# -*- coding: utf-8 -*-
"""
Created on Thu Jun  6 15:40:29 2024

@author: Asus
"""

import requests
import re
company_name_list=[]
company_money_list=[]
for i in range(10):
    # 请求的url
    if i==0:
        url = "https://top.chinaz.com/gongsi/index_zhuce.html"
    else:
        url = "https://top.chinaz.com/gongsi/index_zhuce"+"_"+str(i)+".html"
    # 设置请求头信息
    headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36"
    }
    # 使用reqeusts模快发起 GET 请求
    response = requests.get(url, headers=headers)
    # 获取请求的返回结果
    html = response.text

# 使用 findall 函数来获取数据
    company_name = re.findall('<h3 class=""><a href=(.+?) target="_blank">(.+?)</a></h3>', html)
    company_name = [tuple_item[1] for tuple_item in company_name]  
    company_name_list.append(company_name)
    company_money=re.findall('<div class="CoDate"><em>(.+?)</em>注册资本</div>', html)
    company_money_list.append(company_money)

company_name_list = [item for sublist in company_name_list for item in sublist]
company_money_list = [item for sublist in company_money_list for item in sublist]


print(company_name_list)
print(company_money_list)
import matplotlib.pyplot as plt  
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签  
# 使用zip组合列表，并按注册资金排序  
combined = list(zip(company_name_list,company_money_list)) 
                
# 提取前20个 

top_20=combined[:20]   
# 解包公司名称和注册资金  
top_20_companies, top_20_capital = zip(*top_20) 
a=[]
for i in top_20_capital:
    # 提取数字部分
    number = i[:-1]
    # 提取单位部分
    unit = i[-1]
    if unit=='亿':
        b=number *100
        a.append(eval(number))
# 绘制条形图  
plt.figure(figsize=(10, 6))  
plt.bar(top_20_companies, a)  
plt.title("Top 20 Companies by Registered Capital")  
plt.xlabel("Company Name")  
plt.ylabel("Registered Capital (a hundred million)")  
plt.xticks(rotation=90) 
plt.show()