{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor: Text, Pages and Metadata from PDF Links", "description": "Get the text of every PDF you link, page by page, with page count, language and word count. No OCR, no proxies, no login; robots.txt respected. You pay only for PDFs with readable text.", "version": "1.0", "x-build-id": "lTCLZfJO4EaiEiXTu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rowcraft~pdf-text-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rowcraft-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rowcraft~pdf-text-extractor/runs": { "post": { "operationId": "runs-sync-rowcraft-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rowcraft~pdf-text-extractor/run-sync": { "post": { "operationId": "run-sync-rowcraft-pdf-text-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "PDF links", "type": "array", "description": "Links to PDF files, one per line. With \"Collect PDF links from pages\" below you can also give web pages and the PDF links found on them are read. Duplicates and invalid entries are skipped and never charged.", "items": { "type": "string" } }, "collectPdfLinksFromPages": { "title": "Collect PDF links from pages", "type": "boolean", "description": "Treat every address above as a web page and read the PDF files it links to (links to .pdf files in the page's HTML). An address that turns out to be a PDF itself is read as a document.", "default": false }, "maxItems": { "title": "Maximum documents delivered", "minimum": 0, "type": "integer", "description": "Stop after this many documents with text are delivered. 0 = no limit. Documents without text (scans, password-protected files) are free and do not count.", "default": 0 }, "includePages": { "title": "Text of each page as a list", "type": "boolean", "description": "Add the field textByPage: one text per page, in page order, next to the full text. Useful to cite a page or to split the text for search and AI pipelines.", "default": false }, "pageSeparator": { "title": "Page separator in the full text", "enum": [ "marker", "formfeed" ], "type": "string", "description": "How pages are separated inside the field text: a marker line such as \"--- page 3 ---\" (default) or a form-feed character (\f) that code can split on.", "default": "marker" }, "maxPagesPerDocument": { "title": "Maximum pages per document", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Read at most this many pages of each PDF; a longer document is delivered with maxPagesReached = true and charged once. Default 200.", "default": 200 }, "maxFileMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "PDFs larger than this are not downloaded or charged and are listed in COVERAGE as too_large. Default 25. A run with little memory lowers the limit (reading a PDF takes several times its size); the run summary says so.", "default": 25 }, "maxPdfLinksPerPage": { "title": "PDF links read per page", "minimum": 1, "maximum": 1000, "type": "integer", "description": "With \"Collect PDF links from pages\": the first this many PDF links of each page are read, in page order. Default 50.", "default": 50 }, "onlyNew": { "title": "Only new rows since the last run", "type": "boolean", "description": "Remember the rows already delivered to you (in a key-value store in your Apify account) and deliver only rows that appeared since the last run with the same state key. The first run delivers everything that matches; later runs cost only the new rows. Ideal for schedules.", "default": false }, "stateName": { "title": "State name", "type": "string", "description": "Name of the memory used by \"Only new rows\". Use a different name for each schedule or search (for example `stockholm-python`) so they do not share one memory.", "default": "default" }, "notifyUrl": { "title": "Notify this URL when the run ends", "type": "string", "description": "A webhook address that receives one JSON POST with the number of new rows and links to the dataset: a Slack or Discord incoming webhook, a Make, n8n or Zapier catch hook, or your own endpoint. The message is also in the `text` (Slack) and `content` (Discord) fields." }, "notifyWhenEmpty": { "title": "Notify also when there are no new rows", "type": "boolean", "description": "By default the notification is sent only when at least one row was delivered.", "default": false }, "requestIntervalMs": { "title": "Delay between requests to one host (ms)", "minimum": 250, "maximum": 10000, "type": "integer", "description": "Default 1000 ms (one request per second to the same host; different hosts do not wait for each other). Each host is asked for robots.txt once. Minimum 250.", "default": 1000 } } }, "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 } } } } } } } } } }