From 24448f9d6b815e944afd6b18205ea26719951f26 Mon Sep 17 00:00:00 2001 From: cyian-1756 Date: Mon, 27 Aug 2018 12:18:29 -0400 Subject: [PATCH 1/3] Added Myhentaigallery.com ripper --- .../ripper/rippers/MyhentaigalleryRipper.java | 89 +++++++++++++++++++ 1 file changed, 89 insertions(+) create mode 100644 src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaigalleryRipper.java diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaigalleryRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaigalleryRipper.java new file mode 100644 index 00000000..a6d0d539 --- /dev/null +++ b/src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaigalleryRipper.java @@ -0,0 +1,89 @@ +package com.rarchives.ripme.ripper.rippers; + +import com.rarchives.ripme.ripper.AbstractHTMLRipper; +import com.rarchives.ripme.utils.Http; +import java.io.IOException; +import java.net.MalformedURLException; +import java.net.URL; +import java.util.ArrayList; +import java.util.List; +import java.util.regex.Matcher; +import java.util.regex.Pattern; +import org.jsoup.nodes.Document; +import org.jsoup.nodes.Element; + +public class MyhentaigalleryRipper extends AbstractHTMLRipper { + private static boolean isTag; + + public MyhentaigalleryRipper(URL url) throws IOException { + super(url); + } + + @Override + public String getHost() { + return "myhentaigallery"; + } + + @Override + public String getDomain() { + return "myhentaigallery.com"; + } + + @Override + public String getGID(URL url) throws MalformedURLException { + Pattern p = Pattern.compile("https://myhentaigallery.com/gallery/thumbnails/([0-9]+)/?$"); + Matcher m = p.matcher(url.toExternalForm()); + if (m.matches()) { + return m.group(1); + } + + throw new MalformedURLException("Expected myhentaicomics.com URL format: " + + "myhentaicomics.com/index.php/albumName - got " + url + " instead"); + } + + @Override + public Document getFirstPage() throws IOException { + // "url" is an instance field of the superclass + return Http.url(url).get(); + } + +// @Override +// public Document getNextPage(Document doc) throws IOException { +// // Find next page +// String nextUrl = ""; +// Element elem = doc.select("a.ui-icon-right").first(); +// String nextPage = elem.attr("href"); +// Pattern p = Pattern.compile("/index.php/[a-zA-Z0-9_-]*\\?page=\\d"); +// Matcher m = p.matcher(nextPage); +// if (m.matches()) { +// nextUrl = "https://myhentaicomics.com" + m.group(0); +// } +// if (nextUrl.equals("")) { +// throw new IOException("No more pages"); +// } +// // Sleep for half a sec to avoid getting IP banned +// sleep(500); +// return Http.url(nextUrl).get(); +// } + + + + @Override + public List getURLsFromPage(Document doc) { + List result = new ArrayList<>(); + for (Element el : doc.select(".comic-thumb > img")) { + String imageSource = el.attr("src"); + // We replace thumbs with resizes so we can the full sized images + imageSource = imageSource.replace("thumbnail", "original"); + result.add("https://" + getDomain() + imageSource); + } + return result; + } + + @Override + public void downloadURL(URL url, int index) { + addURLToDownload(url, getPrefix(index)); + } + + +} \ No newline at end of file From aa15ba83c5bdd406c03c1f5c99c049826871bc54 Mon Sep 17 00:00:00 2001 From: cyian-1756 Date: Mon, 27 Aug 2018 18:02:05 -0400 Subject: [PATCH 2/3] Finished up Myhentaigallery ripper --- .../ripper/rippers/MyhentaigalleryRipper.java | 23 +------------------ 1 file changed, 1 insertion(+), 22 deletions(-) diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaigalleryRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaigalleryRipper.java index a6d0d539..0eb0427a 100644 --- a/src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaigalleryRipper.java +++ b/src/main/java/com/rarchives/ripme/ripper/rippers/MyhentaigalleryRipper.java @@ -38,7 +38,7 @@ public class MyhentaigalleryRipper extends AbstractHTMLRipper { } throw new MalformedURLException("Expected myhentaicomics.com URL format: " + - "myhentaicomics.com/index.php/albumName - got " + url + " instead"); + "myhentaigallery.com/gallery/thumbnails/ID - got " + url + " instead"); } @Override @@ -47,27 +47,6 @@ public class MyhentaigalleryRipper extends AbstractHTMLRipper { return Http.url(url).get(); } -// @Override -// public Document getNextPage(Document doc) throws IOException { -// // Find next page -// String nextUrl = ""; -// Element elem = doc.select("a.ui-icon-right").first(); -// String nextPage = elem.attr("href"); -// Pattern p = Pattern.compile("/index.php/[a-zA-Z0-9_-]*\\?page=\\d"); -// Matcher m = p.matcher(nextPage); -// if (m.matches()) { -// nextUrl = "https://myhentaicomics.com" + m.group(0); -// } -// if (nextUrl.equals("")) { -// throw new IOException("No more pages"); -// } -// // Sleep for half a sec to avoid getting IP banned -// sleep(500); -// return Http.url(nextUrl).get(); -// } - - - @Override public List getURLsFromPage(Document doc) { List result = new ArrayList<>(); From 68e89cabc1792890ea3e4f09c72c5c2fb4024e8c Mon Sep 17 00:00:00 2001 From: cyian-1756 Date: Mon, 27 Aug 2018 18:02:28 -0400 Subject: [PATCH 3/3] Added unit test for Myhentaigallery ripper --- .../ripper/rippers/MyhentaigalleryRipperTest.java | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 src/test/java/com/rarchives/ripme/tst/ripper/rippers/MyhentaigalleryRipperTest.java diff --git a/src/test/java/com/rarchives/ripme/tst/ripper/rippers/MyhentaigalleryRipperTest.java b/src/test/java/com/rarchives/ripme/tst/ripper/rippers/MyhentaigalleryRipperTest.java new file mode 100644 index 00000000..6cde566a --- /dev/null +++ b/src/test/java/com/rarchives/ripme/tst/ripper/rippers/MyhentaigalleryRipperTest.java @@ -0,0 +1,14 @@ +package com.rarchives.ripme.tst.ripper.rippers; + +import java.io.IOException; +import java.net.URL; + +import com.rarchives.ripme.ripper.rippers.MyhentaigalleryRipper; + +public class MyhentaigalleryRipperTest extends RippersTest { + + public void testMyhentaigalleryAlbum() throws IOException { + MyhentaigalleryRipper ripper = new MyhentaigalleryRipper(new URL("https://myhentaigallery.com/gallery/thumbnails/9201")); + testRipper(ripper); + } +} \ No newline at end of file