C#网页信息采集方法汇总
程序员文章站
2023-12-15 17:38:58
本文实例总结了三种常用的c#网页信息采集方法。分享给大家供大家参考。具体实现方法如下:
一、通过httpwebresponse 来获取
复制代码 代码如下:public...
本文实例总结了三种常用的c#网页信息采集方法。分享给大家供大家参考。具体实现方法如下:
一、通过httpwebresponse 来获取
复制代码 代码如下:
public static string checkteamsiteurl(string url)
{
string response = "";
httpwebresponse httpresponse = null;
//assert: user have access to url
try
{
httpwebrequest httprequest = (httpwebrequest)webrequest.create(url);
httprequest.headers.set("pragma", "no-cache");
// request.headers.set("keepalive", "true");
httprequest.cookiecontainer = new cookiecontainer();
httprequest.referer = url;
httprequest.useragent = "mozilla/4.0 (compatible; msie 6.0; windows nt 5.0; .net clr 1.1.4322; .net clr 2.0.50727)";
httprequest.credentials = system.net.credentialcache.defaultcredentials;
httpresponse = (httpwebresponse)httprequest.getresponse();
}
catch (exception ex)
{
throw new applicationexception("http 403 access denied, url: " + url, ex);
}
//if here, the url is correct and the user has access
try
{
string strencod = httpresponse.contenttype;
streamreader stream;
if (strencod.tolower().indexof("utf") != -1)
{
stream = new streamreader(httpresponse.getresponsestream(), system.text.encoding.utf8);
}
else
{
stream = new streamreader(httpresponse.getresponsestream(), system.text.encoding.default);
}
char[] buff = new char[4000];
stream.readblock(buff,0,4000);
response = new string(buff);
stream.close();
httpresponse.close();
}
catch (exception ex)
{
throw new applicationexception("http 404 page not found, url: " + url, ex);
}
return response;
}
{
string response = "";
httpwebresponse httpresponse = null;
//assert: user have access to url
try
{
httpwebrequest httprequest = (httpwebrequest)webrequest.create(url);
httprequest.headers.set("pragma", "no-cache");
// request.headers.set("keepalive", "true");
httprequest.cookiecontainer = new cookiecontainer();
httprequest.referer = url;
httprequest.useragent = "mozilla/4.0 (compatible; msie 6.0; windows nt 5.0; .net clr 1.1.4322; .net clr 2.0.50727)";
httprequest.credentials = system.net.credentialcache.defaultcredentials;
httpresponse = (httpwebresponse)httprequest.getresponse();
}
catch (exception ex)
{
throw new applicationexception("http 403 access denied, url: " + url, ex);
}
//if here, the url is correct and the user has access
try
{
string strencod = httpresponse.contenttype;
streamreader stream;
if (strencod.tolower().indexof("utf") != -1)
{
stream = new streamreader(httpresponse.getresponsestream(), system.text.encoding.utf8);
}
else
{
stream = new streamreader(httpresponse.getresponsestream(), system.text.encoding.default);
}
char[] buff = new char[4000];
stream.readblock(buff,0,4000);
response = new string(buff);
stream.close();
httpresponse.close();
}
catch (exception ex)
{
throw new applicationexception("http 404 page not found, url: " + url, ex);
}
return response;
}
二、通过 webresponse 来获取
复制代码 代码如下:
public static string getpage(string url)
{
webresponse result = null;
string resultstring = "";
try
{
webrequest req = webrequest.create(url);
req.timeout = 30000;
result = req.getresponse();
stream receivestream = result.getresponsestream();
//read the stream into a string
//streamreader sr = new streamreader(receivestream, system.text.encoding.utf8);
string strencod = result.contenttype;
streamreader sr;
if (strencod.tolower().indexof("utf") != -1)
{
sr = new streamreader(receivestream, system.text.encoding.utf8);
}
else
{
sr = new streamreader(receivestream, system.text.encoding.default);
}
resultstring = sr.readtoend();
js.alert(resultstring);
//console.writeline(resultstring);
}
catch
{
throw new exception();
}
finally
{
if (result != null)
{
result.close();
}
}
return resultstring;
}
{
webresponse result = null;
string resultstring = "";
try
{
webrequest req = webrequest.create(url);
req.timeout = 30000;
result = req.getresponse();
stream receivestream = result.getresponsestream();
//read the stream into a string
//streamreader sr = new streamreader(receivestream, system.text.encoding.utf8);
string strencod = result.contenttype;
streamreader sr;
if (strencod.tolower().indexof("utf") != -1)
{
sr = new streamreader(receivestream, system.text.encoding.utf8);
}
else
{
sr = new streamreader(receivestream, system.text.encoding.default);
}
resultstring = sr.readtoend();
js.alert(resultstring);
//console.writeline(resultstring);
}
catch
{
throw new exception();
}
finally
{
if (result != null)
{
result.close();
}
}
return resultstring;
}
三、通过webclient来获取
复制代码 代码如下:
public string get(int length)
{
try
{
getencodeing();
webclient wb = new webclient();
stream response = wb.openread(url);
streamreader reader = new streamreader(response, this.encoding, true, 256000);
char[] a = new char[length];
int i = reader.read(a,0,length);
reader.close();
return new string(a);
}
catch (exception e)
{
return e.message;
//return null;
}
}
private void getencodeing()
{
switch (this.encode)
{
case "utf-8": encoding = encoding.utf8; break;
case "gb2312": encoding = encoding.getencoding("gb2312"); break;
case "ascii": encoding = encoding.ascii; break;
default: encoding = encoding.getencoding(encode); break;
}
}
{
try
{
getencodeing();
webclient wb = new webclient();
stream response = wb.openread(url);
streamreader reader = new streamreader(response, this.encoding, true, 256000);
char[] a = new char[length];
int i = reader.read(a,0,length);
reader.close();
return new string(a);
}
catch (exception e)
{
return e.message;
//return null;
}
}
private void getencodeing()
{
switch (this.encode)
{
case "utf-8": encoding = encoding.utf8; break;
case "gb2312": encoding = encoding.getencoding("gb2312"); break;
case "ascii": encoding = encoding.ascii; break;
default: encoding = encoding.getencoding(encode); break;
}
}
希望本文所述对大家的c#程序设计有所帮助。