abcPDF是一个非常强大的pdf插件。在使用过程中,可能会遇到HTML转换为PDF时产生额外空白情况。本文介绍一种解决方法。
protected void RemoveBlankPages(Doc pdf) { for (int i =pdf.theDoc.PageCount; i > 0; i--) { pdf.theDoc.PageNumber = i; //get the pdf content string textContent = pdf.theDoc.GetText("Text"); //替换所有html textContent= Util.f_replacehtml(textContent); //delete the page if it is blank if (string.IsNullOrEmpty(textContent)) pdf.theDoc.Delete(pdf.theDoc.Page); } }
/// <summary>
/// 删除html脚本
/// </summary>
/// <param name="Htmlstring"></param>
/// <returns></returns>
public static string f_replacehtml(string Htmlstring)
{
Htmlstring = Regex.Replace(Htmlstring, @"<script[^>]*?>.*?</script>", "", RegexOptions.IgnoreCase);
//删除HTML
Htmlstring = Regex.Replace(Htmlstring, @"<(.[^>]*)>", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"([\r\n])[\s]+", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"-->", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"<!--.*", "", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(quot|#34);", "\"", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(amp|#38);", "&", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(lt|#60);", "<", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(gt|#62);", ">", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(nbsp|#160);", " ", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(iexcl|#161);", "\xa1", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(cent|#162);", "\xa2", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(pound|#163);", "\xa3", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&(copy|#169);", "\xa9", RegexOptions.IgnoreCase);
Htmlstring = Regex.Replace(Htmlstring, @"&#(\d+);", "", RegexOptions.IgnoreCase);
Htmlstring = Htmlstring.Replace("<", "");
Htmlstring = Htmlstring.Replace(">", "");
Htmlstring = Htmlstring.Replace("\"", "“");
Htmlstring = Htmlstring.Replace("\'", "’");
//Htmlstring = Htmlstring.Replace("—", "");
//Htmlstring = Htmlstring.Replace("…", "");
Htmlstring = HttpContext.Current.Server.HtmlEncode(Htmlstring).Trim();
return Htmlstring;
}