HTML(页面内容)转 PDF 问题 --itextsharp ？

Question

使用版本itextsharp 5.5.4 itextsharp.xmlworker5.5.4

最终希望效果：http://html2pdf.seven49.net/en/Home/Default.htm

遇到的问题

对于自行写的简单的html 能成功转换成 pdf
而对于 复杂的网站界面就 无法实现了
主要报错原因是 html标签的不规范(严谨)
例如：
读取 http://segmentfault.com/u/izhinia
错误提示： iTextSharp.tool.xml.exceptions.RuntimeWorkerException: Invalid nested tag head found, expected closing tag link.

读取

---

报错：

---

读取 http://www.afterlogic.com/mailbee-net/docs-itextsharp/
错误提示： iTextSharp.tool.xml.exceptions.RuntimeWorkerException: Invalid nested tag head found, expected closing tag link.

读取

Byte[] pageData = MyWebClient.DownloadData("http://www.baidu.com/"); //从指定网站下载数据

报错

iTextSharp.tool.xml.exceptions.RuntimeWorkerException: Invalid nested tag head found, expected closing tag meta.

博客园我也创建了一个小组，下面是小组地址：

http://home.cnblogs.com/group/topic/71624.html

---

下面是我实现的代码和效果图(这里只实现了简单的html+css)：

图片效果

下面是我的代码：

    /// <summary>
    /// 判断是否有乱码
    /// </summary>
    /// <param name="txt"></param>
    /// <returns></returns>
    public bool isMessyCode(string txt)
    {
        var bytes = Encoding.UTF8.GetBytes(txt);            //239 191 189            
        for (var i = 0; i < bytes.Length; i++)
        {
            if (i < bytes.Length - 3)
                if (bytes[i] == 239 && bytes[i + 1] == 191 && bytes[i + 2] == 189)
                {
                    return true;
                }
        }
        return false;
    }
    /// <summary>
    /// 获取网站内容，包含了 HTML+CSS+JS
    /// </summary>
    /// <returns>String返回网页信息</returns>
    public string getWebContent()
    {
        try
        {
            WebClient MyWebClient = new WebClient();
            MyWebClient.Credentials = CredentialCache.DefaultCredentials;
            //获取或设置用于向Internet资源的请求进行身份验证的网络凭据
            Byte[] pageData = MyWebClient.DownloadData("D:\\test1.html"); 
            //从指定网站下载数据
            string pageHtml = Encoding.UTF8.GetString(pageData);  
            //如果获取网站页面采用的是GB2312，则使用这句       
            bool isBool = isMessyCode(pageHtml);//判断使用哪种编码 读取网页信息
            if (!isBool)
            {
                string pageHtml1 = Encoding.UTF8.GetString(pageData);
                pageHtml = pageHtml1;
            }
            else
            {
                string pageHtml2 = Encoding.Default.GetString(pageData);
                pageHtml = pageHtml2;
            }
            return pageHtml;
        }

        catch (WebException webEx)
        {
            Console.WriteLine(webEx.Message.ToString());
            return webEx.Message;
        }
    }


    /// <summary>
    /// 执行此Url，下载PDF档案
    /// </summary>
    /// <returns></returns>
    public ActionResult DownloadPdf()
    {
        WebClient wc = new WebClient();
        //从网址下载Html字串
        wc.Encoding = System.Text.Encoding.UTF8;
        string htmlText = getWebContent();
        byte[] pdfFile = this.ConvertHtmlTextToPDF(htmlText);

        return File(pdfFile, "application/pdf", "d:\\范例PDF档1.pdf");
    }
    /// <summary>
    /// 将Html文字 输出到PDF档里
    /// </summary>
    /// <param name="htmlText"></param>
    /// <returns></returns>
    public  byte[] ConvertHtmlTextToPDF(string htmlText)
    {
        if (string.IsNullOrEmpty(htmlText))
        {
            return null;
        }
        //避免当htmlText无任何html tag标签的纯文字时，转PDF时会挂掉，所以一律加上<p>标签
        htmlText = "<p>" + htmlText + "</p>";

        MemoryStream outputStream = new MemoryStream();//要把PDF写到哪个串流
        byte[] data = Encoding.UTF8.GetBytes(htmlText);//字串转成byte[]
        MemoryStream msInput = new MemoryStream(data);
        Document doc = new Document();//要写PDF的文件，建构子没填的话预设直式A4
        PdfWriter writer = PdfWriter.GetInstance(doc, outputStream);
        //指定文件预设开档时的缩放为100%

        PdfDestination pdfDest = new PdfDestination(PdfDestination.XYZ, 0, doc.PageSize.Height, 1f);
        //开启Document文件 
        doc.Open();

        //使用XMLWorkerHelper把Html parse到PDF档里
        XMLWorkerHelper.GetInstance().ParseXHtml(writer, doc, msInput, null, Encoding.UTF8, new UnicodeFontFactory());
        //将pdfDest设定的资料写到PDF档
        PdfAction action = PdfAction.GotoLocalPage(1, pdfDest, writer);
        writer.SetOpenAction(action);
        doc.Close();
        msInput.Close();
        outputStream.Close();
        //回传PDF档案 
        return outputStream.ToArray();

    }

    //设置字体类
    public class UnicodeFontFactory : FontFactoryImp
   {
      private static readonly string arialFontPath = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Fonts),
"arialuni.ttf");//arial unicode MS是完整的unicode字型。
      private static readonly string 标楷体Path = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.Fonts),
      "KAIU.TTF");//标楷体


    public override Font GetFont(string fontname, string encoding, bool embedded, float size, int style, BaseColor color, bool cached)
    {
         BaseFont bfChiness = BaseFont.CreateFont(@"C:\Windows\Fonts\simhei.ttf", BaseFont.IDENTITY_H, BaseFont.NOT_EMBEDDED);
        //可用Arial或标楷体，自己选一个
        BaseFont baseFont = BaseFont.CreateFont(标楷体Path, BaseFont.IDENTITY_H, BaseFont.EMBEDDED);
        return new Font(baseFont, size, style, color);
    }
}

---

---

---

另外一种方法就是先把html的界面生成图片 ，然后用生成的图片来生成pdf 结果：情况效果图(不理想，达不到需求)代码就不贴了，如果需要，请私信！

Answer 1

http://stackoverflow.com/questions/564650/convert-html-to-pdf-in-net

Answer 2

跪求代码，邮箱[e-mail]

Answer 3

跪求代码，邮箱[e-mail]

Answer 4

上面报错应该是html标签没闭合或者不规范吧

Answer 5

跪求"先把html的界面生成图片 ，然后用生成的图片来生成pdf 结果"的代码，邮箱410251819@qq .com