htmlparser解析

Parser parser = new Parser(url);

//*过虑<p>标签

NodeFilter pfilter = new NodeClassFilter(ParagraphTag.class);
NodeList list = parser.extractAllNodesThatMatch(pfilter);

 

//*过虑<span>标签

NodeFilter spanfilter = new NodeClassFilter(Span.class);   

NodeList list = parser.extractAllNodesThatMatch(spanfilter);