{ "openapi": "3.0.1", "info": { "title": "PDF Extractor API: Text, Markdown, Tables, No Login", "description": "Extract text from public PDF URLs: plain text, Markdown, tables, links, outline, page count and metadata per PDF or per page, with scanned pages flagged. $2 per 1,000 PDFs ($1.60 on Starter). Failed files are free. No login.", "version": "0.0", "x-build-id": "kw6gXQggrUUi6Vdgt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/conserving_celerytop~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-conserving_celerytop-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/conserving_celerytop~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-conserving_celerytop-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/conserving_celerytop~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-conserving_celerytop-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", "properties": { "pdfUrls": { "title": "PDF URLs", "type": "array", "description": "Add the public web addresses of PDF files, one per line. Each PDF becomes one dataset row (or one row per page, see Row per).", "items": { "type": "string" } }, "listDatasetId": { "title": "Dataset with the list", "type": "string", "description": "Pick an Apify Dataset that holds your PDF addresses, one entry per item. They are added to the entries typed above." }, "listDatasetField": { "title": "Field in the dataset", "type": "string", "description": "Name of the dataset field that holds the entry. Leave empty to use the first text field it finds." }, "listFileUrl": { "title": "List file URL", "type": "string", "description": "Web address of a .txt, .csv or .json file with your PDF addresses, one entry per line. A header row is skipped. Up to 10 MB." }, "rowPer": { "title": "Row per", "enum": [ "document", "page" ], "type": "string", "description": "Choose one row per PDF (full text, tables, links and metadata together) or one row per page (text and tables of each page, for page citations and chunking).", "default": "document" }, "includeText": { "title": "Plain text", "type": "boolean", "description": "Return the plain text in reading order, with line breaks as in the PDF and a form feed between pages.", "default": true }, "includeMarkdown": { "title": "Markdown", "type": "boolean", "description": "Return Markdown with headings, lists and tables, with running headers, footers and page numbers removed. Ready for LLMs and RAG pipelines.", "default": true }, "extractTables": { "title": "Tables", "type": "boolean", "description": "Detect tables and return each one as rows of cells, in addition to the Markdown table.", "default": true }, "saveFiles": { "title": "Save .txt and .md files", "type": "boolean", "description": "Also save each PDF's text and Markdown as files in the key-value store, linked in textFileUrl and markdownFileUrl (with Row per: Document). Very long documents are always saved this way.", "default": false }, "maxPdfs": { "title": "Maximum PDFs", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Read at most this many PDFs from the list.", "default": 1000 }, "maxPagesPerPdf": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Read at most this many pages of each PDF, starting from page 1. The row says truncated: true when a PDF has more.", "default": 500 }, "maxFileSizeMegabytes": { "title": "Maximum file size", "minimum": 1, "maximum": 200, "type": "integer", "description": "Download PDFs up to this size. Larger files return status too_large and are free. For files over 50 MB, give the run 2 GB of memory or more.", "default": 50 }, "maxConcurrency": { "title": "Parallel PDFs", "minimum": 1, "maximum": 10, "type": "integer", "description": "Read up to this many PDFs at the same time (at most 2 per website). Lowered automatically when large files would not fit in the run's memory.", "default": 3 }, "downloadTimeoutSecs": { "title": "Download timeout", "minimum": 5, "maximum": 600, "type": "integer", "description": "Wait this long for one PDF download before retrying (3 attempts).", "default": 90 } } }, "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 } } } } } } } } } }