Java HTML Parse Jsoup getDistinctImageUrls(String htmlContent)

Description

Finds all image inclusions (looks for img tags).

License

Apache License

Parameter

Parameter	Description
htmlContent	the html content that may contain image files

Return

the list of found images (paths only) or empty if nothing found

Declaration

public static List<String> getDistinctImageUrls(String htmlContent) 

Method Source Code

//package com.java2s;
//License from project: Apache License 

import java.util.ArrayList;
import java.util.List;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class Main {
    private static final String IMG_SELECTOR = "img";
    private static final String SRC_ATTR = "src";

    /**//  w  ww.  ja va2s.c o  m
     * Finds all image inclusions (looks for <code>img</code> tags). Returns
     * only the path or URL to the image. If the several images have the same
     * path, the path is present in the list only one time.
     * 
     * @param htmlContent
     *            the html content that may contain image files
     * @return the list of found images (paths only) or empty if nothing found
     */
    public static List<String> getDistinctImageUrls(String htmlContent) {
        Document doc = Jsoup.parse(htmlContent);
        Elements els = doc.select(IMG_SELECTOR);
        List<String> images = new ArrayList<>(els.size());
        for (Element e : els) {
            String path = e.attr(SRC_ATTR);
            if (!images.contains(path)) {
                images.add(path);
            }
        }
        return images;
    }
}

Related

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