我有一个包含以下html代码的字符串:
...
...
<style>
v\:* {behavior:url(#default#VML);}
o\:* {behavior:url(#default#VML);}
w\:* {behavior:url(#default#VML);}
.shape {behavior:url(#default#VML);}
</style>
<xml>
<w:WordDocument>
<w:View>Normal</w:View>
<w:Zoom>0</w:Zoom>
<w:TrackMoves>false</w:TrackMoves>
</xml>
...
...
当我申请时
string.select("style").remove();
string.select("xml").remove();
似乎没有任何事情发生。我做错了什么?我想完全删除这些标签,包括其内容。
答案 0 :(得分:0)
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.parser.Parser;
public class Main {
public static void main(String[] args) {
try {
String xmlStr = "<style>" +
"v\\:* {behavior:url(#default#VML);}" +
"o\\:* {behavior:url(#default#VML);}" +
"w\\:* {behavior:url(#default#VML);}" +
".shape {behavior:url(#default#VML);}" +
"</style>" +
"<xml>" +
"<w:WordDocument>" +
"<w:View>Normal</w:View>" +
"<w:Zoom>0</w:Zoom>" +
"<w:TrackMoves>false</w:TrackMoves>" +
"</xml>";
Document doc = Jsoup.parse(xmlStr, "", Parser.xmlParser());
doc.select("style").remove();
System.out.println(doc);
} catch (Exception e) {
e.printStackTrace();
}
}
}
<强>输出强>
<xml>
<w:worddocument>
<w:view>
Normal
</w:view>
<w:zoom>
0
</w:zoom>
<w:trackmoves>
false
</w:trackmoves>
</w:worddocument> //Added by jsoup during normalization of the xml document
</xml>