Python 爬取航班信息并解析 - 使用 Requests 库获取数据

import requests

def get_content1(id):
    url = f'https://flights.sda.cn/tRtApi/flight/resultSets/{id}'

    payload={}
    headers = {
      'Accept': 'application/json',
      'Accept-Language': 'zh-CN',
      'Cache-Control': 'no-cache',
      'Connection': 'keep-alive',
      'Market-Country-Code': 'CN',
      'Pragma': 'no-cache',
      'Referer': 'https://flights.sda.cn/flight/search/TNA-CSX-230402',
      'Sec-Fetch-Dest': 'empty',
      'Sec-Fetch-Mode': 'cors',
      'Sec-Fetch-Site': 'same-origin',
      'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36',
      'sec-ch-ua': ''Google Chrome';v='111', 'Not(A:Brand';v='8', 'Chromium';v='111'',
      'sec-ch-ua-mobile': '?0',
      'sec-ch-ua-platform': ''Windows''
    }

    response = requests.request('GET', url, headers=headers, data=payload).json()
    # print(response)
    return response


def get_content3(response):
    # 遍历开始
    for li in response['flightSegments']:

        # 出发
        # 出发城市
        start_city = li['departure']['city']
        # 出发城市三字码
        start_sityString = li['departure']['iataCode']
        # 出发机场名称
        start_airportName = li['departure']['name'] + li['departure']['terminal']
        # 出发日期+时间
        start_datetime = li['departure']['dateTime']

        # 到达
        # 到达城市
        reach_city = li['arrival']['city']
        # 到达城市三字码
        reach_cityString = li['arrival']['iataCode']
        # 到达机场名称
        reach_airportName = li['arrival']['name'] + li['arrival']['terminal']
        # 到达日期+时间
        reach_datetime = li['arrival']['dateTime']

        # 飞机用时
        plan_userTime = str(li['duration']).replace(':', '时') + '分'
        # 飞机名字
        plan_name = '波音' + str(li['equipmentType'])
        # 飞机航班
        plan_flightNumber = li['operatingAirlineInfo']['airlineCode'] + li['marketingAirlineInfo']['flightNumber']

        # plan_seatType=li['mealCode']
        #  ['flightOptions'][0]['prices'][0]['details']['cash']['base']['amount']

        # print(start_city,start_sityString,start_airportName,start_datetime,
        #       reach_city,reach_cityString,reach_airportName,reach_datetime,
        #       plan_userTime,plan_flightNumber,plan_name)
        yield start_city, start_sityString, start_airportName, start_datetime, reach_city, reach_cityString, reach_airportName, reach_datetime, plan_userTime, plan_flightNumber, plan_name

def get_content2(response):
    for div in response['flightOptions']:
        # 飞机价格  要改
        price = div['prices'][0]['details']['cash']['base']['amount']
        if price == '':
            plan_price = div['prices'][0]['details']['cash']['base']['amount']

        else:
            plan_price = div['prices'][1]['fareBreakdowns'][0]['base']['amount']
        plan_seatType = div['prices'][0]['fareInfos'][0]['rbd']
        # print(plan_seatType,plan_price)
        yield plan_seatType, plan_price

def download(id):
    response = get_content1(id)
    for start_city, start_sityString, start_airportName, start_datetime, reach_city, reach_cityString, reach_airportName, reach_datetime, plan_userTime, plan_flightNumber, plan_name, plan_seatType, plan_price in zip(get_content3(response), get_content2(response)):
        wb2 = {
            'q': start_city,
            'w': start_sityString,
            'e': start_airportName,
            'r': start_datetime,
            't': reach_city,
            'y': reach_cityString,
            'u': reach_airportName,
            'i': reach_datetime,
            'o': plan_userTime,
            'p': plan_flightNumber,
            's': plan_name,
            'a': plan_price,
            'b': plan_seatType
        }
        print(wb2)

if __name__ == '__main__':
    # get_content1()
    # get_content3()
    # get_content2()
    download(12345)  # 替换 12345 为实际的 ID

使用方法：

1. 将代码保存为 .py 文件。
2. 替换代码中的 12345 为实际的航班搜索结果 ID。
3. 运行代码，将会输出航班信息字典。

注意：

• 本代码需要 requests 库。如果未安装，请使用 pip install requests 命令安装。
• 代码中的 URL 和 headers 信息来自 https://flights.sda.cn 网站，请根据实际情况修改。
• 代码仅供参考，实际使用时可能需要根据网站的更新情况进行调整。
• 请勿将此代码用于非法目的。