{
"opencollection": "1.0.0",
"info": {
"name": "WebScraping. AI API",
"version": "3.2.1"
},
"request": {
"auth": {
"type": "apikey",
"key": "api_key",
"value": "{{api_key}}",
"placement": "query"
}
},
"items": [
{
"info": {
"name": "AI",
"type": "folder"
},
"items": [
{
"info": {
"name": "Get an answer to a question about a given web page",
"type": "http"
},
"http": {
"method": "GET",
"url": "https://api.webscraping.ai/ai/question",
"params": [
{
"name": "url",
"value": "https://example.com",
"type": "query",
"description": "URL of the target page."
},
{
"name": "question",
"value": "What is the summary of this page content?",
"type": "query",
"description": "Question or instructions to ask the LLM model about the target page."
},
{
"name": "headers",
"value": "{\"Cookie\":\"session=some_id\"}",
"type": "query",
"description": "HTTP headers to pass to the target page. Can be specified either via a nested query parameter (...&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (...&headers={\"One\": \"value1\", \"Another\": \"value2\"})."
},
{
"name": "timeout",
"value": "10000",
"type": "query",
"description": "Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000)."
},
{
"name": "js",
"value": "true",
"type": "query",
"description": "Execute on-page JavaScript using a headless browser (true by default)."
},
{
"name": "js_timeout",
"value": "2000",
"type": "query",
"description": "Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page."
},
{
"name": "wait_for",
"value": "",
"type": "query",
"description": "CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout. If the element doesn't appear within the request timeout, the request fails with a 500 error naming the selector and including the target page's HTTP status code and a preview of the page body."
},
{
"name": "proxy",
"value": "datacenter",
"type": "query",
"description": "Type of proxy. Use `residential` if your site restricts traffic from datacenters, or `stealth` for the most heavily protected sites with advanced anti-bot detection (`datacenter` by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details."
},
{
"name": "country",
"value": "us",
"type": "query",
"description": "Country of the proxy to use (US by default)."
},
{
"name": "custom_proxy",
"value": "null",
"type": "query",
"description": "Your own proxy URL to use instead of our built-in proxy pool in \"http://user:password@host:port\" format (Smartproxy for example)."
},
{
"name": "device",
"value": "desktop",
"type": "query",
"description": "Type of device emulation."
},
{
"name": "error_on_404",
"value": "false",
"type": "query",
"description": "Return error on 404 HTTP status on the target page (false by default)."
},
{
"name": "error_on_redirect",
"value": "false",
"type": "query",
"description": "Return error on redirect on the target page (false by default)."
},
{
"name": "js_script",
"value": "document.querySelector('button').click();",
"type": "query",
"description": "Custom JavaScript code to execute on the target page."
},
{
"name": "format",
"value": "json",
"type": "query",
"description": "Format of the response (text by default). \"json\" will return a JSON object with the response, \"text\" will return a plain text/HTML response."
}
]
},
"docs": "Returns the answer in plain text. Proxies and Chromium JavaScript rendering are used for page retrieval and processing, then the answer is extracted using an LLM model."
},
{
"info": {
"name": "Extract structured data fields from a web page",
"type": "http"
},
"http": {
"method": "GET",
"url": "https://api.webscraping.ai/ai/fields",
"params": [
{
"name": "url",
"value": "https://example.com",
"type": "query",
"description": "URL of the target page."
},
{
"name": "fields",
"value": "[object Object]",
"type": "query",
"description": "Object describing fields to extract from the page and their descriptions"
},
{
"name": "headers",
"value": "{\"Cookie\":\"session=some_id\"}",
"type": "query",
"description": "HTTP headers to pass to the target page. Can be specified either via a nested query parameter (...&headers[One]=value1&headers=[Another]=value2) or as a JSON encoded object (...&headers={\"One\": \"value1\", \"Another\": \"value2\"})."
},
{
"name": "timeout",
"value": "10000",
"type": "query",
"description": "Maximum web page retrieval time in ms. Increase it in case of timeout errors (10000 by default, maximum is 30000)."
},
{
"name": "js",
"value": "true",
"type": "query",
"description": "Execute on-page JavaScript using a headless browser (true by default)."
},
{
"name": "js_timeout",
"value": "2000",
"type": "query",
"description": "Maximum JavaScript rendering time in ms. Increase it in case if you see a loading indicator instead of data on the target page."
},
{
"name": "wait_for",
"value": "",
"type": "query",
"description": "CSS selector to wait for before returning the page content. Useful for pages with dynamic content loading. Overrides js_timeout. If the element doesn't appear within the request timeout, the request fails with a 500 error naming the selector and including the target page's HTTP status code and a preview of the page body."
},
{
"name": "proxy",
"value": "datacenter",
"type": "query",
"description": "Type of proxy. Use `residential` if your site restricts traffic from datacenters, or `stealth` for the most heavily protected sites with advanced anti-bot detection (`datacenter` by default). Residential and stealth proxy requests are more expensive than datacenter, see the pricing page for details."
},
{
"name": "country",
"value": "us",
"type": "query",
"description": "Country of the proxy to use (US by default)."
},
{
"name": "custom_proxy",
"value": "null",
"type": "query",
"description": "Your own proxy URL to use instead of our built-in proxy pool in \"http://user:password@host:port\" format (Smartproxy for example)."
},
{
"name": "device",
"value": "desktop",
"type": "query",
"description": "Type of device emulation."
},
{
"name": "error_on_404",
"value": "false",
"type": "query",
"description": "Return error on 404 HTTP status on the target page (false by default)."
},
{
"name": "error_on_redirect",
"value": "false",
"type": "query",
"description": "Return error on redirect on the target page (false by default)."
},
{
"name": "js_script",
"value": "document.querySelector('button').click();",
"type": "query",
"description": "Custom JavaScript code to execute on the target page."
}
]
},
"docs": "Returns structured data fields extracted from the webpage using an LLM model. Proxies and Chromium JavaScript rendering are used for page retrieval and processing."
}
]
}
],
"bundled": true
}