PDF.co Web API - PDF Splitting API - Python - Split PDF By Text From Uploaded File

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

How to split PDF by text from uploaded file for PDF splitting API in Python and PDF.co Web API

PDF.co Web API 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)

SplitPDFFromUploadedFile.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"
# Split by Text
SplitText = "invoice number"


def main(args = None):
    uploadedFileUrl = uploadFile(SourceFile)
    if (uploadedFileUrl != None):
        splitPDF(uploadedFileUrl)


def splitPDF(uploadedFileUrl):
    """Split PDF By Text using PDF.co Web API"""

    # Prepare requests params as JSON
    # See documentation: https://apidocs.pdf.co
    parameters = {}
    parameters["searchString"] = SplitText
    parameters["url"] = uploadedFileUrl

    # Prepare URL for 'Split PDF By Text' API request
    url = "{}/pdf/split2".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:

            # Download generated PNG files
            part = 1

            for resultFileUrl in json["urls"]:
                # Download Result File
                r = requests.get(resultFileUrl, stream=True)

                localFileUrl = f"Page{part}.pdf"

                if r.status_code == 200:
                    with open(localFileUrl, 'wb') as file:
                        for chunk in r:
                            file.write(chunk)
                    print(f"Result file saved as \"{localFileUrl}\" file.")
                else:
                    print(f"Request error: {response.status_code} {response.reason}")

                part = part + 1
        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()