{ "openapi": "3.0.1", "info": { "title": "GoWork Scraper - Companies, Reviews, Ratings & Contacts", "description": "Extract company profiles from GoWork France and Germany, including contact details, review threads with replies, ratings breakdowns, opening hours, social links, SIREN/NAF identifiers, and 100+ structured company fields. Supports keyword search, URL input, and bulk sitemap discovery.", "version": "1.7", "x-build-id": "tObBufJ1yOLcYorip" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abotapi~gowork-eu-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abotapi-gowork-eu-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abotapi~gowork-eu-scraper/runs": { "post": { "operationId": "runs-sync-abotapi-gowork-eu-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abotapi~gowork-eu-scraper/run-sync": { "post": { "operationId": "run-sync-abotapi-gowork-eu-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start mode", "enum": [ "search", "url", "sitemap" ], "type": "string", "description": "Pick how to seed companies. search: free-text queries. url: paste detail or search URLs (multi). sitemap: walk the gowork.fr or gowork.de sitemap index for bulk discovery.", "default": "search" }, "locale": { "title": "Site locale", "enum": [ "fr", "de" ], "type": "string", "description": "Applies to search and sitemap modes. URL mode infers locale from the host (gowork.fr vs gowork.de) automatically.", "default": "fr" }, "queries": { "title": "Search queries", "type": "array", "description": "Search terms (company name, brand, or keyword). One query becomes one SERP walk.", "items": { "type": "string" } }, "urls": { "title": "Start URLs", "type": "array", "description": "Paste company detail URLs (e.g. https://gowork.fr/b-hive-mulhouse, or with a numeric suffix such as https://gowork.fr/le-carrefour-de-la-fleur-montigny-en-gohelle,1), search URLs (e.g. https://gowork.fr/search?q=Carrefour&page=2, or https://gowork.fr/search for all companies, on gowork.fr or gowork.de), category listing pages (https://gowork.fr/avis/paris;l for a city or region, https://gowork.fr/avis/location-de-logements;tr for a trade, https://gowork.fr/avis/7112b;a for an activity area), a sitemap index (https://gowork.fr/sitemap.xml or https://gowork.de/sitemap.xml) or a single sitemap shard (https://gowork.fr/sitemap_company_1.xml.gz for company profiles, https://gowork.fr/sitemap_cities_1.xml.gz for city listing pages). Sitemap links discover companies per the sitemap kind setting and Max companies. Multi-URL supported. Search and listing URLs auto-paginate forward. Leaving this field untouched works through one example of each shape in order, within the shared Max companies budget.", "default": [ "https://gowork.fr/b-hive-mulhouse", "https://gowork.fr/le-carrefour-de-la-fleur-montigny-en-gohelle,1", "https://gowork.fr/randstad-france", "https://gowork.fr/search", "https://gowork.fr/search?q=Carrefour", "https://gowork.fr/search?q=Carrefour&page=2", "https://gowork.de/search?q=Aldi", "https://gowork.de/search?q=Aldi&page=2", "https://gowork.fr/avis/paris;l", "https://gowork.fr/avis/marseille;l?page=2", "https://gowork.fr/avis/location-de-logements;tr", "https://gowork.fr/avis/restaurants-et-services-alimentaires;tr?page=2", "https://gowork.fr/avis/7112b;a", "https://gowork.fr/sitemap_company_1.xml.gz", "https://gowork.fr/sitemap_cities_1.xml.gz", "https://gowork.fr/sitemap.xml", "https://gowork.de/sitemap.xml" ], "items": { "type": "string" } }, "sitemapKind": { "title": "Sitemap kind", "enum": [ "companies", "constant", "cities", "regions", "rankings", "all" ], "type": "string", "description": "Which sitemap shard family to walk. \"companies\" yields company profile URLs and is the most useful for bulk seeding (\"constant\" is the old name and means the same). Also used when you paste a /sitemap.xml link in URL mode.", "default": "companies" }, "sitemapFilter": { "title": "Sitemap URL keyword filter (optional)", "type": "string", "description": "Case-insensitive substring filter applied to discovered URLs (matches the slug part). Empty = no filter.", "default": "" }, "output": { "title": "Output shape", "enum": [ "company", "reviews" ], "type": "string", "description": "company: standard one-record-per-company shape with reviews nested. reviews: flat shape, each review becomes its own row with companySlug / companyName / companySiteLocale / companyRating / etc. joined in. reviews mode auto-enables fetchDetails.", "default": "company" }, "fetchDetails": { "title": "Fetch full company detail (recommended)", "type": "boolean", "description": "When ON, fetches full company details: opening hours, all reviews, rating histogram, social links, NAF code, geo coordinates. When OFF, only SERP-card data is returned (no detail surcharge); listing-link rows then carry the card's rounded whole-number rating and no review count. Auto-promoted to ON when output=reviews.", "default": true }, "maxPages": { "title": "Max SERP pages per search", "minimum": 0, "type": "integer", "description": "Pagination ceiling per search query / per SERP URL. Leave empty to walk every result page (still bounded by maxListings). URL-mode detail URLs ignore this." }, "maxListings": { "title": "Max companies (hard cap across all modes)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Hard ceiling on companies returned across the whole run, regardless of mode (search / url / sitemap). 0 = unlimited (only bounded by Apify's per-run timeout). This is the authoritative budget cap, applied AFTER per-search pagination.", "default": 25 }, "maxReviewsPerCompany": { "title": "Max review threads per company", "minimum": 0, "maximum": 500, "type": "integer", "description": "Cap on review threads (each thread can also include replies) returned per company. 0 = unlimited. A company page carries up to 30 threads; a higher cap opens that company's following review pages (roughly one extra request for every further block of 30 threads).", "default": 20 }, "minRating": { "title": "Minimum company rating", "minimum": 0, "maximum": 5, "type": "integer", "description": "Skip companies whose aggregate rating is below this threshold (0-5). Applied client-side. On listing links with Fetch full company detail off it compares against the card's rounded whole-number rating (2.6 counts as 3); turn detail on for the exact rating.", "default": 0 }, "minReviewCount": { "title": "Minimum review count", "minimum": 0, "type": "integer", "description": "Skip companies with fewer than N total reviews. City, trade and activity-area listing cards show no review count: turn on full company detail to apply this on those links.", "default": 0 }, "ratedOnly": { "title": "Only companies with at least one rated review", "type": "boolean", "description": "Skip companies with no scored reviews on file (aggregate rating count is zero).", "default": false }, "verifiedOnly": { "title": "Only verified companies", "type": "boolean", "description": "Skip companies not marked as verified.", "default": false }, "proxy": { "title": "Proxy", "type": "object", "description": "This actor uses Apify Residential by default (country FR, or DE for the German locale) and uses the proxy group you pick as chosen. Free-tier accounts without residential access can paste their own residential proxy URLs here." }, "resumeFromRunId": { "title": "Resume from a previous run (optional)", "type": "string", "description": "Paste a previous run ID or dataset ID to continue a full-catalogue walk across separate runs. Companies already collected there (matched by slug) are skipped, so this run only saves the new ones. Leave empty for a normal fresh run. Do not combine with Incremental mode below unless this is the very first incremental run for a new state key — the two solve different problems (one interrupted run vs. recurring monitoring of the same search)." }, "incrementalMode": { "title": "Incremental mode (recurring monitoring)", "type": "boolean", "description": "For a search/URL/sitemap config you run on a schedule (e.g. daily). The actor remembers the companies it saw last time and labels every row's `changeType`: NEW, UPDATED, UNCHANGED, REAPPEARED, or EXPIRED (only when 'Emit expired' is on). A company is UPDATED when any output field differs from last time (rating, review counts, reviews, address, detail fields and so on), except `scrapedAt` and the fields you list under 'Ignore fields when detecting changes'. Distinct from 'Resume from a previous run' above, which continues one interrupted run instead of tracking a recurring search. Off by default so a normal run's output shape is unchanged.", "default": false }, "stateKey": { "title": "State key (incremental mode only, optional)", "type": "string", "description": "Names the saved baseline this run compares against. Leave empty to auto-derive one from your mode/queries/urls/sitemap settings/filters (so two different searches never share a baseline). Set your own value if you want multiple scheduled runs of the SAME search to intentionally share one baseline, or to give a search a stable name across small filter tweaks." }, "emitUnchanged": { "title": "Emit unchanged rows (incremental mode only)", "type": "boolean", "description": "When ON, incremental mode also pushes companies with no detected change (changeType=UNCHANGED). Off by default: a quiet run returns only what's new or changed. Turning this on returns — and bills — a row for every tracked company, every run.", "default": false }, "emitExpired": { "title": "Emit expired rows (incremental mode only)", "type": "boolean", "description": "When ON, incremental mode pushes a changeType=EXPIRED row for any previously-tracked company no longer found, but ONLY after a run that scanned the full tracked search with no cap/page limit cutting it short and no resumeFromRunId (a partial scan can never prove a company is really gone). Off by default: this also bills one extra row per expired company.", "default": false }, "ignoreFieldsForChanges": { "title": "Ignore fields when detecting changes (incremental mode only)", "type": "array", "description": "Field names left out of the UPDATED comparison, one per line. Nested paths use dots (for example `reviews.content`) and apply to every element of a list. The row still contains these fields; they just never turn a company into UPDATED or appear in `changedFields`. `scrapedAt` is always ignored. Changing this list never causes a one-time wave of UPDATED rows: the saved baseline is re-compared with the new list.", "default": [], "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 } } } } } } } } } }