HttpWebRequest获取网页源代码时自动识别网页编码

       /// <summary>
        /// 获取源代码
        /// </summary>
        /// <param name="url"></param>
        /// <returns></returns>
        static string GetHtml(string url, Encoding encoding)
        {
            HttpWebRequest request = null;
            HttpWebResponse response = null;
            StreamReader reader = null;
            try
            {
                request = (HttpWebRequest)WebRequest.Create(url);
                request.Timeout = 20000;
                request.AllowAutoRedirect = false;

                response = (HttpWebResponse)request.GetResponse();
                if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
                {
                    if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
                        reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress), encoding);
                    else
                        reader = new StreamReader(response.GetResponseStream(), encoding);
                    string html = reader.ReadToEnd();

                    return html;
                }
            }
            catch
            {
            }
            finally
            {

                if (response != null)
                {
                    response.Close();
                    response = null;
                }
                if (reader != null)
                    reader.Close();

                if (request != null)
                    request = null;

            }

            return string.Empty;
        }

// 根据URL提取页面的Title，根据网页的charset自动判断Encoding

using System;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;

class Program
{
  // 获取网页的HTML内容，根据网页的charset自动判断Encoding
  static string GetHtml(string url)
  {
    return GetHtml(url, null);
  }

  // 获取网页的HTML内容，指定Encoding
  static string GetHtml(string url, Encoding encoding)
  {
    byte[] buf = new WebClient().DownloadData(url);
    if (encoding != null) return encoding.GetString(buf);
    string html = Encoding.UTF8.GetString(buf);
    encoding = GetEncoding(html);
    if (encoding == null || encoding == Encoding.UTF8) return html;
    return encoding.GetString(buf);
  }

  // 根据网页的HTML内容提取网页的Encoding
  static Encoding GetEncoding(string html)
  {
    string pattern = @"(?i)\bcharset=(?<charset>[-a-zA-Z_0-9]+)";
    string charset = Regex.Match(html, pattern).Groups["charset"].Value;
    try { return Encoding.GetEncoding(charset); }
    catch (ArgumentException) { return null; }
  }

  // 根据网页的HTML内容提取网页的Title
  static string GetTitle(string html)
  {
    string pattern = @"(?si)<title(?:\s+(?:""[^""]*""|'[^']*'|[^""'>])*)?>(?<title>.*?)</title>";
    return Regex.Match(html, pattern).Groups["title"].Value.Trim();
  }

  // 打印网页的Encoding和Title
  static void PrintEncodingAndTitle(string url)
  {
    string html = GetHtml(url);
    Console.WriteLine("[{0}] [{1}]", GetEncoding(html), GetTitle(html));
  }

  // 程序入口
  static void Main()
  {
    PrintEncodingAndTitle("http://www.msdn.net/");
    PrintEncodingAndTitle("http://www.cnblogs.com/");
    PrintEncodingAndTitle("http://www.cnblogs.com/skyiv/");
    PrintEncodingAndTitle("http://www.csdn.net/");
    PrintEncodingAndTitle("http://news.163.com/");
  }
}

/**//* 程序输出：
[] [MSDN: Microsoft Developer Network]
[System.Text.UTF8Encoding] [博客园 - 程序员的网上家园]
[System.Text.UTF8Encoding] [空间/IV - 博客园]
[System.Text.UTF8Encoding] [CSDN.NET - 中国最大的IT技术社区，为IT专业技术人员提供最全面的信息传播和服务平台]
[System.Text.DBCSCodePageEncoding] [新闻中心_网易新闻]
*/
// 试了一下 google 的网页

using System;
using System.Net;
using System.Text;
using System.Text.RegularExpressions;

class Program
{
  // 获取网页的HTML内容，根据网页的charset自动判断Encoding
  static string GetHtml(string url)
  {
    return GetHtml(url, null);
  }

  // 获取网页的HTML内容，指定Encoding
  static string GetHtml(string url, Encoding encoding)
  {
    byte[] buf = new WebClient().DownloadData(url);
    if (encoding != null) return encoding.GetString(buf);
    string html = Encoding.UTF8.GetString(buf);
    encoding = GetEncoding(html);
    if (encoding == null || encoding == Encoding.UTF8) return html;
    return encoding.GetString(buf);
  }

  // 根据网页的HTML内容提取网页的Encoding
  static Encoding GetEncoding(string html)
  {
    string pattern = @"(?i)\bcharset=(?<charset>[-a-zA-Z_0-9]+)";
    string charset = Regex.Match(html, pattern).Groups["charset"].Value;
    try { return Encoding.GetEncoding(charset); }
    catch (ArgumentException) { return null; }
  }

  // 程序入口
  static void Main()
  {
    Console.WriteLine(GetHtml("http://www.google.com"));
  }
}

文章来自: 本站原创
引用通告: 查看所有引用 | 我要引用此文章
Tags:
相关日志: