抓取网页数据

Question

链接如下：http://www.bjfdc.gov.cn/public/house/house.asp?src_id=2&type_id=1&id=3466743&building_id=356213&house_Id=7504287
该网站有2个特点：
1） 操作的快的没有响应了，弹出《为节约服务器资源， 请3秒钟后点击 刷新 重新浏览页面！》
2） 大部分数据都变成图片了。各位大侠，能否给个思路？

Answer 1

请用这个网址进入 http://www.bjfdc.gov.cn/public/Index.asp
点击下边的某个楼盘的信息。

Answer 2

http://www.bjfdc.gov.cn/public/house/house.asp?src_id=2&type_id=1&id=3466743&building_id=356213&house_Id=7504287&ran=随机数

Answer 3

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;
        }
    }
}