{
"openapi": "3.0.1",
"info": {
"title": "Checked PDF Table Extractor",
"description": "PDFs and scans to CSV/Excel tables plus a validation report that flags wrong totals, broken computed columns, unparsed numbers and low-confidence OCR, so you know which numbers to trust.",
"version": "0.0",
"x-build-id": "fxQfFeXwAeelVtflV"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/jyinnovation~checked-pdf-table-extractor/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-jyinnovation-checked-pdf-table-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/jyinnovation~checked-pdf-table-extractor/runs": {
"post": {
"operationId": "runs-sync-jyinnovation-checked-pdf-table-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/jyinnovation~checked-pdf-table-extractor/run-sync": {
"post": {
"operationId": "run-sync-jyinnovation-checked-pdf-table-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"properties": {
"files": {
"title": "PDF / image URLs",
"type": "array",
"description": "Links to PDF, PNG, JPG or TIFF files (public documents). Add one URL per line. You can also use the upload field below.",
"items": {
"type": "string"
}
},
"fileUpload": {
"title": "Or upload a file",
"type": "string",
"description": "Upload one PDF or image instead of (or in addition to) URLs."
},
"pages": {
"title": "Pages (optional)",
"type": "string",
"description": "Which pages to process, e.g. 1-3,5 or 4-. Empty = all pages. Applies to every file."
},
"ocr": {
"title": "OCR",
"enum": [
"auto",
"always",
"never"
],
"type": "string",
"description": "auto: OCR only pages that have no text layer (scans). always: OCR every page (useful when the text layer is garbled). never: skip pages without a text layer. OCR pages cost more than text pages.",
"default": "auto"
},
"ocrLanguage": {
"title": "OCR language",
"type": "string",
"description": "Tesseract language code. Installed: eng, deu, fra, spa. Combine with +, e.g. eng+deu.",
"default": "eng"
},
"mergeMultiPageTables": {
"title": "Merge tables continued across pages",
"type": "boolean",
"description": "Join a table that continues on the next page when its header repeats or the columns line up. Repeated header rows are removed and reported.",
"default": true
},
"outputFormats": {
"title": "Output formats",
"type": "array",
"description": "Files saved per table in the run's key-value store. The dataset always contains the table rows and checks; REPORT.html and REPORT.json are always created.",
"items": {
"type": "string",
"enum": [
"csv",
"xlsx",
"json"
],
"enumTitles": [
"CSV",
"Excel (XLSX)",
"JSON"
]
},
"default": [
"csv",
"xlsx"
]
},
"numberLocale": {
"title": "Number format",
"enum": [
"auto",
"us",
"eu"
],
"type": "string",
"description": "auto decides per table. us = 1,234.56. eu = 1.234,56. Negatives like (1,234.00) and 45- are understood; currency signs and % are removed.",
"default": "auto"
},
"maxPages": {
"title": "Maximum pages per run",
"minimum": 1,
"maximum": 5000,
"type": "integer",
"description": "Safety cap on the number of pages processed (and billed) in one run, across all files.",
"default": 200
}
}
},
"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
}
}
}
}
}
}
}
}
}
}