{ "openapi": "3.0.1", "info": { "title": "SEO Metadata Auditor for Crawled Datasets", "description": "Audit titles, meta descriptions, H1s, canonicals, thin content and URLs straight from a crawl dataset you already have. No re-crawl.", "version": "0.1", "x-build-id": "6lc488yRMFrCiruLV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hiredhandai~seo-metadata-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hiredhandai-seo-metadata-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hiredhandai~seo-metadata-auditor/runs": { "post": { "operationId": "runs-sync-hiredhandai-seo-metadata-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hiredhandai~seo-metadata-auditor/run-sync": { "post": { "operationId": "run-sync-hiredhandai-seo-metadata-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "datasetId": { "title": "Crawl dataset", "type": "string", "description": "The dataset to audit, for example the output of a Website Content Crawler run. Pick it from your datasets, or pass its ID when calling the Actor through the API. Leave empty if you paste pages below. Tip: turn on Save Markdown in the crawler so headings (H1 checks) and word counts are available." }, "pages": { "title": "Pages (inline)", "type": "array", "description": "Up to 5,000 pages as a JSON array of objects, to try the Actor or for small API jobs. Use Crawl dataset for bigger ones. Common field names are detected automatically: url, title, description, canonical, h1, lang, statusCode, markdown, html, wordCount." }, "fieldMap": { "title": "Field mapping (optional)", "type": "object", "description": "Only needed if your crawler uses unusual field names. Map an audit field to your field name or dot path. Supported keys: url, title, description, canonical, statusCode, h1, headings, lang, robots, text, markdown, html, openGraph, twitter, images, depth, wordCount. Example: `{\"title\": \"meta.pageTitle\", \"url\": \"link\"}`." }, "siteUrl": { "title": "Site URL (optional)", "type": "string", "description": "The site's main address, for example https://www.example.com. Used to spot canonicals that point to another host. Default: the most common host in the dataset." }, "profile": { "title": "Strictness profile", "enum": [ "standard", "strict", "lenient" ], "type": "string", "description": "Thresholds for title and description length, thin content, URL length and depth. Standard follows common SEO guidance; Strict suits agencies and large sites; Lenient suits small or older sites.", "default": "standard" }, "rulesDisabled": { "title": "Rules to switch off", "type": "array", "description": "Rule codes to ignore, for example O005 (no twitter:card) or U006 (trailing slash mix). Disabled rules are not checked and do not affect the score. The full list of codes is in the README.", "items": { "type": "string" } }, "crawlIsComplete": { "title": "The crawl covers the whole site", "type": "boolean", "description": "Turn on only if the dataset contains every page of the site. Then a canonical that points to a page missing from the dataset (C008) is reported. Leave off for partial crawls to avoid false alarms.", "default": false }, "onlyStatusCodes": { "title": "Status codes to audit", "type": "string", "description": "Pages with these HTTP status codes get the full metadata checks; other pages only get a status issue (4xx/5xx errors, redirects). Use exact codes or classes, comma separated, for example `200` or `200,2xx,301`. Pages without a status field count as 200.", "default": "200" }, "includeUrlPatterns": { "title": "Only audit URLs matching", "type": "array", "description": "Regular expressions; a page is audited only if its URL matches at least one. Example: `/blog/`. Leave empty to audit everything. Pages that are skipped are neither audited nor charged.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Skip URLs matching", "type": "array", "description": "Regular expressions; pages whose URL matches any of them are skipped, audited by nobody and not charged. Example: `/tag/` or `\\?page=\\d+`.", "items": { "type": "string" } }, "analyzeContent": { "title": "Analyze page content", "type": "boolean", "description": "Counts words, flags thin content and finds pages with identical text. Turn off for a lighter, faster run on very large datasets.", "default": true }, "outputIssueFile": { "title": "Also write the issue list as CSV", "type": "boolean", "description": "Saves every issue as a CSV file (ISSUES_CSV) in the run's key-value store, ready for a spreadsheet.", "default": true }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Upper limit on pages read and audited (and therefore charged). The hard limit is 100,000 per run.", "default": 100000 } } }, "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 } } } } } } } } } }