日期:2014-05-17 浏览次数:21326 次
private static string getHtml(string url, string charSet)//url是要访问的网站地址,charSet是目标网页的编码,如果传入的是null或者"",那就自动分析网页的编码 { charSet = "gb2312"; WebClient myWebClient = new WebClient(); //创建WebClient实例myWebClient // 需要注意的: //有的网页可能下不下来,有种种原因比如需要cookie,编码问题等等 //这是就要具体问题具体分析比如在头部加入cookie // webclient.Headers.Add("Cookie", cookie); //这样可能需要一些重载方法。根据需要写就可以了 //获取或设置用于对向 Internet 资源的请求进行身份验证的网络凭据。 myWebClient.Credentials = CredentialCache.DefaultCredentials; //如果服务器要验证用户名,密码 //NetworkCredential mycred = new NetworkCredential(struser, strpassword); //myWebClient.Credentials = mycred; //从资源下载数据并返回字节数组。(加@是因为网址中间有"/"符号) byte[] myDataBuffer = myWebClient.DownloadData(url); string strWebData = Encoding.GetEncoding("GB2312").GetString(myDataBuffer); //StreamWriter sw = new StreamWriter("D:/qq-utf-8.txt"); //sw.Write(strWebData); //sw.Close(); //获取网页字符编码描述信息 Match charSetMatch = Regex.Match(strWebData, "<meta([^<]*)charset=([^<]*)\"", RegexOptions.IgnoreCase | RegexOptions.Multiline); string webCharSet = charSetMatch.Value; int start = webCharSet.IndexOf("charset="); //if (start == -1) //{ // charSet = "utf-8"; // strWebData = Encoding.GetEncoding(charSet).GetString(myDataBuffer); // charSetMatch = Regex.Match(strWebData, "<meta([^<]*)charset=([^<]*)\"", RegexOptions.IgnoreCase | RegexOptions.Multiline); // webCharSet = charSetMatch.Value; // start = webCharSet.IndexOf("charset="); //} int end = webCharSet.IndexOf("\"", start); webCharSet=webCharSet.Substring(start+8,end-(start+8)); if(webCharSet!=charSet) strWebData = Encoding.GetEncoding(webCharSet).GetString(myDataBuffer); //if (charSet == null || charSet == "") // charSet = webCharSet; //if (charSet != null && charSet != "" && Encoding.GetEncoding(charSet) != Encoding.GetEncoding("utf-8")) // strWebData = Encoding.GetEncoding(charSet).GetString(myDataBuffer); return strWebData; }