/// <summary>
/// 通过PDF文档对象解析PDF
/// </summary>
/// <param name="pdfDocument">PDF文档</param>
/// <param name="tableContainType">表格包含样式</param>
/// <returns></returns>
public static PDFModel Parser(PDDocument pdfDocument, TableContainType tableContainType)
{
ObjectExtractor extractor = new ObjectExtractor(pdfDocument);
PageIterator pageIterator = extractor.extract();
SpreadsheetExtractionAlgorithm tableExtractor = new SpreadsheetExtractionAlgorithm();
PDFModel pdfModel = new PDFModel();
PDFTextStripper pdfStripper = new PDFTextStripper();
pdfStripper.setPageEnd(pageEndMark);
//pdfStripper.setParagraphEnd(paragraphEndMark);
string[] strs = Regex.Split(pdfStripper.getText(pdfDocument), pageEndMark, RegexOptions.IgnoreCase);
if (strs != null && strs.Length > 0)
{
pdfModel.Pages = new List <PdfPageModel>();
int cp = 0;
while (pageIterator.hasNext())
{
PdfPageModel pdfPage = new PdfPageModel();
pdfPage.CurrentPage = cp + 1;
pdfPage.Text = strs[cp];
List <Table> tables = new List <Table>();
Page page = pageIterator.next();
var pageTables = tableExtractor.extract(page).toArray();
if (pageTables != null && pageTables.Length > 0)
{
for (int i = 0; i < pageTables.Length; i++)
{
tables.Add(pageTables[i] as Table);
}
}
pdfPage.Tables = tables;
pdfModel.Pages.Add(pdfPage);
cp++;
}
pdfModel.PageNumber = pdfModel.Pages.Count;
return(PdfTextFormater(pdfModel, tableContainType));
}
return(null);
}
