private string FilterList(string html, M_Collect_ListFilter model)
{
StringBuilder sb = new StringBuilder();
string listFilter = model.ListStart + "[\\s\\S]*?" + model.ListEnd;
MatchCollection matches = new Regex(listFilter).Matches(html);
Match TitleMatch = Regex.Match(html, listFilter, RegexOptions.IgnoreCase | RegexOptions.Multiline);
foreach (Match m in matches)
{
string url = (m.Value.Replace(model.ListStart, "").Replace(model.ListEnd, ""));
if (url.ToLower().Contains("http") || url.ToLower().Contains("https"))
{
}
else
{
url = model.FillStart + url + model.FillEnd;
} //自动用根路径,或用户预设好的值填充前面
sb.AppendLine(url);
}
if (string.IsNullOrEmpty(sb.ToString()))
{
return("");
}
return(htmlHelper.GetAllLink("<html><head></head><body>" + sb.ToString() + "</body></html>", model));
}
protected void Page_Load(object sender, EventArgs e)
{
if (!IsPostBack)
{
M_CollectionItem mc = bc.GetSelect(ItemID);
Url = mc.CollUrl;
lblLink.Text = "<a href='" + mc.CollUrl + "' target=\"_blank\" class='btn btn-info' style='color:white;'>查看原页面</a>";
SourceHtml_Hid.Value = htmlHelper.GetHtmlFromSite(Url);
if (!string.IsNullOrEmpty(mc.ListSettings))
{
lfMod = JsonConvert.DeserializeObject <M_Collect_ListFilter>(mc.ListSettings);
ListStart_T.Text = lfMod.ListStart;
ListEnd_T.Text = lfMod.ListEnd;
CharContain_T.Text = lfMod.CharContain;
CharRegex_T.Text = lfMod.CharRegex;
FillStart_T.Text = lfMod.FillStart;
FillEnd_T.Text = lfMod.FillEnd;
}
if (!string.IsNullOrEmpty(mc.LinkList))
{
txtHtml.Text = mc.LinkList;
}
else
{
txtHtml.Text = SourceHtml_Hid.Value;
}
Call.SetBreadCrumb(Master, "<li><a href='ContentManage.aspx'>内容管理</a></li><li><a href='CollectionManage.aspx'>信息采集</a></li><li class='active'>当前:" + mc.ItemName + "</li>");
}
}
/// <summary>
/// 从Html中获取所有超链接,必须以<html>包裹,自动过滤javascript:;等无效Url
/// </summary>
/// <param name="html">需要筛选的Html代码</param>
/// <param name="pre">链接前加</param>
/// <param name="end">链接后加</param>
/// <param name="charcontain">必须包含指定字符</param>
/// <returns></returns>
public string GetAllLink(string html, M_Collect_ListFilter model)
{
string list = "";
NodeList nodeList = GetTagList(html, "A");
for (int i = 0; i < nodeList.Size(); i++)
{
ATag link = (ATag)nodeList.ElementAt(i);
string href = link.GetAttribute("href");
if (string.IsNullOrEmpty(href) || href.ToLower().IndexOf("javascript") > -1)
{
continue;
}
//必须包含有指定字符串
if (!string.IsNullOrEmpty(model.CharContain) && !href.Contains(model.CharContain))
{
bool flag = false;
foreach (string start in model.CharContain.Split("|".ToCharArray(), StringSplitOptions.RemoveEmptyEntries))
{
if (href.Contains(start))
{
flag = true; break;
}
}
if (flag == false)
{
continue;
}
}
if (!string.IsNullOrEmpty(model.CharRegex) && !Regex.IsMatch(href, model.CharRegex))
{
continue;
}
list += (model.FillStart + link.GetAttribute("href") + model.FillEnd) + "\n";
}
return(list);
}
//筛选列表
protected void FilterA_Btn_Click(object sender, EventArgs e)
{
lfMod = FillListFilter();
txtHtml.Text = FilterList(SourceHtml_Hid.Value, lfMod);
}
/// <summary>
/// 从Html中获取所有超链接,必须以<html>包裹,自动过滤javascript:;等无效Url
/// </summary>
/// <param name="html">需要筛选的Html代码</param>
/// <param name="pre">链接前加</param>
/// <param name="end">链接后加</param>
/// <param name="charcontain">必须包含指定字符</param>
/// <returns></returns>
public string GetAllLink(string html, M_Collect_ListFilter model)
{
return("");
}
