|
|
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
|
|
|
message = []
|
|
|
# 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)
|
|
|
# 注册资本
|
|
|
signfunds = re.findall('注册资本：</span>(.+?)</p>', html)
|
|
|
pageOne = list(zip(company,signfunds))
|
|
|
# 合并列表
|
|
|
message.extend(pageOne)
|
|
|
import csv
|
|
|
with open("content.csv", "w") as f:
|
|
|
w = csv.writer(f)
|
|
|
w.writerows(message)
|
|
|
import pandas as pd
|
|
|
# 读取数据
|
|
|
df = pd.read_csv("content.csv", names=["company","signfunds"])
|
|
|
y_funds = df.loc[df['signfunds'].str.contains('亿')]
|
|
|
y_funds['signfunds'] = y_funds['signfunds'].str.replace('亿元', '')
|
|
|
y_funds['signfunds'] = y_funds['signfunds'].astype(float)
|
|
|
y_funds_sorted = y_funds.sort_values(by=['signfunds'],ascending=False)
|
|
|
import matplotlib.pyplot as plt
|
|
|
%matplotlib inline
|
|
|
# 绘制横向条形图
|
|
|
funds_top_20 = y_funds_sorted.head(20)
|
|
|
plt.rcParams['font.sans-serif'] = ['SimHei']
|
|
|
plt.rcParams['axes.unicode_minus'] = False
|
|
|
plt.barh(funds_top_20['company'], funds_top_20['signfunds'])
|
|
|
plt.xlabel('注册资金（亿元）') # 添加x轴标签
|
|
|
plt.ylabel('公司') # 添加y轴标签
|
|
|
plt.title('注册资金最多的公司 top20 ') # 添加标题
|
|
|
plt.gca().invert_yaxis() # 反转y轴，使得最高条形在顶部
|
|
|
plt.show()
|
