python抓取网页数据

利用python抓取网页数据（省考数据）

以湖南省省考数据为例，将数据转换为表格

import requests
from bs4 import BeautifulSoup
import pandas as pd

# 发起网页请求
url = 'http://rsks.hunanpea.com/Article/9fb511ff-0591-4164-85a1-ddbd101300ef/InternalArticleDetail.do'
response = requests.get(url)

if response.status_code == 200:
    soup = BeautifulSoup(response.text, 'html.parser')

    # 找到包含数据的表格
    table = soup.find('table')
    # 提取表格中的数据
    data = []
    for row in table.find_all('tr'):
        row_data = [cell.text for cell in row.find_all('td')]
        data.append(row_data)

    # 将数据存储到Excel文件
    df = pd.DataFrame(data)
    file_path = 'C:/Users/rc/Desktop/rc/2023湖南省省考报名情况.xlsx'
    df.to_excel(file_path, index=False)
else:
    print('Failed to retrieve the webpage.')

运行结果