{ "openapi": "3.0.1", "info": { "title": "Website Content Crawler — Text, Markdown & AI Chunks", "description": "Extract text or clean Markdown from public HTML websites. Create source-linked sections for AI knowledge bases while keeping one row per page. Preserve headings, code and tables; inspect a crawl report for failed URLs and truncated content. No JavaScript rendering.", "version": "0.3", "x-build-id": "OubAhp8DSbTe3pmmk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/agency-shift~web-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-agency-shift-web-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/agency-shift~web-content-crawler/runs": { "post": { "operationId": "runs-sync-agency-shift-web-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/agency-shift~web-content-crawler/run-sync": { "post": { "operationId": "run-sync-agency-shift-web-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start URLs", "type": "array", "description": "Public HTML page URLs. Use specific articles or documentation pages for the first test. JavaScript is not rendered; pages with no usable HTML content are flagged in both the dataset and crawl report.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Crawl request budget. Use 3 for the three-page example. Concurrent requests can slightly exceed this number; failures can leave fewer results. Check the crawl report for unprocessed inputs.", "default": 10 }, "followLinks": { "title": "Follow same-domain links", "type": "boolean", "description": "Discover same-domain links from the original HTML, including navigation, header and footer links, before text cleanup. The crawl request budget still applies; this does not guarantee complete website coverage.", "default": false }, "maxTextLength": { "title": "Max text length per page", "minimum": 500, "type": "integer", "description": "Maximum text characters stored per page. The output flags truncated text so you can increase this value when needed.", "default": 20000 }, "useProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Optional Apify datacenter proxy. Leave off for the documentation example. It does not render JavaScript or guarantee access to blocked sites.", "default": false }, "exportFormat": { "title": "Content export", "enum": [ "text", "markdown", "markdown-and-chunks" ], "type": "string", "description": "Always retains legacy text fields and one diagnostic dataset row per fetched page. Omitted API field defaults to text; choose markdown-and-chunks for a knowledge base. Inspect contentUsable and RUN_SUMMARY before using results. No AI model, embeddings or browser rendering is called.", "default": "text" }, "maxMarkdownLength": { "title": "Maximum Markdown characters per page", "minimum": 500, "maximum": 1000000, "type": "integer", "description": "Applies only to Markdown/chunks. Stops at a block boundary when possible; a single first block larger than the limit is cut and flagged. Chunks include only this retained Markdown. Check markdownTruncated and the crawl report.", "default": 100000 }, "chunkMaxCharacters": { "title": "Target chunk characters", "minimum": 300, "maximum": 12000, "type": "integer", "description": "Applies to Markdown and chunks. Groups blocks within each heading section. Code, tables and long paragraphs stay intact, so a chunk can exceed this target; oversized chunks are flagged. This is a character target, not a token limit.", "default": 2000 }, "contentSelector": { "title": "Main content CSS selector (optional)", "maxLength": 200, "type": "string", "description": "Applies only to Markdown/chunks. Leave blank to choose a semantic main/article or common documentation container, falling back to body. Set a CSS selector for a known page layout; if it matches nothing, that page fails visibly. When multiple elements match, the largest text container is selected.", "default": "" } } }, "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 } } } } } } } } } }