//只获取网页源码开始到标题位目的进行测试
//第一种方式经过测试,稍微快点
string url = "http://www.ip.cn";
HttpWebRequest req = (HttpWebRequest)WebRequest.Create(url);
req.Method = "GET";
req.ContentType = "application/x-www-form-urlencoded";
HttpWebResponse res = (HttpWebResponse)req.GetResponse();
Stream ReceiveStream = res.GetResponseStream();
Encoding encode = System.Text.Encoding.UTF8;
StreamReader sr = new StreamReader(ReceiveStream, encode);
string strResult = "";
Char[] read = new Char[256];
int count = sr.Read(read, 0, 256);
while (count > 0)
{
String str = new String(read, 0, count);
strResult += str;
count = sr.Read(read, 0, 256);
if (strResult.IndexOf("</title>") != -1)
{
break;
}
}
textBoxTest.Text = strResult;
//第二种获取网页源码
WebClient MyClient = new WebClient();
MyClient.Credentials = CredentialCache.DefaultCredentials;
MyClient.Headers.Add("Host", "www.kuwo.cn");
MyClient.Headers.Add("User-Agent", "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36");
Byte[] pageData = MyClient.DownloadData(url);
//string pageHtml = Encoding.Default.GetString(pageData); //GB2312
string pageHtml = Encoding.UTF8.GetString(pageData); //UTF-8
//字符串截取,从网页源码中截取 两字符串中间信息
private string GetStr(string TxtStr, string FirstStr, string SecondStr)
{
if (FirstStr.IndexOf(SecondStr, 0) != -1)
return "";
int FirstSite = TxtStr.IndexOf(FirstStr, 0);
int SecondSite = TxtStr.IndexOf(SecondStr, FirstSite + 1);
if (FirstSite == -1 || SecondSite == -1)
return "";
return TxtStr.Substring(FirstSite + FirstStr.Length, SecondSite - FirstSite - FirstStr.Length);
}
//正则截取字符串 A.B之间
string title2 = Regex.Match(title, "(?<="+"A"+").*?(?="+"B"+")").Value;
//Regex.Match(sUrl, "(?<=A).*?(?=B)").Value;
//自定义函数
private string MyGetTitle(string url, string endTag, string startStr, string endStr)
{
try
{
//HttpWebRequest类继承于WebRequest,并没有自己的构造函数,需通过WebRequest的Creat方法 建立,并进行强制的类型转换
HttpWebRequest req = (HttpWebRequest)WebRequest.Create(url);
req.Method = "GET";
req.ContentType = "text/html;charset=UTF-8";
//通过HttpWebRequest的GetResponse()方法建立HttpWebResponse,强制类型转换
HttpWebResponse res = (HttpWebResponse)req.GetResponse();
//若成功取得网页的内容,则以System.IO.Stream形式返回,
//若失败则产生ProtoclViolationException错 误。
//在此正确的做法应将以下的代码放到一个try块中处理。这里简单处理
Stream ReceiveStream = res.GetResponseStream();
//返回的内容是Stream形式的,所以可以利用StreamReader类获取GetResponseStream的内容,
//并以StreamReader类的Read方法依次读取网页源程序代码每一行的内容,直至行尾(读取的编码格式:UTF8)
StreamReader sr = new StreamReader(ReceiveStream, Encoding.UTF8);
string strResult = "";
Char[] read = new Char[256];
//Read(char[] buffer,int index,int count);
//从文件流的第index个位置开始读,到count个字符,把它们存到buffer中,
//然后返回一个正数,内部指针后移一位,保证下次从新的位置开始读。
int count = sr.Read(read, 0, 256);
while (count > 0)
{
String str = new String(read, 0, count);
strResult += str;
count = sr.Read(read, 0, 256);
if (strResult.IndexOf(endTag) != -1) break;
}
res.Close();
ReceiveStream.Dispose();
return Regex.Match(strResult, "(?<=" + startStr + ").*?(?=" + endStr + ")").Value;
}
catch (Exception ex)
{
LogAdd(ListBoxDownLog, "异常:" + ex.Message);
throw;
}
}