如何使用iTextSharp在C＃中查找PDF表并将其提取到excel文件 [英] How to find and extract PDF table to excel file in C# using iTextSharp

问题描述

任何人都可以帮我提取PDF表格并以适当的格式输入excel文件。我正在使用iTextSharp dll。

解决方案

这是经常被问到的问题。请参阅： SearchBox [ ^ ]

< blockquote>命名空间





使用System.Text;

使用System.IO;

使用iTextSharp.text;

使用iTextSharp.text.pdf;

使用iTextSharp.text.pdf.parser;









代码





protected void ExportToExcel（object sender，EventArgs e）

{

if（this.fuPdfUpload.HasFile）

{

string file = Path.GetFullPath（fuPdfUpload.PostedFile.FileName）;

this.ExportPDFToExcel（file）;

}

}



private void ExportPDFToExcel（string fileName）

{

StringBuilder text = new StringBuilder（ ）;

PdfReader pdfReader = new PdfReader（fileName）;

for（int page = 1; page< = pdfReader.NumberOfPages;页面++）

{

ITextExtractionStrategy strategy = new LocationTextExtractionStrategy（）;

string currentText = PdfTextExtractor.GetTextFromPage（pdfReader，page，strategy）;

currentText = Encoding.UTF8.GetString（Encoding.Convert（Encoding.Default，Encoding.UTF8，Encoding.UTF8.GetBytes（currentText）））;

text.Append（ currentText）;

pdfReader.Close（）;

}

Response.Clear（）;

响应。 Buffer = true;

Response.AddHeader（content-disposition，attachment; filename = ReceiptExport.xls）;

Response.Charset =;

Response.ContentType =application / vnd.ms-excel;

Response.Write（text）;

Response.Flush（）;

Response.End（）;

}

Can anybody please help me to extract PDF table & put into excel file in proper format. I am using iTextSharp dll.

解决方案

It is quite often asked question. Please, see: SearchBox[^]

Namespaces


using System.Text;
using System.IO;
using iTextSharp.text;
using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;




Code


protected void ExportToExcel(object sender, EventArgs e)
{
if (this.fuPdfUpload.HasFile)
{
string file = Path.GetFullPath(fuPdfUpload.PostedFile.FileName);
this.ExportPDFToExcel(file);
}
}

private void ExportPDFToExcel(string fileName)
{
StringBuilder text = new StringBuilder();
PdfReader pdfReader = new PdfReader(fileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new LocationTextExtractionStrategy();
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.UTF8.GetBytes(currentText)));
text.Append(currentText);
pdfReader.Close();
}
Response.Clear();
Response.Buffer = true;
Response.AddHeader("content-disposition", "attachment;filename=ReceiptExport.xls");
Response.Charset = "";
Response.ContentType = "application/vnd.ms-excel";
Response.Write(text);
Response.Flush();
Response.End();
}

这篇关于如何使用iTextSharp在C＃中查找PDF表并将其提取到excel文件的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！