爬虫--列车时刻表数据（python）

import requests
from bs4 import BeautifulSoup

# 列车时刻表网页URL
url = 'http://www.12306.cn/index/trainlist-N-Q-1.html'

# 发送HTTP请求
response = requests.get(url)

# 检查请求是否成功
if response.status_code == 200:
    # 使用BeautifulSoup解析网页内容
    soup = BeautifulSoup(response.text, 'html.parser')

    # 找到所有列车时刻表信息的表格
    trains_table = soup.find('table', class_='train_list')

    # 遍历每一行（跳过表头）
    for row in trains_table.find_all('tr')[1:]:
        # 提取每一列的数据
        cells = row.find_all('td')
        train_number = cells[0].text.strip()  # 列车号
        start_station = cells[1].text.strip()  # 起点站
        end_station = cells[2].text.strip()  # 终点站
        start_time = cells[3].text.strip()  # 开行时间
        duration = cells[4].text.strip()  # 耗时
        frequency = cells[5].text.strip()  # 频率
        car_type = cells[6].text.strip()  # 车型
        print(train_number, start_station, end_station, start_time, duration, frequency, car_type)
else:
    print("Failed to retrieve webpage")