Substack Publication Post Exporter

{
  "description": "Export custom-domain Substack publications and post URLs, with an RSS fallback for non-Substack sites.",
  "properties": {
    "audienceFilter": {
      "default": "all",
      "description": "Keep all posts, only free posts, or only paid posts.",
      "editor": "select",
      "enum": [
        "all",
        "free",
        "paid"
      ],
      "enumTitles": [
        "All posts",
        "Free posts only",
        "Paid posts only"
      ],
      "prefill": "all",
      "title": "Free or paid",
      "type": "string"
    },
    "bodyFormat": {
      "default": "all",
      "description": "Body fields to include. `none` is fastest; `all` adds HTML, plain text and Markdown.",
      "editor": "select",
      "enum": [
        "none",
        "html",
        "text",
        "markdown",
        "all"
      ],
      "enumTitles": [
        "No body",
        "HTML",
        "Plain text",
        "Markdown",
        "HTML + text + Markdown"
      ],
      "prefill": "none",
      "title": "Post body",
      "type": "string"
    },
    "containsKeyword": {
      "description": "(mode=publicationPosts) Keep posts whose title, teaser or text contains this keyword. Uses Substack's publication search when possible.",
      "editor": "textfield",
      "title": "Contains keyword",
      "type": "string"
    },
    "includeComments": {
      "default": false,
      "description": "Include public comment threads for free posts. Paid-post comments are members-only.",
      "prefill": false,
      "title": "Include comments",
      "type": "boolean"
    },
    "includePaidPreview": {
      "default": true,
      "description": "For paid posts, include the public preview body and flag it as a preview. Turn off for faster metadata-only runs.",
      "prefill": false,
      "title": "Include paid post preview",
      "type": "boolean"
    },
    "includePublicationInfo": {
      "default": true,
      "description": "Add publication details such as pricing plans, sections, language and payment status.",
      "prefill": false,
      "title": "Include publication info",
      "type": "boolean"
    },
    "maxCommentsPerPost": {
      "default": 20,
      "description": "Cap on comments per post, including replies. Set to 0 for no limit.",
      "maximum": 5000,
      "minimum": 0,
      "prefill": 20,
      "title": "Max comments per post",
      "type": "integer"
    },
    "maxItems": {
      "default": 50,
      "description": "Hard cap on emitted records.",
      "maximum": 10000,
      "minimum": 1,
      "prefill": 3,
      "title": "Max items",
      "type": "integer"
    },
    "maxPostsPerPublication": {
      "default": 0,
      "description": "Optional per-publication cap. Set to 0 for no per-publication limit.",
      "maximum": 10000,
      "minimum": 0,
      "prefill": 3,
      "title": "Max posts per publication",
      "type": "integer"
    },
    "mediaFilter": {
      "default": "any",
      "description": "Keep all posts, audio posts, video posts, or text-only posts.",
      "editor": "select",
      "enum": [
        "any",
        "audio",
        "video",
        "text"
      ],
      "enumTitles": [
        "Any media",
        "With audio",
        "With video",
        "Text only"
      ],
      "prefill": "any",
      "title": "Media",
      "type": "string"
    },
    "mode": {
      "default": "publicationPosts",
      "description": "What to scrape. substack.com-hosted inputs are reported as blocked_egress.",
      "editor": "select",
      "enum": [
        "publicationPosts",
        "postUrls"
      ],
      "enumTitles": [
        "Publication posts (archive)",
        "Specific post URLs"
      ],
      "prefill": "publicationPosts",
      "title": "Mode",
      "type": "string"
    },
    "postType": {
      "default": "all",
      "description": "Keep all post types or a single type.",
      "editor": "select",
      "enum": [
        "all",
        "newsletter",
        "podcast",
        "thread"
      ],
      "enumTitles": [
        "All types",
        "Newsletter",
        "Podcast",
        "Thread"
      ],
      "prefill": "all",
      "title": "Post type",
      "type": "string"
    },
    "postUrls": {
      "default": [],
      "description": "(mode=postUrls) Custom-domain post URLs, e.g. `https://www.noahpinion.blog/p/the-internet-breaks`. substack.com share links are reported as blocked_egress.",
      "editor": "stringList",
      "prefill": [],
      "title": "Post URLs",
      "type": "array"
    },
    "publications": {
      "default": [
        "platformer.news"
      ],
      "description": "(mode=publicationPosts) Custom-domain publication URLs or RSS-capable sites, e.g. `https://www.slowboring.com` or `https://platformer.news`. Bare subdomains and substack.com links are blocked from this actor's cloud network.",
      "editor": "stringList",
      "prefill": [
        "platformer.news"
      ],
      "title": "Publications",
      "type": "array"
    },
    "publishedAfter": {
      "description": "Keep posts published on or after this date (`YYYY-MM-DD`).",
      "editor": "textfield",
      "title": "Published after",
      "type": "string"
    },
    "publishedBefore": {
      "description": "Keep posts published on or before this date (`YYYY-MM-DD`).",
      "editor": "textfield",
      "title": "Published before",
      "type": "string"
    },
    "sortBy": {
      "default": "newest",
      "description": "(mode=publicationPosts) Newest first or all-time most popular first.",
      "editor": "select",
      "enum": [
        "newest",
        "top"
      ],
      "enumTitles": [
        "Newest first",
        "Most popular"
      ],
      "prefill": "newest",
      "title": "Sort order",
      "type": "string"
    },
    "tagsAnyOf": {
      "default": [],
      "description": "Keep posts carrying at least one of these tags (case-insensitive).",
      "editor": "stringList",
      "prefill": [],
      "title": "Tags",
      "type": "array"
    }
  },
  "schemaVersion": 1,
  "title": "Substack Scraper Input",
  "type": "object"
}

{
  "actorOutputSchemaVersion": 1,
  "description": "One record per post (metadata, free body HTML/text/Markdown, flagged paid teaser, media, engagement, comments) or one blocked_egress status row per substack.com-hosted input.",
  "properties": {
    "posts": {
      "description": "Dataset containing scraped Substack posts and author profiles.",
      "template": "{{links.apiDefaultDatasetUrl}}/items",
      "title": "Substack posts and author profiles",
      "type": "string"
    }
  },
  "title": "Substack Publication Post Exporter Output"
}

{
  "actorSpecification": 1,
  "views": {
    "overview": {
      "display": {
        "component": "table",
        "properties": {}
      },
      "title": "Substack posts",
      "transformation": {
        "fields": [
          "title",
          "recordType",
          "publication",
          "author",
          "publishedAt",
          "audience",
          "commentCount",
          "url"
        ]
      }
    }
  }
}