{ "openapi": "3.0.1", "info": { "title": "PDF & Office Document Accessibility Auditor - DocA11y", "description": "PDF & Office document accessibility auditor: crawl a website, list every PDF, Word, PowerPoint and Excel file, run PDF/UA and WCAG 2.1 machine checks.", "version": "1.0", "x-build-id": "5TeNQj8gNLDE9vYXB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leons0016~document-accessibility-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leons0016-document-accessibility-auditor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leons0016~document-accessibility-auditor/runs": { "post": { "operationId": "runs-sync-leons0016-document-accessibility-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leons0016~document-accessibility-auditor/run-sync": { "post": { "operationId": "run-sync-leons0016-document-accessibility-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "crawl", "urls" ], "type": "string", "description": "Crawl finds documents for you. URL list audits only the files you give. The prefill uses the URL list with five sample files. Example: crawl.", "default": "crawl" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Pages where the crawl starts, usually your home page. Example: https://www.cityofexample.gov/. Up to 50 (1 on the Apify free plan).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "documentUrls": { "title": "Document URLs", "maxItems": 5000, "type": "array", "description": "Mode 'Audit these document URLs' only. One link per line, up to 5,000. The prefill is five synthetic sample files hosted by the publisher for a self-test. Example: https://www.cityofexample.gov/files/budget-2027.pdf.", "default": [], "items": { "type": "string" } }, "useSitemap": { "title": "Use sitemap.xml", "type": "boolean", "description": "Also reads /sitemap.xml and the sitemaps listed in robots.txt. Sitemap pages count towards the page limit.", "default": true }, "documentTypes": { "title": "Document types", "type": "array", "description": "File types to audit. Old .doc, .ppt and .xls files are always listed as legacy formats but never audited. Example: pdf and docx.", "items": { "type": "string", "enum": [ "pdf", "docx", "pptx", "xlsx" ] }, "default": [ "pdf", "docx", "pptx", "xlsx" ] }, "maxPages": { "title": "Max HTML pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Pages fetched to find documents. Example: 1000. The Apify free plan crawls at most 100.", "default": 1000 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many links away from a start URL the crawl may go. 0 means start pages only. Example: 6.", "default": 6 }, "maxDocuments": { "title": "Max documents to audit", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Stops auditing after this many documents in one run. Example: 2000. The Apify free plan audits at most 10.", "default": 2000 }, "includeGlobs": { "title": "Only follow URLs matching", "type": "array", "description": "If not empty, only pages whose URL matches are followed. * and ** match any characters. Example: https://www.example.gov/departments/**.", "default": [], "items": { "type": "string" } }, "excludeGlobs": { "title": "Never fetch URLs matching", "type": "array", "description": "Pages and documents whose URL matches are never fetched. Example: **/calendar/** keeps the crawl out of endless calendar pages.", "default": [ "**/calendar/**", "**?print=*" ], "items": { "type": "string" } }, "allowedDomains": { "title": "Also allow documents from", "type": "array", "description": "Other host names that may hold your documents, such as a CDN. Pages on these hosts are not crawled; only documents are fetched. Example: docs.example.gov.", "default": [], "items": { "type": "string" } }, "maxDocumentSizeMb": { "title": "Max document size", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are listed but not audited and not charged. Example: 50.", "default": 50 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Recommended. Switching this off needs the permission box below.", "default": true }, "iAmAuthorised": { "title": "I own this site or have permission to audit it", "type": "boolean", "description": "Required to switch off robots.txt. You are responsible for the crawl. The delay between requests to one host stays at 0.5 seconds or more.", "default": false }, "complianceDate": { "title": "Compliance date", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Your accessibility deadline as YYYY-MM-DD. Example: 2027-04-26 (ADA Title II, 50,000 or more people) or 2028-04-26 (smaller entities), as published at the time of writing.", "default": "2027-04-26" }, "archivePathHints": { "title": "Archive paths", "type": "array", "description": "URL path parts that hold archived content, which may fall under an exception. Example: /archive.", "default": [ "/archive", "/archives", "/minutes/20", "/agenda-archive" ], "items": { "type": "string" } }, "standard": { "title": "PDF standard", "enum": [ "ua1" ], "type": "string", "description": "The PDF/UA profile that veraPDF checks. PDF/UA-2 and WTPDF are planned for a later version.", "default": "ua1" }, "onlyNewOrChanged": { "title": "Only audit new or changed documents", "type": "boolean", "description": "Uses the history of this task, so schedules only pay for what changed. Turn off to audit everything again (charged).", "default": true }, "maxResultsPerRun": { "title": "Max results per run", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stops auditing after this many document results. The rest is audited in the next run. Example: 5000.", "default": 5000 }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "Optional. The run summary (OUTPUT) is posted here as JSON when the run ends. Example: https://hooks.example.com/doca11y." }, "slackWebhookUrl": { "title": "Slack incoming webhook", "type": "string", "description": "Optional. A short Slack message with the top documents is posted when the run ends." }, "includePassedDocuments": { "title": "Include documents without failures", "type": "boolean", "description": "Push an item for documents with 0 failed checks too. They are charged either way, because the audit was done.", "default": true }, "stateKey": { "title": "State key", "pattern": "^[A-Za-z0-9._-]{1,64}$", "type": "string", "description": "Share the audit history between tasks or keep it apart. Letters, digits, dot, dash, underscore. Example: city-website." }, "perDocumentTimeoutSecs": { "title": "Time limit per document", "minimum": 30, "maximum": 600, "type": "integer", "description": "A document that takes longer is reported as not parsable and is not charged. Example: 120.", "default": 120 }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many pages and documents are handled at the same time. Lower it for slow sites. Example: 4.", "default": 4 }, "userAgentSuffix": { "title": "User-Agent suffix", "pattern": "^[A-Za-z0-9 ._:/+@-]{0,40}$", "type": "string", "description": "Optional text added to the User-Agent so that site owners can recognise your audit. Example: audit-for-city-it." }, "debugKeepRaw": { "title": "Keep raw veraPDF output", "type": "boolean", "description": "Saves the raw veraPDF JSON of failed PDFs as VERAPDF- records in the key-value store, for support and debugging.", "default": false } } }, "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 } } } } } } } } } }