|
/**
* 解析一個Html頁面,返回一個Html頁面類.
*
* @param resource 文件路徑或者網(wǎng)址
*/
public static SearchHtmlPage parseHtmlPage(String resource)
{
String title = "";
String body = "";
try
{
Parser myParser = new Parser(resource);
//設(shè)置編碼:根據(jù)實際情況修改
myParser.setEncoding("GBK");
HtmlPage visitor = new HtmlPage(myParser);
myParser.visitAllNodesWith(visitor);
title = visitor.getTitle();
body = combineNodeText(visitor.getBody().toNodeArray());
}
catch (ParserException e)
{
LogMan.error("Parse Html Page " + resource + " Error!");
}
SearchHtmlPage result = new SearchHtmlPage(title, body);
return result;
}
/**
* 解析Html內(nèi)容,得到普通文本和鏈接的內(nèi)容.
*
* @param content 要解析的內(nèi)容
* @return 返回解析后的內(nèi)容
*/
public static String parseHtmlContent(String content)
{
Parser myParser;
NodeList nodeList = null;
myParser = Parser.createParser(content, "GBK");
NodeFilter textFilter = new NodeClassFilter(TextNode.class);
NodeFilter linkFilter = new NodeClassFilter(LinkTag.class);
//暫時不處理 meta
//NodeFilter metaFilter = new NodeClassFilter(MetaTag.class);
OrFilter lastFilter = new OrFilter();
lastFilter.setPredicates(new NodeFilter[] { textFilter, linkFilter });
try
{
nodeList = myParser.parse(lastFilter);
}
catch (ParserException e)
{
LogMan.warn("Parse Content Error", e);
}
//中場退出了
if (null == nodeList)
{
return "";
}
Node[] nodes = nodeList.toNodeArray();
String result = combineNodeText(nodes);
return result;
}
//合并節(jié)點的有效內(nèi)容
private static String combineNodeText(Node[] nodes)
{
StringBuffer result = new StringBuffer();
for (int i = 0; i < nodes.length; i++)
{
Node anode = (Node) nodes[i];
String line = "";
if (anode instanceof TextNode)
{
TextNode textnode = (TextNode) anode;
//line = textnode.toPlainTextString().trim();
line = textnode.getText();
}
else if (anode instanceof LinkTag)
{
LinkTag linknode = (LinkTag) anode;
line = linknode.getLink();
//過濾jsp標簽
line = StringFunc.replace(line, "<%.*%>", "");
}
if (StringFunc.isTrimEmpty(line)) continue;
result.append(" ").append(line);
}
return result.toString();
} |