Last active
November 4, 2021 19:11
-
-
Save nstevens1040/e921aeafedd25f58e7dd56aad38658ad to your computer and use it in GitHub Desktop.
iText7 Extract PDF text from select pages
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| $REFS = @( | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\itext.pdfa.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\Microsoft.Bcl.AsyncInterfaces.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\Microsoft.Extensions.DependencyInjection.Abstractions.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\Microsoft.Extensions.DependencyInjection.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\Microsoft.Extensions.Logging.Abstractions.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\Microsoft.Extensions.Logging.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\Microsoft.Extensions.Options.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\Microsoft.Extensions.Primitives.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\System.Buffers.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\System.Diagnostics.DiagnosticSource.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\System.Memory.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\System.Numerics.Vectors.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\System.Runtime.CompilerServices.Unsafe.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\System.Threading.Tasks.Extensions.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\System.ValueTuple.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\BouncyCastle.Crypto.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\itext.commons.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\itext.io.dll", | |
| "$($BINFOLDER)\itext7-dotnet\itext\itext.pdfa\bin\Debug\net461\itext.kernel.dll" | |
| ) | |
| $REFS.ForEach({ Add-Type -Path $_ }) | |
| Add-Type -TypeDefinition @" | |
| namespace ExtractPdf | |
| { | |
| using System; | |
| using System.IO; | |
| using System.Text; | |
| using System.Linq; | |
| using iText.IO; | |
| using iText.Pdfa; | |
| using iText.Kernel; | |
| using iText.Kernel.Pdf; | |
| using System.Collections.Generic; | |
| public class Text | |
| { | |
| public static Dictionary<string,string> From(string filepath, int start_page = 1, int end_page = 0) | |
| { | |
| PdfReader pdfReader = new PdfReader(filepath); | |
| PdfDocument pdfDoc = new PdfDocument(pdfReader); | |
| Dictionary<string,string> results = new Dictionary<string,string>(); | |
| if(end_page == 0) | |
| { | |
| end_page = pdfDoc.GetNumberOfPages(); | |
| } | |
| for(int i = start_page; i <= end_page; i++) | |
| { | |
| iText.Kernel.Pdf.Canvas.Parser.Listener.ITextExtractionStrategy strategy = new iText.Kernel.Pdf.Canvas.Parser.Listener.SimpleTextExtractionStrategy(); | |
| string pageContent = iText.Kernel.Pdf.Canvas.Parser.PdfTextExtractor.GetTextFromPage(pdfDoc.GetPage(i), strategy); | |
| string page_num = i.ToString(); | |
| results.Add(page_num,pageContent); | |
| } | |
| pdfDoc.Close(); | |
| pdfReader.Close(); | |
| return results; | |
| } | |
| } | |
| } | |
| "@ -ReferencedAssemblies $REFS | |
| $from_page = 5 | |
| $to_page = 10 | |
| $source_pdf_file = "C:\.TEMP\PDF\source.pdf" | |
| $output_txt_file = "C:\.TEMP\TXT\destin.txt" | |
| $pdf_ = [ExtractPdf.Text]::From( | |
| $source_pdf_file, | |
| $from_page, | |
| $to_page | |
| ) | |
| $space = "$([System.Text.Encoding]::UTF8.GetString([byte]32))" | |
| $cr = "$([System.Text.Encoding]::UTF8.GetString([byte]13))" | |
| $sixty = '=============================================================' | |
| $one31 = '-------------------------------------------------------------------------------------------------------------------------------------' | |
| $crlf = "$([System.Text.Encoding]::UTF8.GetString(@([byte]13,[byte]10)))" | |
| $down = "$([System.Text.Encoding]::UTF8.GetString(@(0xe2,0x86,0x93)))" | |
| $up= "$([System.Text.Encoding]::UTF8.GetString(@(0xe2,0x86,0x91)))" | |
| $pages = [System.Collections.Generic.List[string]]::new(); | |
| foreach($key in $pdf_.Keys) | |
| { | |
| $page_num = $key | |
| $content = $pdf_[$key] | |
| $formatted = [System.Collections.Generic.List[string]]::New() | |
| foreach($ine in @($content.Split("$([System.Text.Encoding]::UTF8.GetString([byte]10))"))) | |
| { | |
| $line = ("| " + $ine).Replace($cr,[string]::Empty) | |
| $fill = 133 - $line.Length - 2; | |
| $spaces = @();(0..$fill).ForEach({ $spaces += $space });$sp = [string]::Join([string]::Empty,$spaces) | |
| $new = $line.Replace($cr,[string]::Empty) + ($sp + "|").Replace($cr,[string]::Empty) | |
| $formatted.Add($new) | |
| } | |
| $fstring = [string]::Join($crlf,$formatted) | |
| $page = "$($down)$($sixty) page $($page_num) $($sixty)$($down)$($crlf)$($fstring)$($crlf)$($up)$($sixty) page $($page_num) $($sixty)$($up)$($crlf)$($one31)" | |
| $pages.Add($page) | |
| } | |
| [string]::Join($crlf,$pages) | Out-File $output_txt_file -Encoding utf8 | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment