如何获得如新浪、网易等站点上的最新新闻? 我现在的公司想做一个资讯网,上面有大量新的信息,我试过获得RSS XML数据,但详细信息都会链接到了RSS原网站上。这样等于帮他们做了嫁衣。 解决方案 » 免费领取超大流量手机卡,每月29元包185G流量+100分钟通话, 中国电信官方发货 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; } }}然后用正则抓取 求菜单显示代码 文件重命名的问题 js 问题 远程上传图片错误观点,本地可以,肯请高手指点! 动态添加控件时添加事件,触发时无效 上传后的错误 怎么知道dataset里面的一个表是空的 这个SQL怎么写呀?????对我说,有点难度,大家来看看吧? 如何根据条件在DataGrid中显示图片? 下拉式导航条被dropdownlist挡住的问题 求助Repeat控件的一个问题 DBEntry 用orm的方式保存数据出错
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;
}
}
}
然后用正则抓取