Appearance
POST /v1/scrape
POST
/v1/scrape
Scrape a single webpage
Authorizations
bearerAuth
TypeHTTP (bearer)
Request Body
application/json
JSON
{
"formats": [
[
"markdown",
"html"
]
],
"headers": {
"additionalProperties": "string"
},
"includeTags": [
[
"h1",
"h2",
"p",
"article"
]
],
"excludeTags": [
[
"nav",
"footer",
"script",
"style"
]
],
"timeout": 30000,
"waitFor": 3000,
"extract": {
"mode": "string",
"schema": {
"type": "object",
"properties": {
"title": {
"type": "string"
},
"price": {
"type": "number"
},
"description": {
"type": "string"
}
},
"required": [
"title",
"price"
]
},
"systemPrompt": "Based on the information on the page, extract all the information from the schema. Try to extract all the fields even those that might not be marked as required.",
"prompt": "Extract the main article title and author from this page"
},
"url": "string",
"origin": "api",
"webhookUrls": [
[
"https://your-webhook.com/endpoint"
]
],
"metadata": {
"userId": "12345",
"source": "api"
}
}
Responses
Successful response
application/json
JSON
{
"success": true,
"warning": "string",
"data": {
"markdown": "string",
"extract": "string",
"html": "string",
"rawHtml": "string",
"links": [
"string"
],
"screenshot": "string",
"metadata": {
"additionalProperties": {
}
}
},
"scrape_id": "string"
}