/// <summary>
/// Updates the href for simple redirects.
/// </summary>
/// <param name="htmlSource">The HTML source.</param>
/// <param name="linkHref">The link href.</param>
/// <param name="newHref">The new href.</param>
/// <returns></returns>
public static string UpdateHref(string htmlSource, string linkHref, string newHref)
{
var doc = TextCleaner.CreateHtmlDocument(htmlSource);
foreach (var node in doc.DocumentNode.SelectNodes("//a[@href='" + linkHref + "']") ?? Enumerable.Empty <HtmlNode>())
{
node.Attributes["href"].Value = newHref;
}
return(TextCleaner.GetHtmlSource(doc));
}
/// <summary>
/// Marks the specified invalid link with square brackets.
/// </summary>
/// <param name="htmlSource">The HTML source to update.</param>
/// <param name="linkHref">The link href to alter.</param>
/// <returns></returns>
public static string MarkInvalid(string htmlSource, string linkHref)
{
var doc = TextCleaner.CreateHtmlDocument(htmlSource);
foreach (var node in doc.DocumentNode.SelectNodes("//a[@href='" + linkHref + "']") ?? Enumerable.Empty <HtmlNode>())
{
// don't add more than one pair of brackets, but ignore any just outside of this element
node.InnerHtml = "[" + node.InnerHtml.TrimStart('[').TrimEnd(']') + "]";
}
return(TextCleaner.GetHtmlSource(doc));
}
/// <summary>
/// Finds the links in the supplied HTML source.
/// </summary>
/// <param name="html">The HTML.</param>
/// <returns></returns>
public static List <LinkDescription> FindLinks(string html)
{
var doc = TextCleaner.CreateHtmlDocument(html);
var links = doc.DocumentNode.SelectNodes("//a[@href]") ?? Enumerable.Empty <HtmlNode>();
var result = new List <LinkDescription>();
foreach (var link in links)
{
var lnk = new LinkDescription();
lnk.LinkText = HttpUtility.HtmlDecode(link.InnerText);
lnk.OriginalLink = link.GetAttributeValue("href", string.Empty);
if (!lnk.OriginalLink.StartsWith("http", StringComparison.OrdinalIgnoreCase))
{
// neither "http" nor "https"
lnk.Result = LinkCheckSummary.Ignored;
}
result.Add(lnk);
}
return(result);
}
