Python爬取股票交易数据并可视化展示

时间：2022-08-18 11:57:46|栏目：Python代码|点击：次

开发环境

解释器版本: python 3.8

代码编辑器: pycharm 2021.2

第三方模块

requests: pip install requests

csv

爬虫案例的步骤

1.确定url地址(链接地址)

2.发送网络请求

3.数据解析(筛选数据)

4.数据的保存(数据库(mysql\mongodb\redis), 本地文件)

爬虫程序全部代码

分析网页

打开开发者工具，搜索关键字，找到正确url

导入模块

import requests     # 发送网络请求
import csv

请求数据

url = f'https://xueqiu.com/service/v5/stock/screener/quote/list?page=1&size=30&order=desc&order_by=amount&exchange=CN&market=CN&type=sha&_=1637908787379'
# 伪装
headers = {
    # 浏览器伪装
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36'
}
response = requests.get(url, headers=headers)
json_data = response.json()

解析数据

data_list = json_data['data']['list']
for data in data_list:
    data1 = data['symbol']
    data2 = data['name']
    data3 = data['current']
    data4 = data['chg']
    data5 = data['percent']
    data6 = data['current_year_percent']
    data7 = data['volume']
    data8 = data['amount']
    data9 = data['turnover_rate']
    data10 = data['pe_ttm']
    data11 = data['dividend_yield']
    data12 = data['market_capital']
    print(data1, data2, data3, data4, data5, data6, data7, data8, data9, data10, data11, data12)
    data_dict = {
        '股票代码': data1,
        '股票名称': data2,
        '当前价': data3,
        '涨跌额': data4,
        '涨跌幅': data5,
        '年初至今': data6,
        '成交量': data7,
        '成交额': data8,
        '换手率': data9,
        '市盈率(TTM)': data10,
        '股息率': data11,
        '市值': data12,
    }
    csv_write.writerow(data_dict)

翻页

对比1、2、3页数据url，找到规律

for page in range(1, 56):
    url = f'https://xueqiu.com/service/v5/stock/screener/quote/list?page={page}&size=30&order=desc&order_by=amount&exchange=CN&market=CN&type=sha&_=1637908787379'

保存数据

file = open('data2.csv', mode='a', encoding='utf-8', newline='')
csv_write = csv.DictWriter(file, fieldnames=['股票代码','股票名称','当前价','涨跌额','涨跌幅','年初至今','成交量','成交额','换手率','市盈率(TTM)','股息率','市值'])
csv_write.writeheader()
file.close()

实现效果

数据可视化全部代码

导入数据

import pandas as pd
from pyecharts import options as opts
from pyecharts.charts import Bar

读取数据

data_df = pd.read_csv('data2.csv')
df = data_df.dropna()
df1 = df[['股票名称', '成交量']]
df2 = df1.iloc[:20]
print(df2['股票名称'].values)
print(df2['成交量'].values)

可视化图表

c = (
    Bar()
        .add_xaxis(list(df2['股票名称']))
        .add_yaxis("股票成交量情况", list(df2['成交量']))
        .set_global_opts(
        title_opts=opts.TitleOpts(title="成交量图表 - Volume chart"),
        datazoom_opts=opts.DataZoomOpts(),
    )
        .render("data.html")
)

print('数据可视化结果完成,请在当前目录下查找打开 data.html 文件!')