htmlparser使用备注

// 使用 ObjectFindingVisitor 配合不同的 Tag.class
分析网页

try

{

ImageTag imgLink;

ObjectFindingVisitor visitor = new
ObjectFindingVisitor(ImageTag.class);

Parser parser = new Parser();

parser.setURL(url);

parser.setEncoding(parser.getEncoding());

parser.visitAllNodesWith(visitor);

Node[] nodes = visitor.getTags();

for (int i = 0; i < nodes.length; i++)

{

// ImageTag

imgLink = (ImageTag) nodes[i];

// "http://www.msn.com.tw/webinclude/zh-tw/images/msn.gif"
=> ImageURL

System.out.println("ImageURL = " +
imgLink.getImageURL());

// "/webinclude/zh-tw/images/msn.gif" =>
ImageLocation

System.out.println("ImageLocation = " +
imgLink.extractImageLocn());

// SRC value

System.out.println("SRC = " +
imgLink.getAttribute("SRC"));

}

}

catch (Exception e)

{

e.printStackTrace();

}

// 使用不同的 NodeFilter 分析网页

try

{

NodeFilter filter = new TagNameFilter("IMG");

NodeFilter filter1 = new
NodeClassFilter(ImageTag.class);

Parser parser = new Parser();

parser.setURL(url);

parser.setEncoding(parser.getEncoding());

NodeList list =
parser.extractAllNodesThatMatch(filter);

for (int i = 0; i < list.size(); i++)

{


System.out.println(list.elementAt(i).toHtml());

}

}

catch (Exception e)

{

e.printStackTrace();

}

// 直接使用 Tag.class 分析网页

try

{

Parser parser = new Parser();

parser.setURL(url);

parser.setEncoding(parser.getEncoding());

Node[] nodes =
parser.extractAllNodesThatAre(ImageTag.class);

for (int i = 0; i < nodes.length; i++)

{

ImageTag imageTag = (ImageTag) nodes[i];

System.out.println(imageTag.getImageURL());

}

}

catch (Exception e)

{

e.printStackTrace();

}