Html Agility Pack

来自软件开发
跳转至: 导航搜索


判断编码的完整过程

/// <summary>
        /// 函数名称:GetDataFromUrl
        /// 功能说明:获取url指定的网页的源码
        /// 参数:string url用于指定 url
        /// 参数:ref Encoding encode用来获取网页中的字符集编码
        /// </summary>
        public static string GetDataFromUrl(string url, ref Encoding encode)
        {
            string str = string.Empty;
            HttpWebRequest request = (HttpWebRequest)HttpWebRequest.Create(url);

            //设置http头
            request.AllowAutoRedirect = true;
            request.AllowWriteStreamBuffering = true;
            request.Referer = "";
            request.Timeout = 10 * 1000;
            request.UserAgent = "";
            HttpWebResponse response = null;
            response = (HttpWebResponse)request.GetResponse();

            //根据http应答的http头来判断编码
            string characterSet = response.CharacterSet;
            //Encoding encode;
            if (characterSet != "")
            {
                if (characterSet == "ISO-8859-1")
                {
                    characterSet = "gb2312";
                }
                encode = Encoding.GetEncoding(characterSet);
            }
            else
            {
                encode = Encoding.Default;
            }

            //声明一个内存流来保存http应答流
            Stream receiveStream = response.GetResponseStream();
            MemoryStream mStream = new MemoryStream();

            byte[] bf = new byte[255];
            int count = receiveStream.Read(bf, 0, 255);
            while (count > 0)
            {
                mStream.Write(bf, 0, count);
                count = receiveStream.Read(bf, 0, 255);
            }
            receiveStream.Close();

            mStream.Seek(0, SeekOrigin.Begin);

            //从内存流里读取字符串
            StreamReader reader = new StreamReader(mStream, encode);
            char[] buffer = new char[1024];
            count = reader.Read(buffer, 0, 1024);
            while (count > 0)
            {
                str += new String(buffer, 0, count);
                count = reader.Read(buffer, 0, 1024);
            }

            //从解析出的字符串里判断charset,如果和http应答的编码不一直
            //那么以页面声明的为准,再次从内存流里重新读取文本
            Regex reg =
               new Regex(@"<meta[\s\S]+?charset=(.*?)""[\s\S]+?>",
                          RegexOptions.Multiline | RegexOptions.IgnoreCase);
            MatchCollection mc = reg.Matches(str);
            if (mc.Count > 0)
            {
                string tempCharSet = mc[0].Result("$1");
                if (string.Compare(tempCharSet, characterSet, true) != 0)
                {
                    encode = Encoding.GetEncoding(tempCharSet);
                    str = string.Empty;
                    mStream.Seek(0, SeekOrigin.Begin);
                    reader = new StreamReader(mStream, encode);
                    buffer = new char[255];
                    count = reader.Read(buffer, 0, 255);
                    while (count > 0)
                    {
                        str += new String(buffer, 0, count);
                        count = reader.Read(buffer, 0, 255);
                    }
                }
            }
            reader.Close();
            mStream.Close();
            if (response != null)
                response.Close();

            return str;

        }

参考资料