C# 使用PdfCopy合并pdf文件
我需要添加多个pdf（每一页）到我的主pdf。这些需要添加在特定页码之后，而不是追加到末尾 我该怎么办 1：在特定页码处合并pdf 2:pdfCopy.AddDocument不可用。我已经用版本5.4.3、5.4.5和5.5.10进行了测试。我错过了什么？所有人都说使用5.X，我是C# 使用PdfCopy合并pdf文件,c#,winforms,itext,C#,Winforms,Itext,我需要添加多个pdf（每一页）到我的主pdf。这些需要添加在特定页码之后，而不是追加到末尾 我该怎么办 1：在特定页码处合并pdf 2:pdfCopy.AddDocument不可用。我已经用版本5.4.3、5.4.5和5.5.10进行了测试。我错过了什么？所有人都说使用5.X，我是 'PdfCopy' does not contain a definition for 'AddDocument' and no extension method 'AddDocument' accepting a
'PdfCopy' does not contain a definition for 'AddDocument' and no extension method 'AddDocument' accepting a first argument of type 'PdfCopy' could be found (are you missing a using directive or an assembly reference?)
using System;
using System.Windows.Forms;
using iTextSharp.text;
using iTextSharp.text.pdf;
using System.IO;
namespace PdfMergeTest
{
public partial class Form1 : Form
{
private const string baseFile = "baseFile.tmp";
private const string baseTempPdfFileName = "temp.pdf";
public Form1()
{
InitializeComponent();
}
private void Form1_Load(object sender, EventArgs e)
{
}
private void btnMerge_Click(object sender, EventArgs e)
{
if (!CheckBasePaths())
return;
//get the files to merge to baseFile
var filesToMerge = GetAllFilesToMerge();
if (filesToMerge.Length == 0)
return;
//get basefile to which we need to merge the above files, it is with .tmp ext
var baseFileWithPath = GetBaseFile();
if (string.IsNullOrWhiteSpace(baseFileWithPath))
return;
//temp base pdf
var tempPdfWithPath = GetBaseTempFile();
if (string.IsNullOrWhiteSpace(tempPdfWithPath))
return;
//loop through the files to merge and merge into baseFile
var page = 2; //page where to merge the file, we are not appending to the end. Actual code will find the page from source where to merge and will add 1 to it
foreach (FileInfo toMerge in filesToMerge)
{
//copy the base file as temp file for source; for debugging purposes at this time
File.Copy(baseFileWithPath, tempPdfWithPath, true);
//start merging, first at #2, second at #4, third at #6 and so on
MergeFiles(baseFileWithPath, tempPdfWithPath, toMerge.FullName, page);
page += 2;
}
}
private bool CheckBasePaths()
{
if (string.IsNullOrWhiteSpace(txtBaseDir.Text))
{
MessageBox.Show("No Base Directory");
return false;
}
if (string.IsNullOrWhiteSpace(txtFilesToMergeToBase.Text))
{
MessageBox.Show("No files to merge Directory");
return false;
}
if (!Directory.Exists(txtBaseDir.Text))
{
MessageBox.Show("Base dir does not exist");
return false;
}
if (!Directory.Exists(txtFilesToMergeToBase.Text))
{
MessageBox.Show("Files to merge dir does not exist");
return false;
}
return true;
}
private FileInfo[] GetAllFilesToMerge()
{
DirectoryInfo d = new DirectoryInfo(txtFilesToMergeToBase.Text);
FileInfo[] files = d.GetFiles("*.pdf");
if (files.Length == 0)
MessageBox.Show("No files to merge");
return files;
}
private String GetBaseFile()
{
var myBaseFile = Path.Combine(txtBaseDir.Text, baseFile);
if (!File.Exists(myBaseFile))
{
myBaseFile = "";
MessageBox.Show("Base file missing");
}
return myBaseFile;
}
private String GetBaseTempFile()
{
var myBaseTempFile = Path.Combine(txtBaseDir.Text, baseTempPdfFileName);
return myBaseTempFile;
}
private void MergeFiles(string originalFile, string sourceFile, string toMergeFile, int insertPage)
{
Document document = null;
PdfCopy pdfCopy = null;
PdfReader pdfReader = null;
try
{
//Step#1: create a document object
document = new Document();
//Step#2: create a writer that listen to the document
pdfCopy = new PdfSmartCopy(document, new FileStream(originalFile, FileMode.Create));
if (pdfCopy == null)
return;
//Step#3: open document
document.Open();
//Step#4: create a reader for the toMergeFile and add document
pdfReader = new PdfReader(toMergeFile);
//add the entire document instead of page by page
pdfCopy.AddDocument(pdfReader);
pdfReader.Close();
}
catch (Exception ex)
{
MessageBox.Show(ex.Message);
}
finally
{
if (pdfReader != null) pdfReader.Close();
if (pdfCopy != null) pdfCopy.Close();
if (document != null) document.Close();
}
}
}
}
.AddPage以下是对我有效的解决方案。。。它需要一点清洁，这将在漫长的周末之后发生
Private Sub btnExtractMerge_Click(sender As Object, e As EventArgs) Handles btnExtractMerge.Click
txtCurSetupMessages.Text = ""
ShowMessage(txtCurSetupMessages, "Extract & Merge Process Started")
'get and check the paths / files from the form
Dim baseDir As String = txtCurSetupBaseDataFolder.Text
Dim baseInvDir As String = txtCurSetupInvoicesFolder.Text
Dim baseFileName As String = txtEMBaseFile.Text
Dim targetFileName As String = txtEMTargetFile.Text
If String.IsNullOrWhiteSpace(baseDir) Then
ShowMessage(txtCurSetupMessages, "Base folder empty!")
Exit Sub
End If
If String.IsNullOrWhiteSpace(baseInvDir) Then
ShowMessage(txtCurSetupMessages, "Base invoice folder name empty!")
Exit Sub
End If
If String.IsNullOrWhiteSpace(baseFileName) Then
ShowMessage(txtCurSetupMessages, "Base file name empty!")
Exit Sub
End If
If String.IsNullOrWhiteSpace(targetFileName) Then
ShowMessage(txtCurSetupMessages, "Target file name empty!")
Exit Sub
End If
If Not Directory.Exists(baseDir) Then
ShowMessage(txtCurSetupMessages, "Base folder does not exist!")
Exit Sub
End If
baseInvDir = System.IO.Path.Combine(baseDir, baseInvDir)
If Not Directory.Exists(baseInvDir) Then
ShowMessage(txtCurSetupMessages, "Base invoice folder does not exist!")
Exit Sub
End If
'get the invoice files
Dim dirInfo As DirectoryInfo = New DirectoryInfo(baseInvDir)
Dim files As FileInfo() = dirInfo.GetFiles("*.pdf")
If files.Length <= 0 Then
ShowMessage(txtCurSetupMessages, "Invoices missing!")
Exit Sub
End If
baseFileName = System.IO.Path.Combine(baseDir, baseFileName)
If Not File.Exists(baseFileName) Then
ShowMessage(txtCurSetupMessages, "Base file missing!")
Exit Sub
End If
targetFileName = System.IO.Path.Combine(baseDir, targetFileName)
If File.Exists(targetFileName) Then
File.Delete(targetFileName)
End If
Dim tempSource As String = System.IO.Path.Combine(baseDir, "tempSource.pdf")
If File.Exists(tempSource) Then
File.Delete(tempSource)
End If
'copy the base file as temp file
File.Copy(baseFileName, tempSource, True)
'do action
Dim iteration As Integer = 1
Dim totalPages As Integer = 0
Dim page As Integer = 0
Dim temp As String = System.IO.Path.Combine(baseDir, "temp.pdf")
Dim tempBefore As String = System.IO.Path.Combine(baseDir, "tempBefore.pdf")
Dim tempAfter As String = System.IO.Path.Combine(baseDir, "tempAfter.pdf")
Dim reader As PdfReader = Nothing
For Each myFile As FileInfo In files
If File.Exists(temp) Then File.Delete(temp)
If File.Exists(tempBefore) Then File.Delete(tempBefore)
If File.Exists(tempAfter) Then File.Delete(tempAfter)
'get total pages in the pdf
reader = New PdfReader(tempSource)
totalPages = reader.NumberOfPages
reader.Close()
If totalPages = 0 Then
ShowMessage(txtCurSetupMessages, String.Format("0 pages found in the source file"))
Exit For
End If
'find page number, this is the page after which we'll place the invoice pdf
page = FindPageNo(tempSource, 1, myFile.Name.ToUpper.Replace(".PDF", ""))
If page <= 0 Then Continue For
ShowMessage(txtCurSetupMessages, String.Format("Processing Invoice:{0} Page:{1} InvoiceFile:{2}", Format(iteration, "000"), Format(page + 1, "000"), myFile.Name))
If page = totalPages Then
'append the invoice file to the end
AddDocuments(temp, tempSource, myFile.FullName, "")
Else
'divide the pages into temp before and temp after then put together
BuildTempBeforeAndAfter(tempSource, tempBefore, tempAfter, page, totalPages)
'now put together
AddDocuments(temp, tempBefore, myFile.FullName, tempAfter)
End If
'move the temp into temp source
If File.Exists(temp) Then
File.Copy(temp, tempSource, True)
End If
iteration += 1
Next
'clean reader, used for temp number of pages
If Not reader Is Nothing Then reader.Close()
'clean the temp files used by the loop
If File.Exists(temp) Then File.Delete(temp)
If File.Exists(tempBefore) Then File.Delete(tempBefore)
If File.Exists(tempAfter) Then File.Delete(tempAfter)
'move temp source to target file and delete
If File.Exists(tempSource) Then
File.Copy(tempSource, targetFileName, True)
File.Delete(tempSource)
End If
ShowMessage(txtCurSetupMessages, "Process Completed")
End Sub
Private Function FindPageNo(ByVal sourceFiles As String, ByVal startpage As Integer, ByVal invno As String) As Integer
Dim i As Integer
Dim str1 As String
Dim pos1 As Integer, pos2 As Integer
Dim bgReader As PdfReader
Dim pagen As Integer
If File.Exists(sourceFiles) Then
bgReader = New PdfReader(sourceFiles)
If startpage > bgReader.NumberOfPages Then
FindPageNo = -1 'error. invalid
bgReader.Close()
End If
pagen = 0
For i = startpage To bgReader.NumberOfPages
str1 = pdftextextractor.GetTextFromPage(bgReader, i)
pos1 = str1.IndexOf("Invoice No:")
pos2 = str1.IndexOf("Phone:")
If pos2 > pos1 Then
If str1.Substring(pos1 + 11, pos2 - pos1 - 11).Trim.Equals(invno) = True Then
pagen = i 'found the page
'bgReader.Close()
'Exit Function
Else
If pagen <> 0 Then
'we found the page no. so no need to go further.
'exit now
FindPageNo = pagen 'last page found
bgReader.Close()
Exit Function
End If
End If
End If
Next i
bgReader.Close()
End If
If pagen <> 0 Then
FindPageNo = pagen 'last page found
Else
FindPageNo = 0 'not found
End If
End Function
Private Function BuildTempBeforeAndAfter(ByVal tempSource As String, ByVal tempBefore As String, ByVal tempAfter As String, ByVal endPage As Integer, ByVal totalPages As Integer) As Boolean
Dim reader As PdfReader = Nothing
Dim copy As PdfCopy = Nothing
Dim doc As Document = Nothing
Dim impPage As PdfImportedPage = Nothing
Dim isBuild As Boolean = True
Try
reader = New PdfReader(tempSource)
doc = New Document(reader.GetPageSizeWithRotation(1))
'before file
copy = New PdfCopy(doc, New FileStream(tempBefore, FileMode.Create))
doc.Open()
For index = 1 To endPage
impPage = copy.GetImportedPage(reader, index)
copy.AddPage(impPage)
Next
copy.Close()
doc.Close()
'after file
doc = New Document(reader.GetPageSizeWithRotation(1))
copy = New PdfCopy(doc, New FileStream(tempAfter, FileMode.Create))
doc.Open()
For index = endPage + 1 To totalPages
impPage = copy.GetImportedPage(reader, index)
copy.AddPage(impPage)
Next
reader.Close()
copy.Close()
doc.Close()
Catch ex As Exception
isBuild = False
Finally
'clean the objects
If Not reader Is Nothing Then reader.Close()
If Not doc Is Nothing Then doc.Close()
If Not reader Is Nothing Then reader.Close()
End Try
Return isBuild
End Function
Private Function AddDocuments(ByVal targetFile As String, ByVal addFile1 As String, ByVal addFile2 As String, ByVal addFile3 As String) As Boolean
Dim reader As PdfReader = Nothing
Dim copy As PdfCopy = Nothing
Dim doc As Document = Nothing
Dim isAdded As Boolean = True
Try
doc = New Document
copy = New PdfSmartCopy(doc, New FileStream(targetFile, FileMode.Create))
doc.Open()
'add file 1
If Not String.IsNullOrWhiteSpace(addFile1) Then
reader = New PdfReader(addFile1)
copy.AddDocument(reader)
reader.Close()
End If
'add file 2
If Not String.IsNullOrWhiteSpace(addFile2) Then
reader = New PdfReader(addFile2)
copy.AddDocument(reader)
reader.Close()
End If
'add file 3
If Not String.IsNullOrWhiteSpace(addFile3) Then
reader = New PdfReader(addFile3)
copy.AddDocument(reader)
reader.Close()
End If
copy.Close()
doc.Close()
Catch ex As Exception
isAdded = False
Finally
'clean the objects
If Not reader Is Nothing Then reader.Close()
If Not doc Is Nothing Then doc.Close()
If Not reader Is Nothing Then reader.Close()
End Try
Return isAdded
End Function
Private Sub btnExtractMerge\u Click（发送方作为对象，e作为事件参数）处理btnExtractMerge。单击
txtCurSetupMessages.Text=“”
ShowMessage（txtCurSetupMessages，“提取和合并过程已启动”）
'获取并检查表单中的路径/文件
Dim baseDir As String=txtCurSetupBaseDataFolder.Text
Dim baseInvDir As String=txtCurSetupInvoicesFolder.Text
Dim baseFileName为String=txtEMBaseFile.Text
Dim targetFileName为String=txtEMTargetFile.Text
如果String.IsNullOrWhiteSpace（baseDir），则
ShowMessage（txtCurSetupMessages，“基本文件夹为空！”）
出口接头
如果结束
如果String.IsNullOrWhiteSpace（baseInvDir），则
ShowMessage（txtCurSetupMessages，“基本发票文件夹名称为空！”）
出口接头
如果结束
如果String.IsNullOrWhiteSpace（baseFileName），则
ShowMessage（txtCurSetupMessages，“基本文件名为空！”）
出口接头
如果结束
如果String.IsNullOrWhiteSpace（targetFileName），则
ShowMessage（txtCurSetupMessages，“目标文件名为空！”）
出口接头
如果结束
如果目录不存在（baseDir），则
ShowMessage（txtCurSetupMessages，“基本文件夹不存在！”）
出口接头
如果结束
baseInvDir=System.IO.Path.Combine（baseDir，baseInvDir）
如果目录不存在（baseInvDir），则
ShowMessage（txtCurSetupMessages，“基本发票文件夹不存在！”）
出口接头
如果结束
'获取发票文件
Dim dirInfo As DirectoryInfo=新DirectoryInfo（baseInvDir）
Dim文件格式为FileInfo（）=dirInfo.GetFiles（“*.pdf”）
如果是files.Length bgReader.NumberOfPages，则
FindPageNo=-1'错误。无效的
bgrader.Close（）
如果结束
pagen=0
对于i=起始页到bgReader.NumberOfPages
str1=pdftextextractor.GetTextFromPage（bgReader，i）
pos1=str1.IndexOf（“发票号：”）
pos2=str1.IndexOf（“电话：”）
如果pos2>pos1，那么
如果str1.Substring（pos1+11，pos2-pos1-11）.Trim.Equals（invno）=True，则
pagen=我找到了页面
'bgReader.Close（）
'退出功能
其他的
如果第0页，则
“我们找到了页码，因此无需再进一步。
“马上离开
FindPageNo=pagen'找到的最后一页
bgrader.Close（）
退出功能
如果结束
如果结束
如果结束
接下来我
bgrader.Close（）
如果结束
如果第0页，则
FindPageNo=pagen'找到的最后一页
其他的
找不到FindPageNo=0
如果结束
端函数
私有函数BuildTempBeforeAndAfter（ByVal tempSource作为字符串，ByVal tempBefore作为字符串，ByVal tempAfter作为字符串，ByVal endPage作为整数，ByVal totalPages作为整数）作为布尔值
作为PdfReader的Dim读卡器=无
作为PdfCopy的Dim复制=无
Dim doc As Document=无
作为PdfImportedPage的Dim impPage=无
Dim isBuild As Boolean=True
尝试
读卡器=新的PDF读卡器（tempSource）
doc=新文档（reader.GetPageSizeWithRotation（1））
"在归档之前,
复制=新的PdfCopy（文档，新文件流（tempBefore，FileMode.Create））
公开文件（）
对于索引=1到结束页
impPage=copy.GetImportedPage（读取器，索引）
复制.添加页面（导入页面）
下一个
复制。关闭（）
文件关闭（）
"档案之后,
doc=新文档（reader.GetPageSizeWithRotation（1））
copy=newpdfcopy（doc，newfilestream（tempfafter，FileMode.Create））
公开文件（）
对于索引=endPage+1到totalPages
impPage=copy.GetImportedPage（读取器，索引）
复制.添加页面（导入页面）
下一个
reader.Close（）
复制。关闭（）
文件关闭（）
特例
isBuild=False
最后
"清理物品,
如果不是reader，则reader.Close（）为空
如果不是doc，则doc.Close（）为空
如果不是reader，则reader.Close（）为空
结束尝试
返回isBuild
端函数
私有函数AddDocuments（ByVal targetFile作为字符串，ByVal addFile1作为字符串，ByVal addFile2作为字符串，ByVal addFile3作为字符串）作为布尔值
作为PdfReader的Dim读卡器=无
作为PdfCopy的Dim复制=无
Dim doc As Document=无
Dim被添加为布尔值=真
尝试
doc=新文档
copy=newpdfsmartcopy（doc，newfilestream（targetFile，FileMode.Create））
公开文件（）
'添加文件