Examples

Extract Text from File

Extract plain text from various document formats including PDF, DOCX, TXT, and more. This example shows you how to upload a file and extract its text content.

Overview

The /extract/file endpoint accepts file uploads and returns the extracted text content. Supported formats include PDF, Word documents, text files, and many other document types.

cURL Example

Code
 
curl -X POST https://api.crawler.dev/v1/extract/file \
  -H "x-api-key: YOUR_API_KEY" \
  -F "file=@document.pdf"

Response:

Code
 
{
  "filename": "document.pdf",
  "contentType": "application/pdf",
  "size": 245760,
  "text": "This is the extracted text content from the document..."
}

JavaScript Example

Using Fetch API

Code
 
async function extractTextFromFile(file) {
  const formData = new FormData();
  formData.append('file', file);

  const response = await fetch('https://api.crawler.dev/v1/extract/file', {
    method: 'POST',
    headers: {
      'x-api-key': 'YOUR_API_KEY'
    },
    body: formData
  });

  if (!response.ok) {
    const error = await response.json();
    throw new Error(error.error?.message || 'Failed to extract text');
  }

  const result = await response.json();
  return result.text;
}

// Usage with file input
const fileInput = document.querySelector('input[type="file"]');
fileInput.addEventListener('change', async (e) => {
  const file = e.target.files[0];
  if (file) {
    try {
      const text = await extractTextFromFile(file);
      console.log('Extracted text:', text);
    } catch (error) {
      console.error('Error:', error.message);
    }
  }
});

Using Node.js with FormData

Code
 
const FormData = require('form-data');
const fs = require('fs');
const fetch = require('node-fetch');

async function extractTextFromFile(filePath) {
  const form = new FormData();
  form.append('file', fs.createReadStream(filePath));

  const response = await fetch('https://api.crawler.dev/v1/extract/file', {
    method: 'POST',
    headers: {
      'x-api-key': process.env.CRAWLER_API_KEY,
      ...form.getHeaders()
    },
    body: form
  });

  if (!response.ok) {
    const error = await response.json();
    throw new Error(error.error?.message || 'Failed to extract text');
  }

  const result = await response.json();
  return result;
}

// Usage
extractTextFromFile('./document.pdf')
  .then(result => {
    console.log(`Extracted ${result.text.length} characters from ${result.filename}`);
    console.log(result.text);
  })
  .catch(error => console.error('Error:', error.message));

Python Example

Code
 
import requests
import os

def extract_text_from_file(file_path):
    """
    Extract text from a file using the crawler.dev API.
    
    Args:
        file_path: Path to the file to extract text from
        
    Returns:
        dict: API response containing extracted text and metadata
    """
    api_key = os.getenv('CRAWLER_API_KEY')
    
    if not api_key:
        raise ValueError("CRAWLER_API_KEY environment variable not set")
    
    url = "https://api.crawler.dev/v1/extract/file"
    headers = {
        "x-api-key": api_key
    }
    
    with open(file_path, 'rb') as file:
        files = {'file': file}
        response = requests.post(url, headers=headers, files=files)
    
    response.raise_for_status()
    return response.json()

# Usage
try:
    result = extract_text_from_file('document.pdf')
    print(f"Extracted {len(result['text'])} characters from {result['filename']}")
    print(result['text'])
except requests.exceptions.RequestException as e:
    print(f"Error: {e}")

Error Handling

Always handle potential errors when extracting text from files:

Code
 
async function extractTextWithErrorHandling(file) {
  try {
    const formData = new FormData();
    formData.append('file', file);

    const response = await fetch('https://api.crawler.dev/v1/extract/file', {
      method: 'POST',
      headers: {
        'x-api-key': 'YOUR_API_KEY'
      },
      body: formData
    });

    const data = await response.json();

    if (!response.ok) {
      // Handle API errors
      if (response.status === 400) {
        throw new Error(`Invalid request: ${data.error?.message}`);
      } else if (response.status === 401) {
        throw new Error('Invalid API key');
      } else if (response.status === 413) {
        throw new Error('File too large');
      } else {
        throw new Error(data.error?.message || 'Unknown error');
      }
    }

    if (!data.text) {
      throw new Error('No text extracted from file');
    }

    return data;
  } catch (error) {
    if (error.name === 'TypeError' && error.message.includes('fetch')) {
      throw new Error('Network error: Check your internet connection');
    }
    throw error;
  }
}

Supported File Types

The API supports a wide range of file formats. See the Supported File Types page for a complete list.

Common formats include:

• Documents: PDF, DOC, DOCX, RTF, TXT
• Spreadsheets: XLS, XLSX, CSV
• Presentations: PPT, PPTX
• Images: PNG, JPG (with OCR)
• And many more

File Size Limits

• Maximum file size: 100 MB
• Recommended: Files under 10 MB for faster processing

Next Steps

• Learn how to extract text from web pages
• Explore batch processing for multiple files
• Check out the API Reference for complete documentation