PdfReader reader2 = new PdfReader(openFileDialog1.FileName);
int pagen = reader2.NumberOfPages;
reader2.Close();
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
for (int i = 1; i < pagen; i++)
{
textBox1.Text = "";
PdfReader reader = new PdfReader(openFileDialog1.FileName);
String s = PdfTextExtractor.GetTextFromPage(reader, i, its);
//MessageBox.Show(s.Length.ToString());
//PdfTextArray h = new PdfTextArray(s);
//
// s = "";
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
textBox1.Text = s;
reader.Close();
}
答案 0 :(得分:5)
SimpleTextExtractionStrategy不允许你重置它,所以你必须在循环中移动你的“new SimpleTextExtractionStrategy()”而不是重用同一个对象。
答案 1 :(得分:2)
控制循环的语句中还有另一个潜在的问题:
for (int i = 1; i < pagen; i++)
如果pagen = 1,则根本不执行循环。它应该是:
for (int i = 1; i <= pagen; i++)
答案 2 :(得分:0)
public string ReadPdfFile(object Filename,DataTable ReadLibray)
{
PdfReader reader2 = new PdfReader((string)Filename);
string strText = string.Empty;
for (int page = 1; page <= reader2.NumberOfPages; page++)
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
PdfReader reader = new PdfReader((string)Filename);
String s = PdfTextExtractor.GetTextFromPage(reader, page, its);
s = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(s)));
strText = strText + s;
reader.Close();
}
return strText;
}
此代码非常有助于使用itext读取PDf