{ "openapi": "3.0.1", "info": { "title": "Blog Archive Taxonomy Extractor", "description": "Extract blog/archive taxonomy, categories, tags, authors, dates, pagination, article URLs, and archive health from public blog index pages", "version": "1.0", "x-build-id": "drxmcxxphlp3g7Zs9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~blog-archive-taxonomy-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-blog-archive-taxonomy-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~blog-archive-taxonomy-extractor/runs": { "post": { "operationId": "runs-sync-junipr-blog-archive-taxonomy-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~blog-archive-taxonomy-extractor/run-sync": { "post": { "operationId": "run-sync-junipr-blog-archive-taxonomy-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "archiveUrls": { "title": "Archive page URLs", "type": "array", "description": "Public blog archive, category, or author-index URLs.", "items": { "type": "string" }, "default": [] }, "startUrls": { "title": "Additional archive URLs", "type": "array", "description": "Optional public archive URLs; archiveUrls is preferred for role clarity.", "items": { "type": "string" }, "default": [] }, "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "Optional public XML sitemap URLs. Accepted pages remain bounded by maxArchivePages.", "items": { "type": "string" }, "default": [] }, "htmlInputs": { "title": "Captured archive HTML", "type": "array", "description": "Optional records with sourceUrl and html or currentHtml for deterministic extraction.", "items": { "type": "object" }, "default": [] }, "followPagination": { "title": "Follow rel-next pagination", "type": "boolean", "description": "Follow only same-domain rel=next links, bounded by maxDepth and maxArchivePages.", "default": false }, "extractAuthors": { "title": "Extract authors", "type": "boolean", "description": "Extract visible author names when present in archive entries.", "default": true }, "extractTags": { "title": "Extract categories and tags", "type": "boolean", "description": "Extract visible category and tag labels when present.", "default": true }, "extractDates": { "title": "Extract publish and update dates", "type": "boolean", "description": "Extract visible publish or update dates when present.", "default": true }, "maxArchivePages": { "title": "Maximum archive pages", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum archive pagination pages to inspect.", "default": 1 }, "maxArticles": { "title": "Maximum articles per archive page", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum article links to extract from archive pages.", "default": 100 }, "allowedDomains": { "title": "Allowed domains", "type": "array", "description": "Optional hostname allowlist for fetched pages.", "items": { "type": "string" }, "default": [] }, "maxPages": { "title": "Maximum fetched pages", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum pages to fetch in one run.", "default": 1 }, "maxDepth": { "title": "Pagination depth", "minimum": 0, "maximum": 1, "type": "integer", "description": "Maximum same-domain pagination depth to follow from the start URL.", "default": 0 }, "includeEvidence": { "title": "Include evidence", "type": "boolean", "description": "Include short source evidence snippets in output rows.", "default": true }, "includeRawSnapshots": { "title": "Store raw snapshots", "type": "boolean", "description": "Opt in to raw HTML artifacts in key-value storage.", "default": false }, "requestDelayMs": { "title": "Request delay in milliseconds", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Delay in milliseconds between outbound page requests.", "default": 250 }, "timeoutMs": { "title": "Request timeout in milliseconds", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Maximum time in milliseconds to wait for a page request.", "default": 15000 }, "userAgentMode": { "title": "User-agent mode", "enum": [ "standard", "browser" ], "type": "string", "description": "User agent profile to use for public page requests.", "default": "standard" }, "maxChargeUsd": { "title": "Maximum charge", "minimum": 0, "maximum": 15, "type": "number", "description": "Maximum estimated PPE spend before the actor exits gracefully.", "default": 15 }, "includeReport": { "title": "Write reports", "type": "boolean", "description": "Write the markdown summary report to the run key-value store.", "default": true } } }, "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 } } } } } } } } } }