python爬取股票数据并存到数据库

Posted 2021-09-15 Gendan

-- coding: utf-8 --

"""此处为用于爬取和存储到数据库的Tushare.py"""
import tushare as t1
import time # 用以计时
from config import * # 此库为配置库
from SQLserver import * # 此库为作者所写
class Fetch_Data():

"""code股票代码 sd开始日期 ed结束日期"""
def __init__(self, code, start_data, end_data):
    self.code = code
    self.sd = start_data
    self.ed = end_data
    # self.csv_name = "csv_data/" + csv_name + ".csv"
def web_spider(self):  # 爬虫tushare接口
    try:
        df = ts.daily(ts_code=self.code, start_date=self.sd, end_date=self.ed)  # 爬取数据--dataframe格式
        # daily方法所获取的数据ts_code,trade_date,open,high,low,close,pre_close,change,pct_chg,vol,amount,avgprice
        # df.to_csv(self.csv_name) # 转换为csv文件
        return df  # 返回数据
    except Exception as e:
        print(e) # 打印报错信息

class Sql_Data_Handle():

def __init__(self, df, connect, curs):
    self.df = df
    self.connect = connect
    self.curs = curs
def character(self):
    # df = pandas.read_csv(self.csv_name, encoding=\'gbk\') # 用pandas库读取csv文件
    line_num = self.line_num
    # pandas的iloc函数读取每行对应数据
    ts_code = self.df.iloc[line_num]["ts_code"]
    trade_date = self.df.iloc[line_num]["trade_date"]
    open = self.df.iloc[line_num]["open"]
    high = self.df.iloc[line_num]["high"]
    low = self.df.iloc[line_num]["low"]
    close = self.df.iloc[line_num]["close"]
    pre_close = self.df.iloc[line_num]["pre_close"]
    change = self.df.iloc[line_num]["change"]
    pct_chg = self.df.iloc[line_num]["pct_chg"]
    vol = self.df.iloc[line_num]["vol"]
    amount = self.df.iloc[line_num]["amount"]
    # 将数据转换为元祖tuple格式
    values = (
        ts_code, trade_date, float(open), float(high), float(low), float(close), float(pre_close),
        float(change), float(pct_chg), float(vol), float(amount))
    return values
def add_data(self):
    self.line_num = len(self.df) - 1
    # 循环调用character()函数-读取每行数据
    while self.line_num >= 0:
        value_list = self.character()
        try:
            # 插入数据库
            Sql.Sql_execution(
                f"""insert into stock ({tushare["Column"]}) values """ + f"(\\\'{value_list[0]}\\\',\\\'{value_list[1]}\\\',\\\'{value_list[2]}\\\',\\\'{value_list[3]}\\\',\\\'{value_list[4]}\\\',\\\'{value_list[5]}\\\',\\\'{value_list[6]}\\\',\\\'{value_list[7]}\\\',\\\'{value_list[8]}\\\',\\\'{value_list[9]}\\\',\\\'{value_list[10]}\\\')")
        except Exception:
            # 出错信息
            print(f"{value_list[0]}-{value_list[1]}未被添加！")
        self.line_num -= 1
        i += 1
    print(f"The data has been added to the stock database")
    return i

if name == \'__main__\':

count = 0
line_count = len(Stock_list)
print("连接数据库")
Sql = DataServer_Sqlite3("stock")  # 连接数据库
stock_code = Stock_list
# Sql.Empty_database()  # 清空数据库
# print("清空数据库")
# Sql.Zero_Id()  # 将ID归零
# print("将ID归零")

for key in stock_code:

try:
    column = tushare["column"] # config中的tushare字典
    t1.set_token(tushare["token"])  # token值
    ts = t1.pro_api()  # 初始化pro接口
    print("初始化pro接口成功")
    input_code = stock_code[key]
    sd, ed = "20181231", "20201231"  # 起始日期，结束日期
    print(f"抓取{key}[货币代码](https://www.gendan5.com/currencycode.html)股票数据")
    start = time.perf_counter()  # 开始时间
    df = Fetch_Data(input_code, sd, ed).web_spider()  # dataframe格式股票数据
    line_num = Sql_Data_Handle(df, Sql.connection, Sql.curs).add_data()
    end = time.perf_counter()  # 结束时间
    # 记录用时
    print(f"添加{key}股票数据到数据库--成功,用时{start - end}")
    # 记录添加的数据条数
    print(f"{key} 共{line_num}条数据已添加到数据库！")
except Exception as e:
    print e
count += 1
print(f"还剩{line_count - count}支股票...")