HTML網頁保存為PDF文件

開發中遇到的問題，需要把網站的頁面保存為PDF文件

所以自己研究，總結如下：

 

 

一、Pechkin:html->pdf

1.WinForm中轉換為PDF

　　a.在項目添加引用，引用 -> 管理NuGet程序包

 

b.在導出PDF按鈕中添加方法

SynchronizedPechkin sc = new SynchronizedPechkin(new GlobalConfig()
                .SetMargins(new Margins() { Left = 10, Right = 10, Top = 0, Bottom = 0 }) //設置邊距
                .SetPaperOrientation(false) //設置紙張方向為橫向
                .SetPaperSize(ConvertToHundredthsInch(210), ConvertToHundredthsInch(297))); //設置紙張為A4紙大小

            byte[] buf = sc.Convert(new ObjectConfig(), getWebContent());

            if (buf == null)
            {
                MessageBox.Show("Error converting!");
                return;
            }

            File.WriteAllBytes(@"d:\google-news123.pdf", buf);

            try
            {
                string fn = Path.GetTempFileName() + ".pdf";
                FileStream fs = new FileStream(fn, FileMode.Create);
                fs.Write(buf, 0, buf.Length);
                fs.Close();

                //MessageBox.Show("操作成功，文件已保存至F盤下", "提示");

                Process myProcess = new Process();
                myProcess.StartInfo.FileName = fn;
                myProcess.Start();

                //SaveFileDialog();
            }
            catch { }

 相關方法

private int ConvertToHundredthsInch(int millimeter)
        {
            return (int)((millimeter * 10.0) / 2.54);
        }

        /// <summary>
        /// 獲取網站內容，包含了 HTML+CSS+JS
        /// </summary>
        /// <returns>String返回網頁信息</returns>
        public string getWebContent()
        {
            try
            {
                WebClient MyWebClient = new WebClient();
                MyWebClient.Credentials = CredentialCache.DefaultCredentials;
                //獲取或設置用於向Internet資源的請求進行身份驗證的網絡憑據
                Byte[] pageData = MyWebClient.DownloadData("http://a4.keyue.com.cn/out/fwd/2fenhd/yuludan_new.asp?nstr=jwmlYCBYPDcHJlX2VudHJ5X2lkPTIyMjkyMDE1MDc5MTk1MjcyOSZ0b2lwPTExNA==");
                //從指定網站下載數據
                string pageHtml = Encoding.UTF8.GetString(pageData);
                //如果獲取網站頁面采用的是GB2312，則使用這句       
                bool isBool = isMessyCode(pageHtml);//判斷使用哪種編碼 讀取網頁信息
                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>
        /// 判斷是否有亂碼
        /// </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;
        }

優缺點

　　1.只能保存到制定的目錄中，並且直接打開文件

　　2.網頁中的圖片導不出來

　　3.可能會出現亂碼

　　4.生成項目的時候需要把相應的DLL拷貝進去，不然不能生成

 

這是另外一種方法：http://www.cnblogs.com/lsgsanxiao/p/4878077.html

 

 

 

2.WEB網站中轉換為PDF

　　項目Demo http://pan.baidu.com/s/1gfhRR8n

　　a.項目相關引用與上面相同

　　b.網站中采用JS調用一般處理程序的方式

function createPdf() {
            window.open("CreatePdf.ashx?html=222222222222233324243");
        }

using System;
using System.Drawing.Printing;
using System.IO;
using System.Net;
using System.Text;
using System.Web;
using Pechkin;
using Pechkin.Synchronized;

namespace WebApplication3
{
    /// <summary>
    /// CreatePdf 的摘要說明
    /// </summary>
    public class CreatePdf : IHttpHandler
    {

        public void ProcessRequest(HttpContext context)
        {
            string htmlFile = context.Request["html"];

            string html = getWebContent();
            SynchronizedPechkin sc = new SynchronizedPechkin(new GlobalConfig()
                                    .SetMargins(new Margins() { Left = 0, Right = 0, Top = 0, Bottom = 0 }) //設置邊距
                                    .SetPaperOrientation(false) //設置紙張方向為橫向
                                    .SetPaperSize(ConvertToHundredthsInch(210), ConvertToHundredthsInch(297))); //設置紙張大小50mm * 100mm

            byte[] buf = sc.Convert(new ObjectConfig(), html);

            if (buf == null)
            {
                context.Response.ContentType = "text/plain";
                context.Response.Write("Error converting!");
            }

            try
            {
                context.Response.Clear();


                //方式1：提示瀏覽器下載pdf   
                context.Response.AddHeader("content-disposition", "attachment;filename=" + htmlFile + ".pdf");
                context.Response.ContentType = "application/octet-stream";
                context.Response.BinaryWrite(buf);

                //方式2：直接在瀏覽器打開pdf
                //context.Response.ContentType = "application/pdf";
                //context.Response.OutputStream.Write(buf, 0, buf.Length);

                context.Response.End();

            }
            catch (Exception e)
            {
                context.Response.ContentType = "text/plain";
                context.Response.Write(e.Message);
            }
        }

        public bool IsReusable
        {
            get
            {
                return false;
            }
        }

        private int ConvertToHundredthsInch(int millimeter)
        {
            return (int)((millimeter * 10.0) / 2.54);
        }

        /// <summary>
        /// 獲取網站內容，包含了 HTML+CSS+JS
        /// </summary>
        /// <returns>String返回網頁信息</returns>
        public string getWebContent()
        {
            try
            {
                WebClient MyWebClient = new WebClient();
                MyWebClient.Credentials = CredentialCache.DefaultCredentials;
                //獲取或設置用於向Internet資源的請求進行身份驗證的網絡憑據
                Byte[] pageData = MyWebClient.DownloadData("http://a4.keyue.com.cn/out/fwd/2fenhd/yuludan.asp?nstr=AAfFJb_SVvcHJlX2VudHJ5X2lkPTIyMzEyMDE1MDgxMTY0NDUzOSZ0b2lwPTExNA==");
                //從指定網站下載數據
                string pageHtml = Encoding.UTF8.GetString(pageData);
                //如果獲取網站頁面采用的是GB2312，則使用這句       
                bool isBool = isMessyCode(pageHtml);//判斷使用哪種編碼 讀取網頁信息
                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>
        /// 判斷是否有亂碼
        /// </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;
        }
    }
}