{ "openapi": "3.0.1", "info": { "title": "Software Reviews Scraper: Capterra, GetApp & Software Advice", "description": "Scrape software reviews from Capterra, GetApp and Software Advice: star ratings, pros and cons, reviewer industry and company size, vendor replies, newest first. Plus GetApp product listings with pricing and features.", "version": "0.1", "x-build-id": "ggPa42pjOj0RyjZcy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/artsiom_k~getapp-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-artsiom_k-getapp-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/artsiom_k~getapp-scraper/runs": { "post": { "operationId": "runs-sync-artsiom_k-getapp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/artsiom_k~getapp-scraper/run-sync": { "post": { "operationId": "run-sync-artsiom_k-getapp-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "entityType": { "title": "What to scrape", "enum": [ "products", "reviews" ], "type": "string", "description": "\"Software products\": GetApp listings with rating, review count, pricing plans, features, integrations and alternatives. \"Reviews\": individual user reviews, newest first (star ratings, pros, cons, reviewer industry, company size and time used, vendor reply). Capterra, GetApp and Software Advice share one review database, so each review is returned once whichever site's URL you give.", "default": "products" }, "startUrls": { "title": "Product URLs", "type": "array", "description": "Products: GetApp profile URLs (https://www.getapp.com/{category}/a/{product}/); leave empty for the whole catalog (~45,000 listings). Reviews: product URLs from Software Advice (https://www.softwareadvice.com/product/2764-Salesforce/), Capterra (https://www.capterra.com/p/61368/Salesforce/) or GetApp, any page of the product; leave empty for every reviewed product (~11,800).", "items": { "type": "string" } }, "maxItems": { "title": "Max results", "minimum": 1, "type": "integer", "description": "Stop after this many results (products or reviews). Defaults to 50, a fast, cheap preview. Raise it or clear it (set to null) for a full run.", "default": 50 }, "maxReviewsPerProduct": { "title": "Max reviews per product", "minimum": 1, "type": "integer", "description": "Reviews only: at most this many reviews per product. Leave empty for all of them. Reviews come newest first, so a limit gives you the most recent ones." }, "minRating": { "title": "Minimum star rating", "minimum": 1, "maximum": 5, "type": "integer", "description": "Reviews only: keep reviews with an overall rating of at least this many stars (1-5)." }, "maxRating": { "title": "Maximum star rating", "minimum": 1, "maximum": 5, "type": "integer", "description": "Reviews only: keep reviews with an overall rating of at most this many stars (1-5). Set to 2 for negative reviews only." }, "reviewedAfter": { "title": "Written on or after", "type": "string", "description": "Reviews only: keep reviews written on or after this date (YYYY-MM-DD)." }, "companySizes": { "title": "Reviewer company size", "type": "array", "description": "Reviews only: keep reviews from reviewers at companies of these sizes. Empty = all.", "items": { "type": "string", "enum": [ "Self-employed", "1-10 employees", "11-50 employees", "51-200 employees", "201-500 employees", "501-1000 employees", "1001-5000 employees", "5001-10,000 employees", "10,001+ employees" ] } }, "onlyNewReviews": { "title": "Only new reviews", "type": "boolean", "description": "Reviews only: skip reviews already returned by an earlier run with the same product URLs. Schedule a daily or weekly run with this on to get just the newly posted reviews.", "default": false }, "mode": { "title": "Incremental mode (products)", "enum": [ "auto", "full", "incremental" ], "type": "string", "description": "\"auto\" (recommended): full scan on the first run, incremental (new/changed only) afterwards. \"full\": always push every item and refresh the baseline — schedule this periodically to catch delistings. \"incremental\": always push only new/changed items. Only a plain, unscoped sitemap crawl (no startUrls) can detect delistings or update the baseline.", "default": "auto" }, "concurrency": { "title": "Concurrency", "minimum": 1, "type": "integer", "description": "How many software profile pages to fetch in parallel.", "default": 15 }, "impersonate": { "title": "TLS impersonation target", "type": "string", "description": "curl_cffi browser TLS-impersonation target. Defaults to \"chrome\" internally — the only fingerprint verified 100% clean on real Apify infra when paired with the mandatory Residential proxy below." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy configuration. Defaults to the RESIDENTIAL group and should be left there: as of this build, GetApp.com returns HTTP 403 to roughly 35-45% of requests from Apify's datacenter/cloud IPs regardless of TLS fingerprint (a real IP-reputation block, confirmed via a live cloud probe) — only Residential proxy cleared it (100% clean in that same probe). Turning this off or switching to a datacenter group will very likely cause sustained failures.", "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 } } } } } } } } } }