一 功能介绍

功能：获取基金历史净值数据

数据来源：

https://fundf10.eastmoney.com/F10DataApi.aspx?type=lsjz&code={}&page=1&sdate=19950101&edate={}&per=40

编程语言：Python

数据处理工具：Pandas

输出结果文件格式：CSV

二 关键代码

2.1 数据来源截图

 2.2 关键代码

import requests
import pandas as pd
import time
import datetime
import re
from lxml import etree

#基金
def download_fund_history_data(fund_code):
    url = "https://fundf10.eastmoney.com/F10DataApi.aspx?type=lsjz&code={}&page=1&sdate=19950101&edate={}&per=40".format(fund_code,
                                       datetime.datetime.strftime(datetime.datetime.now(), "%Y%m%d"))
    print(url)
    response = requests.get(url)
    print(response.text)
    pages = re.findall('pages:(.*),', response.text)
    int_pages = 0
    if len(pages)>0:
        int_pages = int(pages[0])
    print("总共{}页".format(int_pages))
    td_all = []
    for i in range(int_pages):
        url = "https://fundf10.eastmoney.com/F10DataApi.aspx?type=lsjz&code={}&page={}&sdate=19950101&edate={}&per=40".format(fund_code,
            i+1,
            datetime.datetime.strftime(datetime.datetime.now(), "%Y%m%d"))
        print(url)
        response = requests.get(url)
        print(response.text)
        tables = re.findall('"(.*)"', response.text)
        if len(tables)>0:
            table = tables[0]
            print(table)
            tree = etree.HTML(table)
            td_list = tree.xpath('//tr/td')
            #print(td_list)
            for t in td_list:
                #print(t.text)
                if t.text == None:
                    td_all = td_all + [""]
                else:
                    td_all.append(t.text)
    #print(td_all)
    columns = {
        "date": "净值日期", "a": "单位净值", "b": "累计净值", "c": "日增长率", "d": "申购状态", "e": "赎回状态"
    }
    net_date = []
    net_a = []
    net_b = []
    net_c = []
    net_d = []
    net_e = []
    for k,v in enumerate(td_all):
        i = k%7
        if i == 0:
            net_date.append(v)
        if i == 1:
            net_a.append(v)
        if i == 2:
            net_b.append(v)
        if i == 3:
            net_c.append(v)
        if i == 4:
            net_d.append(v)
        if i == 5:
            net_e.append(v)

    df = pd.DataFrame({'净值日期':net_date,
                       '单位净值':net_a,
                       '累计净值':net_b,
                       '日增长率':net_c,
                       '申购状态':net_d,
                       '赎回状态':net_e})
    df.to_csv("基金{}历史数据.csv".format(fund_code), index=False, encoding="utf-8")



if __name__ == '__main__':
    #510300沪深300ETF
    download_fund_history_data("510300")

2.3 输出结果 

资料参考

https://blog.csdn.net/lildkdkdkjf/article/details/128846897