HttpWebRequest获取网页源代码时自动识别网页编码，通过读取页面中的charset和读取http头中的编码信息获取页面的编码，基本可以正确获取网页编码
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>
/// 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;
}
本站仅提供存储服务，所有内容均由用户发布，如发现有害或侵权内容，请
点击举报。
