|
|
import requests
|
|
|
# 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/101.0.4951.64 Safari/537.36 Edg/101.0.1210.53"
|
|
|
}
|
|
|
import re
|
|
|
# 存储内容
|
|
|
message = []
|
|
|
# 总共17个页面的数据
|
|
|
for page in range(17):
|
|
|
# 组装url # 请求的url
|
|
|
if page == 0:
|
|
|
# https://top.chinaz.com/gongsi/index_zhuce.html
|
|
|
url = "https://top.chinaz.com/gongsi/index_zhuce.html"
|
|
|
else:
|
|
|
# https://top.chinaz.com/gongsi/index_zhuce_2.html
|
|
|
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)
|
|
|
# 获取请求的返回结果
|
|
|
html = response.text
|
|
|
# 使用 findall 函数来获取数据
|
|
|
# 公司名
|
|
|
# <a href="/company/ZhongGuoTieLu.html" target="_blank">中国铁路总公司</a></h3>
|
|
|
company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
|
|
|
# 注册资本
|
|
|
# 注册资本：</span>103600000万人民币</p>
|
|
|
money = re.findall('注册资本：</span>(.*?)</p>', html)
|
|
|
# 对应项目的信息进行打包
|
|
|
pageOne = list(zip(company, money))
|
|
|
# 合并列表
|
|
|
message.extend(pageOne)
|
|
|
import csv
|
|
|
with open("content01.csv", "w") as f:
|
|
|
w = csv.writer(f)
|
|
|
w.writerows(message)
|
|
|
import pandas as pd
|
|
|
# 读取数据
|
|
|
df = pd.read_csv("content01.csv", names=["company", "money"], encoding='gbk')
|
|
|
# 填充空元素
|
|
|
df = df.fillna('0')
|
|
|
# 注册资本单位转换
|
|
|
company_all_top500=list(df.loc[0:499,'company'])
|
|
|
money_all_top500=list(df.loc[0:499,'money'])
|
|
|
money_all_number=[]
|
|
|
for i in money_all_top500:
|
|
|
p=''
|
|
|
for j in i:
|
|
|
if j in '0123456789.':
|
|
|
p=p+j
|
|
|
p=float(p)
|
|
|
if '万' in i:
|
|
|
p=int(p*10000+0.5)
|
|
|
if '亿' in i:
|
|
|
p=int(p*100000000+0.5)
|
|
|
# 汇率取自2022年5月26日
|
|
|
if '美元' in i:
|
|
|
p=int(p*6.7388+0.5)
|
|
|
if '港' in i:
|
|
|
p=int(p*0.8585+0.5)
|
|
|
money_all_number.append(p)
|
|
|
data={'company':company_all_top500,'money':money_all_number}
|
|
|
df=pd.DataFrame(data)
|
|
|
df=df.sort_values(by=['money'],ascending=False)
|
|
|
# 取注册资本最多的前二十公司名称和注册资本
|
|
|
company_top20=df.iloc[0:20,0]
|
|
|
money_top20=df.iloc[0:20,1]
|
|
|
|
|
|
#公司名称竖状表示
|
|
|
company_top20_y=[]
|
|
|
for i in company_top20:
|
|
|
s=''
|
|
|
for j in i:
|
|
|
p=j
|
|
|
if j=='（':
|
|
|
p='︵'
|
|
|
if j=='）':
|
|
|
p='︶'
|
|
|
s=s+p+'\n'
|
|
|
company_top20_y.append(s)
|
|
|
|
|
|
# 在jupyter中直接展示图像
|
|
|
import matplotlib.pyplot as plt
|
|
|
# 步骤一（替换sans-serif字体）
|
|
|
plt.rcParams['font.sans-serif'] = ['SimHei']
|
|
|
# 步骤二（解决坐标轴负数的负号显示问题）
|
|
|
plt.rcParams['axes.unicode_minus'] = False
|
|
|
plt.bar(range(20),money_top20)
|
|
|
plt.xticks(range(20),company_top20_y)
|
|
|
plt.yticks([2000e8,4000e8,6000e8,8000e8,10000e8],['2000','4000','6000','8000','10000'])
|
|
|
plt.ylabel('注册资本/亿元')
|
|
|
plt.title('中国500强公司注册资金前二十的公司及注册资金示意图')
|
|
|
plt.show() |
