public static PageType GetPageType(string sUrl, ref string sHtml)
{
PageType pt = PageType.HTML;
//看有没有RSS FEED
string regRss = @"<link\s+[^>]*((type=""application/rss\+xml"")|(type=application/rss\+xml))[^>]*>";
Regex r = new Regex(regRss, RegexOptions.IgnoreCase);
Match m = r.Match(sHtml);
if (m.Captures.Count != 0)
{//有，则转向从RSS FEED中抓取
string regHref = @"href=\s*(?:'(?<href>[^']+)'|""(?<href>[^""]+)""|(?<href>[^>\s]+))";
r = new Regex(regHref, RegexOptions.IgnoreCase);
m = r.Match(m.Captures[0].Value);
if (m.Captures.Count > 0)
{
//有可能是相对路径，加上绝对路径
string rssFile = CRegex.GetUrl(sUrl, m.Groups["href"].Value);
sHtml = GetHtmlByUrl(rssFile);
pt = PageType.RSS;
}
}
else
{//看这个地址本身是不是一个Rss feed
r = new Regex(@"<rss\s+[^>]*>", RegexOptions.IgnoreCase);
m = r.Match(sHtml);
if (m.Captures.Count > 0)
{
pt = PageType.RSS;
}
}
return(pt);
}
private static string[] DealWithFrame(string strReg, string url, string content)
{
ArrayList alFrame = new ArrayList();
Regex r = new Regex(strReg, RegexOptions.IgnoreCase);
Match m = r.Match(content);
while (m.Success)
{
alFrame.Add(CRegex.GetUrl(url, m.Groups["src"].Value));
m = m.NextMatch();
}
return((string[])alFrame.ToArray(System.Type.GetType("System.String")));
}
