/// <summary>
/// Extracts the meta tag info from the page using RegEx
/// </summary>
/// <param name="p_strPageHtmlContent"></param>
/// <returns>Deprecated</returns>
private static Dict<string, PageMeta> GetPageMetaInfo(string p_strPageHtmlContent)
{
Dict<string, PageMeta> dictReturnSet = new Dict<string, PageMeta>();
PageMeta pmMetaTag = new PageMeta();
// Try grabbing the meta info of the page into a dictionary
string pattern = "<meta.+?(?:name=(?:\"|')(.*?)(?:\"|').*?)?(?:property=(?:\"|')(.*?)(?:\"|').*?)?(?:content=(?:\"|')(.*?)(?:\"|'))?/?>.*?</head>";
RegexOptions rxoOptions = RegexOptions.IgnoreCase | RegexOptions.Singleline;
foreach (Match match in Regex.Matches(p_strPageHtmlContent, pattern, rxoOptions))
{
pmMetaTag = new PageMeta();
pmMetaTag.Name = match.Groups[1].Value;
pmMetaTag.Property = match.Groups[2].Value;
pmMetaTag.Content = match.Groups[3].Value;
if (!dictReturnSet.ContainsKey(match.Groups[1].Value))
{
dictReturnSet.Add(match.Groups[1].Value, pmMetaTag);
}
}
return dictReturnSet;
}
/// <summary>
/// Grabs and returns Meta tags from the page head
/// </summary>
/// <param name="htmlDocDocument"></param>
/// <returns></returns>
private static List<PageMeta> GetPageMetaInfo(HtmlDocument p_htmlDocDocument)
{
PageMeta pmMeta = null;
List<PageMeta> lstMeta = new List<PageMeta>();
if (p_htmlDocDocument.DocumentNode.SelectNodes("//meta") != null)
{
foreach (HtmlNode hnItem in p_htmlDocDocument.DocumentNode.SelectNodes("//meta"))
{
pmMeta = new PageMeta();
pmMeta.Name = GetHtmlAttributeValue(hnItem.Attributes, "name");
pmMeta.Property = GetHtmlAttributeValue(hnItem.Attributes, "property");
pmMeta.Content = GetHtmlAttributeValue(hnItem.Attributes, "content");
lstMeta.Add(pmMeta);
}
}
return lstMeta;
}