62,046
社区成员
发帖
与我相关
我的任务
分享
// 获取网页的HTML内容,指定Encoding
public 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
public 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;
}
}