ADD file via upload

中国500强公司信息爬取.py

@@ -0,0 +1,35 @@
+import requests
+import re
+import csv
+import pandas as pd
+import matplotlib.pyplot as plt
+headers = {
+    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36"
+}
+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)
+    m=re.findall('<em>(.*?)亿</em>注册资本', html)
+    pageOne = list(zip(company,m))
+    message.extend(pageOne)
+with open("content.csv", "w") as f:
+    w = csv.writer(f)
+    w.writerows(message)
+df = pd.read_csv("content.csv", names=["company","m"],encoding="gbk")
+df.head()
+plt.rcParams['font.sans-serif'] = ['SimHei']  
+plt.figure(figsize=(20,10))
+plt.bar(df["company"][:20],df["m"][:20])
+plt.xticks(range(len(df["company"][:20])),df["company"][:20],rotation=90)
+for x,y in zip(range(len(df["m"][:20])),df["m"][:20]):
+    plt.text(x,y,y,ha="center",va='bottom')
+plt.title("注册资金最多公司 top20")
+plt.xlabel("公司")
+plt.ylabel("资金（亿元）")
+plt.show()