You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
69 lines
1.8 KiB
69 lines
1.8 KiB
# 首先我们需要导入 requests 库
|
|
import requests
|
|
# 若是本地没有安装 requests 可以通过“pip install requests”来安装
|
|
|
|
# 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"
|
|
}
|
|
|
|
# 导入 re 模快
|
|
import re
|
|
|
|
# 存储内容
|
|
message = []
|
|
# 总共16个页面的数据
|
|
for page in range(20):
|
|
# 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)
|
|
# 注册资金
|
|
signMoney = re.findall('<div class="CoDate"><em>(.+?)</em>注册资本</div>', html)
|
|
|
|
pageOne = list(zip(company,signMoney))
|
|
# 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", "signMoney"],encoding='gbk')
|
|
|
|
df1 = df.drop(0).head(20)
|
|
|
|
import matplotlib.pyplot as plt
|
|
|
|
# 在spyter中直接展示图像
|
|
%matplotlib inline
|
|
# 设置中文显示
|
|
plt.rcParams['font.sans-serif'] = ['SimHei']
|
|
plt.rcParams['figure.figsize'] = (30, 5) # 设置figure_size尺寸
|
|
|
|
# x轴坐标
|
|
x = df1["company"].values
|
|
# y轴坐标
|
|
y = df1["signMoney"].values
|
|
# 绘制柱状图
|
|
plt.bar(x, y)
|
|
# 设置x轴名称
|
|
plt.xlabel("公司",fontsize=14)
|
|
# 设置x轴名称
|
|
plt.ylabel("注册资本",fontsize=14)
|
|
plt.show()
|
|
|
|
|