Gurkengewuerz/ImgScroll
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #592 from cyian-1756/quickQ

Browse Source 
Quick q
This commit is contained in:
cyian-1756 2018-05-16 11:42:41 -04:00 committed by GitHub
commit d8170fcf64
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 64 additions and 154 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
src/main/java/com/rarchives/ripme/ripper/AbstractHTMLRipper.java
View File

@ -11,6 +11,7 @@ import org.jsoup.nodes.Document;
import com.rarchives.ripme.ui.RipStatusMessage.STATUS;
import com.rarchives.ripme.utils.Utils;
import com.rarchives.ripme.ui.MainWindow;
/**
* Simplified ripper, designed for ripping from sites by parsing HTML.
@ -53,12 +54,29 @@ public abstract class AbstractHTMLRipper extends AlbumRipper {
protected boolean hasDescriptionSupport() {
return false;
}
protected String[] getDescription(String url, Document page) throws IOException {
throw new IOException("getDescription not implemented"); // Do I do this or make an abstract function?
}
protected int descSleepTime() {
return 100;
}
protected List<String> getAlbumsToQueue(Document doc) {
return null;
}
// If a page has Queue support then it has no images we want to download, just a list of urls we want to add to
// the queue
protected boolean hasQueueSupport() {
return false;
}
// Takes a url and checks if it is for a page of albums
protected boolean pageContainsAlbums(URL url) {
return false;
}
@Override
public void rip() throws IOException {
int index = 0;
@ -67,6 +85,16 @@ public abstract class AbstractHTMLRipper extends AlbumRipper {
sendUpdate(STATUS.LOADING_RESOURCE, this.url.toExternalForm());
Document doc = getFirstPage();
if (hasQueueSupport() && pageContainsAlbums(this.url)) {
List<String> urls = getAlbumsToQueue(doc);
for (String url : urls) {
MainWindow.addUrlToQueue(url);
}
// We set doc to null here so the while loop below this doesn't fire
doc = null;
}
while (doc != null) {
if (alreadyDownloadedUrls >= Utils.getConfigInteger("history.end_rip_after_already_seen", 1000000000) && !isThisATest()) {
sendUpdate(STATUS.DOWNLOAD_COMPLETE, "Already seen the last " + alreadyDownloadedUrls + " images ending rip");

185
src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaicomicsRipper.java
View File

@ -34,21 +34,18 @@ public class MyhentaicomicsRipper extends AbstractHTMLRipper {
Pattern p = Pattern.compile("^https?://myhentaicomics.com/index.php/([a-zA-Z0-9-]*)/?$");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
isTag = false;
return m.group(1);
}
Pattern pa = Pattern.compile("^https?://myhentaicomics.com/index.php/search\\?q=([a-zA-Z0-9-]*)([a-zA-Z0-9=&]*)?$");
Matcher ma = pa.matcher(url.toExternalForm());
if (ma.matches()) {
isTag = true;
return ma.group(1);
}
Pattern pat = Pattern.compile("^https?://myhentaicomics.com/index.php/tag/([0-9]*)/?([a-zA-Z%0-9+?=:]*)?$");
Matcher mat = pat.matcher(url.toExternalForm());
if (mat.matches()) {
isTag = true;
return mat.group(1);
}
@ -56,6 +53,37 @@ public class MyhentaicomicsRipper extends AbstractHTMLRipper {
"myhentaicomics.com/index.php/albumName - got " + url + " instead");
}
@Override
public boolean hasQueueSupport() {
return true;
}
@Override
public boolean pageContainsAlbums(URL url) {
Pattern pa = Pattern.compile("^https?://myhentaicomics.com/index.php/search\\?q=([a-zA-Z0-9-]*)([a-zA-Z0-9=&]*)?$");
Matcher ma = pa.matcher(url.toExternalForm());
if (ma.matches()) {
return true;
}
Pattern pat = Pattern.compile("^https?://myhentaicomics.com/index.php/tag/([0-9]*)/?([a-zA-Z%0-9+?=:]*)?$");
Matcher mat = pat.matcher(url.toExternalForm());
if (mat.matches()) {
isTag = true;
return true;
}
return false;
}
@Override
public List<String> getAlbumsToQueue(Document doc) {
List<String> urlsToAddToQueue = new ArrayList<>();
for (Element elem : doc.select(".g-album > a")) {
urlsToAddToQueue.add(getDomain() + elem.attr("href"));
}
return urlsToAddToQueue;
}
@Override
public Document getFirstPage() throws IOException {
// "url" is an instance field of the superclass
@ -81,161 +109,11 @@ public class MyhentaicomicsRipper extends AbstractHTMLRipper {
return Http.url(nextUrl).get();
}
// This replaces getNextPage when downloading from searchs and tags
private List<String> getNextAlbumPage(String pageUrl) {
List<String> albumPagesList = new ArrayList<>();
int pageNumber = 1;
albumPagesList.add("http://myhentaicomics.com/index.php/" + pageUrl.split("\\?")[0] + "?page=" + Integer.toString(pageNumber));
while (true) {
String urlToGet = "http://myhentaicomics.com/index.php/" + pageUrl.split("\\?")[0] + "?page=" + Integer.toString(pageNumber);
Document nextAlbumPage;
try {
logger.info("Grabbing " + urlToGet);
nextAlbumPage = Http.url(urlToGet).get();
} catch (IOException e) {
logger.warn("Failed to log link in Jsoup");
nextAlbumPage = null;
e.printStackTrace();
}
Element elem = nextAlbumPage.select("a.ui-icon-right").first();
String nextPage = elem.attr("href");
pageNumber = pageNumber + 1;
if (nextPage.equals("")) {
logger.info("Got " + pageNumber + " pages");
break;
}
else {
logger.info(nextPage);
albumPagesList.add(nextPage);
logger.info("Adding " + nextPage);
}
}
return albumPagesList;
}
private List<String> getAlbumsFromPage(String url) {
List<String> pagesToRip;
List<String> result = new ArrayList<>();
logger.info("Running getAlbumsFromPage");
Document doc;
try {
doc = Http.url("http://myhentaicomics.com" + url).get();
} catch (IOException e) {
logger.warn("Failed to log link in Jsoup");
doc = null;
e.printStackTrace();
}
// This for goes over every album on the page
for (Element elem : doc.select("li.g-album > a")) {
String link = elem.attr("href");
logger.info("Grabbing album " + link);
pagesToRip = getNextAlbumPage(link);
logger.info(pagesToRip);
for (String element : pagesToRip) {
Document album_doc;
try {
logger.info("grabbing " + element + " with jsoup");
boolean startsWithHttp = element.startsWith("http://");
if (!startsWithHttp) {
album_doc = Http.url("http://myhentaicomics.com/" + element).get();
}
else {
album_doc = Http.url(element).get();
}
} catch (IOException e) {
logger.warn("Failed to log link in Jsoup");
album_doc = null;
e.printStackTrace();
}
for (Element el :album_doc.select("img")) {
String imageSource = el.attr("src");
// This bool is here so we don't try and download the site logo
if (!imageSource.startsWith("http://")) {
// We replace thumbs with resizes so we can the full sized images
imageSource = imageSource.replace("thumbs", "resizes");
String url_string = "http://myhentaicomics.com/" + imageSource;
url_string = url_string.replace("%20", "_");
url_string = url_string.replace("%27", "");
url_string = url_string.replace("%28", "_");
url_string = url_string.replace("%29", "_");
url_string = url_string.replace("%2C", "_");
if (isTag) {
logger.info("Downloading from a tag or search");
try {
sleep(500);
result.add("http://myhentaicomics.com/" + imageSource);
addURLToDownload(new URL("http://myhentaicomics.com/" + imageSource), "", url_string.split("/")[6]);
}
catch (MalformedURLException e) {
logger.warn("Malformed URL");
e.printStackTrace();
}
}
}
}
}
}
return result;
}
private List<String> getListOfPages(Document doc) {
List<String> pages = new ArrayList<>();
// Get the link from the last button
String nextPageUrl = doc.select("a.ui-icon-right").last().attr("href");
Pattern pat = Pattern.compile("/index\\.php/tag/[0-9]*/[a-zA-Z0-9_\\-:+]*\\?page=(\\d+)");
Matcher mat = pat.matcher(nextPageUrl);
if (mat.matches()) {
logger.debug("Getting pages from a tag");
String base_link = mat.group(0).replaceAll("\\?page=\\d+", "");
logger.debug("base_link is " + base_link);
int numOfPages = Integer.parseInt(mat.group(1));
for (int x = 1; x != numOfPages +1; x++) {
logger.debug("running loop");
String link = base_link + "?page=" + Integer.toString(x);
pages.add(link);
}
} else {
Pattern pa = Pattern.compile("/index\\.php/search\\?q=[a-zA-Z0-9_\\-:]*&page=(\\d+)");
Matcher ma = pa.matcher(nextPageUrl);
if (ma.matches()) {
logger.debug("Getting pages from a search");
String base_link = ma.group(0).replaceAll("page=\\d+", "");
logger.debug("base_link is " + base_link);
int numOfPages = Integer.parseInt(ma.group(1));
for (int x = 1; x != numOfPages +1; x++) {
logger.debug("running loop");
String link = base_link + "page=" + Integer.toString(x);
logger.debug(link);
pages.add(link);
}
}
}
return pages;
}
@Override
public List<String> getURLsFromPage(Document doc) {
List<String> result = new ArrayList<>();
// Checks if this is a comic page or a page of albums
// If true the page is a page of albums
if (doc.toString().contains("class=\"g-item g-album\"")) {
// This if checks that there is more than 1 page
if (!doc.select("a.ui-icon-right").last().attr("href").equals("")) {
// There is more than one page so we call getListOfPages
List<String> pagesToRip = getListOfPages(doc);
logger.debug("Pages to rip = " + pagesToRip);
for (String url : pagesToRip) {
logger.debug("Getting albums from " + url);
result = getAlbumsFromPage(url);
}
} else {
logger.debug("There is only one page on this page of albums");
// There is only 1 page so we call getAlbumsFromPage and pass it the page url
result = getAlbumsFromPage(doc.select("div.g-description > a").attr("href"));
}
return result;
}
else {
for (Element el : doc.select("img")) {
String imageSource = el.attr("src");
// This bool is here so we don't try and download the site logo
@ -245,7 +123,6 @@ public class MyhentaicomicsRipper extends AbstractHTMLRipper {
result.add("http://myhentaicomics.com/" + imageSource);
}
}
}
return result;
}

5
src/main/java/com/rarchives/ripme/ui/MainWindow.java
View File

@ -162,6 +162,11 @@ public final class MainWindow implements Runnable, RipStatusHandler {
return checkbox;
}
public static void addUrlToQueue(String url) {
queueListModel.addElement(url);
}
public MainWindow() {
mainFrame = new JFrame("RipMe v" + UpdateUtils.getThisJarVersion());
mainFrame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE);