解析 XML 时出现不匹配的标记异常

Question

这已经成为我背后的真正痛苦。

我要解析的 URL 是 http://torrentz.eu/feed_verifiedP?q=ubuntu

这是 xml 的简短版本：

<?xml version="1.0"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
 <channel>
  <title>Torrentz - ubuntu</title>
  <link>http://torrentz.eu/verified?q=ubuntu</link>
  <description>ubuntu search</description>
  <language>en-us</language>
  <atom:link href="http://torrentz.eu/feed_verifiedP?q=ubuntu" rel="self" type="application/rss+xml" />
  <item>
     <title>ubuntu 11 10 desktop i386 iso</title>
     <link>http://torrentz.eu/8ac3731ad4b039c05393b5404afa6e7397810b41</link>
     <guid>http://torrentz.eu/8ac3731ad4b039c05393b5404afa6e7397810b41</guid>
     <pubDate>Thu, 13 Oct 2011 15:02:06 +0000</pubDate>
     <category>apps linux applications os software</category>
     <description>Size: 695 MB Seeds: 4,613 Peers: 161 Hash: 8ac3731ad4b039c05393b5404afa6e7397810b41</description>
  </item>
 </channel>
</rss>

我的代码：

    SAXParserFactory spf = SAXParserFactory.newInstance();
    SAXParser sp = spf.newSAXParser();
    XMLReader xr = sp.getXMLReader();

    //Get Torrents
    XMLTorrentsRSSHandler torrentsHandler = new XMLTorrentsRSSHandler();
    xr.setContentHandler(torrentsHandler);
    InputStream in = url.openStream();
    xr.parse(new InputSource(in));
    XMLTorrentsRSSParsedDataSet parsedTorrentsDataSet = torrentsHandler.getParsedData();

我不断收到此异常：

org.apache.harmony.xml.ExpatParser$ParseException: At line 1, column 53: mismatched tag

为什么翻转会这样折磨我！？

编辑：这种方法直到今天都运行良好。也许网站发生了变化，但是这个不匹配的标签在哪里？

Answer 1

为什么在构建路径上使用 Harmony？您的代码可以与 Oracle JDK7u3 中的内置 SAXParser 一起正常工作。如果没有理由使用 Harmony 实现，您应该恢复到标准实现。

测试用例形式：

import java.io.IOException;
import java.io.StringReader;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;

class Scratch {
    public static void main(String[] args) throws IOException, SAXException, ParserConfigurationException {
        final String document = "<?xml version=\"1.0\"?>\n" +
                "<rss version=\"2.0\" xmlns:atom=\"http://www.w3.org/2005/Atom\">\n" +
                " <channel>\n" +
                "  <title>Torrentz - ubuntu</title>\n" +
                "  <link>http://torrentz.eu/verified?q=ubuntu</link>\n" +
                "  <description>ubuntu search</description>\n" +
                "  <language>en-us</language>\n" +
                "  <atom:link href=\"http://torrentz.eu/feed_verifiedP?q=ubuntu\" rel=\"self\" type=\"application/rss+xml\" />\n" +
                "  <item>\n" +
                "     <title>ubuntu 11 10 desktop i386 iso</title>\n" +
                "     <link>http://torrentz.eu/8ac3731ad4b039c05393b5404afa6e7397810b41</link>\n" +
                "     <guid>http://torrentz.eu/8ac3731ad4b039c05393b5404afa6e7397810b41</guid>\n" +
                "     <pubDate>Thu, 13 Oct 2011 15:02:06 +0000</pubDate>\n" +
                "     <category>apps linux applications os software</category>\n" +
                "     <description>Size: 695 MB Seeds: 4,613 Peers: 161 Hash: 8ac3731ad4b039c05393b5404afa6e7397810b41</description>\n" +
                "  </item>\n" +
                " </channel>\n" +
                "</rss>\n";

        SAXParserFactory spf = SAXParserFactory.newInstance();
        SAXParser sp = spf.newSAXParser();
        XMLReader xr = sp.getXMLReader();

        ContentHandler torrentsHandler = new DefaultHandler() {
            @Override
            public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
                System.out.printf("%s / %s / %s\n", uri, localName, qName);
            }
        };
        xr.setContentHandler(torrentsHandler);
        xr.parse(new InputSource(new StringReader(document)));
    }
}