Exemple #1
0
        private void ExtractLinksFromHtml(string html, IFilter filter)
        {
            foreach (string match in filter.FilterHTML(html))
            {
                string href = match;
                if (href.StartsWith("//"))
                {
                    continue;
                }

                if (href.StartsWith("/"))
                {
                    href = formatSubDomainToFullAddreess(href, startingAddress);
                }

                if (href.StartsWith(startingAddress) && !visitedSites.Contains(href) && !sitesToVisit.Contains(href) && checkIfURLIsAllowedByFilters(href))
                {
                    sitesToVisit.Push(href);
                }
            }
        }