110,502
社区成员
发帖
与我相关
我的任务
分享
string content = "";
PDDocument doc = PDDocument.load(pdfdoc);
PDFTextStripper stripper = new PDFTextStripper();
content = stripper.getText(doc);//这里报错: "Unknown encoding for 'GBKp-EUC-H'"
doc.close();
StringBuilder text = new StringBuilder();
if (File.Exists(pdfdoc))
{
PdfReader pdfReader = new PdfReader(pdfdoc);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
//ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy(); 下面读取内容为"", 长度为0
ITextExtractionStrategy strategy = new LocationTextExtractionStrategy(); //下面读取内容为"\n \n \n\n \n \n \n \n\n \n \n\n \n\n\n \n \n\n\n\n "
string currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
pdfReader.Close();
}