Try this :
public partial class Form1 : Form
{
public Form1()
{
InitializeComponent();
}
private void Form1_Load(object sender, EventArgs e)
{
var res = Find(html);
}
public static List<LinkItem> Find(string file)
{
List<LinkItem> list = new List<LinkItem>();
// 1.
// Find all matches in file.
MatchCollection m1 = Regex.Matches(file, @"(<a.*?>.*?</a>)",
RegexOptions.Singleline);
// 2.
// Loop over each match.
foreach (Match m in m1)
{
string value = m.Groups[1].Value;
LinkItem i = new LinkItem();
// 3.
// Get href attribute.
Match m2 = Regex.Match(value, @"href=\""(.*?)\""",
RegexOptions.Singleline);
if (m2.Success)
{
i.Href = m2.Groups[1].Value;
}
// 4.
// Remove inner tags from text.
string t = Regex.Replace(value, @"\s*<.*?>\s*", "",
RegexOptions.Singleline);
i.Text = t;
list.Add(i);
}
return list;
}
public struct LinkItem
{
public string Href;
public string Text;
public override string ToString()
{
return Href + "\n\t" + Text;
}
}
}
Input:
string html = "<a href=\"www.aaa.xx/xx.zz?id=xxxx&name=xxxx\" ....></a> 2.<a href=\"http://www.aaa.xx/xx.zz?id=xxxx&name=xxxx\" ....></a> ";
Result:
[0] = {www.aaa.xx/xx.zz?id=xxxx&name=xxxx}
[1] = {http://www.aaa.xx/xx.zz?id=xxxx&name=xxxx}
C# Scraping HTML Links
Scraping HTML extracts important page elements. It has many legal uses
for webmasters and ASP.NET developers. With the Regex type and
WebClient, we implement screen scraping for HTML.
Edited
Another easy way:you can use a web browser control for getting href from tag a,like this:(see my example)
public Form1()
{
InitializeComponent();
webBrowser1.DocumentCompleted += new WebBrowserDocumentCompletedEventHandler(webBrowser1_DocumentCompleted);
}
private void Form1_Load(object sender, EventArgs e)
{
webBrowser1.DocumentText = "<a href=\"www.aaa.xx/xx.zz?id=xxxx&name=xxxx\" ....></a><a href=\"http://www.aaa.xx/xx.zz?id=xxxx&name=xxxx\" ....></a><a href=\"https://www.aaa.xx/xx.zz?id=xxxx&name=xxxx\" ....></a><a href=\"www.aaa.xx/xx.zz/xxx\" ....></a>";
}
void webBrowser1_DocumentCompleted(object sender, WebBrowserDocumentCompletedEventArgs e)
{
List<string> href = new List<string>();
foreach (HtmlElement el in webBrowser1.Document.GetElementsByTagName("a"))
{
href.Add(el.GetAttribute("href"));
}
}
