internal void AddExternalUrl(string href)
{
ExternalUrls.Add(href);
}
public void crawlUrl(string urlToCrawl, List <string> parentWillCrawl = null)
{
Url aUrl = new Url()
{
Uri = urlToCrawl
};
CrawledDomainUrlsAsUrlObjects.Add(aUrl);
if (CrawledAllowedDomainUrls.Contains(urlToCrawl) || CrawledAllowedDomainUrls.Contains(urlToCrawl.Split('#').First()))
{
return;
}
CrawledAllowedDomainUrls.Add(urlToCrawl);
//Load Page And Capture Time To Load
DateTime preLoad = DateTime.Now;
WebDriver.Navigate().GoToUrl(urlToCrawl);
aUrl.MsToLoad = (DateTime.Now - preLoad).Milliseconds;
//Take Screenshot of Page
String basePath = SavePicturesToPath + aUrl.FileNameBase;
int height = WebDriver.FindElement(By.TagName("body")).Size.Height;
WebDriver.Manage().Window.Size = new Size(WebDriver.Manage().Window.Size.Width, height + 250);
((ITakesScreenshot)WebDriver).GetScreenshot().SaveAsFile(basePath + ".png",
ScreenshotImageFormat.Png);
aUrl.PicturePath = basePath + ".png";
aUrl.HtmlSourcePath = basePath + ".html";
File.WriteAllText(aUrl.HtmlSourcePath, WebDriver.PageSource);
//Save Source Code of Page
ReadOnlyCollection <IWebElement> links = WebDriver.FindElements(By.TagName("a"));
List <String> urlsFoundOnThisPage = new List <string>();
foreach (var link in links)
{
if (link.GetAttribute("href") != null)
{
urlsFoundOnThisPage.Add(link.GetAttribute("href").Split('#').First());
}
}
UpdateProgressListeners(urlToCrawl, urlsFoundOnThisPage);
//Generate list of known urls to pass to this method so that we don't crawl forever.
List <String> parentsWillCrawl = new List <string>();
if (parentWillCrawl != null)
{
parentsWillCrawl.AddRange(parentWillCrawl);
}
parentsWillCrawl.AddRange(urlsFoundOnThisPage);
foreach (var url in urlsFoundOnThisPage)
{
if (InAllowedDomain(url) && !CrawledAllowedDomainUrls.Contains(url) && (parentWillCrawl == null || !parentWillCrawl.Contains(url)))
{
crawlUrl(url, parentsWillCrawl);
}
else
{
ExternalUrls.Add(url);
//If it is a url that is in the list of external urls to capture, go ahead.
foreach (var captureExternalUrl in Config.CapturePagesLinkedInTheseDomains)
{
if (UrlsMatch(captureExternalUrl, url))
{
crawlUrl(url, parentsWillCrawl);
break;
}
}
}
}
}
/// <summary>
/// Parses a page looking for links.
/// </summary>
/// <param name="page">The page whose text is to be parsed.</param>
/// <param name="sourceUrl">The source url of the page.</param>
public void ParseLinks(InputSite inputSite, Page page, string sourceUrl)
{
if (sourceUrl.EndsWith(".xml"))
{
var matches = Regex.Matches(page.Text, _SITEMAP_REGEX);
for (var i = 0; i <= matches.Count - 1; i++)
{
var anchorMatch = matches[i];
var foundHref = BddJson.NormalizeUrl(anchorMatch.Value);
// TODO faire un Regex Match
foundHref = foundHref.Replace("<loc>", "");
foundHref = foundHref.Replace("</loc>", "");
if (!IsBad(foundHref) && !GoodUrls.Contains(foundHref))
{
GoodUrls.Add(foundHref);
}
}
}
else
{
var matches = Regex.Matches(page.Text, _LINK_REGEX);
for (var i = 0; i <= matches.Count - 1; i++)
{
var anchorMatch = matches[i];
if (anchorMatch.Value == string.Empty)
{
BadUrls.Add("Blank url value on page " + sourceUrl);
continue;
}
string foundHref = null;
try
{
foundHref = anchorMatch.Value.Replace("href=\"", "");
foundHref = foundHref.Substring(0, foundHref.IndexOf("\""));
}
catch (Exception exc)
{
Exceptions.Add("Error parsing matched href: " + exc.Message);
}
foundHref = BddJson.NormalizeUrl(foundHref);
if (!IsBad(foundHref) && !GoodUrls.Contains(foundHref))
{
if (IsExternalUrl(inputSite, foundHref))
{
ExternalUrls.Add(foundHref);
}
else if (!IsAWebPage(foundHref))
{
foundHref = Crawler.FixPath(inputSite, sourceUrl);
OtherUrls.Add(foundHref);
}
else
{
GoodUrls.Add(foundHref);
}
}
}
}
}
