Merge pull request #6 from RipMeApp/master

Sync

pom.xml

@@ -4,7 +4,7 @@
   <groupId>com.rarchives.ripme</groupId>
   <artifactId>ripme</artifactId>
   <packaging>jar</packaging>
-  <version>1.7.23</version>
+  <version>1.7.24</version>
   <name>ripme</name>
   <url>http://rip.rarchives.com</url>
   <properties>

ripme.json

@@ -1,6 +1,7 @@
 {
-    "latestVersion": "1.7.23",
+    "latestVersion": "1.7.24",
     "changeList": [
+        "1.7.24: Added sta.sh ripper; Added sinfest.com ripper; Added femjoyhunter.com ripper; Disabled flaky unit tests",
         "1.7.23: Fixed xvideos ripper; InstagramRipper now works with lastseenfeature",
         "1.7.22: Added func to normalize urls before reading from/writing to url history file; last seen feature now works with instagram",
         "1.7.21: Fixed last seen feature",

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

@@ -0,0 +1,64 @@
+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 FemjoyhunterRipper extends AbstractHTMLRipper {
+
+    public FemjoyhunterRipper(URL url) throws IOException {
+        super(url);
+    }
+
+    @Override
+    public String getHost() {
+        return "femjoyhunter";
+    }
+
+    @Override
+    public String getDomain() {
+        return "femjoyhunter.com";
+    }
+
+    @Override
+    public String getGID(URL url) throws MalformedURLException {
+        Pattern p = Pattern.compile("https?://www.femjoyhunter.com/([a-zA-Z0-9_-]+)/?");
+        Matcher m = p.matcher(url.toExternalForm());
+        if (m.matches()) {
+            return m.group(1);
+        }
+        throw new MalformedURLException("Expected femjoyhunter URL format: " +
+                "femjoyhunter.com/ID - got " + url + " instead");
+    }
+
+    @Override
+    public Document getFirstPage() throws IOException {
+        // "url" is an instance field of the superclass
+        return Http.url(url).get();
+    }
+
+    @Override
+    public List<String> getURLsFromPage(Document doc) {
+        List<String> result = new ArrayList<>();
+        for (Element el : doc.select("ul.gallery-b > li > a")) {
+            result.add(el.attr("href"));
+        }
+        return result;
+    }
+
+    @Override
+    public void downloadURL(URL url, int index) {
+
+        addURLToDownload(url, getPrefix(index), "", "https://a2h6m3w6.ssl.hwcdn.net/", null);
+    }
+}

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

@@ -0,0 +1,80 @@
+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 SinfestRipper extends AbstractHTMLRipper {
+
+    public SinfestRipper(URL url) throws IOException {
+        super(url);
+    }
+
+    @Override
+    public String getHost() {
+        return "sinfest";
+    }
+
+    @Override
+    public String getDomain() {
+        return "sinfest.net";
+    }
+
+    @Override
+    public String getGID(URL url) throws MalformedURLException {
+        Pattern p = Pattern.compile("https?://sinfest.net/view.php\\?date=([0-9-]*)/?");
+        Matcher m = p.matcher(url.toExternalForm());
+        if (m.matches()) {
+            return m.group(1);
+        }
+        throw new MalformedURLException("Expected sinfest URL format: " +
+                "sinfest.net/view.php?date=XXXX-XX-XX/ - 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 {
+        Element elem = doc.select("td.style5 > a > img").last();
+        logger.info(elem.parent().attr("href"));
+        if (elem == null || elem.parent().attr("href").equals("view.php?date=")) {
+            throw new IOException("No more pages");
+        }
+        String nextPage = elem.parent().attr("href");
+        // Some times this returns a empty string
+        // This for stops that
+        if (nextPage == "") {
+            return null;
+        }
+        else {
+            return Http.url("http://sinfest.net/" + nextPage).get();
+        }
+    }
+
+    @Override
+    public List<String> getURLsFromPage(Document doc) {
+        List<String> result = new ArrayList<>();
+        Element elem = doc.select("tbody > tr > td > img").last();
+        result.add("http://sinfest.net/" + elem.attr("src"));
+        return result;
+    }
+
+    @Override
+    public void downloadURL(URL url, int index) {
+        addURLToDownload(url, getPrefix(index));
+    }
+}

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

@@ -0,0 +1,112 @@
+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.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
+
+import org.jsoup.Connection;
+import org.jsoup.Jsoup;
+import org.jsoup.nodes.Document;
+import org.jsoup.nodes.Element;
+
+import com.rarchives.ripme.ripper.AbstractHTMLRipper;
+import com.rarchives.ripme.utils.Http;
+
+public class StaRipper extends AbstractHTMLRipper {
+
+    public StaRipper(URL url) throws IOException {
+        super(url);
+    }
+
+    private Map<String,String> cookies = new HashMap<>();
+
+    @Override
+    public String getHost() {
+        return "sta";
+    }
+
+    @Override
+    public String getDomain() {
+        return "sta.sh";
+    }
+
+    @Override
+    public String getGID(URL url) throws MalformedURLException {
+        Pattern p = Pattern.compile("https://sta.sh/([A-Za-z0-9]+)");
+        Matcher m = p.matcher(url.toExternalForm());
+        if (m.matches()) {
+            return m.group(1);
+        }
+        throw new MalformedURLException("Expected sta.sh URL format: " +
+                "sta.sh/ALBUMID - got " + url + " instead");
+    }
+
+    @Override
+    public Document getFirstPage() throws IOException {
+        // "url" is an instance field of the superclass
+        return Http.url(url).get();
+    }
+
+    @Override
+    public List<String> getURLsFromPage(Document doc) {
+        List<String> result = new ArrayList<>();
+        for (Element el : doc.select("span > span > a.thumb")) {
+            String thumbPageURL = el.attr("href");
+            Document thumbPage = null;
+            if (checkURL(thumbPageURL)) {
+                try {
+                    Connection.Response resp = Http.url(new URL(thumbPageURL)).response();
+                    cookies.putAll(resp.cookies());
+                    thumbPage = resp.parse();
+                } catch (MalformedURLException e) {
+                    logger.info(thumbPageURL + " is a malformed URL");
+                } catch (IOException e) {
+                    logger.info(e.getMessage());
+                }
+                String imageDownloadUrl = thumbPage.select("a.dev-page-download").attr("href");
+                if (imageDownloadUrl != null && !imageDownloadUrl.equals("")) {
+                    result.add(getImageLinkFromDLLink(imageDownloadUrl));
+                }
+            }
+
+        }
+        return result;
+    }
+
+    private boolean checkURL(String url) {
+        try {
+            new URL(url);
+            return true;
+        } catch (MalformedURLException e) {
+            return false;
+        }
+    }
+
+    private String getImageLinkFromDLLink(String url) {
+        try {
+            Connection.Response response = Jsoup.connect(url)
+                    .userAgent(USER_AGENT)
+                    .timeout(10000)
+                    .cookies(cookies)
+                    .followRedirects(false)
+                    .execute();
+            String imageURL = response.header("Location");
+            logger.info(imageURL);
+            return imageURL;
+            } catch (IOException e) {
+                logger.info("Got error message " + e.getMessage() + " trying to download " + url);
+                return null;
+            }
+    }
+
+    @Override
+    public void downloadURL(URL url, int index) {
+        addURLToDownload(url, getPrefix(index));
+    }
+}

src/main/java/com/rarchives/ripme/ui/UpdateUtils.java

@@ -21,7 +21,7 @@ import com.rarchives.ripme.utils.Utils;
 public class UpdateUtils {
 
     private static final Logger logger = Logger.getLogger(UpdateUtils.class);
-    private static final String DEFAULT_VERSION = "1.7.23";
+    private static final String DEFAULT_VERSION = "1.7.24";
     private static final String REPO_NAME = "ripmeapp/ripme";
     private static final String updateJsonURL = "https://raw.githubusercontent.com/" + REPO_NAME + "/master/ripme.json";
     private static final String mainFileName = "ripme.jar";

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

@@ -0,0 +1,13 @@
+package com.rarchives.ripme.tst.ripper.rippers;
+
+import java.io.IOException;
+import java.net.URL;
+
+import com.rarchives.ripme.ripper.rippers.FemjoyhunterRipper;
+
+public class FemjoyhunterRipperTest extends RippersTest {
+    public void testRip() throws IOException {
+        FemjoyhunterRipper ripper = new FemjoyhunterRipper(new URL("https://www.femjoyhunter.com/alisa-i-got-nice-big-breasts-and-fine-ass-so-she-seems-to-be-a-hottest-brunette-5936/"));
+        testRipper(ripper);
+    }
+}

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

@@ -0,0 +1,13 @@
+package com.rarchives.ripme.tst.ripper.rippers;
+
+import java.io.IOException;
+import java.net.URL;
+
+import com.rarchives.ripme.ripper.rippers.SinfestRipper;
+
+public class SinfestRipperTest extends RippersTest {
+    public void testRip() throws IOException {
+        SinfestRipper ripper = new SinfestRipper(new URL("http://sinfest.net/view.php?date=2000-01-17"));
+        testRipper(ripper);
+    }
+}

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

@@ -0,0 +1,13 @@
+package com.rarchives.ripme.tst.ripper.rippers;
+
+import java.io.IOException;
+import java.net.URL;
+
+import com.rarchives.ripme.ripper.rippers.StaRipper;
+
+public class StaRipperTest extends RippersTest {
+    public void testRip() throws IOException {
+        StaRipper ripper = new StaRipper(new URL("https://sta.sh/2hn9rtavr1g"));
+        testRipper(ripper);
+    }
+}

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

@@ -83,10 +83,10 @@ public class WordpressComicRipperTest extends RippersTest {
                 new URL("http://tnbtu.com/comic/01-00/"));
         testRipper(ripper);
     }
-
+    // https://github.com/RipMeApp/ripme/issues/269 - Disabled test - WordpressRipperTest: various domains flaky in CI
-    public void test_pepsaga() throws IOException {
+//    public void test_pepsaga() throws IOException {
-        WordpressComicRipper ripper = new WordpressComicRipper(
+//        WordpressComicRipper ripper = new WordpressComicRipper(
-                new URL("http://shipinbottle.pepsaga.com/?p=281"));
+//                new URL("http://shipinbottle.pepsaga.com/?p=281"));
-        testRipper(ripper);
+//        testRipper(ripper);
-    }
+//    }
 }