def query_zz500_stocks(): rs = bs.query_zz500_stocks() while BaoStock.retried_num < BaoStock.RETRY_MAX_NUM and rs.error_code != '0': sleep(BaoStock.RETRY_DELAY_S) rs = bs.query_zz500_stocks() BaoStock.retried_num += 1 assert('0' == rs.error_code) BaoStock.retried_num = 0 return BaoStock.rs_to_list(rs)
def query_zz500_stocks(): rs = bs.query_zz500_stocks() while Stock.retried_num < Stock.RETRY_MAX_NUM and rs.error_code != '0': sleep(Stock.RETRY_DELAY_S) rs = bs.query_zz500_stocks() Stock.retried_num += 1 if '0' == rs.error_code: Stock.retried_num = 0 return Stock.rs_to_list(rs)
def getStockList(type: str = "default", date: str = ""): result = [] data: DataFrame if type == "sz50": data = BaoStock.query_sz50_stocks(date).get_data() elif type == "hs300": data = BaoStock.query_hs300_stocks(date).get_data() elif type == "zz500": data = BaoStock.query_zz500_stocks(date).get_data() elif type == "default": path = Path(__file__).parent.absolute()/"list.json" file = open(str(path), "r", encoding="utf8") return Json.loads(file.read()) else: data = BaoStock.query_stock_basic().get_data() keys = data.keys() data = [x[1] for x in BaoStock.query_stock_basic().get_data().iterrows()] if type == "index": data = [x for x in data if x["type"] == "2"] elif type == "stock": data = [x for x in data if x["type"] == "1"] for row in data: result.append({getStockListMap[key][0]: row[key] for key in keys if key in getStockListMap}) return result for row in data.iterrows(): result.append({getStockListMap[key][0]: row[1][key] for key in data.keys() if key in getStockListMap}) return result
def getList(self): stocks = [] # 获取中证500成分股 rs = bs.query_zz500_stocks() print('query_zz500 error_code:' + rs.error_code) print('query_zz500 error_msg:' + rs.error_msg) while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 stocks.append(rs.get_row_data()) # 获取中证500成分股 rs = bs.query_hs300_stocks() print('query_hs300 error_code:' + rs.error_code) print('query_hs300 error_msg:' + rs.error_msg) while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 stocks.append(rs.get_row_data()) result = pd.DataFrame(stocks, columns=rs.fields) # 结果集输出到csv文件 self.makeDIR('./data') result.to_csv('data/' + 'stockList.csv', index=False)
def get_history_companies(self) -> pd.DataFrame: """ Returns ------- pd.DataFrame: symbol date type SH600000 2019-11-11 add SH600000 2020-11-10 remove dtypes: symbol: str date: pd.Timestamp type: str, value from ["add", "remove"] """ bs.login() today = pd.datetime.now() date_range = pd.DataFrame( pd.date_range(start="2007-01-15", end=today, freq="7D"))[0].dt.date ret_list = [] col = ["date", "symbol", "code_name"] for date in tqdm(date_range, desc="Download CSI500"): rs = bs.query_zz500_stocks(date=str(date)) zz500_stocks = [] while (rs.error_code == "0") & rs.next(): zz500_stocks.append(rs.get_row_data()) result = pd.DataFrame(zz500_stocks, columns=col) result["symbol"] = result["symbol"].apply( lambda x: x.replace(".", "").upper()) result = self.get_data_from_baostock(date) ret_list.append(result[["date", "symbol"]]) bs.logout() return pd.concat(ret_list, sort=False)
def get_data_from_baostock(self, date) -> pd.DataFrame: """ Data source: http://baostock.com/baostock/index.php/%E4%B8%AD%E8%AF%81500%E6%88%90%E5%88%86%E8%82%A1 Avoid a large number of parallel data acquisition, such as 1000 times of concurrent data acquisition, because IP will be blocked Returns ------- pd.DataFrame: date symbol code_name SH600039 2007-01-15 四川路桥 SH600051 2020-01-15 宁波联合 dtypes: date: pd.Timestamp symbol: str code_name: str """ col = ["date", "symbol", "code_name"] rs = bs.query_zz500_stocks(date=str(date)) zz500_stocks = [] while (rs.error_code == "0") & rs.next(): zz500_stocks.append(rs.get_row_data()) result = pd.DataFrame(zz500_stocks, columns=col) result["symbol"] = result["symbol"].apply( lambda x: x.replace(".", "").upper()) return result
def get_zz500_stocks(): rs = BS.query_zz500_stocks() zz500_stocks = [] while (rs.error_code == '0') & rs.next(): zz500_stocks.append(rs.get_row_data()) result = PD.DataFrame(zz500_stocks, columns=rs.fields) print(result) return result
def queryZZ500Stocks(date): rs = bs.query_zz500_stocks(date=date) # 打印结果集 zz500_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 zz500_stocks.append(rs.get_row_data()) result = pd.DataFrame(zz500_stocks, columns=rs.fields) return result
def bao_zz500_stocks() -> pd.DataFrame: """ 获取沪深300成分股信息 :return: """ df = bao.query_zz500_stocks().get_data() df['code'] = df['code'].apply(lambda x: ts_code(x)) df.set_index(keys='code', drop=False, inplace=True) logging.info(colorama.Fore.YELLOW + '获取中证500成分股信息') return df
def get_constituent_stock(i): basepath = os.path.dirname(__file__) basicpath = 'static/morestock/' + i + '-stock' show_time = today_time() param = request.form show_code = "" if param and (param['code'] or param['code'] == ""): code = param['code'] show_code = stock_com(code) if show_code == "": # baostock相关设置 lg = bs.login() if i == "hs300": rs = bs.query_hs300_stocks() elif i == "sz": rs = bs.query_sz50_stocks() elif i == "zz": rs = bs.query_zz500_stocks() result = res_data(rs) # 创建个股文件夹 create_file(basicpath) # 存储csv、excel、josn文件 parsed = save_all(basicpath, i, show_time, result, 'data') # 从json获取数据(all) all_len = len(parsed) type_name = i + "Stock" show_obj = {"data": parsed, "total": all_len, "type": type_name} # baostock登出 bs.logout() return show_obj else: jsonpath = basicpath + '/json/' + i + '_' + show_time + '.json' joson_file = os.path.join(basepath, jsonpath) jsonFlag = "0" search_arr = [] with open(joson_file, 'r+', encoding="utf-8") as load_f: load_file = load_f.read() home_file = json.loads(load_file, strict=False) if show_code == "-1": search_arr = home_file['data'] elif show_code == "-2": search_arr = [] else: for item in home_file['data']: if item['code'] == show_code or item[ 'code_name'] == show_code: jsonFlag = "1" search_arr.append(item) all_len = len(search_arr) type_name = i + "Stock" show_obj = {"data": search_arr, "total": all_len, "type": type_name} return show_obj
def get_500_codes(self, date='2017-01-01'): # 获取中证500成分股 rs = bs.query_zz500_stocks(date) print('query_zz500 error_code:' + rs.error_code) print('query_zz500 error_msg:' + rs.error_msg) # 打印结果集 zz500_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 zz500_stocks.append(rs.get_row_data()) result = pd.DataFrame(zz500_stocks, columns=rs.fields) return result
def query_zz500_stocks(self, date = None): ''' date:查询日期,格式XXXX-XX-XX,为空时默认最新日期。 ''' rs = bs.query_zz500_stocks(date = date) self.log('query_zz500 error_msg:', rs) # 打印结果集 zz500_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 zz500_stocks.append(rs.get_row_data()) result = pd.DataFrame(zz500_stocks, columns=rs.fields) return result
def main(): # 沪深300 rs = bs.query_hs300_stocks() # 获取上证50成分股 rs1 = bs.query_sz50_stocks() # 获取中证500成分股 rs2 = bs.query_zz500_stocks() while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 re = Combine(rs.get_row_data()[1]) if re: datalist.append(re) result = pd.DataFrame(datalist) result.to_csv("/tmp/a.csv", index=False)
def bs_save_zz500_stocks(): ''' 获取中证500成分股信息 :return: ''' bs.login() rs = bs.query_zz500_stocks() data_list = [] while (rs.error_code == '0') & rs.next(): data_list.append(rs.get_row_data()) result = pd.DataFrame(data_list, columns=rs.fields) engine = create_engine( 'mysql+pymysql://root:root@localhost:3306/stock_quant?charset=utf8') result.to_sql('bs_zz500_stocks', engine, index=True) bs.logout()
def get_zz500_stocks(date=today): # 获取中证500成分股 rs = bs.query_zz500_stocks(date=date) if rs.error_code != '0': print('query_zz500 respond error_code::' + rs.error_msg) login() return get_zz500_stocks(date) # 打印结果集 zz500_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 zz500_stocks.append(rs.get_row_data()) result = pd.DataFrame(zz500_stocks, columns=rs.fields) # 结果集输出到csv文件 return result
def dispatch_request(self): post_data = request.get_json() date = post_data.get('date', '') attr_fields = post_data.get('attr_fields', None) rs = bs.query_zz500_stocks(date=date) zz500_stocks = [] while (rs.error_code == '0') & rs.next(): zz500_stocks.append(rs.get_row_data()) fields = ['updateDate', 'code', 'code_name'] data = jsonWrapper(zz500_stocks, fields) result = { 'code': 200 if rs.error_code == '0' else rs.error_code, 'data': list(map(lambda x: { attr: x.get(attr, '') for attr in attr_fields }, data)) if attr_fields else data, 'msg': rs.error_msg } self.logout() return jsonify(result)
def get_zz500_stocks(): lg = bs.login() # 显示登陆返回信息 print('login respond error_code:' + lg.error_code) print('login respond error_msg:' + lg.error_msg) #### 获取交易日信息 #### rs = bs.query_zz500_stocks() print('query_trade_dates respond error_code:' + rs.error_code) print('query_trade_dates respond error_msg:' + rs.error_msg) #### 打印结果集 #### data_list = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 data_list.append(rs.get_row_data()) result = pd.DataFrame(data_list, columns=rs.fields) bs.logout() return result
def zz500_index_component(self): file_path = './raw_data/zz500_stocks.csv' if os.path.exists(file_path): is_outdate = None else: is_outdate = True # 获取中证500成分股 rs = bs.query_zz500_stocks() print(f'zz500_index_component, error_code:{rs.error_code}') # 打印结果集 zz500_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 row = rs.get_row_data() if is_outdate is None: is_outdate = self.check_index_component_outdate( row[0], file_path) # is_outdate = True zz500_stocks.append(row) elif is_outdate == True: # 获取一条记录,将记录合并在一起 zz500_stocks.append(row) else: return result = pd.DataFrame(zz500_stocks, columns=rs.fields) result = result.set_index("code") # result = self.get_stock_industry_from_dongcai(result) for code in result.index.values.tolist(): stock_info = self.get_stock_detail(code) result.loc[code, 'url'] = stock_info['url'] result.loc[code, 'industry'] = stock_info['industry'] result.loc[code, 'pe_max'] = stock_info['pe_max'] result.loc[code, 'pe_mean'] = stock_info['pe_mean'] result.loc[code, 'pe_min'] = stock_info['pe_min'] # 结果集输出到csv文件 result.to_csv(file_path, encoding="gbk")
def get_zz500_stocks(): """ 获取中证500成分股 """ # 登陆系统 lg = bs.login() # 显示登陆返回信息 print('login respond error_code:' + lg.error_code) print('login respond error_msg:' + lg.error_msg) # 获取中证500成分股 rs = bs.query_zz500_stocks() print('query_zz500 error_code:' + rs.error_code) print('query_zz500 error_msg:' + rs.error_msg) # 打印结果集 zz500_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 zz500_stocks.append(rs.get_row_data()) result = pd.DataFrame(zz500_stocks, columns=rs.fields) dtype = { 'updateDate': String(10), 'code': String(9), 'code_name': String(10) } result.to_sql('odl_bs_zz500_stocks', engine, schema=CQ_Config.DB_SCHEMA, if_exists='replace', index=False, dtype=dtype) # 登出系统 bs.logout()
def query_zz500_stocks(date=None): """ 中证500成分股 方法说明:通过API接口获取中证500成分股信息,更新频率:每周一更新。 返回类型:pandas的DataFrame类型。 date:查询日期,格式XXXX-XX-XX,为空时默认最新日期。 """ lg = bs.login() if lg.error_code != '0': logger.error('login respond error_msg:' + lg.error_msg) rs = bs.query_zz500_stocks(date) if rs.error_code != '0': logger.error('query_zz500_stocks respond error_msg:' + rs.error_msg) zz500_stocks = [] while (rs.error_code == '0') & rs.next(): zz500_stocks.append(rs.get_row_data()) result = pd.DataFrame(zz500_stocks, columns=rs.fields) bs.logout() return result
def download_sample_stocks(sample_name='sz50'): if sample_name == 'sz50': filename = FILE_PATH + "sz50_stocks.csv" rs = bs.query_sz50_stocks() elif sample_name == 'hs300': filename = FILE_PATH + "hs300_stocks.csv" rs = bs.query_hs300_stocks() elif sample_name == 'zz500': filename = FILE_PATH + "zz500_stocks.csv" rs = bs.query_zz500_stocks() elif sample_name == 'all': filename = FILE_PATH + "all_stocks.csv" # 取前七天的成分股信息,如果取当前天的,可能当天没有更新 trade_cal = get_trade_cal() trade_day = trade_cal[( trade_cal['is_trading_day'] == 1)]['calendar_date'].values rs = bs.query_all_stock() stocks = [] while (rs.error_code == '0') & rs.next(): stocks.append(rs.get_row_data()) result = pd.DataFrame(stocks, columns=rs.fields) result.to_csv(filename, encoding="gbk", index=False) logger.debug("将成分股%s保存至%s" % (sample_name, filename))
def get_hs300_zz500_data(): # 获取沪深300和中证500成分股 rs_hs300 = bs.query_hs300_stocks("2020-07-30") rs_zz500 = bs.query_zz500_stocks("2020-07-30") print('query_hs300 error_code:' + rs_hs300.error_code) print('query_hs300 error_msg:' + rs_hs300.error_msg) print('query_zz500 error_code:' + rs_zz500.error_code) print('query_zz500 error_msg:' + rs_zz500.error_msg) # 打印结果集 hs300_stocks = [] zz500_stocks = [] while (rs_hs300.error_code == '0') & rs_hs300.next(): # 获取一条记录,将记录合并在一起 hs300_stocks.append(rs_hs300.get_row_data()) while (rs_zz500.error_code == '0') & rs_zz500.next(): # 获取一条记录,将记录合并在一起 zz500_stocks.append(rs_zz500.get_row_data()) stocks_result = pd.DataFrame(hs300_stocks + zz500_stocks, columns=rs_hs300.fields) # stocks_result.to_csv("./stocks-pool/hs300_zz500_stocks.csv", encoding="gbk", index=False) return stocks_result
import baostock as bs import pandas as pd #### 登陆系统 #### lg = bs.login() # 显示登陆返回信息 print('login respond error_code:' + lg.error_code) print('login respond error_msg:' + lg.error_msg) #### 获取沪深A股历史K线数据 #### # 详细指标参数,参见“历史行情指标参数”章节;“分钟线”参数与“日线”参数不同。 # 分钟线指标:date,time,code,open,high,low,close,volume,amount,adjustflag rs = bs.query_zz500_stocks() print('query_sz50 error_code:' + rs.error_code) print('query_sz50 error_msg:' + rs.error_msg) # 打印结果集 sz50_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 sz50_stocks.append(rs.get_row_data()) list_50 = [] for i in range(len(sz50_stocks)): list_50.append(sz50_stocks[i][1]) for i in list_50: rs = bs.query_history_k_data_plus( i, "date,time,code,open,high,low,close,volume,amount,adjustflag", start_date='2015-01-01',
import baostock as bs import pandas as pd import datetime startdate = (datetime.datetime.now()-datetime.timedelta(days=50)).strftime("%Y-%m-%d") enddate = datetime.datetime.now().strftime("%Y-%m-%d") # baostock login lg = bs.login() # print login error msg if lg.error_code != '0': print('login respond error_code:'+lg.error_code) print('login respond error_msg:'+lg.error_msg) zz500_data = bs.query_zz500_stocks() # 打印结果集 zz500_stocks = [] while (zz500_data.error_code == '0') & zz500_data.next(): # 获取一条记录,将记录合并在一起 row_data = zz500_data.get_row_data() code = row_data[1] # query history k data rs = bs.query_history_k_data_plus(code, "date,code,close,tradeStatus,open,volume", start_date=startdate, end_date=enddate, frequency="d", adjustflag="3") # handle k data result_list = [] while (rs.error_code == '0') & rs.next():
def getA50StockList(self): try: self.initMysqlConn() # 查询当前所有正常上市交易的股票列表 df = ts.get_sz50s() # 不能用了?返回值是none # 登陆系统 lg = bs.login() rs = bs.query_sz50_stocks() # 打印结果集 sz50_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 sz50_stocks.append(rs.get_row_data()) result = pd.DataFrame(sz50_stocks, columns=rs.fields) # result['code']='\t'+result['code'].str[3:] # ex=os.path.isfile('sz50s') # if ex==False: result.to_csv('G:\\stockData\\sz50s.csv', encoding='utf_8_sig') #指数直接覆盖掉 rs = bs.query_hs300_stocks() # 打印结果集 hs300_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 hs300_stocks.append(rs.get_row_data()) result1 = pd.DataFrame(hs300_stocks, columns=rs.fields) # result1['code']=result1['code'].str[3:] # ex=os.path.isfile('sz50s') # if ex==False: result1.to_csv('G:\\stockData\\hs300s.csv', encoding='utf_8_sig') #指数直接覆盖掉 # result1.to_csv('G:\\stockData\\hs300s.csv',encoding='gbk')#指数直接覆盖掉 rs = bs.query_zz500_stocks() # 打印结果集 zz500_stocks = [] while (rs.error_code == '0') & rs.next(): # 获取一条记录,将记录合并在一起 zz500_stocks.append(rs.get_row_data()) result2 = pd.DataFrame(zz500_stocks, columns=rs.fields) # result2['code']=result2['code'].str[3:]#没有t的话会丢掉前面的0 # ex=os.path.isfile('sz50s') # if ex==False: result2.to_csv('G:\\stockData\\zz500s.csv', encoding='utf_8_sig') #指数直接覆盖掉 # 登出系统 bs.logout() print('getsz50StockList & hs300s & zz500s Finished!') return c_len = 0 if (df == None): df = result c_len = df.shape[0] # 行数 except Exception as aa: print(aa) print('get error') for j in range(c_len): # 按行读取股票列表 resu0 = list(df.loc[c_len - 1 - j]) resu = [] for k in range(len(resu0)): # 读取股票的字段 if str(resu0[k]) == 'nan': resu.append(-1) else: resu.append(resu0[k]) try: sql_insert = "INSERT INTO sz50StockList(date,code,name) VALUES ('%s', '%s', '%s')" % ( str(resu[0]), str(resu[1]), str(resu[2])) self.cursor.execute(sql_insert) self.db.commit() except Exception as err: continue self.cursor.close() self.db.close() # 登出系统 bs.logout() print('getsz50StockList Finished!')
def zz500(self): '''中证500''' return get_data(bs.query_zz500_stocks())
def zz500_stocks(self): self.getStockInstance() rs = bs.query_zz500_stocks() self._test_rs(rs) return rs