{ "openapi": "3.0.1", "info": { "title": "IndiaMART Supplier Scraper", "description": "Build Indian supplier shortlists from IndiaMART.com in minutes — full GST numbers, phone, address, prices, MOQ, ratings, TrustSeal and exporter flags in every row. Works with keyword searches (city/state filter) or any IndiaMART URL. New-listings monitoring mode. JSON or CSV out.", "version": "0.0", "x-build-id": "B5MRZ5Fm0KvG419lR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~indiamart-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-indiamart-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~indiamart-scraper/runs": { "post": { "operationId": "runs-sync-memo23-indiamart-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~indiamart-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-indiamart-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Search queries", "type": "array", "description": "Product or supplier search terms, e.g. `stainless steel pipes`, `pharma packaging`, `industrial valves`. Each query is resolved through IndiaMART's search API.", "items": { "type": "string" } }, "location": { "title": "Location filter", "type": "string", "description": "Optional city or state applied to every search query (e.g. `Mumbai`, `Maharashtra`). Leave empty for all-India results." }, "startUrls": { "title": "IndiaMART URLs", "type": "array", "description": "Full IndiaMART URLs to crawl. All URL shapes are auto-classified; mix them freely in one run.", "items": { "type": "string" } }, "includeExtraProducts": { "title": "Include extra products per supplier", "type": "boolean", "description": "IndiaMART bundles up to 4 adjacent products from the same supplier with every search result. When enabled these are emitted as extra rows (flagged `isAdditionalProduct: true`) that inherit the supplier's contact and verification fields — roughly 3-5× more rows per query.", "default": true }, "enrichSupplier": { "title": "Fetch supplier storefront (adds phone + address + rating)", "type": "boolean", "description": "For rows coming from category pages or direct product URLs, fetch each unique supplier storefront once to add `phone`, `address`, `supplierRating`, `ratingCount` and `companyDescription`. Search-API rows already include these, so no extra fetch happens for them.", "default": true }, "enrichEmails": { "title": "Enrich with supplier contact emails (experimental)", "type": "boolean", "description": "If enabled, tries to find a contact email for each supplier by visiting its own website (when listed) or discovering it, then reading contact/about pages. Adds `contactEmail` + `contactWebsite` columns plus a detailed `emailEnrichment` object. Best-effort.", "default": false }, "qualifyByPayment": { "title": "💳 Qualify by payment (flag businesses that take money online)", "type": "boolean", "description": "Requires \"Enrich with contact emails\". Scans each supplier's website — reusing the pages already fetched for email discovery, so no extra cost or time — for payment processors and e-commerce platforms (Stripe, Shopify, PayPal, Razorpay, WooCommerce, Square and more). Adds `takesPayments`, `paymentProcessors`, `stripeLiveKey` and `paymentConfidence`.", "default": false }, "monitoringMode": { "title": "Monitoring mode (only return products not seen on previous runs)", "type": "boolean", "description": "When enabled, products whose IndiaMART display ID has already been delivered to you are silently skipped (no charge applies for them). The first run after enabling monitoring returns every match — that builds your baseline. Every subsequent run returns only new listings. Combine with Apify's scheduler for a 'new suppliers since last run' feed.", "default": false }, "resetMonitoringState": { "title": "Reset monitoring state (one-shot)", "type": "boolean", "description": "One-shot toggle: clear the saved 'products already seen' record at the start of this run. Use this when you change queries, want to rebuild the baseline, or recover from a missed delivery. Has no effect when monitoring mode is off.", "default": false }, "maxItems": { "title": "Maximum items to scrape", "minimum": 1, "type": "integer", "description": "Hard cap on the number of supplier/product rows collected across all queries and start URLs. Use this to limit billing.", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Maximum number of pages processed in parallel.", "default": 10 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "type": "integer", "description": "Minimum number of pages processed in parallel.", "default": 1 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Number of retries before a failed request is given up.", "default": 5 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy settings. IndiaMART serves residential IPs fine; datacenter ranges are riskier. Residential proxy recommended.", "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 } } }, "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 } } } } } } } } } }