{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler", "description": "Website content crawler for RAG and LLMs: each page as clean Markdown, menus and footers removed, optional chunks. $3 per 1,000 saved pages ($2.10 on Business); refused and failed pages are free. HTML only: no JavaScript rendering, proxy or PDF. Max 5,000 pages per website.", "version": "0.1", "x-build-id": "F3zsPuoVyi1hw7bjh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pumpkinapi~website-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pumpkinapi-website-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/pumpkinapi~website-content-crawler/runs": { "post": { "operationId": "runs-sync-pumpkinapi-website-content-crawler", "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/pumpkinapi~website-content-crawler/run-sync": { "post": { "operationId": "run-sync-pumpkinapi-website-content-crawler", "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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites to crawl", "type": "array", "description": "One address per line: a whole website (example.com), a section (https://example.com/docs/) or single pages. Addresses of the same website are crawled together. Crawl scope below says how far the crawl goes from them.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages per website", "minimum": 1, "maximum": 5000, "type": "integer", "description": "The crawl of one website stops after reading this many pages. You pay only for the pages it saves, so this also caps the cost of each website: copies of another page and pages without text of their own are read but not saved. Up to 5,000.", "default": 1000 }, "crawlScope": { "title": "Crawl scope", "enum": [ "path", "site", "pages" ], "type": "string", "description": "Which pages the crawl takes. Pages under the start address: https://example.com/docs/ reads only pages whose path starts with /docs/. Whole website: every page of the same website, www or not. Only the start addresses: reads the given pages and follows no links.", "default": "path" }, "splitIntoChunks": { "title": "Split text into chunks", "type": "boolean", "description": "Save each page as several rows of up to Chunk size characters, ready for embeddings and a vector database. Each chunk keeps the headings above it, tables are cut between rows with the header row repeated. You still pay per page, not per chunk.", "default": false }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 400, "maximum": 20000, "type": "integer", "description": "The longest a chunk may be, in characters. About 4 characters make one token in English text.", "default": 1500 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Each chunk after the first starts with up to this many characters from the end of the chunk before it, cut at a word, a table row or a line of code. At most a quarter of the chunk size. 0 means no overlap.", "default": 0 }, "removeRepeatedText": { "title": "Remove menus, footers and banners", "type": "boolean", "description": "Text blocks found on at least half of the pages of a website (and on at least 3) are taken out of every page and saved once, in a row of type shared. A website in several languages is counted language by language, and each language gets its own shared row. A website of up to 3 pages keeps every page whole. Turn off to keep every page as it is.", "default": true }, "removeElementsCssSelector": { "title": "Remove HTML elements (CSS selector)", "type": "string", "description": "Elements matching this CSS selector are left out of the text, besides scripts, styles, forms and buttons, which are always left out (a FAQ question on a button stays). The default leaves out navigation menus. Clear it to keep them.", "default": "nav, [role=\"navigation\"]" }, "keepElementsCssSelector": { "title": "Keep only HTML elements (CSS selector)", "type": "string", "description": "Optional. Only the elements matching this CSS selector are read, for example main or article, and the rest of the page is left out. A page where nothing matches has no text and is not saved or charged. Empty reads the whole page.", "default": "" }, "includeUrls": { "title": "Only pages whose address contains", "type": "array", "description": "Optional. A found page is read only when its address contains one of these, in any case. * stands for anything, for example /blog/ or /docs/*/guide. Start addresses are always read.", "default": [], "items": { "type": "string" } }, "excludeUrls": { "title": "Skip pages whose address contains", "type": "array", "description": "Optional. A found page is skipped when its address contains one of these, in any case. * stands for anything, for example /tag/ or ?page=. Skipped pages are not downloaded.", "default": [], "items": { "type": "string" } }, "useSitemaps": { "title": "Use sitemaps", "type": "boolean", "description": "After the links run out, also read the pages listed in the website's sitemaps (from robots.txt, or /sitemap.xml and the usual places) that no link led to. They follow the same scope and filters.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip the pages the website's robots.txt does not allow, and wait as long as its Crawl-delay asks, up to 10 seconds. Turn off only for a website you own or may crawl anyway.", "default": true } } }, "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 } } } } } } } } } }