问题
I used this code for convert a English pdf and it work perfectly, but when i use it for Persian file, its output has no Persian character !! how i can parse a Unicode pdf to a text file and a folder contains image files?
using System;
using System.IO;
using iTextSharp.text.pdf;
using System.Text.RegularExpressions;
namespace Spider.Utils
{
/// <summary>
/// Parses a PDF file and extracts the text from it.
/// </summary>
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
/// <summary>
/// The number of characters to keep, when extracting text.
/// </summary>
private static int _numberOfCharsToKeep = 15;
#endregion
#endregion
#region ExtractText
/// <summary>
/// Extracts a text from a PDF file.
/// </summary>
/// <param name="inFileName">the full path to the pdf file.</param>
/// <param name="outFileName">the output file name.</param>
/// <returns>the extracted text</returns>
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
/// <summary>
/// This method processes an uncompressed Adobe (text) object
/// and extracts text.
/// </summary>
/// <param name="input">uncompressed</param>
/// <returns></returns>
public string ExtractTextFromPDFBytes(byte[] input)
{
if (input == null || input.Length == 0) return "";
try
{
string resultString = "";
// Flag showing if we are we currently inside a text object
bool inTextObject = false;
// Flag showing if the next character is literal
// e.g. '\\' to get a '\' character or '\(' to get '('
bool nextLiteral = false;
// () Bracket nesting level. Text appears inside ()
int bracketDepth = 0;
// Keep previous chars to get extract numbers etc.:
char[] previousCharacters = new char[_numberOfCharsToKeep];
for (int j = 0; j < _numberOfCharsToKeep; j++) previousCharacters[j] = ' ';
for (int i = 0; i < input.Length; i++)
{
char c = (char)input[i];
if (input[i] == 213)
c = "'".ToCharArray()[0];
if (inTextObject)
{
// Position the text
if (bracketDepth == 0)
{
if (CheckToken(new string[] { "TD", "Td" }, previousCharacters))
{
resultString += "\n\r";
}
else
{
if (CheckToken(new string[] { "'", "T*", "\"" }, previousCharacters))
{
resultString += "\n";
}
else
{
if (CheckToken(new string[] { "Tj" }, previousCharacters))
{
resultString += " ";
}
}
}
}
// End of a text object, also go to a new line.
if (bracketDepth == 0 &&
CheckToken(new string[] { "ET" }, previousCharacters))
{
inTextObject = false;
resultString += " ";
}
else
{
// Start outputting text
if ((c == '(') && (bracketDepth == 0) && (!nextLiteral))
{
bracketDepth = 1;
}
else
{
// Stop outputting text
if ((c == ')') && (bracketDepth == 1) && (!nextLiteral))
{
bracketDepth = 0;
}
else
{
// Just a normal text character:
if (bracketDepth == 1)
{
// Only print out next character no matter what.
// Do not interpret.
if (c == '\\' && !nextLiteral)
{
resultString += c.ToString();
nextLiteral = true;
}
else
{
if (((c >= ' ') && (c <= '~')) ||
((c >= 128) && (c < 255)))
{
resultString += c.ToString();
}
nextLiteral = false;
}
}
}
}
}
}
// Store the recent characters for
// when we have to go back for a checking
for (int j = 0; j < _numberOfCharsToKeep - 1; j++)
{
previousCharacters[j] = previousCharacters[j + 1];
}
previousCharacters[_numberOfCharsToKeep - 1] = c;
// Start of a text object
if (!inTextObject && CheckToken(new string[] { "BT" }, previousCharacters))
{
inTextObject = true;
}
}
return CleanupContent(resultString);
}
catch
{
return "";
}
}
private string CleanupContent(string text)
{
string[] patterns = { @"\\\(", @"\\\)", @"\\226", @"\\222", @"\\223", @"\\224", @"\\340", @"\\342", @"\\344", @"\\300", @"\\302", @"\\304", @"\\351", @"\\350", @"\\352", @"\\353", @"\\311", @"\\310", @"\\312", @"\\313", @"\\362", @"\\364", @"\\366", @"\\322", @"\\324", @"\\326", @"\\354", @"\\356", @"\\357", @"\\314", @"\\316", @"\\317", @"\\347", @"\\307", @"\\371", @"\\373", @"\\374", @"\\331", @"\\333", @"\\334", @"\\256", @"\\231", @"\\253", @"\\273", @"\\251", @"\\221"};
string[] replace = { "(", ")", "-", "'", "\"", "\"", "à", "â", "ä", "À", "Â", "Ä", "é", "è", "ê", "ë", "É", "È", "Ê", "Ë", "ò", "ô", "ö", "Ò", "Ô", "Ö", "ì", "î", "ï", "Ì", "Î", "Ï", "ç", "Ç", "ù", "û", "ü", "Ù", "Û", "Ü", "®", "™", "«", "»", "©", "'" };
for (int i = 0; i < patterns.Length; i++)
{
string regExPattern = patterns[i];
Regex regex = new Regex(regExPattern, RegexOptions.IgnoreCase);
text = regex.Replace(text, replace[i]);
}
return text;
}
#endregion
#region CheckToken
/// <summary>
/// Check if a certain 2 character token just came along (e.g. BT)
/// </summary>
/// <param name="tokens">the searched token</param>
/// <param name="recent">the recent character array</param>
/// <returns></returns>
private bool CheckToken(string[] tokens, char[] recent)
{
foreach (string token in tokens)
{
if ((recent[_numberOfCharsToKeep - 3] == token[0]) &&
(recent[_numberOfCharsToKeep - 2] == token[1]) &&
((recent[_numberOfCharsToKeep - 1] == ' ') ||
(recent[_numberOfCharsToKeep - 1] == 0x0d) ||
(recent[_numberOfCharsToKeep - 1] == 0x0a)) &&
((recent[_numberOfCharsToKeep - 4] == ' ') ||
(recent[_numberOfCharsToKeep - 4] == 0x0d) ||
(recent[_numberOfCharsToKeep - 4] == 0x0a))
)
{
return true;
}
}
return false;
}
#endregion
}
}
回答1:
Is there a specific reason you're not using the relatively new parsing classes? I don't know the Persian language, but the first Persian PDF I found on Google works, and it's much less code:
PdfReader reader = new PdfReader(pdfPath);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
StringBuilder sb = new StringBuilder();
for (int i = 1; i <= reader.NumberOfPages; i++) {
ITextExtractionStrategy strategy = parser.ProcessContent(
i, new SimpleTextExtractionStrategy()
);
sb.Append(strategy.GetResultantText());
}
A number of bugs have been fixed recently, so I'm using the latest iTextSharp SVN build. Also your question title includes parsing images, but your code doesn't, so the example above is not extracting any images.
来源:https://stackoverflow.com/questions/9447648/parse-a-persian-pdf-file-to-txt-and-its-images