//public string ReadFromPositionSpire()
//{
// PdfPageBase page = Document.Pages[0];
// string text = page.ExtractText(new RectangleF(50, 50, 500, 100));
// StringBuilder sb = new StringBuilder();
// sb.AppendLine(text);
// return sb.ToString();
// return string.Empty;
//}
public string BytescoutPDFExtractor(string path)
{
TextExtractor extractor = new TextExtractor("demo", "demo");
path = @"C:\Users\zulfiqar\Downloads\ExpenseClaimForm1_b2abe30fabca4b1ca322fafd74306ceb (1).pdf";
// load the document
extractor.LoadDocumentFromFile(path);
// get page count
//int pageCount = extractor.GetPageCount();
//int count = 0;
// iterate through pages
// 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(0);
return(extractedString);
}
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();
}
/// <summary>
/// Get text from particular region
/// </summary>
private static string GetTextFromRegion(TextExtractor textExtractor, RectangleF extractionRegion, int pageIndex = 0)
{
// Set Extraction Area
textExtractor.SetExtractionArea(extractionRegion);
// Get Text from that region
return(textExtractor.GetTextFromPage(pageIndex));
}
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)
{
// Create Bytescout.PDFExtractor.InfoExtractor instance
InfoExtractor infoExtractor = new InfoExtractor();
infoExtractor.RegistrationName = "demo";
infoExtractor.RegistrationKey = "demo";
TextExtractor textExtractor = new TextExtractor();
textExtractor.RegistrationName = "demo";
textExtractor.RegistrationKey = "demo";
// List all PDF files in directory
foreach (string file in Directory.GetFiles(@"..\..\..\..", "*.pdf"))
{
infoExtractor.LoadDocumentFromFile(file);
Console.WriteLine("File Name: " + Path.GetFileName(file));
Console.WriteLine("Page Count: " + infoExtractor.GetPageCount());
Console.WriteLine("Author: " + infoExtractor.Author);
Console.WriteLine("Title: " + infoExtractor.Title);
Console.WriteLine("Producer: " + infoExtractor.Producer);
Console.WriteLine("Subject: " + infoExtractor.Subject);
Console.WriteLine("CreationDate: " + infoExtractor.CreationDate);
Console.WriteLine("Text (first 2 lines): ");
// Load a couple of lines from each document
textExtractor.LoadDocumentFromFile(file);
using (StringReader stringReader = new StringReader(textExtractor.GetTextFromPage(0)))
{
Console.WriteLine(stringReader.ReadLine());
Console.WriteLine(stringReader.ReadLine());
}
Console.WriteLine();
}
// Cleanup
infoExtractor.Dispose();
textExtractor.Dispose();
Console.WriteLine();
Console.WriteLine("Press any key to continue...");
Console.ReadLine();
}
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");
// 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)
{
// 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();
}
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);
}
