怎么识别网页编码,能够正确独处网页内容,如下是我的写法,读取有的网页有时会有编码问题,出现乱码 System.Net.WebRequest myRequest = System.Net.WebRequest.Create(Url);
System.Net.WebResponse myResponse = myRequest.GetResponse();
Stream searchStream = myResponse.GetResponseStream();
Encoding encoding = Encoding.UTF8;
string ContentType = encoding.EncodingName;
if (ContentType.IndexOf("utf-8") != -1)
encoding = Encoding.UTF8;
else if (ContentType.IndexOf("utf-7") != -1)
encoding = Encoding.UTF7;
else if (ContentType.IndexOf("unicode") != -1)
encoding = Encoding.Unicode;
StreamReader sreader = new StreamReader(searchStream, encoding);求解
System.Net.WebResponse myResponse = myRequest.GetResponse();
Stream searchStream = myResponse.GetResponseStream();
Encoding encoding = Encoding.UTF8;
string ContentType = encoding.EncodingName;
if (ContentType.IndexOf("utf-8") != -1)
encoding = Encoding.UTF8;
else if (ContentType.IndexOf("utf-7") != -1)
encoding = Encoding.UTF7;
else if (ContentType.IndexOf("unicode") != -1)
encoding = Encoding.Unicode;
StreamReader sreader = new StreamReader(searchStream, encoding);求解
http://wenbloger.blogspot.com/2009/04/c_5580.html希望回答前最好测试下,我在网上找了一些,但都有BUG
根据URL提取页面的Title,根据网页的charset自动判断Encodingusing 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]
*/
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);
}
和我说的这篇文章类似http://wenbloger.blogspot.com/2009/04/c_5580.html
我试了,在获取一些小站网页时到byte[] buf = new WebClient().DownloadData(url);就不走了,他自己不会超时,一直等待中时间很长