一个小需求,获取远程页面的源码,主要用于抓数据。原来用的好好的。最近突然不能获取页面源码了,但是仍然可以用浏览器正常浏览。
一个小需求,获取远程页面的源码,主要用于抓数据。原来用的好好的,最近突然不能获取页面源码了,但是仍然可以用浏览器正常浏览。(文后附源码下载。^_^)
经过分析,原来用的代码如下:
Code
StreamReader sreader = null;
string result = string.Empty;
try
{
HttpWebRequest httpWebRequest = (HttpWebRequest)WebRequest.Create(Url);
//httpWebRequest.Timeout = 20;
httpWebRequest.KeepAlive = false;
#endregion
HttpWebResponse httpWebResponse = (HttpWebResponse)httpWebRequest.GetResponse();
if (httpWebResponse.StatusCode == HttpStatusCode.OK)
{
sreader = new StreamReader(httpWebResponse.GetResponseStream(), encoding);
result = reader.ReadToEnd();
if (null != httpWebResponse) { httpWebResponse.Close(); }
return result;
}
return result; ;
}
catch (WebException e) { return null; }
finally { if (sreader != null) { sreader.Close(); } }
查了下资料,原来需要加参数。
#region 关键参数,否则会取不到内容 Important Parameters,else get nothing.
httpWebRequest.UserAgent = "User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705;)";
httpWebRequest.Accept = "*/*";
httpWebRequest.KeepAlive = true;
httpWebRequest.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5");
#endregion
修正后的代码如下:
Code
读取页面详细信息#region 读取页面详细信息
/**//// <summary> /// 读取页面详细信息
/// </summary>
///<param name="Url">需要读取的地址</param>
/// <param name="encoding">读取的编码方式</param>
/// <returns></returns>
public static string GetStringByUrl(string Url, System.Text.Encoding encoding)
{
if (Url.Equals("about:blank")) return null; ;
if (!Url.StartsWith("http://") && !Url.StartsWith("https://")) { Url = "http://" + Url; }
int dialCount = 0;
loop:
StreamReader sreader = null;
string result = string.Empty;
try
{
HttpWebRequest httpWebRequest = (HttpWebRequest)WebRequest.Create(Url);
//httpWebRequest.Timeout = 20;
关键参数,否则会取不到内容 Important Parameters,else get nothing.#region 关键参数,否则会取不到内容 Important Parameters,else get nothing.
httpWebRequest.UserAgent = "User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2; .NET CLR 1.0.3705;)";
httpWebRequest.Accept = "*/*";
httpWebRequest.KeepAlive = true;
httpWebRequest.Headers.Add("Accept-Language", "zh-cn,en-us;q=0.5");
#endregion
HttpWebResponse httpWebResponse = (HttpWebResponse)httpWebRequest.GetResponse();
if (httpWebResponse.StatusCode == HttpStatusCode.OK)
{
sreader = new StreamReader(httpWebResponse.GetResponseStream(), encoding);
char[] cCont = new char[256];
int count = sreader.Read(cCont, 0, 256);
while (count > 0)
{ // Dumps the 256 characters on a string and displays the string to the console.
String str = new String(cCont, 0, count);
result += str;
count = sreader.Read(cCont, 0, 256);
}
}
if (null != httpWebResponse) { httpWebResponse.Close(); }
return result;
}
catch (WebException e)
{
if (e.Status == WebExceptionStatus.ConnectFailure) { dialCount++; ReDial(); }
if (dialCount < 5) { goto loop; }
return null;
}
finally { if (sreader != null) { sreader.Close(); } }
}
#endregion
public static void ReDial()
{
int res = 1;
/**/////while (res != 0)
////{
//// CSDNWebTest.RASDisplay ras = new RASDisplay();
//// ras.Disconnect();
//// res = ras.Connect("asdl");
//// System.Threading.Thread.Sleep(TimeSpan.FromSeconds(10));
////}
}
问题是解决了,后来再想了想,可以用WebClient先把页面download到本地临时文件,再读取文本内容。
代码如下:
Code
private string GetPageByWebClient(string url)
{
string result = null;
if (url.Equals("about:blank")) return null; ;
if (!url.StartsWith("http://") && !url.StartsWith("https://")) { url = "http://" + url; }
string filename = RandomKey(1111, 9999) + ".txt";
DownloadOneFileByURLWithWebClient(filename, url, "C:\\");
StreamReader sr = new StreamReader("c:\\" + filename, System.Text.Encoding.Default);
try { result = sr.ReadToEnd(); return result; }
catch { return null; }
finally
{
if (sr != null) { sr.Close(); }
}
}
private string RandomKey(int b, int e)
{
return DateTime.Now.ToString("yyyyMMdd-HHmmss-fff-") + this.getRandomID(b, e);
}
private int getRandomID(int minValue, int maxValue)
{
Random ri = new Random(unchecked((int)DateTime.Now.Ticks));
int k = ri.Next(minValue, maxValue);
return k;
}
private string GuidString
{
get { return Guid.NewGuid().ToString(); }
}
/**////Web Client Method ,only For Small picture
/// </summary>
/// <param name="fileName"></param>
/// <param name="url"></param>
/// <param name="localPath"></param>
public static void DownloadOneFileByURLWithWebClient(string fileName, string url, string localPath)
{
System.Net.WebClient wc = new System.Net.WebClient();
if (File.Exists(localPath + fileName)) { File.Delete(localPath + fileName); }
if (Directory.Exists(localPath) == false) { Directory.CreateDirectory(localPath); }
wc.DownloadFile(url + fileName, localPath + fileName);
}
结果不能获取源码。错误如下:
再想想,还有Webbrowser控件可以用啊。在WinFrom下只要在主线程前加[STAThread]即可。
Code
[STAThread]
public void GetURLContentByWebBrowser()
{
try
{
//webBrowser1 = new WebBrowser();
string url = txtUrl.Text.Trim();
string result = null;
WebBrowser wb = new WebBrowser();
/**/////if (wb != null){ wb.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(wb_DocumentCompleted); }
if (String.IsNullOrEmpty(url)) return;
if (url.Equals("about:blank")) return; ;
if (!url.StartsWith("http://") && !url.StartsWith("https://")) { url = "http://" + url; }
try
{
wb.Navigate(new Uri(url));
result = wb.DocumentText;
lbResult.Text = result;
}
catch (System.UriFormatException)
{ }
return;
}
catch (Exception ex)
{
//WriteLog.Writelog("这是获取页面全部html代码时发生的错误:" + url, ex);
throw ex;
//return ;
}
}
在WebForm就麻烦些了,出现错误,线程不在单线程单元中,故无法实例化 ActiveX 控件“8856f961-340a-11d0-a96b-00c04fd705a2”
代码如下:
Code
private string GetPageStringbyWebBrowser(string url)
{
if (url.Equals("about:blank")) return null; ;
if (!url.StartsWith("http://") && !url.StartsWith("https://")) { url = "http://" + url; }
WebBrowser myWB = new WebBrowser();
myWB.ScrollBarsEnabled = false;
myWB.Navigate(url);
while (myWB.ReadyState != WebBrowserReadyState.Complete)
{
System.Windows.Forms.Application.DoEvents();
}
if (myWB != null)
{
System.IO.StreamReader getReader = null;
try
{
getReader = new System.IO.StreamReader(myWB.DocumentStream, System.Text.Encoding.GetEncoding(myWB.Document.Encoding));
string gethtml = getReader.ReadToEnd();
return gethtml;
}
catch { return null; }
finally
{
if (getReader != null) { getReader.Close(); }
myWB.Dispose();
}
}
return null;
}
后来搜索N小时(N>=5)后,终于找到可行解决方案,在WebPage页面头部加入AspCompat="true"
即<%@ Page Language="C#" AspCompat="true" ******/>
MSDN给出的解释是:
在 ASP .NET 网页的 <%@Page> 标记中包含兼容性属性 aspcompat=true,如 <%@Page aspcompat=true Language=VB%>。使用此属性将强制网页以 STA 模式执行,从而确保您的组件可以继续正确运行。如果试图使用 STA 组件但没有指定此标记,运行时将会发生异常情况。
将此属性的值设置为 true 时,将允许网页调用 COM+ 1.0 组件,该组件需要访问非管理的 ASP 内置对象。可以通过 ObjectContext 对象进行访问。
如果将此标记的值设为 true,性能会稍微有些下降。建议只在确实需要时才这样做。
终于可以了! 不知道有没有更好的方法??
附:源码下载。
邀月注:
如果不能测试,请注意是否在域(AD)环境下,如果是! 请注意设置代理和防火墙
请参考:
http://dev.csdn.net/article/83914.shtm
或http://blog.csdn.net/downmoon/archive/2006/04/14/663337.aspx
或
http://www.cnblogs.com/downmoon/archive/2007/12/29/1019701.html