{ "opencollection": "1.0.0", "info": { "name": "Crawlbase Crawling API API", "version": "1.0" }, "request": { "auth": { "type": "apikey", "key": "token", "value": "{{token}}", "placement": "query" } }, "items": [ { "info": { "name": "Crawling API", "type": "folder" }, "items": [ { "info": { "name": "Crawl a URL", "type": "http" }, "http": { "method": "GET", "url": "https://api.crawlbase.com/", "params": [ { "name": "url", "value": "", "type": "query", "description": "Fully URL-encoded target URL, including http:// or https://." }, { "name": "format", "value": "", "type": "query", "description": "Response format - html (default), json, or md (Markdown)." }, { "name": "country", "value": "", "type": "query", "description": "Two-letter ISO 3166 country code to geolocate the request (for example US, DE, GB)." }, { "name": "device", "value": "", "type": "query", "description": "Device profile - desktop (default), tablet, or mobile." }, { "name": "user_agent", "value": "", "type": "query", "description": "Override the User-Agent header sent to the target." }, { "name": "scraper", "value": "", "type": "query", "description": "Name of a built-in extractor to apply to the crawled page (returns parsed JSON)." }, { "name": "autoparse", "value": "", "type": "query", "description": "Auto-detect the page type and return parsed JSON." }, { "name": "page_wait", "value": "", "type": "query", "description": "Milliseconds to wait after page load before capture (JavaScript token only)." }, { "name": "ajax_wait", "value": "", "type": "query", "description": "Wait for AJAX / network idle before capture (JavaScript token only)." }, { "name": "css_click_selector", "value": "", "type": "query", "description": "CSS selector to click before capture (JavaScript token only)." }, { "name": "scroll", "value": "", "type": "query", "description": "Scroll toward the bottom of the page before capture (JavaScript token only)." }, { "name": "scroll_interval", "value": "", "type": "query", "description": "Maximum seconds to scroll (default 10, max 60)." }, { "name": "screenshot", "value": "", "type": "query", "description": "Capture a JPEG screenshot of the rendered page (JavaScript token only)." }, { "name": "get_headers", "value": "", "type": "query", "description": "Return the target's response headers alongside the body." }, { "name": "get_cookies", "value": "", "type": "query", "description": "Return the target's Set-Cookie values." }, { "name": "cookies_session", "value": "", "type": "query", "description": "Sticky session identifier to reuse cookies across requests." }, { "name": "store", "value": "", "type": "query", "description": "Persist the response in Crawlbase Cloud Storage." }, { "name": "async", "value": "", "type": "query", "description": "Queue the request and return immediately with a request id (rid)." }, { "name": "callback", "value": "", "type": "query", "description": "Webhook URL that Crawlbase posts async results to." } ] }, "docs": "Fetches the target `url` through Crawlbase's proxy network and returns the page. Use the Normal (TCP) token for static HTML/JSON, or the JavaScript token to render the page in headless Chrome before returning it. Crawlbase status is surfaced in the `pc_status` response header; requests that do not return `pc_status: 200` are not charged." }, { "info": { "name": "Crawl a URL (POST)", "type": "http" }, "http": { "method": "POST", "url": "https://api.crawlbase.com/", "params": [ { "name": "url", "value": "", "type": "query", "description": "Fully URL-encoded target URL, including http:// or https://." }, { "name": "format", "value": "", "type": "query", "description": "Response format - html (default), json, or md (Markdown)." }, { "name": "country", "value": "", "type": "query", "description": "Two-letter ISO 3166 country code to geolocate the request (for example US, DE, GB)." }, { "name": "device", "value": "", "type": "query", "description": "Device profile - desktop (default), tablet, or mobile." } ], "body": { "type": "form-urlencoded", "data": [] } }, "docs": "Same as the GET crawl operation, but the request payload (for example, POST form data to submit to the target) is sent in the request body. The `token` and `url` remain query parameters." } ] } ], "bundled": true }