有没有一个开源库可以帮助我在.Net/C#中阅读/解析PDF文档？
自从这个问题在2008年被最后一次回答以来,iTextSharp已经大大提高了他们的api.如果您从下载最新版本的他们的API的http://sourceforge.net/projects/itextsharp/,你可以使用下面的代码片段从PDF中的所有文本提取到一个字符串.
using iTextSharp.text.pdf;
using iTextSharp.text.pdf.parser;
namespace PdfParser
{
public static class PdfTextExtractor
{
public static string pdfText(string path)
{
PdfReader reader = new PdfReader(path);
string text = string.Empty;
for(int page = 1; page <= reader.NumberOfPages; page++)
{
text += PdfTextExtractor.GetTextFromPage(reader,page);
}
reader.Close();
return text;
}
}
}
iTextSharp是最好的选择.用它来制作lucene.Net的蜘蛛,以便它可以抓取PDF.
using System;
using System.IO;
using iTextSharp.text.pdf;
using System.Text.RegularExpressions;
namespace Spider.Utils
{
///
/// Parses a PDF file and extracts the text from it.
///
public class PDFParser
{
/// BT = Beginning of a text object operator
/// ET = End of a text object operator
/// Td move to the start of next line
/// 5 Ts = superscript
/// -5 Ts = subscript
#region Fields
#region _numberOfCharsToKeep
///
/// The number of characters to keep, when extracting text.
///
private static int _numberOfCharsToKeep = 15;
#endregion
#endregion
#region ExtractText
///
/// Extracts a text from a PDF file.
///
/// the full path to the pdf file.
/// the output file name.
/// the extracted text
public bool ExtractText(string inFileName, string outFileName)
{
StreamWriter outFile = null;
try
{
// Create a reader for the given PDF file
PdfReader reader = new PdfReader(inFileName);
//outFile = File.CreateText(outFileName);
outFile = new StreamWriter(outFileName, false, System.Text.Encoding.UTF8);
Console.Write("Processing: ");
int totalLen = 68;
float charUnit = ((float)totalLen) / (float)reader.NumberOfPages;
int totalWritten = 0;
float curUnit = 0;
for (int page = 1; page <= reader.NumberOfPages; page++)
{
outFile.Write(ExtractTextFromPDFBytes(reader.GetPageContent(page)) + " ");
// Write the progress.
if (charUnit >= 1.0f)
{
for (int i = 0; i < (int)charUnit; i++)
{
Console.Write("#");
totalWritten++;
}
}
else
{
curUnit += charUnit;
if (curUnit >= 1.0f)
{
for (int i = 0; i < (int)curUnit; i++)
{
Console.Write("#");
totalWritten++;
}
curUnit = 0;
}
}
}
if (totalWritten < totalLen)
{
for (int i = 0; i < (totalLen - totalWritten); i++)
{
Console.Write("#");
}
}
return true;
}
catch
{
return false;
}
finally
{
if (outFile != null) outFile.Close();
}
}
#endregion
#region ExtractTextFromPDFBytes
///
/// This method processes an uncompressed Adobe (text) object
/// and extracts text.
///
/// uncompressed
///
/// Check if a certain 2 character token just came along (e.g. BT)
///
/// the searched token
/// the recent character array
///
PDFClown可能有所帮助,但我不推荐它用于大型或重型应用程序.
京公网安备 11010802040832号 | 京ICP备19059560号-6 