{ "openapi": "3.0.1", "info": { "title": "PDF Harvester", "description": "Finds PDFs linked from a list of URLs and extracts their text and metadata — point it at pages, not PDF links.", "version": "0.1", "x-build-id": "lhXgjDmoY9lPMbbSP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/openrows~pdf-harvester/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-openrows-pdf-harvester", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/openrows~pdf-harvester/runs": { "post": { "operationId": "runs-sync-openrows-pdf-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/openrows~pdf-harvester/run-sync": { "post": { "operationId": "run-sync-openrows-pdf-harvester", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "URLs", "type": "array", "description": "Pages to scan for linked PDFs. A URL that is itself a PDF is also accepted and extracted directly. You choose the sources and are responsible for them (see the README's Data and compliance section).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxDepth": { "title": "Link-following depth", "minimum": 0, "maximum": 1, "type": "integer", "description": "0: only scan the given URLs for PDF links. 1: also follow same-host links found on those pages, one level deep, and scan those pages for PDF links too. No other values are used.", "default": 0 }, "extractText": { "title": "Extract text", "type": "boolean", "description": "Read each PDF's text content. Page count and metadata (producer, created, modified) are always read; turning this off skips only the (slower) per-page text extraction, so text comes back null.", "default": true }, "maxTextLength": { "title": "Max text length per PDF", "minimum": 100, "maximum": 1000000, "type": "integer", "description": "Truncate each PDF's extracted text to this many characters. Ignored when Extract text is off.", "default": 20000 }, "maxItems": { "title": "Max results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop after this many PDFs are extracted. You are charged per result, so this is also your cost cap. Maximum 10,000 per run; split a bigger job across runs.", "default": 100 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy settings. Apify datacenter proxies are the default and are enough for most targets.", "default": { "useApifyProxy": true } }, "maxPdfs": { "title": "Max PDFs to fetch", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on how many PDFs this run will process once confirmed to actually be a PDF (by content, not just by URL). A link that looked like a PDF but wasn't, or that robots.txt disallowed, does not count against this cap. Keeps a large, PDF-heavy site from being fetched beyond what Max results actually needs.", "default": 100 }, "maxPdfSizeBytes": { "title": "Max PDF size", "minimum": 1, "type": "integer", "description": "PDFs larger than this are skipped (counted under skipped.filteredOut in the run summary) rather than downloaded and parsed in full.", "default": 20971520 }, "maxRequestsPerCrawl": { "title": "Max pages to fetch", "minimum": 1, "type": "integer", "description": "Hard cap on pages fetched while looking for PDF links (separate from Max PDFs to fetch). Defaults to a formula based on the number of URLs given and Max PDFs to fetch." } } }, "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 } } } } } } } } } }