private void button2_Click(object sender, EventArgs e)
{
string strCon = "Data Source=(local);database=lucene;uid=sa;pwd=qq901;";
DataClasses1DataContext db;
db = new DataClasses1DataContext(strCon);
string url = "http://quote.eastmoney.com/stocklist.html";
string htmlbody = GetPageData(url);
//获取 链接地址和标题
string pattern5 = @"<a[\s\S]*?>[\s\S]*?</a>";
string pattern11 = @"(?<=href=[\u0022\u0027]?)(?!javascript)((?<Protocol>\w+):/)?[\/]?(?<Domain>[\w.]+\/?)((?![\u0022\u0027])\S)*";
///定义获取标题的正则表达式
string pattern = @"(?<=<title\s*[^>]*>).*(?=<\/title>)";
string title = @"(?<=<a\s*[^>]*>)[\s\S]*?(?=<\/a>)";
string pattern_dd = @"<dd[\s\S]*?>[\s\S]*?</dd>";
htmlbody = htmlbody.Replace("<a name=\"sh\"/>", "");
htmlbody = htmlbody.Replace("<a name=\"sz\"/>", "");
MatchCollection matches_url_title = Regex.Matches(htmlbody, pattern5, RegexOptions.IgnoreCase);
foreach (Match m_u_t in matches_url_title)
{
//寻找带下一页文字的链接全部
if (m_u_t.Value.IndexOf("(") > -1)
{
MatchCollection matches_title = Regex.Matches(m_u_t.Value, title, RegexOptions.IgnoreCase);
foreach (Match t in matches_title)
{
stock_id_name id_name = new stock_id_name();
// MessageBox.Show(t.Value);
id_name.stock_name = t.Value;
string strTest = t.Value;
int startIndex = strTest.LastIndexOf("(") + 1;
int length = strTest.Length - strTest.IndexOf(")");
id_name.stock_id = strTest.Substring(startIndex, strTest.Length - length - startIndex);
db.stock_id_name.InsertOnSubmit(id_name);
///提交插入操作
db.SubmitChanges();
}
}
}
MessageBox.Show("ok!");
}
partial void Deletestock_id_name(stock_id_name instance);
partial void Updatestock_id_name(stock_id_name instance);
partial void Insertstock_id_name(stock_id_name instance);