ADD file via upload

chinaz(1).py

@@ -0,0 +1,39 @@
+import csv
+import requests
+import re
+import pandas as pd
+import matplotlib.pyplot as plt
+page_num = 17 
+message = []
+for i in range(1, page_num + 1):
+    if i == 1:
+        url = 'https://top.chinaz.com/gongsi/index_zhuce.html'
+    else:
+        url = f'https://top.chinaz.com/gongsi/index_zhuce_{i}.html'
+    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/108.0.1462.46"
+    }
+    resp = requests.get(url,headers=headers)
+    html = resp.text
+    company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
+    register_money = re.findall('<div class="CoDate"><em>(.+?)亿</em>注册资本</div>', html)
+    pageOne = list(zip(company, register_money))
+    message.extend(pageOne)
+    print(f"第{i}页爬取完毕")
+with open("content.csv", "w", encoding='utf-8', newline='') as f:
+    w = csv.writer(f)
+    w.writerows(message)
+plt.rcParams['font.sans-serif'] = ['SimHei']
+df = pd.read_csv("content.csv", names=["company","register_money"])
+df.sort_values(by=['register_money'])
+xlabels = df["company"].values[:20]
+ylabels = df["register_money"].values[:20]
+data = pd.Series(ylabels, index=xlabels)
+data.plot(kind='bar')
+plt.title('注册资金最多的公司 top20')
+plt.xlabel('公司') 
+plt.xticks(rotation=270,fontsize=5)
+plt.ylabel('注册资金')
+for x, y in enumerate(data):
+    plt.text(x, y, y)
+plt.show()