Advanced Conversion Options | PowerShell | PDF To XML APIByteScout PDF Extractor SDK

Advanced Conversion Options | PowerShell | PDF To XML API

run.bat:

@echo off

powershell -NoProfile -ExecutionPolicy Bypass -Command "& .\ConvertPdfToXmlFromUrlAsynchronously.ps1"
echo Script finished with errorlevel=%errorlevel%

pause
        

ConvertPdfToXmlFromUrlAsynchronously.ps1:

# Cloud API asynchronous "PDF To XML" job example.
# Allows to avoid timeout errors when processing huge or scanned PDF documents.

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

# Direct URL of source PDF file.
$SourceFileUrl = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-xml/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

# Some of advanced options available through profiles:
# (it can be single/double-quoted and contain comments.)
# {
# 	"profiles": [
# 		{
# 			"profile1": {
# 				"SaveImages": "None", // Whether to extract images. Values: "None", "Embed".
# 				"ImageFormat": "PNG", // Image format for extracted images. Values: "PNG", "JPEG", "GIF", "BMP".
# 				"SaveVectors": false, // Whether to extract vector objects (vertical and horizontal lines). Values: true / false
# 				"ExtractInvisibleText": true, // Invisible text extraction. Values: true / false
# 				"ExtractShadowLikeText": true, // Shadow-like text extraction. Values: true / false
# 				"LineGroupingMode": "None", // Values: "None", "GroupByRows", "GroupByColumns", "JoinOrphanedRows"
# 				"ColumnDetectionMode": "ContentGroupsAndBorders", // Values: "ContentGroupsAndBorders", "ContentGroups", "Borders", "BorderedTables"
# 				"Unwrap": false, // Unwrap grouped text in table cells. Values: true / false
# 				"ShrinkMultipleSpaces": false, // Shrink multiple spaces in table cells that affect column detection. Values: true / false
# 				"DetectNewColumnBySpacesRatio": 1, // Spacing ratio that affects column detection.
# 				"CustomExtractionColumns": [ 0, 50, 150, 200, 250, 300 ], // Explicitly specify columns coordinates for table extraction.
# 				"CheckPermissions": true, // Ignore document permissions. Values: true / false
# 			}
# 		}
# 	]
# }

# Sample profile that sets advanced conversion options
# Advanced options are properties of XMLExtractor class from ByteScout XML Extractor SDK used in the back-end:
# https://cdn.bytescout.com/help/BytescoutPDFExtractorSDK/html/6f2b5e9c-ba15-f9fe-192b-c3e31ec4a0ee.htm
$Profiles = '{ "profiles": [ { "profile1": { "TrimSpaces": "False", "PreserveFormattingOnTextExtraction": "True", "Unwrap": "True", "ShrinkMultipleSpaces": "True" } } ] }'


# Prepare URL for `PDF To XML` API call
$query = "https://api.pdf.co/v1/pdf/convert/to/xml"

# Prepare request body (will be auto-converted to JSON by Invoke-RestMethod)
# See documentation: https://apidocs.pdf.co
$body = @{
    "name" = $(Split-Path $DestinationFile -Leaf)
    "password" = $Password
    "pages" = $Pages
    "url" = $SourceFileUrl
    "async" = $Async
    "profiles" = $Profiles
} | ConvertTo-Json

try {
    # Execute request
    $response = Invoke-WebRequest -Method Post -Headers @{ "x-api-key" = $API_KEY; "Content-Type" = "application/json" } -Body $body -Uri $query

    $jsonResponse = $response.Content | ConvertFrom-Json

    if ($jsonResponse.error -eq $false) {
        # Asynchronous job ID
        $jobId = $jsonResponse.jobId
        # URL of generated XML file that will available after the job completion
        $resultFileUrl = $jsonResponse.url

        # Check the job status in a loop. 
        do {
            $statusCheckUrl = "https://api.pdf.co/v1/job/check?jobid=" + $jobId
            $jsonStatus = Invoke-RestMethod -Method Get -Headers @{ "x-api-key" = $API_KEY } -Uri $statusCheckUrl

            # Display timestamp and status (for demo purposes)
            Write-Host "$(Get-date): $($jsonStatus.status)"

            if ($jsonStatus.status -eq "success") {
                # Download XML file
                Invoke-WebRequest -Headers @{ "x-api-key" = $API_KEY } -OutFile $DestinationFile -Uri $resultFileUrl
                Write-Host "Generated XML file saved as `"$($DestinationFile)`" file."
                break
            }
            elseif ($jsonStatus.status -eq "working") {
                # Pause for a few seconds
                Start-Sleep -Seconds 3
            }
            else {
                Write-Host $jsonStatus.status
                break
            }
        }
        while ($true)
    }
    else {
        # Display service reported error
        Write-Host $jsonResponse.message
    }
}
catch {
    # Display request error
    Write-Host $_.Exception
}