{ "openapi": "3.0.1", "info": { "title": "Smart Fetch - URL to Markdown from US, Singapore, EU or Taiwan", "description": "Fetch any public URL as clean Markdown, HTML and JSON metadata. Pick the region it is fetched from (US, Singapore, EU, Taiwan residential) or let Auto switch region when a site blocks. JavaScript rendering, robots.txt respected, failed pages free. From $1/1,000 pages.", "version": "0.1", "x-build-id": "i7E3uPDgO4Q7iR0N4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidytools~smart-fetch/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidytools-smart-fetch", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidytools~smart-fetch/runs": { "post": { "operationId": "runs-sync-tidytools-smart-fetch", "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/tidytools~smart-fetch/run-sync": { "post": { "operationId": "run-sync-tidytools-smart-fetch", "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", "properties": { "urls": { "title": "URLs", "type": "array", "description": "Pages to fetch, one per line: full URLs or bare domains like example.com. Up to 50,000 per run. Invalid lines become a result row with errorType \"invalid_input\" (not charged) instead of failing the run.", "items": { "type": "string" } }, "region": { "title": "Fetch from (region)", "enum": [ "auto", "cf", "us", "sg", "eu", "tw" ], "type": "string", "description": "Where the request leaves from. Auto (recommended): Cloudflare HTTP first; a JavaScript shell goes straight to a browser, while a blocked HTTP page tries our US server before a browser. A chosen region fetches only from there (turn on \"Try other regions\" to fall back). HTTP pages delivered from US, Singapore, EU or Taiwan add the region fee; browser pages do not.", "default": "auto" }, "mode": { "title": "Page fetching", "enum": [ "auto", "http", "browser" ], "type": "string", "description": "Auto: plain HTTP first; a short JavaScript shell goes straight to a browser. With region Auto, our Taiwan Chrome pool takes over when Cloudflare Browser Rendering is busy or at the 9-hour monthly cap. HTTP: never a browser. Browser: always render, from Cloudflare (Auto or Cloudflare) or our Taiwan residential Chrome (Taiwan); US, Singapore and Europe do not support Browser. A page is charged as a browser page only when the browser result is used.", "default": "auto" }, "includeMarkdown": { "title": "Markdown", "type": "boolean", "description": "Clean Markdown of the page (PDF, Word and Excel files too) with a YAML header (title, description, image).", "default": true }, "includeHtml": { "title": "HTML", "type": "boolean", "description": "The page's HTML as received (or as rendered in browser mode), up to 2,000,000 characters.", "default": false }, "includeLinks": { "title": "Links", "type": "boolean", "description": "All absolute links on the page in metadata.links.", "default": false }, "respectRobots": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that the site's robots.txt disallows for our user agent TidyToolsSmartFetch (errorType robots_disallowed, not charged).", "default": true }, "tryOtherRegions": { "title": "Try other regions when blocked", "type": "boolean", "description": "Leave unset for the default: on for Auto, off for a chosen region. On: when the chosen region is refused, Cloudflare, US and Taiwan are tried too." }, "removeBoilerplate": { "title": "Remove navigation, header and footer", "type": "boolean", "description": "Leave site navigation, cookie banners, headers and footers out of the Markdown.", "default": true }, "mainContent": { "title": "Main content only", "type": "boolean", "description": "Convert only the page's main element (article / main) when it is unambiguous. Falls back to the whole page when that is nearly empty.", "default": false }, "waitUntil": { "title": "Browser: wait until", "enum": [ "load", "domcontentloaded", "networkidle2" ], "type": "string", "description": "When a browser page counts as loaded.", "default": "load" }, "timeoutSecs": { "title": "Time limit per network (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "How long one attempt may take before the next region is tried.", "default": 30 }, "maxConcurrency": { "title": "Parallel URLs", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many URLs are fetched at the same time.", "default": 5 }, "maxTokens": { "title": "Markdown token limit", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Return at most this many tokens of Markdown (about 4 characters per token for Latin text, one per CJK character). The Markdown is cut at a blank-line boundary so a block is never split in half; the row's nextStartIndex is where to continue (pass it as startIndex in the next run). Leave empty for the whole page." }, "startIndex": { "title": "Start at character", "minimum": 0, "maximum": 50000000, "type": "integer", "description": "Return the Markdown from this character offset onward (a page you got earlier via nextStartIndex). 0 means the start of the page.", "default": 0 }, "links": { "title": "Links in Markdown", "enum": [ "inline", "footnotes", "none" ], "type": "string", "description": "How links appear in the Markdown. Inline keeps [text](url). Footnotes moves the URLs to numbered [^n] notes at the end. None keeps the link text only.", "default": "inline" }, "images": { "title": "Images in Markdown", "enum": [ "all", "alt", "none" ], "type": "string", "description": "How images appear in the Markdown. Keep images leaves ![alt](url) as is; Alt text only keeps the image's alt text; None drops the images.", "default": "all" }, "query": { "title": "Keep blocks matching a query", "type": "string", "description": "Rank the Markdown blocks with BM25 against this query and keep only the most relevant ones (up to Blocks kept for a query), in the original page order. No AI model is used. Leave empty to keep the whole page." }, "queryMaxBlocks": { "title": "Blocks kept for a query", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many blocks the query keeps (the most relevant ones, in page order).", "default": 5 }, "startUrls": { "title": "URL list files (optional)", "type": "array", "description": "Upload or link .txt/.csv files of URLs (every http(s) URL in a file is read). Full URLs only here.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }