{ "openapi": "3.0.1", "info": { "title": "PDF Text Extractor - Watch PDFs and Get Only What Changed", "description": "For watching published price lists, tariffs, timetables and terms, and for feeding RAG pipelines: PDF links in, text out, one row per PDF with page count, title, author and dates. The IRS W-9 gave 21,855 characters on 2026-09-07. Watch the same URLs and a PDF returns only when its text changed.", "version": "0.1", "x-build-id": "ZIPrkcyiCoPCHtnkf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neverempty~pdf-text-extractor-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neverempty-pdf-text-extractor-monitor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neverempty~pdf-text-extractor-monitor/runs": { "post": { "operationId": "runs-sync-neverempty-pdf-text-extractor-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neverempty~pdf-text-extractor-monitor/run-sync": { "post": { "operationId": "run-sync-neverempty-pdf-text-extractor-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "PDF URLs", "type": "array", "description": "Direct links to the PDF files you want read. Anything that is not a PDF is reported as such rather than returned as empty text. If this and the paste box below are both left empty, two example PDFs (IRS Form W-9 and arXiv 1706.03762) are read and a free row says so. If the two example PDFs are still here when you paste your own URLs below, they are skipped and not charged.", "items": { "type": "string" } }, "urlsText": { "title": "PDF URLs (paste, one per line)", "type": "string", "description": "The same thing, as a block you can paste. Both fields are merged and duplicates are dropped.", "default": "" }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Password for protected PDFs. A protected PDF with no password is reported as password-required and is not charged.", "default": "" }, "pageRange": { "title": "Page range", "type": "string", "description": "Which pages to read, for example 1-5 or 2 or 1-3,7. Empty means every page.", "default": "" }, "maxPagesPerPdf": { "title": "Maximum pages per PDF", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Stop after this many pages in each PDF. 0 = no limit.", "default": 0 }, "maxPdfs": { "title": "Maximum PDFs per run", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many of the given URLs to read in this run.", "default": 25 }, "maxPdfSizeMb": { "title": "Maximum PDF size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "A PDF larger than this is reported with its actual size instead of being downloaded in full.", "default": 50 }, "timeoutPerPdfSecs": { "title": "Timeout per PDF (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Give up on a single PDF after this many seconds. The other PDFs in the run are still returned.", "default": 30 }, "includeFullText": { "title": "Full text", "type": "boolean", "description": "Return the whole document as one text field.", "default": true }, "includePerPageText": { "title": "Per-page text", "type": "boolean", "description": "Also return an array with the text of each page separately.", "default": false }, "removeRepeatedLines": { "title": "Remove repeated headers and footers", "type": "boolean", "description": "Drops lines that appear on 70% or more of the pages, which is what a running header or footer looks like. Only applies to documents of 3 pages or more.", "default": true }, "minCharCount": { "title": "Minimum characters", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Skip a PDF whose extracted text is shorter than this. 0 = keep everything.", "default": 0 }, "keywords": { "title": "Keywords", "type": "array", "description": "Keep only PDFs whose text, title, subject or author contains these. Empty = keep everything.", "default": [], "items": { "type": "string" } }, "keywordMatch": { "title": "Keyword match", "enum": [ "any", "all" ], "type": "string", "description": "any = contains at least one of them. all = contains every one of them.", "default": "any" }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Drop a PDF if its text contains any of these.", "default": [], "items": { "type": "string" } }, "monitoringMode": { "title": "Monitoring mode: return a PDF only when it has changed", "type": "boolean", "description": "Reads the same URLs again and returns a PDF only when its text is different from the last run. The first run returns everything and remembers it. Unchanged PDFs are not returned and not charged, so a daily watch on a price list, a timetable or a set of terms costs nothing on the days nothing moved.", "default": false }, "resetMonitoringState": { "title": "Forget what was already returned", "type": "boolean", "description": "Clears the memory so the next monitoring run treats every PDF as new.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many PDFs to download at the same time.", "default": 5 } } }, "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 } } } } } } } } } }