Jsoup进行网页的抓取

引入Jsoup和分词器的JAR包

<dependency>
	<groupId>org.jsoup</groupId>
	<artifactId>jsoup</artifactId>
	<version>1.10.2</version>
</dependency>
<!--分词-->
		<!-- https://mvnrepository.com/artifact/com.hankcs/hanlp -->
		<dependency>
			<groupId>com.hankcs</groupId>
			<artifactId>hanlp</artifactId>
			<version>portable-1.7.2</version>
		</dependency>

工具类

import com.hankcs.hanlp.HanLP;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

import java.io.IOException;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class HtmlUtil {
    private static String url ="https://www.baidu.com/s";
    public static void main(String[] args) {
        String rela = GetRela("哥哥的儿子");
        System.out.println(rela);
    }
    public static String GetRela(String wd) {
        StringBuffer English=new StringBuffer();
        StringBuffer Chinese=new StringBuffer();
        try {
            Document doc = Jsoup.connect(url+"?wd="+wd+"怎么称呼") .get();
            Elements body = doc.getElementsByTag("body");
            for (Element Text : body) {
                String text = Text.text();
                for(int i=0;i<text.length();i++) {
                    char c=text.charAt(i);
                    if(c >= 0x4E00 &&  c <= 0x9FA5) {
                        Chinese.append(c);
                    }
                    else if ((c>='a' && c<='z') || (c>='A' && c<='Z') || c==' ') {
                        English.append(c);
                    }
                }
            }
        }
        catch (IOException e) {
            e.printStackTrace();
        }
        String EnglishText=new String(English);
        String ChineseText=new String(Chinese);
        String code = null;
        String regString = ""+wd+"怎么称呼"+"([\\d\\D]*)来自百度百科";
        Pattern pattern = Pattern.compile(regString);
        Matcher matcher = pattern.matcher(ChineseText);
        if (matcher.find()) {
            code = matcher.group(1);
            List<String> list = HanLP.extractKeyword(code, 2);
            return list.get(0);
        }
        return null;
    }
}