templateName: Multipage Table Test
templateVersion: 4
templatePriority: 0
detectionRules:
  keywords:
  - Sample document with multi-page table
objects:
- name: total
  objectType: field
  fieldProperties:
    fieldType: macros
    expression: TOTAL{{Spaces}}({{Number}})
    regex: true
    dataType: decimal
- name: table1
  objectType: table
  tableProperties:
    start:
      expression: Item{{Spaces}}Description{{Spaces}}Price
      regex: true
    end:
      expression: TOTAL{{Spaces}}{{Number}}
      regex: true
    row:
      expression: '{{LineStart}}{{Spaces}}(?<itemNo>{{Digits}}){{Spaces}}(?<description>{{SentenceWithSingleSpaces}}){{Spaces}}(?<price>{{Number}}){{Spaces}}(?<qty>{{Digits}}){{Spaces}}(?<extPrice>{{Number}})'
      regex: true
    columns:
    - name: itemNo
      dataType: integer
    - name: description
      dataType: string
    - name: price
      dataType: decimal
    - name: qty
      dataType: integer
    - name: extPrice
      dataType: decimal
    multipage: true

import os
import requests # pip install requests

# 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 url
# You can also upload your own file into PDF.co and use it as url. Check "Upload File" samples for code snippets: https://github.com/bytescout/pdf-co-api-samples/tree/master/File%20Upload/    
SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/document-parser/MultiPageTable.pdf"

# Destination JSON file name
DestinationFile = ".\\result.json"

// Template text. Use Document Parser (https://pdf.co/document-parser, https://app.pdf.co/document-parser)
# to create templates.
# Read template from file:
file_read = open(".\\MultiPageTable-template1.yml", mode='r', encoding="utf-8",errors="ignore")
Template = file_read.read()
file_read.close()

def main(args = None):
    PerformDocumentParser(SourceFileUrl, Template, DestinationFile)

def PerformDocumentParser(uploadedFileUrl, template, destinationFile):

    # Content
    data = {
        'url': uploadedFileUrl,
        'template': template
    }

    # Prepare URL for 'Document Parser' API request
    url = "{}/pdf/documentparser".format(BASE_URL)

    # Execute request and get response as JSON
    response = requests.post(url, data= data, headers={ "x-api-key": API_KEY })

    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}")


if __name__ == '__main__':
    main()