不使用第三方工具将PDF文件转换为Excel文件 [英] Convert PDF File to Excel File without using third party tool

问题描述

我搜索了更多的资源，但找不到任何资源。我想将pdf表格式转换为excel。我使用iTextSharp但我无法更正输出所有列值合并。因此，PLZ告诉任何来源使用c＃

I have search more number of resource but i can't find any one. I want to convert the pdf table formate into excel. I use iTextSharp but i can't correct output all the column values are merged. So plz tell any source to convert pdf table format to excel using c#

推荐答案

将pdf表格式转换为Excel格式嗨...检查此代码。它运行正常。



private void PDFToExcel（DataTable dt）

{

string strPath =D：\\sample.pdf;

string strSplit =;

DataTable dt = new DataTable（）;

StringBuilder sbTxt = new StringBuilder（）;



使用（PdfReader pReader = new PdfReader（strPath））

{

for（int i = 1; i< = pReader .NumberOfPages; i ++）

{

strSplit = PdfTextExtractor.GetTextFromPage（pReader，i）;

}

}



string [] strSplitArr = strSplit.Split（'\ n'）;

if（strSplitArr.Length> 0）

{

string [] strCol = strSplitArr [0] .Split（''）;

foreach（strCol中的var col）

{

dt.Columns.Add（col）;

}



for（int i = 1;我< strSplitArr.Length; i ++）

{

string [] strRow = strSplitArr [i] .Split（''）;

DataRow dr = dt.NewRow（ ）;



for（int j = 0; j< strCol.Length; j ++）

{

dr [strCol [j] .ToString（）] = strRow [j] .ToString（）;

}

dt.Rows.Add（dr）;

}



DatatableToExcel（dt）;

}

}





private void DatatableToExcel（DataTable dt）

{



GridView GridView1 = new GridView（）;

GridView1.AllowPaging = false;

GridView1.DataSource = dt;

GridView1.DataBind（）;



Response.Clear（ ）;

Response.Buffer = true;

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

Response.Charset =;

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

StringWriter sw = new StringWriter（）;

HtmlTextWriter hw = new HtmlTextWriter（sw）;





for（int i = 0; i< GridView1 .Rows.Count; i ++）



{

GridView1.Rows [i] .Attributes.Add（class，textmode）;



}



GridView1.RenderControl（hw）;

string style = @。textmode {mso-number-format：\ @;};

Response.Write（样式）;

Response.Output.Write（sw.ToString（））;

Response.Flush（）;

Response.End（）;

}

Hi...check this code.It's working perfectly.

private void PDFToExcel(DataTable dt)
{
string strPath = "D:\\sample.pdf";
string strSplit="";
DataTable dt = new DataTable();
StringBuilder sbTxt = new StringBuilder();

using (PdfReader pReader = new PdfReader(strPath))
{
for (int i = 1; i <= pReader.NumberOfPages; i++)
{
strSplit = PdfTextExtractor.GetTextFromPage(pReader, i);
}
}

string[] strSplitArr = strSplit.Split('\n');
if (strSplitArr.Length > 0)
{
string[] strCol = strSplitArr[0].Split(' ');
foreach (var col in strCol)
{
dt.Columns.Add(col);
}

for (int i = 1; i < strSplitArr.Length; i++)
{
string[] strRow = strSplitArr[i].Split(' ');
DataRow dr = dt.NewRow();

for (int j = 0; j < strCol.Length; j++)
{
dr[strCol[j].ToString()] = strRow[j].ToString();
}
dt.Rows.Add(dr);
}

DatatableToExcel(dt);
}
}


private void DatatableToExcel(DataTable dt)
{

GridView GridView1 = new GridView();
GridView1.AllowPaging = false;
GridView1.DataSource = dt;
GridView1.DataBind();

Response.Clear();
Response.Buffer = true;
Response.AddHeader("content-disposition","attachment;filename=MyPdfExcel.xls");
Response.Charset = "";
Response.ContentType = "application/vnd.ms-excel";
StringWriter sw = new StringWriter();
HtmlTextWriter hw = new HtmlTextWriter(sw);


for (int i = 0; i < GridView1.Rows.Count; i++)

{
GridView1.Rows[i].Attributes.Add("class", "textmode");

}

GridView1.RenderControl(hw);
string style = @" .textmode { mso-number-format:\@; } ";
Response.Write(style);
Response.Output.Write(sw.ToString());
Response.Flush();
Response.End();
}

这篇关于不使用第三方工具将PDF文件转换为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！