{ "openapi": "3.0.1", "info": { "title": "TechCrunch Scraper", "description": "Scrape full-text TechCrunch articles as clean markdown, text or HTML. Search by keyword, filter by category, author, tag and date, or enrich a list of article URLs. Fast (no browser), MCP-ready and built for RAG pipelines.", "version": "0.1", "x-build-id": "QZTDh9U6GIk9MluPt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapelabmax~techcrunch-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapelabmax-techcrunch-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapelabmax~techcrunch-scraper/runs": { "post": { "operationId": "runs-sync-scrapelabmax-techcrunch-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapelabmax~techcrunch-scraper/run-sync": { "post": { "operationId": "run-sync-scrapelabmax-techcrunch-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "keywords": { "title": "Keywords", "type": "array", "description": "Search terms, each run as a separate TechCrunch search (e.g. a company, product or sector).", "items": { "type": "string" } }, "strictKeywordMatch": { "title": "Exact phrase match", "type": "boolean", "description": "Keep only results that contain each keyword as a whole phrase (TechCrunch search alone matches the words separately).", "default": true }, "startUrls": { "title": "Article URLs", "type": "array", "description": "TechCrunch article URLs (techcrunch.com/YYYY/MM/DD/slug/) to fetch in addition to any search; other pages are skipped with a warning.", "items": { "type": "string" } }, "categories": { "title": "Categories", "type": "array", "description": "Category slugs, names or URLs, e.g. \"artificial-intelligence\", \"Fintech\" or https://techcrunch.com/category/venture/.", "items": { "type": "string" } }, "authors": { "title": "Authors", "type": "array", "description": "Author slugs, names or profile URLs, e.g. \"kyle-wiggers\" or https://techcrunch.com/author/kyle-wiggers/.", "items": { "type": "string" } }, "tags": { "title": "Tags", "type": "array", "description": "Tag slugs, names or URLs, e.g. \"openai\" or https://techcrunch.com/tag/openai/.", "items": { "type": "string" } }, "dateFrom": { "title": "Published on or after", "type": "string", "description": "Earliest publish date: ISO date/datetime (2026-10-01) or relative (\"7 days\", \"2 weeks\", \"1 month\", \"yesterday\")." }, "dateTo": { "title": "Published on or before", "type": "string", "description": "Latest publish date (inclusive): ISO date/datetime (2026-10-25) or relative (\"1 day\", \"yesterday\", \"today\")." }, "maxItems": { "title": "Max articles", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Maximum number of articles to return across all sources (1 to 100,000; 0 means the default of 100).", "default": 100 }, "includeBody": { "title": "Include full text", "type": "boolean", "description": "Include the full article body; turn off for metadata-only results (title, author, date, excerpt, URL).", "default": true }, "bodyFormat": { "title": "Body format", "enum": [ "markdown", "text", "html" ], "type": "string", "description": "Format of the article body: markdown (best for LLMs and RAG), plain text, or cleaned HTML.", "default": "markdown" }, "includeEventPromos": { "title": "Include TechCrunch event ads", "type": "boolean", "description": "Include TechCrunch's own event marketing posts (byline \"TechCrunch Events\", e.g. ticket deadlines); excluded by default.", "default": false }, "dedupe": { "title": "Only new articles (dedupe across runs)", "type": "boolean", "description": "Remember returned articles in a named key-value store and skip them in later runs; turn on for scheduled feeds.", "default": false }, "dedupeStoreName": { "title": "Dedupe store name", "type": "string", "description": "Named key-value store that remembers seen articles (default \"techcrunch-scraper-seen\"); use one name per scheduled feed." }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum parallel requests to TechCrunch (1 to 50); keep it low to stay polite.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional proxy. The TechCrunch API works without one; Apify datacenter proxy helps if you hit rate limits.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }