Delete '中国五百强公司信息爬取.py'

master
hnu202109070101 3 years ago
parent 183b2621ce
commit 7e8685b250

@ -1,100 +0,0 @@
# -*- coding: utf-8 -*-
"""
Created on Sat May 21 21:38:27 2022
@author: dell
"""
# 首先我们需要导入 requests 库
import requests
# 请求的url
url = "https://top.chinaz.com/gongsi/index_zhuce.html"
# 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"
}
# 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
print(html)
# 导入 re 模快
import re
# 使用 findall 函数来获取数据
# 公司名
company = re.findall('<a.*?target="_blank">(.+?)</a></h3>', html)
#注册资本
money=re.findall('<em>(.+?)</em>注册资本</div>', html)
pageOne = list(zip(company,money))
# 存储内容
message = []
# 总共16个页面的数据
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('<a.*?target="_blank">(.+?)</a></h3>', html)
money=re.findall('<em>(.+?)</em>注册资本</div>', html)
pageOne = list(zip(company,money))
# 合并列表
message.extend(pageOne)
# 导入python中的内置模块csv
import csv
with open("content.csv", "w") as f:
w = csv.writer(f)
w.writerows(message)
import pandas as pd
# 读取数据
df = pd.read_csv("content.csv", names=["company",'money'],encoding='gbk')
df.head()
df.info()
#数据预处理
df['money']=df['money'].apply(lambda x:x.replace('亿','') )
df['money']=df['money'].apply(lambda x: float(x) )
#获取top20
df1=df.sort_values(by='money',ascending=False)
df2=df1.iloc[0:20]
#数据可视化 绘制水平条形图
import matplotlib.pyplot as plt
x=df2['company']
y=df2['money']
plt.barh(x,y,height=0.8)
for i,j in zip(x,y):
plt.text(j,i,j)
plt.title('中国500强注册资金top20企业')
plt.show()
Loading…
Cancel
Save