{
"openapi": "3.0.1",
"info": {
"title": "PDF Text Extractor",
"description": "Extract the text of PDF files from their web addresses. For each PDF you get the full text, optional text per page, page count, document data (title, author, dates), word count and a flag for scanned PDFs. Paste a list or link a text file.",
"version": "1.0",
"x-build-id": "7YrGetHInGytzFgGe"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/cyber1nj3ct0r~pdf-text-extractor/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-cyber1nj3ct0r-pdf-text-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/cyber1nj3ct0r~pdf-text-extractor/runs": {
"post": {
"operationId": "runs-sync-cyber1nj3ct0r-pdf-text-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/cyber1nj3ct0r~pdf-text-extractor/run-sync": {
"post": {
"operationId": "run-sync-cyber1nj3ct0r-pdf-text-extractor",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"pdfUrls"
],
"properties": {
"pdfUrls": {
"title": "PDF web addresses",
"minItems": 1,
"type": "array",
"description": "The addresses of the PDF files, for example https://www.example.com/report.pdf. Add them one by one, paste many at once with Bulk edit, or link a text file (or a Google Sheet published as CSV) that holds them. Duplicates are read once. Only these addresses are fetched; the tool follows no links.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"includePages": {
"title": "Text of each page",
"type": "boolean",
"description": "Add the text of every page as a separate entry (page number, text, number of characters) next to the full text. Useful when you need to say on which page something stands. Makes the results about twice as large.",
"default": false
},
"maxPagesPerPdf": {
"title": "Maximum pages per PDF",
"minimum": 1,
"maximum": 500,
"type": "integer",
"description": "Only the first pages of a longer PDF are read, and the result says so. Reading a page takes the same effort in every PDF, so this limit keeps the price per PDF fair. Raise it (up to 500) for longer reports; a PDF longer than 500 pages is read up to page 500.",
"default": 100
},
"maxFileSizeMb": {
"title": "Maximum file size",
"minimum": 1,
"maximum": 1000,
"type": "integer",
"description": "PDF files larger than this are not downloaded fully and come back with the error FILE_TOO_LARGE. A run with the default memory (1024 MB) reads files up to about 70 MB; for larger ones start the run with more memory.",
"default": 50
},
"maxPdfs": {
"title": "Maximum number of PDFs",
"minimum": 1,
"type": "integer",
"description": "Read at most this many PDFs from your list, in the order of the list. Leave empty to read all of them."
},
"password": {
"title": "Password for protected PDFs",
"type": "string",
"description": "Only needed for PDFs that ask for a password to open. The same password is tried on every PDF in the run. It is stored encrypted and never saved in the results. PDFs with a password and no password given come back with the error PASSWORD_REQUIRED."
},
"requestTimeoutSecs": {
"title": "Time limit per download",
"minimum": 5,
"maximum": 600,
"type": "integer",
"description": "How long to wait for one PDF to download completely before counting it as not answering.",
"default": 60
}
}
},
"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
}
}
}
}
}
}
}
}
}
}