| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324 |
- # -*- coding: utf-8 -*-
- # Author : Charley
- # Python : 3.10.8
- # Date : 2025/3/19 18:55
- import time
- import inspect
- import requests
- import schedule
- import user_agent
- from loguru import logger
- from datetime import datetime
- from mysq_pool import MySQLConnectionPool
- from tenacity import retry, stop_after_attempt, wait_fixed
- """
- com.jihuanshe
- """
- 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
- def save_product_data(sql_pool, product_info: tuple):
- """
- 保存 product 数据
- :param sql_pool: MySQL连接池对象
- :param product_info: 要保存的数据
- """
- sql = """
- INSERT INTO jhs_product_record (seller_user_id, seller_username, product_id, app_id, nonce_str, signature, auction_product_name, auction_product_images, game_key, language_text, authenticator_name, grading, starting_price, max_bid_price, status, auction_product_start_time, auction_product_end_time)
- VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)"""
- sql_pool.insert_one(sql, product_info)
- def save_biddings_data(sql_pool, biddings_list: list):
- """
- 保存 biddings 数据
- :param sql_pool: MySQL连接池对象
- :param biddings_list: 要保存的数据 -> list
- """
- sql = """
- INSERT INTO jhs_biddings_record (product_id, username, bid_price, bid_status, created_at)
- VALUES (%s, %s, %s, %s, %s)"""
- sql_pool.insert_all(sql, biddings_list)
- def save_shop_data(sql_pool, shop_info: tuple):
- """
- 保存 product 数据
- :param sql_pool: MySQL连接池对象
- :param shop_info: 要保存的数据
- """
- sql = """
- INSERT INTO jhs_shop_record (seller_user_id, seller_username, follower_count, success_order_user_count, seller_credit_rank_image_url)
- VALUES (%s, %s, %s, %s, %s)"""
- sql_pool.insert_one(sql, shop_info)
- def parse_data(log, resp_json, sql_product_id, sql_pool, sql_shop_id_list):
- """
- 解析数据, 将解析后的数据, 分成三个表存储 product
- biddings
- shop
- :param log: logger对象
- :param resp_json: resp_json
- :param sql_product_id: sql_product_id
- :param sql_pool: MySQL连接池对象
- :param sql_shop_id_list: sql_shop_id_list
- """
- sql_id = sql_product_id[0]
- pid = sql_product_id[1]
- status = resp_json.get('status')
- if status not in ['ongoing', 'pending']:
- """
- 获取 shop 信息
- """
- seller_user_id = resp_json.get('seller_user_id')
- seller_username = resp_json.get('seller_username')
- # print(seller_user_id)
- # # 查询商家id在不在数据库中
- # sql_exists_flag = """SELECT EXISTS (SELECT 1 FROM jhs_shop_record WHERE seller_user_id = %s) AS exists_flag"""
- # exists_flag = sql_pool.select_one(sql_exists_flag, (seller_user_id,))
- # exists_flag = exists_flag[0]
- # if exists_flag == 1:
- if str(seller_user_id) in sql_shop_id_list:
- log.info(
- f"----------------- The seller_user_id {seller_user_id} is already in the database, Not need save -----------------")
- else:
- follower_count = resp_json.get('follower_count')
- success_order_user_count = resp_json.get('success_order_user_count')
- seller_credit_rank_image_url = resp_json.get('seller_credit_rank_image_url')
- shop_info = (
- seller_user_id, seller_username, follower_count, success_order_user_count, seller_credit_rank_image_url
- )
- # print(shop_info)
- try:
- save_shop_data(sql_pool, shop_info)
- sql_shop_id_list.append(seller_user_id)
- except Exception as e:
- if "Duplicate entry" in str(e):
- logger.warning(f"存在重复的 seller_user_id{seller_user_id},跳过插入....")
- else:
- logger.error(f"保存数据 seller_user_id 时出错: {str(e)}")
- # sql_pool.update_one("update jhs_task set task_state = 1 where id = %s", (sql_id,))
- """
- 获取 product 信息
- """
- app_id = resp_json.get('appId')
- nonce_str = resp_json.get('nonceStr')
- signature = resp_json.get('signature')
- # auction_product_id = resp_json.get('auction_product_id')
- auction_product_name = resp_json.get('auction_product_name')
- auction_product_images_list = resp_json.get('auction_product_images', [])
- if auction_product_images_list:
- auction_product_images = ','.join(auction_product_images_list)
- else:
- auction_product_images = None
- game_key = resp_json.get('game_key')
- language_text = resp_json.get('language_text')
- authenticator_name = resp_json.get('authenticator_name')
- grading = resp_json.get('grading')
- starting_price = resp_json.get('starting_price')
- max_bid_price = resp_json.get('max_bid_price')
- auction_product_start_timestamp = resp_json.get('auction_product_start_timestamp')
- auction_product_start_time = datetime.fromtimestamp(auction_product_start_timestamp).strftime(
- '%Y-%m-%d %H:%M:%S') if auction_product_start_timestamp else None
- auction_product_end_timestamp = resp_json.get('auction_product_end_timestamp')
- auction_product_end_time = datetime.fromtimestamp(auction_product_end_timestamp).strftime(
- '%Y-%m-%d %H:%M:%S') if auction_product_end_timestamp else None
- product_info = (
- seller_user_id, seller_username, pid, app_id, nonce_str, signature, auction_product_name,
- auction_product_images, game_key, language_text, authenticator_name, grading, starting_price, max_bid_price,
- status, auction_product_start_time, auction_product_end_time
- )
- # print(product_info)
- try:
- save_product_data(sql_pool, product_info)
- sql_pool.update_one("update jhs_task set task_state = 1 where id = %s", (sql_id,))
- except Exception as e:
- if "Duplicate entry" in str(e):
- logger.warning(f"存在重复的 pid{pid},跳过插入....")
- else:
- logger.error(f"保存数据时出错: {str(e)}")
- return
- """
- 获取 biddings 信息
- """
- biddings = resp_json.get('biddings', [])
- # print(biddings)
- # 创建一个字典来存储每个用户的最高出价记录
- highest_bids = {}
- for record in biddings:
- username = record['username']
- bid_price = float(record['bid_price']) # 将出价转换为浮点数以便比较
- # 如果用户不在字典中,或者当前出价高于已存储的最高出价,则更新记录
- if username not in highest_bids or bid_price > float(highest_bids[username]['bid_price']):
- highest_bids[username] = record
- bids_list = list(highest_bids.values())
- biddings_list = [
- (pid, record['username'], record['bid_price'], record['bid_status'], record['created_at'])
- for record in bids_list
- ]
- # print(biddings_list)
- if biddings_list:
- save_biddings_data(sql_pool, biddings_list)
- else:
- log.info(f"................ No biddings found for product {pid}, Not need save ................")
- else:
- log.info(f"................ The product {pid} is ongoing or pending, Not need parse ................")
- sql_pool.update_one("update jhs_task set task_state = 4 where id = %s", (sql_id,))
- @retry(stop=stop_after_attempt(5), wait=wait_fixed(1), after=after_log)
- def get_resp(log, sql_product_id, sql_pool, sql_shop_id_list):
- """
- 获取 response 响应
- :param log: logger对象
- :param sql_product_id: sql_product_id
- :param sql_pool: MySQL连接池对象
- :param sql_shop_id_list: sql_shop_id_list
- """
- sql_id = sql_product_id[0]
- pid = sql_product_id[1]
- headers = {
- "accept": "application/json, text/plain, */*",
- "referer": "https://www.jihuanshe.com/",
- "user-agent": user_agent.generate_user_agent()
- }
- url = "https://api.jihuanshe.com/api/market/share/auction-product"
- params = {
- "auction_product_id": pid,
- "url": f"https://www.jihuanshe.com/app/auction?auctionProductId={pid}"
- }
- response = requests.get(url, headers=headers, params=params, timeout=5, proxies=get_proxys(log))
- # print(response.json())
- # print(response)
- resp_json = response.json()
- if resp_json:
- if resp_json.get("code") == 440:
- log.debug(f"< 抱歉,该竞价商品已被移除, pid:{pid} >")
- sql_pool.update_one("update jhs_task set task_state = 2 where id = %s", (sql_id,))
- else:
- try:
- parse_data(log, resp_json, sql_product_id, sql_pool, sql_shop_id_list)
- except Exception as e:
- log.error(f"get_resp call parse_data() sql_product_id:{sql_product_id} 获取失败, error:{e}")
- @retry(stop=stop_after_attempt(100), wait=wait_fixed(3600), after=after_log)
- def jhs_main(log):
- """
- 主函数
- :param log: logger对象
- """
- 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:
- max_sql_pid = sql_pool.select_one("select max(product_id) from jhs_product_record")
- if max_sql_pid:
- max_sql_pid = max_sql_pid[0]
- else:
- max_sql_pid = 568835
- log.debug(f"当前数据库中最大的 product_id max_sql_id:{max_sql_pid}")
- # 从数据库获取需要爬取的 product_id 从最大的id max_sql_id 开始
- product_id_list = sql_pool.select_all(
- f"SELECT id, product_id FROM jhs_task WHERE task_state != 1 AND id > '{max_sql_pid-2000}' LIMIT 5000")
- # "SELECT id, product_id FROM jhs_task WHERE task_state IN (0, 2) AND id > 420107 LIMIT 10000")
- # "SELECT id, product_id FROM jhs_task WHERE task_state IN (0, 2) AND id > %s LIMIT 6000", (max_sql_id,))
- # "SELECT id, product_id FROM jhs_task WHERE task_state IN (0, 2) AND id < 376575 ORDER BY id DESC")
- product_id_list = [keyword for keyword in product_id_list]
- sql_shop_id_list = sql_pool.select_all("SELECT seller_user_id FROM jhs_shop_record")
- sql_shop_id_list = [keyword[0] for keyword in sql_shop_id_list]
- for sql_product_id in product_id_list:
- try:
- get_resp(log, sql_product_id, sql_pool, sql_shop_id_list)
- except Exception as e:
- log.error(f"Loop sql_product_id:{sql_product_id} 获取失败, error:{e}")
- sql_pool.update_one("update jhs_task set task_state = 3 where id = %s", (sql_product_id[0],))
- 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():
- """
- 设置定时任务
- """
- jhs_main(log=logger)
- schedule.every().day.at("01:31").do(jhs_main, log=logger)
- while True:
- schedule.run_pending()
- time.sleep(1)
- if __name__ == '__main__':
- schedule_task()
- # get_resp(logger, (438807, 438807), MySQLConnectionPool(log=logger),[])
|