{ "openapi": "3.0.1", "info": { "title": "Website SEO Spider — On-Page Crawl Export", "description": "Crawl a public website and export one on-page SEO row per URL (title, meta, H1, canonical, indexability, inlinks, issue flags). Use for site crawls and scheduled audits. Pair with broken-link-checker or complete-seo-audit. Charged $0.01 per page crawled.", "version": "0.1", "x-build-id": "mMtR5WJwhZJ35dNXV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/khadinakbar~website-seo-spider/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-khadinakbar-website-seo-spider", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/khadinakbar~website-seo-spider/runs": { "post": { "operationId": "runs-sync-khadinakbar-website-seo-spider", "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/khadinakbar~website-seo-spider/run-sync": { "post": { "operationId": "run-sync-khadinakbar-website-seo-spider", "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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Public website URLs where the crawl begins. Example: https://example.com. Same-host or same-domain links are followed up to maxPages. This is not a list of already-known broken links — for that inventory use broken-link-checker.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlScope": { "title": "Crawl scope", "enum": [ "same-hostname", "same-domain", "page-only" ], "type": "string", "description": "Which internal links to follow from each HTML page. same-hostname stays on the exact host; same-domain also follows subdomains; page-only fetches the start URLs and stops. Defaults to same-hostname. This does not control off-site outbound counts, which are always recorded.", "default": "same-hostname" }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Hard cap on HTML/HTTP pages fetched in this run. Example: 10. Default 100, maximum 2000. Prefill 10 keeps the quality sample fast. When in-scope URLs remain at this cap, the run finishes PARTIAL. This is a page budget, not a broken-link check limit.", "default": 100 }, "maxDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many link hops from a start URL the crawler may follow. 0 means unlimited within maxPages. Default 10, prefill 3. Depth 0 is the start URL itself. This is not a sitemap-only mode — enable seedFromSitemap to add sitemap URLs as extra starts.", "default": 10 }, "seedFromSitemap": { "title": "Seed from sitemap", "type": "boolean", "description": "When true, read robots.txt Sitemap: entries and /sitemap.xml, then add those URLs to the crawl queue up to maxPages. Defaults to false. Useful for coverage beyond the homepage link graph. This is not a sitemap validator — URLs are crawled for on-page SEO, not merely listed.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "When true, skip paths disallowed for the crawler user-agent in robots.txt. Defaults to true. Turn off only for sites you are authorized to audit beyond the public robots policy. This setting applies to HTML crawl enqueue, not to a separate link-checker pass.", "default": true }, "ignoreUrlParameters": { "title": "Ignore URL parameters", "type": "boolean", "description": "When true, strip query strings before uniqueness so /page and /page?ref=nav count as one URL. Defaults to false, matching typical desktop spider defaults. Enable for tracking-parameter cleanup. This does not rewrite canonical tags on the page.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel HTTP requests. Default 10, prefill 5, maximum 50. Lower this when the target rate-limits. This is request parallelism, not a browser-tab count — the crawler is HTTP-only.", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify proxy. Leave off for the default direct HTTP path. Enable datacenter or residential when the site rate-limits your IP. This is not a login session or cookie jar." } } }, "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 } } } } } } } } } }