lexer html解析一个js过滤的改进 - JAVA

;script> 或者
然后在parseString中修改其解析方法就可以了，下面是完整的代码：
Java代码
import java.net.URLConnection;

import org.htmlparser.Node;
import org.htmlparser.lexer.Lexer;
import org.htmlparser.lexer.Page;
import org.htmlparser.nodes.TagNode;
import org.htmlparser.util.ParserException;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
* @author edwardpro
*
*/
public class LexerFixed extends Lexer {
private static final Logger logger = LoggerFactory
.getLogger(LexerFixed.class);

/**
*
*/
private static final long serialVersionUID = 8425806017089419815L;

//script标签标记，如果发现当前在script里就掠过所有的< >
private int script=0;

/**
*
*/
public LexerFixed() {
super();
}

/**
* @param page
*/
public LexerFixed(Page page) {
super(page);
}

/**
* @param text
*/
public LexerFixed(String text) {
super(text);
}

/**
* @param connection
* @throws ParserException
*/
public LexerFixed(URLConnection connection) throws ParserException {
super(connection);
}

@Override
public Node nextNode(boolean quotesmart) throws ParserException {
Node ret = super.nextNode(quotesmart);
checkTag(ret);
return (ret);
}

/**
* checkTag用于修改tagNode的方法当有入参数时都会进行一次参数修正另外容行一下escape操作且行判是否存在已 escape的象

*
* @param node
*/
private void checkTag(Node node) {
if (node != null && node instanceof TagNode
&& !((TagNode) node).isEmptyXmlTag()) {
String tagName = ((TagNode) node).getTagName();
if("SCRIPT".equalsIgnoreCase(tagName)){
if (!((TagNode) node).isEndTag() ) {
this.script=1;
} else{
this.script=0;
}
}
}
}

@Override
protected Node parseString(int start, boolean quotesmart)
throws ParserException {
boolean done;
char ch;
char quote;

done = false;
quote = 0;
while (!done) {
ch = mPage.getCharacter(mCursor);
if (Page.EOF == ch)
done = true;
else if (0x1b == ch) // escape
{
ch = mPage.getCharacter(mCursor);
if (Page.EOF == ch)
done = true;
else if ('$' == ch) {
ch = mPage.getCharacter(mCursor);
if (Page.EOF == ch)
done = true;
// JIS X 0208-1978 and JIS X 0208-1983
else if ('@' == ch || 'B' == ch)
scanJIS(mCursor);
/*
* // JIS X 0212-1990 else if ('(' == ch) { ch =
* mPage.getCharacter (mCursor); if (Page.EOF == ch) done =
* true; else if ('D' == ch) scanJIS (mCursor); else {
* mPage.ungetCharacter (mCursor); mPage.ungetCharacter
* (mCursor); mPage.ungetCharacter (mCursor); } }
*/
else {
mPage.ungetCharacter(mCursor);
mPage.ungetCharacter(mCursor);
}
} else
mPage.ungetCharacter(mCursor);
} else if (quotesmart && (0 == quote)
&& (('\'' == ch) || ('"' == ch)))
quote = ch; // enter quoted state
// patch from Gernot Fricke to handle escaped closing quote
else if (quotesmart && (0 != quote) && ('\\' == ch)) {
ch = mPage.getCharacter(mCursor); // try to consume escape
if ((Page.EOF != ch) && ('\\' != ch) // escaped backslash
&& (ch != quote)) // escaped quote character
// ( reflects ["] or ['] whichever opened the quotation)
mPage.ungetCharacter(mCursor); // unconsume char if char not
// an escape
} else if (quotesmart && (ch == quo

lexer html解析一个js过滤的改进(二)