Supported File Types

# Extract with PDF-specific options
result = client.extract(
    file_path="document.pdf",
    pages="1-10",  # Process specific pages
    extract_figure=True,  # Extract embedded images
    return_html=False  # Get markdown output
)

# High-quality image extraction
result = client.extract(
    file_path="scanned_document.jpg"
)

# Extract structured data from Excel
schema = {
    "headers": ["string"],
    "data": [["string"]]
}

result = client.extract(
    file_path="spreadsheet.xlsx",
    schema=schema
)

# Direct file upload (recommended for files < 10MB)
with open("document.pdf", "rb") as f:
    response = requests.post(
        "https://api.runpulse.com/extract",
        headers={"x-api-key": API_KEY},
        files={"file": f}
    )

# Upload to S3 first
upload_response = requests.post(
    "https://api.runpulse.com/convert",
    headers={"x-api-key": API_KEY},
    files={"file": open("large_file.pdf", "rb")}
)

file_url = upload_response.json()["s3_object_url"]

# Then extract using the URL
extract_response = requests.post(
    "https://api.runpulse.com/extract",
    headers={"x-api-key": API_KEY},
    json={"file-url": file_url}
)

# Extract from URL
response = requests.post(
    "https://api.runpulse.com/extract",
    headers={"x-api-key": API_KEY},
    json={"file-url": "https://example.com/document.pdf"}
)

# API automatically detects format
result = client.extract(file_path="document")  # Works even without extension