/// <summary>
/// Process a URL
/// </summary>
/// <param name="page">the URL to process</param>
private void ProcessPage(string page)
{
ParseHTML parse = new ParseHTML();
parse.Source = page;
while (!parse.Eof())
{
char ch = parse.Parse();
if (ch == 0)
{
Attribute a = parse.GetTag()["HREF"];
if (a != null)
{
ProcessLink(a.Value);
}
a = parse.GetTag()["SRC"];
if (a != null)
{
ProcessLink(a.Value);
}
}
}
}
private void ProcessPage(string page)
{
ParseHTML parse = new ParseHTML();
parse.Source = page; //page为要解析的HTML文档
while (!parse.eof()) //利用循环来检查HTML文档包含的所有文本和标记
{
char ch = parse.Parse();
//Parse方法将返回HTML文档包含的字符--它返回的内容只包含那些非HTML标记的字符，如果遇到了HTML标记，Parse方法将返回0值，表示现在遇到了一个HTML标记。
//遇到一个标记之后，用GetTag()方法来处理它。
if (ch == 0)
{
Attribute a = parse.get()["HREF"];
if (a != null)
{
ProcessLink(a.Value); //提取出HREF属性的值
}
a = parse.get()["SRC"];
if (a != null)
{
ProcessLink(a.Value); //提取出SRC属性的值
}
if (spider.Flag == 1)
{
a = parse.get()["IMG"];
if (a != null && (a.Name.ToLower() == "src" || a.Name.ToLower() == "href"))
{
Uri url = new Uri(uri, a.Value);
if (spider.addIMG(url))
{
getpage(url);
}
}
}
}
}
}
/// <summary>
/// Process a URL
/// </summary>
/// <param name="page">the URL to process</param>
private void ProcessPage(string page)
{
ParseHTML parse = new ParseHTML();
parse.Source = page;
while(!parse.Eof())
{
char ch = parse.Parse();
if(ch==0)
{
Attribute a = parse.GetTag()["HREF"];
if( a!=null )
ProcessLink(a.Value);
a = parse.GetTag()["SRC"];
if( a!=null )
ProcessLink(a.Value);
}
}
}
