Merge pull request #1028 from buzzlightmonth/master

Added pinups and homepage to Sinner Comics ripper

src/main/java/com/rarchives/ripme/ripper/rippers/SinnercomicsRipper.java

@@ -15,29 +15,91 @@ import org.jsoup.nodes.Element;
 
 public class SinnercomicsRipper extends AbstractHTMLRipper {
 
+    private static final String HOST   = "sinnercomics",
+                                DOMAIN = "sinnercomics.com";
+
+    private static final int SLEEP_TIME = 500;
+
+    enum RIP_TYPE {
+        HOMEPAGE,
+        PINUP,
+        COMIC
+    }
+
+    private RIP_TYPE ripType;
+    private Integer pageNum;
+
     public SinnercomicsRipper(URL url) throws IOException {
-    super(url);
+        super(url);
     }
 
     @Override
     public String getHost() {
-        return "sinnercomics";
+        return HOST;
     }
 
     @Override
     public String getDomain() {
-        return "sinnercomics.com";
+        return DOMAIN;
+    }
+
+    @Override
+    public String normalizeUrl(String url) {
+        // Remove the comments hashtag
+        return url.replaceAll("/#(comments|disqus_thread)", "/");
     }
 
     @Override
     public String getGID(URL url) throws MalformedURLException {
-        Pattern p = Pattern.compile("^https?://sinnercomics.com/comic/([a-zA-Z0-9-]*)/?$");
+        String cleanUrl = normalizeUrl(url.toExternalForm());
-        Matcher m = p.matcher(url.toExternalForm());
+        Pattern p;
+        Matcher m;
+
+        p = Pattern.compile("^https?://sinnercomics\\.com/comic/([a-zA-Z0-9-]*)/?$");
+        m = p.matcher(cleanUrl);
         if (m.matches()) {
+            // Comic
+            this.ripType = RIP_TYPE.COMIC;
             return m.group(1).replaceAll("-page-\\d+", "");
         }
+
+        p = Pattern.compile("^https?://sinnercomics\\.com(?:/page/([0-9]+))?/?$");
+        m = p.matcher(cleanUrl);
+        if (m.matches()) {
+            // Homepage
+            this.ripType = RIP_TYPE.HOMEPAGE;
+            if (m.group(1) != null) {
+                this.pageNum = Integer.valueOf(m.group(1));
+            } else {
+                this.pageNum = 1;
+            }
+            return "homepage";
+        }
+
+        p = Pattern.compile("^https?://sinnercomics\\.com/([a-zA-Z0-9-]+)(?:/#comments)?/?$");
+        m = p.matcher(cleanUrl);
+        if (m.matches()) {
+            // Pinup image
+            this.ripType = RIP_TYPE.PINUP;
+            return m.group(1);
+        }
+
         throw new MalformedURLException("Expected sinnercomics.com URL format: " +
-                        "sinnercomics.com/comic/albumName - got " + url + " instead");
+                        "/pinupName or /comic/albumName or /page/number  - got " + cleanUrl + " instead");
+    }
+
+    @Override
+    public boolean canRip(URL url) {
+        if (!url.getHost().endsWith(DOMAIN)) {
+            return false;
+        }
+        try {
+            getGID(url);
+        } catch (MalformedURLException e) {
+            // Can't get GID, can't rip it.
+            return false;
+        }
+        return true;
     }
 
     @Override
@@ -48,27 +110,53 @@ public class SinnercomicsRipper extends AbstractHTMLRipper {
 
     @Override
     public Document getNextPage(Document doc) throws IOException {
-        // Find next page
+        String nextUrl = null;
-        String nextUrl = "";
+
-        // We use comic-nav-next to the find the next page
+        switch (this.ripType) {
-        Element elem = doc.select("a.comic-nav-next").first();
+            case PINUP:
-            if (elem == null) {
+                throw new IOException("No next page on a pinup");
-                throw new IOException("No more pages");
+
-            }
+            case COMIC:
-            String nextPage = elem.attr("href");
+                // We use comic-nav-next to the find the next page
-            // Wait half a sec to avoid IP bans
+                Element elem = doc.select("a.comic-nav-next").first();
-            sleep(500);
+                if (elem == null) {
-            return Http.url(nextPage).get();
+                    throw new IOException("No more pages");
+                }
+                nextUrl = elem.attr("href");
+                break;
+
+            default: // case HOMEPAGE:
+                this.pageNum++;
+                nextUrl = "https://sinnercomics.com/page/" + String.valueOf(this.pageNum);
+                break;
         }
 
+        // Wait to avoid IP bans
+        sleep(SLEEP_TIME);
+        return Http.url(nextUrl).get();
+    }
+
     @Override
     public List<String> getURLsFromPage(Document doc) {
         List<String> result = new ArrayList<>();
-        for (Element el : doc.select("meta[property=og:image]")) {
+
-            String imageSource = el.attr("content");
+        switch (this.ripType) {
-            imageSource = imageSource.replace(" alt=", "");
+            case COMIC:
-            result.add(imageSource);
+                // comic pages only contain one image, determined by a meta tag
+                for (Element el : doc.select("meta[property=og:image]")) {
+                    String imageSource = el.attr("content");
+                    imageSource = imageSource.replace(" alt=", "");
+                    result.add(imageSource);
+                }
+                break;
+            default:
+                for (Element el : doc.select(".entry p img")) {
+                    // These filters match the full size images but might match ads too...
+                    result.add(el.attr("src"));
+                }
+                break;
         }
+
         return result;
     }
 
@@ -77,5 +165,4 @@ public class SinnercomicsRipper extends AbstractHTMLRipper {
         addURLToDownload(url, getPrefix(index));
     }
 
-
 }

src/test/java/com/rarchives/ripme/tst/ripper/rippers/SinnercomicsRipperTest.java

@@ -7,13 +7,39 @@ import com.rarchives.ripme.ripper.rippers.SinnercomicsRipper;
 
 public class SinnercomicsRipperTest extends RippersTest {
     public void testSinnercomicsAlbum() throws IOException {
-        SinnercomicsRipper ripper = new SinnercomicsRipper(new URL("https://sinnercomics.com/comic/beyond-the-hotel-page-01/"));
+        SinnercomicsRipper ripper;
+
+        // Comic test
+        ripper = new SinnercomicsRipper(new URL("https://sinnercomics.com/comic/beyond-the-hotel-page-01/"));
         testRipper(ripper);
+
+        // Homepage test
+        ripper = new SinnercomicsRipper(new URL("https://sinnercomics.com/page/2/"));
+        testRipper(ripper);
+
+        // Pinup test
+        ripper = new SinnercomicsRipper(new URL("https://sinnercomics.com/elsa-frozen-2/#comments"));
+        testRipper(ripper);
+
     }
 
     public void testGetGID() throws IOException {
-        URL url = new URL("https://sinnercomics.com/comic/beyond-the-hotel-page-01/");
+        URL url;
-        SinnercomicsRipper ripper = new SinnercomicsRipper(url);
+        SinnercomicsRipper ripper;
+
+        // Comic test
+        url = new URL("https://sinnercomics.com/comic/beyond-the-hotel-page-01/");
+        ripper = new SinnercomicsRipper(url);
         assertEquals("beyond-the-hotel", ripper.getGID(url));
+
+        // Homepage test
+        url = new URL("https://sinnercomics.com/page/2/");
+        ripper = new SinnercomicsRipper(url);
+        assertEquals("homepage", ripper.getGID(url));
+
+        // Comic test
+        url = new URL("https://sinnercomics.com/elza-frozen-2/#comments");
+        ripper = new SinnercomicsRipper(url);
+        assertEquals("elza-frozen-2", ripper.getGID(url));
     }
 }