爬取基金收盘价并用pyecharts进行展现

一、用到的第三方包

因为使用到了一些第三方的包，包还是比较大的如果直接从社区下载比较费劲，所以建议配置国内镜像源，这里以清华的镜像源为例。

pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
pip config set global.trusted_host pypi.tuna.tsinghua.edu.cn

安装第三方包

pip install pandas bs4 pyecharts

二、数据获取

从网页爬取数据

import requests
from bs4 import BeautifulSoup
# 从url获取信息
response = requests.get('url地址')
# 解析HTML内容
soup = BeautifulSoup(response.text, 'html.parser')
soup.get_text()

1、从网页爬取每日最新数据

2、将数据追加存储到excel

# !/usr/bin/python
# -*-coding:utf-8 -*-
"""
 File        : spider.py
 Time        : 2024/1/17 10:00
 Author      : 天选之子
 Email       : 
 version     : python 3.10.11
 Description : 
"""
import datetime
import os

import numpy
import requests
from bs4 import BeautifulSoup
import pandas

url = "https://qt.gtimg.cn"
fund_code_list = ['sh510300', 'sz159995']
target_path = r'excel存储位置'
sheet_name = '存储的excel的sheet页'


def get_fund_close_price(url_str):
    """
    获取基金收盘价
    """
    response = requests.get(url_str)
    soup = BeautifulSoup(response.text, 'html.parser')
    if soup is None:
        return '没找到'
    else:
        market = soup.get_text()
    return market.split('~')[4]


def df_combiner(targetpath, dataframe, sheetname):
    """
    将来源excel合并到目标excel
    :param targetpath:
    :param dataframe:
    :param sheetname:
    :return: dataframe合并后的最终excel对象
    """
    if not os.path.exists(targetpath):
        return None
    tar_data_frame = pandas.DataFrame(pandas.read_excel(targetpath, sheet_name=sheetname, keep_default_na=False))
    tar_date = set(numpy.array(tar_data_frame['日期']).tolist())
    to_date = set(numpy.array(dataframe['日期']).tolist())
    if to_date.issubset(tar_date):
        tar_df_all = tar_data_frame
    else:
        if tar_data_frame is None:
            return dataframe
        tar_df_all = pandas.concat([tar_data_frame, dataframe], ignore_index=True)
    return tar_df_all


def main():
    df_all = None
    for fund_code in fund_code_list:
        fund_url = f'{url}/?q={fund_code}'
        result = get_fund_close_price(fund_url)
        print("该只基金的收盘价为：", result)
        print(datetime.datetime.now().strftime('%Y-%m-%d'))
        # 创建一个DataFrame
        data = {'日期': [datetime.datetime.now().strftime('%Y%m%d')], '基金代码': [fund_code], '收盘价': [result]}
        df = pandas.DataFrame(data)
        df_all = pandas.concat([df_all, df], ignore_index=True)

    target_df = df_combiner(target_path, df_all, sheet_name)
    excel_writer = pandas.ExcelWriter(target_path)
    target_df.to_excel(excel_writer, index=False, sheet_name='基金收盘价')
    excel_writer.close()


if __name__ == '__main__':
    main()

三、展示

将获取的excel数据展示成折线图，这里使用的是pyecharts，不多废话直接上代码

# https://pyecharts.org/#/zh-cn/quickstart
import numpy
import pandas
from pyecharts import options as opts
from pyecharts.charts import Line

target_path = r'excel位置'
sheet_name = '基金收盘价'
fund_code_list = ['sh510300', 'sz159995']
tar_data_frame = pandas.DataFrame(pandas.read_excel(target_path, sheet_name=sheet_name, keep_default_na=False))
data_date = list(set(numpy.array(tar_data_frame['日期']).tolist()))
sh510300_date = numpy.array(tar_data_frame.loc[tar_data_frame['基金代码'] == 'sh510300']['收盘价']).tolist()
sz159995_date = numpy.array(tar_data_frame.loc[tar_data_frame['基金代码'] == 'sz159995']['收盘价']).tolist()

# 创建柱状图
bar_chart = Line()
bar_chart.add_xaxis(data_date)
title_opts = opts.TitleOpts(title="月度销售额折线图"),
bar_chart.add_yaxis(series_name='sh510300'
                    , linestyle_opts=opts.LineStyleOpts(color="red", width=2, is_show=True)
                    , itemstyle_opts=opts.ItemStyleOpts(color="red", border_width=1)
                    , is_smooth=True
                    , y_axis=sh510300_date)
bar_chart.add_yaxis(series_name='sz159995_date'
                    , linestyle_opts=opts.LineStyleOpts(color="yellow", width=2, is_show=True)
                    , itemstyle_opts=opts.ItemStyleOpts(color="yellow", border_width=1)
                    , is_smooth=True
                    , y_axis=sz159995_date)
bar_chart.set_global_opts(title_opts=opts.TitleOpts(title="基金收盘价格走势", is_show=True, pos_left='center')
                          , xaxis_opts=opts.AxisOpts(name="月份")
                          , yaxis_opts=opts.AxisOpts(name="收盘价（元）", min_=0, max_=10)
                          , legend_opts=opts.LegendOpts(pos_left='right'))

# 渲染图表到 HTML 文件
bar_chart.render("基金收盘价.html")

展示结果如下：