static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.StructuredExtractor instance
StructuredExtractor extractor = new StructuredExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile(@".\sample3.pdf");
for (int pageIndex = 0; pageIndex < extractor.GetPageCount(); pageIndex++)
{
Console.WriteLine("Starting extraction from page #" + pageIndex);
Console.WriteLine();
extractor.PrepareStructure(pageIndex);
int rowCount = extractor.GetRowCount(pageIndex);
for (int row = 0; row < rowCount; row++)
{
int columnCount = extractor.GetColumnCount(pageIndex, row);
for (int col = 0; col < columnCount; col++)
{
Console.WriteLine(extractor.GetCellValue(pageIndex, row, col));
}
}
}
Console.WriteLine();
Console.WriteLine("Press any key..");
Console.ReadKey();
}
static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.StructuredExtractor instance (former TableExtractor)
StructuredExtractor extractor = new StructuredExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample3.pdf");
for (int ipage = 0; ipage < extractor.GetPageCount(); ipage++)
{
Console.WriteLine("starting extraction from page #" + ipage);
extractor.PrepareStructure(ipage);
int rowCount = extractor.GetRowCount(ipage);
int CellsAlreadyScanned = 0;
for (int row = 0; row < rowCount; row++)
{
int columnCount = extractor.GetColumnCount(ipage, row);
for (int col = 0; col < columnCount; col++)
{
Console.WriteLine(extractor.GetCellValue(ipage, row, col));
}
CellsAlreadyScanned += columnCount;
}
}
Console.WriteLine("Press any key..");
Console.ReadKey();
}
static void Main(string[] args)
{
var allInputFiles = new string[] { "Sample_Files\\InvoiceMar.pdf", "Sample_Files\\InvoiceApr.pdf" };
// Google Sheet data to write
var reqRowData = new List <RowData>();
// Set page index
var pageIndex = 0;
// Loop through all input files
foreach (var itmFile in allInputFiles)
{
var invName = Path.GetFileNameWithoutExtension(itmFile);
// Create TextExtractor instance
using (var tableExtractor = new StructuredExtractor("demo", "demo"))
{
var tableExtractionArea = GetTableExtractionArea(itmFile);
if (tableExtractionArea.HasValue)
{
// Load document from file
tableExtractor.LoadDocumentFromFile(itmFile);
// Set extraction area
tableExtractor.SetExtractionArea(tableExtractionArea.Value);
// Prepare table structure
tableExtractor.PrepareStructure(pageIndex);
int rowCount = tableExtractor.GetRowCount(pageIndex);
// Ignoring first title row
for (int row = 1; row < rowCount; row++)
{
// Google Sheet RowData Input
var itmRowData = new RowData();
// Google Sheet CellData Input
var lstCellData = new List <CellData>();
int columnCount = tableExtractor.GetColumnCount(pageIndex, row);
// Add invName to CellData Collection
lstCellData.Add(new CellData {
UserEnteredValue = new ExtendedValue()
{
StringValue = invName
}
});
for (int col = 0; col < columnCount; col++)
{
// Get table cell value
var tableCellValue = tableExtractor.GetCellValue(pageIndex, row, col);
// Google Sheet CellData Input
var itmCellData = new CellData {
UserEnteredValue = new ExtendedValue()
{
StringValue = tableCellValue
}
};
// Add to CellData Collection
lstCellData.Add(itmCellData);
}
// Add to Google Sheet RowData Request
reqRowData.Add(new RowData {
Values = lstCellData
});
}
}
}
}
// Proceed with writing to Google Sheets
UserCredential credential;
// Follow article "https://developers.google.com/sheets/api/quickstart/dotnet" to generate credentials.json
using (var stream = new FileStream("credentials.json", FileMode.Open, FileAccess.Read))
{
// The file token.json stores the user's access and refresh tokens, and is created
// automatically when the authorization flow completed for the first time.
string credPath = "token.json";
credential = GoogleWebAuthorizationBroker.AuthorizeAsync(
GoogleClientSecrets.Load(stream).Secrets,
Scopes,
"user",
CancellationToken.None,
new FileDataStore(credPath, true)).Result;
Console.WriteLine($"Credential file saved to : {credPath}");
}
// Create Google Sheets API Service
var service = new SheetsService(new Google.Apis.Services.BaseClientService.Initializer()
{
HttpClientInitializer = credential,
ApplicationName = ApplicationName
});
// Fill following parameter with your google spreadsheet Id
// Usually find at url of spreadsheet: https://docs.google.com/spreadsheets/d/...ThisIsSpreadsheetId.../edit
var spreadsheetId = "xxxxxxSpreadsheetIdxxxxxxxxxx";
// Get exising row counts
var existingRowCount = service.Spreadsheets.Values.Get(spreadsheetId, range: "A1:D").Execute().Values.Count;
var lstRequsts = new List <Request>();
lstRequsts.Add(new Request
{
// New data to be written
UpdateCells = new UpdateCellsRequest()
{
Range = new GridRange {
StartRowIndex = existingRowCount, StartColumnIndex = 0
},
Rows = reqRowData,
Fields = "*"
}
});
// Prepare batch update spreadsheet request
var batchUpdateSpreadsheetRequest = new BatchUpdateSpreadsheetRequest()
{
Requests = lstRequsts
};
var batchUpdateRequest = service.Spreadsheets.BatchUpdate(batchUpdateSpreadsheetRequest, spreadsheetId);
// Perform google sheet updation
batchUpdateRequest.Execute();
Console.WriteLine("Google spreadsheet updated!");
Console.ReadLine();
}
static void Main(string[] args)
{
// char to delimit cells in a row
const string delimChar = ",";
// char to service as decimal separator
const string precChar = ".";
// output filename
const string outputCSVFileName = "outputTable.csv";
// Create Bytescout.PDFExtractor.StructuredExtractor object
StructuredExtractor structuredExtractor = new StructuredExtractor();
// set the registration key
structuredExtractor.RegistrationName = "demo";
structuredExtractor.RegistrationKey = "demo";
// Load sample PDF document
structuredExtractor.LoadDocumentFromFile("Prices.pdf");
// page to process
int PageIndex = 0;
// prepare structure of the first page (zero index)
structuredExtractor.PrepareStructure(PageIndex);
// get total number of rows in a table
int iRowCount = structuredExtractor.GetRowCount(PageIndex);
// search for the header column
// index of the row with the header
int iHeaderRowIndex = -1;
// iterate through rows to find the header row
for (int y = 0; y < iRowCount; y++)
{
// checking if the very first column (with date) is empty in the row
// if date is empty it means this row contains superscript values for the row below
if (structuredExtractor.GetCellValue(PageIndex, y, 0).IndexOf("Date") == 0 && // if 1st column starts with "Date"
structuredExtractor.GetCellValue(PageIndex, y, 1).IndexOf("Product") == 0 // if 2nd column starts with "Product"
)
{
// found row with the header, saving its index
iHeaderRowIndex = y;
break;
}
} // end for
// save number of columns in the header (so we are using the header row as a reference for the whole table)
int iHeaderColumnCount = structuredExtractor.GetColumnCount(PageIndex, iHeaderRowIndex);
// writing the header to the console
for (int jj = 0; jj < iHeaderColumnCount; jj++)
{
Console.Write(structuredExtractor.GetCellValue(PageIndex, iHeaderRowIndex, jj) + " | ");
}
Console.Write("\n"); // add line break
// we found a header i.e. we have a table below
// now reading row by row
// if first cell in a row contains superscript values for the row below
// we should save it and process along with the next row
// array to store superscript row
string[] superScriptRow = new string[iHeaderColumnCount];
bool PreviousRowWasSuperscript = false;
StringBuilder finalOutput = new StringBuilder();
// now iterate through rows from row after the header until we got to the stop text (ending the table)
for (int y = iHeaderRowIndex + 1; y < iRowCount; y++)
{
// current row
string[] currentRow = new string[iHeaderColumnCount];
// fill up row array with values
for (int x = 0; x < iHeaderColumnCount; x++)
{
currentRow[x] = structuredExtractor.GetCellValue(PageIndex, y, x);
}
// if no values in 1st and 2nd column for the current row then it means we have
// superscript values in this row. These superscript values belong to cells below
if (currentRow[0] == "" & currentRow[1] == "")
{
// clean the superscript row
superScriptRow.Initialize();
// copy current row to superscriptRow
for (int i = 0; i < iHeaderColumnCount; i++)
{
superScriptRow[i] = currentRow[i];
}
PreviousRowWasSuperscript = true;
// jump to next iteration
continue;
} // end if
// if previous row was superscript then add it to current row
if (PreviousRowWasSuperscript)
{
for (int i = 0; i < iHeaderColumnCount; i++)
{
// if previous row (with superscript values) is NOT empty then add superscript values
// to values in the current row separated by decimal char
if (superScriptRow[i] != "")
{
currentRow[i] = currentRow[i] + precChar + superScriptRow[i];
}
}
}
// reset flag for next iteration not to use
PreviousRowWasSuperscript = false;
// get current row as a string
StringBuilder rowString = new StringBuilder();
foreach (string cc in currentRow)
{
rowString.Append("\"" + cc + "\"");
rowString.Append(delimChar);
}
// add to final output string
finalOutput.AppendLine(rowString.ToString());
}
// write the generated csv into the console
Console.WriteLine(finalOutput.ToString());
// save the generate csv text into a file
System.IO.File.WriteAllText(outputCSVFileName, finalOutput.ToString());
Console.WriteLine("Done! Press any key to exit...");
Console.ReadKey();
Process.Start(outputCSVFileName);
}
static void Main(string[] args)
{
var allInputFiles = new string[] { "Sample_Files\\InvoiceMar.pdf", "Sample_Files\\InvoiceApr.pdf" };
var resultFileName = "output.xlsx";
// Set page index
var pageIndex = 0;
// Create output Spreadsheet
using (var document = new Spreadsheet())
{
// Add new worksheet
Worksheet worksheet = document.Workbook.Worksheets.Add("Invoices");
var ws_row = 0;
var ws_column = 0;
// Set Header value
worksheet.Cell(ws_row, ws_column).Font = new Font("Arial", 11, FontStyle.Bold);
worksheet.Cell(ws_row, (ws_column++)).Value = "Invoice";
worksheet.Cell(ws_row, ws_column).Font = new Font("Arial", 11, FontStyle.Bold);
worksheet.Cell(ws_row, (ws_column++)).Value = "Product Name";
worksheet.Cell(ws_row, ws_column).Font = new Font("Arial", 11, FontStyle.Bold);
worksheet.Cell((ws_row++), (ws_column++)).Value = "Price";
// Loop through all input files
foreach (var itmFile in allInputFiles)
{
var invName = Path.GetFileNameWithoutExtension(itmFile);
// Create TextExtractor instance
using (var tableExtractor = new StructuredExtractor("demo", "demo"))
{
var tableExtractionArea = GetTableExtractionArea(itmFile);
if (tableExtractionArea.HasValue)
{
// Load document from file
tableExtractor.LoadDocumentFromFile(itmFile);
// Set extraction area
tableExtractor.SetExtractionArea(tableExtractionArea.Value);
// Prepare table structure
tableExtractor.PrepareStructure(pageIndex);
int rowCount = tableExtractor.GetRowCount(pageIndex);
// Ignoring first title row
for (int row = 1; row < rowCount; row++)
{
int columnCount = tableExtractor.GetColumnCount(pageIndex, row);
// Write Invoice Data
ws_column = 0;
worksheet.Cell(ws_row, (ws_column++)).Value = invName;
for (int col = 0; col < columnCount; col++)
{
// Get table cell value
var tableCellValue = tableExtractor.GetCellValue(pageIndex, row, col);
// Write to spreadsheet
worksheet.Cell(ws_row, (ws_column++)).Value = tableCellValue;
}
// Set row pointer to next row
ws_row++;
}
}
}
}
// Save document
document.SaveAs(resultFileName, Bytescout.Spreadsheet.Constants.SpreadsheetFormatType.XLSX);
}
// Open generated XLSX file in default program
Process.Start(resultFileName);
}
/// <summary>
/// Parse Pdf and save into xlsx format
/// </summary>
/// <param name="file">File info for parse</param>
/// <param name="sw">stream writer </param>
/// <returns>File info of parsed file</returns>
public static bool ParsePdf(FileInfo file, StreamWriter sw)
{
try
{
var names = file.Name.Replace(".pdf", "").Split('-');
string teamName, value, matchName = names[0], matchId = names[1];
int columnCount, rowCount, teamNo = 0, count = 0;
var extractor = new StructuredExtractor
{
RegistrationName = "demo",
RegistrationKey = "demo"
};
// Load sample PDF document
extractor.LoadDocumentFromFile(file.FullName);
for (var pageIndex = 0; pageIndex < extractor.GetPageCount(); pageIndex++)
{
Console.WriteLine("Starting extraction from page #" + pageIndex);
extractor.PrepareStructure(pageIndex);
rowCount = extractor.GetRowCount(pageIndex);
for (var row = 0; row < rowCount; row++)
{
if (row < 2)
{
continue;
}
try
{
teamName = "";
columnCount = extractor.GetColumnCount(pageIndex, row);
for (var col = 0; col < columnCount; col++)
{
value = extractor.GetCellValue(pageIndex, row, col);
if (string.IsNullOrEmpty(value))
{
continue;
}
if (value.Contains("(") && value.Contains(")") && col == 0)
{
teamName = value.Substring(0, value.LastIndexOf("("));
teamNo = value.Substring(value.IndexOf("(") + 1, value.Length - (value.IndexOf(")"))).ToInt();
break;
}
if (col != 0)
{
continue;
}
while (!value.Contains("(") && !value.Contains(")") && count < 5)
{
value += $" {extractor.GetCellValue(pageIndex, ++row, col)}";
value = value.Replace(" ", " ");
count++;
}
count = 0;
teamName = value.Substring(0, value.LastIndexOf("(")).Trim();
teamNo = value.Substring(value.IndexOf("(") + 1, value.Length - (value.IndexOf(")"))).ToInt();
break;
}
Db.MatchDatas.Add(new MatchData()
{
LeagueId = matchId.ToInt(),
MatchName = matchName,
TeamName = teamName,
TeamNo = teamNo
});
Db.SaveChanges();
}
catch (Exception e)
{
sw.WriteLine("--------------------------------------------------------------------------------------");
sw.WriteLine(extractor.GetCellValue(pageIndex, row, 0));
sw.WriteLine("Error in file roe no :" + row + "--------" + file.Name);
sw.WriteLine(e.GetBaseException().Message);
sw.WriteLine("--------------------------------------------------------------------------------------");
}
}
}
return(true);
}
catch (Exception e)
{
Console.WriteLine(e.GetBaseException().Message);
sw.WriteLine(e.GetBaseException().Message);
}
return(false);
}
