ByteScout Cloud API Server – PDF To XML API – Python – Convert PDF To XML From Uploaded File Asynchronously

On-demand (REST Web API) version:
 Web API (on-demand version)

On-premise offline SDK for Windows:
 60 Day Free Trial (on-premise)

ConvertPdfToXmlFromUploadedFileAsynchronously.py

      
""" Cloud API asynchronous "PDF To Text" job example.
    Allows to avoid timeout errors when processing huge or scanned PDF documents.
"""
import os
import requests # pip install requests
import time
import datetime

# Please NOTE: In this sample we're assuming Cloud Api Server is hosted at "https://localhost". 
# If it's not then please replace this with with your hosting url.

# Base URL for PDF.co Web API requests
BASE_URL = "https://localhost"

# Source PDF file
SourceFile = ".\\sample.pdf"
# Comma-separated list of page indices (or ranges) to process. Leave empty for all pages. Example: '0,2-5,7-'.
Pages = ""
# PDF document password. Leave empty for unprotected documents.
Password = ""
# Destination XML file name
DestinationFile = ".\\result.xml"
# (!) Make asynchronous job
Async = True


def main(args = None):
    uploadedFileUrl = uploadFile(SourceFile)
    if (uploadedFileUrl != None):
        convertPdfToXml(uploadedFileUrl, DestinationFile)


def convertPdfToXml(uploadedFileUrl, destinationFile):
    """Converts PDF To Xml using PDF.co Web API"""

    # Prepare URL for 'PDF To Xml' API request
    url = "{}/pdf/convert/to/xml?async={}&name={}&password={}&pages={}&url={}".format(
        BASE_URL,
        Async,
        os.path.basename(destinationFile),
        Password,
        Pages,
        uploadedFileUrl
    )

    # Execute request and get response as JSON
    response = requests.get(url, headers={  "content-type": "application/octet-stream" })
    if (response.status_code == 200):
        json = response.json()

        if json["error"] == False:
            # Asynchronous job ID
            jobId = json["jobId"]
            #  URL of the result file
            resultFileUrl = json["url"]
            
            # Check the job status in a loop. 
            # If you don't want to pause the main thread you can rework the code 
            # to use a separate thread for the status checking and completion.
            while True:
                status = checkJobStatus(jobId) # Possible statuses: "working", "failed", "aborted", "success".
                
                # Display timestamp and status (for demo purposes)
                print(datetime.datetime.now().strftime("%H:%M.%S") + ": " + status)
                
                if status == "success":
                    # Download result file
                    r = requests.get(resultFileUrl, stream=True)
                    if (r.status_code == 200):
                        with open(destinationFile, 'wb') as file:
                            for chunk in r:
                                file.write(chunk)
                        print(f"Result file saved as \"{destinationFile}\" file.")
                    else:
                        print(f"Request error: {response.status_code} {response.reason}")
                    break
                elif status == "working":
                    # Pause for a few seconds
                    time.sleep(3)
                else:
                    print(status)
                    break
        else:
            # Show service reported error
            print(json["message"])
    else:
        print(f"Request error: {response.status_code} {response.reason}")


def checkJobStatus(jobId):
    """Checks server job status"""

    url = f"{BASE_URL}/job/check?jobid={jobId}"
    
    response = requests.get(url)
    if (response.status_code == 200):
        json = response.json()
        return json["status"]
    else:
        print(f"Request error: {response.status_code} {response.reason}")

    return None


def uploadFile(fileName):
    """Uploads file to the cloud"""
    
    # 1. RETRIEVE PRESIGNED URL TO UPLOAD FILE.

    # Prepare URL for 'Get Presigned URL' API request
    url = "{}/file/upload/get-presigned-url?contenttype=application/octet-stream&name={}".format(
        BASE_URL, os.path.basename(fileName))
    
    # Execute request and get response as JSON
    response = requests.get(url)
    if (response.status_code == 200):
        json = response.json()
        
        if json["error"] == False:
            # URL to use for file upload
            uploadUrl = json["presignedUrl"]
            # URL for future reference
            uploadedFileUrl = json["url"]

            # 2. UPLOAD FILE TO CLOUD.
            with open(fileName, 'rb') as file:
                requests.put(uploadUrl, data=file, headers={  "content-type": "application/octet-stream" })

            return uploadedFileUrl
        else:
            # Show service reported error
            print(json["message"])    
    else:
        print(f"Request error: {response.status_code} {response.reason}")

    return None


if __name__ == '__main__':
    main()
    

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Cloud API Server Home Page

Explore ByteScout Cloud API Server Documentation

Explore Samples

Sign Up for ByteScout Cloud API Server Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout Cloud API Server Home Page

Explore ByteScout Cloud API Server Documentation

Explore Samples

Sign Up for ByteScout Cloud API Server Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples