-----------------提取網頁內容----------------
1】
<<WebClient類>>
WebClient wc = new WebClient();
wc.Encoding = Encoding.UTF8;
string str = wc.DownloadString("http://tieba.baidu.com/p/2314539885");//下載頁面中所有的字符串
MatchCollection mc = Regex.Matches(str, "([0-9a-zA-Z_.-]+)@([0-9a-zA-Z_.]+([.][a-zA-Z]+){1,2})");
foreach (Match item in mc)
{
if (item.Success)
{
Console.WriteLine(item.Groups[1].Value+"==="+item.Groups[2].Value);
}
}
Console.WriteLine(mc.Count);
Console.ReadKey();
或者》》
WebClient MyWebClient = new WebClient();
MyWebClient.Credentials = CredentialCache.DefaultCredentials;//獲取或設置用於向Internet資源的請求進行身份驗證的網絡憑據
Byte[] pageData = MyWebClient.DownloadData(“http://www.163.com”); //從指定網站下載數據
string pageHtml = Encoding.Default.GetString(pageData); //如果獲取網站頁面採用的是GB2312,則使用這句
//string pageHtml = Encoding.UTF8.GetString(pageData); //如果獲取網站頁面採用的是UTF-8,則使用這句
Console.WriteLine(pageHtml);//在控制檯輸入獲取的內容
2】
<<WebRequest類>>
public void RequestSite(string url)
{
WebRequest req = WebRequest.Create(url);
HttpWebResponse res;
try
{
res = (HttpWebResponse)(req.GetResponse());
}
catch (WebException ex) { res = (HttpWebResponse)ex.Response; }
Stream st = res.GetResponseStream();
StreamReader rdr = new StreamReader(st);
string s = rdr.ReadToEnd();
todo.AddRange(GetLink(s));
}
3】
<<WebBrowser類>>//using System.Windows.Forms;估計是用在客戶端的;
WebBrowser web = new WebBrowser();
web.Navigate("http://www.xjflcp.com/ssc/");
web.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(web_DocumentCompleted);
void web_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
{
WebBrowser web = (WebBrowser)sender;
HtmlElementCollection ElementCollection = web.Document.GetElementsByTagName("Table");
foreach (HtmlElement item in ElementCollection)
{
File.AppendAllText("Kaijiang_xj.txt", item.InnerText);
}
}
c#爬蟲三類
發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.