求C# 怎么从html中获取想要的数据

Question

如题
如题
谢谢

Answer 1

先抓取内容 然后用正则来取。。抓取网页
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Net;
using System.IO;
using System.IO.Compression;
using System.Text.RegularExpressions;namespace WikiPageCreater.Common
{
    public class PageHelper
    {
        /// <summary>
        /// 根据 url 获取网页编码
        /// </summary>
        /// <param name="url"></param>
        /// <returns></returns>
        public static string GetEncoding(string url)
        {
            HttpWebRequest request = null;
            HttpWebResponse response = null;
            StreamReader reader = null;
            try
            {
                request = (HttpWebRequest)WebRequest.Create(url);
                request.Timeout = 20000;
                request.AllowAutoRedirect = false;                response = (HttpWebResponse)request.GetResponse();
                if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
                {
                    if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
                        reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress));
                    else
                        reader = new StreamReader(response.GetResponseStream(), Encoding.ASCII);                    string html = reader.ReadToEnd();                    Regex reg_charset = new Regex(@"charset\b\s*=\s*(?<charset>[^""]*)");
                    if (reg_charset.IsMatch(html))
                    {
                        return reg_charset.Match(html).Groups["charset"].Value;
                    }
                    else if (response.CharacterSet != string.Empty)
                    {
                        return response.CharacterSet;
                    }
                    else
                        return Encoding.Default.BodyName;
                }
            }
            catch
            {
            }
            finally
            {                if (response != null)
                {
                    response.Close();
                    response = null;
                }
                if (reader != null)
                    reader.Close();                if (request != null)
                    request = null;            }            return Encoding.Default.BodyName;
        }        /// <summary>
        /// 根据 url 和 encoding 获取当前url页面的 html 源代码        
       /// </summary>
        /// <param name="url"></param>
        /// <param name="encoding"></param>
        /// <returns></returns>
        public static string GetHtml(string url, Encoding encoding)
        {
            HttpWebRequest request = null;
            HttpWebResponse response = null;
            StreamReader reader = null;
            try
            {
                request = (HttpWebRequest)WebRequest.Create(url);
                request.Timeout = 20000;
                request.AllowAutoRedirect = false;                response = (HttpWebResponse)request.GetResponse();
                if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
                {
                    if (response.ContentEncoding != null && response.ContentEncoding.Equals("gzip", StringComparison.InvariantCultureIgnoreCase))
                        reader = new StreamReader(new GZipStream(response.GetResponseStream(), CompressionMode.Decompress), encoding);
                    else
                        reader = new StreamReader(response.GetResponseStream(), encoding);
                    string html = reader.ReadToEnd();                    return html;
                }
            }
            catch
            {
            }
            finally
            {                if (response != null)
                {
                    response.Close();
                    response = null;
                }
                if (reader != null)
                    reader.Close();                if (request != null)
                    request = null;            }            return string.Empty;
        }
    }
}

Answer 2

        /// <summary>
        /// 从地址栏获取值
        /// </summary>
        /// <param name="page">页面</param>
        /// <param name="para">参数</param>
        /// <returns></returns>
        public static string GetQueryString(string para)
        {
            string queryString = "";
            if (System.Web.HttpContext.Current.Request.QueryString[para] != null)
            {
                queryString = System.Web.HttpContext.Current.Request.QueryString[para].ToString();
            }
            else
            {
                queryString = "";
            }
            return StringHelper.InputTexts(queryString.Trim());
        }        /// <summary>
        /// 从地址栏获取相关int值
        /// </summary>
        /// <param name="page">页面</param>
        /// <param name="para">参数</param>
        /// <returns></returns>
        public static int GetQueryInt(string para)
        {
            int queryInt = -1;
            string tempQueryString = GetQueryString(para);
            if (ValidateHelper.IsNumber(tempQueryString))
            {
                queryInt = int.Parse(tempQueryString);
            }
            return queryInt;
        }
        /// <summary>
        /// 清除所有脚本
        /// </summary>
        /// <param name="text"></param>
        /// <returns></returns>
        public static string InputTexts(string text)
        {
            if (string.IsNullOrEmpty(text))
                return string.Empty;
            text = Regex.Replace(text, "[\\s]{2,}", " "); //two or more spaces
            text = Regex.Replace(text, "(<[b|B][r|R]/*>)+|(<[p|P](.|\\n)*?>)", "\n"); //<br>
            text = Regex.Replace(text, "(\\s*&[n|N][b|B][s|S][p|P];\\s*)+", " "); //&nbsp;
            text = Regex.Replace(text, "<(.|\\n)*?>", string.Empty); //any other tags
            text = text.Replace("'", "''");
            return text;
        }
        /// <summary>
        /// 是否数字字符串
        /// </summary>
        /// <param name="inputData">输入字符串</param>
        /// <returns></returns>
        public static bool IsNumber(string inputData)
        {
            if (!string.IsNullOrEmpty(inputData))
            {
                Match m = RegNumber.Match(inputData);
                return m.Success;
            }
            else
            {
                return false;
            }
        }
        private static Regex RegNumber = new Regex("^[0-9]+$");

Answer 3

可以通过GET传值的方式把html中需要在后台使用的元素通过参数的方式传给处理页面
在处理页面后台可以后去参数Request.QueryString["参数"]的方式获取