{ "openapi": "3.0.1", "info": { "title": "Capterra 0.9$šŸ’° Reviews Products, Categories & Compare Scraper", "description": "[Only 0.9$šŸ’°] Capterra all-in-one scraper: product, reviews, category & compare URLs in one actor. Flat per-review rows (100% field fill: reviewer name, company size, recommendation score, incentivization), Capterra awards & badges, sentiment breakdown, structured integrations. Pure HTTP, no browser", "version": "0.1", "x-build-id": "mmRKl5zSihQJnwkpA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~capterra-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-capterra-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/memo23~capterra-scraper/runs": { "post": { "operationId": "runs-sync-memo23-capterra-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/memo23~capterra-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-capterra-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Capterra URLs", "type": "array", "description": "Paste any mix of:\nā€¢ Product URLs ā€” `https://www.capterra.com/p/{id}/{slug}/`\nā€¢ Reviews URLs ā€” `https://www.capterra.com/p/{id}/{slug}/reviews/`\nā€¢ Category URLs ā€” `https://www.capterra.com/{slug}-software/`\nā€¢ Compare URLs ā€” `https://www.capterra.com/compare/{ids}/{slug-a}-vs-{slug-b}/`\n\nBare numeric product IDs (e.g. `137005`) and bare category slugs (e.g. `project-management`) also work. Each entry is auto-classified and emits the matching row type ā€” one row per URL.", "items": { "type": "string" } }, "maxItems": { "title": "Max dataset rows to emit", "minimum": 1, "type": "integer", "description": "Safety cap on total dataset rows. Product / compare URLs each emit 1 row. A reviews URL emits one row per individual review (each carrying the thread-level aggregate under `productAggregate`); a category URL emits one row per product listed (each carrying the category-level aggregate under `categoryAggregate`). So a reviews URL with 100 reviews fills 100 rows, a category URL with 50 products fills 50 rows. Each emitted row = one paid output-record event.", "default": 1000 }, "maxReviewsPerProduct": { "title": "Max reviews per product", "minimum": 0, "type": "integer", "description": "Maximum number of individual reviews to include in each reviews-URL row. Reviews pages can list hundreds; capping keeps row size manageable for CSV consumers. Set 0 for no limit.", "default": 100 }, "maxProductsPerCategory": { "title": "Max products per category", "minimum": 0, "type": "integer", "description": "Maximum number of category-product rows emitted per category URL. Category index pages list up to ~100 products. Set 0 for no limit.", "default": 50 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "type": "integer", "description": "Reserved for future use. Capterra requires a session-aware sticky-IP pattern, so the actor currently processes URLs sequentially through one warm session for highest pass rate.", "default": 1 }, "minConcurrency": { "title": "Min concurrency", "minimum": 1, "type": "integer", "description": "Reserved for future use.", "default": 1 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "type": "integer", "description": "Maximum number of retries inside the warm session before giving up on a URL.", "default": 8 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Apify residential proxy works well. The actor uses a sticky session (same IP for the whole run) plus cookie-jar reuse to ride past Cloudflare's deep-page WAF ā€” see the README's 'How it works' section.", "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 } } } } } } } } } }