{ "info": { "name": "Crawlbase API", "description": "Crawlbase (formerly ProxyCrawl) web crawling and scraping platform. All products share the host https://api.crawlbase.com and authenticate with a `token` query parameter. Each account has two tokens: a Normal (TCP) token for static content and a JavaScript token for headless-Chrome rendering. Endpoints and the token auth model are confirmed from Crawlbase docs; response bodies are raw upstream content or scraper-specific JSON.", "schema": "https://schema.getpostman.com/json/collection/v2.1.0/collection.json" }, "variable": [ { "key": "baseUrl", "value": "https://api.crawlbase.com", "type": "string" }, { "key": "token", "value": "", "type": "string" }, { "key": "jsToken", "value": "", "type": "string" } ], "item": [ { "name": "Crawling API", "item": [ { "name": "Crawl a URL (HTML)", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/?token={{token}}&url=https%3A%2F%2Fexample.com", "host": ["{{baseUrl}}"], "path": [""], "query": [ { "key": "token", "value": "{{token}}" }, { "key": "url", "value": "https%3A%2F%2Fexample.com" } ] }, "description": "Fetch a URL through the proxy network and return raw HTML. Use the Normal token for static pages." } }, { "name": "Crawl a URL (JavaScript rendered, JSON)", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/?token={{jsToken}}&url=https%3A%2F%2Fexample.com&format=json&page_wait=2000", "host": ["{{baseUrl}}"], "path": [""], "query": [ { "key": "token", "value": "{{jsToken}}" }, { "key": "url", "value": "https%3A%2F%2Fexample.com" }, { "key": "format", "value": "json" }, { "key": "page_wait", "value": "2000" } ] }, "description": "Render the page in headless Chrome (JavaScript token) and return a JSON envelope. page_wait waits milliseconds after load." } }, { "name": "Crawl a URL with a built-in scraper", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/?token={{token}}&url=https%3A%2F%2Fwww.amazon.com%2Fdp%2FB0EXAMPLE&scraper=amazon-product-details", "host": ["{{baseUrl}}"], "path": [""], "query": [ { "key": "token", "value": "{{token}}" }, { "key": "url", "value": "https%3A%2F%2Fwww.amazon.com%2Fdp%2FB0EXAMPLE" }, { "key": "scraper", "value": "amazon-product-details" } ] }, "description": "Apply a named extractor via the Crawling API to return parsed JSON." } }, { "name": "Crawl a URL (async with callback)", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/?token={{token}}&url=https%3A%2F%2Fexample.com&async=true&callback=https%3A%2F%2Fyour-app.example%2Fhook", "host": ["{{baseUrl}}"], "path": [""], "query": [ { "key": "token", "value": "{{token}}" }, { "key": "url", "value": "https%3A%2F%2Fexample.com" }, { "key": "async", "value": "true" }, { "key": "callback", "value": "https%3A%2F%2Fyour-app.example%2Fhook" } ] }, "description": "Queue the request; Crawlbase returns a request id (rid) immediately and POSTs the result to the callback URL." } } ] }, { "name": "Scraper API", "item": [ { "name": "Scrape a supported site", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/scraper?token={{token}}&url=https%3A%2F%2Fwww.amazon.com%2Fdp%2FB0EXAMPLE&scraper=amazon-product-details", "host": ["{{baseUrl}}"], "path": ["scraper"], "query": [ { "key": "token", "value": "{{token}}" }, { "key": "url", "value": "https%3A%2F%2Fwww.amazon.com%2Fdp%2FB0EXAMPLE" }, { "key": "scraper", "value": "amazon-product-details" } ] }, "description": "Legacy structured-data endpoint. Returns parsed JSON for the named scraper. Superseded by the Crawling API &scraper= parameter." } } ] }, { "name": "Storage API", "item": [ { "name": "Get a stored page by rid", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/storage?token={{token}}&rid=RID_HERE", "host": ["{{baseUrl}}"], "path": ["storage"], "query": [ { "key": "token", "value": "{{token}}" }, { "key": "rid", "value": "RID_HERE" } ] }, "description": "Retrieve a previously stored crawl by its request id. Use ?url= instead of ?rid= to get the most recent stored version of a URL." } }, { "name": "Delete a stored page", "request": { "method": "DELETE", "header": [], "url": { "raw": "{{baseUrl}}/storage?token={{token}}&rid=RID_HERE", "host": ["{{baseUrl}}"], "path": ["storage"], "query": [ { "key": "token", "value": "{{token}}" }, { "key": "rid", "value": "RID_HERE" } ] }, "description": "Delete a single stored crawl by request id." } }, { "name": "Bulk retrieve stored pages", "request": { "method": "POST", "header": [{ "key": "Content-Type", "value": "application/json" }], "body": { "mode": "raw", "raw": "{\n \"rids\": [\"rid1\", \"rid2\"]\n}" }, "url": { "raw": "{{baseUrl}}/storage/bulk?token={{token}}", "host": ["{{baseUrl}}"], "path": ["storage", "bulk"], "query": [{ "key": "token", "value": "{{token}}" }] }, "description": "Fetch up to 100 stored crawls in one request." } }, { "name": "Bulk delete stored pages", "request": { "method": "POST", "header": [{ "key": "Content-Type", "value": "application/json" }], "body": { "mode": "raw", "raw": "{\n \"rids\": [\"rid1\", \"rid2\"]\n}" }, "url": { "raw": "{{baseUrl}}/storage/bulk_delete?token={{token}}", "host": ["{{baseUrl}}"], "path": ["storage", "bulk_delete"], "query": [{ "key": "token", "value": "{{token}}" }] }, "description": "Delete multiple stored crawls in one request." } }, { "name": "List stored request ids", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/storage/rids?token={{token}}&limit=100", "host": ["{{baseUrl}}"], "path": ["storage", "rids"], "query": [ { "key": "token", "value": "{{token}}" }, { "key": "limit", "value": "100" } ] }, "description": "List stored request ids with scroll-based pagination." } }, { "name": "Total stored count", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/storage/total_count?token={{token}}", "host": ["{{baseUrl}}"], "path": ["storage", "total_count"], "query": [{ "key": "token", "value": "{{token}}" }] }, "description": "Return the total number of pages currently in Cloud Storage." } } ] }, { "name": "Screenshots API", "item": [ { "name": "Capture a screenshot", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/screenshots?token={{jsToken}}&url=https%3A%2F%2Fexample.com&mode=fullpage&format=png", "host": ["{{baseUrl}}"], "path": ["screenshots"], "query": [ { "key": "token", "value": "{{jsToken}}" }, { "key": "url", "value": "https%3A%2F%2Fexample.com" }, { "key": "mode", "value": "fullpage" }, { "key": "format", "value": "png" } ] }, "description": "Render and capture a screenshot in headless Chrome. Requires the JavaScript token. Legacy endpoint (closed to new sign-ups 2024-11-01)." } } ] }, { "name": "Leads API", "item": [ { "name": "Discover emails for a domain", "request": { "method": "GET", "header": [], "url": { "raw": "{{baseUrl}}/leads?token={{token}}&domain=slack.com&limit=10", "host": ["{{baseUrl}}"], "path": ["leads"], "query": [ { "key": "token", "value": "{{token}}" }, { "key": "domain", "value": "slack.com" }, { "key": "limit", "value": "10" } ] }, "description": "Return publicly visible emails for a bare domain, with source URLs. One credit per ten emails. Legacy endpoint (closed to new sign-ups 2024-10-01)." } } ] } ] }