You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
39 lines
1.2 KiB
39 lines
1.2 KiB
import requests
|
|
import pandas as pd
|
|
import matplotlib.pyplot as plt
|
|
import re
|
|
plt.rcParams['font.sans-serif'] = ["SimHei"]
|
|
def crawl_data():
|
|
|
|
response = requests.get("https://top.chinaz.com/gongsitop/index_500top.html")
|
|
data = response.text
|
|
company_names = re.findall('<a.*?target="_blank">(.+?)</a></h3>', data)
|
|
legal_representatives = re.findall('法定代表人：</span>(.+?)</p>',data)
|
|
registration_times = re.findall('注册时间：</span>(.+?)</p>', data)
|
|
securities = re.findall('证券类别：</span>(.+?)</p>', data)
|
|
|
|
df = pd.DataFrame({
|
|
"公司名": company_names,
|
|
"法定代表人": legal_representatives,
|
|
"注册时间": registration_times,
|
|
"证券类别": securities
|
|
})
|
|
|
|
df.to_csv("500qiang.csv", index=False)
|
|
|
|
def analyze_data():
|
|
df = pd.read_csv("500qiang.csv")
|
|
securities_counts = df["证券类别"].value_counts()
|
|
total = len(df)
|
|
proportions = securities_counts / total
|
|
|
|
labels = securities_counts.index
|
|
sizes = proportions * 100
|
|
|
|
plt.pie(sizes, labels=labels, autopct='%1.1f%%')
|
|
plt.axis('equal')
|
|
plt.title("500 强公司证券占比")
|
|
plt.show()
|
|
|
|
crawl_data()
|
|
analyze_data() |