Convert PDF To XML From Uploaded File Asynchronously - Python
PDF To XML sample in Python demonstrating ‘Convert PDF To XML From Uploaded File Asynchronously’
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
# The authentication key (API Key).
# Get your own by registering at https://app.pdf.co
API_KEY = "******************************************"
# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"
# 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 requests params as JSON
# See documentation: https://apidocs.pdf.co
parameters = {}
parameters["async"] = Async
parameters["name"] = os.path.basename(destinationFile)
parameters["password"] = Password
parameters["pages"] = Pages
parameters["url"] = uploadedFileUrl
# Prepare URL for 'PDF To Xml' API request
url = "{}/pdf/convert/to/xml".format(BASE_URL)
# Execute request and get response as JSON
response = requests.post(url, data=parameters, headers={ "x-api-key": API_KEY })
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, headers={ "x-api-key": API_KEY })
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, headers={ "x-api-key": API_KEY })
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={ "x-api-key": API_KEY, "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()
PDF.co Web API: the Web API with a set of tools for documents manipulation, data conversion, data extraction, splitting and merging of documents. Includes image recognition, built-in OCR, barcode generation and barcode decoders to decode bar codes from scans, pictures and pdf.
Download Source Code (.zip)
return to the previous page explore PDF To XML endpoint
Copyright © 2016 - 2024 PDF.co