From 8f635dc48bbc1b03be12fa486fe9ef6c53b64a6d Mon Sep 17 00:00:00 2001
From: hnu202110040418 <hnu202110040418@qq.com>
Date: Sat, 4 Jun 2022 22:09:33 +0800
Subject: [PATCH] ADD file via upload

---
 500强爬取.py | 65 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100644 500强爬取.py

diff --git a/500强爬取.py b/500强爬取.py
new file mode 100644
index 0000000..3462f7c
--- /dev/null
+++ b/500强爬取.py
@@ -0,0 +1,65 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Jun  3 14:51:42 2022
+
+@author: 86136
+"""
+
+#### 代码窗口
+import requests
+url = "https://top.chinaz.com/gongsi/index_zhuce.html"
+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"}
+response = requests.get(url, headers=headers)
+html = response.text
+import re
+message=[]
+for page in range(16):
+    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)
+    response = requests.get(url, headers=headers)
+    html = response.text
+    company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
+    money = re.findall('注册资本：</span>(.*?)</p>', html)
+    pageOne = list(zip(company, money))
+    message.extend(pageOne)
+message=message[0:500]
+import csv
+with open("content.csv", "w") as f:
+    w = csv.writer(f)
+    w.writerows(message)
+import pandas as pd
+df = pd.read_csv("content.csv", names=["company", "money"],encoding='gbk')
+df=df.fillna('0')
+money1=list(df['money'])[:20]
+company1=list(df['company'])[:20]
+money2=[]
+for i in money1:
+    p=''
+    j=re.findall(r'\d+\.\d+',i)
+    if j==[]:
+        j=re.findall(r'\d+',i)
+    for q in j:
+        if '万' in i:
+            p=round(float(q)*0.0001)
+        elif '亿' in i:
+            p=round(float(q))
+    money2.append(p)
+import matplotlib.pyplot as plt
+plt.rcParams['font.sans-serif'] = ['SimHei']  
+plt.rcParams['axes.unicode_minus']=False
+money2.reverse()
+company1.reverse()
+x=company1
+y=money2
+colors=['red']*5+['blue']*5+['green']*5+['yellow']*5
+plt.barh(x,y,height=0.7,color=colors)
+plt.yticks(x,x)
+for i,j in zip(x,y):
+    plt.text(j,i,j,fontsize=8)
+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()    
+