FancyKing

第1关:清洗HTML文档中无意义数据

Apr 3rd, 2020
353
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Java 1.02 KB | None | 0 0
  1. package step1;
  2. import java.io.File;
  3. import java.io.IOException;
  4. import java.util.ArrayList;
  5. import java.util.List;
  6. import org.jsoup.Jsoup;
  7. import org.jsoup.nodes.Document;
  8. import org.jsoup.safety.Whitelist;
  9. public class Task {
  10.    
  11.     //通过filePath文件路径获取Docment对象
  12.     public Document getDoc(String filePath) throws IOException{
  13.         /**********   Begin   **********/
  14.         File input = new File(filePath);
  15.         Document document =Jsoup.parse(input,"UTF-8","http://www.ctrip.com/");
  16.         return document;
  17.         /**********   End   **********/
  18.     }
  19.  
  20.     /**
  21.      * 获取清理后的信息
  22.      * @param doc
  23.      * @return
  24.      */
  25.     public List<String> cleanHTML(Document doc){
  26.         /**********   Begin   **********/
  27.        
  28.         List<String> tmp=new ArrayList<>();
  29.         String tmpb =Jsoup.clean(doc.toString() ,Whitelist.basic());
  30.         String tmpc =Jsoup.clean(doc.toString() ,Whitelist.simpleText());
  31.         tmp.add(tmpb);
  32.         tmp.add(tmpc);
  33.         return tmp;
  34.         /**********   End   **********/
  35.     }
  36.    
  37. }
Advertisement
Add Comment
Please, Sign In to add comment