private string GetTextFromPDF(string path, int pagesToReturn)
{
try
{
var strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();//LocationTextExtractionStrategy();
StringBuilder text = new StringBuilder();
using (PdfReader reader = new PdfReader(path))
{
if (pagesToReturn >= reader.NumberOfPages || pagesToReturn == -1)
{
for (int i = 1; i <= reader.NumberOfPages; i++)
{
text.Append(iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, i, strategy));
}
}
else
{
for (int i = 1; i <= pagesToReturn; i++)
{
text.Append(iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, i, strategy));
}
}
}
return(text.ToString());
}
catch (Exception e)
{
Log.AddMessage(e.ToString(), "Error");
Console.WriteLine(e.ToString() + " : " + e.InnerException);
return(null);
}
}
public static bool ReadPdfText(string filepath, out string docText)
{
docText = string.Empty;
try
{
string pdffilename = filepath;
PdfReader pdfReader = new PdfReader(pdffilename);
int numberOfPages = pdfReader.NumberOfPages;
StringBuilder sbDocText = new StringBuilder();
for (int i = 1; i <= numberOfPages; ++i)
{
iTextSharp.text.pdf.parser.ITextExtractionStrategy strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
sbDocText.Append(iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfReader, i, strategy));
}
sbDocText.Append(" ");
pdfReader.Close();
docText = sbDocText.ToString();
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
return(false);
}
return(true);
}
private string GetTableAsStringFromPDF(string PdfFileName, int startPage)
{
iTextSharp.text.pdf.PdfReader pdfReader = new iTextSharp.text.pdf.PdfReader(PdfFileName);
string sOut = string.Empty;
for (int i = startPage; i <= pdfReader.NumberOfPages; i++)
{
iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy its = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
sOut += iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfReader, i, its);
}
return(sOut);
}
public List <PayStub> GenerateIndividualStubs(string filename)
{
List <PayStub> stubs = new List <PayStub>();
using (var reader = new PdfReader(filename))
{
for (var page = 1; page <= reader.NumberOfPages; page++)
{
//extract page text
var strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
var currentText = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, page, strategy);
var paystub = FindPayStubMatch(currentText);
if (paystub == null)
{
continue;
}
//write this individual page into a temp file
var outFileName = System.IO.Path.GetTempPath() + Guid.NewGuid() + ".pdf";
var pdfDoc = new Document(reader.GetPageSizeWithRotation(page));
var stream = new MemoryStream();
var pdf = new PdfCopy(pdfDoc, stream);
pdf.CloseStream = false;
pdfDoc.Open();
pdf.AddPage(pdf.GetImportedPage(reader, page));
pdf.Close();
pdfDoc.Close();
stream.Position = 0;
var stamper = new PdfStamper(new PdfReader(stream), new FileStream(outFileName, FileMode.Create));
if ((paystub.Password + "").Length > 0)
{
stamper.SetEncryption(Encoding.ASCII.GetBytes(paystub.Password), Encoding.ASCII.GetBytes(paystub.Password), PdfWriter.ALLOW_PRINTING,
PdfWriter.ENCRYPTION_AES_128 | PdfWriter.DO_NOT_ENCRYPT_METADATA);
}
stamper.Close();
stream.Close();
paystub.Filename = outFileName;
stubs.Add(paystub);
}
}
return(stubs);
}
public TDocs Process(FileInfo fi)
{
StringBuilder strBuilder = new StringBuilder();
PdfReader pdfReader = null;
TDocs tdoc = new TDocs();
tdoc.Path = fi.FullName;
tdoc.Name = fi.Name;
tdoc.Extension = fi.Extension.ToLower();
tdoc.Title = tdoc.Name.Substring(0, tdoc.Name.LastIndexOf('.'));
try
{
DateTime dtStart = DateTime.Now;
pdfReader = new PdfReader(fi.FullName);
int numberOfPages = pdfReader.NumberOfPages;
int i;
for (i = 1; i <= numberOfPages; ++i)
{
if (dtStart.AddMilliseconds(timeLimit) < DateTime.Now)
{
break;
}
iTextSharp.text.pdf.parser.ITextExtractionStrategy strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
strBuilder.Append(iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfReader, i, strategy));
}
DateTime dtEnd = DateTime.Now;
TimeSpan timeInter = dtEnd - dtStart;
tdoc.Content = strBuilder.ToString();
}
catch (Exception ex)
{
Debug.WriteLine(ex.Message);
}
finally
{
if (pdfReader != null)
{
pdfReader.Close();
}
}
return(tdoc);
}
static void Main(string[] args)
{
ITextParse.ExtractText("employe-1.pdf", "iparse.txt");
//using (PdfReader reader = new PdfReader("letter.pdf")) //Index was outside the bounds of the array.
//using (PdfReader reader = new PdfReader("employe-1.pdf")) //ok
//using (PdfReader reader = new PdfReader("feuille_de_paie.pdf")) //Rebuild failed: trailer not found.; Original message: PDF startxref not found.
using (iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader("modele-bulletin-de-salaire.pdf")) //ok
{
StringBuilder text = new StringBuilder();
for (int page = 1; page <= reader.NumberOfPages; page++)
{
iTextSharp.text.pdf.parser.ITextExtractionStrategy strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
//ITextExtractionStrategy strategy = new LocationTextExtractionStrategy();
string currentText = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, page, strategy);
currentText = Encoding.UTF8.GetString(ASCIIEncoding.Convert(Encoding.Default, Encoding.UTF8, Encoding.Default.GetBytes(currentText)));
text.Append(currentText);
}
System.IO.StreamWriter file = new System.IO.StreamWriter("itextsharp.txt");
file.WriteLine(text);
file.Close();
//return text.ToString();
}
//PdfSharp
using (var _document = PdfReader.Open("letter.pdf", PdfDocumentOpenMode.ReadOnly)) //ok
//using (var _document = PdfReader.Open("employe-1.pdf", PdfDocumentOpenMode.ReadOnly)) //ok
//using (var _document = PdfReader.Open("feuille_de_paie.pdf", PdfDocumentOpenMode.ReadOnly)) //Non-negative number required.
//using (var _document = PdfReader.Open("modele-bulletin-de-salaire.pdf", PdfDocumentOpenMode.ReadOnly)) //ok
{
System.IO.StreamWriter file = new System.IO.StreamWriter("pdfsharp.txt");
foreach (PdfPage page in _document.Pages)
{
var text = ExtractText(page);
foreach (string s in text)
{
file.Write(s);
}
}
file.Close();
}
//iTextSharp too
PDFParser parser = new PDFParser();
//parser.ExtractText("letter.pdf", "pdfparser.txt"); //error
parser.ExtractText("employe-1.pdf", "pdfparser.txt"); //ok
//parser.ExtractText("feuille_de_paie.pdf", "pdfparser.txt"); //error
//parser.ExtractText("modele-bulletin-de-salaire.pdf", "pdfparser.txt"); //error
//PdfSharp
//string text2 = PdfTextExtractor.GetText("letter.pdf"); //ok
//string text2 = PdfTextExtractor.GetText("employe-1.pdf"); //ok
//string text2 = PdfTextExtractor.GetText("feuille_de_paie.pdf"); //Non-negative number required.
string text2 = PdfTextExtractor.GetText("modele-bulletin-de-salaire.pdf"); //ok
System.IO.StreamWriter file2 = new System.IO.StreamWriter("PdfTextExtractor.txt");
file2.Write(text2);
file2.Close();
}
private void InputDir(string srcPath)
{
string fullName, paperName, paperXiangduiPath, paperTextXiangduiPath;
try
{
DirectoryInfo dir = new DirectoryInfo(srcPath);
FileSystemInfo[] fileinfo = dir.GetFileSystemInfos(); //返回目录中所有文件和子目录
foreach (FileSystemInfo i in fileinfo)
{
if (i is DirectoryInfo) //判断是否文件夹
{
DirectoryInfo subdir = new DirectoryInfo(i.FullName);
//subdir.Delete(true); //删除子目录和文件
InputDir(subdir.FullName);
}
else
{
if (i.Extension == ".pdf" || i.Extension == ".PDF" || i.Extension == ".txt" || i.Extension == ".TXT")
{
fullName = i.FullName;
paperName = i.Name.Substring(0, i.Name.Length - 4);
//判断文章表中是否有该名称的文件
var data = (from wz in wz_dt
where wz.文章名 == paperName
select wz).ToList();
if (data.Count == 0)
{
//如果文章表中没有，则在文章表中创建新的记录
DataRow newRow;
newRow = wz_dt.NewRow();
newRow["文章名"] = paperName;
//将绝对路径改为相对路径
MatchCollection mc;
List <Regex> regex_list = new List <Regex>();
regex_list.Add(new Regex("科学研究"));
regex_list.Add(new Regex("社会科学"));
regex_list.Add(new Regex("文学艺术"));
regex_list.Add(new Regex("应用科学"));
regex_list.Add(new Regex("哲学"));
regex_list.Add(new Regex("自然科学"));
for (int regex_int = 0; regex_int < regex_list.Count; regex_int++)
{
Regex r = regex_list[regex_int];
mc = r.Matches(fullName);
if (mc.Count != 0)
{
int index = mc[0].Index; //正则表达式位置
int qian_location = 1; //正则表达式的前一字符位置
int hou_location; //正则表达式的后一字符位置
if (mc[0].Value == "哲学")
{
hou_location = 2;
}
else
{
hou_location = 4;
}
int houZhui_length = 4; //扩展名长度
char qian = fullName[index - qian_location];
char hou = fullName[index + hou_location];
if ((qian == '/' || qian == '\\') & (hou == '/' || hou == '\\'))
{
if (i.Extension == ".pdf" || i.Extension == ".PDF")
{
paperXiangduiPath = ".\\" + fullName.Substring(index);
newRow["文件"] = paperXiangduiPath;
}
string hh = fullName.Substring(index);
string kk = hh.Substring(0, hh.Length - houZhui_length);
paperTextXiangduiPath = ".\\" + kk + ".txt";
newRow["text文件"] = paperTextXiangduiPath;
wz_dt.Rows.Add(newRow);
wz_ta.Update(wz_dt);
//将pdf文件内容写入txt文件
if (i.Extension == ".pdf" || i.Extension == ".PDF")
{
string text = "";
try
{
string pdffilename = fullName;
PdfReader pdfReader = new PdfReader(pdffilename);
int numberOfPages = pdfReader.NumberOfPages;
text = string.Empty;
for (int j = 1; j <= numberOfPages; ++j)
{
iTextSharp.text.pdf.parser.ITextExtractionStrategy strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
text += iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(pdfReader, j, strategy);
}
pdfReader.Close();
}
catch (Exception ex)
{
StreamWriter wlog = File.AppendText(System.AppDomain.CurrentDomain.SetupInformation.ApplicationBase + "\\mylog.log");
wlog.WriteLine("出错文件：" + "原因：" + ex.ToString());
wlog.Flush();
wlog.Close();
}
string ss = fullName.Substring(0, fullName.Length - houZhui_length) + ".txt";
StreamWriter fileWriter = new StreamWriter(ss, true);
fileWriter.Write(text);
fileWriter.Close();
}
}
}
}
}
}
}
}
}
catch (Exception e)
{
MessageBox.Show(e.Message);
}
}
public static bool CombineBriefPages_AddingBlanks(
List <CockleFilePdf> srcFiles, string src, TypeOfBindEnum bind)
{
// new attempt Dec 28, to account for divider pages (or any page without text)
// text has to start on odd-numbered page, if followed by divider page
// first, add 2 pages for each divider page, to account for front and back.
// then, when everything is together, cycle through doc to add extra dividers...
// ... so that text always falls on odd-numbered page
// should work for both Saddle Stitch and Perfect Bind
// create new list without cover, ordered by rank
List <CockleFilePdf> files = new List <CockleFilePdf>(
srcFiles
.Where(f => f.FileType != SourceFileTypeEnum.Cover)
.Where(f => f.FileType != SourceFileTypeEnum.InsideCv)
.Where(f => f.FileType != SourceFileTypeEnum.SidewaysPage)
.Where(f => f.FileType != SourceFileTypeEnum.Brief_Foldout)
.Where(f => f.FileType != SourceFileTypeEnum.Brief_ZFold)
.Where(f => f.FileType != SourceFileTypeEnum.App_Foldout)
.Where(f => f.FileType != SourceFileTypeEnum.App_ZFold)
.Where(f => f.FileType != SourceFileTypeEnum.Unrecognized)
.OrderBy(f => f.Rank));
if (files.Count < 1)
{
return(false);
}
// what if files.Count == 1 ??? just return ???
int pageCount = 0;
bool hasDividers = false;
bool firstAppFileFound = false;
int firstPageOfApp = -1;
try
{
using (var stream = new System.IO.FileStream(src, System.IO.FileMode.Create))
{
// initiate iTextSharp processes
iTextSharp.text.Document pdfdoc = new iTextSharp.text.Document(iTextSharp.text.PageSize.LETTER);
iTextSharp.text.pdf.PdfCopy pdfcopy = new iTextSharp.text.pdf.PdfCopy(pdfdoc, stream);
pdfdoc.Open();
// merge pdfs in folder
CockleFilePdf f;
for (int i = 0; i < files.Count; i++)
{
f = files[i];
// read file
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(f.FullName);
int filePageCount = reader.NumberOfPages;
// set up pdfstamper
iTextSharp.text.pdf.PdfStamper stamper = new iTextSharp.text.pdf.PdfStamper(reader, stream);
// look for divider pages here, add blank if exists
List <int> divider_pages = new List <int>();
iTextSharp.text.pdf.parser.PdfReaderContentParser parser = new iTextSharp.text.pdf.parser.PdfReaderContentParser(reader);
for (int j = 1; j <= reader.NumberOfPages; j++)
{
iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy extract = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
var extractedText = parser.ProcessContent(j, extract);
string textFromPage = extractedText.GetResultantText();
int cnt = textFromPage.ToCharArray().Count();
int mch_cnt = System.Text.RegularExpressions.Regex.Matches(textFromPage, @"A(PPENDIX|ppendix)").Count;
if (System.Text.RegularExpressions.Regex.Matches(textFromPage, @"\S").Count == 0)
{
// collect blank pages
divider_pages.Add(j);
}
else if (cnt < 50 && mch_cnt > 0)
{
// collect other divider pages
divider_pages.Add(j);
}
}
if (divider_pages.Count > 0)
{
hasDividers = true;
int k = 0; // adjust for total page number change
foreach (int page in divider_pages)
{
stamper.InsertPage(page + k, reader.GetPageSizeWithRotation(1));
filePageCount = reader.NumberOfPages;
k++;
}
}
// add blank page if needed to make even number
if (files[i].FileType == SourceFileTypeEnum.Index ||
files[i].FileType == SourceFileTypeEnum.Brief ||
files[i].FileType == SourceFileTypeEnum.App_Index ||
files[i].FileType == SourceFileTypeEnum.Motion ||
files[i].FileType == SourceFileTypeEnum.Divider_Page)
{
f.AssignNeedsBlankPage(files, reader.NumberOfPages);
if (f.NeedsBlankPage)
{
//PdfStamper stamper2 = new PdfStamper(reader, stream);
stamper.InsertPage(reader.NumberOfPages + 1, reader.GetPageSizeWithRotation(1));
filePageCount = reader.NumberOfPages;
}
}
// with last document in 'files', add extra pages to make divisible by 4
if (bind == TypeOfBindEnum.SaddleStitch && i == files.Count - 1)
{
if (bind == TypeOfBindEnum.SaddleStitch &&
(pageCount + reader.NumberOfPages) % 4 != 0)
{
//PdfStamper stamper3 = new PdfStamper(reader, stream);
while ((pageCount + reader.NumberOfPages) % 4 != 0)
{
stamper.InsertPage(reader.NumberOfPages + 1, reader.GetPageSizeWithRotation(1));
}
}
}
// get first page of first app file
if (!firstAppFileFound && files[i].FileType == SourceFileTypeEnum.App_File)
{
firstAppFileFound = true;
firstPageOfApp = pageCount + 1;
}
// add document to 'src'
pdfcopy.AddDocument(new iTextSharp.text.pdf.PdfReader(reader));
pageCount += reader.NumberOfPages;
}
pdfcopy.Close();
pdfdoc.CloseDocument();
}
// final cycle, if dividers, to make sure text starts on odd-sided pages
if (bind == TypeOfBindEnum.PerfectBind && hasDividers)
{
string dest = (System.IO.Path.GetDirectoryName(src) + @"\temp " + DateTime.Now.ToString("ddMMyyyyhhmmssffff"));
using (var stream = new System.IO.FileStream(dest, System.IO.FileMode.Create))
{
iTextSharp.text.pdf.PdfReader reader = new iTextSharp.text.pdf.PdfReader(src);
iTextSharp.text.pdf.PdfStamper stamper = new iTextSharp.text.pdf.PdfStamper(reader, stream);
// get all blank pages in appendix
iTextSharp.text.pdf.parser.PdfReaderContentParser parser = new iTextSharp.text.pdf.parser.PdfReaderContentParser(reader);
List <List <int> > groupsOfBlanks = new List <List <int> >();
List <int> group_list = new List <int>();
int x;
for (x = firstPageOfApp; x <= reader.NumberOfPages; x++)
{
iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy extract = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
var extractedText = parser.ProcessContent(x, extract);
string textFromPage = extractedText.GetResultantText();
// find blank pages and cluster into group_list
if (System.Text.RegularExpressions.Regex.Matches(textFromPage, @"\S").Count == 0)
{
// capture blank page cluster (??? but what if only 1 page ???)
if (group_list.Count == 0 || group_list.Contains(x - 1))
{
group_list.Add(x);
}
}
else
{
// find first page after cluster
if (group_list.Count > 0)
{
if (group_list.Last() % 2 == 1)
{
// add blank page
stamper.InsertPage(group_list.Last() + 1, reader.GetPageSizeWithRotation(1));
}
}
// clear list
group_list.Clear();
}
}
stamper.Close();
reader.Close();
}
System.IO.File.Delete(src);
System.IO.File.Move(dest, src);
}
}
catch (Exception excpt)
{
System.Diagnostics.Debug.WriteLine(excpt); return(false);
}
return(true);
}
public static void SplitPdf(string pdfPath, int step, string outPath = "")
{
var sw = new Stopwatch();
sw.Start();
string path = outPath == "" ? "" : outPath + "\\";
var files = Directory.EnumerateFiles(pdfPath, "*.pdf");
if (files.Count() == 0)
{
throw new Exception("По указанному пути PDF файлы не найдены.");
}
foreach (var file in files)
{
using (var reader = new PdfReader(file))
{
if (reader.NumberOfPages % 2 != 0)
{
throw new Exception("В документе нечетное количество страниц");
}
for (int i = 1; i <= reader.NumberOfPages; i += step)
{
string barcode = string.Empty;
using (var fs = new FileStream($"{path}{i}.pdf", FileMode.Create))
{
var doc = new Document();
var copy = new PdfCopy(doc, fs);
doc.Open();
var matches = new List <string>();
for (int j = 0; j < step; j++)
{
var strategy = new iTextSharp.text.pdf.parser.SimpleTextExtractionStrategy();
var parsedText = iTextSharp.text.pdf.parser.PdfTextExtractor.GetTextFromPage(reader, i + j);
Match firstPageMatches;
MatchCollection secondPageMatch;
if (j == 1)
{
secondPageMatch = Regex.Matches(parsedText, @"18810154\d{12,12}");
foreach (Match item in secondPageMatch)
{
matches.Add(item.Value);
}
}
else
{
firstPageMatches = Regex.Match(parsedText, @"18810154\d{12,12}");
if (firstPageMatches.Success)
{
barcode = firstPageMatches.Value;
matches.Add(firstPageMatches.Value);
}
}
copy.AddPage(copy.GetImportedPage(reader, i + j));
}
if (matches.Count < 2)
{
throw new Exception($"В {Path.GetFileName(file)} около страницы {i} не найден один из штрихкодов.");
}
if (!matches.GetRange(1, matches.Count - 1).Contains(matches.First()))
{
throw new Exception($"Файл: {Path.GetFileName(file)} Штрихкоды не совпадают около страницы {i}.");
}
doc.Close();
matches.Clear();
}
if (File.Exists($"{path}{i}.pdf"))
{
if (File.Exists($"{path}{barcode}.pdf"))
{
File.Delete($"{path}{barcode}.pdf");
}
File.Move($"{path}{i}.pdf", $"{path}{barcode}.pdf");
}
}
}
}
sw.Stop();
Console.WriteLine($"Elapsed: {sw.ElapsedMilliseconds} ms.");
}
