{ "openapi": "3.0.1", "info": { "title": "French Website to SIREN & Mentions Légales Extractor", "description": "Turn a list of French websites or domains into SIREN, SIRET, VAT number, RCS city, legal name and address, read from each site's mentions légales and checked against official SIRENE data. Pay only for websites matched to a company.", "version": "1.0", "x-build-id": "TQWemobIMiLw2gDGP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/atesen-software~french-website-siren-mentions-legales/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-atesen-software-french-website-siren-mentions-legales", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/atesen-software~french-website-siren-mentions-legales/runs": { "post": { "operationId": "runs-sync-atesen-software-french-website-siren-mentions-legales", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/atesen-software~french-website-siren-mentions-legales/run-sync": { "post": { "operationId": "run-sync-atesen-software-french-website-siren-mentions-legales", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "websites" ], "properties": { "websites": { "title": "Websites or domains", "type": "array", "description": "One per line: a domain (pennylane.com), a URL (https://www.payfit.com/fr/) or a sub-site. Duplicates are removed. Use 'Bulk edit' to paste a whole column.", "items": { "type": "string" } }, "enrichWithSirene": { "title": "Enrich with official SIRENE data", "type": "boolean", "description": "Verify each SIREN found against the official Recherche d'entreprises API (INSEE SIRENE + RNE) and add the registered legal name, address, NAF code, headcount range, size category, latest revenue and the computed VAT number.", "default": true }, "maxPagesPerSite": { "title": "Max pages per website", "minimum": 1, "maximum": 15, "type": "integer", "description": "Homepage + the most likely legal pages (mentions légales, informations légales, CGV, à propos, contact). The crawl stops early as soon as a legal page with a SIREN is found.", "default": 6 }, "maxConcurrency": { "title": "Websites in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many websites are processed at the same time. Each website is crawled politely, one page per second.", "default": 3 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that the website's robots.txt disallows.", "default": true }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Some large sites (Cloudflare/DataDome) answer 403 to cloud servers; an Apify residential proxy usually helps. Not needed for most SME websites." } } }, "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 } } } } } } } } } }