Method trigger_crawl

mcp_server/tools/system.py:201–293

手动触发一次临时爬取任务（可选持久化） Args: platforms: 指定平台列表，为空则爬取所有平台 save_to_local: 是否保存到本地 output 目录，默认 False include_url: 是否包含URL链接，默认False（节省token） Returns: 爬取结果字典，包含新闻数据和保存路径（如果保存）

(self, platforms: Optional[List[str]] = None, save_to_local: bool = False, include_url: bool = False)

        return result

    def trigger_crawl(self, platforms: Optional[List[str]] = None, save_to_local: bool = False, include_url: bool = False) -> Dict:
        """
        手动触发一次临时爬取任务（可选持久化）

        Args:
            platforms: 指定平台列表，为空则爬取所有平台
            save_to_local: 是否保存到本地 output 目录，默认 False
            include_url: 是否包含URL链接，默认False（节省token）

        Returns:
            爬取结果字典，包含新闻数据和保存路径（如果保存）
        """
        try:
            from trendradar.crawler.fetcher import DataFetcher
            from trendradar.storage.local import LocalStorageBackend
            from trendradar.storage.base import convert_crawl_results_to_news_data
            from trendradar.utils.time import get_configured_time, format_date_folder, format_time_filename
            from ..services.cache_service import get_cache

            platforms = validate_platforms(platforms)

            # 1. 加载配置
            config_data, all_platforms = self._load_crawl_config()
            target_platforms, ids = self._resolve_target_platforms(all_platforms, platforms)

            print(f"开始临时爬取，平台: {[p.get('name', p['id']) for p in target_platforms]}")

            # 2. 执行爬取
            advanced = config_data.get("advanced", {})
            crawler_config = advanced.get("crawler", {})
            platforms_config = config_data.get("platforms", {})
            proxy_url = crawler_config.get("default_proxy") if crawler_config.get("use_proxy") else None
            api_url = (
                os.environ.get("PLATFORMS_API_URL", "").strip()
                or platforms_config.get("api_url", "")
            ) or None

            domain_rules = {}
            for p in target_platforms:
                ed = p.get("expected_domain", "")
                if ed:
                    domain_rules[p["id"]] = ed

            fetcher = DataFetcher(proxy_url=proxy_url, api_url=api_url)
            results, id_to_name, failed_ids = fetcher.crawl_websites(
                ids_list=ids,
                request_interval=crawler_config.get("request_interval", 100),
                domain_rules=domain_rules,
            )

            # 3. 转换与持久化
            timezone = config_data.get("app", {}).get("timezone", "Asia/Shanghai")
            current_time = get_configured_time(timezone)
            crawl_date = format_date_folder(None, timezone)
            crawl_time_str = format_time_filename(timezone)

            news_data = convert_crawl_results_to_news_data(
                results=results, id_to_name=id_to_name,