private string FetchPage (String url) // take the specified source page URL of the page {String page = "null"; try {WebClient mywc = new WebClient (); using (Stream strm = mywc.OpenRead (url)) {StreamReader sr = New streamreader (STRM); Page = Sr.ReadToend (); strm.close ();}} catch {} return page;} PUBLIC STRING GETLINK (String URL) // Absolute link {String Content = this.FetchPage (URL ); // regex linkRegex = new regex ("HREF // S * = // s * (?: /" (? <1> [^ / "] *) /" | (? <1> // s ) ", Regexoptions.ignorecase); @@" ^/w ((-/w )) **/@/w ((((((@ )/w )**/w $" ; Regex link = new regex (@ "http: // ([/ w-] /.) [/ W-] (/ [/W-./? %&=] *)?", Regexoptions. IgnoreCase; stringbuilder sb = new stringbuilder (); matchcollection emailmatchs = link.matches (content); forward (Match n in emailmatchs) {sb.append (n.tostring ()); sb.append (";");} IF (sb.Length == 0) {sb.append ("null");} return sb.tostring ();} public string getemailaddr (String URL) // Relative link
{
String content = this.FetchPage (URL);
// regex linkRegex = new regex ("HREF / / S * = // s * (?: /" (^ / "] *) /" | (? <1> // s ) ", Regexoptions.ignorecase;
@@ "^/w ((-/w )| (/./w ))**@/w (((/.|-)/w )**/w $";
Regex r = new regex (@ "/ w ((- / w) | (/ w)) * / @ / w ((/. | -) / w ) * /. / W [com | CN | COM .cn | NET | ORG | CC | UK] {1,6} ", regexoptions.ignorecase;
Stringbuilder SB = New StringBuilder ();
Matchcollection emailmatch = r.matches (content);
FOREACH (Match N in emailmatchs)
{
sb.append (n.tostring ());
sb.append (";");
}
IF (sb.length == 0) sb.append ("null");
Return sb.toString ();
}
Some of the code must feel my friends Fan Fan.
