GK/3.31GK/other_code/request_curl_cffi.py

from datetime import datetime, timedelta

from curl_cffi import requests
# import requests
from requests.exceptions import Timeout
import retrying
import execjs
import json
import time
from loguru import logger


class GK:

    def __init__(self):
        self.akm_url = 'https://www.jetstar.com/c9NCrswc1aL9a_poKlkL/Y5OpJhrfcSzf/MwUVAg/SE0/adRNiWCo'
        self.search_flights_api = "https://booking.jetstar.com/hk/zh/booking/search-flights"

        self.headers = {
            "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7",
            "accept-language": "zh-CN,zh;q=0.9",
            "cache-control": "no-cache",
            "pragma": "no-cache",
            "priority": "u=0, i",
            "referer": "https://booking.jetstar.com/",
            "sec-ch-ua": "\"Google Chrome\";v=\"135\", \"Not-A.Brand\";v=\"8\", \"Chromium\";v=\"135\"",
            "sec-ch-ua-mobile": "?0",
            "sec-ch-ua-platform": "\"Windows\"",
            "sec-fetch-dest": "document",
            "sec-fetch-mode": "navigate",
            "sec-fetch-site": "same-origin",
            "sec-fetch-user": "?1",
            "upgrade-insecure-requests": "1",
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36"
        }
        with open('../akm/akm_5.26.js', encoding='utf-8') as f:
            js = f.read()
        self.ctx = execjs.compile(js)
        self.session = requests.Session()

    def get_cookie(self):
        # akm js file url
        akm_url = self.akm_url
        statusTs = str(int(time.time() * 1000))

        data = {
            'sensor_data': self.ctx.call('encrypt1', statusTs)
        }
        response = self.session.post(akm_url, headers=self.headers, verify=False, data=data,
                                     impersonate='chrome100',
                                     # 不指定 impersonate 时，TLS 指纹是 curl 原生的，而非浏览器指纹（依旧过不了检测）。需显式设置该参数以绕过 TLS 指纹检测
                                     http_version=2
                                     )

        logger.info(f'第一次请求cookie bmsz 状态吗 {response.status_code}')
        print('内容 ', response.text)
        print('响应cookie ', response.cookies.get_dict())

        bmsz = response.cookies.get_dict()['bm_sz']
        print('bmsz =>', bmsz)

        data2 = {
            "sensor_data": self.ctx.call('encrypt2', statusTs, bmsz)
        }

        data2 = json.dumps(data2)
        response2 = self.session.post(akm_url, headers=self.headers, data=data2, verify=False,
                                      impersonate='chrome101',
                                      http_version=2
                                      )
        logger.info(f'第2次请求验证 cookie bmsz 状态吗 {response.status_code}')
        print(response2.text)
        print(response2.cookies.get_dict())

    @retrying.retry(stop_max_attempt_number=3)
    def send_get(self, url, params):

        try:
            response = self.session.get(
                url,
                headers=self.headers, params=params,
                timeout=20,
                verify=False,
                # proxies=proxies
                impersonate='chrome99',
                http_version=2
            )
            response.raise_for_status()
            print('请求返回cookie', response.cookies.get_dict())
            return response
        # 捕获超时请求，可能是cookie不行了，更新后报错触发重试
        except Timeout as e:
            print(f"请求超时，重新更换cookie: {e}")
            # # 清除旧 Cookie
            # self.session.cookies.clear()
            # print(self.session.cookies.get_dict())
            # self.get_cookie()
            raise

        # except Exception as e:
        #     logger.error(e)
        #
        #     return None

    def get_data(self, datetime_str):
        params = {
            "s": "true",
            "adults": "1",  # 成年人
            "children": "0",  # 儿童
            "infants": "0",  # 婴儿
            "selectedclass1": "economy",  # 选择类型：经济舱
            "currency": "CNY",  # 货币
            "mon": "true",
            "channel": "DESKTOP",
            "origin1": "PVG",  # 出发地
            "destination1": "NRT",  # 目的地
            "departuredate1": datetime_str  # 出发时间
        }

        response = self.send_get(self.search_flights_api, params)
        if not response:
            return

        # print(response.text)
        print(response)

        from lxml import etree
        import json

        html = etree.HTML(response.text)
        data = html.xpath("//script[@id='bundle-data-v2']/text()")
        if data:
            json_data = json.loads(data[0])
            print(datetime_str, ' => ', json_data)
        else:
            print(response.text)

    @staticmethod
    def gen_datetime(start_date, end_date):
        """生成抓取日期: 2025-03-09 传入这种格式"""
        # 将字符串转换为 datetime 对象
        current_date = datetime.strptime(start_date, '%Y-%m-%d')
        end_date = datetime.strptime(end_date, '%Y-%m-%d')

        # 初始化一个空列表来存储日期
        date_list = []

        # 使用 timedelta 循环遍历每一天
        while current_date <= end_date:
            date_list.append(current_date.strftime('%Y-%m-%d'))  # 转换为字符串格式存储
            current_date += timedelta(days=1)

        return date_list

    def run(self, start_date, end_date):
        self.get_cookie()
        # # 获取采集时间
        for num, datetime_str in enumerate(self.gen_datetime(start_date, end_date), start=1):
            # if num % 5 == 0:
            #     self.session = requests.Session()
            #     self.get_cookie()

            self.get_data(datetime_str)
        #     # time.sleep(1)


if __name__ == '__main__':
    gk = GK()
    gk.run(start_date='2025-05-29', end_date='2025-06-29')