Can we extract pdf Paragraph by Paragraph
Please try the following code example:
[C#]
Document doc = new Document(dataDir + "amblatt2013-10-05.pdf");
ParagraphAbsorber absorber = new ParagraphAbsorber();
absorber.Visit(doc);
foreach (PageMarkup markup in absorber.PageMarkups)
{
int i = 1;
foreach (MarkupSection section in markup.Sections)
{
int j = 1;
foreach (MarkupParagraph paragraph in section.Paragraphs)
{
StringBuilder paragraphText = new StringBuilder();
foreach (List<TextFragment> line in paragraph.Lines)
{
foreach (TextFragment fragment in line)
{
paragraphText.Append(fragment.Text);
}
paragraphText.Append("\r\n");
}
paragraphText.Append("\r\n");
Console.WriteLine("Paragraph {0} of section {1} on page {2}:", j, i, markup.Number);
Console.WriteLine(paragraphText.ToString());
j++;
}
i++;
}
}Not able to get ParagraphAbsorber class from my dll.