{ "openapi": "3.0.1", "info": { "title": "Original Source Finder - Syndicated Article & Canonical Checker", "description": "For AI agents citing news: give article URLs (Yahoo, MSN, dev.to, AP/Reuters reprints) and get the original source, the original URL or news agency, with every clue, a confidence and a same-article check. On 37 pages with a known answer, 35 were right and none named a wrong source.", "version": "0.1", "x-build-id": "sU5xyhldVcqbcDPtx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neverempty~original-source-finder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neverempty-original-source-finder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neverempty~original-source-finder/runs": { "post": { "operationId": "runs-sync-neverempty-original-source-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neverempty~original-source-finder/run-sync": { "post": { "operationId": "run-sync-neverempty-original-source-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Article URLs", "type": "array", "description": "Article pages to check (1 to 1,000 per run), for example a Yahoo News, Yahoo Finance, MSN, dev.to or Medium copy, a news site running an AP or Reuters story, or an AMP / Google News link. Each URL gets one row: the original article URL when the page names one, or the original publisher or news agency when only a name is given, with every clue as evidence. If this and the single URL field are both empty, an example dev.to cross-post is checked.", "items": { "type": "string" } }, "url": { "title": "Single article URL (optional)", "type": "string", "description": "For checking one page without a list. Added to Article URLs if both are given." }, "verifyOriginal": { "title": "Open the original page to confirm it is the same article", "type": "boolean", "description": "When the page names an original article URL, read that page too (respecting its robots.txt) and compare the headline and the opening text, so the row says originVerified true (same article), false (the named page is a different article) or null (could not be read or not conclusive). Rows where the original page was read and compared are charged as source-verified; turn this off to only read the page you give (source-checked).", "default": true }, "onlyChanges": { "title": "Monitor: return only URLs whose answer changed", "type": "boolean", "description": "Return a row only when the original-source answer for a URL differs from the last run of the same watch (for example a page that later adds a canonical link or an attribution). The first run of a watch returns every URL. A changed answer is read a second time before it is reported.", "default": false }, "watchName": { "title": "Watch name (monitor)", "type": "string", "description": "Name of the watch whose results are remembered between runs (letters, digits, dot, dash, underscore; up to 40). Setting it turns on monitor mode; use different names for different lists." }, "resetMonitoringState": { "title": "Forget what this watch remembered", "type": "boolean", "description": "Start the watch over: this run treats every URL as a first check.", "default": false }, "maxConcurrency": { "title": "Pages read at the same time", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many URLs are handled in parallel (1 to 8). Requests to the same site still follow its robots.txt Crawl-delay.", "default": 4 }, "requestTimeoutSecs": { "title": "Time limit per request (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "How long to wait for one page to answer (5 to 60). A page that does not answer is asked again up to two more times.", "default": 20 } } }, "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 } } } } } } } } } }