/// <summary>
/// 对文章内容的清洗。依据TOP20总结出的，较为广泛适用的规则
/// </summary>
/// <param name="nodes">通过ItemContentXPath选出的nodes</param>
/// <param name="Url">该url，用于FormatHtml函数以整理文章格式</param>
/// <param name="Format">是否运用FormatHtml来进行文章格式的整理。若否，则在后期会清洗掉p、br等标签</param>
/// <returns></returns>
public static string CleanContent(HtmlNodeCollection nodes, string Url, bool Format = true)
{
string Content = string.Empty;
foreach (HtmlNode cnode in nodes)
{
string temp = HtmlFormatter.FormatHtml(cnode.InnerHtml, Url);
temp = CleanContent_CleanEditor(temp);
temp = CleanContent_CleanA(temp);
if (!Format)
{
temp = TextCleaner.FullClean(temp);
}
Content += temp;
}
return(Content);
}
