private void GetAll(UrlType type)
{
List <string> urls = new List <string>();
switch (type)
{
case UrlType.Page:
urls.Add(SearchRoot);
break;
case UrlType.Item:
urls.AddRange(UrlManager.GetAll(UrlType.Page));
break;
case UrlType.Image:
string[] tmpUrls = UrlManager.GetAll(UrlType.Item);
tmpUrls = ClearExsitItems(tmpUrls);
if (tmpUrls.Length == 0)
{
PassOutputAndStopRunning();
}
urls.AddRange(tmpUrls);
break;
}
foreach (string url in urls)
{
string html = HtmlDownloader.DownloadHtml(url);
string[] newUrls = HtmlParser.Parse(html, type);
for (int i = 0; i < newUrls.Length; i++)
{
newUrls[i] = newUrls[i].Replace("amp;", "");
}
UrlManager.AddRange(newUrls, type);
}
}
public MimiSearcher(string url)
{
SearchRoot = url;
UrlManager = new UrlManager();
HtmlDownloader = new HtmlDownloader();
HtmlParser = new HtmlParser();
HtmlOutputer = new HtmlOutputer();
// add root-url into url-manager
UrlManager.Add(SearchRoot, UrlType.Page);
}
