2 * rhynodge - ComicFilter.java - Copyright © 2013 David Roden
4 * This program is free software: you can redistribute it and/or modify
5 * it under the terms of the GNU General Public License as published by
6 * the Free Software Foundation, either version 3 of the License, or
7 * (at your option) any later version.
9 * This program is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details.
14 * You should have received a copy of the GNU General Public License
15 * along with this program. If not, see <http://www.gnu.org/licenses/>.
18 package net.pterodactylus.rhynodge.filters;
20 import static com.google.common.base.Preconditions.*;
22 import java.util.List;
24 import net.pterodactylus.rhynodge.Filter;
25 import net.pterodactylus.rhynodge.State;
26 import net.pterodactylus.rhynodge.states.ComicState;
27 import net.pterodactylus.rhynodge.states.ComicState.Comic;
28 import net.pterodactylus.rhynodge.states.HtmlState;
30 import com.google.common.base.Optional;
31 import org.jsoup.nodes.Document;
34 * {@link Filter} implementation that can extract {@link ComicState}s from
37 * @author <a href="mailto:bombe@pterodactylus.net">David ‘Bombe’ Roden</a>
39 public abstract class ComicSiteFilter implements Filter {
42 public State filter(State state) {
43 checkArgument(state instanceof HtmlState, "state must be an HTML state");
45 /* initialize states: */
46 HtmlState htmlState = (HtmlState) state;
47 ComicState comicState = new ComicState();
50 Optional<String> title = extractTitle(htmlState.document());
51 List<String> imageUrls = extractImageUrls(htmlState.document());
53 /* store comic, if found, into state. */
54 if (title.isPresent() && !imageUrls.isEmpty()) {
55 Comic comic = new Comic(title.get());
56 for (String imageUrl : imageUrls) {
57 comic.addImageUrl(imageUrl);
69 * Extracts the title of the comic from the given document.
72 * The document to extract the title from
73 * @return The extracted title, or {@link Optional#absent()}} if no title could
76 protected abstract Optional<String> extractTitle(Document document);
79 * Extracts the image URLs from the given document.
82 * The document to extract the image URLs from
83 * @return The extracted image URLs, or an empty list if no URLs could be
86 protected abstract List<String> extractImageUrls(Document document);