static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("words-with-hyphens.pdf");
int pageCount = extractor.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
// Search each page for "hyphen" string
if (extractor.Find(i, "hyphen", false))
{
do
{
Console.WriteLine("Found on page " + i + " at location " + extractor.FoundText.Bounds.ToString());
}while (extractor.FindNext());
}
}
// Cleanup
extractor.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample2.pdf");
// Get page count
int pageCount = extractor.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
string fileName = "page" + i + ".txt";
// Save extracted page text to file
extractor.SavePageTextToFile(i, fileName);
}
// Open first output file in default associated application
System.Diagnostics.Process.Start(@".\page1.txt");
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample2.pdf");
// Get page count
int pageCount = extractor.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
string fileName = "page" + i + ".txt";
// Save extracted page text to file
extractor.SavePageTextToFile(i, fileName);
}
// Cleanup
extractor.Dispose();
// Open first output file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\page1.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample2.pdf");
int pageCount = extractor.GetPageCount();
// Search each page for some keyword
for (int i = 0; i < pageCount; i++)
{
if (extractor.Find(i, "References", false))
{
// If page contains the keyword, extract a text from it.
// For demonstration we'll extract the text from top part of the page only
extractor.SetExtractionArea(0, 0, 600, 200);
string text = extractor.GetTextFromPage(i);
Console.WriteLine(text);
}
}
Console.WriteLine();
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample1.pdf");
// Get page count
int pageCount = extractor.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
// Create new stream. You can use MemoryStream or any other System.IO.Stream inheritor.
FileStream stream = new FileStream(@".\page" + i + ".txt", FileMode.Create);
// Save text from page to the file stream
extractor.SavePageTextToStream(i, stream);
// Close stream
stream.Dispose();
}
// Cleanup
extractor.Dispose();
// Open first output file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\page1.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample1.pdf");
// Get page count
int pageCount = extractor.GetPageCount();
string outputText = "";
for (int i = 0; i < pageCount; i++)
{
// create new file stream
FileStream fStream = new FileStream("page" + i.ToString() + ".txt", FileMode.Create);
// save text from page #i to the file stream
extractor.SavePageTextToStream(i, fStream);
// close stream
fStream.Close();
}
// Open first output file in default associated application
System.Diagnostics.Process.Start("page1.txt");
}
static void Main(string[] args)
{
// Create and setup Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor("demo", "demo");
// Load PDF document
extractor.LoadDocumentFromFile(InputFile);
// List to keep non-empty page numbers
List <string> nonEmptyPages = new List <string>();
// Iterate through pages
for (int pageIndex = 0; pageIndex < extractor.GetPageCount(); pageIndex++)
{
// Extract page text
string pageText = extractor.GetTextFromPage(pageIndex);
// If extracted text is not empty keep the page number
if (pageText.Length > 0)
{
nonEmptyPages.Add((pageIndex + 1).ToString());
}
}
// Cleanup
extractor.Dispose();
// Form comma-separated list of page numbers to split("1,3,5")
string ranges = string.Join(",", nonEmptyPages);
// Create Bytescout.PDFExtractor.DocumentSplitter instance
DocumentSplitter splitter = new DocumentSplitter("demo", "demo");
splitter.OptimizeSplittedDocuments = true;
// Split document by non-empty in temp folder
string[] parts = splitter.Split(InputFile, ranges, TempFolder);
// Cleanup
splitter.Dispose();
// Create Bytescout.PDFExtractor.DocumentMerger instance
DocumentMerger merger = new DocumentMerger("demo", "demo");
// Merge parts
merger.Merge(parts, OutputFile);
// Cleanup
merger.Dispose();
// Delete temp folder
Directory.Delete(TempFolder, true);
// Open the result file in default PDF viewer (for demo purposes)
Process.Start(OutputFile);
}
static void Main(string[] args)
{
try
{
// Get all settings VM
var allSettings = GetSettingsVM("settings.json");
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
foreach (var fileName in Directory.GetFiles("InputFiles"))
{
// Load sample PDF document
extractor.LoadDocumentFromFile(fileName);
// Enable regex search
extractor.RegexSearch = true;
// Get Number of pages PDF contains
int pageCount = extractor.GetPageCount();
for (int iPage = 0; iPage < pageCount; iPage++)
{
// Loop through all search settings
foreach (var itmSearchSetting in allSettings.Settings)
{
// If found, then copy file to sub-category folder
if (extractor.Find(iPage, itmSearchSetting.regex, false))
{
// If Directory does not exists, then create them
if (!Directory.Exists($"{allSettings.MainFolderName}/{itmSearchSetting.category}"))
{
Directory.CreateDirectory($"{allSettings.MainFolderName}/{itmSearchSetting.category}");
}
// Copy File
File.Copy(fileName, $"{allSettings.MainFolderName}/{itmSearchSetting.category}/{Path.GetFileName(fileName)}", true);
}
}
}
}
// Cleanup
extractor.Dispose();
}
catch (Exception ex)
{
Console.WriteLine("Error: " + ex.Message);
}
Console.WriteLine();
Console.WriteLine("Press enter key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\Invoice.pdf");
extractor.RegexSearch = true; // Enable the regular expressions
int pageCount = extractor.GetPageCount();
// Search through pages
for (int i = 0; i < pageCount; i++)
{
// Search dates in format 12/31/1999
string regexPattern = "[0-9]{2}/[0-9]{2}/[0-9]{4}";
// See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
// Search each page for the pattern
if (extractor.Find(i, regexPattern, false))
{
do
{
Console.WriteLine("");
Console.WriteLine("Found on page " + i + " at location " + extractor.FoundText.Bounds);
Console.WriteLine("");
// Iterate through each element in the found text
foreach (ISearchResultElement element in extractor.FoundText.Elements)
{
Console.WriteLine(" Text: " + element.Text);
Console.WriteLine(" Font is bold: " + element.FontIsBold);
Console.WriteLine(" Font is italic: " + element.FontIsItalic);
Console.WriteLine(" Font name: " + element.FontName);
Console.WriteLine(" Font size: " + element.FontSize);
Console.WriteLine(" Font color: " + element.FontColor);
Console.WriteLine();
}
}while (extractor.FindNext());
}
}
// Cleanup
extractor.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample1.pdf");
// Set the matching mode.
// WordMatchingMode.None - treats the search string as substring
// WordMatchingMode.ExactMatch - treats the search string as separate word
// WordMatchingMode.SmartMatch - will find the word in various forms (like Adobe Reader).
extractor.WordMatchingMode = WordMatchingMode.ExactMatch;
int pageCount = extractor.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
// Search each page for "ipsum" string
if (extractor.Find(i, "ipsum", false))
{
do
{
Console.WriteLine("");
Console.WriteLine("Found on page " + i + " at location " + extractor.FoundText.Bounds.ToString());
Console.WriteLine("");
// Iterate through each element in the found text
foreach (SearchResultElement element in extractor.FoundText.Elements)
{
Console.WriteLine("Element #" + element.Index + " at left=" + element.Left + "; top=" + element.Top + "; width=" + element.Width + "; height=" + element.Height);
Console.WriteLine("Text: " + element.Text);
Console.WriteLine("Font is bold: " + element.FontIsBold);
Console.WriteLine("Font is italic:" + element.FontIsItalic);
Console.WriteLine("Font name: " + element.FontName);
Console.WriteLine("Font size:" + element.FontSize);
Console.WriteLine("Font color:" + element.FontColor);
}
}while (extractor.FindNext());
}
}
// Cleanup
extractor.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample1.pdf");
int pageCount = extractor.GetPageCount();
extractor.RegexSearch = true; // ' turn on the regular expression search
// search through pages
for (int i = 0; i < pageCount; i++)
{
// searches for the text starting from LABORIS and ending with VELIT words
string regexPattern = "LABORIS.*VELIT";
// see the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
// Search each page for the pattern
if (extractor.Find(i, regexPattern, false))
{
do
{
Console.WriteLine("");
Console.WriteLine("Found on page " + i + " at location " + extractor.FoundText.Bounds.ToString());
Console.WriteLine("");
// iterate through each element in the found text
foreach (SearchResultElement element in extractor.FoundText.Elements)
{
Console.WriteLine("Element #" + element.Index + " at left=" + element.Left + "; top=" + element.Top + "; width=" + element.Width + "; height=" + element.Height);
Console.WriteLine("Text: " + element.Text);
Console.WriteLine("Font is bold: " + element.FontIsBold);
Console.WriteLine("Font is italic:" + element.FontIsItalic);
Console.WriteLine("Font name: " + element.FontName);
Console.WriteLine("Font size:" + element.FontSize);
Console.WriteLine("Font color:" + element.FontColor);
}
}while (extractor.FindNext());
}
}
Console.WriteLine();
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
try
{
// Create Bytescout.PDFExtractor.TextExtractor instance
using (TextExtractor extractor = new TextExtractor())
{
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("SampleInvoice.pdf");
extractor.RegexSearch = true; // Enable the regular expressions
int pageCount = extractor.GetPageCount();
// Search through pages
for (int i = 0; i < pageCount; i++)
{
// Search credit card number in format of (XXXX XXXX XXXX XXXX)
string regexPattern = @"[0-9]{4} [0-9]{4} [0-9]{4} [0-9]{4}";
// See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
// Search each page for the pattern
if (extractor.Find(i, regexPattern, false))
{
do
{
// Iterate through each element in the found text
foreach (ISearchResultElement element in extractor.FoundText.Elements)
{
Console.WriteLine("Found Credit Card Number: " + element.Text);
}
}while (extractor.FindNext());
}
}
}
}
catch (Exception ex)
{
Console.WriteLine("Error: " + ex.Message);
}
Console.WriteLine();
Console.WriteLine("Press enter key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample1.pdf");
int pageCount = extractor.GetPageCount();
for (int i = 0; i < pageCount; i++)
{
// Search each page for "ipsum" string
if (extractor.Find(i, "ipsum", false))
{
do
{
Console.WriteLine("");
Console.WriteLine("Found on page " + i + " at location " + extractor.FoundText.Bounds.ToString());
Console.WriteLine("");
// iterate through each element in the found text
foreach (SearchResultElement element in extractor.FoundText.Elements)
{
Console.WriteLine("Element #" + element.Index + " at left=" + element.Left + "; top=" + element.Top + "; width=" + element.Width + "; height=" + element.Height);
Console.WriteLine("Text: " + element.Text);
Console.WriteLine("Font is bold: " + element.FontIsBold);
Console.WriteLine("Font is italic:" + element.FontIsItalic);
Console.WriteLine("Font name: " + element.FontName);
Console.WriteLine("Font size:" + element.FontSize);
Console.WriteLine("Font color:" + element.FontColor);
}
}while (extractor.FindNext());
}
}
Console.WriteLine();
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
static void Main(string[] args)
{
string inputFile = @".\sample2.pdf";
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(inputFile);
int pageCount = extractor.GetPageCount();
// Search each page for a keyword
for (int i = 0; i < pageCount; i++)
{
if (extractor.Find(i, "bombardment", false))
{
// Extract page
using (DocumentSplitter splitter = new DocumentSplitter("demo", "demo"))
{
splitter.OptimizeSplittedDocuments = true;
int pageNumber = i + 1; // (!) page number in ExtractPage() is 1-based
string outputFile = @".\page" + pageNumber + ".pdf";
splitter.ExtractPage(inputFile, outputFile, pageNumber);
Console.WriteLine("Extracted page " + pageNumber + " to file \"" + outputFile + "\"");
}
}
}
// Cleanup
extractor.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key...");
Console.ReadKey();
}
static void Main(string[] args)
{
TextExtractor extractor = new TextExtractor("demo", "demo");
// Load the document
extractor.LoadDocumentFromFile("sample2.pdf");
// Smart match the search string like Adobe Reader
extractor.WordMatchingMode = WordMatchingMode.SmartMatch;
string searchString = "land";
// Get page count
int pageCount = extractor.GetPageCount();
// Iterate through pages
for (int i = 0; i < pageCount; i++)
{
// Search for text string
if (extractor.Find(i, searchString, false))
{
do
{
// Output search results
Console.WriteLine("Found on page " + i + " at location " + extractor.FoundText.Bounds.ToString());
// Now we are getting the found text
string extractedString = extractor.FoundText.Text;
Console.WriteLine("Found text: " + extractedString);
}while (extractor.FindNext()); // Search next occurrence of the search string
}
}
// Cleanup
extractor.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key to exit...");
Console.ReadKey();
}
static void Main(string[] args)
{
TextExtractor extractor = new TextExtractor("demo", "demo");
// Load document
extractor.LoadDocumentFromFile(@".\sample2.pdf");
// Get page count
int pageCount = extractor.GetPageCount();
// Iterate through pages
for (int i = 0; i < pageCount; i++)
{
// Define rectangle location to extract from
RectangleF location = new RectangleF(0, 0, 200, 200);
// Set extraction area
extractor.SetExtractionArea(location);
// Extract text from the extraction area
string text = extractor.GetTextFromPage(i);
Console.WriteLine("Extracted from page #" + i + ":");
Console.WriteLine();
Console.WriteLine(text);
// Reset the extraction area
extractor.ResetExtractionArea();
Console.WriteLine();
}
// Cleanup
extractor.Dispose();
Console.WriteLine("Press any key to exit...");
Console.ReadKey();
}
static void Main(string[] args)
{
TextExtractor extractor = new TextExtractor("demo", "demo");
// load the document
extractor.LoadDocumentFromFile("sample2.pdf");
string searchString = "what";
// get page count
int pageCount = extractor.GetPageCount();
int count = 0;
// iterate through pages
for (int i = 0; i < pageCount; i++)
{
// search for text string
if (extractor.Find(i, searchString, false))
{
do
{
count++;
// output search results
Console.WriteLine("Found on page " + i + " at location " + extractor.FoundText.Bounds.ToString());
// now we are getting the found text
string extractedString = extractor.FoundText.Text;
Console.WriteLine("Extracted string: " + extractedString);
}while (extractor.FindNext()); // search next occurance of the search string
}
}
Console.WriteLine("Press any key to exit...");
Console.ReadKey();
}
private void BtnFindAll_Click(object sender, EventArgs e)
{
if (tbSearchExpression.Text.Length > 1)
{
// Prepare TextExtractor
using (TextExtractor textExtractor = new TextExtractor("demo", "demo"))
{
// Load document into TextExtractor
textExtractor.LoadDocumentFromFile(pdfViewerControl1.InputFile);
// Set options from UI
textExtractor.RegexSearch = cbRegex.Checked;
textExtractor.WordMatchingMode = WordMatchingMode.None;
// Search for text in all pages and store rectangles of found pieces
for (int pageIndex = 0; pageIndex < textExtractor.GetPageCount(); pageIndex++)
{
ISearchResult[] searchResults = textExtractor.FindAll(pageIndex, tbSearchExpression.Text, caseSensitive: true);
if (searchResults.Length > 0)
{
_foundTextRectangles[pageIndex] = searchResults.Select(searchResult => searchResult.Bounds).ToArray();
}
}
}
// Select fount rectangles in PDF Viewer
if (_foundTextRectangles.ContainsKey(pdfViewerControl1.CurrentPageIndex))
{
pdfViewerControl1.SelectionInPoints = _foundTextRectangles[pdfViewerControl1.CurrentPageIndex];
}
}
else
{
MessageBox.Show(@"Try larger search string");
}
}
static void Main(string[] args)
{
TextExtractor extractor = new TextExtractor("demo", "demo");
// load the document
extractor.LoadDocumentFromFile("../../sample2.pdf");
// get page count
int pageCount = extractor.GetPageCount();
int count = 0;
// iterate through pages
for (int i = 0; i < pageCount; i++)
{
// define rectangle location to extract from
RectangleF location = new RectangleF(0, 0, 200, 200);
// set extraction area
extractor.SetExtractionArea(location);
// extract text bounded by the extraction area
string extractedString = extractor.GetTextFromPage(i);
Console.WriteLine("Extracted from page #" + i + ":\r\n" + extractedString);
// reset extraction area to full page (by default)
extractor.ResetExtractionArea();
Console.WriteLine("\r\n");
}
Console.WriteLine("Press any key to exit...");
Console.ReadKey();
}
static void Main(string[] args)
{
string inputDocument = @".\samplePDF_SSNNo.pdf";
string outputDocument = @".\samplePDF_SSNNo_edited.pdf";
try
{
// Create Bytescout.PDFExtractor.TextExtractor instance
using (TextExtractor extractor = new TextExtractor("demo", "demo"))
{
// Create Bytescout.PDFExtractor.Remover2 instance
using (Remover2 remover = new Remover2("demo", "demo"))
{
// Load sample PDF document
extractor.LoadDocumentFromFile("samplePDF_SSNNo.pdf");
remover.LoadDocumentFromFile(inputDocument);
extractor.RegexSearch = true; // Enable the regular expressions
int pageCount = extractor.GetPageCount();
// Search through pages
for (int pageIndex = 0; pageIndex < pageCount; pageIndex++)
{
// Search SSN in format 202-55-0130 using regular expression.
// See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx
string regexPattern = "[0-9]{3}-[0-9]{2}-[0-9]{4}";
// Search each page for the pattern
ISearchResult[] searchResults = extractor.FindAll(pageIndex, regexPattern, caseSensitive: false);
foreach (var element in searchResults)
{
Console.WriteLine("Found SSN No: " + element.Text);
// Add rectangle of the found SSN to Remover
remover.AddTextToRemove(pageIndex, element.Bounds);
}
}
// Mask replaced text with black rectangle
remover.MaskRemovedText = true;
// Change the color of the mask rectangle, if necessary
//remover.MaskColor = Color.Red;
remover.PerformRemoval(outputDocument);
Console.WriteLine("Found SSNs removed, result saved to file \"" + outputDocument + "\"");
}
}
// Open result file in default associated application (for the demonstration purpose)
var processStartInfo = new ProcessStartInfo(outputDocument)
{
UseShellExecute = true
};
Process.Start(processStartInfo);
}
catch (Exception ex)
{
Console.WriteLine("Error: " + ex.Message);
}
Console.WriteLine();
Console.WriteLine("Press enter key to continue...");
Console.ReadLine();
}
public static Dictionary <int, PDFLineInfo> ScrapyDataFromPDFiles(string[] urllist)
{
PDFLineInfo temp = new PDFLineInfo();
Dictionary <int, PDFLineInfo> dictionary = new Dictionary <int, PDFLineInfo>();
//dictionary = new Dictionary<int, PDFLineInfo>();
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
for (int nFileIndex = 0; nFileIndex < urllist.Length; nFileIndex++)
{
//string currentFileName = "sample2.pdf";
string currentFileName = urllist[nFileIndex];
string currentTitleName = "";
// Load each PDF Document
extractor.LoadDocumentFromFile(currentFileName);
int pageCount = extractor.GetPageCount();
//most of all case i = 0 but one case i = 0
int pdfDocumentType = -1;// 1: material type 2: spirit type 3: Empty type.
/*if(currentFileName.Contains("R92(592112)_ExpViewPartList") == true)
* {
* int zz = 5;
* }*/
for (int i = 1; i < pageCount; i++)
{
if (currentTitleName.Contains("notable") == true)
{
break;
}
//if (extractor.Find(i, "Dyaco", false))
{
//extractor.SetExtractionArea(0, 0, 800, 2000);
string wholetext = extractor.GetTextFromPage(i);
//Console.WriteLine(wholetext);
string[] lines = wholetext.Split(new[] { "\r\n", "\r", "\n" }, StringSplitOptions.None);
//Console.WriteLine("Length ===================== >" + lines.Length);
//if line.getlen is not 4 alert!!
//1 . Notify Header Strings
int j = 0;
while (j < lines.Length)
{
if ((lines[j].ToLower().Contains("part") == true) && (findTitle == false))
{
//Console.WriteLine("Title = = = = => " + detectTitle(lines[i]));
currentTitleName = detectTitle(lines[j]);
findTitle = true;
j++;
continue;
}
if (currentTitleName.Contains("notable") == true)
{
break;
}
if (findTitle == false)
{
if (j > 2)
{
currentTitleName = "notable";
break;
}
j++;
continue;
}
var array = lines[j].Split(new string[] { " " }, StringSplitOptions.RemoveEmptyEntries);
if ((findheader == false) && (findTitle == true))
{
if ((lines[j].ToLower().Contains("dyaco") == true) || (lines[j].ToLower().Contains("material") == true) ||
(lines[j].ToLower().Contains("spirit") == true) || (lines[j].ToLower().Contains("no") == true) ||
(lines[j].ToLower().Contains("part") == true) || (lines[j].ToLower().Contains("qty") == true))
{
findheader = true;
{
if (lines[j].ToLower().Contains("material") == true)
{
pdfDocumentType = 1;
}
else if (lines[j].ToLower().Contains("spirit") == true)
{
pdfDocumentType = 2;
}
else
{
if (array.Length > 2)
{
if (array[2].ToLower().Contains("part") == true)
{
pdfDocumentType = 2;
}
}
pdfDocumentType = 3;
}
}
j++;
continue;
}
if (array.Length < 4)
{
j++;
continue;
}
}
if ((lines[j].Contains("(TRIAL VER. PDF Extractor SDK 8.4.1.2829.888331924)") == true) || ((lines[j].Contains("TRIAL VERSION EXPIRES 90 DAYS AFTER INSTALLATION") == true)))
{
j++;
continue;
}
if (pdfDocumentType == -1)
{
MessageBox.Show("Can not get pdf Type");
}
if (pdfDocumentType == 3)
{
if ((array.Length != 3) || (array[0].Length > 5))
{
j++;
continue;
}
}
else
{
if (array.Length != 4)
{
j++;
continue;
}
}
//Console.WriteLine("Document Type =====>" + pdfDocumentType);
//Console.WriteLine(RemoveSpace(array[0]));
//Console.WriteLine(RemoveSpace(array[1]));
//Console.WriteLine(RemoveSpace(array[2]));
//Console.WriteLine(RemoveSpace(array[3]));
/*if(array[0].Contains("57") == true)
* {
* int awe = 5;
* }*/
switch (pdfDocumentType)
{
case 1:
temp.PartID = RemoveSpace(array[1]);
temp.PartName = RemoveSpace(array[2]);
temp.PartKey = RemoveSpace(array[0]);
temp.Quantity = Int32.Parse(RemoveSpace(array[3])); //no change
break;
case 2:
temp.PartID = RemoveSpace(array[2]);
temp.PartName = RemoveSpace(array[1]);
temp.PartKey = RemoveSpace(array[0]);
temp.Quantity = Int32.Parse(RemoveSpace(array[3])); //no change
break;
case 3:
temp.PartID = ""; //empty
temp.PartName = RemoveSpace(array[1]);
temp.PartKey = RemoveSpace(array[0]);
temp.Quantity = Int32.Parse(RemoveSpace(array[2])); //no change
break;
}
temp.ProductName = currentTitleName; //no change
/*if(currentTitleName.Length <3)
* {
* int qqq = 5;
* }*/
j++;
//2. Add values to PDFLineInfo
dictionary.Add(nTotalIndex, temp);
nTotalIndex++;
}
}
}
findheader = false;
findTitle = false;
currentTitleName = "";
int currentpercent = (int)(20 * nFileIndex / urllist.Length);
Console.WriteLine("*******" + nFileIndex + "*********" + currentpercent + "********");
//updateing value
Form1.progressvalue = currentpercent;
Form1.progressBar1.BeginInvoke(new Action(() => Form1.progressBar1.Value = currentpercent));
Form1.percentlabel.Text = currentpercent.ToString() + "%";
}
return(dictionary);
}
static void Main(string[] args)
{
// Create TextExtractor instance
TextExtractor textExtractor = new TextExtractor("demo", "demo");
textExtractor.WordMatchingMode = WordMatchingMode.ExactMatch; // Set exact search (default is SmartSearch that works like in Adobe Reader)
// Create XMLExtractor instance
XMLExtractor xmlExtractor = new XMLExtractor("demo", "demo");
// Load document
textExtractor.LoadDocumentFromFile("Invoice.pdf");
xmlExtractor.LoadDocumentFromFile("Invoice.pdf");
// Results
string invoiceNo = string.Empty;
string invoiceDate = string.Empty;
string total = string.Empty;
string tableData = string.Empty;
// Iterate pages
for (int i = 0; i < textExtractor.GetPageCount(); i++)
{
RectangleF pageRectangle = textExtractor.GetPageRectangle(i);
RectangleF tableRect = new RectangleF(0, 0, pageRectangle.Width, 0);
// Search for "Invoice No."
if (textExtractor.Find(i, "Invoice No.", false))
{
// Get the found text rectangle
RectangleF textRect = textExtractor.FoundText.Bounds;
// Assume the text at right is the invoice number.
// Shift the rectangle to the right:
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
// Set the extraction region and extract the text
textExtractor.SetExtractionArea(textRect);
invoiceNo = textExtractor.GetTextFromPage(i).Trim();
}
// Search for "Invoice Date" and extract text at right
if (textExtractor.Find(i, "Invoice Date", false))
{
RectangleF textRect = textExtractor.FoundText.Bounds;
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
textExtractor.SetExtractionArea(textRect);
invoiceDate = textExtractor.GetTextFromPage(i).Trim();
}
// Search for "Quantity" keyword to detect the top of the tabular data rectangle
if (textExtractor.Find(i, "Quantity", false))
{
// Keep the top table coordinate
tableRect.Y = textExtractor.FoundText.Bounds.Top; // use textRect.Bottom if you want to skip column headers
}
// Search for "TOTAL" (it will be also the bottom of tabular data rectangle)
if (textExtractor.Find(i, "TOTAL", true /* case sensitive! */))
{
RectangleF textRect = textExtractor.FoundText.Bounds;
textRect.X = textRect.Right;
textRect.Width = pageRectangle.Right - textRect.Left;
textExtractor.SetExtractionArea(textRect);
total = textExtractor.GetTextFromPage(i).Trim();
// Calculate the table height
tableRect.Height = textRect.Top - tableRect.Top;
}
// Extract tabular data using XMLExtractor
if (tableRect.Height > 0)
{
xmlExtractor.SetExtractionArea(tableRect);
tableData = xmlExtractor.GetXMLFromPage(i);
}
}
// Display extracted data
Console.WriteLine("Invoice No.: " + invoiceNo);
Console.WriteLine("Invoice Date: " + invoiceDate);
Console.WriteLine("TOTAL: " + total);
Console.WriteLine("Table Data: ");
Console.WriteLine(tableData);
Console.WriteLine("Press any key...");
Console.ReadKey();
}
