X-Git-Url: https://git.pterodactylus.net/?a=blobdiff_plain;f=src%2Fmain%2Fjava%2Fnet%2Fpterodactylus%2Frhynodge%2Ffilters%2FComicSiteFilter.java;h=1d9e6f7273c34a6e48a82751be9067cd6896d5d6;hb=69d447cc799fe71306d66a495e53698f0bab77c1;hp=5f6a11e016fde3a5e313cef9f8633b7a8a91ea10;hpb=0279bd0b97ae8353d4cfd114214cafd7e6f8f3ae;p=rhynodge.git diff --git a/src/main/java/net/pterodactylus/rhynodge/filters/ComicSiteFilter.java b/src/main/java/net/pterodactylus/rhynodge/filters/ComicSiteFilter.java index 5f6a11e..1d9e6f7 100644 --- a/src/main/java/net/pterodactylus/rhynodge/filters/ComicSiteFilter.java +++ b/src/main/java/net/pterodactylus/rhynodge/filters/ComicSiteFilter.java @@ -17,14 +17,18 @@ package net.pterodactylus.rhynodge.filters; -import static com.google.common.base.Preconditions.*; +import static com.google.common.base.Preconditions.checkArgument; +import java.net.URI; +import java.net.URISyntaxException; import java.util.List; import net.pterodactylus.rhynodge.Filter; import net.pterodactylus.rhynodge.State; import net.pterodactylus.rhynodge.states.ComicState; import net.pterodactylus.rhynodge.states.ComicState.Comic; +import net.pterodactylus.rhynodge.states.ComicState.Strip; +import net.pterodactylus.rhynodge.states.FailedState; import net.pterodactylus.rhynodge.states.HtmlState; import com.google.common.base.Optional; @@ -44,19 +48,32 @@ public abstract class ComicSiteFilter implements Filter { /* initialize states: */ HtmlState htmlState = (HtmlState) state; - ComicState comicState = new ComicState(); /* extract comics. */ Optional title = extractTitle(htmlState.document()); List imageUrls = extractImageUrls(htmlState.document()); + List imageComments = extractImageComments(htmlState.document()); /* store comic, if found, into state. */ - if (title.isPresent() && !imageUrls.isEmpty()) { - Comic comic = new Comic(title.get()); - for (String imageUrl : imageUrls) { - comic.addImageUrl(imageUrl); + if (!title.isPresent() || imageUrls.isEmpty()) { + return new FailedState(); + } + + ComicState comicState = new ComicState(); + Comic comic = new Comic(title.get()); + int imageCounter = 0; + for (String imageUrl : imageUrls) { + String imageComment = (imageCounter < imageComments.size()) ? imageComments.get(imageCounter) : ""; + try { + URI stripUri = new URI(htmlState.uri()).resolve(imageUrl); + Strip strip = new Strip(stripUri.toString(), imageComment); + imageCounter++; + comic.add(strip); + } catch (URISyntaxException use1) { + throw new IllegalStateException(String.format("Could not resolve image URL “%s” against base URL “%s”.", imageUrl, htmlState.uri()), use1); } } + comicState.add(comic); return comicState; } @@ -85,4 +102,16 @@ public abstract class ComicSiteFilter implements Filter { */ protected abstract List extractImageUrls(Document document); + /** + * Extracts the image comments from the given document. The elements of this + * last and of the list returned by {@link #extractImageUrls(org.jsoup.nodes.Document)} + * are paired up and added as {@link Strip}s. If the list returned by this + * method has less elements, an empty string is used for the remaining images. + * + * @param document + * The document to extract the image comments from + * @return The extracted image comments + */ + protected abstract List extractImageComments(Document document); + }