{ "openapi": "3.0.1", "info": { "title": "SEO Site Audit Crawler: On-Page SEO, Broken Links & Redirects", "description": "Crawl a website with plain HTTP, respecting robots.txt, and audit every page: titles, meta descriptions, headings, canonicals, noindex, hreflang, structured data, alt text, broken links, redirect chains and duplicates. One row per page, a site summary and score, and alerts for new issues.", "version": "0.1", "x-build-id": "lT8zIDD6iadW9bhAh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/subtleasianmerch~seo-site-audit/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-subtleasianmerch-seo-site-audit", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/subtleasianmerch~seo-site-audit/runs": { "post": { "operationId": "runs-sync-subtleasianmerch-seo-site-audit", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/subtleasianmerch~seo-site-audit/run-sync": { "post": { "operationId": "run-sync-subtleasianmerch-seo-site-audit", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 pages", "type": "array", "description": "Where the crawl starts, usually a site's home page, e.g. https://www.example.com. \"example.com\" works too (https is added). Links are followed within the same site (www and non-www count as one). Several sites can be crawled in one run.", "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Pages per site", "minimum": 1, "maximum": 5000, "type": "integer", "description": "At most this many HTML pages are audited (and charged) per site, nearest the start page first. Redirects, error pages and files are listed too, free. A run audits at most 5,000 pages in all.", "default": 100 }, "sitemapUrls": { "title": "Sitemaps", "type": "array", "description": "Optional. Without any, the sitemaps listed in each site's robots.txt are read (or /sitemap.xml). XML, .xml.gz, text sitemaps and sitemap indexes work. A sitemap on its own (no start page) is fine too: its pages become the start pages.", "items": { "type": "string" } }, "sitemapPages": { "title": "Sitemap pages", "enum": [ "crawl", "compare", "ignore" ], "type": "string", "description": "What to do with the pages the sitemaps list. Crawl: after the linked pages, also audit sitemap pages no crawled page links to (orphan pages). Compare: only mark which pages are in the sitemap and list sitemap pages the crawl didn't reach. Ignore: don't read sitemaps.", "default": "crawl" }, "maxDepth": { "title": "Link depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "Optional. How many clicks from the start page to follow: 0 audits only the start pages, 1 adds the pages they link to, and so on. Empty: no limit (the page limit still applies)." }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Also crawl subdomains of the start page's site, e.g. blog.example.com and shop.example.com for example.com. Each subdomain's own robots.txt is respected.", "default": false }, "includePatterns": { "title": "Only addresses matching", "type": "array", "description": "Optional. Only crawl addresses that match one of these patterns. * stands for any characters, e.g. https://www.example.com/blog/*. A pattern without * matches addresses that contain it, e.g. /blog/. Start pages are always crawled.", "items": { "type": "string" } }, "excludePatterns": { "title": "Skip addresses matching", "type": "array", "description": "Optional. Don't crawl addresses that match one of these patterns (same rules as above), e.g. */tag/* or ?sort=.", "items": { "type": "string" } }, "removeTrackingParams": { "title": "Ignore tracking parameters", "type": "boolean", "description": "Treat /page?utm_source=x (and gclid, fbclid and similar) as /page, so one page isn't crawled many times. Other parameters are kept as they are.", "default": true }, "checkExternalLinks": { "title": "Check links to other sites", "type": "boolean", "description": "Also check whether links to other sites still work (status only, nothing is audited or charged there). Each site's robots.txt and pace are respected; a site that turns the check away (HTTP 401, 403, 429) is listed as \"refused\", not as broken.", "default": false }, "maxExternalLinks": { "title": "External links to check", "minimum": 1, "maximum": 5000, "type": "integer", "description": "With the option above: at most this many different external links are checked per run, in the order they were found.", "default": 300 }, "delayMs": { "title": "Pause between requests", "minimum": 250, "maximum": 60000, "type": "integer", "description": "Requests to a site go one at a time, with at least this pause after each answer (500 ms means at most 2 requests a second). If the site's robots.txt asks for a longer Crawl-delay, that is used instead. Sites in one run are crawled side by side.", "default": 500 }, "monitorId": { "title": "Monitor ID", "type": "string", "description": "Give scheduled runs the same ID (letters, digits and dashes) to compare each crawl with the last one: every row then says whether the page is new and which issues are new or fixed since the last run. Leave empty for one-off audits." } } }, "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 } } } } } } } } } }