HttpWebRequest获取网页html源代码（并自动获取encoding）

能识别压缩的文件GZIP压缩

以下内容转载之/article/5653806.html

HttpWebRequest获取网页html源代码（并自动获取encoding）

?
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Net;
using System.IO;
using System.IO.Compression;
using System.Text.RegularExpressions;

namespace WikiPageCreater.Common
{
public class PageHelper
{
/// <summary>
/// 根据 url 获取网页编码
/// </summary>
/// <param name="url"></param>
/// <returns></returns>
public static string GetEncoding(string url)
{
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));
else
reader = new StreamReader(response.GetResponseStream(), Encoding.ASCII);

string html = reader.ReadToEnd();

Regex reg_charset = new Regex(@"charset\b\s*=\s*(?<charset>[^""]*)");
if (reg_charset.IsMatch(html))
{
return reg_charset.Match(html).Groups["charset"].Value;
}
else if (response.CharacterSet != string.Empty)
{
return response.CharacterSet;
}
else
return Encoding.Default.BodyName;
}
}
catch
{
}
finally
{

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

if (request != null)
request = null;

}

return Encoding.Default.BodyName;
}

/// <summary>
/// 根据 url 和 encoding 获取当前url页面的 html 源代码
/// </summary>
/// <param name="url"></param>
/// <param name="encoding"></param>
/// <returns></returns>
public 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;
}
}
}

==============================================================
更多示例代码，可以访问微软Codeplex网站: http://1code.codeplex.com ,下载微软的 All-In-One Code Framework.

在获取html编码时，可以一次只读取部分字节。若得到了编码就返回，不需要进行全部读取完毕。如采集谷歌的程序，是不需要加Gzip这种解码头部。最好使用user-agent代理去模防采取。