{ "openapi": "3.0.1", "info": { "title": "OTTO.de Scraper - Products, Prices, Variants & Reviews", "description": "Scrape OTTO.de products by search or URL. Extract prices, discounts, variants, availability, brand, seller, EAN/GTIN, specifications, categories, and customer reviews across fashion, furniture, electronics, and homeware.", "version": "1.0", "x-build-id": "DCAwUdeEbJy1s9icr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abotapi~otto-de-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abotapi-otto-de-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abotapi~otto-de-scraper/runs": { "post": { "operationId": "runs-sync-abotapi-otto-de-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abotapi~otto-de-scraper/run-sync": { "post": { "operationId": "run-sync-abotapi-otto-de-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "'search' finds products by keyword or category name, with real site filters and sort. 'url' scrapes any product, search-result, or category page URL you paste, walking pagination forward automatically.", "default": "search" }, "searchTerm": { "title": "Search keyword or category name", "type": "string", "description": "Free-text keyword (e.g. 'ecksofa') or a category name (e.g. 'sofas', 'laptop', 'waschmaschine') to browse a whole listing -- both go through OTTO's own search route." }, "urls": { "title": "URLs to scrape", "uniqueItems": true, "type": "array", "description": "Paste OTTO search pages (.../suche//), category pages (.../moebel/sofas/ecksofas/), department hubs (.../moebel/), with optional ?sortiertnach= sort or ?marke=&preis= filters, or the internal /dundee/tilelist JSON route (o=offset starts mid-list = partial scope). Product pages (.../p/-/) are also accepted. Leaving this field untouched scrapes one example of each shape (see README). Rival alias: startUrls.", "default": [ "https://www.otto.de/suche/ecksofa/", "https://www.otto.de/moebel/sofas/ecksofas/", "https://www.otto.de/moebel/sofas/", "https://www.otto.de/suche/ecksofa/?sortiertnach=preis-aufsteigend", "https://www.otto.de/moebel/sofas/ecksofas/?sortiertnach=preis-aufsteigend", "https://www.otto.de/moebel/sofas/ecksofas/?marke=sit-more&preis=100-500", "https://www.otto.de/dundee/tilelist?rule=%28und.%28suchbegriff.ecksofa%29.%28~.%28v.1%29%29%29&sortiertnach=topseller&o=120", "https://www.otto.de/dundee/tilelist?rule=%28und.%28suchbegriff.ecksofa%29.%28~.%28v.1%29%29%29&sortiertnach=topseller", "https://otto.de/suche/ecksofa", "https://www.otto.de/technik/fernseher/", "https://www.otto.de/suche/laptop/?suchbegriff=laptop", "https://www.otto.de/moebel/" ], "items": { "type": "string" } }, "specialsOnly": { "title": "Specials / offers only", "type": "boolean", "description": "Keep only products currently showing a reduced price (strike-through original price + discount %). Narrows the same search/category listing, verified live -- combine with Sort = 'Highest discount' to surface the best offers first. No extra fetch.", "default": false }, "brands": { "title": "Brands", "uniqueItems": true, "type": "array", "description": "Only return products from these brands, e.g. '99rooms', 'Samsung', 'Jockenhöfer Gruppe'. Match the exact brand name as shown on the site. Leave empty for all brands.", "items": { "type": "string" } }, "minRating": { "title": "Minimum rating", "minimum": 1, "maximum": 5, "type": "integer", "description": "Only return products rated at or above this many stars, 1-5." }, "minPrice": { "title": "Minimum price (EUR)", "type": "number", "description": "Only return products priced at or above this amount, in euros." }, "maxPrice": { "title": "Maximum price (EUR)", "type": "number", "description": "Only return products priced at or below this amount, in euros." }, "sortBy": { "title": "Sort order", "enum": [ "RELEVANCE", "PRICE_ASC", "PRICE_DESC", "DISCOUNT", "NEWEST", "RATING" ], "type": "string", "description": "OTTO's own real sort order, applied server-side so paginated results stay correctly ordered across pages.", "default": "RELEVANCE" }, "fetchDetails": { "title": "Fetch full product detail", "type": "boolean", "description": "Adds the full breadcrumb category path, flattened technical specs, seller/partner identity (OTTO vs marketplace partner), EAN/GTIN/SKU, return policy, and full image gallery from the product detail page. Current price, was-price/discount, variant matrix and rating are already included without this toggle. A pasted product URL always fetches this page regardless of the toggle (it is the only source of that item's data) -- the toggle controls whether these extra fields are kept.", "default": false }, "fetchReviews": { "title": "Fetch reviews", "type": "boolean", "description": "Fetch each product's native customer reviews: overall rating, review count, and per-review author/location/date/rating/verified-purchase/title/body/helpful-votes. Products with no reviews simply return an empty list. Shares the same product-detail fetch as 'Fetch full product detail' when both are on.", "default": true }, "maxReviewsPerProduct": { "title": "Max reviews per product", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Cap on reviews fetched per product when 'Fetch reviews' is on. The detail page renders about a dozen; a higher cap reads further pages of OTTO's own review list. 0 = all reviews the product detail page renders.", "default": 10 }, "maxPages": { "title": "Max pages per search", "minimum": 0, "type": "integer", "description": "Stop after this many result-page fetches per search/category/URL entry. 0 (default) = no explicit limit -- the run walks the catalogue and stops at Max products total, or at an internal hard cap of 1000 pages per entry.", "default": 0 }, "maxItems": { "title": "Max products total", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Hard cap on total products returned across every search/category/URL entry. 0 = the maximum of 100000 (still bounded by Max pages per search).", "default": 20 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Governs the product listing/search connection, which works on every Apify plan including the free tier. The product detail and reviews fetch (on by default) always uses a residential connection at extra cost, regardless of this setting.", "default": { "useApifyProxy": true } }, "resumeFromRunId": { "title": "Resume from a previous run", "type": "string", "description": "Paste a previous run id (or its dataset id) to continue that run: products already collected there are skipped, so this run only returns new products (a delta). Leave empty for a normal run. For recurring daily/weekly 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 recurring monitoring. The first run returns all matching products as NEW. Later runs normally return only NEW, UPDATED, and REAPPEARED products. A product counts as UPDATED when any returned field changes (price, original price, availability, name, images, variants, and the detail and review fields when those are on), and changedFields names them; integral prices such as 25 and 25.0 are the same value. Nothing is excluded by default; use \"Ignore fields when detecting changes\" to leave out a noisy field. Turn on \"Emit unchanged\" or \"Emit expired\" only when you also want those products returned (and billed). State is kept separately for each search/URL and detail-mode setup; use State key when you want 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/URL and detail settings -- different searches then never mix state with each other." }, "emitUnchanged": { "title": "Emit unchanged products (incremental mode only)", "type": "boolean", "description": "Off by default. Turn on to also return products 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 the full snapshot every run.", "default": false }, "emitExpired": { "title": "Emit expired products (incremental mode only)", "type": "boolean", "description": "Off by default. Turn on to also return products 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 products capped it or when Resume was used. This returns -- and bills -- extra synthetic rows, so leave it off unless you need expiry tracking.", "default": false }, "ignoreFieldsForChanges": { "title": "Ignore fields when detecting changes (incremental mode only)", "type": "array", "description": "Optional. Top-level field names (for example promoLabel) to leave out of UPDATED change detection and out of changedFields, on top of the built-in handling. The field is still returned in the output. Use it when a field turns out to be noisy in your setup. Changing this list never causes a one-time wave of UPDATED rows.", "items": { "type": "string" } }, "mcpConnectors": { "title": "Pipe results into your apps (optional)", "type": "array", "description": "Optionally send the scraped results into the apps you already use, via Model Context Protocol (MCP) connectors. Authorize a connector once under Apify -> Settings -> Integrations, then select it here. The connector receives a condensed, human-readable summary per item (title + key fields), not the full JSON; the complete record stays in the dataset. Leave empty to skip. 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 item 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 items written to each connector per run. Does not affect the dataset.", "default": 50 } } }, "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 } } } } } } } } } }