日期:2014-05-18  浏览次数:20866 次

高分求一个 抓取网页数据软件
个抓取网页数据软件(网页源码中产品的图片 价格 描述 重量 等等信息)


------解决方案--------------------
去下载一个小偷程序看看,看完基本就知道怎么写了....
------解决方案--------------------
火车头采集器
------解决方案--------------------
获得html源码,正则分析源码并提取所需要的。
会写正则就好办了
------解决方案--------------------
顶,也顺便学习下!
------解决方案--------------------
网页抓取类:

using System;
using System.Collections.Generic;
using System.Linq;
using System.Web;
using System.Text;
using System.Net;
using System.IO;
using System.Text.RegularExpressions;
using System.Collections;
using System.IO.Compression;

public class webCrawl
{
public webCrawl() { }

//获取网页字符根据url
public static string getHtml(string url)
{
try
{
string str = "";
Encoding en = Encoding.GetEncoding(getEncoding(url));
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
request.Headers.Set("Pragma", "no-cache");
request.Timeout = 30000;
HttpWebResponse response = (HttpWebResponse)request.GetResponse();
if (response.StatusCode == HttpStatusCode.OK && response.ContentLength < 1024 * 1024)
{
Stream strM = response.GetResponseStream();
StreamReader sr = new StreamReader(strM, en);
str = sr.ReadToEnd();
strM.Close();
sr.Close();
}
return str;
}
catch
{
return String.Empty;
}
}

//获取编码
public static string getEncoding(string url)
{
HttpWebRequest request = null;
HttpWebResponse response = null;
StreamReader reader = null;
try
{
request = (HttpWebRequest)WebRequest.Create(url);
request.Timeout = 30000;
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 (Exception ex)
{
throw new Exception(ex.Message);
}
finally
{
if (response != null)
{
response.Close();
response = null;
}
if (reader != null)
reader.Close();