c# – 从互联网下载HTML后,字符串中的字符已更改

概述使用以下代码,我可以从互联网下载文件的 HTML： WebClient wc = new WebClient();// ....string downloadedFile = wc.DownloadString("http://www.myurl.com/"); 但是,有时该文件包含“有趣”的字符,如é至é,←到â†和フシギダネ到フã,·ã,®ãƒ€ãƒ. 我认为这可能与不同的uni 使用以下代码,我可以从互联网下载文件的 HTML：

WebClIEnt wc = new WebClIEnt();// ....string downloadedfile = wc.DownloadString("http://www.myurl.com/");

但是,有时该文件包含“有趣”的字符,如é至é,←到â†和フシギダネ到フã,·ã,®ãƒ€ãƒ.

我认为这可能与不同的unicode类型或某些东西有关,因为每个角色都会变成2个新角色,也许每一个角色分为两部分,但我在这方面的知识很少.你觉得是错的？

解决方法 这是一个包装的下载类,它支持gzip并检查编码头和元标记,以正确解码它.

实例化类,并调用GetPage().

public class httpDownloader{    private Readonly string _referer;    private Readonly string _userAgent;    public EnCoding EnCoding { get; set; }    public WebheaderCollection headers { get; set; }    public Uri Url { get; set; }    public httpDownloader(string url,string referer,string userAgent)    {        EnCoding = EnCoding.GetEnCoding("ISO-8859-1");        Url = new Uri(url); // verify the uri        _userAgent = userAgent;        _referer = referer;    }    public string GetPage()    {        httpWebRequest request = (httpWebRequest)WebRequest.Create(Url);        if (!string.IsNullOrEmpty(_referer))            request.Referer = _referer;        if (!string.IsNullOrEmpty(_userAgent))            request.UserAgent = _userAgent;        request.headers.Add(httpRequestheader.AcceptEnCoding,"gzip,deflate");        using (httpWebResponse response = (httpWebResponse)request.GetResponse())        {            headers = response.headers;            Url = response.ResponseUri;            return ProcessContent(response);        }    }    private string ProcessContent(httpWebResponse response)    {        SetEnCodingFromheader(response);        Stream s = response.GetResponseStream();        if (response.ContentEnCoding.Tolower().Contains("gzip"))            s = new GZipStream(s,CompressionMode.Decompress);        else if (response.ContentEnCoding.Tolower().Contains("deflate"))            s = new DeflateStream(s,CompressionMode.Decompress);          MemoryStream memStream = new MemoryStream();        int bytesRead;        byte[] buffer = new byte[0x1000];        for (bytesRead = s.Read(buffer,buffer.Length); bytesRead > 0; bytesRead = s.Read(buffer,buffer.Length))        {            memStream.Write(buffer,bytesRead);        }        s.Close();        string HTML;        memStream.position = 0;        using (StreamReader r = new StreamReader(memStream,EnCoding))        {            HTML = r.ReadToEnd().Trim();            HTML = CheckMetaCharSetAndReEncode(memStream,HTML);        }                    return HTML;    }    private voID SetEnCodingFromheader(httpWebResponse response)    {        string charset = null;        if (string.IsNullOrEmpty(response.CharacterSet))        {            Match m = Regex.Match(response.ContentType,@";\s*charset\s*=\s*(?<charset>.*)",RegexOptions.IgnoreCase);            if (m.Success)            {                charset = m.Groups["charset"].Value.Trim(new[] { '\'','"' });            }        }        else        {            charset = response.CharacterSet;        }        if (!string.IsNullOrEmpty(charset))        {            try            {                EnCoding = EnCoding.GetEnCoding(charset);            }            catch (ArgumentException)            {            }        }    }    private string CheckMetaCharSetAndReEncode(Stream memStream,string HTML)    {        Match m = new Regex(@"<Meta\s+.*?charset\s*=\s*(?<charset>[A-Za-z0-9_-]+)",RegexOptions.Singleline | RegexOptions.IgnoreCase).Match(HTML);        if (m.Success)        {            string charset = m.Groups["charset"].Value.Tolower() ?? "iso-8859-1";            if ((charset == "unicode") || (charset == "utf-16"))            {                charset = "utf-8";            }            try            {                EnCoding MetaEnCoding = EnCoding.GetEnCoding(charset);                if (EnCoding != MetaEnCoding)                {                    memStream.position = 0L;                    StreamReader recodeReader = new StreamReader(memStream,MetaEnCoding);                    HTML = recodeReader.ReadToEnd().Trim();                    recodeReader.Close();                }            }            catch (ArgumentException)            {            }        }        return HTML;    }}

总结

以上是内存溢出为你收集整理的c# – 从互联网下载HTML后,字符串中的字符已更改全部内容，希望文章能够帮你解决c# – 从互联网下载HTML后,字符串中的字符已更改所遇到的程序开发问题。

如果觉得内存溢出网站内容还不错，欢迎将内存溢出网站推荐给程序员好友。