"], errors="coerce")
temp_df["市盈率动"] = pd.to_numeric(temp_df["市盈率动"], errors="coerce")
temp_df["市盈率TTM"] = pd.to_numeric(temp_df["市盈率TTM"], errors="coerce")
temp_df["市盈率静"] = pd.to_numeric(temp_df["市盈率静"], errors="coerce")
temp_df["市净率"] = pd.to_numeric(temp_df["市净率"], errors="coerce")
temp_df["每股收益"] = pd.to_numeric(temp_df["每股收益"], errors="coerce")
temp_df["每股净资产"] = pd.to_numeric(temp_df["每股净资产"], errors="coerce")
temp_df["每股公积金"] = pd.to_numeric(temp_df["每股公积金"], errors="coerce")
temp_df["每股未分配利润"] = pd.to_numeric(temp_df["每股未分配利润"], errors="coerce")
temp_df["加权净资产收益率"] = pd.to_numeric(temp_df["加权净资产收益率"], errors="coerce")
temp_df["毛利率"] = pd.to_numeric(temp_df["毛利率"], errors="coerce")
temp_df["资产负债率"] = pd.to_numeric(temp_df["资产负债率"], errors="coerce")
temp_df["营业收入"] = pd.to_numeric(temp_df["营业收入"], errors="coerce")
temp_df["营业收入同比增长"] = pd.to_numeric(temp_df["营业收入同比增长"], errors="coerce")
temp_df["归属净利润"] = pd.to_numeric(temp_df["归属净利润"], errors="coerce")
temp_df["归属净利润同比增长"] = pd.to_numeric(temp_df["归属净利润同比增长"], errors="coerce")
temp_df["报告期"] = pd.to_datetime(temp_df["报告期"], format='%Y%m%d', errors="coerce")
temp_df["总股本"] = pd.to_numeric(temp_df["总股本"], errors="coerce")
temp_df["已流通股份"] = pd.to_numeric(temp_df["已流通股份"], errors="coerce")
temp_df["总市值"] = pd.to_numeric(temp_df["总市值"], errors="coerce")
temp_df["流通市值"] = pd.to_numeric(temp_df["流通市值"], errors="coerce")
temp_df["上市时间"] = pd.to_datetime(temp_df["上市时间"], format='%Y%m%d', errors="coerce")
return temp_df
@lru_cache()
def code_id_map_em() -> dict:
"""
东方财富-股票和市场代码
http://quote.eastmoney.com/center/gridlist.html#hs_a_board
:return: 股票和市场代码
:rtype: dict
"""
url = "http://80.push2.eastmoney.com/api/qt/clist/get"
params = {
"pn": "1",
"pz": "50000",
"po": "1",
"np": "1",
"ut": "bd1d9ddb04089700cf9c27f6f7426281",
"fltt": "2",
"invt": "2",
"fid": "f3",
"fs": "m:1 t:2,m:1 t:23",
"fields": "f12",
"_": "1623833739532",
}
r = requests.get(url, params=params)
data_json = r.json()
if not data_json["data"]["diff"]:
return dict()
temp_df = pd.DataFrame(data_json["data"]["diff"])
temp_df["market_id"] = 1
temp_df.columns = ["sh_code", "sh_id"]
code_id_dict = dict(zip(temp_df["sh_code"], temp_df["sh_id"]))
params = {
"pn": "1",
"pz": "50000",
"po": "1",
"np": "1",
"ut": "bd1d9ddb04089700cf9c27f6f7426281",
"fltt": "2",
"invt": "2",
"fid": "f3",
"fs": "m:0 t:6,m:0 t:80",
"fields": "f12",
"_": "1623833739532",
}
r = requests.get(url, params=params)
data_json = r.json()
if not data_json["data"]["diff"]:
return dict()
temp_df_sz = pd.DataFrame(data_json["data"]["diff"])
temp_df_sz["sz_id"] = 0
code_id_dict.update(dict(zip(temp_df_sz["f12"], temp_df_sz["sz_id"])))
params = {
"pn": "1",
"pz": "50000",
"po": "1",
"np": "1",
"ut": "bd1d9ddb04089700cf9c27f6f7426281",
"fltt": "2",
"invt": "2",
"fid": "f3",
"fs": "m:0 t:81 s:2048",
"fields": "f12",
"_": "1623833739532",
}
r = requests.get(url, params=params)
data_json = r.json()
if not data_json["data"]["diff"]:
return dict()
temp_df_sz = pd.DataFrame(data_json["data"]["diff"])
temp_df_sz["bj_id"] = 0
code_id_dict.update(dict(zip(temp_df_sz["f12"], temp_df_sz["bj_id"])))
return code_id_dict
def stock_zh_a_hist(
symbol: str = "000001",
period: str = "daily",
start_date: str = "19700101",
end_date: str = "20500101",
adjust: str = "",
) -> pd.DataFrame:
"""
东方财富网-行情首页-沪深京 A 股-每日行情
https://quote.eastmoney.com/concept/sh603777.html?from=classic
:param symbol: 股票代码
:type symbol: str
:param period: choice of {'daily', 'weekly', 'monthly'}
:type period: str
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:param adjust: choice of {"qfq": "前复权", "hfq": "后复权", "": "不复权"}
:type adjust: str
:return: 每日行情
:rtype: pandas.DataFrame
"""
code_id_dict = code_id_map_em()
adjust_dict = {"qfq": "1", "hfq": "2", "": "0"}
period_dict = {"daily": "101", "weekly": "102", "monthly": "103"}
url = "http://push2his.eastmoney.com/api/qt/stock/kline/get"
params = {
"fields1": "f1,f2,f3,f4,f5,f6",
"fields2": "f51,f52,f53,f54,f55,f56,f57,f58,f59,f60,f61,f116",
"ut": "7eea3edcaed734bea9cbfc24409ed989",
"klt": period_dict[period],
"fqt": adjust_dict[adjust],
"secid": f"{code_id_dict[symbol]}.{symbol}",
"beg": start_date,
"end": end_date,
"_": "1623766962675",
}
r = requests.get(url, params=params)
data_json = r.json()
if not (data_json["data"] and data_json["data"]["klines"]):
return pd.DataFrame()
temp_df = pd.DataFrame(
[item.split(",") for item in data_json["data"]["klines"]]
)
temp_df.columns = [
"日期",
"开盘",
"收盘",
"最高",
"最低",
"成交量",
"成交额",
"振幅",
"涨跌幅",
"涨跌额",
"换手率",
]
temp_df.index = pd.to_datetime(temp_df["日期"])
temp_df.reset_index(inplace=True, drop=True)
temp_df["开盘"] = pd.to_numeric(temp_df["开盘"])
temp_df["收盘"] = pd.to_numeric(temp_df["收盘"])
temp_df["最高"] = pd.to_numeric(temp_df["最高"])
temp_df["最低"] = pd.to_numeric(temp_df["最低"])
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"])
temp_df["振幅"] = pd.to_numeric(temp_df["振幅"])
temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"])
temp_df["涨跌额"] = pd.to_numeric(temp_df["涨跌额"])
temp_df["换手率"] = pd.to_numeric(temp_df["换手率"])
return temp_df
def stock_zh_a_hist_min_em(
symbol: str = "000001",
start_date: str = "1979-09-01 09:32:00",
end_date: str = "2222-01-01 09:32:00",
period: str = "5",
adjust: str = "",
) -> pd.DataFrame:
"""
东方财富网-行情首页-沪深京 A 股-每日分时行情
https://quote.eastmoney.com/concept/sh603777.html?from=classic
:param symbol: 股票代码
:type symbol: str
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:param period: choice of {'1', '5', '15', '30', '60'}
:type period: str
:param adjust: choice of {'', 'qfq', 'hfq'}
:type adjust: str
:return: 每日分时行情
:rtype: pandas.DataFrame
"""
code_id_dict = code_id_map_em()
adjust_map = {
"": "0",
"qfq": "1",
"hfq": "2",
}
if period == "1":
url = "https://push2his.eastmoney.com/api/qt/stock/trends2/get"
params = {
"fields1": "f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13",
"fields2": "f51,f52,f53,f54,f55,f56,f57,f58",
"ut": "7eea3edcaed734bea9cbfc24409ed989",
"ndays": "5",
"iscr": "0",
"secid": f"{code_id_dict[symbol]}.{symbol}",
"_": "1623766962675",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(
[item.split(",") for item in data_json["data"]["trends"]]
)
temp_df.columns = [
"时间",
"开盘",
"收盘",
"最高",
"最低",
"成交量",
"成交额",
"最新价",
]
temp_df.index = pd.to_datetime(temp_df["时间"])
temp_df = temp_df[start_date:end_date]
temp_df.reset_index(drop=True, inplace=True)
temp_df["开盘"] = pd.to_numeric(temp_df["开盘"])
temp_df["收盘"] = pd.to_numeric(temp_df["收盘"])
temp_df["最高"] = pd.to_numeric(temp_df["最高"])
temp_df["最低"] = pd.to_numeric(temp_df["最低"])
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"])
temp_df["最新价"] = pd.to_numeric(temp_df["最新价"])
temp_df["时间"] = pd.to_datetime(temp_df["时间"]).astype(str)
return temp_df
else:
url = "http://push2his.eastmoney.com/api/qt/stock/kline/get"
params = {
"fields1": "f1,f2,f3,f4,f5,f6",
"fields2": "f51,f52,f53,f54,f55,f56,f57,f58,f59,f60,f61",
"ut": "7eea3edcaed734bea9cbfc24409ed989",
"klt": period,
"fqt": adjust_map[adjust],
"secid": f"{code_id_dict[symbol]}.{symbol}",
"beg": "0",
"end": "20500000",
"_": "1630930917857",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(
[item.split(",") for item in data_json["data"]["klines"]]
)
temp_df.columns = [
"时间",
"开盘",
"收盘",
"最高",
"最低",
"成交量",
"成交额",
"振幅",
"涨跌幅",
"涨跌额",
"换手率",
]
temp_df.index = pd.to_datetime(temp_df["时间"])
temp_df = temp_df[start_date:end_date]
temp_df.reset_index(drop=True, inplace=True)
temp_df["开盘"] = pd.to_numeric(temp_df["开盘"])
temp_df["收盘"] = pd.to_numeric(temp_df["收盘"])
temp_df["最高"] = pd.to_numeric(temp_df["最高"])
temp_df["最低"] = pd.to_numeric(temp_df["最低"])
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"])
temp_df["振幅"] = pd.to_numeric(temp_df["振幅"])
temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"])
temp_df["涨跌额"] = pd.to_numeric(temp_df["涨跌额"])
temp_df["换手率"] = pd.to_numeric(temp_df["换手率"])
temp_df["时间"] = pd.to_datetime(temp_df["时间"]).astype(str)
temp_df = temp_df[
[
"时间",
"开盘",
"收盘",
"最高",
"最低",
"涨跌幅",
"涨跌额",
"成交量",
"成交额",
"振幅",
"换手率",
]
]
return temp_df
def stock_zh_a_hist_pre_min_em(
symbol: str = "000001",
start_time: str = "09:00:00",
end_time: str = "15:50:00",
) -> pd.DataFrame:
"""
东方财富网-行情首页-沪深京 A 股-每日分时行情包含盘前数据
http://quote.eastmoney.com/concept/sh603777.html?from=classic
:param symbol: 股票代码
:type symbol: str
:param start_time: 开始时间
:type start_time: str
:param end_time: 结束时间
:type end_time: str
:return: 每日分时行情包含盘前数据
:rtype: pandas.DataFrame
"""
code_id_dict = code_id_map_em()
url = "https://push2.eastmoney.com/api/qt/stock/trends2/get"
params = {
"fields1": "f1,f2,f3,f4,f5,f6,f7,f8,f9,f10,f11,f12,f13",
"fields2": "f51,f52,f53,f54,f55,f56,f57,f58",
"ut": "fa5fd1943c7b386f172d6893dbfba10b",
"ndays": "1",
"iscr": "1",
"iscca": "0",
"secid": f"{code_id_dict[symbol]}.{symbol}",
"_": "1623766962675",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(
[item.split(",") for item in data_json["data"]["trends"]]
)
temp_df.columns = [
"时间",
"开盘",
"收盘",
"最高",
"最低",
"成交量",
"成交额",
"最新价",
]
temp_df.index = pd.to_datetime(temp_df["时间"])
date_format = temp_df.index[0].date().isoformat()
temp_df = temp_df[
date_format + " " + start_time : date_format + " " + end_time
]
temp_df.reset_index(drop=True, inplace=True)
temp_df["开盘"] = pd.to_numeric(temp_df["开盘"])
temp_df["收盘"] = pd.to_numeric(temp_df["收盘"])
temp_df["最高"] = pd.to_numeric(temp_df["最高"])
temp_df["最低"] = pd.to_numeric(temp_df["最低"])
temp_df["成交量"] = pd.to_numeric(temp_df["成交量"])
temp_df["成交额"] = pd.to_numeric(temp_df["成交额"])
temp_df["最新价"] = pd.to_numeric(temp_df["最新价"])
temp_df["时间"] = pd.to_datetime(temp_df["时间"]).astype(str)
return temp_df
if __name__ == "__main__":
stock_zh_a_hist_df = stock_zh_a_hist(
symbol="000858",
period="daily",
start_date="20220516",
end_date="20220722",
adjust="",
)
print(stock_zh_a_hist_df)
exit(0)
stock_zh_a_spot_em_df = stock_zh_a_spot_em()
print(stock_zh_a_spot_em_df)
code_id_map_em_df = code_id_map_em()
print(code_id_map_em_df)
stock_zh_a_hist_df = stock_zh_a_hist(
symbol="430090",
period="daily",
start_date="20220516",
end_date="20220722",
adjust="hfq",
)
print(stock_zh_a_hist_df)
stock_zh_a_hist_min_em_df = stock_zh_a_hist_min_em(symbol="833454", period="1")
print(stock_zh_a_hist_min_em_df)
stock_zh_a_hist_pre_min_em_df = stock_zh_a_hist_pre_min_em(symbol="833454")
print(stock_zh_a_hist_pre_min_em_df)
stock_zh_a_spot_em_df = stock_zh_a_spot_em()
print(stock_zh_a_spot_em_df)
stock_zh_a_hist_min_em_df = stock_zh_a_hist_min_em(
symbol="000001", period='1'
)
print(stock_zh_a_hist_min_em_df)
stock_zh_a_hist_df = stock_zh_a_hist(
symbol="833454",
period="daily",
start_date="20170301",
end_date="20211115",
adjust="hfq",
)
print(stock_zh_a_hist_df)

888
stockapp/src/crawling/stock_lhb_em.py Normal file
View File

@ -0,0 +1,888 @@
# -*- coding:utf-8 -*-
# !/usr/bin/env python
"""
Date: 2022/3/15 17:32
Desc: 东方财富网-数据中心-龙虎榜单
https://data.eastmoney.com/stock/tradedetail.html
"""
import pandas as pd
import requests
from tqdm import tqdm
def stock_lhb_detail_em(
start_date: str = "20230403", end_date: str = "20230417"
) -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-龙虎榜详情
https://data.eastmoney.com/stock/tradedetail.html
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:return: 龙虎榜详情
:rtype: pandas.DataFrame
"""
start_date = "-".join([start_date[:4], start_date[4:6], start_date[6:]])
end_date = "-".join([end_date[:4], end_date[4:6], end_date[6:]])
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"sortColumns": "SECURITY_CODE,TRADE_DATE",
"sortTypes": "1,-1",
"pageSize": "5000",
"pageNumber": "1",
"reportName": "RPT_DAILYBILLBOARD_DETAILSNEW",
"columns": "SECURITY_CODE,SECUCODE,SECURITY_NAME_ABBR,TRADE_DATE,EXPLAIN,CLOSE_PRICE,CHANGE_RATE,BILLBOARD_NET_AMT,BILLBOARD_BUY_AMT,BILLBOARD_SELL_AMT,BILLBOARD_DEAL_AMT,ACCUM_AMOUNT,DEAL_NET_RATIO,DEAL_AMOUNT_RATIO,TURNOVERRATE,FREE_MARKET_CAP,EXPLANATION,D1_CLOSE_ADJCHRATE,D2_CLOSE_ADJCHRATE,D5_CLOSE_ADJCHRATE,D10_CLOSE_ADJCHRATE,SECURITY_TYPE_CODE",
"source": "WEB",
"client": "WEB",
"filter": f"(TRADE_DATE<='{end_date}')(TRADE_DATE>='{start_date}')",
}
r = requests.get(url, params=params)
data_json = r.json()
total_page_num = data_json["result"]["pages"]
big_df = pd.DataFrame()
for page in range(1, total_page_num + 1):
params.update(
{
"pageNumber": page,
}
)
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df["index"] = big_df.index + 1
big_df.rename(
columns={
"index": "序号",
"SECURITY_CODE": "代码",
"SECUCODE": "-",
"SECURITY_NAME_ABBR": "名称",
"TRADE_DATE": "上榜日",
"EXPLAIN": "解读",
"CLOSE_PRICE": "收盘价",
"CHANGE_RATE": "涨跌幅",
"BILLBOARD_NET_AMT": "龙虎榜净买额",
"BILLBOARD_BUY_AMT": "龙虎榜买入额",
"BILLBOARD_SELL_AMT": "龙虎榜卖出额",
"BILLBOARD_DEAL_AMT": "龙虎榜成交额",
"ACCUM_AMOUNT": "市场总成交额",
"DEAL_NET_RATIO": "净买额占总成交比",
"DEAL_AMOUNT_RATIO": "成交额占总成交比",
"TURNOVERRATE": "换手率",
"FREE_MARKET_CAP": "流通市值",
"EXPLANATION": "上榜原因",
"D1_CLOSE_ADJCHRATE": "上榜后1日",
"D2_CLOSE_ADJCHRATE": "上榜后2日",
"D5_CLOSE_ADJCHRATE": "上榜后5日",
"D10_CLOSE_ADJCHRATE": "上榜后10日",
},
inplace=True,
)
big_df = big_df[
[
"序号",
"代码",
"名称",
"上榜日",
"解读",
"收盘价",
"涨跌幅",
"龙虎榜净买额",
"龙虎榜买入额",
"龙虎榜卖出额",
"龙虎榜成交额",
"市场总成交额",
"净买额占总成交比",
"成交额占总成交比",
"换手率",
"流通市值",
"上榜原因",
"上榜后1日",
"上榜后2日",
"上榜后5日",
"上榜后10日",
]
]
big_df["上榜日"] = pd.to_datetime(big_df["上榜日"]).dt.date
big_df["收盘价"] = pd.to_numeric(big_df["收盘价"], errors="coerce")
big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"], errors="coerce")
big_df["龙虎榜净买额"] = pd.to_numeric(big_df["龙虎榜净买额"], errors="coerce")
big_df["龙虎榜买入额"] = pd.to_numeric(big_df["龙虎榜买入额"], errors="coerce")
big_df["龙虎榜卖出额"] = pd.to_numeric(big_df["龙虎榜卖出额"], errors="coerce")
big_df["龙虎榜成交额"] = pd.to_numeric(big_df["龙虎榜成交额"], errors="coerce")
big_df["市场总成交额"] = pd.to_numeric(big_df["市场总成交额"], errors="coerce")
big_df["净买额占总成交比"] = pd.to_numeric(big_df["净买额占总成交比"], errors="coerce")
big_df["成交额占总成交比"] = pd.to_numeric(big_df["成交额占总成交比"], errors="coerce")
big_df["换手率"] = pd.to_numeric(big_df["换手率"], errors="coerce")
big_df["流通市值"] = pd.to_numeric(big_df["流通市值"], errors="coerce")
big_df["上榜后1日"] = pd.to_numeric(big_df["上榜后1日"], errors="coerce")
big_df["上榜后2日"] = pd.to_numeric(big_df["上榜后2日"], errors="coerce")
big_df["上榜后5日"] = pd.to_numeric(big_df["上榜后5日"], errors="coerce")
big_df["上榜后10日"] = pd.to_numeric(big_df["上榜后10日"], errors="coerce")
return big_df
def stock_lhb_stock_statistic_em(symbol: str = "近一月") -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-个股上榜统计
https://data.eastmoney.com/stock/tradedetail.html
:param symbol: choice of {"近一月", "近三月", "近六月", "近一年"}
:type symbol: str
:return: 个股上榜统计
:rtype: pandas.DataFrame
"""
symbol_map = {
"近一月": "01",
"近三月": "02",
"近六月": "03",
"近一年": "04",
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"sortColumns": "BILLBOARD_TIMES,LATEST_TDATE,SECURITY_CODE",
"sortTypes": "-1,-1,1",
"pageSize": "500",
"pageNumber": "1",
"reportName": "RPT_BILLBOARD_TRADEALL",
"columns": "ALL",
"source": "WEB",
"client": "WEB",
"filter": f'(STATISTICS_CYCLE="{symbol_map[symbol]}")',
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
temp_df.reset_index(inplace=True)
temp_df["index"] = temp_df.index + 1
temp_df.columns = [
"序号",
"-",
"代码",
"最近上榜日",
"名称",
"近1个月涨跌幅",
"近3个月涨跌幅",
"近6个月涨跌幅",
"近1年涨跌幅",
"涨跌幅",
"收盘价",
"-",
"龙虎榜总成交额",
"龙虎榜净买额",
"-",
"-",
"机构买入净额",
"上榜次数",
"龙虎榜买入额",
"龙虎榜卖出额",
"机构买入总额",
"机构卖出总额",
"买方机构次数",
"卖方机构次数",
"-",
]
temp_df = temp_df[
[
"序号",
"代码",
"名称",
"最近上榜日",
"收盘价",
"涨跌幅",
"上榜次数",
"龙虎榜净买额",
"龙虎榜买入额",
"龙虎榜卖出额",
"龙虎榜总成交额",
"买方机构次数",
"卖方机构次数",
"机构买入净额",
"机构买入总额",
"机构卖出总额",
"近1个月涨跌幅",
"近3个月涨跌幅",
"近6个月涨跌幅",
"近1年涨跌幅",
]
]
temp_df["最近上榜日"] = pd.to_datetime(temp_df["最近上榜日"]).dt.date
return temp_df
def stock_lhb_jgmmtj_em(
start_date: str = "20220906", end_date: str = "20220906"
) -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-机构买卖每日统计
https://data.eastmoney.com/stock/jgmmtj.html
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:return: 机构买卖每日统计
:rtype: pandas.DataFrame
"""
start_date = "-".join([start_date[:4], start_date[4:6], start_date[6:]])
end_date = "-".join([end_date[:4], end_date[4:6], end_date[6:]])
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"sortColumns": "NET_BUY_AMT,TRADE_DATE,SECURITY_CODE",
"sortTypes": "-1,-1,1",
"pageSize": "5000",
"pageNumber": "1",
"reportName": "RPT_ORGANIZATION_TRADE_DETAILS",
"columns": "ALL",
"source": "WEB",
"client": "WEB",
"filter": f"(TRADE_DATE>='{start_date}')(TRADE_DATE<='{end_date}')",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
temp_df.reset_index(inplace=True)
temp_df["index"] = temp_df.index + 1
temp_df.columns = [
"序号",
"-",
"名称",
"代码",
"上榜日期",
"收盘价",
"涨跌幅",
"买方机构数",
"卖方机构数",
"机构买入总额",
"机构卖出总额",
"机构买入净额",
"市场总成交额",
"机构净买额占总成交额比",
"换手率",
"流通市值",
"上榜原因",
"-",
"-",
"-",
"-",
"-",
"-",
"-",
"-",
"-",
]
temp_df = temp_df[
[
"序号",
"代码",
"名称",
"收盘价",
"涨跌幅",
"买方机构数",
"卖方机构数",
"机构买入总额",
"机构卖出总额",
"机构买入净额",
"市场总成交额",
"机构净买额占总成交额比",
"换手率",
"流通市值",
"上榜原因",
"上榜日期",
]
]
temp_df["上榜日期"] = pd.to_datetime(temp_df["上榜日期"]).dt.date
temp_df["收盘价"] = pd.to_numeric(temp_df["收盘价"], errors="coerce")
temp_df["涨跌幅"] = pd.to_numeric(temp_df["涨跌幅"], errors="coerce")
temp_df["买方机构数"] = pd.to_numeric(temp_df["买方机构数"], errors="coerce")
temp_df["卖方机构数"] = pd.to_numeric(temp_df["卖方机构数"], errors="coerce")
temp_df["机构买入总额"] = pd.to_numeric(temp_df["机构买入总额"], errors="coerce")
temp_df["机构卖出总额"] = pd.to_numeric(temp_df["机构卖出总额"], errors="coerce")
temp_df["机构买入净额"] = pd.to_numeric(temp_df["机构买入净额"], errors="coerce")
temp_df["市场总成交额"] = pd.to_numeric(temp_df["市场总成交额"], errors="coerce")
temp_df["机构净买额占总成交额比"] = pd.to_numeric(temp_df["机构净买额占总成交额比"], errors="coerce")
temp_df["换手率"] = pd.to_numeric(temp_df["换手率"], errors="coerce")
temp_df["流通市值"] = pd.to_numeric(temp_df["流通市值"], errors="coerce")
return temp_df
def stock_lhb_jgstatistic_em(symbol: str = "近一月") -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-机构席位追踪
https://data.eastmoney.com/stock/jgstatistic.html
:param symbol: choice of {"近一月", "近三月", "近六月", "近一年"}
:type symbol: str
:return: 机构席位追踪
:rtype: pandas.DataFrame
"""
symbol_map = {
"近一月": "01",
"近三月": "02",
"近六月": "03",
"近一年": "04",
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"sortColumns": "ONLIST_TIMES,SECURITY_CODE",
"sortTypes": "-1,1",
"pageSize": "5000",
"pageNumber": "1",
"reportName": "RPT_ORGANIZATION_SEATNEW",
"columns": "ALL",
"source": "WEB",
"client": "WEB",
"filter": f'(STATISTICSCYCLE="{symbol_map[symbol]}")',
}
r = requests.get(url, params=params)
data_json = r.json()
total_page = data_json["result"]["pages"]
big_df = pd.DataFrame()
for page in tqdm(range(1, total_page + 1), leave=False):
params.update({"pageNumber": page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df["index"] = big_df.index + 1
big_df.rename(
columns={
"index": "序号",
"SECURITY_CODE": "代码",
"SECURITY_NAME_ABBR": "名称",
"CLOSE_PRICE": "收盘价",
"CHANGE_RATE": "涨跌幅",
"AMOUNT": "龙虎榜成交金额",
"ONLIST_TIMES": "上榜次数",
"BUY_AMT": "机构买入额",
"BUY_TIMES": "机构买入次数",
"SELL_AMT": "机构卖出额",
"SELL_TIMES": "机构卖出次数",
"NET_BUY_AMT": "机构净买额",
"M1_CLOSE_ADJCHRATE": "近1个月涨跌幅",
"M3_CLOSE_ADJCHRATE": "近3个月涨跌幅",
"M6_CLOSE_ADJCHRATE": "近6个月涨跌幅",
"Y1_CLOSE_ADJCHRATE": "近1年涨跌幅",
},
inplace=True,
)
big_df = big_df[
[
"序号",
"代码",
"名称",
"收盘价",
"涨跌幅",
"龙虎榜成交金额",
"上榜次数",
"机构买入额",
"机构买入次数",
"机构卖出额",
"机构卖出次数",
"机构净买额",
"近1个月涨跌幅",
"近3个月涨跌幅",
"近6个月涨跌幅",
"近1年涨跌幅",
]
]
big_df["收盘价"] = pd.to_numeric(big_df["收盘价"], errors="coerce")
big_df["涨跌幅"] = pd.to_numeric(big_df["涨跌幅"], errors="coerce")
big_df["龙虎榜成交金额"] = pd.to_numeric(big_df["龙虎榜成交金额"], errors="coerce")
big_df["上榜次数"] = pd.to_numeric(big_df["上榜次数"], errors="coerce")
big_df["机构买入额"] = pd.to_numeric(big_df["机构买入额"], errors="coerce")
big_df["机构买入次数"] = pd.to_numeric(big_df["机构买入次数"], errors="coerce")
big_df["机构卖出额"] = pd.to_numeric(big_df["机构卖出额"], errors="coerce")
big_df["机构卖出次数"] = pd.to_numeric(big_df["机构卖出次数"], errors="coerce")
big_df["机构净买额"] = pd.to_numeric(big_df["机构净买额"], errors="coerce")
big_df["近1个月涨跌幅"] = pd.to_numeric(big_df["近1个月涨跌幅"], errors="coerce")
big_df["近3个月涨跌幅"] = pd.to_numeric(big_df["近3个月涨跌幅"], errors="coerce")
big_df["近6个月涨跌幅"] = pd.to_numeric(big_df["近6个月涨跌幅"], errors="coerce")
big_df["近1年涨跌幅"] = pd.to_numeric(big_df["近1年涨跌幅"], errors="coerce")
return big_df
def stock_lhb_hyyyb_em(
start_date: str = "20220324", end_date: str = "20220324"
) -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-每日活跃营业部
https://data.eastmoney.com/stock/jgmmtj.html
:param start_date: 开始日期
:type start_date: str
:param end_date: 结束日期
:type end_date: str
:return: 每日活跃营业部
:rtype: pandas.DataFrame
"""
start_date = "-".join([start_date[:4], start_date[4:6], start_date[6:]])
end_date = "-".join([end_date[:4], end_date[4:6], end_date[6:]])
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"sortColumns": "TOTAL_NETAMT,ONLIST_DATE,OPERATEDEPT_CODE",
"sortTypes": "-1,-1,1",
"pageSize": "5000",
"pageNumber": "1",
"reportName": "RPT_OPERATEDEPT_ACTIVE",
"columns": "ALL",
"source": "WEB",
"client": "WEB",
"filter": f"(ONLIST_DATE>='{start_date}')(ONLIST_DATE<='{end_date}')",
}
r = requests.get(url, params=params)
data_json = r.json()
total_page = data_json["result"]["pages"]
big_df = pd.DataFrame()
for page in tqdm(range(1, total_page + 1), leave=False):
params.update({"pageNumber": page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df["index"] = big_df.index + 1
big_df.columns = [
"序号",
"营业部名称",
"上榜日",
"买入个股数",
"卖出个股数",
"买入总金额",
"卖出总金额",
"总买卖净额",
"-",
"-",
"买入股票",
"-",
"-",
]
big_df = big_df[
[
"序号",
"营业部名称",
"上榜日",
"买入个股数",
"卖出个股数",
"买入总金额",
"卖出总金额",
"总买卖净额",
"买入股票",
]
]
big_df["上榜日"] = pd.to_datetime(big_df["上榜日"]).dt.date
big_df["买入个股数"] = pd.to_numeric(big_df["买入个股数"])
big_df["卖出个股数"] = pd.to_numeric(big_df["卖出个股数"])
big_df["买入总金额"] = pd.to_numeric(big_df["买入总金额"])
big_df["卖出总金额"] = pd.to_numeric(big_df["卖出总金额"])
big_df["总买卖净额"] = pd.to_numeric(big_df["总买卖净额"])
return big_df
def stock_lhb_yybph_em(symbol: str = "近一月") -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-营业部排行
https://data.eastmoney.com/stock/yybph.html
:param symbol: choice of {"近一月", "近三月", "近六月", "近一年"}
:type symbol: str
:return: 营业部排行
:rtype: pandas.DataFrame
"""
symbol_map = {
"近一月": "01",
"近三月": "02",
"近六月": "03",
"近一年": "04",
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"sortColumns": "TOTAL_BUYER_SALESTIMES_1DAY,OPERATEDEPT_CODE",
"sortTypes": "-1,1",
"pageSize": "5000",
"pageNumber": "1",
"reportName": "RPT_RATEDEPT_RETURNT_RANKING",
"columns": "ALL",
"source": "WEB",
"client": "WEB",
"filter": f'(STATISTICSCYCLE="{symbol_map[symbol]}")',
}
r = requests.get(url, params=params)
data_json = r.json()
total_page = data_json["result"]["pages"]
big_df = pd.DataFrame()
for page in tqdm(range(1, total_page + 1), leave=False):
params.update({"pageNumber": page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df["index"] = big_df.index + 1
big_df.rename(
columns={
"index": "序号",
"OPERATEDEPT_NAME": "营业部名称",
"TOTAL_BUYER_SALESTIMES_1DAY": "上榜后1天-买入次数",
"AVERAGE_INCREASE_1DAY": "上榜后1天-平均涨幅",
"RISE_PROBABILITY_1DAY": "上榜后1天-上涨概率",
"TOTAL_BUYER_SALESTIMES_2DAY": "上榜后2天-买入次数",
"AVERAGE_INCREASE_2DAY": "上榜后2天-平均涨幅",
"RISE_PROBABILITY_2DAY": "上榜后2天-上涨概率",
"TOTAL_BUYER_SALESTIMES_3DAY": "上榜后3天-买入次数",
"AVERAGE_INCREASE_3DAY": "上榜后3天-平均涨幅",
"RISE_PROBABILITY_3DAY": "上榜后3天-上涨概率",
"TOTAL_BUYER_SALESTIMES_5DAY": "上榜后5天-买入次数",
"AVERAGE_INCREASE_5DAY": "上榜后5天-平均涨幅",
"RISE_PROBABILITY_5DAY": "上榜后5天-上涨概率",
"TOTAL_BUYER_SALESTIMES_10DAY": "上榜后10天-买入次数",
"AVERAGE_INCREASE_10DAY": "上榜后10天-平均涨幅",
"RISE_PROBABILITY_10DAY": "上榜后10天-上涨概率",
},
inplace=True,
)
big_df = big_df[
[
"序号",
"营业部名称",
"上榜后1天-买入次数",
"上榜后1天-平均涨幅",
"上榜后1天-上涨概率",
"上榜后2天-买入次数",
"上榜后2天-平均涨幅",
"上榜后2天-上涨概率",
"上榜后3天-买入次数",
"上榜后3天-平均涨幅",
"上榜后3天-上涨概率",
"上榜后5天-买入次数",
"上榜后5天-平均涨幅",
"上榜后5天-上涨概率",
"上榜后10天-买入次数",
"上榜后10天-平均涨幅",
"上榜后10天-上涨概率",
]
]
big_df["上榜后1天-买入次数"] = pd.to_numeric(big_df["上榜后1天-买入次数"], errors="coerce")
big_df["上榜后1天-平均涨幅"] = pd.to_numeric(big_df["上榜后1天-平均涨幅"], errors="coerce")
big_df["上榜后1天-上涨概率"] = pd.to_numeric(big_df["上榜后1天-上涨概率"], errors="coerce")
big_df["上榜后2天-买入次数"] = pd.to_numeric(big_df["上榜后2天-买入次数"], errors="coerce")
big_df["上榜后2天-平均涨幅"] = pd.to_numeric(big_df["上榜后2天-平均涨幅"], errors="coerce")
big_df["上榜后2天-上涨概率"] = pd.to_numeric(big_df["上榜后2天-上涨概率"], errors="coerce")
big_df["上榜后3天-买入次数"] = pd.to_numeric(big_df["上榜后3天-买入次数"], errors="coerce")
big_df["上榜后3天-平均涨幅"] = pd.to_numeric(big_df["上榜后3天-平均涨幅"], errors="coerce")
big_df["上榜后3天-上涨概率"] = pd.to_numeric(big_df["上榜后3天-上涨概率"], errors="coerce")
big_df["上榜后5天-买入次数"] = pd.to_numeric(big_df["上榜后5天-买入次数"], errors="coerce")
big_df["上榜后5天-平均涨幅"] = pd.to_numeric(big_df["上榜后5天-平均涨幅"], errors="coerce")
big_df["上榜后5天-上涨概率"] = pd.to_numeric(big_df["上榜后5天-上涨概率"], errors="coerce")
big_df["上榜后10天-买入次数"] = pd.to_numeric(big_df["上榜后10天-买入次数"], errors="coerce")
big_df["上榜后10天-平均涨幅"] = pd.to_numeric(big_df["上榜后10天-平均涨幅"], errors="coerce")
big_df["上榜后10天-上涨概率"] = pd.to_numeric(big_df["上榜后10天-上涨概率"], errors="coerce")
return big_df
def stock_lhb_traderstatistic_em(symbol: str = "近一月") -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-营业部统计
https://data.eastmoney.com/stock/traderstatistic.html
:param symbol: choice of {"近一月", "近三月", "近六月", "近一年"}
:type symbol: str
:return: 营业部统计
:rtype: pandas.DataFrame
"""
symbol_map = {
"近一月": "01",
"近三月": "02",
"近六月": "03",
"近一年": "04",
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"sortColumns": "AMOUNT,OPERATEDEPT_CODE",
"sortTypes": "-1,1",
"pageSize": "5000",
"pageNumber": "1",
"reportName": "RPT_OPERATEDEPT_LIST_STATISTICS",
"columns": "ALL",
"source": "WEB",
"client": "WEB",
"filter": f'(STATISTICSCYCLE="{symbol_map[symbol]}")',
}
r = requests.get(url, params=params)
data_json = r.json()
total_page = data_json["result"]["pages"]
big_df = pd.DataFrame()
for page in tqdm(range(1, total_page + 1), leave=False):
params.update({"pageNumber": page})
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.reset_index(inplace=True)
big_df["index"] = big_df.index + 1
big_df.rename(
columns={
"index": "序号",
"OPERATEDEPT_NAME": "营业部名称",
"AMOUNT": "龙虎榜成交金额",
"SALES_ONLIST_TIMES": "上榜次数",
"ACT_BUY": "买入额",
"TOTAL_BUYER_SALESTIMES": "买入次数",
"ACT_SELL": "卖出额",
"TOTAL_SELLER_SALESTIMES": "卖出次数",
},
inplace=True,
)
big_df = big_df[
[
"序号",
"营业部名称",
"龙虎榜成交金额",
"上榜次数",
"买入额",
"买入次数",
"卖出额",
"卖出次数",
]
]
big_df["龙虎榜成交金额"] = pd.to_numeric(big_df["龙虎榜成交金额"], errors="coerce")
big_df["上榜次数"] = pd.to_numeric(big_df["上榜次数"], errors="coerce")
big_df["买入额"] = pd.to_numeric(big_df["买入额"], errors="coerce")
big_df["买入次数"] = pd.to_numeric(big_df["买入次数"], errors="coerce")
big_df["卖出额"] = pd.to_numeric(big_df["卖出额"], errors="coerce")
big_df["卖出次数"] = pd.to_numeric(big_df["卖出次数"], errors="coerce")
return big_df
def stock_lhb_stock_detail_date_em(symbol: str = "600077") -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-个股龙虎榜详情-日期
https://data.eastmoney.com/stock/tradedetail.html
:param symbol: 股票代码
:type symbol: str
:return: 个股龙虎榜详情-日期
:rtype: pandas.DataFrame
"""
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"reportName": "RPT_LHB_BOARDDATE",
"columns": "SECURITY_CODE,TRADE_DATE,TR_DATE",
"filter": f'(SECURITY_CODE="{symbol}")',
"pageNumber": "1",
"pageSize": "1000",
"sortTypes": "-1",
"sortColumns": "TRADE_DATE",
"source": "WEB",
"client": "WEB",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
temp_df.reset_index(inplace=True)
temp_df["index"] = temp_df.index + 1
temp_df.columns = [
"序号",
"股票代码",
"交易日",
"-",
]
temp_df = temp_df[
[
"序号",
"股票代码",
"交易日",
]
]
temp_df["交易日"] = pd.to_datetime(temp_df["交易日"]).dt.date
return temp_df
def stock_lhb_stock_detail_em(
symbol: str = "000788", date: str = "20220315", flag: str = "卖出"
) -> pd.DataFrame:
"""
东方财富网-数据中心-龙虎榜单-个股龙虎榜详情
https://data.eastmoney.com/stock/lhb/600077.html
:param symbol: 股票代码
:type symbol: str
:param date: 查询日期; 需要通过 ak.stock_lhb_stock_detail_date_em(symbol="600077") 接口获取相应股票的有龙虎榜详情数据的日期
:type date: str
:param flag: choice of {"买入", "卖出"}
:type flag: str
:return: 个股龙虎榜详情
:rtype: pandas.DataFrame
"""
flag_map = {
"买入": "BUY",
"卖出": "SELL",
}
report_map = {
"买入": "RPT_BILLBOARD_DAILYDETAILSBUY",
"卖出": "RPT_BILLBOARD_DAILYDETAILSSELL",
}
url = "https://datacenter-web.eastmoney.com/api/data/v1/get"
params = {
"reportName": report_map[flag],
"columns": "ALL",
"filter": f"""(TRADE_DATE='{'-'.join([date[:4], date[4:6], date[6:]])}')(SECURITY_CODE="{symbol}")""",
"pageNumber": "1",
"pageSize": "500",
"sortTypes": "-1",
"sortColumns": flag_map[flag],
"source": "WEB",
"client": "WEB",
"_": "1647338693644",
}
r = requests.get(url, params=params)
data_json = r.json()
temp_df = pd.DataFrame(data_json["result"]["data"])
temp_df.reset_index(inplace=True)
temp_df["index"] = temp_df.index + 1
if flag == "买入":
temp_df.columns = [
"序号",
"-",
"-",
"-",
"-",
"交易营业部名称",
"类型",
"-",
"-",
"-",
"-",
"买入金额",
"卖出金额",
"净额",
"-",
"-",
"-",
"-",
"买入金额-占总成交比例",
"卖出金额-占总成交比例",
"-",
]
temp_df = temp_df[
[
"序号",
"交易营业部名称",
"买入金额",
"买入金额-占总成交比例",
"卖出金额",
"卖出金额-占总成交比例",
"净额",
"类型",
]
]
temp_df["买入金额"] = pd.to_numeric(temp_df["买入金额"])
temp_df["买入金额-占总成交比例"] = pd.to_numeric(temp_df["买入金额-占总成交比例"])
temp_df["卖出金额"] = pd.to_numeric(temp_df["卖出金额"])
temp_df["卖出金额-占总成交比例"] = pd.to_numeric(temp_df["卖出金额-占总成交比例"])
temp_df.sort_values("类型", inplace=True)
temp_df.reset_index(inplace=True, drop=True)
temp_df["序号"] = range(1, len(temp_df["序号"]) + 1)
else:
temp_df.columns = [
"序号",
"-",
"-",
"-",
"-",
"交易营业部名称",
"类型",
"-",
"-",
"-",
"-",
"买入金额",
"卖出金额",
"净额",
"-",
"-",
"-",
"-",
"买入金额-占总成交比例",
"卖出金额-占总成交比例",
"-",
]
temp_df = temp_df[
[
"序号",
"交易营业部名称",
"买入金额",
"买入金额-占总成交比例",
"卖出金额",
"卖出金额-占总成交比例",
"净额",
"类型",
]
]
temp_df["买入金额"] = pd.to_numeric(temp_df["买入金额"])
temp_df["买入金额-占总成交比例"] = pd.to_numeric(temp_df["买入金额-占总成交比例"])
temp_df["卖出金额"] = pd.to_numeric(temp_df["卖出金额"])
temp_df["卖出金额-占总成交比例"] = pd.to_numeric(temp_df["卖出金额-占总成交比例"])
temp_df.sort_values("类型", inplace=True)
temp_df.reset_index(inplace=True, drop=True)
temp_df["序号"] = range(1, len(temp_df["序号"]) + 1)
return temp_df
if __name__ == "__main__":
stock_lhb_detail_em_df = stock_lhb_detail_em(
start_date="20230403", end_date="20230417"
)
print(stock_lhb_detail_em_df)
stock_lhb_stock_statistic_em_df = stock_lhb_stock_statistic_em(symbol="近一月")
print(stock_lhb_stock_statistic_em_df)
stock_lhb_stock_statistic_em_df = stock_lhb_stock_statistic_em(symbol="近三月")
print(stock_lhb_stock_statistic_em_df)
stock_lhb_stock_statistic_em_df = stock_lhb_stock_statistic_em(symbol="近六月")
print(stock_lhb_stock_statistic_em_df)
stock_lhb_stock_statistic_em_df = stock_lhb_stock_statistic_em(symbol="近一年")
print(stock_lhb_stock_statistic_em_df)
stock_lhb_jgmmtj_em_df = stock_lhb_jgmmtj_em(
start_date="20220904", end_date="20220906"
)
print(stock_lhb_jgmmtj_em_df)
stock_lhb_jgstatistic_em_df = stock_lhb_jgstatistic_em(symbol="近一月")
print(stock_lhb_jgstatistic_em_df)
stock_lhb_hyyyb_em_df = stock_lhb_hyyyb_em(
start_date="20220324", end_date="20220324"
)
print(stock_lhb_hyyyb_em_df)
stock_lhb_yybph_em_df = stock_lhb_yybph_em(symbol="近一月")
print(stock_lhb_yybph_em_df)
stock_lhb_traderstatistic_em_df = stock_lhb_traderstatistic_em(symbol="近一月")
print(stock_lhb_traderstatistic_em_df)
stock_lhb_stock_detail_date_em_df = stock_lhb_stock_detail_date_em(symbol="002901")
print(stock_lhb_stock_detail_date_em_df)
stock_lhb_stock_detail_em_df = stock_lhb_stock_detail_em(
symbol="002901", date="20221012", flag="买入"
)
print(stock_lhb_stock_detail_em_df)
stock_lhb_stock_detail_em_df = stock_lhb_stock_detail_em(
symbol="600016", date="20220324", flag="买入"
)
print(stock_lhb_stock_detail_em_df)

216
stockapp/src/crawling/stock_lhb_sina.py Normal file
View File

@ -0,0 +1,216 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
Date: 2022/11/19 12:00
Desc: 新浪财经-龙虎榜
https://vip.stock.finance.sina.com.cn/q/go.php/vInvestConsult/kind/lhb/index.phtml
"""
import pandas as pd
import requests
from bs4 import BeautifulSoup
from tqdm import tqdm
def stock_lhb_detail_daily_sina(
trade_date: str = "20200730", symbol: str = "当日无价格涨跌幅限制的A股，出现异常波动停牌的股票"
) -> pd.DataFrame:
"""
龙虎榜-每日详情
http://vip.stock.finance.sina.com.cn/q/go.php/vInvestConsult/kind/lhb/index.phtml
:param trade_date: 交易日, e.g., trade_date="20200729"
:type trade_date: str
:param symbol: 指定标题
:type symbol: str
:return: 龙虎榜-每日详情
:rtype: pandas.DataFrame
"""
trade_date = "-".join([trade_date[:4], trade_date[4:6], trade_date[6:]])
url = "http://vip.stock.finance.sina.com.cn/q/go.php/vInvestConsult/kind/lhb/index.phtml"
params = {"tradedate": trade_date}
r = requests.get(url, params=params)
soup = BeautifulSoup(r.text, "lxml")
table_name_list = [
item.get_text().strip()
for item in soup.find_all(
"span", attrs={"style": "font-weight:bold;font-size:14px;"}
)
if item.get_text().strip() != ""
]
if symbol == "返回当前交易日所有可查询的指标":
return table_name_list
else:
position_num = table_name_list.index(symbol)
if len(table_name_list) == position_num + 1:
temp_df_1 = pd.read_html(r.text, flavor='bs4', header=1)[position_num].iloc[0:, :]
temp_df_2 = pd.read_html(r.text, flavor='bs4', header=1)[position_num + 1].iloc[0:, :]
temp_df_3 = pd.read_html(r.text, flavor='bs4', header=1)[position_num + 2].iloc[0:, :]
temp_df = pd.concat([temp_df_1, temp_df_2, temp_df_3], ignore_index=True)
else:
temp_df = pd.read_html(r.text, flavor='bs4', header=1)[position_num].iloc[0:, :]
temp_df["股票代码"] = temp_df["股票代码"].astype(str).str.zfill(6)
del temp_df["查看详情"]
temp_df.columns = ["序号", "股票代码", "股票名称", "收盘价", "对应值", "成交量", "成交额"]
return temp_df
def _find_last_page(url: str = None, recent_day: str = "60"):
url = "http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/ggtj/index.phtml"
params = {
"last": recent_day,
"p": "1",
}
r = requests.get(url, params=params)
soup = BeautifulSoup(r.text, "lxml")
try:
previous_page = int(soup.find_all(attrs={"class": "page"})[-2].text)
except:
previous_page = 1
if previous_page != 1:
while True:
params = {
"last": recent_day,
"p": previous_page,
}
r = requests.get(url, params=params)
soup = BeautifulSoup(r.text, "lxml")
last_page = int(soup.find_all(attrs={"class": "page"})[-2].text)
if last_page != previous_page:
previous_page = last_page
continue
else:
break
return previous_page
def stock_lhb_ggtj_sina(recent_day: str = "30") -> pd.DataFrame:
"""
龙虎榜-个股上榜统计
http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/ggtj/index.phtml
:param recent_day: choice of {"5": 最近 5 天; "10": 最近 10 天; "30": 最近 30 天; "60": 最近 60 天;}
:type recent_day: str
:return: 龙虎榜-每日详情
:rtype: pandas.DataFrame
"""
url = "http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/ggtj/index.phtml"
last_page_num = _find_last_page(url, recent_day)
big_df = pd.DataFrame()
for page in tqdm(range(1, last_page_num + 1), leave=False):
params = {
"last": recent_day,
"p": page,
}
r = requests.get(url, params=params)
temp_df = pd.read_html(r.text)[0].iloc[0:, :]
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df["股票代码"] = big_df["股票代码"].astype(str).str.zfill(6)
big_df.columns = ["股票代码", "股票名称", "上榜次数", "累积购买额", "累积卖出额", "净额", "买入席位数", "卖出席位数"]
return big_df
def stock_lhb_yytj_sina(recent_day: str = "5") -> pd.DataFrame:
"""
龙虎榜-营业部上榜统计
http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/yytj/index.phtml
:param recent_day: choice of {"5": 最近 5 天; "10": 最近 10 天; "30": 最近 30 天; "60": 最近 60 天;}
:type recent_day: str
:return: 龙虎榜-营业部上榜统计
:rtype: pandas.DataFrame
"""
url = "http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/yytj/index.phtml"
last_page_num = _find_last_page(url, recent_day)
big_df = pd.DataFrame()
for page in tqdm(range(1, last_page_num + 1), leave=False):
params = {
"last": "5",
"p": page,
}
r = requests.get(url, params=params)
temp_df = pd.read_html(r.text)[0].iloc[0:, :]
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df.columns = ["营业部名称", "上榜次数", "累积购买额", "买入席位数", "累积卖出额", "卖出席位数", "买入前三股票"]
big_df['上榜次数'] = pd.to_numeric(big_df['上榜次数'], errors="coerce")
big_df['买入席位数'] = pd.to_numeric(big_df['买入席位数'], errors="coerce")
big_df['卖出席位数'] = pd.to_numeric(big_df['卖出席位数'], errors="coerce")
return big_df
def stock_lhb_jgzz_sina(recent_day: str = "5") -> pd.DataFrame:
"""
龙虎榜-机构席位追踪
http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/jgzz/index.phtml
:param recent_day: choice of {"5": 最近 5 天; "10": 最近 10 天; "30": 最近 30 天; "60": 最近 60 天;}
:type recent_day: str
:return: 龙虎榜-机构席位追踪
:rtype: pandas.DataFrame
"""
url = "http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/jgzz/index.phtml"
last_page_num = _find_last_page(url, recent_day)
big_df = pd.DataFrame()
for page in tqdm(range(1, last_page_num + 1), leave=False):
params = {
"last": recent_day,
"p": page,
}
r = requests.get(url, params=params)
temp_df = pd.read_html(r.text)[0].iloc[0:, :]
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df["股票代码"] = big_df["股票代码"].astype(str).str.zfill(6)
del big_df["当前价"]
del big_df["涨跌幅"]
big_df.columns = ["股票代码", "股票名称", "累积买入额", "买入次数", "累积卖出额", "卖出次数", "净额"]
big_df['买入次数'] = pd.to_numeric(big_df['买入次数'], errors="coerce")
big_df['卖出次数'] = pd.to_numeric(big_df['卖出次数'], errors="coerce")
return big_df
def stock_lhb_jgmx_sina() -> pd.DataFrame:
"""
龙虎榜-机构席位成交明细
http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/jgmx/index.phtml
:return: 龙虎榜-机构席位成交明细
:rtype: pandas.DataFrame
"""
url = "http://vip.stock.finance.sina.com.cn/q/go.php/vLHBData/kind/jgmx/index.phtml"
params = {
"p": "1",
}
r = requests.get(url, params=params)
soup = BeautifulSoup(r.text, "lxml")
try:
last_page_num = int(soup.find_all(attrs={"class": "page"})[-2].text)
except:
last_page_num = 1
big_df = pd.DataFrame()
for page in tqdm(range(1, last_page_num + 1), leave=False):
params = {
"p": page,
}
r = requests.get(url, params=params)
temp_df = pd.read_html(r.text)[0].iloc[0:, :]
big_df = pd.concat([big_df, temp_df], ignore_index=True)
big_df["股票代码"] = big_df["股票代码"].astype(str).str.zfill(6)
return big_df
if __name__ == "__main__":
indicator_name_list = stock_lhb_detail_daily_sina(
trade_date="20221118", symbol="返回当前交易日所有可查询的指标"
)
print(indicator_name_list)
stock_lhb_detail_daily_sina_df = stock_lhb_detail_daily_sina(
trade_date="20221118", symbol="换手率达20%的证券"
)
print(stock_lhb_detail_daily_sina_df)
stock_lhb_ggtj_sina_df = stock_lhb_ggtj_sina(recent_day="60")
print(stock_lhb_ggtj_sina_df)
stock_lhb_yytj_sina_df = stock_lhb_yytj_sina(recent_day="60")
print(stock_lhb_yytj_sina_df)
stock_lhb_jgzz_sina_df = stock_lhb_jgzz_sina(recent_day="30")
print(stock_lhb_jgzz_sina_df)
stock_lhb_jgmx_sina_df = stock_lhb_jgmx_sina()
print(stock_lhb_jgmx_sina_df)

79
stockapp/src/crawling/stock_selection.py Normal file
View File

@ -0,0 +1,79 @@
# -*- coding:utf-8 -*-
# !/usr/bin/env python
import pandas as pd
import requests
import instock.core.tablestructure as tbs
__author__ = 'myh '
__date__ = '2023/5/9 '
def stock_selection() -> pd.DataFrame:
"""
东方财富网-个股-选股器
https://data.eastmoney.com/xuangu/
:return: 选股器
:rtype: pandas.DataFrame
"""
cols = tbs.TABLE_CN_STOCK_SELECTION['columns']
sty = "" # 初始值 "SECUCODE,SECURITY_CODE,SECURITY_NAME_ABBR,CHANGE_RATE"
for k in cols:
sty = f"{sty},{cols[k]['map']}"
url = "https://data.eastmoney.com/dataapi/xuangu/list"
params = {
"sty": sty[1:],
"filter": "(MARKET+in+(\"上交所主板\",\"深交所主板\",\"深交所创业板\"))(NEW_PRICE>0)",
"p": 1,
"ps": 10000,
"source": "SELECT_SECURITIES",
"client": "WEB"
}
r = requests.get(url, params=params)
data_json = r.json()
data = data_json["result"]["data"]
if not data:
return pd.DataFrame()
temp_df = pd.DataFrame(data)
mask = ~temp_df['CONCEPT'].isna()
temp_df.loc[mask, 'CONCEPT'] = temp_df.loc[mask, 'CONCEPT'].apply(lambda x: ', '.join(x))
mask = ~temp_df['STYLE'].isna()
temp_df.loc[mask, 'STYLE'] = temp_df.loc[mask, 'STYLE'].apply(lambda x: ', '.join(x))
for k in cols:
t = tbs.get_field_type_name(cols[k]["type"])
if t == 'numeric':
temp_df[cols[k]["map"]] = pd.to_numeric(temp_df[cols[k]["map"]], errors="coerce")
elif t == 'datetime':
temp_df[cols[k]["map"]] = pd.to_datetime(temp_df[cols[k]["map"]], errors="coerce").dt.date
return temp_df
def stock_selection_params():
"""
东方财富网-个股-选股器-选股指标
https://data.eastmoney.com/xuangu/
:return: 选股器-选股指标
:rtype: pandas.DataFrame
"""
url = "https://datacenter-web.eastmoney.com/wstock/selection/api/data/get"
params = {
"type": "RPTA_PCNEW_WHOLE",
"sty": "ALL",
"p": 1,
"ps": 50000,
"source": "SELECT_SECURITIES",
"client": "WEB"
}
r = requests.get(url, params=params)
data_json = r.json()
zxzb = data_json["zxzb"] # 指标
print(zxzb)
if __name__ == "__main__":
stock_selection_df = stock_selection()
print(stock_selection)

331
stockapp/src/crawling/trade_date_hist.py Normal file
View File

@ -0,0 +1,331 @@
#!/usr/bin/env python
# -*- coding:utf-8 -*-
"""
Date: 2022/10/1 19:27
Desc: 新浪财经-交易日历
https://finance.sina.com.cn/realstock/company/klc_td_sh.txt
此处可以用来更新 calendar.json 文件，注意末尾没有 "," 号
"""
import datetime
import pandas as pd
import requests
from py_mini_racer import py_mini_racer
hk_js_decode = """
function d(t) {
var e, i, n, r, a, o, s, l = (arguments,
864e5), u = 7657, c = [], h = [], d = ~(3 << 30), f = 1 << 30,
p = [0, 3, 5, 6, 9, 10, 12, 15, 17, 18, 20, 23, 24, 27, 29, 30], m = Math, g = function () {
var l, u;
for (l = 0; 64 > l; l++)
h[l] = m.pow(2, l),
26 > l && (c[l] = v(l + 65),
c[l + 26] = v(l + 97),
10 > l && (c[l + 52] = v(l + 48)));
for (c.push("+", "/"),
c = c.join(""),
i = t.split(""),
n = i.length,
l = 0; n > l; l++)
i[l] = c.indexOf(i[l]);
return r = {},
e = o = 0,
a = {},
u = w([12, 6]),
s = 63 ^ u[1],
{
_1479: T,
_136: _,
_200: S,
_139: k,
_197: _mi_run
}["_" + u[0]] || function () {
return []
}
}, v = String.fromCharCode, b = function (t) {
return t === {}._
}, N = function () {
var t, e;
for (t = y(),
e = 1; ;) {
if (!y())
return e * (2 * t - 1);
e++
}
}, y = function () {
var t;
return e >= n ? 0 : (t = i[e] & 1 << o,
o++,
o >= 6 && (o -= 6,
e++),
!!t)
}, w = function (t, r, a) {
var s, l, u, c, d;
for (l = [],
u = 0,
r || (r = []),
a || (a = []),
s = 0; s < t.length; s++)
if (c = t[s],
u = 0,
c) {
if (e >= n)
return l;
if (t[s] <= 0)
u = 0;
else if (t[s] <= 30) {
for (; d = 6 - o,
d = c > d ? d : c,
u |= (i[e] >> o & (1 << d) - 1) << t[s] - c,
o += d,
o >= 6 && (o -= 6,
e++),
c -= d,
!(0 >= c);)
;
r[s] && u >= h[t[s] - 1] && (u -= h[t[s]])
} else
u = w([30, t[s] - 30], [0, r[s]]),
a[s] || (u = u[0] + u[1] * h[30]);
l[s] = u
} else
l[s] = 0;
return l
}, x = function (t) {
var e, i, n;
for (t > 1 && (e = 0),
e = 0; t > e; e++)
r.d++,
n = r.d % 7,
(3 == n || 4 == n) && (r.d += 5 - n);
return i = new Date,
i.setTime((u + r.d) * l),
i
}, S = function () {
var t, i, a, o, l;
if (s >= 1)
return [];
for (r.d = w([18], [1])[0] - 1,
a = w([3, 3, 30, 6]),
r.p = a[0],
r.ld = a[1],
r.cd = a[2],
r.c = a[3],
r.m = m.pow(10, r.p),
r.pc = r.cd / r.m,
i = [],
t = 0; o = {
d: 1
},
y() && (a = w([3])[0],
0 == a ? o.d = w([6])[0] : 1 == a ? (r.d = w([18])[0],
o.d = 0) : o.d = a),
l = {
day: x(o.d)
},
y() && (r.ld += N()),
a = w([3 * r.ld], [1]),
r.cd += a[0],
l.close = r.cd / r.m,
i.push(l),
!(e >= n) && (e != n - 1 || 63 & (r.c ^ t + 1)); t++)
;
return i[0].prevclose = r.pc,
i
}, _ = function () {
var t, i, a, o, l, u, c, h, d, f, p;
if (s > 2)
return [];
for (c = [],
d = {
v: "volume",
p: "price",
a: "avg_price"
},
r.d = w([18], [1])[0] - 1,
h = {
day: x(1)
},
a = w(1 > s ? [3, 3, 4, 1, 1, 1, 5] : [4, 4, 4, 1, 1, 1, 3]),
t = 0; 7 > t; t++)
r[["la", "lp", "lv", "tv", "rv", "zv", "pp"][t]] = a[t];
for (r.m = m.pow(10, r.pp),
s >= 1 ? (a = w([3, 3]),
r.c = a[0],
a = a[1]) : (a = 5,
r.c = 2),
r.pc = w([6 * a])[0],
h.pc = r.pc / r.m,
r.cp = r.pc,
r.da = 0,
r.sa = r.sv = 0,
t = 0; !(e >= n) && (e != n - 1 || 7 & (r.c ^ t)); t++) {
for (l = {},
o = {},
f = r.tv ? y() : 1,
i = 0; 3 > i; i++)
if (p = ["v", "p", "a"][i],
(f ? y() : 0) && (a = N(),
r["l" + p] += a),
u = "v" == p && r.rv ? y() : 1,
a = w([3 * r["l" + p] + ("v" == p ? 7 * u : 0)], [!!i])[0] * (u ? 1 : 100),
o[p] = a,
"v" == p) {
if (!(l[d[p]] = a) && (s > 1 || 241 > t) && (r.zv ? !y() : 1)) {
o.p = 0;
break
}
} else
"a" == p && (r.da = (1 > s ? 0 : r.da) + o.a);
r.sv += o.v,
l[d.p] = (r.cp += o.p) / r.m,
r.sa += o.v * r.cp,
l[d.a] = b(o.a) ? t ? c[t - 1][d.a] : l[d.p] : r.sv ? ((m.floor((r.sa * (2e3 / r.m) + r.sv) / r.sv) >> 1) + r.da) / 1e3 : l[d.p] + r.da / 1e3,
c.push(l)
}
return c[0].date = h.day,
c[0].prevclose = h.pc,
c
}, T = function () {
var t, e, i, n, a, o, l;
if (s >= 1)
return [];
for (r.lv = 0,
r.ld = 0,
r.cd = 0,
r.cv = [0, 0],
r.p = w([6])[0],
r.d = w([18], [1])[0] - 1,
r.m = m.pow(10, r.p),
a = w([3, 3]),
r.md = a[0],
r.mv = a[1],
t = []; a = w([6]),
a.length;) {
if (i = {
c: a[0]
},
n = {},
i.d = 1,
32 & i.c)
for (; ;) {
if (a = w([6])[0],
63 == (16 | a)) {
l = 16 & a ? "x" : "u",
a = w([3, 3]),
i[l + "_d"] = a[0] + r.md,
i[l + "_v"] = a[1] + r.mv;
break
}
if (32 & a) {
o = 8 & a ? "d" : "v",
l = 16 & a ? "x" : "u",
i[l + "_" + o] = (7 & a) + r["m" + o];
break
}
if (o = 15 & a,
0 == o ? i.d = w([6])[0] : 1 == o ? (r.d = o = w([18])[0],
i.d = 0) : i.d = o,
!(16 & a))
break
}
n.date = x(i.d);
for (o in {
v: 0,
d: 0
})
b(i["x_" + o]) || (r["l" + o] = i["x_" + o]),
b(i["u_" + o]) && (i["u_" + o] = r["l" + o]);
for (i.l_l = [i.u_d, i.u_d, i.u_d, i.u_d, i.u_v],
l = p[15 & i.c],
1 & i.u_v && (l = 31 - l),
16 & i.c && (i.l_l[4] += 2),
e = 0; 5 > e; e++)
l & 1 << 4 - e && i.l_l[e]++,
i.l_l[e] *= 3;
i.d_v = w(i.l_l, [1, 0, 0, 1, 1], [0, 0, 0, 0, 1]),
o = r.cd + i.d_v[0],
n.open = o / r.m,
n.high = (o + i.d_v[1]) / r.m,
n.low = (o - i.d_v[2]) / r.m,
n.close = (o + i.d_v[3]) / r.m,
a = i.d_v[4],
"number" == typeof a && (a = [a, a >= 0 ? 0 : -1]),
r.cd = o + i.d_v[3],
l = r.cv[0] + a[0],
r.cv = [l & d, r.cv[1] + a[1] + !!((r.cv[0] & d) + (a[0] & d) & f)],
n.volume = (r.cv[0] & f - 1) + r.cv[1] * f,
t.push(n)
}
return t
}, k = function () {
var t, e, i, n;
if (s > 1)
return [];
for (r.l = 0,
n = -1,
r.d = w([18])[0] - 1,
i = w([18])[0]; r.d < i;)
e = x(1),
0 >= n ? (y() && (r.l += N()),
n = w([3 * r.l], [0])[0] + 1,
t || (t = [e],
n--)) : t.push(e),
n--;
return t
};
return _mi_run = function () {
var t, i, a, o;
if (s >= 1)
return [];
for (r.f = w([6])[0],
r.c = w([6])[0],
a = [],
r.dv = [],
r.dl = [],
t = 0; t < r.f; t++)
r.dv[t] = 0,
r.dl[t] = 0;
for (t = 0; !(e >= n) && (e != n - 1 || 7 & (r.c ^ t)); t++) {
for (o = [],
i = 0; i < r.f; i++)
y() && (r.dl[i] += N()),
r.dv[i] += w([3 * r.dl[i]], [1])[0],
o[i] = r.dv[i];
a.push(o)
}
return a
}
,
g()()
}
"""
def tool_trade_date_hist_sina() -> pd.DataFrame:
"""
交易日历-历史数据
https://finance.sina.com.cn/realstock/company/klc_td_sh.txt
:return: 交易日历
:rtype: pandas.DataFrame
"""
url = "https://finance.sina.com.cn/realstock/company/klc_td_sh.txt"
r = requests.get(url)
js_code = py_mini_racer.MiniRacer()
js_code.eval(hk_js_decode)
dict_list = js_code.call(
"d", r.text.split("=")[1].split(";")[0].replace('"', "")
) # 执行js解密代码
temp_df = pd.DataFrame(dict_list)
temp_df.columns = ["trade_date"]
temp_df["trade_date"] = pd.to_datetime(temp_df["trade_date"]).dt.date
temp_list = temp_df["trade_date"].to_list()
temp_list.append(datetime.date(1992, 5, 4)) # 是交易日但是交易日历缺失该日期
temp_list.sort()
temp_df = pd.DataFrame(temp_list, columns=["trade_date"])
return temp_df
if __name__ == "__main__":
tool_trade_date_hist_df = tool_trade_date_hist_sina()
print(tool_trade_date_hist_df)