/**
* 提取部分页面文本
* @param file pdf文档路径
* @param startPage 开始页数
* @param endPage 结束页数
*/
public static string ExtractTXT(String file, int startPage, int endPage)
{
String content = string.Empty;
try
{
PDDocument document = PDDocument.load(file);
//获取一个PDFTextStripper文本剥离对象
PDFTextStripper stripper = new PDFTextStripper();
// 设置按顺序输出
stripper.setSortByPosition(true);
// 设置起始页
stripper.setStartPage(startPage);
// 设置结束页
stripper.setEndPage(endPage);
//获取文本内容
content = stripper.getText(document);
document.close();
}
catch (java.io.FileNotFoundException ex)
{
}
catch (java.io.IOException ex)
{
}
return(content);
}
public static string Pdf2txt(string pdfName)
{
PDDocument doc = PDDocument.load(pdfName);
PDFTextStripper pdfStripper = new PDFTextStripper();
// 设置按顺序输出
pdfStripper.setSortByPosition(true);
return(pdfStripper.getText(doc));
}
protected void Button1_Click(object sender, EventArgs e)
{
String savePath = @"C:\upload";
if (FileUpload1.HasFile)
{
String fileName = FileUpload1.FileName;
savePath += fileName;
FileUpload1.SaveAs(savePath);
}
java.io.File mfile = new File(savePath);
PDDocument doc = PDDocument.load(mfile, MemoryUsageSetting.setupMainMemoryOnly());
PDFTextStripper Stripper = new PDFTextStripper();
Stripper.setSortByPosition(true);
TextBox1.Text = (Stripper.getText(doc));
}
