/// <summary>
/// Grabs and returns Link tags from the page head
/// </summary>
/// <param name="htmlDocDocument"></param>
/// <returns></returns>
private static List <PageMetaLink> GetPageMetaLinkInfo(HtmlDocument p_htmlDocDocument)
{
PageMetaLink pmlLink = null;
List <PageMetaLink> lstLink = new List <PageMetaLink>();
if (p_htmlDocDocument.DocumentNode.SelectNodes("//link") != null)
{
foreach (HtmlNode hnItem in p_htmlDocDocument.DocumentNode.SelectNodes("//link"))
{
pmlLink = new PageMetaLink();
pmlLink.Rel = GetHtmlAttributeValue(hnItem.Attributes, "rel");
pmlLink.Href = GetHtmlAttributeValue(hnItem.Attributes, "href");
pmlLink.Type = GetHtmlAttributeValue(hnItem.Attributes, "type");
lstLink.Add(pmlLink);
}
}
return(lstLink);
}
/// <summary>
/// Extracts the link tag info from the page using RegEx
/// </summary>
/// <param name="p_strPageHtmlContent"></param>
/// <returns>Deprecated</returns>
private static Dict <string, PageMetaLink> GetPageMetaLinkInfo(string p_strPageHtmlContent)
{
Dict <string, PageMetaLink> dictReturnSet = new Dict <string, PageMetaLink>();
PageMetaLink pmlLinkTag = new PageMetaLink();
// Try grabbing the meta info of the page into a dictionary
string pattern = "<link.+?(?:rel=(?:\"|')(.*?)(?:\"|').*?)?(?:type=(?:\"|')(.*?)(?:\"|').*?)?(?:href=(?:\"|')(.*?)(?:\"|'))?/?>.*?</head>";
RegexOptions rxoOptions = RegexOptions.IgnoreCase | RegexOptions.Singleline;
foreach (Match match in Regex.Matches(p_strPageHtmlContent, pattern, rxoOptions))
{
pmlLinkTag = new PageMetaLink();
pmlLinkTag.Rel = match.Groups[1].Value;
pmlLinkTag.Type = match.Groups[2].Value;
pmlLinkTag.Href = match.Groups[3].Value;
dictReturnSet.Add(match.Groups[1].Value, pmlLinkTag);
}
return(dictReturnSet);
}
