static void Main(string[] args)
{
PdfReader reader = new PdfReader(@"D:\191.pdf");
IEnumerable <string> GetColumnText(float llx, float lly, float urx, float ury)
{
int get_PageNum = reader.NumberOfPages;
for (int pagecount = 1; pagecount <= get_PageNum; pagecount++)
{
var rect = new iTextSharp.text.Rectangle(llx, lly, urx, ury);
var renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
var textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
var text = PdfTextExtractor.GetTextFromPage(reader, pagecount, textExtractionStrategy);
yield return(text);
}
}
foreach (string result in GetColumnText(0, 0, 500, 500000))
{
Console.Write("{0} ", result);
Console.ReadLine();
}
}
public static string ExtractText(this PdfReader pr, int pageI, RenderFilter[] f)
{
ITextExtractionStrategy s = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), f);
return(PdfTextExtractor.GetTextFromPage(pr, pageI, new LimitedTextStrategy2(s)));
//return PdfTextExtractor.GetTextFromPage(pr, pageI, new LimitedTextStrategy(new LocationTextExtractionStrategy(), f));
}
public List <string> getTextByCoOrdinate(PdfReader reader, int pageNumber, int cordinate1, int coordinate2, int coordinate3, int coordinate4)
{
List <string> data = new List <string>();
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(cordinate1, coordinate2, coordinate3, coordinate4);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
string text = PdfTextExtractor.GetTextFromPage(reader, pageNumber, textExtractionStrategy);
string[] words = text.Split('\n');
foreach (var x in words)
{
if (!string.IsNullOrWhiteSpace(x))
{
data.Add(x.Trim());
}
}
foreach (var y in data)
{
Console.WriteLine(y);
}
return(data);
}
//Extract word by location(rect)/
string GetTextByLocation(int page, RectangleJ area, bool landscape)
{
const float dpi = 72.0f;
float landscapeHeight = 8.23f;
RectangleJ location = new RectangleJ(area.X, area.Y, area.Width, area.Height);
if (landscape)
{
location.X = landscapeHeight - area.Y - area.Height;
location.Y = area.X;
location.Width = area.Height;
location.Height = area.Width;
}
location.X *= dpi;
location.Y *= dpi;
location.Width *= dpi;
location.Height *= dpi;
RenderFilter[] filter = { new RegionTextRenderFilter(location) };
ITextExtractionStrategy strategy;
StringBuilder text = new StringBuilder();
using (PdfReader reader = new PdfReader(filepath))
{
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
text.AppendLine(PdfTextExtractor.GetTextFromPage(reader, page, strategy));
}
return(text.ToString());
}
public void GetRectAnno()
{
string appRootDir = new DirectoryInfo(Environment.CurrentDirectory).Parent.Parent.FullName;
string filePath = outputFile;
int pageFrom = 0;
int pageTo = 0;
listaRectangulos.Clear();
try
{
using (PdfReader reader = new PdfReader(filePath))
{
pageTo = reader.NumberOfPages;
for (int i = 1; i <= reader.NumberOfPages; i++)
{
PdfDictionary page = reader.GetPageN(i);
PdfArray annots = page.GetAsArray(iTextSharp.text.pdf.PdfName.ANNOTS);
if (annots != null)
{
foreach (PdfObject annot in annots.ArrayList)
{
//abtiene Annotation de PDF File
PdfDictionary annotationDic = (PdfDictionary)PdfReader.GetPdfObject(annot);
PdfName subType = (PdfName)annotationDic.Get(PdfName.SUBTYPE);
//solo el subtype highlight
if (subType.Equals(PdfName.HIGHLIGHT))
{
// Obtiene Quadpoints y Rectángulo de texto resaltado
//Console.Write("HighLight at Rectangle {0} with QuadPoints {1}\n", annotationDic.GetAsArray(PdfName.RECT), annotationDic.GetAsArray(PdfName.QUADPOINTS));
outputData = "HighLight at Rectangle {0} with QuadPoints {1}\n" + annotationDic.GetAsArray(PdfName.RECT) + annotationDic.GetAsArray(PdfName.QUADPOINTS);
//Extraer texto usando la estrategia de rectángulo
PdfArray coordinates = annotationDic.GetAsArray(PdfName.RECT);
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(float.Parse(coordinates.ArrayList[0].ToString(), CultureInfo.InvariantCulture.NumberFormat), float.Parse(coordinates.ArrayList[1].ToString(), CultureInfo.InvariantCulture.NumberFormat),
float.Parse(coordinates.ArrayList[2].ToString(), CultureInfo.InvariantCulture.NumberFormat), float.Parse(coordinates.ArrayList[3].ToString(), CultureInfo.InvariantCulture.NumberFormat));
listaRectangulos.Add(rect);
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
ITextExtractionStrategy strategy;
StringBuilder sb = new StringBuilder();
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
sb.AppendLine(PdfTextExtractor.GetTextFromPage(reader, i, strategy));
}
}
}
}
}
}
catch (Exception ex)
{
}
}
/// <summary>
/// Gets the contents text from page to put in TOC.
/// </summary>
/// <returns>The name of the page.</returns>
/// <param name="pdfPath">The Pdf to read from.</param>
/// <param name="page">The pages to read from.</param>
public static string GetContentsTextFromPage(String pdfPath, int page)
{
PdfReader reader = new PdfReader(pdfPath);
StringWriter output = new StringWriter();
//Create rectangle to read from header
Rectangle mediabox = reader.GetPageSize(page);
float llx = mediabox.GetRight(10f) - 100f;
float urx = mediabox.GetRight(0f);
float lly = mediabox.GetTop(10f) - 50f;
float ury = mediabox.GetTop(0f);
Rectangle rect = new Rectangle(llx, lly, urx, ury);
//The header contains the name of the page. Read from Heaedr.
RenderFilter regionFilter = new RegionTextRenderFilter(rect);
ITextExtractionStrategy strategy = new FilteredTextRenderListener(
new LocationTextExtractionStrategy(), regionFilter);
output.WriteLine(PdfTextExtractor.GetTextFromPage(reader, page, strategy));
Console.WriteLine(output.ToString());
string ret = output.ToString();
//Remove newline characters
return(Regex.Replace(ret, @"\t|\n|\r", ""));
}
protected void Button1_Click(object sender, EventArgs e)
{
PdfReader pdfReader = new PdfReader("C:\\TESTE\\export.pdf");
//
// Summary:
// Constructs a Rectangle-object.
//
// Parameters:
// llx:
// lower left x
//
// lly:
// lower left y
//
// urx:
// upper right x
//
// ury:
// upper right y
Rectangle rect = new Rectangle(800, 700, 0, 500);
RenderFilter regionFilter = new RegionTextRenderFilter(rect);
ITextExtractionStrategy strategy = new FilteredTextRenderListener(
new LocationTextExtractionStrategy(), regionFilter);
lblText.Text = PdfTextExtractor.GetTextFromPage(pdfReader, 1, strategy).ToString();
}
private bool TextIsInRectangle(PdfReader reader, String text, Rectangle rect)
{
FilteredTextRenderListener filterListener = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), new RegionTextRenderFilter(rect));
String extractedText = PdfTextExtractor.GetTextFromPage(reader, 1, filterListener);
return(extractedText.Equals(text));
}
public static string GetRectangle(PdfReader reader, int pageNumber, float llx, float lly, float urx, float ury)
{
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(llx, lly, urx, ury);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
return(PdfTextExtractor.GetTextFromPage(reader, pageNumber, textExtractionStrategy));
}
private string[] ExtractCurrentColumnFromPage(Rectangle column, PdfReader reader, int page)
{
var renderFilter = new RegionTextRenderFilter(column);
var renderFilterArray = new RenderFilter[] { renderFilter };
var filteredTextRenderListener = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilterArray);
var textFromColumn = PdfTextExtractor.GetTextFromPage(reader, page, filteredTextRenderListener);
return(SplitColumnTextIntoRows(textFromColumn));
}
public string GetStringValueFromRegion(string file, iTextSharp.text.Rectangle rectangle)
{
var reader = new PdfReader(file);
var renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rectangle);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
return(PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategy));
}
private static string GetStringFromFile(PdfReader reader, Rectangle rect, int pageNumber)
{
ITextExtractionStrategy strategy;
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
string result = PdfTextExtractor.GetTextFromPage(reader, pageNumber, strategy).Replace((char)10, ' ');
return(result);
}
public static ITextExtractionStrategy MakeRectangle(float pixelDistanceFromLeft, float pixelDistanceFromBottom, float pixelDistanceWidth, float pixelDistanceHeight)
{
var rectangle = new System.util.RectangleJ(pixelDistanceFromLeft, pixelDistanceFromBottom, pixelDistanceWidth, pixelDistanceHeight);
var filters = new RenderFilter[1];
filters[0] = new RegionTextRenderFilter(rectangle);
ITextExtractionStrategy strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filters);
return(strategy);
}
private static string GetColumnText(PdfReader reader, int pageNum, float llx, float lly, float urx, float ury)
{
// reminder, parameters are in points, and 1 in = 2.54 cm = 72 points
var rect = new iTextSharp.text.Rectangle(llx, lly, urx, ury);
var renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
var textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
var text = PdfTextExtractor.GetTextFromPage(reader, pageNum, textExtractionStrategy);
return(text);
}
public List <Line> getTextFromRectangle(int x, int y, int w, int h)
{
System.util.RectangleJ rect0 = new System.util.RectangleJ(x, y, w, h);
RenderFilter[] filter = { new RegionTextRenderFilter(rect0) };
ITextExtractionStrategy strategy;
StringBuilder sb = new StringBuilder();
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
sb.AppendLine(PdfTextExtractor.GetTextFromPage(reader, 1, strategy));
List <Line> line = stockLine(sb.ToString());
return(line);
}
private void ReadText()
{
//List<string> linestringlist = new List<string>();
//PdfReader reader = new PdfReader(pdfFileName);
iTextSharp.text.Rectangle rectA = new iTextSharp.text.Rectangle(coordinate1a, coordinate2a, coordinate3a, coordinate4a);
iTextSharp.text.Rectangle rectB = new iTextSharp.text.Rectangle(coordinate1b, coordinate2b, coordinate3b, coordinate4b);
RenderFilter[] renderFilter = new RenderFilter[2];
renderFilter[0] = new RegionTextRenderFilter(rectA);
renderFilter[1] = new RegionTextRenderFilter(rectB);
ITextExtractionStrategy textExtractionStrategyA = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter[0]);
ITextExtractionStrategy textExtractionStrategyB = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter[1]);
textA = PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategyA);
textB = PdfTextExtractor.GetTextFromPage(reader, 1, textExtractionStrategyB);
}
public static void ExtractIDs()
{
PdfReader reader = new PdfReader($@"{jobDir}\PDF Extraction\temp\{sourcePDF}");
FileStream fs = new FileStream($@"{jobDir}\PDF Extraction\temp\extractedIDs.txt", FileMode.Create);
StreamWriter sw = new StreamWriter(fs);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
ITextExtractionStrategy strategy;
TextMarginFinder finder;
string previousVal = "";
string currentVal = "";
int count = 0;
string pages = "";
sw.WriteLine("Index\tID\tPageCounter\tPageNumber\tFileName");
for (int i = 1; i <= reader.NumberOfPages; i++)
{
try
{
// finder = parser.ProcessContent(i, new TextMarginFinder());
//Rectangle area = new Rectangle(finder.GetLlx(), finder.GetLly(), finder.GetWidth() / 2, finder.GetHeight() / 2);
Rectangle area = new Rectangle(414, 660, 522, 689);
RenderFilter filter = new RegionTextRenderFilter(area);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
currentVal = PdfTextExtractor.GetTextFromPage(reader, i, strategy);
Rectangle area2 = new Rectangle(465, 565, 555, 635);
RenderFilter filter2 = new RegionTextRenderFilter(area2);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter2);
pages = PdfTextExtractor.GetTextFromPage(reader, i, strategy);
if (previousVal != currentVal)
{
count = 0;
}
count++;
previousVal = currentVal;
sw.WriteLine($"{i}\t{currentVal}\t{pages.Split('\n')[0]}\t{count}\t{currentVal}-{count}");
}
catch (Exception)
{
sw.WriteLine($"{i}\tfailed");
}
}
sw.Flush();
sw.Close();
}
/// <summary>
/// Parse a Pdf file in two part.
/// Every part will be written in an existing text file (which in my case is on the desktop)
/// </summary>
/// <param name="args"></param>
static void Main(string[] args)
{
const string filePath = @"c:\Users\sofiane\Desktop\25_1.pdf";
const string outPath = @"c:\Users\sofiane\Desktop\test.txt";
//The following line is to prevent a warning when reading more than one pdf page. On the second page you'll get an encoding error otherwise
System.Text.Encoding.RegisterProvider(System.Text.CodePagesEncodingProvider.Instance);
PdfReader reader = new PdfReader(filePath);
string strText = string.Empty;
HashSet <String> names = new HashSet <string>();
var pdfDictionary = new PdfDictionary();
//ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy() if you want to extract info everywhere;
for (int page = 1; page <= reader.NumberOfPages; page++)
{
PdfDictionary dic = reader.GetPageN(page);
PdfDictionary resources = dic.GetAsDict(PdfName.RESOURCES);
if (resources != null)
{
//get fonts dico
PdfDictionary fonts = resources.GetAsDict(PdfName.FONT);
if (fonts != null)
{
PdfDictionary font;
foreach (PdfName key in fonts.Keys)
{
font = fonts.GetAsDict(key);
string name = font.GetAsName(PdfName.BASEFONT).ToString();
Console.WriteLine(name);
names.Add(name);
}
}
}
//ITextExtractionStrategy its = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
RenderFilter[] filter = get_render(page, 0);
ITextExtractionStrategy its = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
WriteInfile(reader, page, its, outPath);
leaRenderFilter[] filter2 = get_render(page, 1);
ITextExtractionStrategy itsL = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter2);
WriteInfile(reader, page, itsL, outPath);
}
reader.Close();
}
/// <summary>
/// Extracts text from PDF file. (only selectable text content from the pages, not OCR from images)
/// </summary>
/// <param name="filepath">input file path</param>
/// <param name="zone">Rectangle which specifies the zone where the text is extracted from a page. if it's null, then the full page is processed.</param>
/// <param name="pages">List of pages to extract data from. If null or first item is 0, all pages will be extracted.</param>
/// <returns>a list of strings. one string from each page</returns>
public static List <string> GetPdfTextFromPages(string filepath, RectangleF?zone = null, List <int> pages = null)
{
using (PdfReader reader = new PdfReader(filepath))
{
List <string> result = new List <string>();
if (pages == null || pages.First() == 0) //then read all pages
{
pages = Enumerable.Range(1, reader.NumberOfPages).ToList(); //create the list of all pagenumbers in the actual PDF
}
foreach (var i in pages)
{
if (i > reader.NumberOfPages)
{
continue;
}
if (zone.HasValue)
{ //zone based text extract
float x = Utilities.MillimetersToPoints(zone.Value.X);
float y = Utilities.MillimetersToPoints(zone.Value.Y);
float w = Utilities.MillimetersToPoints(zone.Value.Width);
float h = Utilities.MillimetersToPoints(zone.Value.Height);
var pagesize = reader.GetPageSizeWithRotation(i);
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(x, pagesize.Top - y, x + w, pagesize.Top - y - h); //tanslate coordinates to iText
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
string text = PdfTextExtractor.GetTextFromPage(reader, i, textExtractionStrategy);
result.Add(text.Replace("\n", Environment.NewLine));
}
else
{ //full page text extract
string text = PdfTextExtractor.GetTextFromPage(reader, i);
result.Add(text.Replace("\n", Environment.NewLine));
}
}
reader.Close();
return(result);
}
}
void TakeDataFromPdf(UnityWebRequest www)
{
MemoryStream mm = new MemoryStream(www.downloadHandler.data);
bytes = mm.ToArray();
PdfReader reader = new PdfReader(mm);
ITextExtractionStrategy strategy;
for (int q = 0; q < 6; q++)
{
for (int j = 0; j < 8; j++)
{
Rectangle rect = new Rectangle(45 + (j * Adeltax), 40 + (q * Adeltay), 138 + (j * Bdeltax), 130 + (q * Bdeltay));
RenderFilter filter = new RegionTextRenderFilter(rect);
string s;
strategy = new FilteredTextRenderListener(new SimpleTextExtractionStrategy(), filter);
s = "";
s = PdfTextExtractor.GetTextFromPage(reader, 1, strategy);
//step1_____________________________________
if (IsLaba(s))
{
float microBdeltaX = 0;
if (j == 0)
{
microBdeltaX = Bdeltax;
}
Bdeltax *= 2;
rect = new Rectangle(45 + (j * Adeltax), 40 + (q * Adeltay), 138 + (j * Bdeltax) + microBdeltaX, 130 + (q * Bdeltay));
filter = new RegionTextRenderFilter(rect);
strategy = new FilteredTextRenderListener(new SimpleTextExtractionStrategy(), filter);
s = PdfTextExtractor.GetTextFromPage(reader, 1, strategy);
j++;
Bdeltax /= 2;
}
nakedData.Add(s);
}
}
mm.Close();
}
public string ExtractByCoordinate()
{
ITextExtractionStrategy strategy;
Rectangle rectangle = new Rectangle(320, 785 - 250, 368, 799 - 250);
// Rectangle rectangle = new Rectangle(447, 934-250, 678, 951); -> Ok
RenderFilter filter = new RegionTextRenderFilter(rectangle);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
Console.WriteLine(PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy));
}
return(null);
}
public string ExtractData(float UIWith, float UIHeight, Point ll, Point ur,
int page = 1)
{
Console.WriteLine("Test");
float MultX = PageSize().Width / UIWith;
float MultY = PageSize().Height / UIHeight;
ITextExtractionStrategy strategy;
Rectangle rectangle = new Rectangle(ll.X * MultX, (UIHeight - ll.Y) * MultY, ur.X * MultX, (UIHeight - ur.Y) * MultY);
// Rectangle rectangle = new Rectangle(447, 934-250, 678, 951); // -> Ok
RenderFilter filter = new RegionTextRenderFilter(rectangle);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
// return "" + UIWith + " " + UIHeight + " " + ll.X + " " + ll.Y + " " + ur.X + " " + ur.Y;
return(PdfTextExtractor.GetTextFromPage(PdfReader, page, strategy));
}
public static string ReadID(string fileName)
{
try
{
PdfReader reader = new PdfReader(fileName);
PdfReaderContentParser parser = new PdfReaderContentParser(reader);
ITextExtractionStrategy strategy;
//TextMarginFinder finder;
//finder = parser.ProcessContent(1, new TextMarginFinder());
Rectangle area = new Rectangle(414, 660, 522, 689);
RenderFilter filter = new RegionTextRenderFilter(area);
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
return(PdfTextExtractor.GetTextFromPage(reader, 1, strategy));
}
catch (Exception)
{
return("unreadable");
}
}
public string GetTextInArea(string filename, int page, int x, int y, int width, int height)
{
string text = string.Empty;
using (PdfReader pdfReader = new PdfReader(filename))
{
RenderFilter filter = new RegionTextRenderFilter(new System.util.RectangleJ(x, y, width, height));
var strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
//var strategy = new SimpleTextExtractionStrategy();
text = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
text = Encoding.UTF8.GetString(ASCIIEncoding.Convert(
Encoding.Default, Encoding.UTF8,
Encoding.Default.GetBytes(text)));
}
return(text);
}
public string ReadFromPosistionIText()
{
RectangleJ rect = new RectangleJ(0, 0, 2000, 1800);
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
ITextExtractionStrategy strategy;
StringBuilder sb = new StringBuilder();
for (int i = 1; i <= Document.NumberOfPages; i++)
{
strategy = new FilteredTextRenderListener(
new LocationTextExtractionStrategy(), filter
);
sb.AppendLine(
PdfTextExtractor.GetTextFromPage(Document, i, strategy)
);
}
return(sb.ToString());
}
public override void ParseTag(String tag, PdfObject obj, PdfDictionary page)
{
if (obj is PdfNumber)
{
PdfNumber mcid = (PdfNumber)obj;
RenderFilter filter = new AcroFieldsFlattenTest.MyMarkedContentRenderFilter(mcid.IntValue);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
FilteredTextRenderListener listener = new FilteredTextRenderListener(
strategy, filter);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(
listener);
processor.ProcessContent(PdfReader.GetPageContent(page), page
.GetAsDict(PdfName.RESOURCES));
outp.Write(XMLUtil.EscapeXML(listener.GetResultantText(), true));
}
else
{
base.ParseTag(tag, obj, page);
}
}
public static string ReadDATAFromPDF(string fileName, string path)
{
StringBuilder sb = new StringBuilder();
if (File.Exists(fileName))
{
PdfReader reader = new PdfReader(fileName);
Rectangle rect = new Rectangle(0, 0, 415, 775);
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
ITextExtractionStrategy strategy;
for (int i = 1; i <= reader.NumberOfPages; i++)
{
strategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
sb.AppendLine(PdfTextExtractor.GetTextFromPage(reader, i, strategy));
}
}
MakeTempFile(sb, path);
return(sb.ToString());
}
/// <summary>
/// Retorna os campos do PDF por posição faz um retangulo
/// </summary>
/// <param name="CaminhoArquivo">Caminho do arqivo a ser lido</param>
/// <param name="Posicoes">Array com 3 posições</param>
/// <param name="Pagina">Número da página aonde se encontra os dados do cliente</param>
/// <returns>Retorna o valor encontrado</returns>
private string RetornarValor(String CaminhoArquivo, string[] Posicoes, int Pagina)
{
string retorno = string.Empty;
using (PdfReader pdfReader = new PdfReader(CaminhoArquivo))
{
RectangleJ rect = new RectangleJ(float.Parse(Posicoes[0]), float.Parse(Posicoes[1]), float.Parse(Posicoes[2]), float.Parse(Posicoes[3]));
RenderFilter[] renderFilter = { new RegionTextRenderFilter(rect) };
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
retorno = PdfTextExtractor.GetTextFromPage(pdfReader, Pagina, textExtractionStrategy);
rect = null;
renderFilter = null;
textExtractionStrategy = null;
pdfReader.Close();
pdfReader.Dispose();
}
return(retorno == string.Empty ? " " : retorno);
}
public string getParagraphByCoOrdinate(string filepath, int pageno, int cordinate1, int coordinate2, int coordinate3, int coordinate4, bool filter)
{
PdfReader reader = new PdfReader(filepath);
if (filter == false)
{
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(cordinate1, 1000 - coordinate2, coordinate3, 1000 - coordinate4);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
string text = PdfTextExtractor.GetTextFromPage(reader, pageno, textExtractionStrategy);
return(text);
}
else
{
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(cordinate1, coordinate2, coordinate3, coordinate4);
RenderFilter[] renderFilter = new RenderFilter[1];
renderFilter[0] = new RegionTextRenderFilter(rect);
ITextExtractionStrategy textExtractionStrategy = new FilteredTextRenderListener(new LocationTextExtractionStrategy(), renderFilter);
string text = PdfTextExtractor.GetTextFromPage(reader, pageno, textExtractionStrategy);
return(text);
}
}
// ---------------------------------------------------------------------------
public void Write(Stream stream)
{
using (ZipFile zip = new ZipFile()) {
zip.AddFile(PREFACE, "");
PdfReader reader = new PdfReader(PREFACE);
System.util.RectangleJ rect = new System.util.RectangleJ(
70, 80, 420, 500
);
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
ITextExtractionStrategy strategy;
StringBuilder sb = new StringBuilder();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
strategy = new FilteredTextRenderListener(
new LocationTextExtractionStrategy(), filter
);
sb.AppendLine(
PdfTextExtractor.GetTextFromPage(reader, i, strategy)
);
}
zip.AddEntry(RESULT, sb.ToString());
zip.Save(stream);
}
}
