{
  "_meta": {
    "version": "1.0.0",
    "created_at": "2026-03-25",
    "agent": "hunter",
    "task_id": "T-mn5uzcwt",
    "description": "讽刺新闻网站抓取配置 - 支持RSS和网页双模式"
  },

  "sources": {
    "tier1_core": [
      {
        "name": "The Onion",
        "domain": "theonion.com",
        "language": "en",
        "country": "US",
        "founded": 1988,
        "style": "news_parody",
        "political_leaning": "neutral",
        "rss": {
          "enabled": true,
          "url": "https://www.theonion.com/rss",
          "format": "rss2.0",
          "update_frequency": "hourly"
        },
        "categories": ["politics", "entertainment", "technology", "sports", "local", "lifestyle"],
        "priority": 1,
        "reliability": "elite"
      },
      {
        "name": "Babylon Bee",
        "domain": "babylonbee.com",
        "language": "en",
        "country": "US",
        "founded": 2016,
        "style": "conservative_satire",
        "political_leaning": "conservative",
        "religious_affiliation": "christian",
        "rss": {
          "enabled": true,
          "url": "https://babylonbee.com/feed",
          "format": "rss2.0",
          "update_frequency": "hourly"
        },
        "categories": ["politics", "crime", "lifestyle", "sports", "life", "us", "entertainment"],
        "priority": 1,
        "reliability": "elite"
      },
      {
        "name": "ClickHole",
        "domain": "clickhole.com",
        "language": "en",
        "country": "US",
        "founded": 2014,
        "parent_company": "G/O Media",
        "style": "clickbait_spoof",
        "political_leaning": "neutral",
        "rss": {
          "enabled": true,
          "url": "https://clickhole.com/feed",
          "format": "rss2.0",
          "update_frequency": "hourly"
        },
        "categories": ["quiz", "news", "lifestyle"],
        "priority": 1,
        "reliability": "elite"
      }
    ],

    "tier2_high_value": [
      {
        "name": "Reductress",
        "domain": "reductress.com",
        "language": "en",
        "country": "US",
        "style": "womens_media_parody",
        "political_leaning": "liberal",
        "rss": {
          "enabled": true,
          "url": "https://reductress.com/feed",
          "format": "rss2.0"
        },
        "priority": 2,
        "reliability": "elite"
      },
      {
        "name": "The Hard Times",
        "domain": "thehardtimes.net",
        "language": "en",
        "country": "US",
        "style": "music_scene_satire",
        "political_leaning": "neutral",
        "rss": {
          "enabled": true,
          "url": "https://thehardtimes.net/feed",
          "format": "rss2.0"
        },
        "priority": 2,
        "reliability": "elite"
      },
      {
        "name": "The Daily Mash",
        "domain": "thedailymash.co.uk",
        "language": "en",
        "country": "UK",
        "style": "british_dry_humor",
        "political_leaning": "neutral",
        "rss": {
          "enabled": true,
          "url": "https://thedailymash.co.uk/feed",
          "format": "rss2.0"
        },
        "priority": 2,
        "reliability": "elite"
      },
      {
        "name": "NewsThump",
        "domain": "newsthump.com",
        "language": "en",
        "country": "UK",
        "style": "political_satire",
        "political_leaning": "left_leaning",
        "rss": {
          "enabled": true,
          "url": "https://newsthump.com/feed",
          "format": "rss2.0"
        },
        "priority": 2,
        "reliability": "elite"
      },
      {
        "name": "Waterford Whispers News",
        "domain": "waterfordwhispersnews.com",
        "language": "en",
        "country": "Ireland",
        "style": "irish_satire",
        "political_leaning": "neutral",
        "rss": {
          "enabled": true,
          "url": "https://waterfordwhispersnews.com/feed",
          "format": "rss2.0"
        },
        "priority": 2,
        "reliability": "elite"
      }
    ],

    "tier3_supplementary": [
      {
        "name": "The Betoota Advocate",
        "domain": "betootaadvocate.com",
        "language": "en",
        "country": "Australia",
        "style": "australian_outback",
        "rss": {
          "enabled": true,
          "url": "https://betootaadvocate.com/feed",
          "format": "rss2.0"
        },
        "priority": 3,
        "reliability": "high"
      },
      {
        "name": "The Beaverton",
        "domain": "thebeaverton.com",
        "language": "en",
        "country": "Canada",
        "style": "canadian_politics",
        "rss": {
          "enabled": true,
          "url": "https://thebeaverton.com/feed",
          "format": "rss2.0"
        },
        "priority": 3,
        "reliability": "high"
      },
      {
        "name": "The Shovel",
        "domain": "theshovel.com.au",
        "language": "en",
        "country": "Australia",
        "style": "australian_satire",
        "rss": {
          "enabled": true,
          "url": "https://theshovel.com.au/feed",
          "format": "rss2.0"
        },
        "priority": 3,
        "reliability": "high"
      },
      {
        "name": "Duffel Blog",
        "domain": "duffelblog.com",
        "language": "en",
        "country": "US",
        "style": "military_satire",
        "rss": {
          "enabled": true,
          "url": "https://duffelblog.com/feed",
          "format": "rss2.0"
        },
        "priority": 3,
        "reliability": "elite"
      },
      {
        "name": "The Fauxy",
        "domain": "thefauxy.com",
        "language": "en",
        "country": "India",
        "style": "south_asian_perspective",
        "rss": {
          "enabled": true,
          "url": "https://thefauxy.com/feed",
          "format": "rss2.0"
        },
        "priority": 3,
        "reliability": "high"
      },
      {
        "name": "The Poke",
        "domain": "thepoke.co.uk",
        "language": "en",
        "country": "UK",
        "style": "image_led_satire",
        "rss": {
          "enabled": true,
          "url": "https://thepoke.co.uk/feed",
          "format": "rss2.0"
        },
        "priority": 3,
        "reliability": "average"
      },
      {
        "name": "The Spoof",
        "domain": "thespoof.com",
        "language": "en",
        "country": "UK",
        "style": "user_generated",
        "rss": {
          "enabled": true,
          "url": "https://thespoof.com/rss",
          "format": "rss2.0"
        },
        "priority": 3,
        "reliability": "average"
      }
    ]
  },

  "collection_modes": {
    "rss": {
      "enabled": true,
      "description": "RSS feed实时监控 - 推荐主模式",
      "polling_intervals": {
        "tier1": 900,
        "tier2": 1800,
        "tier3": 3600
      },
      "batch_size": 50,
      "max_items_per_feed": 100
    },
    "web_scraping": {
      "enabled": true,
      "description": "网页抓取 - 用于历史数据补充",
      "frequency": "monthly",
      "respect_robots_txt": true,
      "delay_between_requests": 2,
      "user_agent": "SatireNewsBot/1.0 (Research Purpose)"
    }
  },

  "url_templates": {
    "rss_standard": "{domain}/feed",
    "rss_wordpress": "{domain}/feed",
    "rss_category": "{domain}/category/{category}/feed",
    "site_archive": "{domain}/archives/{year}/{month}",
    "site_sitemap": "{domain}/sitemap.xml",
    "site_post": "{domain}/{year}/{month}/{day}/{slug}"
  },

  "field_mapping": {
    "rss_common": {
      "title": {
        "xpath": "//item/title",
        "required": true,
        "type": "string"
      },
      "link": {
        "xpath": "//item/link",
        "required": true,
        "type": "url"
      },
      "pub_date": {
        "xpath": "//item/pubDate",
        "required": true,
        "type": "datetime",
        "format": "RFC2822"
      },
      "description": {
        "xpath": "//item/description",
        "required": false,
        "type": "html"
      },
      "category": {
        "xpath": "//item/category",
        "required": false,
        "type": "array"
      },
      "guid": {
        "xpath": "//item/guid",
        "required": true,
        "type": "string"
      },
      "creator": {
        "xpath": "//item/dc:creator",
        "required": false,
        "type": "string"
      }
    },

    "web_scraping_selectors": {
      "the_onion": {
        "article_list": {
          "container": "article",
          "title": "h2 a, h1",
          "link": "a[href]",
          "summary": ".summary, h1 + p"
        },
        "article_detail": {
          "title": "h1",
          "content": "article .entry-content p, article p",
          "author": ".author, [data-testid='AuthorName']",
          "publish_date": "time",
          "category": ".category a, [data-testid='Breadcrumb']"
        }
      },
      "babylon_bee": {
        "article_list": {
          "container": "article.post",
          "title": "h2.entry-title a",
          "link": "h2.entry-title a",
          "summary": ".entry-summary"
        },
        "article_detail": {
          "title": "h1.entry-title",
          "content": ".entry-content p",
          "author": ".author-name, .byline a",
          "publish_date": "time.entry-date",
          "category": ".cat-links a"
        }
      },
      "clickhole": {
        "article_list": {
          "container": "article",
          "title": "h2.entry-title a, .post-title",
          "link": "h2.entry-title a",
          "summary": ".entry-summary"
        },
        "article_detail": {
          "title": "h1.entry-title",
          "content": ".entry-content p, .post-content p",
          "author": ".author",
          "publish_date": "time",
          "category": ".category a"
        }
      }
    }
  },

  "category_taxonomy": {
    "theme_categories": {
      "politics": "政治",
      "entertainment": "娱乐",
      "technology": "科技",
      "sports": "体育",
      "lifestyle": "生活方式",
      "crime": "犯罪/法律",
      "business": "商业",
      "religion": "宗教",
      "international": "国际",
      "local": "本地新闻",
      "science": "科学",
      "health": "健康",
      "education": "教育",
      "culture": "文化"
    },
    "satire_types": {
      "news_parody": "新闻模仿",
      "clickbait_spoof": "点击诱饵讽刺",
      "exaggeration": "夸张",
      "irony": "反讽",
      "absurdism": "荒诞",
      "political_satire": "政治讽刺",
      "social_commentary": "社会评论"
    },
    "content_formats": {
      "article": "文章",
      "quiz": "测验",
      "listicle": "列表",
      "video": "视频",
      "image": "图片"
    }
  },

  "filter_rules": {
    "content_quality": {
      "min_title_length": 10,
      "max_title_length": 200,
      "require_pub_date": true,
      "require_valid_url": true,
      "dedup_by_guid": true,
      "dedup_by_title_similarity": 0.9
    },
    "satire_detection": {
      "keywords": [
        "satire", "parody", "spoof", "fake news",
        "讽刺", "恶搞", "假新闻"
      ],
      "source_whitelist": true,
      "cross_check_real_news": false
    },
    "exclusion": {
      "sponsored_content": true,
      "duplicate_reposts": true,
      "error_pages": true
    }
  },

  "output_schema": {
    "article": {
      "required_fields": [
        "id",
        "title",
        "url",
        "source",
        "published_at",
        "collected_at"
      ],
      "optional_fields": [
        "summary",
        "content",
        "author",
        "categories",
        "tags",
        "featured_image",
        "satire_type",
        "political_leaning"
      ]
    },
    "metadata": {
      "required_fields": [
        "source_name",
        "source_domain",
        "collection_method",
        "schema_version"
      ]
    }
  },

  "scheduling": {
    "jobs": [
      {
        "name": "tier1_rss_poll",
        "description": "核心来源RSS轮询",
        "sources": ["the_onion", "babylon_bee", "clickhole"],
        "mode": "rss",
        "frequency": "*/15 * * * *",
        "enabled": true
      },
      {
        "name": "tier2_rss_poll",
        "description": "高价值来源RSS轮询",
        "sources": ["reductress", "the_hard_times", "the_daily_mash", "newsthump", "waterford_whispers"],
        "mode": "rss",
        "frequency": "*/30 * * * *",
        "enabled": true
      },
      {
        "name": "tier3_rss_poll",
        "description": "补充来源RSS轮询",
        "sources": ["the_betoota_advocate", "the_beaverton", "the_shovel", "duffel_blog", "the_fauxy"],
        "mode": "rss",
        "frequency": "0 * * * *",
        "enabled": true
      },
      {
        "name": "full_archive_scrape",
        "description": "全量历史数据抓取",
        "sources": ["the_onion", "babylon_bee", "clickhole"],
        "mode": "web",
        "frequency": "0 2 1 * *",
        "enabled": false
      }
    ]
  },

  "storage": {
    "format": "jsonl",
    "compression": "gzip",
    "partitioning": {
      "by_source": true,
      "by_date": "%Y/%m/%d"
    },
    "retention": {
      "raw_data_days": 90,
      "processed_data_days": 365
    }
  },

  "monitoring": {
    "metrics": [
      "articles_collected",
      "sources_polled",
      "parse_errors",
      "duplicate_rate",
      "avg_processing_time"
    ],
    "alerting": {
      "source_down_threshold": 3,
      "error_rate_threshold": 0.05,
      "stale_data_threshold_hours": 24
    }
  },

  "api_endpoints": {
    "third_party": {
      "rapidapi_onion": {
        "name": "RapidAPI The Onion",
        "url": "https://rapidapi.com/ionxccd/api/the-onion-api",
        "type": "unofficial",
        "format": "json",
        "requires_key": true
      },
      "webz_news": {
        "name": "Webz News API",
        "url": "https://webz.io/",
        "type": "aggregator",
        "format": "json",
        "tag_support": ["satirical_news"],
        "requires_key": true
      }
    }
  },

  "notes": {
    "babylon_bee_disclaimer": "有明确保守派政治立场和基督教倾向，使用时需标注",
    "clickhole_content_warning": "内容可能过于荒诞，需评估适用场景",
    "copyright_notice": "仅供研究和合理使用，请遵守各网站的版权政策",
    "rss_limitations": "RSS通常只返回最近50-100条，历史数据需网页抓取"
  }
}