{ "openapi": "3.0.1", "info": { "title": "ASOS Scraper - Products, Prices & Stock", "description": "Scrape ASOS by keyword, category or URL. Every row carries the selling price and the original price, the discount, brand, colour and selling-fast flags. Sizes, per-size stock and reviews are one toggle away. Recurring change tracking is first-class.", "version": "0.1", "x-build-id": "bCpC4qBoEX39L24WG" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abotapi~asos-com-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abotapi-asos-com-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abotapi~asos-com-scraper/runs": { "post": { "operationId": "runs-sync-abotapi-asos-com-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abotapi~asos-com-scraper/run-sync": { "post": { "operationId": "run-sync-abotapi-asos-com-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "search", "url" ], "type": "string", "description": "How to start the scrape. 'search' runs store searches. 'url' processes the store URLs you paste: a product URL is fetched as a single product, and a search or category URL is paged like a search, its own query or category deciding the scope. The filters below apply to every walk in both modes; a pasted product URL is the one exception and returns that single product in full.", "default": "search" }, "searchTerms": { "title": "Search terms", "type": "array", "description": "One or more things to search ASOS for, for example 'midi dress', 'slim jeans', 'white trainers'. Each term is scraped independently. Search mode only: in URL mode the scope is read out of each pasted URL instead. Leave this empty and the run browses with only the filters applied.", "default": [ "midi dress" ], "items": { "type": "string" } }, "urls": { "title": "ASOS URLs", "type": "array", "description": "Paste product URLs (https://www.asos.com/brand/product-name/prd/0000001, the short https://www.asos.com/prd/0000001 form works too), search URLs (https://www.asos.com/search/?q=midi+dress) or category URLs (https://www.asos.com/women/dresses/cat/?cid=8799). A pasted URL decides its own scope. Add &page=3 (search URLs) or &offset=48 (category URLs) to start the walk further in; a product URL ignores paging and returns that one product in full. The filters below narrow what the walks read: the brand, colour and ordering filters are sent to the store with every page, and the price bounds and Discounted rows only are applied to the rows this run reads.", "items": { "type": "string" } }, "brandIds": { "title": "Brand ids", "type": "array", "description": "Only these brands, as the store's own numeric brand ids, for example 15370 (Bershka). Comma-tolerant: the store accepts a list and returns the union. The id is in each row's brandId field, so scrape any product once to look an id up. Applies in BOTH search mode and URL mode.", "items": { "type": "string" } }, "baseColourIds": { "title": "Colour ids", "type": "array", "description": "Only these base colours, as the store's own numeric colour ids, for example 12 or a list like 10,12. The id is the store's internal base-colour token; each row carries its colour name, so verify an id with a one-row run before a large one. Applies in BOTH search mode and URL mode.", "items": { "type": "string" } }, "sortBy": { "title": "Sort the store's results by", "enum": [ "relevance", "freshness", "priceasc", "pricedesc" ], "type": "string", "description": "The store's own server-side ordering, sent with every page of every walk. This orders the walk itself (and therefore which rows a capped run keeps), not just the output. Applies in BOTH search mode and URL mode.", "default": "relevance" }, "minPrice": { "title": "Minimum price (GBP)", "minimum": 0, "type": "integer", "description": "Only keep rows whose selling price is at least this many pounds. The store has no parameter for this, so it is applied to the rows this run reads. Applies in BOTH search mode and URL mode." }, "maxPrice": { "title": "Maximum price (GBP)", "minimum": 0, "type": "integer", "description": "Only keep rows whose selling price is at most this many pounds. The store has no parameter for this, so it is applied to the rows this run reads. Applies in BOTH search mode and URL mode." }, "onSaleOnly": { "title": "Discounted rows only", "type": "boolean", "description": "Only keep rows whose selling price is below the original price, that is rows with a discount. The store has no parameter for this, so it is applied to the rows this run reads. Applies in BOTH search mode and URL mode.", "default": false }, "fetchDetails": { "title": "Fetch product details", "type": "boolean", "description": "Fetch each item's product page for the description, the full size list (brand size and store size), and per-size stock availability including low-stock and restocking flags. Slower, and charged once per record. Leave off for a fast crawl: identity, prices, discount, brand and colour are included either way, without a stock state (the store does not serve one on its listing cards).", "default": false }, "fetchReviews": { "title": "Fetch reviews", "type": "boolean", "description": "Fetch each item's customer reviews: the rating summary (average, count and the Fit/Quality score breakdown) and the most recent reviews up to Max reviews per product. Slower, and charged once per record under the same details surcharge (never twice, even with Fetch product details also on). Leave off by default.", "default": false }, "maxReviewsPerProduct": { "title": "Max reviews per product", "minimum": 1, "maximum": 100, "type": "integer", "description": "Cap on review rows returned per product when Fetch reviews is on. The store serves one reviews page per product to automated readers, so this is a cap, not a pagination promise: rows beyond it are not fetched.", "default": 10 }, "maxItems": { "title": "Max items", "minimum": 0, "type": "integer", "description": "The single cap on this run: stop after collecting this many records across all search terms and URLs. Set 0 for unlimited.", "default": 20 }, "maxPages": { "title": "Max pages per source", "minimum": 0, "type": "integer", "description": "Safety bound on how many result pages to walk per search term or URL. Leave empty (0) for no page limit: the run then stops at Max items, not here. Does not impose a separate cap below Max items.", "default": 0 }, "resumeFromRunId": { "title": "Resume from a previous run", "type": "string", "description": "Paste a previous run ID or dataset ID to continue a large crawl without returning or charging for records already collected there. Use this after an interrupted or capped run. For recurring monitoring of the same search, use Incremental mode below instead." }, "incrementalMode": { "title": "Incremental changes for scheduled runs", "type": "boolean", "description": "Turn this on for daily or weekly recurring monitoring of the same search, for example a price watch. The first run returns everything matching as NEW. Later runs normally return only NEW, UPDATED and REAPPEARED records. Price moves and stock changes ARE reported as UPDATED: on a store they are the signal, not noise. Turn on Emit unchanged or Emit expired only when you also want those rows returned (and billed). State is kept separately per search, URL and filter setup; use State key to name or deliberately share a monitoring campaign. To continue one specific interrupted run instead, use Resume from a previous run above.", "default": false }, "stateKey": { "title": "State key (optional, incremental mode only)", "type": "string", "description": "Optional. Name this monitoring campaign to keep its state stable, or to deliberately share state across differently configured runs. Leave empty to let the actor derive a key automatically from the search terms, URLs and filters, so two different searches never mix state." }, "emitUnchanged": { "title": "Emit unchanged records (incremental mode only)", "type": "boolean", "description": "Off by default. Turn on to also return records that have not changed since the last run, marked UNCHANGED. This returns, and bills, extra rows you already have, so leave it off unless you specifically want a full snapshot every run.", "default": false }, "emitExpired": { "title": "Emit expired records (incremental mode only)", "type": "boolean", "description": "Off by default. Turn on to also return records that were present in a previous run but are no longer found, marked EXPIRED. Only produced once a run has fully scanned the tracked search: not when Max items capped it, not when Resume was used, and not when the run was refused. This returns, and bills, extra synthetic rows, so leave it off unless you need expiry tracking.", "default": false }, "mcpConnectors": { "title": "Pipe results into your apps (optional)", "type": "array", "description": "Optionally send results into the apps you already use, via Model Context Protocol (MCP) connectors. Authorize one under Apify, Settings, API & Integrations, then select it here. Notion gets a page per record; other connectors get a best-effort write or digest. Each connector receives a condensed summary per record, not the full record; the complete record always stays in the dataset. Leave empty to skip; this never changes the dataset output. Supported: Notion (https://mcp.notion.com/mcp), Linear (https://mcp.linear.app/sse), Airtable (https://mcp.airtable.com/mcp), Apify (https://mcp.apify.com)." }, "notionParentPageUrl": { "title": "Notion parent page (Notion connector only)", "type": "string", "description": "URL or id of the Notion page under which record pages are created. Required to enable the Notion export; ignored by other connectors." }, "maxNotifyListings": { "title": "Max items to export per connector", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Cap on records written to each connector per run. Does not affect the dataset.", "default": 50 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Leave the default for the cheapest run. The store serves ordinary shared connections, so the default pool is enough. Change it only if a run reports that it could not read any results.", "default": { "useApifyProxy": 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 } } } } } } } } } }