#pachong
import requests
# 请求的url
url = "https://top.chinaz.com/gongsitop/index_500top.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
import re
# 使用 findall 函数来获取数据
# 公司名
company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
# 法定代表人
person = re.findall('法定代表人：</span>(.+?)</p>', html)
# 注册时间
signDate = re.findall('注册时间：</span>(.+?)</p>', html)
# 证券类别
category = re.findall('证券类别：</span>(.+?)</p>', html)
pageOne = list(zip(company, person, signDate, category))
message = []
message2=[]
# 总共16个页面的数据
for page in range(16):
    # 组装url
    if page == 0:
        url = "https://top.chinaz.com/gongsitop/index_500top.html"
    else:
        url = "https://top.chinaz.com/gongsitop/index_500top_{}.html".format(page + 1)
    # 使用reqeusts模快发起 GET 请求
    response = requests.get(url, headers=headers)
    html = response.text
    # 使用 findall 函数来获取数据
    # 公司名
    company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
    # 法定代表人
    person = re.findall('法定代表人：</span>(.*?)</p>', html)
    # 注册时间
    signDate = re.findall('注册时间：</span>(.*?)</p>', html)
    # 证券类别
    category = re.findall('证券类别：</span>(.*?)</p>', html)
    pageOne = list(zip(company, person, signDate, category))
    money = re.findall('注册资本：</span(.*?)</p>',html)
    pageTwo=list(zip(company,money))
    # 合并列表
    message.extend(pageOne)
    message2.extend(pageTwo)
import csv
with open("content.csv", "w",encoding='utf-8') as f:
    w = csv.writer(f)
    w.writerows(message)
with open("content2.csv", "w",encoding='utf-8') as f:
    w = csv.writer(f)
    w.writerows(message2)
import pandas as pd
import chardet
with open('content.csv','rb') as f:
    rawdata=f.read()
    result=chardet.detect(rawdata)
    print(result['encoding'])
    encoding=result['encoding']
# 读取数据
df = pd.read_csv("content.csv", names=["company", "person", "signDate", "category"], encoding=encoding)
df.head()
df.info()
df1 = df.groupby("category").count()["company"]
import pandas as pd
import chardet
with open('content2.csv','rb') as f:
    rawdata2=f.read()
    result2=chardet.detect(rawdata)
    print(result2['encoding'])
    encoding=result2['encoding']
# 读取数据2
df = pd.read_csv("content2.csv", names=["company",'money'], encoding=encoding)
df.head()
df.info()
sorted_data=df.sort_values(by='money',ascending=False)
top_20=sorted_data.head(20)
df2 = top_20.groupby("money").count()["company"]
import matplotlib.pyplot as plt

# 用黑体显示中文
plt.rcParams['font.sans-serif'] = ['SimHei']  

labels=df2.index
sizes=df2.values
fig1,ax2=plt.subplots()
ax2.pie(sizes,labels=labels,autopct='%d%%',radius=2,textprops={'fontsize': 20},
        shadow=False, startangle=90)
ax2.axis()
plt.title("top20")
plt.show()