{ "openapi": "3.0.1", "info": { "title": "Page Link Extractor: all links, anchor text, nofollow", "description": "Lists every link on the pages you give it, internal and external, with anchor text, rel values, nofollow, sponsored and ugc flags, target and image link alt text. Many pages in one run, one row per link or one row per page.", "version": "0.1", "x-build-id": "u4Ltiii9bOlQesoJi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/examsens.ai~page-link-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-examsens.ai-page-link-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/examsens.ai~page-link-extractor/runs": { "post": { "operationId": "runs-sync-examsens.ai-page-link-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/examsens.ai~page-link-extractor/run-sync": { "post": { "operationId": "run-sync-examsens.ai-page-link-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Page URLs", "type": "array", "description": "Pages to read, one per line. An address without http:// or https:// is read as https://. Redirects are followed.", "items": { "type": "string" } }, "linkTypes": { "title": "Links to return", "enum": [ "all", "internal", "external" ], "type": "string", "description": "Internal means the link's host matches the page's host, ignoring a leading www.", "default": "all" }, "outputFormat": { "title": "Output format", "enum": [ "links", "pages" ], "type": "string", "description": "Both cost the same: one event per page processed.", "default": "links" }, "uniqueLinksOnly": { "title": "One row per unique URL on a page", "type": "boolean", "description": "Merge repeated links to the same URL on a page into one row with an occurrences count.", "default": false }, "subdomainsAreInternal": { "title": "Count subdomains as internal", "type": "boolean", "description": "Treat links to subdomains of the page's host (and its parent host) as internal.", "default": false }, "removeFragments": { "title": "Remove #fragments from link URLs", "type": "boolean", "description": "Return https://site.com/page for https://site.com/page#section. The raw href is always kept.", "default": true }, "skipSamePageAnchors": { "title": "Skip links to a spot on the same page", "type": "boolean", "description": "Leave out links such as #top that point back to the page being read.", "default": true }, "includeNonHttpLinks": { "title": "Include mailto, tel and other non web links", "type": "boolean", "description": "Return mailto:, tel:, ftp: and similar links as type other. javascript: and data: links are always left out.", "default": false }, "timeoutSecs": { "title": "Timeout per page (seconds)", "minimum": 1, "maximum": 120, "type": "integer", "description": "How long to wait for each page.", "default": 20 }, "maxConcurrency": { "title": "Pages read at once", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many pages are read at the same time.", "default": 10 }, "userAgent": { "title": "User agent", "type": "string", "description": "The User-Agent header sent with every request. Leave empty to send Mozilla/5.0 (compatible; PageLinkExtractor/1.0)." } } }, "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 } } } } } } } } } }