抓取html 写正则

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;
        }
    }
}

抓取后

 

 

Regex regex = new Regex("<a.*?href=\"(?<href>.*?)\".*?title=\"(?<title>.*?)\".*?>", RegexOptions.Compiled);

可以取到href和title

 

Regex reg = new Regex(@"(?is)<img[^>]*?scr=(['""\s]?)([^'""\s]+)\1[^>]*?>");
抓取图片src

 

 

 

Regex regexObj = new Regex("<li class=\"vImg\"><img.*?src=\"(?<src>.+?)\".*?></li>.*?<li class=\"vStatus\">.*?<a.*?href=\"(?<href>.+?)\".*?>(?<title>.*?)</a></li>", RegexOptions.Singleline);


可以获取图片src,title,href,其它信息可以类推，一次截取出来