{ "openapi": "3.0.1", "info": { "title": "Scientific Table and Footnote Extractor", "description": "Extract scientific tables, cells, units, and explicit footnotes from authorized HTML and born-digital PDF sources.", "version": "0.1", "x-build-id": "yMmlG3dMMFiwNmmOn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/flintglade~scientific-table-footnote-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-flintglade-scientific-table-footnote-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/flintglade~scientific-table-footnote-extractor/runs": { "post": { "operationId": "runs-sync-flintglade-scientific-table-footnote-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/flintglade~scientific-table-footnote-extractor/run-sync": { "post": { "operationId": "run-sync-flintglade-scientific-table-footnote-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sources" ], "properties": { "inputSchemaVersion": { "title": "Input schema version", "minimum": 1, "maximum": 1, "type": "integer", "description": "Versioned runtime contract.", "default": 1 }, "sources": { "title": "Explicit authorized sources", "minItems": 1, "maxItems": 50, "type": "array", "description": "Provide 1-50 explicit HTTPS URLs or user-selected KVS records. Every source requires a rights basis.", "items": { "type": "object", "additionalProperties": false, "properties": { "url": { "title": "Explicit URL", "description": "One public or user-authorized HTTPS HTML/PDF URL.", "type": "string", "maxLength": 2048 }, "kvsRecord": { "title": "KVS record", "description": "One explicitly selected key-value-store record.", "type": "object", "additionalProperties": false, "properties": { "key": { "title": "Record key", "description": "Exact record key to read without store enumeration.", "type": "string", "minLength": 1, "maxLength": 256, "pattern": "^[A-Za-z0-9!_.-]+$" }, "storeId": { "title": "Store ID", "description": "Optional authorized store ID; omit for the run's default store.", "type": "string", "maxLength": 128 } }, "required": [ "key" ] }, "rightsBasis": { "title": "Rights basis", "description": "Required user declaration supporting authorized processing.", "type": "object", "additionalProperties": false, "properties": { "type": { "title": "Basis type", "description": "The user's authorization category; this is not a legal conclusion.", "type": "string", "enum": [ "user_owned", "open_license", "public_domain", "permission" ] }, "evidence": { "title": "Basis evidence", "description": "Concise evidence supporting the declaration.", "type": "string", "minLength": 3, "maxLength": 500 } }, "required": [ "type", "evidence" ] }, "formatHint": { "title": "Format", "description": "Expected media; runtime detection must agree.", "type": "string", "enum": [ "html", "pdf" ] }, "tableSelectors": { "title": "HTML table selectors", "description": "Optional bounded CSS selectors that must select table elements.", "type": "array", "minItems": 1, "maxItems": 20, "items": { "type": "string", "maxLength": 200 } }, "pageRanges": { "title": "PDF page ranges", "description": "Optional one-based inclusive page ranges.", "type": "array", "minItems": 1, "maxItems": 50, "items": { "type": "object", "additionalProperties": false, "properties": { "start": { "title": "Start page", "description": "First one-based page.", "type": "integer", "minimum": 1, "maximum": 1000 }, "end": { "title": "End page", "description": "Last one-based page.", "type": "integer", "minimum": 1, "maximum": 1000 } }, "required": [ "start", "end" ] } } }, "required": [ "rightsBasis", "formatHint" ] } }, "includeFootnotes": { "title": "Include footnotes", "type": "boolean", "description": "Retain explicit and nearby footnotes without inventing links.", "default": true }, "retainRaw": { "title": "Retain raw values", "type": "boolean", "description": "Write a separate raw-value KVS artifact for each admitted table.", "default": false }, "maxBytesPerSource": { "title": "Maximum bytes per source", "minimum": 1024, "maximum": 100000000, "type": "integer", "description": "Oversized sources are refused and uncharged.", "default": 50000000 }, "maxPdfPages": { "title": "Maximum PDF pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "PDFs over this cap are refused before table extraction.", "default": 200 }, "concurrency": { "title": "Source concurrency", "minimum": 1, "maximum": 2, "type": "integer", "description": "Bounded parallel source processing.", "default": 1 } } }, "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 } } } } } } } } } }