{ "openapi": "3.0.1", "info": { "title": "SEC Document Content Extractor", "description": "Extract bounded, reproducible text, table, XML, and data blocks from confirmed public SEC filing documents.", "version": "0.1", "x-build-id": "O8w0FBudpp8Zm6Oqy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bb-tradetec~sec-document-content-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bb-tradetec-sec-document-content-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bb-tradetec~sec-document-content-extractor/runs": { "post": { "operationId": "runs-sync-bb-tradetec-sec-document-content-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bb-tradetec~sec-document-content-extractor/run-sync": { "post": { "operationId": "run-sync-bb-tradetec-sec-document-content-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "queries" ], "properties": { "queries": { "title": "C03-confirmed document queries", "minItems": 1, "maxItems": 20, "type": "array", "description": "One to twenty exact C03-compatible document identities with bounded extraction options.", "items": { "type": "object", "additionalProperties": false, "required": [ "requestId", "accession", "filerCik", "filename" ], "properties": { "requestId": { "title": "Request ID", "description": "Caller correlation ID; never a secret.", "editor": "textfield", "type": "string", "minLength": 1, "maxLength": 128, "pattern": "^[A-Za-z0-9._:-]+$" }, "accession": { "title": "Exact EDGAR accession", "description": "Confirmed accession from the C03 manifest candidate.", "editor": "textfield", "type": "string", "pattern": "^\\d{10}-\\d{2}-\\d{6}$" }, "filerCik": { "title": "Filer CIK", "description": "Confirmed filer CIK from the C03 manifest candidate.", "editor": "textfield", "type": "string", "pattern": "^\\d{1,10}$" }, "filename": { "title": "C03-confirmed archive filename", "description": "Flat filename from the C03 manifest candidate; never a URL.", "editor": "textfield", "type": "string", "minLength": 1, "maxLength": 255, "pattern": "^[A-Za-z0-9][A-Za-z0-9._-]*$" }, "expectedSha256": { "title": "Expected SHA-256", "description": "Optional expected document digest.", "editor": "textfield", "type": "string", "pattern": "^[0-9a-f]{64}$" }, "blockTypes": { "title": "Block types", "description": "Optional controlled block-type allowlist.", "editor": "json", "type": "array", "default": [], "maxItems": 12, "uniqueItems": true, "items": { "type": "string", "pattern": "^(heading|paragraph|table|xmlElement|text|csvSchema|csvRow|jsonObject|pdfPage|worksheet|worksheetRow)$" } }, "headingPatterns": { "title": "Heading patterns", "description": "Optional bounded heading filters interpreted only by a later parser package.", "editor": "json", "type": "array", "default": [], "maxItems": 20, "uniqueItems": true, "items": { "type": "string", "minLength": 1, "maxLength": 200 } }, "maxDocumentBytes": { "title": "Maximum document bytes", "description": "Per-document hard download ceiling.", "editor": "number", "type": "integer", "minimum": 1, "maximum": 52428800, "default": 10485760 }, "maxBlocks": { "title": "Maximum blocks", "description": "Per-document hard block ceiling.", "editor": "number", "type": "integer", "minimum": 1, "maximum": 5000, "default": 500 }, "maxCharactersPerBlock": { "title": "Maximum characters per block", "description": "Per-block hard character ceiling.", "editor": "number", "type": "integer", "minimum": 1, "maximum": 100000, "default": 20000 }, "includeRawMarkup": { "title": "Include raw markup", "description": "Off by default; a later parser applies the 2 MiB aggregate cap.", "editor": "checkbox", "type": "boolean", "default": false } } } }, "maxResults": { "title": "Maximum content blocks", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard run-wide output ceiling.", "default": 100 }, "maxSourceRequests": { "title": "Maximum SEC source requests", "minimum": 1, "maximum": 100, "type": "integer", "description": "Hard run-wide SEC request ceiling.", "default": 100 }, "maxDownloadBytes": { "title": "Maximum downloaded bytes", "minimum": 1, "maximum": 104857600, "type": "integer", "description": "Hard run-wide byte ceiling.", "default": 104857600 }, "outputSchemaVersion": { "title": "Output schema version", "enum": [ "1.0" ], "type": "string", "description": "Only stable schema 1.0 is supported.", "default": "1.0" }, "outputMode": { "title": "Output mode", "enum": [ "full", "compact" ], "type": "string", "description": "Full or compact output shape.", "default": "full" }, "cursor": { "title": "Continuation cursor", "minLength": 1, "maxLength": 32768, "type": "string", "description": "Opaque cursor reserved for a later service package." } } }, "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 } } } } } } } } } }