{ "openapi": "3.0.1", "info": { "title": "MercadoLibre Chile Scraper - High Reliability", "description": "High-reliability MercadoLibre Chile scraper for mercadolibre.cl. Runs parallel worker shards with mission dedupe, Envio local filtering, local/import classification, CLP prices, VIP detail shipping/sold/quantity evidence, residential/custom proxies, retries, and cost/block guardrails.", "version": "0.1", "x-build-id": "98lQH5pFch1pafvI9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jchame~atomic-actor-1/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jchame-atomic-actor-1", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jchame~atomic-actor-1/runs": { "post": { "operationId": "runs-sync-jchame-atomic-actor-1", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jchame~atomic-actor-1/run-sync": { "post": { "operationId": "run-sync-jchame-atomic-actor-1", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "atomicMode": { "title": "Atomic mode", "enum": [ "orchestrator", "worker" ], "type": "string", "description": "Use orchestrator for reliability fan-out on Apify cloud. Use worker only for direct single-shard runs or local debugging.", "default": "orchestrator" }, "runMode": { "title": "Run mode", "enum": [ "search", "item_detail" ], "type": "string", "description": "Use search for normal Atomic search-result extraction. Use item_detail for VIP detail mode over known item/catalog URLs.", "default": "search" }, "childActorId": { "title": "Worker actor ID", "type": "string", "description": "Optional Apify actor ID to launch as child workers. Leave empty when Atomic is deployed and should call itself.", "default": "" }, "childBuild": { "title": "Worker build tag", "type": "string", "description": "Optional build tag for child worker runs, such as experimental. Leave empty to use the actor default.", "default": "" }, "maxConcurrentChildRuns": { "title": "Max concurrent worker runs", "minimum": 1, "maximum": 250, "type": "integer", "description": "How many child worker runs the orchestrator may run at once. Start moderate; 8-12 is the first recommended paid test range. Higher values depend on Apify account concurrency and proxy capacity.", "default": 8 }, "childMemoryMbytes": { "title": "Worker memory MB", "minimum": 512, "maximum": 8192, "type": "integer", "description": "Memory allocated to each child worker run.", "default": 2048 }, "childTimeoutSecs": { "title": "Worker timeout seconds", "minimum": 60, "maximum": 3600, "type": "integer", "description": "Timeout for each child worker run.", "default": 180 }, "maxShardRetries": { "title": "Retries per shard", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many fresh child worker attempts to try for a blocked or empty shard before marking it failed.", "default": 2 }, "maxAtomicShards": { "title": "Maximum shards", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum query/page/url shards planned by the orchestrator.", "default": 100 }, "targetRowsPerShard": { "title": "Rows per worker shard", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum rows each child worker should try to return.", "default": 60 }, "stopOnCostUsd": { "title": "Cost guardrail USD", "minimum": 0, "maximum": 10000, "type": "number", "description": "Stop launching new shards after estimated child-run cost reaches this amount. First paid stress default is 50 USD.", "default": 50 }, "stopOnBlockRate": { "title": "Block-rate guardrail", "minimum": 0, "maximum": 1, "type": "number", "description": "Stop launching new shards if the completed-shard block rate rises above this ratio after the minimum sample size.", "default": 0.35 }, "minShardsForBlockRate": { "title": "Block-rate sample size", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Minimum completed shards before the block-rate guardrail can stop the run.", "default": 20 }, "adaptiveCooldownMs": { "title": "Retry cooldown", "minimum": 0, "maximum": 300000, "type": "integer", "description": "Milliseconds to wait before retrying a failed or blocked shard with a fresh worker run.", "default": 15000 }, "adaptiveConcurrency": { "title": "Adaptive concurrency", "type": "boolean", "description": "Start with a lower worker count and ramp concurrency up or down based on hard-blocked shard rate.", "default": true }, "initialConcurrentChildRuns": { "title": "Initial worker concurrency", "minimum": 1, "maximum": 250, "type": "integer", "description": "Worker count used at the start of an adaptive run before hard-block rate is known.", "default": 8 }, "concurrencyRampStep": { "title": "Concurrency ramp step", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many workers to add or remove when adaptive concurrency changes the current worker limit.", "default": 4 }, "concurrencyRampEveryShards": { "title": "Ramp sample interval", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Completed shard interval for considering a ramp-up when hard-block rate remains low.", "default": 10 }, "rampUpHardBlockRate": { "title": "Ramp-up hard-block rate", "minimum": 0, "maximum": 1, "type": "number", "description": "Ramp up only when hard-blocked shard rate is at or below this ratio.", "default": 0.05 }, "rampDownHardBlockRate": { "title": "Ramp-down hard-block rate", "minimum": 0, "maximum": 1, "type": "number", "description": "Ramp down when hard-blocked shard rate reaches or exceeds this ratio after the minimum sample size.", "default": 0.2 }, "fairQueryDistribution": { "title": "Fair query distribution", "type": "boolean", "description": "When multiple search queries are provided, enforce a fair per-query collection cap so one fast query cannot consume the entire run limit. Set maxItemsPerQuery to 0 to disable query caps entirely.", "default": true }, "childCostFinalRefreshWaitMs": { "title": "Child cost settling max wait", "minimum": 0, "maximum": 180000, "type": "integer", "description": "Maximum milliseconds the parent spends polling finished child run billing from Apify until child cost totals stabilize. Increase for cleaner cost accounting; set to 0 for fastest runs.", "default": 60000 }, "orchestrationSearchOnly": { "title": "Search-only orchestration", "type": "boolean", "description": "Keep orchestrated child runs search-page-only. Recommended for the first reliability stress tests.", "default": true }, "missionId": { "title": "Mission ID", "type": "string", "description": "Stable ID for a coordinated scrape mission. Runs with the same mission ID share shard claiming and item dedupe. Leave empty to derive one from the inputs.", "default": "" }, "missionStorageNamespace": { "title": "Mission storage namespace", "type": "string", "description": "Prefix for the Apify Request Queue and Key-Value Store used by mission coordination.", "default": "atomic-actor-1" }, "missionDedupeMode": { "title": "Mission dedupe mode", "enum": [ "mission", "run", "off" ], "type": "string", "description": "mission skips item IDs already recorded by previous/current runs of the same mission. run dedupes only inside the current parent run. off disables persistent item dedupe.", "default": "mission" }, "useMissionQueue": { "title": "Use mission shard queue", "type": "boolean", "description": "Use an Apify Request Queue so concurrent parent runs with the same mission ID do not claim the same query/page/url shard.", "default": true }, "resumeMission": { "title": "Resume mission", "type": "boolean", "description": "When true, reuse the mission queue/store and continue unhandled work. When false, create a fresh storage scope for this run.", "default": true }, "skipKnownItems": { "title": "Skip known mission items", "type": "boolean", "description": "When mission dedupe is enabled, skip item IDs already recorded in the mission Key-Value Store.", "default": true }, "missionShardQueueName": { "title": "Mission shard queue name", "type": "string", "description": "Advanced override for the Apify Request Queue name. Leave empty unless coordinating external tooling.", "default": "" }, "missionStateStoreName": { "title": "Mission state store name", "type": "string", "description": "Advanced override for the Apify Key-Value Store name. Leave empty unless coordinating external tooling.", "default": "" }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Product names or keywords to search on MercadoLibre Chile.", "default": [], "items": { "type": "string" } }, "startUrls": { "title": "MercadoLibre search URLs", "type": "array", "description": "Optional MercadoLibre Chile search/listing URLs. Direct product URLs are skipped in search mode. In runMode=item_detail, startUrls may be used as detail URLs if itemDetailUrls is empty.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "itemDetailUrls": { "title": "Item/catalog detail URLs", "type": "array", "description": "MercadoLibre Chile item or catalog product URLs to fetch when runMode=item_detail. Accepts articulo/producto URLs, including /p/ catalog URLs and URLs with wid=MLC item IDs.", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Maximum listings", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum unique search-card listings to save across all inputs.", "default": 60 }, "maxDetailPages": { "title": "Maximum detail pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum item/catalog detail URLs to fetch in runMode=item_detail. In orchestrator mode, each detail URL becomes a bounded worker shard.", "default": 10 }, "detailBrowserFirst": { "title": "Detail browser first", "type": "boolean", "description": "For item/catalog detail pages, skip plain HTML probes and go directly to Chromium when browser fallback is enabled. This usually reduces MercadoLibre challenge traffic on detail pages.", "default": true }, "detailHtmlRetryCount": { "title": "Detail HTML retry count", "minimum": 0, "maximum": 5, "type": "integer", "description": "Plain-HTML attempts for item/catalog detail pages before browser rendering. Default is 0 because MercadoLibre detail pages commonly challenge plain HTML traffic.", "default": 0 }, "detailBrowserRetryCount": { "title": "Detail browser retry count", "minimum": 0, "maximum": 10, "type": "integer", "description": "Chromium retry budget for item/catalog detail pages with fresh proxy sessions. Higher values are more stubborn but slower and more expensive.", "default": 4 }, "detailBrowserWaitMs": { "title": "Detail browser wait time", "minimum": 500, "maximum": 15000, "type": "integer", "description": "Milliseconds to wait after detail-page browser navigation before parsing sold, quantity, catalog, and shipping evidence.", "default": 3000 }, "maxItemsPerQuery": { "title": "Maximum listings per query", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Optional per-query cap. Use 0 for no per-query cap.", "default": 60 }, "maxPagesPerQuery": { "title": "Maximum search pages per query", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many public search-result pages to read for each query. One page is usually enough for market evidence and URL samples.", "default": 1 }, "searchFilterMode": { "title": "Search filter mode", "enum": [ "default", "envio_local" ], "type": "string", "description": "Choose default to scrape the normal search page. Choose Envio local to have each worker load MercadoLibre's Productos con envio nacional / Envio local filtered page and save only rows from that filtered search page.", "default": "default" }, "localOnly": { "title": "Local stock only", "type": "boolean", "description": "Shortcut for searchFilterMode=envio_local. When enabled, Atomic returns only rows from MercadoLibre's Envio local filtered search pages when that filter is available.", "default": false }, "htmlRetryCount": { "title": "HTML retry count", "minimum": 0, "maximum": 5, "type": "integer", "description": "Extra plain-HTML attempts for each search page before browser fallback.", "default": 2 }, "browserFallback": { "title": "Use browser fallback", "type": "boolean", "description": "Render search pages in Chromium when plain HTML is blocked or incomplete. Recommended for MercadoLibre.", "default": true }, "browserWaitMs": { "title": "Browser wait time", "minimum": 500, "maximum": 10000, "type": "integer", "description": "Milliseconds to wait after browser navigation before parsing search cards and filters.", "default": 2500 }, "browserRetryCount": { "title": "Browser retry count", "minimum": 0, "maximum": 5, "type": "integer", "description": "Browser retry budget with session rotation when MercadoLibre returns a security or bot-check page.", "default": 3 }, "requestDelayMs": { "title": "Request delay", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Base delay between search-page requests in milliseconds.", "default": 700 }, "requestJitterMs": { "title": "Request jitter", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Maximum random extra delay added to each request.", "default": 1200 }, "includeRaw": { "title": "Include raw snippets", "type": "boolean", "description": "Include compact parser/debug snippets in the dataset. Off keeps the output lean.", "default": false }, "sellerEnrichmentMode": { "title": "Seller enrichment mode", "enum": [ "off", "local_only" ], "type": "string", "description": "Optional seller/detail enrichment. Use local_only to open bounded item detail pages only for listings classified as local Chile stock.", "default": "off" }, "includeSellerDetails": { "title": "Include seller details", "type": "boolean", "description": "Compatibility alias for sellerEnrichmentMode=local_only.", "default": false }, "maxSellerDetailPages": { "title": "Maximum item detail pages", "minimum": 0, "maximum": 100, "type": "integer", "description": "Maximum local item detail pages to open when seller enrichment is enabled.", "default": 10 }, "maxSellerProfilePages": { "title": "Maximum seller profile pages", "minimum": 0, "maximum": 100, "type": "integer", "description": "Maximum seller profile pages to open when seller enrichment is enabled. Seller profile results are cached by seller identity.", "default": 10 }, "failOnBlockedNoItems": { "title": "Fail when blocked with no listings", "type": "boolean", "description": "Fail the run when MercadoLibre blocks all attempted search pages and no listings are saved.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. Default is Apify Residential Chile. You can also use Apify Console's custom proxy URLs here for an external paid proxy pool.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "CL" } } } }, "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 } } }, "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 } } } } } } } } } }