commit
f742ebda79
@ -20,15 +20,36 @@ import java.util.regex.Pattern;
|
|||||||
|
|
||||||
public class NhentaiRipper extends AbstractHTMLRipper {
|
public class NhentaiRipper extends AbstractHTMLRipper {
|
||||||
|
|
||||||
// All sleep times are in milliseconds
|
|
||||||
private static final int IMAGE_SLEEP_TIME = 1500;
|
|
||||||
|
|
||||||
private String albumTitle;
|
private String albumTitle;
|
||||||
private Document firstPage;
|
private Document firstPage;
|
||||||
|
|
||||||
// Thread pool for finding direct image links from "image" pages (html)
|
// Thread pool for finding direct image links from "image" pages (html)
|
||||||
private DownloadThreadPool nhentaiThreadPool = new DownloadThreadPool("nhentai");
|
private DownloadThreadPool nhentaiThreadPool = new DownloadThreadPool("nhentai");
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public boolean hasQueueSupport() {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public boolean pageContainsAlbums(URL url) {
|
||||||
|
Pattern pa = Pattern.compile("^https?://nhentai\\.net/tag/([a-zA-Z0-9_\\-]+)/?");
|
||||||
|
Matcher ma = pa.matcher(url.toExternalForm());
|
||||||
|
if (ma.matches()) {
|
||||||
|
return true;
|
||||||
|
}
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
|
||||||
|
@Override
|
||||||
|
public List<String> getAlbumsToQueue(Document doc) {
|
||||||
|
List<String> urlsToAddToQueue = new ArrayList<>();
|
||||||
|
for (Element elem : doc.select("a.cover")) {
|
||||||
|
urlsToAddToQueue.add("https://" + getDomain() + elem.attr("href"));
|
||||||
|
}
|
||||||
|
return urlsToAddToQueue;
|
||||||
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public DownloadThreadPool getThreadPool() {
|
public DownloadThreadPool getThreadPool() {
|
||||||
return nhentaiThreadPool;
|
return nhentaiThreadPool;
|
||||||
@ -129,84 +150,17 @@ public class NhentaiRipper extends AbstractHTMLRipper {
|
|||||||
@Override
|
@Override
|
||||||
public List<String> getURLsFromPage(Document page) {
|
public List<String> getURLsFromPage(Document page) {
|
||||||
List<String> imageURLs = new ArrayList<>();
|
List<String> imageURLs = new ArrayList<>();
|
||||||
Elements thumbs = page.select(".gallerythumb");
|
Elements thumbs = page.select("a.gallerythumb > img");
|
||||||
for (Element el : thumbs) {
|
for (Element el : thumbs) {
|
||||||
String imageUrl = el.attr("href");
|
imageURLs.add(el.attr("data-src").replaceAll("t\\.n", "i.n").replaceAll("t\\.", "."));
|
||||||
imageURLs.add("https://nhentai.net" + imageUrl);
|
|
||||||
}
|
}
|
||||||
return imageURLs;
|
return imageURLs;
|
||||||
}
|
}
|
||||||
|
|
||||||
@Override
|
@Override
|
||||||
public void downloadURL(URL url, int index) {
|
public void downloadURL(URL url, int index) {
|
||||||
NHentaiImageThread t = new NHentaiImageThread(url, index, this.workingDir);
|
addURLToDownload(url, getPrefix(index), "", this.url.toExternalForm(), null);
|
||||||
nhentaiThreadPool.addThread(t);
|
|
||||||
try {
|
|
||||||
Thread.sleep(IMAGE_SLEEP_TIME);
|
|
||||||
} catch (InterruptedException e) {
|
|
||||||
logger.warn("Interrupted while waiting to load next image", e);
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
|
|
||||||
private class NHentaiImageThread extends Thread {
|
|
||||||
|
|
||||||
private URL url;
|
|
||||||
private int index;
|
|
||||||
private File workingDir;
|
|
||||||
|
|
||||||
NHentaiImageThread(URL url, int index, File workingDir) {
|
|
||||||
super();
|
|
||||||
this.url = url;
|
|
||||||
this.index = index;
|
|
||||||
this.workingDir = workingDir;
|
|
||||||
}
|
|
||||||
|
|
||||||
@Override
|
|
||||||
public void run() {
|
|
||||||
fetchImage();
|
|
||||||
}
|
|
||||||
|
|
||||||
private void fetchImage() {
|
|
||||||
try {
|
|
||||||
//Document doc = getPageWithRetries(this.url);
|
|
||||||
Document doc = Http.url(this.url).get();
|
|
||||||
|
|
||||||
// Find image
|
|
||||||
Elements images = doc.select("#image-container > a > img");
|
|
||||||
if (images.size() == 0) {
|
|
||||||
// Attempt to find image elsewise (Issue #41)
|
|
||||||
images = doc.select("img#img");
|
|
||||||
if (images.size() == 0) {
|
|
||||||
logger.warn("Image not found at " + this.url);
|
|
||||||
return;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
Element image = images.first();
|
|
||||||
String imgsrc = image.attr("src");
|
|
||||||
logger.info("Found URL " + imgsrc + " via " + images.get(0));
|
|
||||||
|
|
||||||
Pattern p = Pattern.compile("^https?://i.nhentai.net/galleries/\\d+/(.+)$");
|
|
||||||
Matcher m = p.matcher(imgsrc);
|
|
||||||
if (m.matches()) {
|
|
||||||
// Manually discover filename from URL
|
|
||||||
String savePath = this.workingDir + File.separator;
|
|
||||||
if (Utils.getConfigBoolean("download.save_order", true)) {
|
|
||||||
savePath += String.format("%03d_", index);
|
|
||||||
}
|
|
||||||
savePath += m.group(1);
|
|
||||||
addURLToDownload(new URL(imgsrc), new File(savePath));
|
|
||||||
} else {
|
|
||||||
// Provide prefix and let the AbstractRipper "guess" the filename
|
|
||||||
String prefix = "";
|
|
||||||
if (Utils.getConfigBoolean("download.save_order", true)) {
|
|
||||||
prefix = String.format("%03d_", index);
|
|
||||||
}
|
|
||||||
addURLToDownload(new URL(imgsrc), prefix);
|
|
||||||
}
|
|
||||||
} catch (IOException e) {
|
|
||||||
logger.error("[!] Exception while loading/parsing " + this.url, e);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
}
|
}
|
||||||
}
|
|
||||||
|
Loading…
Reference in New Issue
Block a user