private void nextSample() //从original表格中得到样本用于概念计算,存放在类变量sampleString中;
{
originalid++;
original toriginal = htmlpage.original.Find(originalid);
if (originalid > originalendid) //大于不包括需要抽取的节点时程序退出
{
Application.Exit();
}
if (toriginal != null) //该originalid有对应的取值
{
sampleString = toriginal.info;
Console.Out.WriteLine("对照的样本 ：" + sampleString);
}
else
{
originalid++; //如果该id对应的urltable元组不存在则记录抽取的extractid自增，抽取下一条；
nextSample();
}
}
private void extract_timer_Tick(object sender, EventArgs e)
{
count2++;
if (count2 >= 35) //count >=35仍然没有加载完成则直接取下一进行抽取
{
extract_timer.Stop();
Console.Out.WriteLine("此处记得添加解析不成功是的下一页代码");
extractid++;
nextextraturl(extractid);
return;
}
if (this.webBrowser1.ReadyState == WebBrowserReadyState.Complete || this.webBrowser1.ReadyState == WebBrowserReadyState.Interactive)
{
extract_timer.Stop();
//string strPath = @"D:\testtest.txt";
//string value = this.webBrowser1.Document.Body.OuterHtml;
//if (!Directory.Exists(Path.GetDirectoryName(strPath)))
//{
// Directory.CreateDirectory(Path.GetDirectoryName(strPath));
//}
// File.AppendAllText(strPath, value, Encoding.Default);
foreach (HtmlElement el in this.webBrowser1.Document.Body.GetElementsByTagName(tag))
{
bool isRight = true;
// Console.Out.WriteLine("tag"+ tag +"attr: "+ attrs[0].Value);
foreach (var item in attrs)
{
// Console.Out.WriteLine("name " + item.Name);
// Console.Out.WriteLine("value " + item.Value);
String attr = item.Name;
if (item.Name.Equals("classname") || item.Name.Equals("class"))
{
attr = "className";
}
// Console.Out.WriteLine(el.GetAttribute(attr));
if (!item.Value.Equals(el.GetAttribute(attr)))
{
isRight = false; //如果有一个节点属性不能匹配则结束循环不在匹配后续属性
break;
}
}
if (isRight) //如果所有节点属性都匹配成功则进行抽取
{
if (el.InnerText != null && el.InnerText.Trim().Length > 0)
{
//int urlid = extractid;
//String info =Regex.Replace(el.InnerText.Trim(),"\\s+"," ");
////site、extracturl已经在提取url是设置；
//String doc = this.webBrowser1.DocumentText;
//Console.Out.WriteLine("urlid: "+urlid + "抽取信息： " + info + " 网站： " + site + "来源url " + extracturl + "分类： " + mark);
original orig = new original();
orig.info = Regex.Replace(el.InnerText.Trim(), "\\s+", " ");
orig.mark = mark;
orig.site = site;
orig.url = extracturl;
orig.urlid = extractid;
orig.doc = this.webBrowser1.DocumentText;
htmlpage.original.Add(orig);
htmlpage.SaveChanges();
}
}
}
extractid++;
nextextraturl(extractid);
}
// public void extract
}
