{ "openapi": "3.0.1", "info": { "title": "News Site Article Archive", "description": "Name news sites and a past date range and get full article text, dates, and authors as rows. Walks sitemaps and the Internet Archive index across years. No code, no AI, no login. Paywalled pages are left out.", "version": "0.1", "x-build-id": "lnhUmpOrfzggFJhwW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mambalabs~news-site-article-archive/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mambalabs-news-site-article-archive", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mambalabs~news-site-article-archive/runs": { "post": { "operationId": "runs-sync-mambalabs-news-site-article-archive", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mambalabs~news-site-article-archive/run-sync": { "post": { "operationId": "run-sync-mambalabs-news-site-article-archive", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sites": { "title": "News sites", "type": "array", "description": "News sites by domain, for example techcrunch.com, up to 20.", "items": { "type": "string" } }, "date_from": { "title": "Date from", "type": "string", "description": "The earliest published date, as YYYY-MM-DD. Default: 30 days before Date to." }, "date_to": { "title": "Date to", "type": "string", "description": "The latest published date, as YYYY-MM-DD. Default: today." }, "max_articles_per_site": { "title": "Maximum articles per site", "type": "string", "description": "Articles to return from each site, up to 5,000. Default 100.", "default": "100" }, "url_contains": { "title": "Address contains", "type": "array", "description": "Optional. Keep only addresses with any of these texts, for example /politics/.", "items": { "type": "string" } }, "min_words": { "title": "Minimum words", "type": "string", "description": "Pages with fewer words are not counted as articles and are free. Default 80.", "default": "80" }, "use_archive_index": { "title": "Find addresses in the archive index", "type": "string", "description": "yes (default): when the sitemaps run out, also find addresses in the Internet Archive capture index, which reaches years that sitemaps no longer list. no: sitemaps only.", "default": "yes" }, "use_archive_copy": { "title": "Read archive copies of gone pages", "type": "string", "description": "yes (default): a page the site answers with 404, 410, 500, 502, or 504 is read from the Internet Archive, at the archived row price. Refused and paywalled pages are never read from an archive. no: gone pages return a free row.", "default": "yes" }, "obey_robots": { "title": "Obey robots.txt", "type": "string", "description": "yes (default): pages robots.txt disallows are skipped and counted. no: read them anyway.", "default": "yes" }, "max_charge_usd": { "title": "Maximum charge for this run (USD)", "type": "string", "description": "Optional. The run stops before a charge that would pass this amount. Summary rows are always returned." }, "source_tag": { "title": "Source tag", "type": "string", "description": "Internal attribution tag. Leave empty." } } }, "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 } } } } } } } } } }