/// <summary>
/// Reading PDF File line by line.
/// word[] contains lines of PDF.
/// </summary>
/// <param name="path">Absolute path of PDF</param>
public static void ReadLineByLine(string path)
{
if (File.Exists(path))
{
PdfReader reader = new PdfReader(path);
int intPageNum = reader.NumberOfPages;
string[] words;
string line;
string text;
for (int i = 1; i <= intPageNum; i++)
{
text = PdfTextExtractor.GetTextFromPage(reader, i, new LocationTextExtractionStrategy());
words = text.Split('\n');
for (int j = 0, len = words.Length; j < len; j++)
{
line = Encoding.UTF8.GetString(Encoding.UTF8.GetBytes(words[j]));
//Console.WriteLine(line);
if (line.Substring(0, 5).Equals("DIMTS"))
{
//Console.WriteLine(line);
string[] lineArray = line.Split(' ');
//Console.WriteLine(lineArray[0]+" "+lineArray[1]);
// Add Data to Dictionary
PDF_Data.Add(lineArray[1], new List <string>());
PDF_Data[lineArray[1]].Add(lineArray[2]);
PDF_Data[lineArray[1]].Add(lineArray[3] + " " + lineArray[4] + " " + lineArray[5]);
PDF_Data[lineArray[1]].Add(lineArray[6]);
PDF_Data[lineArray[1]].Add(lineArray[7]);
}
}
}
}
else
{
Console.WriteLine("File Not Found at the location specified");
}
}
public List <SearchResult> SearchPdfFiles(string path, List <string> searchStrings, List <string> searchFilters)
{
List <SearchResult> searchResults = new List <SearchResult>();
if (searchFilters.Contains("*.pdf"))
{
foreach (string file in Directory.GetFiles(path, "*.pdf"))
{
PdfDocument pdfDoc = new PdfDocument(new PdfReader(file));
int numberOfPages = pdfDoc.GetNumberOfPages();
foreach (string searchString in searchStrings)
{
if (!string.IsNullOrEmpty(searchString))
{
for (int i = 1; i <= numberOfPages; i++)
{
PdfPage page = pdfDoc.GetPage(i);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
var pageText = PdfTextExtractor.GetTextFromPage(page, strategy);
if (pageText.Contains(searchString))
{
string pageNumber = pdfDoc.GetPageNumber(page).ToString();
var searchResult = new SearchResult()
{
FilePath = file,
PageNumber = Int16.Parse(pageNumber),
Keyword = searchString
};
searchResults.Add(searchResult);
}
}
}
}
}
}
return(searchResults);
}
///原有读pdf的方法，已作废
public string ReadPdf2(string path)
{
text = "";
PdfReader pr = null;
try
{
pr = new PdfReader(path);
PdfReaderContentParser parser = new PdfReaderContentParser(pr);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
int i, Page = 4;
if (Page > pr.NumberOfPages)
{
Page = pr.NumberOfPages;
}
for (i = 1; i <= Page; i++)
{
text += PdfTextExtractor.GetTextFromPage(pr, i, strategy);
}
pr.Close();
text = text.Replace("", "").Replace(" ", "").Replace(" ", "").Replace(" ", "").Replace("\r", "").Replace("\f", "").Replace("\n", "").Replace("\t", "").Replace(" ", "");
if (text.Length > 300)
{
text = text.Substring(0, 300);
}
}
catch (Exception e)
{
if (pr != null)
{
pr.Close();
}
text = "文件读取异常";
}
return(text);
}
private string getContent(PdfReader pdfReader, string page1, string page2)
{
string pdfText = null;
int pageCount = pdfReader.NumberOfPages;
if (Convert.ToInt32(page2) > pageCount)
{
throw new Exception("PDF结尾页数不可超过最大页数 " + pageCount);
}
int begin = 1, last = pageCount;
if (page1 == "开始")
{
begin = 1;
}
else
{
begin = Convert.ToInt32(page1);
}
if (page2 == "结束")
{
last = pageCount;
}
else
{
last = Convert.ToInt32(page2);
}
for (int pg = begin; pg <= last; pg++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string value = PdfTextExtractor.GetTextFromPage(pdfReader, pg, strategy);
pdfText += value;
}
return(pdfText);
}
/// <summary>
/// Helper method to quick get the text out of a PDF file.
/// </summary>
/// <param name="pdfBuffer"></param>
/// <returns></returns>
public static string GetPdfText(byte[] pdfBuffer)
{
var pdfText = new StringBuilder();
if (pdfBuffer == null || pdfBuffer.Length <= 0)
{
return(null);
}
using (var reader = new PdfReader(pdfBuffer))
{
var numOfPages = reader.NumberOfPages;
for (var i = 1; i <= numOfPages; i++)
{
var pageText = PdfTextExtractor.GetTextFromPage(reader, i);
if (String.IsNullOrWhiteSpace(pageText))
{
continue;
}
pdfText.Append(pageText);
}
}
return(pdfText.ToString());
}
protected bool SearchPdfFile(string fileName, String searchText)
{
if (!File.Exists(fileName))
{
throw new FileNotFoundException("Arquivo não encontrado", fileName);
}
using (PdfReader reader = new PdfReader(fileName))
{
var strategy = new SimpleTextExtractionStrategy();
for (int page = 1; page <= reader.NumberOfPages; page++)
{
var currentPageText = PdfTextExtractor.GetTextFromPage(reader, page, strategy);
currentPageText = removerAcentos(currentPageText);
if (currentPageText.Contains(searchText))
{
return(true);
}
}
}
return(false);
}
public string readPDF(string fileName)
{
StringBuilder text = new StringBuilder();
if (File.Exists(fileName))
{
PdfReader pdfReader = new PdfReader(@fileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
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();
}
else
{
MessageBox.Show("No File Found :( ", "Error", MessageBoxButtons.OK, MessageBoxIcon.Error);
}
return(richTextBoxFileData.Text = text.ToString());
}
public void FindTextInPdf(string SearchStr, string[] sources)
{
if (sources.Count() > 2)
{
foreach (var item in sources.Skip(2))
{
if (File.Exists(item))
{
using (PdfReader reader = new PdfReader(item))
using (var doc = new PdfDocument(reader))
{
var pageCount = doc.GetNumberOfPages();
for (int i = 1; i <= pageCount; i++)
{
PdfPage page = doc.GetPage(i);
var box = page.GetCropBox();
var rect = new Rectangle(box.GetX(), box.GetY(), box.GetWidth(), box.GetHeight());
var filter = new IEventFilter[1];
filter[0] = new TextRegionEventFilter(rect);
ITextExtractionStrategy strategy = new FilteredTextEventListener(new LocationTextExtractionStrategy(), filter);
var str = PdfTextExtractor.GetTextFromPage(page, strategy);
if (str.Contains(SearchStr) == true)
{
Console.WriteLine("Searched text found in file:[ " + item + " ] page : [ " + i + " ]");
}
}
}
}
}
}
}
public static void ReadPDF(string fileName, RichTextBox rtb)
{
using (PdfReader reader = new PdfReader(fileName))
{
string fullText = String.Empty;
for (int i = 1; i <= reader.NumberOfPages; i++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string text = PdfTextExtractor.GetTextFromPage(reader, i, strategy).Replace(Environment.NewLine, String.Empty);
fullText += text;
//rtb.AppendText(text);
}
var res = Regex.Replace(fullText, @"[-]\s*(\n|\r|\r\n)\s*", "", RegexOptions.IgnoreCase | RegexOptions.Multiline);
var res2 = Regex.Replace(res, @",\s*(\n|\r|\r\n)\s*", ", ", RegexOptions.IgnoreCase | RegexOptions.Multiline);
var resultText = Regex.Replace(res2, @"[\s*](\n|\r|\r\n)*[\s*]", " ", RegexOptions.IgnoreCase | RegexOptions.Multiline);
foreach (var item in MainWindow.Keys)
{
foreach (var key in item)
{
// var regex = new Regex(Regex.Escape(key));
// resultText = regex.Replace(resultText, "\n" + key + ": \n", 1);
var pattern = "(\n|\r|\r\n)*\\s?" + key + "\\s*(\n|\r|\r\n)*\\s?";
var regexRemoveRN = new Regex(@pattern);
resultText = regexRemoveRN.Replace(resultText, "\n" + key + ": \n", 1);
}
}
rtb.AppendText(resultText);
TextWithFontExtractionStategy S = new TextWithFontExtractionStategy();
string rtbText = new TextRange(rtb.Document.ContentStart, rtb.Document.ContentEnd).Text;
string F = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, 4, S).Replace(Environment.NewLine, String.Empty);
}
}
public static string GetISBN(string path)
{
PdfReader reader = new PdfReader(path);
string isbn = "";
string pagetext = "";
for (int i = 1; i <= 10; i++)
{
pagetext = PdfTextExtractor.GetTextFromPage(reader, i);
string[] words = pagetext.Split(' ');
int wordsInPage = words.Length;
int currentWordIndex = 0;
foreach (string word in words)
{
if (word.Contains("ISBN"))
{
isbn = words[++currentWordIndex];
return(isbn);
}
currentWordIndex++;
}
}
return("ISBN coulden't be found");
}
/// <summary>
/// PDFs to text.
/// </summary>
/// <param name="path">The path.</param>
/// <returns>return extracted all string from pdf file</returns>
public static string PdfToText(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);
////text = "";
//string line;
//string []words = text.Split('\n');
//for (int j = 0, len = words.Length; j < len; j++)
//{
// string s= Encoding.UTF7.GetString(f);
// byte[] ff = Encoding.UTF7.GetBytes(words[j]);
// line = Encoding.UTF7.GetString(ff);
//}
}
public string ReadAll()
{
try
{
var reader = new PdfReader(_file);
var doc = new PdfDocument(reader);
var sb = new StringBuilder();
for (var page = 1; page <= doc.GetNumberOfPages(); page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
var content = PdfTextExtractor.GetTextFromPage(doc.GetPage(page), strategy);
sb.Append(content);
}
return(sb.ToString());
}
catch (Exception e)
{
Console.WriteLine(e);
SentrySdk.CaptureException(e);
return(_file.Extension == "" ? _file.Name : _file.Name.Replace(_file.Extension, ""));
}
}
public bool TakeSomeCellOfData(int x)
{
int y = 0;
x = EnterManager.instance.checkNumberOfLesson(x, ref y);
MemoryStream mm = new MemoryStream(bytes);
PdfReader reader = new PdfReader(mm);
ITextExtractionStrategy strategy;
RenderFilter filter;
string s;
Rectangle rect = new Rectangle(45 + (x * Adeltax), 40 + (y * Adeltay), 138 + (x * Bdeltax), 130 + (y * Bdeltay));
filter = new RegionTextRenderFilter(rect);
strategy = new FilteredTextRenderListener(new SimpleTextExtractionStrategy(), filter);
s = PdfTextExtractor.GetTextFromPage(reader, 1, strategy);
if (s.Contains("семинар") || s.Contains("лекции"))
{
return(true);
}
return(false);
}
public void ExtractData()
{
if (SourceLabels.Count > 0)
{
SourceLabels.Clear();
}
var SourceFiles = FileList(SourceFolder, new string[] { ".pdf" });
foreach (var file in SourceFiles)
{
using (FileStream fileStream = new FileStream(file, FileMode.Open, FileAccess.Read, FileShare.Read))
using (PdfReader reader = new PdfReader(fileStream))
{
for (int page = 1; page <= reader.NumberOfPages; page++)
{
string[] PageLines = new string[] { };
var text = PdfTextExtractor.GetTextFromPage(reader, page, new SimpleTextExtractionStrategy());
PageLines = text.Split(new[] { "\n" }, StringSplitOptions.RemoveEmptyEntries);
TLabel tempLabel = DataSorter(PageLines);
var add = 0;
SourceLabels.ForEach(s =>
{
if (s.ConsignmentNumber == tempLabel.ConsignmentNumber)
{
add++;
}
});
if (add == 0)
{
SourceLabels.Add(tempLabel);
}
}
Console.WriteLine("completed sourcelist update");
}
}
}
static void Main(string[] args)
{
string filePath = @"Your said path\the file name.pdf";
string outPath = @"the output said path\the text file name.txt";
int pagesToScan = 2;
string strText = string.Empty;
try
{
PdfReader reader = new PdfReader(filePath);
for (int page = 1; page <= pagesToScan; page++) //(int page = 1; page <= reader.NumberOfPages; page++) <- for scanning all the pages in A PDF
{
ITextExtractionStrategy its = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
strText = PdfTextExtractor.GetTextFromPage(reader, page, its);
strText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(strText)));
//creating the string array and storing the PDF line by line
string[] lines = strText.Split('\n');
foreach (string line in lines)
{
//Creating and appending to a text file
using (System.IO.StreamWriter file = new System.IO.StreamWriter(outPath, true))
{
file.WriteLine(line);
}
}
}
reader.Close();
}
catch (Exception ex)
{
Console.Write(ex);
}
}
/*
* Attempts to parse a PDF selected by the user on the file system. Calls "ContinueUpdate()" after
* a successful parse.
*/
private void btnOpen_Click(object sender, RoutedEventArgs e)
{
// The open file dialog to let the user select their pdf file.
OpenFileDialog dialog = new OpenFileDialog();
dialog.InitialDirectory = Environment.GetFolderPath(Environment.SpecialFolder.MyDocuments);
dialog.Filter = "Pdf Files|*.pdf";
if (dialog.ShowDialog() == true)
{
StringBuilder text = new StringBuilder();
try
{
// Using the iTextSharp library, we extract the text from the PDF and save it to a StringBuilder
PdfReader pdfReader = new PdfReader(dialog.FileName);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
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();
}
catch (Exception ex)
{
MessageBox.Show("Something is wrong with the file you have uploaded. Please choose a different file.", "Invalid File.");
return;
}
// If this point is reached, extraction was successful and the program will continue with the extracted text.
ContinueUpdate(text);
}
}
public static List <int> ReadPdfFile(string pdfFilePath, String searthText, string logFilePath)
{
List <int> pages = new List <int>();
try
{
LogMsg(logFilePath, string.Format("ReadPdfFile Marker 01", new object[] { pdfFilePath }));
FileInfo finfo = new FileInfo(pdfFilePath);
LogMsg(logFilePath, string.Format("ReadPdfFile Marker 02", new object[] { }));
if (File.Exists(pdfFilePath))
{
LogMsg(logFilePath, string.Format("ReadPdfFile Marker 03", new object[] { }));
PdfReader pdfReader = new PdfReader(pdfFilePath);
for (int page = 1; page <= pdfReader.NumberOfPages; page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
string currentPageText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
if (currentPageText.Contains(searthText))
{
pages.Add(page);
}
}
pdfReader.Close();
LogMsg(logFilePath, string.Format("ReadPdfFile completed full method", new object[] { }));
}
LogMsg(logFilePath, string.Format("ReadPdfFile before returning", new object[] { }));
return(pages);
}
catch (Exception ex)
{
LogMsg(logFilePath, string.Format("ReadPdfFile of SplitPDF: Error Msg: {0} Trace: {1}", new object[] { ex.Message, ex.StackTrace }));
return(pages);
}
}
private static Dictionary <string, string> GetFileContentsThroughIText(string[] files)
{
Dictionary <string, string> contents = new Dictionary <string, string>();
foreach (var file in files)
{
StringBuilder text = new StringBuilder();
using (PdfReader reader = new PdfReader(file))
{
ITextExtractionStrategy Strategy = new iTextSharp.text.pdf.parser.LocationTextExtractionStrategy();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
string page = PdfTextExtractor.GetTextFromPage(reader, i, Strategy);
text.Append(page);
}
}
contents.Add(file, text.ToString());
}
return(contents);
}
public static Dictionary <int, string[]> ExtractTextFromPdf(string path)
{
Dictionary <int, string[]> pdfTextDict = new Dictionary <int, string[]>();
string bomPage = string.Empty;
int bomPageNo = -1;
using (PdfReader reader = new PdfReader(path))
{
StringBuilder text = new StringBuilder();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
string page = PdfTextExtractor.GetTextFromPage(reader, i, new SimpleTextExtractionStrategy());
MatchCollection bomMatches = bomRegex.Matches(page);
if (bomMatches.Count > 0)
{
bomPageNo = i;
bomPage = string.Join("\n", from Match match in bomMatches select match.Value);
break;
}
pdfTextDict.Add(i, page.Split('\n'));
}
}
if (bomPageNo > -1 && !string.IsNullOrEmpty(bomPage))
{
pdfTextDict = new Dictionary <int, string[]>();
pdfTextDict.Add(bomPageNo, bomPage.Split('\n'));
}
return(pdfTextDict);
}
private string GetPlainTextFromDocument(Document document)
{
string plainText = string.Empty;
try
{
string destinationFilePath = string.Format("{0}\\{1}", _folderService.GenerateFolderPath(document.ParentFolderID), document.FileID);
if (document.FileExtension == ".pdf")
{
PdfReader reader = new PdfReader(destinationFilePath);
StringWriter output = new StringWriter();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
output.WriteLine(PdfTextExtractor.GetTextFromPage(reader, i, new SimpleTextExtractionStrategy()));
}
plainText = output.ToString();
}
}
catch { }
return(plainText);
}
public static string ReadText(string filePath, int pageNumber = -1)
{
if (pageNumber == 0)
{
throw new Exception("page must bigger than 0");
}
PdfReader reader = new PdfReader(filePath);
StringWriter output = new StringWriter();
SimpleTextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
if (pageNumber == -1)
{
pageNumber = reader.NumberOfPages;
}
for (int i = 1; i <= pageNumber; i++)
{
output.WriteLine(PdfTextExtractor.GetTextFromPage(reader, i, strategy));
}
return(output.ToString());
}
public PdfInfo Parse(string path)
{
var reader = new PdfReader(path);
var text = string.Empty;
for (var page = 1; page <= reader.NumberOfPages; page++)
{
text += PdfTextExtractor.GetTextFromPage(reader, page);
}
reader.Close();
return(new PdfInfo
{
Path = path,
ImplicitKeywords = reader.Info["Keywords"].Split(ExplicitDelimitater).Select(x => new Keyword {
Value = x
}).ToHashSet(),
ExplicitKeywords = text.Split(ExplicitDelimitater).Select(x => new Keyword {
Value = x
}).ToHashSet(),
VisitedDateTime = DateTime.Now
});
}
} // KamilFunct
public static string ExtractTextFromPdf(string path)
{
using (PdfReader reader = new PdfReader(path))
{
StringBuilder text = new StringBuilder();
for (int i = 1; i <= reader.NumberOfPages; i++)
{
string temp_str = "";
temp_str = PdfTextExtractor.GetTextFromPage(reader, i);
if (i == 22)
{
;
}
text.Append(temp_str);
}
return(text.ToString());
}
}
public BaseFileExtract(string fileName_, int startpage_ = 1, int endPage_ = 0)
{
_fileName = fileName_;
StringBuilder sBuilder = new StringBuilder();
using (PdfReader pdfReader = new PdfReader(fileName_))
{
if (endPage_ == 0)
{
endPage_ = pdfReader.NumberOfPages;
}
// Loop through each page of the document
for (var page = startpage_; page <= endPage_; page++)
{
ITextExtractionStrategy strategy = new LocationTextExtractionStrategy();
var currentText = PdfTextExtractor.GetTextFromPage(pdfReader, page, strategy);
currentText = Encoding.UTF8.GetString(Encoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
sBuilder.Append(currentText);
}
}
_rawtxt = sBuilder.ToString();
}
public static List <string> PdfRead()
{
List <string> list = new List <string>();
PdfReader reader = new PdfReader("../../2015yerlestirme.pdf");
int intPageNum = reader.NumberOfPages;
string[] words;
string line;
string text;
for (int i = 1; i <= intPageNum; i++)
{
text = PdfTextExtractor.GetTextFromPage(reader, i, new LocationTextExtractionStrategy());
words = text.Split('\n');
for (int j = 0, len = words.Length; j < len; j++)
{
line = Encoding.UTF8.GetString(Encoding.UTF8.GetBytes(words[j]));
list.Add(line);
}
}
return(list);
}
public string FindMatch(string Regex)
{
PdfReader reader = new PdfReader(this.FileLocation);
Regex regex = new Regex(Regex);
string result = "Match not Found";
int n = reader.NumberOfPages;
for (int i = 1; i <= n; i++)
{
string text = PdfTextExtractor.GetTextFromPage(reader, i);
if (regex.IsMatch(text))
{
Match m = regex.Match(text);
result = m.Value.ToString();
}
if (result != "Match not Found")
{
break;
}
}
reader.Close();
return(result);
}
// ---------------------------------------------------------------------------
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);
}
}
/// <summary>
/// Gets texts from PDF file and calls returns their differences
/// </summary>
private ICollection <string> ComparePDF()
{
var originalPDF = new PdfDocument(new PdfReader(_originalFile));
var modifiedPDF = new PdfDocument(new PdfReader(_modifiedFile));
List <string> originalText = new List <string>();
List <string> modifiedText = new List <string>();
for (int i = 1; i <= originalPDF.GetNumberOfPages(); i++)
{
string originalPage = PdfTextExtractor.GetTextFromPage(originalPDF.GetPage(i));
originalText.AddRange(originalPage.Split('\n'));
}
for (int i = 1; i <= modifiedPDF.GetNumberOfPages(); i++)
{
string modifiedPage = PdfTextExtractor.GetTextFromPage(modifiedPDF.GetPage(i));
modifiedText.AddRange(modifiedPage.Split('\n'));
}
originalPDF.Close();
modifiedPDF.Close();
return(CompareTexts(originalText, modifiedText));
}
private async Task ParserPdf(string pdfFilePath)
{
using (PdfReader reader = new PdfReader(pdfFilePath))
{
for (int page = 1; page <= reader.NumberOfPages; page++)
{
var its = new Core.LocationTextExtractionStrategyEx();
String str = PdfTextExtractor.GetTextFromPage(reader, page, its);
using (StringReader stringReader = new StringReader(str))
{
string line;
while ((line = stringReader.ReadLine()) != null)
{
if (line.StartsWith("#"))
{
int col = int.Parse(line.Substring(1, line.IndexOf(" ")).Trim());
var column = GetCulumn(col);
if (!dPages.ContainsKey(page))
{
dPages[page] = new Dictionary <int, StringBuilder>();
}
if (!dPages[page].ContainsKey(column))
{
dPages[page][column] = new StringBuilder();
}
dPages[page][column].Append(line.Substring(line.IndexOf(" ")));
}
}
}
}
}
}
/// <summary>
/// Extracts all text from PDF file and separates it by lines
/// </summary>
/// <param name="filePath">The location of PDF file to read from</param>
/// <returns>Array of <see cref="string"/> each containing a single line</returns>
private string[] ReadAllLines(string filePath)
{
// Create the return array first
string[] lines = { "" };
// Make sure the file exists
if (File.Exists(filePath))
{
// Make sure we are looking at a PDF file
string ext = Path.GetExtension(filePath);
if (ext.ToLower() == ".pdf")
{
string allExtractedText = "";
// Load the PDF file and extract all text
using (PdfReader reader = new PdfReader(filePath))
{
using (PdfDocument doc = new PdfDocument(reader))
{
for (int page = 1; page <= doc.GetNumberOfPages(); page++)
{
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
allExtractedText = string.Concat(allExtractedText, PdfTextExtractor.GetTextFromPage(doc.GetPage(page), strategy));
}
}
}
lines = allExtractedText.Split(
new[] { "\r\n", "\r", "\n" },
StringSplitOptions.None
);
}
}
return(lines);
}