{ "openapi": "3.0.1", "info": { "title": "The Guardian Article Search & Archive Scraper", "description": "Search The Guardian's full article archive (2.6M+ articles since 1999). Filter by query, section, tag, contributor, date, or production office. Returns headline, byline, body, tags, contributors, and publication metadata.", "version": "0.0", "x-build-id": "5Py51mci4jPtyBo98" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~guardian-content-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-guardian-content-search-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~guardian-content-search-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-guardian-content-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~guardian-content-search-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-guardian-content-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Search Query", "type": "string", "description": "Free-text search across The Guardian's archive. Supports operators: AND, OR, NOT, quoted phrases. Leave empty to browse the latest articles.", "default": "" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Free users: Limited to 10 items (preview). Paid users: Optional, max 1,000,000" }, "sectionCaptionFilters": { "title": "Filters", "type": "string", "description": "Refine the search by section, tag, contributor, date, or production office." }, "section": { "title": "Section Filter", "enum": [ "all", "world", "uk-news", "us-news", "australia-news", "politics", "business", "money", "technology", "science", "environment", "sport", "football", "culture", "books", "music", "film", "tv-and-radio", "stage", "fashion", "lifeandstyle", "food", "travel", "media", "education", "society", "law", "global-development", "opinion", "commentisfree", "artanddesign", "games" ], "type": "string", "description": "Pick one section. Choose 'all' to search every section.", "default": "all" }, "tag": { "title": "Tag Filter", "type": "string", "description": "Filter by tag (e.g. 'environment/climate-change', 'football/premierleague', 'profile/jonathan-freedland'). Use comma to combine.", "default": "" }, "fromDate": { "title": "From Date", "type": "string", "description": "Earliest publication date (YYYY-MM-DD). Articles older than this are excluded." }, "toDate": { "title": "To Date", "type": "string", "description": "Latest publication date (YYYY-MM-DD). Articles newer than this are excluded." }, "productionOffice": { "title": "Production Office", "enum": [ "any", "uk", "us", "aus", "int" ], "type": "string", "description": "Edition responsible for the article: UK, US, AU, or international.", "default": "any" }, "orderBy": { "title": "Sort Order", "enum": [ "newest", "oldest", "relevance" ], "type": "string", "description": "Sort articles by newest, oldest, or relevance to the search query.", "default": "newest" }, "lang": { "title": "Language", "type": "string", "description": "Limit to articles in a specific language code (en, fr, es, de, ar, etc.).", "default": "" }, "starRating": { "title": "Minimum Star Rating", "minimum": 1, "maximum": 5, "type": "integer", "description": "Only include reviews with this minimum star rating (1-5). Best for film, TV, music, restaurant reviews." }, "includeBodyText": { "title": "Include Full Body Text", "type": "boolean", "description": "Include the article's full body text and HTML in each record. Disable for lighter records.", "default": true }, "includeBlocks": { "title": "Include Liveblog Blocks", "type": "boolean", "description": "Include the structured 'blocks' object (liveblog updates, body blocks, embedded media) for each article. Useful for liveblog scraping.", "default": false }, "includeReferences": { "title": "Include References", "type": "boolean", "description": "Include the article's external reference IDs (ISBN, MusicBrainz, IMDb, etc.) when present.", "default": false }, "includeRights": { "title": "Include Syndication Rights", "type": "boolean", "description": "Include each article's syndication and reuse rights metadata.", "default": false } } }, "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 } } } } } } } } } }