求C# 网页源代码获取以及html转xml然后提取其中纯文本信息的完整代码

Question

本帖最后由 Erric77 于 2010-04-22 15:24:54 编辑

Answer 1

html本身就是xml格式。如果你是要获取文本信息，正则替换所有的< /> <> 这种内容。

Answer 2

如果不用登陆的话可以直接这样       System.Net.HttpWebRequest hwr = (System.Net.HttpWebRequest)System.Net.WebRequest.Create("请求页面");
            System.IO.StreamReader sr = new System.IO.StreamReader(hwr.GetResponse().GetResponseStream(), Encoding.Default);
string str =  sr.ReadToEnd();#region 过滤掉 html代码
        public static string StripHTML(string strHtml)
        {
            string[] aryReg ={ 
                        @"<script[^>]*?>.*?</script>",                         @"<(\/\s*)?!?((\w+:)?\w+)(\w+(\s*=?\s*(([""'])(\\[""'tbnr]|[^\7])*?\7|\w+)|.{0})|\s)*?(\/\s*)?>", 
                        @"([\r\n])[\s]+", 
                        @"&(quot|#34);", 
                        @"&(amp|#38);", 
                        @"&(lt|#60);", 
                        @"&(gt|#62);", 
                        @"&(nbsp|#160);", 
                        @"&(iexcl|#161);", 
                        @"&(cent|#162);", 
                        @"&(pound|#163);", 
                        @"&(copy|#169);", 
                        @"&#(\d+);", 
                        @"-->", 
                        @"<!--.*\n" 
                        };                                    string[] aryRep = { 
                        "", 
                        "", 
                        "", 
                        "\"", 
                        "&", 
                        "<", 
                        ">", 
                        " ", 
                        "\xa1",//chr(161), 
                        "\xa2",//chr(162), 
                        "\xa3",//chr(163), 
                        "\xa9",//chr(169), 
                        "", 
                        "\r\n", 
                        "" 
                        };            string newReg = aryReg[0];
            string strOutput = strHtml;
            for (int i = 0; i < aryReg.Length; i++)
            {
                System.Text.RegularExpressions.Regex regex = new System.Text.RegularExpressions.Regex(aryReg[i], System.Text.RegularExpressions.RegexOptions.IgnoreCase);
                strOutput = regex.Replace(strOutput, aryRep[i]);
            }
            strOutput.Replace("<", "");
            strOutput.Replace(">", "");
            strOutput.Replace("\r\n", "");
            return strOutput;
        }
        #endregion这样就成了纯文本信息