content = content.replaceAll("/div>", "/span>
");

//关闭未封闭式标签br

content = content.replaceAll("
]*>", "
");

//处理样式background-color: transparent; IE模式下存在兼容问题，火狐谷歌正常

content = content.replaceAll("background-color: transparent;", " ");

//使用word拷贝到富文本生成的html内容，存在各作word标签，固然转换过程当中大部分都支持，若是遇到个别的能够作下处理

// content = content.replaceAll("", "");

// content = content.replaceAll("", "");

// content = content.replaceAll("", "");

// content = content.replaceAll("]*?>", "");

// content = content.replaceAll("]*)(?:lang|LANG|size|SIZE|face|FACE|[ovwxpOVWXP]:\\w+)=(?:'[^']*'|\"\"[^\"\"]*\"\"|[^>]+)([^>]*)>", "");

提取文本中的css样式

html中css优化是必不可少的，能够在富文本保存html的时候，对标签内容(表格、段落、字体等)使用css样式优化，目的就是转换的PDF能够更加贴近html页面样式，XMLWorkerHelper转换中能够支持css。html

public static String getCssStr(String content){

String reg = "\\.([a-zA-Z0-9_]*)\\s*(\\{[^\\}]*\\})";

Pattern p = Pattern.compile(reg);

Matcher m = p.matcher(content);

String cssStr="";

while(m.find()){

cssStr += m.group()+" ";

}

System.out.println(cssStr);

return cssStr;

}

字体处理

html内容字体设置，能够处理中文乱码，内容重叠，字体大小，字体颜色等java

import com.itextpdf.text.BaseColor;

import com.itextpdf.text.Font;

import com.itextpdf.tool.xml.XMLWorkerFontProvider;

public class PdfFont extends XMLWorkerFontProvider {

@Override

public Font getFont(String fontname, String encoding, boolean embedded, float size, int style, BaseColor color) {

String font = fontname;

if(font==null){//字体家族

font = "宋体";

}

if(size<=0){//size<0 会使内容重叠在一体

size=10.5f;

}

return super.getFont(fontname, encoding, embedded, size, style, color);

}

}

html转PDF文件

private static void htmlToPdf(String content,String css) throws IOException, DocumentException {

content = htmlTag(content);

ByteArrayInputStream in = new ByteArrayInputStream(content.getBytes());

Document document = new Document();

document.setMargins(30, 30, 30, 30); // 左，右，上，下

ByteArrayInputStream is = null;

if(!"".equals(css)){

is = new ByteArrayInputStream(css.getBytes());

}

PdfWriter writer = PdfWriter.getInstance(document, new FileOutputStream("C:\\Users\\Administrator\\Desktop\\temp.pdf"));// 建立书写器(Writer)

document.open();

//将html格式写入文档

XMLWorkerHelper.getInstance().parseXHtml(writer, document, in,is,new PdfFont());

document.close();

}