crawl_config.json 3.42 KB
{
  "skill_name": "lemonv_drama",
  "version": "1.0.0",
  "crawl_time": "2026-04-13T02:40:00Z",
  "sources": [
    {
      "id": "zhonghuadiancan",
      "name": "中华典藏古籍",
      "type": "web_scraper",
      "endpoint": "https://www.zhonghuadiancan.com/",
      "method": "GET",
      "headers": {
        "User-Agent": "Mozilla/5.0"
      },
      "parse_rules": {
        "list_selector": ".book-item",
        "fields": {
          "title": "h3",
          "author": ".author"
        }
      },
      "rate_limit": {
        "requests_per_minute": 10,
        "sleep_ms": 3000,
        "respect_robots_txt": true
      },
      "priority": 1
    },
    {
      "id": "gushiwen",
      "name": "古诗文网",
      "type": "web_scraper",
      "endpoint": "https://so.gushiwen.cn/guwen/",
      "method": "GET",
      "headers": {
        "User-Agent": "Mozilla/5.0"
      },
      "parse_rules": {
        "list_selector": ".sons",
        "fields": {
          "title": "b",
          "dynasty": ".source"
        }
      },
      "rate_limit": {
        "requests_per_minute": 10,
        "sleep_ms": 3000,
        "respect_robots_txt": true
      },
      "priority": 2
    },
    {
      "id": "douban_gufeng",
      "name": "豆瓣古风小说分类",
      "type": "web_scraper",
      "endpoint": "https://book.douban.com/tag/古风",
      "method": "GET",
      "headers": {
        "User-Agent": "Mozilla/5.0"
      },
      "parse_rules": {
        "list_selector": ".subject-item",
        "fields": {
          "title": "h2 a",
          "rating": ".rating_nums"
        }
      },
      "rate_limit": {
        "requests_per_minute": 5,
        "sleep_ms": 3000,
        "respect_robots_txt": true
      },
      "priority": 3
    },
    {
      "id": "bilibili_gufeng",
      "name": "B站古风区热门",
      "type": "api",
      "endpoint": "https://api.bilibili.com/x/web-interface/ranking/v2",
      "method": "GET",
      "params": {
        "rid": 168,
        "type": "all"
      },
      "headers": {
        "User-Agent": "Mozilla/5.0",
        "Referer": "https://www.bilibili.com"
      },
      "parse_rules": {
        "list_path": "data.list",
        "fields": {
          "title": "title",
          "bvid": "bvid",
          "author": "owner.name",
          "view": "stat.view"
        }
      },
      "rate_limit": {
        "requests_per_minute": 10,
        "sleep_ms": 2000
      },
      "priority": 4
    },
    {
      "id": "wikipedia_chinese_history",
      "name": "维基百科中国历史页面",
      "type": "web_scraper",
      "endpoint": "https://zh.wikipedia.org/wiki/中国历史",
      "method": "GET",
      "headers": {
        "User-Agent": "Mozilla/5.0"
      },
      "parse_rules": {
        "list_selector": "#mw-content-text h2",
        "fields": {
          "title": "span.mw-headline"
        }
      },
      "rate_limit": {
        "requests_per_minute": 10,
        "sleep_ms": 3000,
        "respect_robots_txt": true
      },
      "priority": 5
    }
  ],
  "data_schema": {
    "required_fields": [
      "drama_id",
      "title",
      "era",
      "genre",
      "source_url",
      "crawl_time",
      "source_type",
      "source_content"
    ],
    "optional_fields": [
      "characters",
      "scenes",
      "plots",
      "endings",
      "image_prompts",
      "word_count"
    ]
  },
  "output_format": {
    "file": "seed_data.json",
    "encoder": "json",
    "append_timestamp": true
  }
}