{ "openapi": "3.0.1", "info": { "title": "Article Extractor: Paywall, Split Pages & Tables", "description": "Extracts article text and Markdown, and reports three things other extractors stay quiet about: a paywall that cut the body short, an article that continues on later pages, and tables and links that plain-text output destroys.", "version": "0.1", "x-build-id": "mBLEKkQU8hMgrUTKA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/aiqlabs~article-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-aiqlabs-article-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/aiqlabs~article-extractor/runs": { "post": { "operationId": "runs-sync-aiqlabs-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/aiqlabs~article-extractor/run-sync": { "post": { "operationId": "run-sync-aiqlabs-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Article URLs", "type": "array", "description": "Article, blog post or news pages to extract. Full URLs (https://example.com/post) or bare hosts both work, and one entry may hold several URLs separated by newlines, commas or spaces.", "items": { "type": "string" } }, "followSplitPages": { "title": "Follow articles split across pages", "type": "boolean", "description": "When a page declares a continuation (rel=\"next\", or a \"Page 2 of 5\" style pager), fetch the rest and return one merged body. The repeated header and footer of each part are removed before merging.", "default": true }, "maxPagesPerArticle": { "title": "Maximum parts per article", "minimum": 1, "maximum": 50, "type": "integer", "description": "Upper bound on how many continuation pages one article may pull in, so a mislabelled pager cannot walk a whole site.", "default": 10 }, "outputFormats": { "title": "Body formats to return", "type": "array", "description": "Which representations of the body to include. Markdown keeps tables, links, lists, quotes and code; text is plain reading order; html is the cleaned article HTML.", "items": { "type": "string", "enum": [ "markdown", "text", "html" ], "enumTitles": [ "Markdown", "Plain text", "Cleaned HTML" ] }, "default": [ "markdown", "text" ] }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that robots.txt disallows. The URL is still reported, with the rule that blocked it, instead of being dropped silently.", "default": true }, "skipTruncatedByPaywall": { "title": "Drop bodies a paywall cut short", "type": "boolean", "description": "Leave partial articles out of the dataset instead of returning them. Off by default so the finding stays visible; turn it on when the output feeds a corpus that must not contain half articles.", "default": false }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many articles to fetch at the same time. Lower this for small servers.", "default": 8 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for one response before giving up on it.", "default": 20 }, "maxUrls": { "title": "Maximum URLs", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on how many input URLs are processed in one run, counted after duplicates are removed.", "default": 5000 }, "maxHtmlKbPerPage": { "title": "HTML read limit per page (KB)", "minimum": 64, "maximum": 32768, "type": "integer", "description": "How much of each page's HTML to read. Raise it if a row reports \"html_read_limit_reached\" — that means the end of the document, and anything in it, was cut off. Lower it to cap memory on very large crawls.", "default": 6144 } } }, "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 } } } } } } } } } }