From f4a2ed1af497464a7f8a21e0dbdc4011dda626c7 Mon Sep 17 00:00:00 2001
From: hnu202110040210 <hnu202110040210@qq.com>
Date: Sat, 21 May 2022 22:47:58 +0800
Subject: [PATCH] ADD file via upload

---
 500爬.py | 58 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 58 insertions(+)
 create mode 100644 500爬.py

diff --git a/500爬.py b/500爬.py
new file mode 100644
index 0000000..67ca1c3
--- /dev/null
+++ b/500爬.py
@@ -0,0 +1,58 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Sat May 21 21:00:02 2022
+
+@author: FengWei
+"""
+
+import requests
+import re
+
+# 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
+
+message = []
+# 总共17个页面的数据
+for page in range(17):
+    # 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
+    # 公司名
+    company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
+    # 法定代表人
+    money=re.findall('<em>(.+?)亿</em>注册资本', html)
+    pageOne = list(zip(company, money))
+    # 合并列表
+    message.extend(pageOne)
+    
+A={}
+for  i in range(20):
+    A[message[i][0]]=message[i][1]
+print(A)
+import matplotlib.pyplot as plt
+plt.rcParams['font.sans-serif'] = ['SimHei'] 
+plt.rcParams['axes.unicode_minus'] = False 
+M=A.keys()
+n=A.values()
+x = range(20) 
+y=[10.3,8.2,7.6,4.2,3.8,3.5,3.2,3.1,3.0,2.9,2.7,2.5,2.2,2.2,1.9,1.8,1.8,1.5,1.5,1.3]
+plt.figure(figsize=(45,15))
+plt.bar(x, y,width=0.6) 
+plt.xticks(x,M)
+plt.yticks(y,n)
+for i,j,l in zip(x,y,n):
+    plt.text(i,j,l,size=20,ha='center')
+plt.xlabel("公司",fontsize=20)
+plt.ylabel("注册资本/亿元",fontsize=20)
+plt.title('注册资本前20名的公司')
+plt.tick_params(labelsize=10)
+plt.show()