spider_work/bgs_spider/bgs_lack_add.py

# -*- coding: utf-8 -*-
# Author : Charley
# Python : 3.10.8
# Date   : 2025/5/28 15:35
import inspect
import requests
import user_agent
from loguru import logger
import concurrent.futures
from tenacity import stop_after_attempt, wait_fixed, retry
from mysql_pool import MySQLConnectionPool

logger.remove()
logger.add("logs/add_{time:YYYYMMDD}.log", encoding='utf-8', rotation="00:00",
           format="[{time:YYYY-MM-DD HH:mm:ss.SSS}] {level} {message}",
           level="DEBUG", retention="1 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):
    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_data(log, bgs_id, sql_pool):
    """
    :param log:
    :param bgs_id:
    :param sql_pool:
    :return:
    """
    headers = {
        "accept": "application/json, text/plain, */*",
        "user-agent": user_agent.generate_user_agent()
    }
    url = "https://www.beckett.com/api/grading/lookup"
    params = {
        "category": "BGS",
        "serialNumber": str(bgs_id)
    }
    response = requests.get(url, headers=headers, params=params, proxies=get_proxys(log), timeout=5)
    if response.status_code == 404:
        # 没有数据 No Record Found 将状态改为3
        log.warning(f"No Record Found for {bgs_id}")
        sql_pool.update_one("UPDATE bgs_task SET state=3 WHERE auth_code=%s", (bgs_id,))
        return

    if response.status_code != 200:
        # 查询失败  将状态改为2
        log.warning(f"Error getting data for {bgs_id}, {response.status_code}")
        sql_pool.update_one("UPDATE bgs_task SET state=2 WHERE auth_code=%s", (bgs_id,))
        return

    result_dict = response.json()
    if result_dict:
        centering_grade = result_dict.get('center_grade')
        corner_grade = result_dict.get('corners_grade')
        edges_grade = result_dict.get('edges_grade')
        surfaces_grade = result_dict.get('surface_grade')

        total_grade = result_dict.get('pop_report')
        cards_grade = result_dict.get('pop_higher')
        info = (centering_grade, corner_grade, edges_grade, surfaces_grade, total_grade, cards_grade, int(bgs_id))

        # 检查所有值是否都为 None或空字符串, 不包含bgs_id
        all_none_or_empty = all(x is None or x == '' for x in info[:-1])
        if all_none_or_empty:
            log.debug("All values are empty")
        else:
            # print(info)
            sql_pool.update_one(
                "UPDATE beckett_bgs_record SET centering_grade=%s, corner_grade=%s, edges_grade=%s ,surfaces_grade=%s, total_grade=%s, cards_grade=%s WHERE number=%s",
                info)

            # 查询成功  将状态改为1
            sql_pool.update_one("UPDATE bgs_task SET state=1 WHERE auth_code=%s", (bgs_id,))


def process_urls(log, ids, mysql_pool, batch_size=1000, max_workers=5):
    with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
        for i in range(0, len(ids), batch_size):
            # print(i)
            batch = ids[i:i + batch_size]
            # print(batch)
            try:
                futures_to_urls = {executor.submit(get_data, log, url, mysql_pool): url for url in batch}
                for future in concurrent.futures.as_completed(futures_to_urls):
                    url = futures_to_urls[future]
                    try:
                        future.result()
                        log.debug(f"处理 {url} 成功")
                    except Exception as exc:
                        log.debug(f"处理 {url} 出错: {exc}")
            except Exception as e:
                log.error(f"提交任务失败: {e}")


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

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

        # 补充之前接口变化的异常数据
        sql = "SELECT number FROM beckett_bgs_record WHERE centering_grade IS NULL AND corner_grade IS NULL AND surfaces_grade IS NULL;"
        sql_bgs_id_list = sql_pool.select_all(sql)
        sql_bgs_id_list = [bid[0] for bid in sql_bgs_id_list]
        try:
            process_urls(log, sql_bgs_id_list, sql_pool, batch_size=1000,
                         max_workers=10)  # 根据需要调整batch_size和max_workers
        except Exception as e:
            log.error('process urls: ', e)

    except Exception as e:
        log.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............')


if __name__ == '__main__':
    bgs_add_main(logger)