From 51050d521c2243e31e87f361670cd6d8585fd8d3 Mon Sep 17 00:00:00 2001 From: hnu202109010305 <731615514@qq.com> Date: Thu, 8 Dec 2022 23:55:58 +0800 Subject: [PATCH] ADD file via upload --- 中国企业五百强.py | 55 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 中国企业五百强.py diff --git a/中国企业五百强.py b/中国企业五百强.py new file mode 100644 index 0000000..d4a453f --- /dev/null +++ b/中国企业五百强.py @@ -0,0 +1,55 @@ +import csv +import requests +import re +import pandas as pd +from matplotlib import pyplot as plt +# 用黑体显示中文 +plt.rcParams['font.sans-serif'] = ['SimHei'] +# 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" +} +# 存储内容 +message = [] +# 总共16个页面的数据 +for page in range(16): + # 组装url + if page == 0: + url = "https://top.chinaz.com/gongsitop/index_500top.html" + else: + url = "https://top.chinaz.com/gongsitop/index_500top_{}.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('(.+?)', html) + # 法定代表人 + person = re.findall('法定代表人:(.*?)

', html) + # 注册时间 + signDate = re.findall('注册时间:(.*?)

', html) + # 证券类别 + category = re.findall('证券类别:(.*?)

', html) + pageOne = list(zip(company, person, signDate, category)) + # 合并列表 + message.extend(pageOne) +with open("content.csv", "w") as f: + w = csv.writer(f) + w.writerows(message) +# 读取数据 +df = pd.read_csv("content.csv", names=["company", "person", "signDate", "category"],encoding='gbk') +# 根据证券类型进行分组 +df1 = df.groupby("category").count()["company"] +print(df1) +# 每个扇形的标签 +labels = df1.index +# 每个扇形的占比 +sizes = df1.values +plt.figure(figsize=(80,40),dpi=80) +fig1, ax1 = plt.subplots() +# 绘制饼图 +ax1.pie(sizes, labels=labels, autopct='%d%%',radius=1.3,textprops={'fontsize': 20}, + shadow=False, startangle=90) +ax1.axis() + +plt.show()