// Sets the _text field to the HTML content of the URL link
private void SetText(PageStructure page)
{
try
{
// Create web connection to specific URL
var req = (HttpWebRequest)WebRequest.Create(page.Url);
// Get the response from the website, stream its content, and read it
// Need to create some sort of handling for ill-formatted response/error response from the website
var res = req.GetResponse();
var resStream = res.GetResponseStream();
if (resStream == null)
{
return;
}
var readStream = new StreamReader(resStream);
// Turn stream into a usable string
Text = WebUtility.HtmlDecode(readStream.ReadToEnd());
}
catch (WebException)
{
//var except = new StreamReader(wex.Response.GetResponseStream()).ReadToEnd();
Text = string.Empty;
}
}
public WebPage(PageStructure pageStructure)
{
PageStructure = pageStructure;
SetText(PageStructure); //sets the _text of the webpage given the page url as raw HTML
SetArticle(Text); // sets the Boolean representing whether or not the page is an article page
document.LoadHtml(Text);
if (Article)
{
SetBlurb(); // sets the _blurb of the webpage given the text of the page
SetTitle(); // sets the _title of the webpage given the text of the page
}
else
{
Title = "";
Blurb = "";
}
}
private void CrawlPage(WebPage webPage)
{
_crawledPages.Add(webPage.PageStructure.Url, "");
// iterate over all the URL strings of the children, turn them into a webpage, and
// put them on the queue if they havem't been crawled yet
if (!TooDeep(webPage))
{
// all the "children" of the webpage...all links the webpage contains
var children = webPage.SetUrls();
foreach (var child in children)
{
if ((!HasBeenCrawled(child)) && IsDescendent(child, webPage) && (!_childrenInQueue.ContainsKey(child)))
{
_childrenInQueue.Add(child, "");
var childPage = new PageStructure(child, webPage.PageStructure.Depth + 1, webPage.PageStructure.ArticleStructure, webPage.PageStructure.BaseUri);
_queue.Enqueue(childPage);
}
}
}
}
