spider_work/zhongjian_spider/zj_new_daily_spider.py

# -*- coding: utf-8 -*-
# Author : Charley
# Python : 3.10.8
# Date   : 2025/6/9 15:56
import time
import inspect
import requests
import schedule
import user_agent
from loguru import logger
from tenacity import retry, stop_after_attempt, wait_fixed
from mysq_pool import MySQLConnectionPool

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")


@retry(stop=stop_after_attempt(5), wait=wait_fixed(1), after=after_log)
def get_proxys(log):
    """
    获取代理
    :return: 代理
    """
    tunnel = "x371.kdltps.com:15818"
    kdl_username = "t13753103189895"
    kdl_password = "o0yefv6z"
    try:
        proxies = {
            "http": "http://%(user)s:%(pwd)s@%(proxy)s/" % {"user": kdl_username, "pwd": kdl_password, "proxy": tunnel},
            "https": "http://%(user)s:%(pwd)s@%(proxy)s/" % {"user": kdl_username, "pwd": kdl_password, "proxy": tunnel}
        }
        return proxies
    except Exception as e:
        log.error(f"Error getting proxy: {e}")
        raise e


@retry(stop=stop_after_attempt(5), wait=wait_fixed(1), after=after_log)
def get_request_one_page(log, rating_no) -> dict:
    headers = {
        "accept": "*/*",
        "accept-language": "en,zh-CN;q=0.9,zh;q=0.8",
        "content-type": "application/json;charset=UTF-8",
        "origin": "https://www.zhongjianjiantong.com",
        "priority": "u=1, i",
        "referer": "https://www.zhongjianjiantong.com/web/index.html",
        "sec-ch-ua": "\"Not(A:Brand\";v=\"99\", \"Google Chrome\";v=\"133\", \"Chromium\";v=\"133\"",
        "sec-ch-ua-mobile": "?1",
        "sec-ch-ua-platform": "\"Android\"",
        "sec-fetch-dest": "empty",
        "sec-fetch-mode": "cors",
        "sec-fetch-site": "same-origin",
        "user-agent": user_agent.generate_user_agent()
    }
    url = "https://www.zhongjianjiantong.com/Api/OrderRatingGoods/detail"
    data = {
        "rating_no": rating_no
    }

    with requests.Session() as session:
        response = session.post(url, headers=headers, json=data, proxies=get_proxys(log), timeout=5)
    # print(response.text)
    response.raise_for_status()
    return response.json()


def parse_data(resp_json, sql_pool):
    card_id = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('id')
    order_no = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('order_no')
    tag_no = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('tag_no')  # 标签号/查询的号码

    images = resp_json.get('data', {}).get('obj_order_rating_goods', []).get('images')
    card_create_time = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('create_time')
    card_update_time = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('update_time')
    score = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('score')  # 中检评分
    corners = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get('corners')  # 四角
    eoges = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get('eoges')  # 边缘
    surface = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get('surface')  # 表面
    centering = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get('centering')  # 居中
    colour = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get('colour')  # 颜色
    repair = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get('repair')  # 修复

    rating_no = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('rating_no')  # 证书编号
    obj_brand_title = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_brand', {}).get(
        'title')  # 商品品牌
    obj_detail_spxl = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get(
        'spxl')  # 商品系列
    obj_detail_spmc = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get(
        'spmc')  # 商品名称
    obj_detail_fxnf = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get(
        'fxnf')  # 发行年份
    obj_detail_yy = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get('yy')  # 语言
    obj_detail_spbh = resp_json.get('data', {}).get('obj_order_rating_goods', {}).get('obj_detail', {}).get(
        'spbh')  # 商品编号

    info = (
        card_id, order_no, tag_no, images, card_create_time, card_update_time, score, corners, eoges, surface,
        centering,
        colour, repair, rating_no, obj_brand_title, obj_detail_spxl, obj_detail_spmc, obj_detail_fxnf, obj_detail_yy,
        obj_detail_spbh)
    sql = """
    INSERT INTO zhongjian_record (card_id, order_no, tag_no, images, card_create_time, card_update_time, score, corners, eoges, surface, centering, colour, repair, rating_no, obj_brand_title, obj_detail_spxl, obj_detail_spmc, obj_detail_fxnf, obj_detail_yy, obj_detail_spbh)
    VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
    """
    sql_pool.insert_one(sql, info)


def loop_rating_no(log, sql_pool, sql_ra_no_list):
    # sql_ra_no_list = sql_pool.select_all('select tag_no from zhongjian_task where state = 0 limit 10000')
    # sql_ra_no_list = [i[0] for i in sql_ra_no_list]
    for rating_no_ in sql_ra_no_list:
        log.info(f"{rating_no_} is start ......................................")
        try:
            resp_json = get_request_one_page(log, rating_no_)

            if resp_json and resp_json.get('code') == 200:
                # print(resp_json)
                parse_data(resp_json, sql_pool)
                sql_pool.update_one('update zhongjian_task set state = 1 where tag_no = %s', (rating_no_,))
            elif resp_json and resp_json.get('code') == 400:
                log.warning(f"{rating_no_} is not exist ......................................")
                sql_pool.update_one('update zhongjian_task set state = 2 where tag_no = %s', (rating_no_,))
            else:
                log.warning(f"other warning, please check ......................................")
                sql_pool.update_one('update zhongjian_task set state = 3 where tag_no = %s', (rating_no_,))
        except Exception as e:
            log.warning(f"{inspect.currentframe().f_code.co_name} error: {e}")
            sql_pool.update_one('update zhongjian_task set state = 3 where tag_no = %s', (rating_no_,))
            continue


@retry(stop=stop_after_attempt(100), wait=wait_fixed(3600), after=after_log)
def zhongjian_main(log):
    """
    主函数
    :param log:
    """
    log.info(
        f'开始运行 {inspect.currentframe().f_code.co_name} 爬虫任务....................................................')

    # 配置 MySQL 连接池
    sql_pool = MySQLConnectionPool(log=log)
    if not sql_pool:
        log.error("MySQL数据库连接失败")
        raise Exception("MySQL数据库连接失败")

    try:
        while True:
            sql_ra_no_list = sql_pool.select_all('select tag_no from zhongjian_task where state = 0 limit 10000')
            sql_ra_no_list = [i[0] for i in sql_ra_no_list]
            if not sql_ra_no_list:
                log.info(f'没有需要处理的数据,等待下一轮处理........................................................')
                break

            try:
                loop_rating_no(log, sql_pool, sql_ra_no_list)
            except  Exception as e:
                log.error(f'{inspect.currentframe().f_code.co_name} error: {e}')
    except Exception as e:
        log.error(f'{inspect.currentframe().f_code.co_name} error: {e}')
    finally:
        log.info(f'爬虫程序 {inspect.currentframe().f_code.co_name} 运行结束,等待下一轮的采集任务............')


def schedule_task():
    """
    爬虫模块的启动文件
    """
    # 立即运行一次任务
    zhongjian_main(log=logger)

    # 设置定时任务
    schedule.every(30).days.at("00:01").do(zhongjian_main, log=logger)

    while True:
        schedule.run_pending()
        time.sleep(1)


if __name__ == '__main__':
    schedule_task()