PDF.co Web API – PDF Text Search API – PowerShell – PDF Text Search from URL Asynchronously

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

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

PDFTextSearchFromUrlAsynchronously.ps1

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

# Direct URL of PDF file to get information
$SourceFileURL = "https://bytescout-com.s3.amazonaws.com/files/demo-files/cloud-api/pdf-to-text/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 = ""

# Search string. 
$SearchString = '\d{1,}\.\d\d' #Regular expression to find numbers like '100.00'

# Enable regular expressions (Regex) 
$RegexSearch = 'True'

# (!) Make asynchronous job
$Async = $true

# Prepare URL for PDF text search API call.
# See documentation: https://app.pdf.co/documentation/api/1.0/pdf/find.html
$query = "https://api.pdf.co/v1/pdf/find"

# Prepare request body (will be auto-converted to JSON by Invoke-RestMethod)
# See documentation: https://apidocs.pdf.co
$body = @{
    "password" = $Password
    "pages" = $Pages
    "url" = $SourceFileURL
    "searchString" = $SearchString
    "regexSearch" = $RegexSearch
    "async" = $Async
} | 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 JSON file with search result that will available after the job completion
        $resultFileUrl = $jsonResponse.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.
        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") {
                # Get JSON for search result
                $jsonSearchResult = Invoke-RestMethod -Method Get -Headers @{ "x-api-key" = $API_KEY } -Uri $resultFileUrl
                
                # Display found result in console
                foreach ($item in $jsonSearchResult)
                {
                    Write-Host "Found text $($item.text) at coordinates $($item.left), $($item.top)"
                }
                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
}
    

run.bat

      
@echo off

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

pause
    

ON-PREMISE OFFLINE SDK

Get 60 Day Free Trial

See also:

• Explore Documentation
• Explore Source Code Samples
• Watch Video Course

ON-DEMAND REST WEB API

Get Your API Key

See also:

• Web API Docs
• Learn About Security
• Explore Source Code Samples