{ "openapi": "3.0.1", "info": { "title": "PagesJaunes Scraper — French Business Directory, per result", "description": "Business listings from pagesjaunes.fr: name, address, activities, rating, plus phone, SIRET, NAF code, GPS and opening hours from the professional's own page. Drop-in compatible with memo23/pagesjaunes-scraper-cheerio.", "version": "0.1", "x-build-id": "hNftnWrMdd86JfNPw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/diopside~pagesjaunes-businesses/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-diopside-pagesjaunes-businesses", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/diopside~pagesjaunes-businesses/runs": { "post": { "operationId": "runs-sync-diopside-pagesjaunes-businesses", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/diopside~pagesjaunes-businesses/run-sync": { "post": { "operationId": "run-sync-diopside-pagesjaunes-businesses", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "pagesjaunes.fr URLs to scrape. Either a search listing (`https://www.pagesjaunes.fr/annuaire/paris-75/restaurant` or `https://www.pagesjaunes.fr/annuaire/chercherlespros?quoiqui=plombier&ou=Paris`) or a single professional's page (`https://www.pagesjaunes.fr/pros/64217247`). Leave empty and use Search term + Location instead if you prefer.", "items": { "type": "string" } }, "searchTerm": { "title": "Search term (quoiqui)", "type": "string", "description": "Activity, trade or business name to search for, exactly as you would type it on pagesjaunes.fr — e.g. `plombier`, `restaurant`, `boulangerie`. Ignored when Start URLs are given." }, "location": { "title": "Location (ou)", "type": "string", "description": "Town, department or postcode — e.g. `Paris`, `Lyon`, `69003`. Ignored when Start URLs are given." }, "maxItems": { "title": "Maximum number of results", "minimum": 0, "type": "integer", "description": "Stop after this many businesses per run. Set to 0 to scrape every page of every start URL.", "default": 100 }, "extractDetails": { "title": "Extract details from each professional's page", "type": "boolean", "description": "Open each business's own `/pros/` page to add phone, website, GPS coordinates, SIRET, SIREN, NAF code, legal form, opening hours and accepted payment methods. Costs one extra request per business and is billed as an enriched result. Turn off for a fast, cheap name + address + rating sweep.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "pagesjaunes.fr is behind a Cloudflare managed challenge that scores the exit IP, so French residential IPs are required — measured on the Apify platform, the raw egress IP and the datacenter pool passed 0 of 9 requests while RESIDENTIAL/FR passed every request that got an exit IP. Leave this at the default unless you are supplying your own French residential proxies.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "FR" } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of pages fetched at the same time.", "default": 4 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "type": "integer", "description": "Accepted for compatibility with other PagesJaunes actors. This actor paces itself with Max requests per minute instead, so the value is not used.", "default": 1 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 10, "maximum": 300, "type": "integer", "description": "Request rate ceiling. Lower it if you see challenges in the log.", "default": 90 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many times a blocked or failed page is retried on a fresh exit IP before the target is given up on.", "default": 4 }, "proxy": { "title": "Proxy configuration (compatibility)", "type": "object", "description": "Accepted so an input written for memo23/pagesjaunes-scraper-cheerio runs unchanged. Used only when Proxy configuration is not set." } } }, "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 } } } } } } } } } }