Java HTML Parse Jsoup getExplanation(String html)

Here you can find the source of getExplanation(String html)

Description

get Explanation

License

Apache License

Declaration

public static String getExplanation(String html) 

Method Source Code

//package com.java2s;
/*//w  w  w  .j a v  a 2s .  com
 Copyright 2015 Joseph Tranquillo {name of copyright owner}

 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;

public class Main {
    private static final String EXPLANATION = "Explanation:";
    private static final String TOMORROWS_PIC = "Tomorrow's picture";
    private static final String WE_KEEP_AN_ARCHIVE = "We keep an archive";

    public static String getExplanation(String html) {
        String text = Jsoup.parse(html).text();

        int indexof_explanation = -1;
        int indexof_tomorrowspic = -1;
        int indexof_wekeepanarchive = -1;

        indexof_explanation = text.indexOf(EXPLANATION);
        indexof_tomorrowspic = text.indexOf(TOMORROWS_PIC);
        indexof_wekeepanarchive = text.indexOf(WE_KEEP_AN_ARCHIVE);

        if (indexof_explanation == -1
                || (indexof_tomorrowspic == -1 && indexof_wekeepanarchive == -1)) {
            return null;
        }

        String explanation = null;

        if (indexof_tomorrowspic != -1) {
            explanation = text.substring(1 + indexof_explanation
                    + EXPLANATION.length(), indexof_tomorrowspic);
        } else if (indexof_wekeepanarchive != -1) {
            explanation = text.substring(1 + indexof_explanation
                    + EXPLANATION.length(), indexof_wekeepanarchive);
        }

        explanation = explanation.replace("\n", " ");
        explanation = explanation.replace("[s]+", " ");
        explanation = explanation.trim();

        return explanation;
    }
}

Related

  1. getDoc(File file)
  2. getDoc(String path)
  3. getDoc(String url)
  4. getDoctypeName(InputStream s)
  5. getErrorMessage(String htmlStr)
  6. getFirstImageSrc(String html)
  7. getFirstSentence(final String html)
  8. getFirstTableFromHTML(String result)
  9. getHtml(String url, String ruta_fich)