# -*- coding: utf-8 -*- # Author : Charley # Python : 3.10.8 # Date : 2025/8/19 15:58 import re import json import inspect import requests import user_agent from loguru import logger from parsel import Selector from mysql_pool import MySQLConnectionPool 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") crawler_language = "jp" class JPPokemonCardSpider: # 类变量 BASE_URL = "https://www.pokemon-card.com" def __init__(self, log=None): self.log = log or logger self.headers = { "accept": "application/json, text/javascript, */*; q=0.01", "user-agent": user_agent.generate_user_agent() } @staticmethod def _after_log(retry_state): """ retry 回调 - 静态方法 :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") @staticmethod def _parse_html_json(html_content, log): """ 解析网页源码, 获取json数据 - 静态方法 :param html_content: 网页源码 :param log: logger对象 :return: json数据 """ log.debug(f"{inspect.currentframe().f_code.co_name} start.....................") # 查找PTC.master.uiData的开始位置 start_marker = 'PTC.master.uiData = ' start_pos = html_content.find(start_marker) if start_pos == -1: log.debug("PTC.master.uiData not found") return None # 从开始标记后的位置查找第一个 { start_pos = html_content.find('{', start_pos + len(start_marker)) if start_pos == -1: log.debug("Opening brace not found") return None # 查找匹配的大括号 brace_count = 1 pos = start_pos + 1 while pos < len(html_content) and brace_count > 0: if html_content[pos] == '{': brace_count += 1 elif html_content[pos] == '}': brace_count -= 1 pos += 1 if brace_count == 0: # 提取完整的JavaScript对象 js_object_str = html_content[start_pos:pos] # 转换为有效的JSON try: # 添加引号到键，移除注释等 json_str = js_object_str # 为键添加引号 json_str = re.sub(r'([{,])\s*([a-zA-Z_][a-zA-Z0-9_]*)\s*:', r'\1 "\2":', json_str) # 移除注释 json_str = re.sub(r'//.*?(\n|$)', r'\1', json_str) json_str = re.sub(r'/\*.*?\*/', '', json_str, flags=re.DOTALL) # 移除尾随逗号 json_str = re.sub(r',(\s*[}\]])', r'\1', json_str) ui_data = json.loads(json_str) return ui_data except json.JSONDecodeError as e: log.error(f"{inspect.currentframe().f_code.co_name}Failed to decode JSON: {e}") else: log.warning(f"{inspect.currentframe().f_code.co_name} Could not find complete JavaScript object") return None @retry(stop=stop_after_attempt(5), wait=wait_fixed(1), after=_after_log) def get_classification_list(self, sql_pool): """ 获取分类列表 :param sql_pool: MySQL连接池对象 """ self.log.debug(f"{inspect.currentframe().f_code.co_name} start.....................") url = f"{self.BASE_URL}/card-search/index.php" params = { "keyword": "", "se_ta": "", "regulation_sidebar_form": "all", "pg": "", "illust": "", "sm_and_keyword": "true" } response = requests.get(url, headers=self.headers, params=params, timeout=10) json_ui_data = self._parse_html_json(response.text, self.log) pg_list = json_ui_data.get("pg", {}).get("list", []) if pg_list: for pg in pg_list[1:]: pg_value = pg.get("value") pg_label = pg.get("label") self.log.info(f"pg_list -> pg_value:{pg_value}, pg_label: {pg_label}") self.get_pokemon_card_list(pg_value, pg_label, sql_pool) else: self.log.debug( f"{inspect.currentframe().f_code.co_name} NOt found pg_list !!! get_classification_list end.....................") @retry(stop=stop_after_attempt(5), wait=wait_fixed(1), after=_after_log) def _get_pokemon_card_single_page(self, pg_value, page=1): """ 获取指定分类和页码的卡片列表 """ self.log.debug(f"{inspect.currentframe().f_code.co_name} start.....................") url = f"{self.BASE_URL}/card-search/resultAPI.php" params = { "keyword": "", "se_ta": "", "regulation_sidebar_form": "all", "pg": pg_value, "illust": "", "sm_and_keyword": "true", "page": str(page) } response = requests.get(url, headers=self.headers, params=params, timeout=10) response.raise_for_status() resp_json = response.json() return resp_json def _parse_pokemon_card_list(self, card_list, pg_value, pg_label, sql_pool): """ 解析卡片列表，获取卡片信息 """ self.log.debug(f"{inspect.currentframe().f_code.co_name} start.....................") card_info_list = [] data_list = [] for card in card_list: card_id = card.get("cardID") data_dict = {"pg_value": pg_value, "pg_label": pg_label} data_list.append(data_dict) condition_dict = { "card_id": card_id, "crawler_language": crawler_language } card_info_list.append(condition_dict) if card_info_list: sql_pool.update_many(table="pokemon_card_record", data_list=card_info_list, condition_list=card_info_list) def get_pokemon_card_list(self, pg_value='', pg_label='', sql_pool=None): """ 获取指定分类下的所有卡片列表 翻页 """ self.log.debug(f"{inspect.currentframe().f_code.co_name} start.....................") page = 1 max_page = 1 while page <= max_page: self.log.debug(f"正在获取第 {page} 页数据, pg_label: {pg_label} .........") page_data = self._get_pokemon_card_single_page(pg_value, page) if page_data.get("result") == 1: # 更新max_page（仅在第一页时需要更新） if page == 1: max_page = page_data.get("maxPage", 1) self.log.info(f"分类 {pg_label} 共有 {max_page} 页数据") cardList = page_data.get("cardList", []) if not cardList: self.log.warning(f"{inspect.currentframe().f_code.co_name} NOt found cardList !!!") break try: self._parse_pokemon_card_list(cardList, pg_value, pg_label, sql_pool) except Exception as e: self.log.error(f"{inspect.currentframe().f_code.co_name} parse_pokemon_card_list error: {e}") if len(cardList) < 39: self.log.debug(f"{inspect.currentframe().f_code.co_name} 获取的卡片数量小于39 !!! 停止翻页") break if page >= max_page: self.log.debug( f"{inspect.currentframe().f_code.co_name} -> page: {page}, max_page: {max_page}, 停止翻页") break if page >= 10: self.log.debug( f"{inspect.currentframe().f_code.co_name} -> page: {page}, page >= 10, 停止翻页.......") break page += 1 else: self.log.warning(f"获取第 {page} 页数据失败: {page_data.get('errMsg')}") break def get_details(self, item_id, sql_pool): """ 获取商品详情 """ self.log.debug(f"{inspect.currentframe().f_code.co_name} start, item_id: {item_id}.....................") url = f'{self.BASE_URL}/card-search/details.php/card/{item_id}' response = requests.get(url, headers=self.headers, timeout=10) response.raise_for_status() selector = Selector(response.text) card_no_list = selector.xpath('//div[@class="subtext Text-fjalla"]/text()').getall() card_no = ''.join(card_no_list) card_no = card_no.strip().replace('\xa0', '') if card_no else None tag_ic_rare = selector.xpath( '//div[@class="subtext Text-fjalla"]/img[not(contains(@class, "img-regulation"))]/@src').get() ic_rare_sp = tag_ic_rare.split('/')[-1].split('.')[0] if tag_ic_rare else None if ic_rare_sp and '_' in ic_rare_sp: ic_rare = ic_rare_sp.split('_')[-1] else: ic_rare = ic_rare_sp data_dict = { "card_no": card_no, "rarity": ic_rare } sql_pool.update_one_or_dict( table="pokemon_card_record", data=data_dict, condition={"card_id": item_id} ) @retry(stop=stop_after_attempt(100), wait=wait_fixed(3600), after=_after_log) def run(self): """ 主函数 """ self.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=self.log) if not sql_pool.check_pool_health(): self.log.error("数据库连接池异常") raise RuntimeError("数据库连接池异常") try: # 1. 获取已售出商品列表 按系列获取 先获取这个!!! self.log.debug(f"........... 开始获取已售出商品列表 按系列获取 ..........") try: self.get_classification_list(sql_pool) except Exception as e: self.log.error(f"Request get_classification_list error: {e}") # # 2. 获取商品列表 所有 去重 # self.log.debug(f"........... 获取商品列表 所有 去重 ..........") # try: # self.get_pokemon_card_list(sql_pool=sql_pool) # except Exception as e: # self.log.error(f"Request get_pokemon_card_list error: {e}") # 获取商品详情 # self.log.debug(f"........... 获取商品详情 ..........") # sql_ietm_id_list = sql_pool.select_all( # f"SELECT card_id FROM pokemon_card_record WHERE card_no IS NULL AND crawler_language='{crawler_language}'") # sql_ietm_id_list = [item_id[0] for item_id in sql_ietm_id_list] # for item_id in sql_ietm_id_list: # try: # self.get_details(item_id, sql_pool) # except Exception as e: # self.log.error(f"Request get_details error: {e}") except Exception as e: self.log.error(f'{inspect.currentframe().f_code.co_name} error: {e}') finally: self.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 定时任务 的启动文件 # """ # # 创建爬虫实例 # spider = JPPokemonCardSpider() # # # 立即运行一次任务 # # spider.run() # # # 设置定时任务 # schedule.every().day.at("01:06").do(spider.run) # # while True: # schedule.run_pending() # time.sleep(1) if __name__ == '__main__': # schedule_task() spider = JPPokemonCardSpider() spider.run()