{ "version": "1.0", "skill_name": "community-manager", "description": "社区运营与马甲运营知识库的爬虫配置。由于社区平台规则更新频繁且部分数据需登录态,本配置以公开榜单和规则页面为主数据源。", "crawl_policy": { "respect_robots_txt": true, "request_interval_seconds": 3, "max_retries": 2, "user_agent": "Mozilla/5.0 (compatible; ArenaSK-Hunter/1.0)" }, "sources": [ { "name": "weibo_hot_search", "platform": "微博", "url": "https://s.weibo.com/top/summary", "type": "html_parse", "update_frequency": "realtime", "fields": ["rank", "title", "hot_value", "category"], "headers": { "Accept": "text/html,application/xhtml+xml", "Accept-Language": "zh-CN,zh;q=0.9" }, "parser": { "selector": "#pl_top_realtimehot tbody tr", "field_mapping": { "rank": "td.td-01.ranktop | text", "title": "td.td-02 a | text", "hot_value": "td.td-02 span | text" } } }, { "name": "bilibili_ranking", "platform": "B站", "url": "https://api.bilibili.com/x/web-interface/ranking/v2?rid=0&type=all", "type": "api_json", "update_frequency": "daily", "fields": ["bvid", "title", "pic", "author", "view_count", "danmaku_count", "like_count"], "headers": { "Referer": "https://www.bilibili.com", "User-Agent": "Mozilla/5.0" }, "parser": { "root_path": "data.list", "field_mapping": { "bvid": "bvid", "title": "title", "pic": "pic", "author": "owner.name", "view_count": "stat.view", "danmaku_count": "stat.danmaku", "like_count": "stat.like" } } }, { "name": "douyin_hot_search", "platform": "抖音", "url": "https://www.douyin.com/hot", "type": "html_parse_js_rendered", "update_frequency": "realtime", "fields": ["rank", "title", "hot_value", "label"], "note": "需 Selenium/Playwright 等无头浏览器渲染 JS 后抓取", "parser": { "selector": "[data-e2e='hot-list'] li", "field_mapping": { "rank": ".rank | text", "title": ".title | text", "hot_value": ".hot-value | text" } } }, { "name": "xiaohongshu_explore", "platform": "小红书", "url": "https://www.xiaohongshu.com/explore", "type": "rpa_browser", "update_frequency": "daily", "fields": ["note_id", "title", "author", "likes", "cover_image"], "note": "小红书核心内容需登录态,建议通过 RPA 配合 cookies 获取首页推荐流" }, { "name": "platform_rules", "platform": "通用", "type": "manual_reference", "urls": [ "https://www.xiaohongshu.com/protocols/agreement", "https://www.douyin.com/aboutus/rules.html", "https://www.bilibili.com/blackboard/account-cn.html", "https://weibo.com/signup/v5/protocol" ], "update_frequency": "monthly", "note": "平台规则页面主要用于人工核对和引用,机器爬取后需人工校验" } ], "data_schema": { "required_fields": ["source_name", "crawl_time", "platform"], "optional_fields": ["rank", "title", "author", "view_count", "hot_value", "url"] }, "fallback": { "description": "当公开榜单因反爬升级不可用时,可切换至第三方数据平台 API(如新榜、蝉妈妈、飞瓜数据),但需付费授权。" } }