diff --git a/shijiewubaiqiang.py b/shijiewubaiqiang.py new file mode 100644 index 0000000..ee6712b --- /dev/null +++ b/shijiewubaiqiang.py @@ -0,0 +1,79 @@ +# -*- coding: utf-8 -*- +""" +Created on Wed Nov 30 12:30:46 2022 + +@author: lenovo +""" + +import requests +# 请求的url +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"} +# 使用reqeusts模快发起 GET 请求 +response = requests.get(url, headers=headers) +# 获取请求的返回结果 +html = response.text + +# 使用 findall 函数来获取数据 +import re +# 公司名 +company = re.findall('(.+?)', html) +# 注册资金: +money = re.findall('"CoDate">(.+?)', html) +pageOne = list(zip(company,money)) + + +# for循环获取其他页面的所有数据 +# 存储内容 +message = [] +# 所有页面的数据 +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('(.+?)', html) + # 注册资金 + money = re.findall('"CoDate">(.+?)', html) + pageOne = list(zip(company,money)) + # 合并列表 + message.extend(pageOne) +message=message[0:500] + +#保存内容到 csv 文件 +import csv +with open("content.csv", "w") as f: + w = csv.writer(f) + w.writerows(message) + +#数据可视化 +import pandas as pd +import numpy as np +df=pd.read_csv("content.csv", names=["company", "money"]) +df=df.head(20) +df=df[::-1] + +import matplotlib.pyplot as plt +plt.figure() +plt.rcParams['font.sans-serif'] = ['SimHei'] + +x=list(range(1,21)) +df_array = np.array(df["company"]) +l=df_array.tolist() +df_array = np.array(df["money"]) +y=df_array.tolist() +plt.xticks(x,l,rotation=90) +plt.bar(x,y,width=0.8,color='r') +plt.xlabel('company') +plt.ylabel('money') +for i,j in zip(x,y): + plt.text(i,j,ha='center',va='bottom') +plt.show() + +