private void btn_OK_Click(object sender, EventArgs e)
{
if (!String.IsNullOrEmpty(txt_NewExpression.Text))
{
using (RegularDAL dal = new RegularDAL ())
{
if (dal.GetRegular(txt_NewExpression.Text.Trim()) == null)
{
Regular regular = new Regular()
{
ID = Guid.NewGuid(),
Name = txt_NewExpression.Text.Trim(),
Site = comb_Site.SelectedItem as Site,
Type = comb_TypeList.SelectedItem as Entities.Type
};
if (dal.AddRegular(regular))
{
txt_NewExpression.Text = "";
BindRegularList(comb_Site.SelectedItem as Site);
MessageBox.Show("添加成功！");
}
else
{
MessageBox.Show("添加失败！");
}
}
else {
MessageBox.Show("该正则已存在!");
}
}
}
else
{
MessageBox.Show("正则表达式不能为空!");
}
}
public List<Model.Address> GetArticleAddress(Regular regular, string html)
{
List<Model.Address> addressList = new List<Model.Address>();
string clearFilter = @"[\t\n\r]";
html = Regex.Replace(html, clearFilter, "");
string mainNews = "";
string newsFilter =@"<div class=" +"\""+regular.Name+"\""+ ">.*?</div>";
MatchCollection newsMatch = Regex.Matches(html, newsFilter);
if (newsMatch.Count<=0)
{
newsFilter =@"<div class="+"\'"+ regular.Name+"\'"+ ">.*?</div>";
newsMatch = Regex.Matches(html, newsFilter);
}
//去掉换行 拼接字符串
foreach (var item in newsMatch)
{
mainNews += item.ToString();
}
//取链接的正则表达式
Regex regex2 = new Regex(@"<a[^>]+href=\s*(?:'(?<href>[^']+)'|""(?<href>[^""]+)""|(?<href>[^>\s]+))\s*[^>]*>(?<text>.*?)</a>", RegexOptions.IgnoreCase);
for (Match match2 = regex2.Match(mainNews); match2.Success; match2 = match2.NextMatch())
{
string url = match2.Groups["href"].Value;
addressList.Add(new Model.Address()
{
address = url,
site = regular.Site,
type = regular.Type
});
}
return addressList;
}
