Scrape Content

Scrape Content

curl --request POST \
  --url https://api.example.com/scrape \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "<string>",
  "async": true,
  "render": true,
  "method": "<string>",
  "format": "<string>",
  "country": "<string>",
  "includeHeaders": true,
  "headers": {},
  "body": {},
  "documentOptions": {},
  "documentOptions.password": "<string>",
  "documentOptions.pages": [
    123
  ],
  "documentOptions.pageBreak": "<string>",
  "documentOptions.stripHeadersFooters": true,
  "extract": {},
  "extract.schema": {},
  "extract.prompt": "<string>",
  "extract.systemPrompt": "<string>",
  "extract.model": "<string>",
  "extract.includeMetadata": true
}
'

import requests

url = "https://api.example.com/scrape"

payload = {
    "url": "<string>",
    "async": True,
    "render": True,
    "method": "<string>",
    "format": "<string>",
    "country": "<string>",
    "includeHeaders": True,
    "headers": {},
    "body": {},
    "documentOptions": {},
    "documentOptions.password": "<string>",
    "documentOptions.pages": [123],
    "documentOptions.pageBreak": "<string>",
    "documentOptions.stripHeadersFooters": True,
    "extract": {},
    "extract.schema": {},
    "extract.prompt": "<string>",
    "extract.systemPrompt": "<string>",
    "extract.model": "<string>",
    "extract.includeMetadata": True
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    url: '<string>',
    async: true,
    render: true,
    method: '<string>',
    format: '<string>',
    country: '<string>',
    includeHeaders: true,
    headers: {},
    body: JSON.stringify({}),
    documentOptions: {},
    'documentOptions.password': '<string>',
    'documentOptions.pages': [123],
    'documentOptions.pageBreak': '<string>',
    'documentOptions.stripHeadersFooters': true,
    extract: {},
    'extract.schema': {},
    'extract.prompt': '<string>',
    'extract.systemPrompt': '<string>',
    'extract.model': '<string>',
    'extract.includeMetadata': true
  })
};

fetch('https://api.example.com/scrape', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/scrape",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'url' => '<string>',
    'async' => true,
    'render' => true,
    'method' => '<string>',
    'format' => '<string>',
    'country' => '<string>',
    'includeHeaders' => true,
    'headers' => [
        
    ],
    'body' => [
        
    ],
    'documentOptions' => [
        
    ],
    'documentOptions.password' => '<string>',
    'documentOptions.pages' => [
        123
    ],
    'documentOptions.pageBreak' => '<string>',
    'documentOptions.stripHeadersFooters' => true,
    'extract' => [
        
    ],
    'extract.schema' => [
        
    ],
    'extract.prompt' => '<string>',
    'extract.systemPrompt' => '<string>',
    'extract.model' => '<string>',
    'extract.includeMetadata' => true
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/scrape"

	payload := strings.NewReader("{\n  \"url\": \"<string>\",\n  \"async\": true,\n  \"render\": true,\n  \"method\": \"<string>\",\n  \"format\": \"<string>\",\n  \"country\": \"<string>\",\n  \"includeHeaders\": true,\n  \"headers\": {},\n  \"body\": {},\n  \"documentOptions\": {},\n  \"documentOptions.password\": \"<string>\",\n  \"documentOptions.pages\": [\n    123\n  ],\n  \"documentOptions.pageBreak\": \"<string>\",\n  \"documentOptions.stripHeadersFooters\": true,\n  \"extract\": {},\n  \"extract.schema\": {},\n  \"extract.prompt\": \"<string>\",\n  \"extract.systemPrompt\": \"<string>\",\n  \"extract.model\": \"<string>\",\n  \"extract.includeMetadata\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/scrape")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"<string>\",\n  \"async\": true,\n  \"render\": true,\n  \"method\": \"<string>\",\n  \"format\": \"<string>\",\n  \"country\": \"<string>\",\n  \"includeHeaders\": true,\n  \"headers\": {},\n  \"body\": {},\n  \"documentOptions\": {},\n  \"documentOptions.password\": \"<string>\",\n  \"documentOptions.pages\": [\n    123\n  ],\n  \"documentOptions.pageBreak\": \"<string>\",\n  \"documentOptions.stripHeadersFooters\": true,\n  \"extract\": {},\n  \"extract.schema\": {},\n  \"extract.prompt\": \"<string>\",\n  \"extract.systemPrompt\": \"<string>\",\n  \"extract.model\": \"<string>\",\n  \"extract.includeMetadata\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/scrape")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"url\": \"<string>\",\n  \"async\": true,\n  \"render\": true,\n  \"method\": \"<string>\",\n  \"format\": \"<string>\",\n  \"country\": \"<string>\",\n  \"includeHeaders\": true,\n  \"headers\": {},\n  \"body\": {},\n  \"documentOptions\": {},\n  \"documentOptions.password\": \"<string>\",\n  \"documentOptions.pages\": [\n    123\n  ],\n  \"documentOptions.pageBreak\": \"<string>\",\n  \"documentOptions.stripHeadersFooters\": true,\n  \"extract\": {},\n  \"extract.schema\": {},\n  \"extract.prompt\": \"<string>\",\n  \"extract.systemPrompt\": \"<string>\",\n  \"extract.model\": \"<string>\",\n  \"extract.includeMetadata\": true\n}"

response = http.request(request)
puts response.read_body

POST

scrape

Scrape Content

curl --request POST \
  --url https://api.example.com/scrape \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "<string>",
  "async": true,
  "render": true,
  "method": "<string>",
  "format": "<string>",
  "country": "<string>",
  "includeHeaders": true,
  "headers": {},
  "body": {},
  "documentOptions": {},
  "documentOptions.password": "<string>",
  "documentOptions.pages": [
    123
  ],
  "documentOptions.pageBreak": "<string>",
  "documentOptions.stripHeadersFooters": true,
  "extract": {},
  "extract.schema": {},
  "extract.prompt": "<string>",
  "extract.systemPrompt": "<string>",
  "extract.model": "<string>",
  "extract.includeMetadata": true
}
'

import requests

url = "https://api.example.com/scrape"

payload = {
    "url": "<string>",
    "async": True,
    "render": True,
    "method": "<string>",
    "format": "<string>",
    "country": "<string>",
    "includeHeaders": True,
    "headers": {},
    "body": {},
    "documentOptions": {},
    "documentOptions.password": "<string>",
    "documentOptions.pages": [123],
    "documentOptions.pageBreak": "<string>",
    "documentOptions.stripHeadersFooters": True,
    "extract": {},
    "extract.schema": {},
    "extract.prompt": "<string>",
    "extract.systemPrompt": "<string>",
    "extract.model": "<string>",
    "extract.includeMetadata": True
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    url: '<string>',
    async: true,
    render: true,
    method: '<string>',
    format: '<string>',
    country: '<string>',
    includeHeaders: true,
    headers: {},
    body: JSON.stringify({}),
    documentOptions: {},
    'documentOptions.password': '<string>',
    'documentOptions.pages': [123],
    'documentOptions.pageBreak': '<string>',
    'documentOptions.stripHeadersFooters': true,
    extract: {},
    'extract.schema': {},
    'extract.prompt': '<string>',
    'extract.systemPrompt': '<string>',
    'extract.model': '<string>',
    'extract.includeMetadata': true
  })
};

fetch('https://api.example.com/scrape', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.example.com/scrape",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'url' => '<string>',
    'async' => true,
    'render' => true,
    'method' => '<string>',
    'format' => '<string>',
    'country' => '<string>',
    'includeHeaders' => true,
    'headers' => [
        
    ],
    'body' => [
        
    ],
    'documentOptions' => [
        
    ],
    'documentOptions.password' => '<string>',
    'documentOptions.pages' => [
        123
    ],
    'documentOptions.pageBreak' => '<string>',
    'documentOptions.stripHeadersFooters' => true,
    'extract' => [
        
    ],
    'extract.schema' => [
        
    ],
    'extract.prompt' => '<string>',
    'extract.systemPrompt' => '<string>',
    'extract.model' => '<string>',
    'extract.includeMetadata' => true
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.example.com/scrape"

	payload := strings.NewReader("{\n  \"url\": \"<string>\",\n  \"async\": true,\n  \"render\": true,\n  \"method\": \"<string>\",\n  \"format\": \"<string>\",\n  \"country\": \"<string>\",\n  \"includeHeaders\": true,\n  \"headers\": {},\n  \"body\": {},\n  \"documentOptions\": {},\n  \"documentOptions.password\": \"<string>\",\n  \"documentOptions.pages\": [\n    123\n  ],\n  \"documentOptions.pageBreak\": \"<string>\",\n  \"documentOptions.stripHeadersFooters\": true,\n  \"extract\": {},\n  \"extract.schema\": {},\n  \"extract.prompt\": \"<string>\",\n  \"extract.systemPrompt\": \"<string>\",\n  \"extract.model\": \"<string>\",\n  \"extract.includeMetadata\": true\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.example.com/scrape")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"<string>\",\n  \"async\": true,\n  \"render\": true,\n  \"method\": \"<string>\",\n  \"format\": \"<string>\",\n  \"country\": \"<string>\",\n  \"includeHeaders\": true,\n  \"headers\": {},\n  \"body\": {},\n  \"documentOptions\": {},\n  \"documentOptions.password\": \"<string>\",\n  \"documentOptions.pages\": [\n    123\n  ],\n  \"documentOptions.pageBreak\": \"<string>\",\n  \"documentOptions.stripHeadersFooters\": true,\n  \"extract\": {},\n  \"extract.schema\": {},\n  \"extract.prompt\": \"<string>\",\n  \"extract.systemPrompt\": \"<string>\",\n  \"extract.model\": \"<string>\",\n  \"extract.includeMetadata\": true\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.example.com/scrape")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'application/json'
request.body = "{\n  \"url\": \"<string>\",\n  \"async\": true,\n  \"render\": true,\n  \"method\": \"<string>\",\n  \"format\": \"<string>\",\n  \"country\": \"<string>\",\n  \"includeHeaders\": true,\n  \"headers\": {},\n  \"body\": {},\n  \"documentOptions\": {},\n  \"documentOptions.password\": \"<string>\",\n  \"documentOptions.pages\": [\n    123\n  ],\n  \"documentOptions.pageBreak\": \"<string>\",\n  \"documentOptions.stripHeadersFooters\": true,\n  \"extract\": {},\n  \"extract.schema\": {},\n  \"extract.prompt\": \"<string>\",\n  \"extract.systemPrompt\": \"<string>\",\n  \"extract.model\": \"<string>\",\n  \"extract.includeMetadata\": true\n}"

response = http.request(request)
puts response.read_body

Overview

The /scrape endpoint initiates a new web scraping job with the specified URL and options. It returns the scraped content directly and supports both renderless and renderful scraping modes. You can also use AI-powered extraction to get structured data from the page.

Parameters

Request Body

string

required

The URL to scrape

boolean

default:"false"

Whether the request should be asynchronous. When true, returns a job ID immediately that can be used to check status.

boolean

default:"false"

Whether to render JavaScript on the page. Enable for dynamic content loaded via JavaScript.

string

default:"get"

HTTP method for the request. Options: get, post, put, delete, patch, head, options

string

default:"raw"

Response format. Options: raw, json, markdown.When format is markdown, ScrapEngine auto-detects the response type:

HTML → converted via Turndown
PDF / XLSX / DOCX → extracted via the built-in document parser (see documentOptions below)

string

default:"us"

Proxy country for geo-targeted requests (e.g., us, uk, de)

boolean

default:"false"

Whether to include response headers in the response

object

HTTP headers for the request

{
  "User-Agent": "Mozilla/5.0...",
  "Accept-Language": "en-US,en;q=0.9"
}

object

Request body content (for POST/PUT requests)

Document Extraction Options

Applied only when format is markdown AND the target response is a PDF, XLSX, or DOCX file. Ignored for HTML responses.

object

PDF / XLSX / DOCX extraction options.

string

Password for encrypted PDFs.

number[]

1-based page numbers to include (PDF only). Omit for the whole document.

{ "pages": [1, 2, 5] }

string

How PDF page boundaries appear in the output markdown. Options: none (no separator), hr (horizontal rule), comment (HTML comment).

boolean

default:"true"

Strip recurring page headers and footers from PDF output.

LLM Extraction Options

object

AI-powered extraction options. When provided, the scraped content will be processed by an LLM to extract structured data.

object

JSON Schema defining the structure to extract. Use this for precise, typed extraction.

{
  "type": "object",
  "properties": {
    "title": { "type": "string", "description": "The page title" },
    "price": { "type": "number", "description": "Product price" },
    "features": {
      "type": "array",
      "items": { "type": "string" }
    }
  },
  "required": ["title", "price"]
}

string

Natural language prompt describing what to extract. Use this for flexible, conversational extraction.

string

Custom system prompt to guide the LLM behavior

string

default:"gpt-4o-mini"

LLM model to use for extraction. Options: gpt-4o, gpt-4o-mini, claude-3-5-sonnet

boolean

default:"true"

Whether to include extraction metadata (tokens used, cost) in response

Example Requests

Basic Scraping

curl -X POST "https://api.scrapengine.io/api/v1/scrape" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.example.com/product",
    "render": true
  }'

const response = await fetch("https://api.scrapengine.io/api/v1/scrape", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    url: "https://www.example.com/product",
    render: true,
  }),
});

const data = await response.text();
console.log(data);

import requests

url = "https://api.scrapengine.io/api/v1/scrape"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "url": "https://www.example.com/product",
    "render": True
}

response = requests.post(url, headers=headers, json=data)
print(response.text)

Scrape a PDF as Markdown

Point /scrape at a PDF (or XLSX / DOCX) URL with format: "markdown" to get extracted text back as Markdown.

curl -X POST "https://api.scrapengine.io/api/v1/scrape" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.example.com/whitepaper.pdf",
    "format": "markdown",
    "documentOptions": {
      "pages": [1, 2, 3],
      "stripHeadersFooters": true
    }
  }'

const response = await fetch("https://api.scrapengine.io/api/v1/scrape", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    url: "https://www.example.com/whitepaper.pdf",
    format: "markdown",
    documentOptions: {
      pages: [1, 2, 3],
      stripHeadersFooters: true,
    },
  }),
});

const markdown = await response.text();
console.log(markdown);

import requests

url = "https://api.scrapengine.io/api/v1/scrape"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "url": "https://www.example.com/whitepaper.pdf",
    "format": "markdown",
    "documentOptions": {
        "pages": [1, 2, 3],
        "stripHeadersFooters": True
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.text)

With LLM Extraction (Schema)

Extract structured data using a JSON schema:

curl -X POST "https://api.scrapengine.io/api/v1/scrape" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.example.com/product",
    "render": true,
    "extract": {
      "schema": {
        "type": "object",
        "properties": {
          "productName": { "type": "string", "description": "The product name" },
          "price": { "type": "number", "description": "Price in USD" },
          "rating": { "type": "number", "description": "Average rating out of 5" },
          "features": {
            "type": "array",
            "items": { "type": "string" },
            "description": "List of product features"
          }
        },
        "required": ["productName", "price"]
      },
      "model": "gpt-4o-mini"
    }
  }'

const response = await fetch("https://api.scrapengine.io/api/v1/scrape", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    url: "https://www.example.com/product",
    render: true,
    extract: {
      schema: {
        type: "object",
        properties: {
          productName: { type: "string", description: "The product name" },
          price: { type: "number", description: "Price in USD" },
          rating: { type: "number", description: "Average rating out of 5" },
          features: {
            type: "array",
            items: { type: "string" },
            description: "List of product features",
          },
        },
        required: ["productName", "price"],
      },
      model: "gpt-4o-mini",
    },
  }),
});

const data = await response.json();
console.log(data);

import requests

url = "https://api.scrapengine.io/api/v1/scrape"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "url": "https://www.example.com/product",
    "render": True,
    "extract": {
        "schema": {
            "type": "object",
            "properties": {
                "productName": {"type": "string", "description": "The product name"},
                "price": {"type": "number", "description": "Price in USD"},
                "rating": {"type": "number", "description": "Average rating out of 5"},
                "features": {
                    "type": "array",
                    "items": {"type": "string"},
                    "description": "List of product features"
                }
            },
            "required": ["productName", "price"]
        },
        "model": "gpt-4o-mini"
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

With LLM Extraction (Prompt)

Extract data using a natural language prompt:

curl -X POST "https://api.scrapengine.io/api/v1/scrape" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.example.com/article",
    "extract": {
      "prompt": "Extract the article title, author name, publication date, and a brief summary of the main points",
      "model": "claude-3-5-sonnet"
    }
  }'

const response = await fetch("https://api.scrapengine.io/api/v1/scrape", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    url: "https://www.example.com/article",
    extract: {
      prompt:
        "Extract the article title, author name, publication date, and a brief summary of the main points",
      model: "claude-3-5-sonnet",
    },
  }),
});

const data = await response.json();
console.log(data);

import requests

url = "https://api.scrapengine.io/api/v1/scrape"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "url": "https://www.example.com/article",
    "extract": {
        "prompt": "Extract the article title, author name, publication date, and a brief summary of the main points",
        "model": "claude-3-5-sonnet"
    }
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

Response

Success Response (200)

Without extraction - Returns the scraped HTML content directly:

<html>
  <head>
    <title>Example Product</title>
  </head>
  <body>
    <!-- Scraped content here -->
  </body>
</html>

With extraction - Returns structured JSON:

{
  "data": {
    "productName": "Premium Wireless Headphones",
    "price": 299.99,
    "rating": 4.5,
    "features": [
      "Active Noise Cancellation",
      "40-hour battery life",
      "Bluetooth 5.0"
    ]
  },
  "metadata": {
    "tokensUsed": 1250,
    "model": "gpt-4o-mini"
  }
}

Response Headers

Header	Description
`x-remaining-credits`	Number of API credits remaining
`x-trace-id`	Unique identifier for the request

Error Responses

Status	Description
`400`	Bad Request - Invalid parameters or URL
`401`	Unauthorized - Invalid or missing API key
`403`	Forbidden - Access denied to target resource
`404`	Not Found - Target URL not found
`408`	Request Timeout
`500`	Internal Server Error
`550`	Faulted After Retries - Job failed after multiple attempts

Error Response Format:

{
  "error": "Error description message",
  "traceId": "abc123-def456",
  "timestamp": "2024-01-15T10:30:00.000Z"
}

Use Cases

E-commerce scraping: Extract product information, prices, and availability
Content aggregation: Collect articles, blog posts, and news content
Lead generation: Extract contact information and company details
Competitor analysis: Monitor competitor websites and pricing
SEO analysis: Extract meta tags, headings, and content structure
AI-powered extraction: Use LLM to extract structured data without writing parsers

API documentation

Web Scraping

Browser Sessions

Sessions

Tools

Tasks

AI

Recording

Extensions

Session Proxy

Clipboard

Filesystem

Session Files

Credentials & Vault

Search Engines

E-Commerce

Overview

Parameters

Request Body

Document Extraction Options

LLM Extraction Options

Example Requests

Basic Scraping

Scrape a PDF as Markdown

With LLM Extraction (Schema)

With LLM Extraction (Prompt)

Response

Success Response (200)

Response Headers

Error Responses

Use Cases

​Overview

​Parameters

​Request Body

​Document Extraction Options

​LLM Extraction Options

​Example Requests

​Basic Scraping

​Scrape a PDF as Markdown

​With LLM Extraction (Schema)

​With LLM Extraction (Prompt)

​Response

​Success Response (200)

​Response Headers

​Error Responses

​Use Cases

Overview

Parameters

Request Body

Document Extraction Options

LLM Extraction Options

Example Requests

Basic Scraping

Scrape a PDF as Markdown

With LLM Extraction (Schema)

With LLM Extraction (Prompt)

Response

Success Response (200)

Response Headers

Error Responses

Use Cases