Java HTML Parse Jsoup getContentFromHTML(String html)

Description

get Content From HTML

License

Apache License

Declaration

public static String getContentFromHTML(String html) 

Method Source Code

//package com.java2s;
/*//from   www  .  j a  va  2s  .c o m
Designed and developed by Ismail E. Kartoglu
Copyright 2015 King's College London
    
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
    
http://www.apache.org/licenses/LICENSE-2.0
    
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
 */

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;

public class Main {
    public static String getContentFromHTML(String html) {
        Document doc = Jsoup.parse(html);
        return doc.body().text();
    }
}

Related

1. clearBody(String html)
2. coverTag(String html, String... tagNames)
3. extractRssUrl(String html, URI base)
4. filter(String html)
5. fixHtml(String htmlContent, String outputFile, String contentFile)
6. getDistinctImageUrls(String htmlContent)
7. getDoc(Connection conn)
8. getDoc(File file)
9. getDoc(String path)