From 71652ecb00bb5ae1ffaf6ea76897a9b4f873c0b1 Mon Sep 17 00:00:00 2001
From: Edvin Boul <kittenparry@users.noreply.github.com>
Date: Mon, 1 Jul 2019 13:19:54 +0300
Subject: [PATCH 1/2] Added Meituri Ripper [NSFW]

---
 .../ripme/ripper/rippers/MeituriRipper.java   | 91 +++++++++++++++++++
 .../tst/ripper/rippers/MeituriRipperTest.java | 19 ++++
 2 files changed, 110 insertions(+)
 create mode 100644 src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java
 create mode 100644 src/test/java/com/rarchives/ripme/tst/ripper/rippers/MeituriRipperTest.java

diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java
new file mode 100644
index 00000000..8855846a
--- /dev/null
+++ b/src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java
@@ -0,0 +1,91 @@
+package com.rarchives.ripme.ripper.rippers;
+
+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;
+
+import com.rarchives.ripme.ripper.AbstractHTMLRipper;
+import com.rarchives.ripme.utils.Http;
+
+public class MeituriRipper extends AbstractHTMLRipper {
+    public MeituriRipper(URL url) throws IOException {
+        super(url);
+    }
+
+    @Override
+    public String getHost() {
+        return "meituri";
+    }
+
+    @Override
+    public String getDomain() {
+        return "meituri.com";
+    }
+
+    // To use in getting URLs
+    String albumID = "";
+
+    @Override
+    public String getGID(URL url) throws MalformedURLException {
+        // without escape
+        // ^https?://[w.]*meituri\.com/a/([0-9]+)/$
+        // https://www.meituri.com/a/14449/
+        // group 1 is 14449
+        Pattern p = Pattern.compile("^https?://[w.]*meituri\\.com/a/([0-9]+)/$");
+        Matcher m = p.matcher(url.toExternalForm());
+        if (m.matches()) {
+            albumID = m.group(1);
+            return m.group(1);
+        }
+        throw new MalformedURLException(
+                "Expected meituri.com URL format: " + "meituri.com/a/albumid/ - got " + url + "instead");
+    }
+
+    @Override
+    public Document getFirstPage() throws IOException {
+        return Http.url(url).get();
+    }
+
+    @Override
+    public List<String> getURLsFromPage(Document doc) {
+        List<String> imageURLs = new ArrayList<>();
+        // Get number of images from the page
+        // Then generate links according to that
+        String numOfImages = "";
+        // A very ugly way of getting "图片数量： 55P" from paragraphs
+        // 3rd p in div.tuji
+        int n = 0;
+        for (Element para : doc.select("div.tuji > p")) {
+            // 图片数量： 55P
+            if (n == 2) {
+                numOfImages = para.toString();
+            }
+            n++;
+        }
+        // ["<p>图片数量：", "55P</p>"]
+        String[] splitNumOfImages = numOfImages.split(" ");
+        // "55P</p>" -> "55" -> 55
+        int actualNumOfImages = Integer.parseInt(splitNumOfImages[1].replace("P</p>", ""));
+
+        // Base URL: http://ii.hywly.com/a/1/albumid/imgnum.jpg
+        String baseURL = "http://ii.hywly.com/a/1/" + albumID + "/";
+
+        // Loop through and add images to the URL list
+        for (int i = 1; i <= actualNumOfImages; i++) {
+            imageURLs.add(baseURL + i + ".jpg");
+        }
+        return imageURLs;
+    }
+
+    @Override
+    public void downloadURL(URL url, int index) {
+        addURLToDownload(url, getPrefix(index));
+    }
+}
diff --git a/src/test/java/com/rarchives/ripme/tst/ripper/rippers/MeituriRipperTest.java b/src/test/java/com/rarchives/ripme/tst/ripper/rippers/MeituriRipperTest.java
new file mode 100644
index 00000000..a8505590
--- /dev/null
+++ b/src/test/java/com/rarchives/ripme/tst/ripper/rippers/MeituriRipperTest.java
@@ -0,0 +1,19 @@
+package com.rarchives.ripme.tst.ripper.rippers;
+
+import java.io.IOException;
+import java.net.URL;
+
+import com.rarchives.ripme.ripper.rippers.MeituriRipper;
+
+public class MeituriRipperTest extends RippersTest {
+    public void testMeituriRip() throws IOException {
+        MeituriRipper ripper = new MeituriRipper(new URL("https://www.meituri.com/a/14449/"));
+        testRipper(ripper);
+    }
+
+    public void testGetGID() throws IOException {
+        URL url = new URL("https://www.meituri.com/a/14449/");
+        MeituriRipper ripper = new MeituriRipper(url);
+        assertEquals("14449", ripper.getGID(url));
+    }
+}

From ec22b13cc3c4e6a3cabeba1e4631eca1fc679063 Mon Sep 17 00:00:00 2001
From: Edvin Boul <kittenparry@users.noreply.github.com>
Date: Mon, 1 Jul 2019 13:28:40 +0300
Subject: [PATCH 2/2] Regex change to also match pagination

---
 .../com/rarchives/ripme/ripper/rippers/MeituriRipper.java    | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java b/src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java
index 8855846a..4e39a985 100644
--- a/src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java
+++ b/src/main/java/com/rarchives/ripme/ripper/rippers/MeituriRipper.java
@@ -35,10 +35,11 @@ public class MeituriRipper extends AbstractHTMLRipper {
     @Override
     public String getGID(URL url) throws MalformedURLException {
         // without escape
-        // ^https?://[w.]*meituri\.com/a/([0-9]+)/$
+        // ^https?://[w.]*meituri\.com/a/([0-9]+)/([0-9\.html]+)*$
         // https://www.meituri.com/a/14449/
+        // also matches https://www.meituri.com/a/14449/3.html etc.
         // group 1 is 14449
-        Pattern p = Pattern.compile("^https?://[w.]*meituri\\.com/a/([0-9]+)/$");
+        Pattern p = Pattern.compile("^https?://[w.]*meituri\\.com/a/([0-9]+)/([0-9\\.html]+)*$");
         Matcher m = p.matcher(url.toExternalForm());
         if (m.matches()) {
             albumID = m.group(1);