spider_work/panini_coming_soon_spider/panini_control_price.py

# -*- coding: utf-8 -*-
# Author : Charley
# Python : 3.10.8
# Date   : 2025/2/12 13:16
import time
import datetime
from loguru import logger
from CloudflareBypasser import CloudflareBypasser
from DrissionPage import ChromiumPage, ChromiumOptions
from tenacity import retry, stop_after_attempt, wait_fixed

logger.remove()
logger.add("./logs/{time:YYYYMMDD}.log", encoding='utf-8', rotation="00:00",
           format="[{time:YYYY-MM-DD HH:mm:ss.SSS}] {level} {message}",
           level="DEBUG", retention="7 day")


def after_log(retry_state):
    """
    retry 回调
    :param retry_state: RetryCallState 对象
    """
    # 检查 args 是否存在且不为空
    if retry_state.args and len(retry_state.args) > 0:
        log = retry_state.args[0]  # 获取传入的 logger
    else:
        log = logger  # 使用全局 logger

    if retry_state.outcome.failed:
        log.warning(
            f"Function '{retry_state.fn.__name__}', Attempt {retry_state.attempt_number} Times")
    else:
        log.info(f"Function '{retry_state.fn.__name__}', Attempt {retry_state.attempt_number} succeeded")


def get_screen_shot(log, page, end_time):
    """
    每分钟刷新页面并截图
    :param log:
    :param page:
    :param end_time:
    """
    log.info("开始截图....................")
    while datetime.datetime.now() < end_time:
        page.refresh()

        page.wait.load_start()  # 等待页面进入加载状态

        page.wait.eles_loaded('.card-body')  # 等待 class 为 div1 的元素加载

        time.sleep(3)
        page.wait.load_start()  # 等待页面进入加载状态

        path = "./panini_screenshot_images"
        current_time = datetime.datetime.now()
        screenshot_filename = current_time.strftime("%Y%m%d%H%M%S") + ".jpg"

        # full_page参数   为True截取的是整页截图, 为False截取可视窗口  默认为False
        # page.get_screenshot(path, name=screenshot_filename, full_page=True)
        page.get_screenshot(path, name=screenshot_filename)
        log.info(f"已保存截图: {screenshot_filename}")
        time.sleep(60)  # 每隔1分钟刷新一次


def get_screen_cast(log, tab, end_time):
    """
    每分钟刷新页面并录制视频
    :param log:
    :param tab:
    :param end_time:
    """
    tab.screencast.set_save_path('video')  # 设置视频存放路径
    tab.screencast.set_mode.video_mode()  # 设置录制模式
    tab.screencast.start()  # 开始录制

    try:
        while datetime.datetime.now() < end_time:
            tab.refresh()
            tab.wait.load_start()  # 等待页面进入加载状态

            current_time = datetime.datetime.now()
            screenshot_filename = current_time.strftime("%Y%m%d%H%M%S") + ".jpg"
            tab.get_screenshot('./panini_screenshot_video', name=screenshot_filename)
            log.info(f"已保存截图: {screenshot_filename}")
            time.sleep(60)  # 每隔1分钟刷新一次
    except Exception as e:
        log.error(f"录制过程中发生错误: {e}")
    finally:
        tab.screencast.stop()  # 停止录制


@retry(stop=stop_after_attempt(2), wait=wait_fixed(1), after=after_log)
def panini_control_price(log):
    log.info("开始请求页面....................")
    options = ChromiumOptions().set_paths(local_port=9103,
                                          user_data_path=r'D:\Drissionpage_temp\panini_control_price_port_9103')
    options.set_argument("--disable-gpu")
    options.set_argument("-accept-lang=en-US")
    page = ChromiumPage(options)
    page.set.window.full()

    try:
        url = "https://www.paniniamerica.net/2024-25-select-basketball-white-sparkle-pack-3-cards-per-pack-on-average-look-for-randomly-inserted-1-1-autographs.html"
        page.get(url, timeout=20)

        # page_title = page.title.lower()
        # print(page_title)
        # if "just a moment" in page_title:
        #     cf_bypasser = CloudflareBypasser(page, max_retries=5, log=log)
        #     cf_bypasser.bypass()
        #     page.wait.load_start()  # 等待页面进入加载状态
        # else:
        #     logger.info("无需绕过")

        # 设置开始时间和结束时间
        # start_time = datetime.datetime.strptime("2025-02-12 23:55:00", "%Y-%m-%d %H:%M:%S")
        start_time = datetime.datetime.strptime("2025-07-21 23:55:50", "%Y-%m-%d %H:%M:%S")
        end_time = start_time + datetime.timedelta(hours=2.5)

        # 等待到开始时间
        while datetime.datetime.now() < start_time:
            time.sleep(1)

        get_screen_shot(log, page, end_time)


    except Exception as e:
        log.error(f"操作失败: {e}")
    finally:
        log.info("结束请求页面....................")
        page.close()
        page.quit()


if __name__ == '__main__':
    panini_control_price(logger)
#     http://grafana.ipangyou.com/explore?panes=%7B%220xD%22:%7B%22datasource%22:%22e0f7c4fb-4dc6-4665-9d15-2c5faa0f4fc2%22,%22queries%22:%5B%7B%22refId%22:%22A%22,%22expr%22:%22%7Bapplication%3D%5C%22ins-python%5C%22%7D%22,%22queryType%22:%22range%22,%22datasource%22:%7B%22type%22:%22loki%22,%22uid%22:%22e0f7c4fb-4dc6-4665-9d15-2c5faa0f4fc2%22%7D,%22editorMode%22:%22builder%22,%22legendFormat%22:%22%22%7D%5D,%22range%22:%7B%22from%22:%22now-2d%22,%22to%22:%22now%22%7D%7D%7D&schemaVersion=1&orgId=1