WebClient wc = new WebClient();
string content = wc.DownloadString("http://blog.sina.com.cn/s/blog_498eab7d0100et7j.html");
char[] chars = content.ToCharArray();
byte[] buffer = Encoding.GetEncoding("gb2312").GetBytes(chars);
content = Encoding.GetEncoding("gb2312").GetString(buffer);
Console.WriteLine(content);想要修改乱码问题 希望大手帮忙谢谢
string content = wc.DownloadString("http://blog.sina.com.cn/s/blog_498eab7d0100et7j.html");
char[] chars = content.ToCharArray();
byte[] buffer = Encoding.GetEncoding("gb2312").GetBytes(chars);
content = Encoding.GetEncoding("gb2312").GetString(buffer);
Console.WriteLine(content);想要修改乱码问题 希望大手帮忙谢谢
byte[] buffer = Encoding.GetEncoding("gb2312").GetBytes(content);
content = Encoding.UTF8.GetString(buffer);
wc.Encoding.EncodingName
其实是Gb2312,需要转成utf8,页面设置的utf8
原网页使用utf8,但是使用gzip压缩了。它在html中标记了是utf8,可惜webclient.downloadstring这个功能不认识html,只有靠你自己去解析了。