{ "version": "1.0", "description": "topic-selector 选题筛选器爬取配置", "data_sources": [ { "name": "百度热搜", "url": "https://top.baidu.com/board?tab=realtime", "method": "GET", "headers": { "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" }, "update_frequency": "实时", "status": "active", "parser": { "type": "html", "selector": ".item-wrap .item-title", "fields": ["rank", "title", "heat"] } }, { "name": "哔哩哔哩热搜", "url": "https://api.bilibili.com/x/web-interface/popular", "method": "GET", "headers": { "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" }, "update_frequency": "实时", "status": "active", "parser": { "type": "json", "path": "data.list", "fields": ["title", "desc", "pic", "stat"] } } ], "filter_rules": { "pre_filters": [ { "type": "exclude_keywords", "keywords": ["敏感", "违规", "作弊", "谣言"] }, { "type": "min_heat_threshold", "value": 1000 } ], "scoring_dimensions": [ { "name": "热度指数", "key": "heat_score", "weight": 0.3, "metrics": ["search_volume", "read_count", "discussion_count"] }, { "name": "话题延展性", "key": "extendability", "weight": 0.25, "metrics": ["angle_count", "controversy_level", "knowledge增量"] }, { "name": "受众覆盖", "key": "audience_coverage", "weight": 0.25, "metrics": ["age_group", "purchasing_power", "interest_match"] }, { "name": "生命周期", "key": "lifecycle", "weight": 0.2, "metrics": ["trend_phase", "time_sensitivity", "reversal_risk"] } ], "industry_categories": [ "科技数码", "娱乐明星", "社会民生", "国际关系", "财经商业", "健康养生", "教育职场" ], "output_top_n": 20 }, "output_format": { "type": "json", "schema": { "topic_id": "string", "title": "string", "category": "string", "source": "string", "source_url": "string", "heat_score": "number", "extendability_score": "number", "audience_score": "number", "lifecycle_score": "number", "total_score": "number", "crawl_time": "string" } }, "crawl_settings": { "request_interval_ms": 2000, "max_retries": 3, "timeout_ms": 10000, "respect_robots_txt": true } }