import requests
url="https://top.chinaz.com/gongsi/index_HuNan_zhuce.html"
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"
}
response=requests.get(url, headers=headers)
html=response.text

import re
company=re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
person=re.findall('法定代表人：</span>(.+?)</p>', html)
signDate=re.findall('注册时间：</span>(.+?)</p>', html)
category=re.findall('证券类别：</span>(.+?)</p>', html)
pageOne=list(zip(company, person, signDate, category))
message=[]

for page in range(16):
    if page==0:
        url="https://top.chinaz.com/gongsi/index_HuNan_zhuce.html"
    else:
        url="https://top.chinaz.com/gongsi/index_HuNan_zhuce_{}.html".format(page + 1)
    response=requests.get(url, headers=headers)
    html=response.text
    message.extend(pageOne)


import csv
with open("content.csv", "w") as f:
    w=csv.writer(f)
    w.writerows(message)

import pandas as pd
df=pd.read_csv("content.csv", names=["company", "person", "signDate", "category"],encoding='cp936')
df.head()
df1=df.groupby("category").count()["company"]

import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif']=['SimHei']  
names=df1.index
values=df1.values
fig1,ax1=plt.subplots()
ax1.pie(values, labels=names, autopct='%3.1f%%',explode=(0.11,0.2),textprops={'fontsize':18,'color':'k'},radius=2,
        shadow=True, startangle=180,colors=('c','y'))
ax1.set_title('湖南企业五百强')
ax1.axis('equal')
plt.show()