import java.io.IOException;
import java.util.logging.Level;
import java.util.logging.Logger;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
public class JavaApplication14 {
public static void main(String[] args) {
try {
Document doc = Jsoup.connect("tanmoy_mahathir.makes.org/thimble/146").get();
String html= "<html><head></head>" + "<body><p>Parsed HTML into a doc."
+ "</p></body></html>";
Elements paragraphs = doc.select("p");
for(Element p : paragraphs)
System.out.println(p.text());
} catch (IOException ex) {
Logger.getLogger(JavaApplication14.class.getName()).log(Level.SEVERE, null, ex);
}
}
}
任何人都可以帮我解决jsoup代码如何解析包括段落的部分,以便只打印
Hello ,World!
Nothing is impossible
对于这一小部分 html，您只需要做
String html= "<html><head></head>" + "<body><p>Parsed HTML into a doc."+
+"</p></body></html>";
Document doc = Jsoup.parse(html);
Elements paragraphs = doc.select("p");
for(Element p : paragraphs)
System.out.println(p.text());
正如我看到你的链接包含几乎相同的 html 你也可以doc用
Document doc = Jsoup.connect("https://tanmoy_mahathir.makes.org/thimble/146").get();
更新
这是对我来说编译和运行良好的完整代码。
import java.io.IOException;
import java.util.logging.*;
import org.jsoup.*;
import org.jsoup.nodes.*;
import org.jsoup.select.*;
public class JavaApplication14 {
public static void main(String[] args) {
try {
String url = "https://tanmoy_mahathir.makes.org/thimble/146";
Document doc = Jsoup.connect(url).get();
Elements paragraphs = doc.select("p");
for(Element p : paragraphs)
System.out.println(p.text());
}
catch (IOException ex) {
Logger.getLogger(JavaApplication14.class.getName())
.log(Level.SEVERE, null, ex);
}
}
}