ADD file via upload

"https:/top.chinaz.com/gongsi/index_zhuce.html"

@@ -0,0 +1 @@
+#### 代码窗口

#1.数据爬取
import requests
import re
import csv
#构建地址
url = "https://top.chinaz.com/gongsi/index_zhuce.html"
# 设置请求头信息

# 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/108.0.0.0 Safari/537.36 Edg/108.0.1462.42"
}

# 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



# 存储内容
message = []
# 总共903个页面的数据
for page in range(903):
    # 组装url
    if page == 0:
        url = "https://top.chinaz.com/gongsi/index_zhuce.html"
    else:
        url = "https://top.chinaz.com/gongsi/index_zhuce_{}.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
    # 找公司名
    company = re.findall('target="_blank">(.*?)</a></h3>\r\n', html)
    # 找注册资金
    money = re.findall('<div class="CoDate"><em>(.*?)</em>注册资本</div>', html)
    pageOne = list(zip(company,money))
    # 合并列表
    message.extend(pageOne)
   
#保存文件
with open("contents.csv", "w") as f:
    w = csv.writer(f)
    w.writerows(message)
!cat contents.csv
    
#绘图
import matplotlib.pyplot as plt
import pandas as pd    
%matplotlib inline
# 读取数据
df = pd.read_csv("contents.csv", names=["company", "money"],encoding='utf-8')
# 用黑体显示中文
plt.rcParams['font.sans-serif'] = ['SimHei']  

#获取所需数据
j=df.values[0:20]
companys=[i for i,k in j]    
moneyss=[k for i,k in j]    
moneys=[float(k[:-1]) for i,k in j]  

#设置柱状图长宽
plt.figure(figsize=(20,10))

#画柱状图
plt.bar(companys,moneys)
#标签
plt.xticks(range(len(companys)),companys,rotation=90) 
#标注资金
for x,y in zip(range(len(moneys)),moneys):
    plt.text(x,y,y,ha='center',va='bottom')
#x,y轴标注和图标题
plt.title("注册资金最多的公司 top20")
plt.xlabel("公司")
plt.ylabel("注册资金（亿元）")
plt.show