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)
{
// 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();
}
/// <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);
}