Java 使用jsoup提取html代码-两个相邻的span标记

我的html代码如下所示：

<div class="cloud recommended">
    <div id="bigcloud" class="eventwithfoto">
        <h1>Artist Name</h1>
        <div id="eventphoto">
            <a href="http://linkToPhoto.jpg" target="_top" rel="lightbox"><img src="http://linkToPhoto.jpg" height="150"></a>
        </div>

        <div id="eventmain" style="margin-top: 12px;">
            <p id="eventwhere"><span><b>Name of place<br></b></span><span>Address of place</span>
            <br> tel.: +48 111 222 111 <br><a href="http://www.linktoplace.com" target="_blank">http://www.linktoplace.com</a> </p>
            <p id="eventdate">2017-04-20 godz. 20:00</p>


            <div id="eventadmission">
                120 zł
            </div>

        </div>

        <div class="clear"></div>
        <div id="eventdesc">
            Here is some descr<br/>Some other descr 
            <div class="clear"></div>

            <br>
                <a href="http://link.com" target="_blank">link to event</a>
        </div>
    </div>
</div>

但每个字符串都是空的。我做错了什么？

---

如何解析这种特定的html格式来获取这些变量？

编写了一个小示例来演示：

package sandbox.jsoup;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class JsoupMain {
    private final String HTML = "<div class=\"cloud recommended\">\n" +
            "    <div id=\"bigcloud\" class=\"eventwithfoto\">\n" +
            "        <h1>Artist Name</h1>\n" +
            "        <div id=\"eventphoto\">\n" +
            "            <a href=\"http://linkToPhoto.jpg\" target=\"_top\" rel=\"lightbox\"><img src=\"http://linkToPhoto.jpg\" height=\"150\"></a>\n" +
            "        </div>\n" +
            "\n" +
            "        <div id=\"eventmain\" style=\"margin-top: 12px;\">\n" +
            "            <p id=\"eventwhere\"><span><b>Name of place<br></b></span><span>Address of place</span>\n" +
            "            <br> tel.: +48 111 222 111 <br><a href=\"http://www.linktoplace.com\" target=\"_blank\">http://www.linktoplace.com</a> </p>\n" +
            "            <p id=\"eventdate\">2017-04-20 godz. 20:00</p>\n" +
            "\n" +
            "\n" +
            "            <div id=\"eventadmission\">\n" +
            "                120 zł\n" +
            "            </div>\n" +
            "\n" +
            "        </div>\n" +
            "\n" +
            "        <div class=\"clear\"></div>\n" +
            "        <div id=\"eventdesc\">\n" +
            "            Here is some descr<br/>Some other descr \n" +
            "            <div class=\"clear\"></div>\n" +
            "\n" +
            "            <br>\n" +
            "                <a href=\"http://link.com\" target=\"_blank\">link to event</a>\n" +
            "        </div>\n" +
            "    </div>\n" +
            "</div>";

    public static void main(String[] args) {
        new JsoupMain().findTwoSpans();
    }

    private void findTwoSpans() {
        Document doc = Jsoup.parse(HTML);
        Element eventWhere = doc.getElementById("eventwhere");
        Elements spans = eventWhere.select("span");
        System.out.println("span[0]="+spans.get(0).text());
        Element spanTwo = spans.get(1);
        System.out.println("span[1]="+spanTwo.text());

        // Get phone
        Element eventMain = doc.getElementById("eventmain");
        String textMain = eventMain.after(spanTwo).after("br").text();

        int beginPos = textMain.indexOf("tel.: ");
        int endPos = textMain.indexOf(" http://");
        if (beginPos>0 && endPos>0) {
            String phone = textMain.substring(beginPos+6, endPos);
            System.out.println("Found phone: "+phone);
        }
        else {
            System.out.println("Phone not found: "+textMain);
        }
    }
}

---

尝试使用nextSiblingElement（）-找到第一个跨度后，迭代直到找到下一个跨度。@AlexC谢谢你的提示！目前，我只能看到

eventName

，您能帮助我并告诉我显示其他元素时我做错了什么吗？CSS3选择器可以选择第n个子元素，可能类似于：“#eventwhere>span:nth child（2）>b”我必须测试这个，但您可以通过CSS选择器进行测试，或者您可以找到doc.getElementsByTag（“#eventwhere”）。选择(“span”）.getnextSiblingElement（）（如果不存在，则检查空值等），因此我不确定我做错了什么，因为现在甚至

doc.getElementsByTag（“#eventwhere”）.select（“span”）.text（）

这将返回空字符串：（谢谢男人：）还有一个问题-你能看看我原来的html代码，告诉我如何提取手机号码吗？更新了手机的“低技术”提取代码。

package sandbox.jsoup;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class JsoupMain {
    private final String HTML = "<div class=\"cloud recommended\">\n" +
            "    <div id=\"bigcloud\" class=\"eventwithfoto\">\n" +
            "        <h1>Artist Name</h1>\n" +
            "        <div id=\"eventphoto\">\n" +
            "            <a href=\"http://linkToPhoto.jpg\" target=\"_top\" rel=\"lightbox\"><img src=\"http://linkToPhoto.jpg\" height=\"150\"></a>\n" +
            "        </div>\n" +
            "\n" +
            "        <div id=\"eventmain\" style=\"margin-top: 12px;\">\n" +
            "            <p id=\"eventwhere\"><span><b>Name of place<br></b></span><span>Address of place</span>\n" +
            "            <br> tel.: +48 111 222 111 <br><a href=\"http://www.linktoplace.com\" target=\"_blank\">http://www.linktoplace.com</a> </p>\n" +
            "            <p id=\"eventdate\">2017-04-20 godz. 20:00</p>\n" +
            "\n" +
            "\n" +
            "            <div id=\"eventadmission\">\n" +
            "                120 zł\n" +
            "            </div>\n" +
            "\n" +
            "        </div>\n" +
            "\n" +
            "        <div class=\"clear\"></div>\n" +
            "        <div id=\"eventdesc\">\n" +
            "            Here is some descr<br/>Some other descr \n" +
            "            <div class=\"clear\"></div>\n" +
            "\n" +
            "            <br>\n" +
            "                <a href=\"http://link.com\" target=\"_blank\">link to event</a>\n" +
            "        </div>\n" +
            "    </div>\n" +
            "</div>";

    public static void main(String[] args) {
        new JsoupMain().findTwoSpans();
    }

    private void findTwoSpans() {
        Document doc = Jsoup.parse(HTML);
        Element eventWhere = doc.getElementById("eventwhere");
        Elements spans = eventWhere.select("span");
        System.out.println("span[0]="+spans.get(0).text());
        Element spanTwo = spans.get(1);
        System.out.println("span[1]="+spanTwo.text());

        // Get phone
        Element eventMain = doc.getElementById("eventmain");
        String textMain = eventMain.after(spanTwo).after("br").text();

        int beginPos = textMain.indexOf("tel.: ");
        int endPos = textMain.indexOf(" http://");
        if (beginPos>0 && endPos>0) {
            String phone = textMain.substring(beginPos+6, endPos);
            System.out.println("Found phone: "+phone);
        }
        else {
            System.out.println("Phone not found: "+textMain);
        }
    }
}

span[0]=Name of place
span[1]=Address of place
Found phone: +48 111 222 111