PDF.co Web API - Replace Text From PDF - Python - Replace Text From Uploaded File

printable version:
PDF-co-Web-API-Python-Replace-Text-From-Uploaded-File.pdf

How to replace text from PDF in Python with PDF.co Web API

What is PDF.co Web API? It is the Rest API that provides set of data extraction functions, tools for documents manipulation, splitting and merging of pdf files. Includes built-in OCR, images recognition, can generate and read barcodes from images, scans and pdf.

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

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

ReplaceTextFromUploadedFile.py

      import os
import requests # pip install requests

# The authentication key (API Key).
# Get your own by registering at https://app.pdf.co/documentation/api
API_KEY = "******************************************"

# Base URL for PDF.co Web API requests
BASE_URL = "https://api.pdf.co/v1"

# Source PDF file
SourceFile = ".\\sample.pdf"
# PDF document password. Leave empty for unprotected documents.
Password = ""
# Destination PDF file name
DestinationFile = ".\\result.pdf"


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


def replaceStringFromPdf(uploadedFileUrl, destinationFile):
    """Replace Text FROM UPLOADED PDF FILE using PDF.co Web API"""

    # Prepare URL for 'Replace Text from PDF' API request
    url = "{}/pdf/edit/replace-text?name={}&password={}&url={}&searchString=The most conspicuous feature of&replaceString=replaced text".format(
        BASE_URL,
        os.path.basename(destinationFile),
        Password,
        uploadedFileUrl
    )

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

        if json["error"] == False:
            #  Get URL of result file
            resultFileUrl = json["url"]            
            # 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}")
        else:
            # Show service reported error
            print(json["message"])
    else:
        print(f"Request error: {response.status_code} {response.reason}")


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()