{ "openapi": "3.0.1", "info": { "title": "Haraj Classifieds Scraper", "description": "Saudi classifieds from Haraj: cars, real estate, jobs and general goods by category tag, city or seller. Every row is fully detailed — description, all images, precise location, and category-specific fields (price, car/property/job info).", "version": "0.1", "x-build-id": "uvfY0ilWTd4cBnMs6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~haraj-classifieds-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-haraj-classifieds-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~haraj-classifieds-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-haraj-classifieds-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~haraj-classifieds-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-haraj-classifieds-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "queries": { "title": "Queries", "type": "array", "description": "One crawl per entry, each with its own SEARCH_SUMMARY row. Each item: {\"tag\": \"تويوتا\", \"city\": \"الرياض\", \"notTag\": \"كامري\", \"authorUsername\": null, \"onlyWithImage\": true, \"onlyWithVideo\": false} -- at least one of 'tag', 'city', 'cities', or 'authorUsername' is required. 'tag' is Haraj's own category/brand/model taxonomy (e.g. 'حراج السيارات' for cars, 'تويوتا' for Toyota, 'شقق للايجار' for apartments for rent) -- there are many thousands of tags and no lookup endpoint to enumerate them from, but an unrecognised value is honest (an empty result), never a silent fallback to the whole site. IMPORTANT: despite the name, 'city'/'cities' filter by Saudi Arabia's 13 ADMINISTRATIVE REGIONS, not individual municipalities — 'جدة' (Jeddah, a city) returns nothing, 'مكة المكرمة' (Makkah, the region Jeddah belongs to) does. All 13 region names verified working: الرياض (Riyadh), مكة المكرمة (Makkah), المدينة المنورة (Madinah), الشرقية (Eastern Province), القصيم (Qassim), عسير (Asir), تبوك (Tabuk), حائل (Hail), جازان (Jazan), نجران (Najran), الباحة (Al-Bahah), الجوف (Al-Jouf), الحدود الشمالية (Northern Borders)." }, "postIds": { "title": "Direct post IDs", "type": "array", "description": "Fetch specific classified ads directly by their numeric post id (found in a post's URL, e.g. the '186515219' in '/11186515219/...'). Each one becomes its own row -- exactly as complete as a row found via 'queries', since this site's API answers both the same way.", "default": [], "items": { "type": "string" } }, "maxItemsPerQuery": { "title": "Max posts per query", "minimum": 0, "type": "integer", "description": "Stop each query after this many posts. Set to 0 for unlimited -- pagination on this target is genuinely honest, with an explicit 'hasMoreAvailable' signal upstream provides directly rather than this actor having to infer it.", "default": 40 }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many requests may be in flight at once. This absorbs latency variance; it is NOT the throttle -- the crawl rate is set by 'Minimum interval between requests' below.", "default": 5 }, "minRequestInterval": { "title": "Minimum interval between requests (seconds)", "minimum": 0.05, "maximum": 10, "type": "number", "description": "The actual speed control: the shortest gap between two requests, across all workers. No bot mitigation was observed during recon (8/8 TLS profiles clean, ten rapid sequential requests all succeeded with no rate-limit response).", "default": 0.4 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential with no country pin is the cloud default. No WAF was observed anywhere during recon, so there's no known reason to narrow the exit-IP pool.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }