{ "openapi": "3.0.1", "info": { "title": "Tumblr Scraper", "description": "Scrape Tumblr posts from any public blog, tag or search query. Full-resolution media, tags, note counts, engagement metrics, reblog info and NSFW classification. No API key, no login needed.", "version": "0.1", "x-build-id": "hPZimRPd1wgKlJOMw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/subimpact~tumblr-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-subimpact-tumblr-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/subimpact~tumblr-scraper/runs": { "post": { "operationId": "runs-sync-subimpact-tumblr-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/subimpact~tumblr-scraper/run-sync": { "post": { "operationId": "run-sync-subimpact-tumblr-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "blog", "tag", "search" ], "type": "string", "description": "blog = posts from one or more blogs (legacy read API, paginates through the whole archive). tag = posts from a tag hub page. search = posts matching a search query.", "default": "blog" }, "blogNames": { "title": "Blog names (blog mode)", "type": "string", "description": "One or more blogs, comma-separated. Accepts a bare name (staff), a host (staff.tumblr.com), a custom domain, or a full URL (https://staff.tumblr.com)." }, "tags": { "title": "Tags (tag mode)", "type": "string", "description": "One or more tags, comma-separated. A leading # and a full /tagged/ URL are both accepted. Note: only the first page (~8 posts per tag) is reachable from an EU exit IP — see the README on the consent wall." }, "searchQueries": { "title": "Search queries (search mode)", "type": "string", "description": "One or more search queries, comma-separated. Note: only the first page (~16 posts per query) is reachable from an EU exit IP — see the README on the consent wall." }, "postTypes": { "title": "Post types", "type": "array", "description": "Keep only these post types. Leave empty for all types. Types are detected by sniffing the actual post media, not by trusting Tumblr's declared type — a 'regular' post with inline photos matches both text and photo.", "items": { "type": "string", "enum": [ "text", "photo", "video", "audio", "quote", "link", "chat", "answer" ], "enumTitles": [ "Text", "Photo", "Video", "Audio", "Quote", "Link", "Chat", "Answer" ] }, "default": [] }, "maxPosts": { "title": "Max posts", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Total posts to collect across all targets. Deduplicated by post ID, so overlapping tags/queries never double-count.", "default": 50 }, "includeNotes": { "title": "Include notes", "type": "boolean", "description": "Request note details (notes_info + reblog_info) and emit a notes[] column. Note counts always come back; individual note bodies are NOT returned by Tumblr's keyless endpoints, so notes[] is usually null — see the README.", "default": false }, "downloadMedia": { "title": "Download media files", "type": "boolean", "description": "Download images and videos into the run's key-value store and reference them from each row's mediaFiles column. Files over 50 MB and third-party embeds are skipped. Billed per file downloaded.", "default": false }, "fullResMedia": { "title": "Resolve full-resolution media", "type": "boolean", "description": "Pick the largest available rendition of every image/video instead of Tumblr's small thumbnail. Uses inline srcset / NPF data where possible, and only falls back to fetching the post page when a post offers nothing better.", "default": true }, "includeRaw": { "title": "Include raw payload", "type": "boolean", "description": "Keep the untouched Tumblr object in a raw column for full fidelity. Turn off for smaller datasets.", "default": true }, "requestDelayMs": { "title": "Delay between requests (ms)", "minimum": 500, "maximum": 30000, "type": "integer", "description": "Hard floor between HTTP requests. Tumblr rate-limits per IP and starts returning 429 after bursts of 3-6 rapid requests, so values under 1000 ms are not recommended.", "default": 1100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings. Datacenter is enough for blog mode. For tag and search mode set a non-EU country (US) — Tumblr redirects its /v2/ pagination endpoints to an EU consent wall, which caps those modes at one page. Switch to RESIDENTIAL if you see repeated 429s.", "default": { "useApifyProxy": true, "apifyProxyGroups": [] } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }