מדריך המרת PDF ל‑XML בפייתון

import os
import xml.etree.ElementTree as ET

import asposebarcodecloud
from asposebarcodecloud import Configuration, BarcodeApi
from asposebarcodecloud.rest import ApiException

# ----------------------------------------------------------------------
# Configuration – replace with your own Aspose Cloud credentials
# ----------------------------------------------------------------------
client_id = os.getenv("ASPOSE_CLIENT_ID", "YOUR_CLIENT_ID")
client_secret = os.getenv("ASPOSE_CLIENT_SECRET", "YOUR_CLIENT_SECRET")

config = Configuration()
config.api_key['client_id'] = client_id
config.api_key['client_secret'] = client_secret
# Optional: set a custom base URL if needed
# config.host = "https://api.aspose.cloud"

barcode_api = BarcodeApi(asposebarcodecloud.ApiClient(config))

# ----------------------------------------------------------------------
# Input / Output files
# ----------------------------------------------------------------------
input_pdf_path = "input.pdf"
output_xml_path = "output.xml"

def recognize_barcodes_from_pdf(pdf_path):
    """Send PDF to Aspose.BarCode Cloud and return recognized barcodes."""
    with open(pdf_path, "rb") as pdf_file:
        try:
            # The API automatically detects the file type; we explicitly set it to PDF.
            # The response is a list of RecognizedBarcode objects.
            result = barcode_api.post_barcode_recognize_from_url_or_content(
                file=pdf_file,
                type="pdf"
            )
            return result.barcodes if result else []
        except ApiException as e:
            print(f"API call failed: {e}")
            return []

def build_xml_from_barcodes(barcodes):
    """Create an XML document from a list of RecognizedBarcode objects."""
    root = ET.Element("Barcodes")
    for barcode in barcodes:
        barcode_el = ET.SubElement(root, "Barcode")
        ET.SubElement(barcode_el, "CodeText").text = barcode.code_text or ""
        ET.SubElement(barcode_el, "Type").text = barcode.type or ""
        # Region information (optional)
        if barcode.region:
            region_el = ET.SubElement(barcode_el, "Region")
            ET.SubElement(region_el, "X").text = str(barcode.region.x)
            ET.SubElement(region_el, "Y").text = str(barcode.region.y)
            ET.SubElement(region_el, "Width").text = str(barcode.region.width)
            ET.SubElement(region_el, "Height").text = str(barcode.region.height)
    return ET.ElementTree(root)

def main():
    barcodes = recognize_barcodes_from_pdf(input_pdf_path)
    if not barcodes:
        print("No barcodes were detected.")
        return

xml_tree = build_xml_from_barcodes(barcodes)
    xml_tree.write(output_xml_path, encoding="utf-8", xml_declaration=True)
    print(f"XML conversion completed. Output saved to '{output_xml_path}'.")

if __name__ == "__main__":
    main()

curl -X POST "https://api.aspose.cloud/connect/token" \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "grant_type=client_credentials&client_id=YOUR_CLIENT_ID&client_secret=YOUR_CLIENT_SECRET"

curl -X PUT "https://api.aspose.cloud/v3.0/barcode/recognize/pdf" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "Content-Type: application/pdf" \
  --data-binary @input.pdf \
  -o response.json

curl -X POST "https://api.aspose.cloud/v3.0/barcode/recognize/fromurlorcontent" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"type":"pdf","file":"input.pdf"}' \
  -o barcodes.json

curl -X GET "https://api.aspose.cloud/v3.0/barcode/recognize/xml/output.xml" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -o output.xml

config = Configuration()
config.api_key['client_id'] = client_id
config.api_key['client_secret'] = client_secret

barcode_api = BarcodeApi(asposebarcodecloud.ApiClient(config))

result = barcode_api.post_barcode_recognize_from_url_or_content(
    file=pdf_file,
    type="pdf"
)

root = ET.Element("Barcodes")
for barcode in barcodes:
    barcode_el = ET.SubElement(root, "Barcode")
    ET.SubElement(barcode_el, "CodeText").text = barcode.code_text or ""
    ET.SubElement(barcode_el, "Type").text = barcode.type or ""

xml_tree.write(output_xml_path, encoding="utf-8", xml_declaration=True)

pip install aspose-barcode-cloud

# config.host = "https://api.yourdomain.com"

config.timeout = 120  # seconds

except ApiException as e:
    print(f"API call failed: {e}")