Implement Fapwiz Ripper (#2086)

* Implement FapwizRipper

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

@@ -0,0 +1,154 @@
+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.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+import org.jsoup.nodes.Document;
+import org.jsoup.select.Elements;
+
+import com.rarchives.ripme.ripper.AbstractHTMLRipper;
+import com.rarchives.ripme.utils.Http;
+
+public class FapwizRipper extends AbstractHTMLRipper {
+
+    private static final Logger logger = LogManager.getLogger(FapwizRipper.class);
+
+    private static final Pattern CATEGORY_PATTERN = Pattern.compile("https?://fapwiz.com/category/([a-zA-Z0-9_-]+)/?$");
+
+    private static final Pattern USER_PATTERN = Pattern.compile("https?://fapwiz.com/([a-zA-Z0-9_-]+)/?$");
+
+    // Note that the last part of the pattern can contain unicode emoji which
+    // get encoded as %-encoded UTF-8 bytes in the URL, so we allow % characters.
+    private static final Pattern POST_PATTERN = Pattern
+            .compile("https?://fapwiz.com/([a-zA-Z0-9_-]+)/([a-zA-Z0-9_%-]+)/?$");
+
+    public FapwizRipper(URL url) throws IOException {
+        super(url);
+    }
+
+    @Override
+    public String getHost() {
+        return "fapwiz";
+    }
+
+    @Override
+    public String getDomain() {
+        return "fapwiz.com";
+    }
+
+    @Override
+    public String getGID(URL url) throws MalformedURLException {
+        Matcher m;
+
+        m = CATEGORY_PATTERN.matcher(url.toExternalForm());
+        if (m.matches()) {
+            return "category_" + m.group(1);
+        }
+
+        m = USER_PATTERN.matcher(url.toExternalForm());
+        if (m.matches()) {
+            return "user_" + m.group(1);
+        }
+
+        m = POST_PATTERN.matcher(url.toExternalForm());
+        if (m.matches()) {
+            return "post_" + m.group(1) + "_" + m.group(2);
+        }
+
+        throw new MalformedURLException("Expected fapwiz URL format: " +
+                "fapwiz.com/USER or fapwiz.com/USER/POST or " +
+                "fapwiz.com/CATEGORY - got " + url + " instead");
+    }
+
+    void processUserOrCategoryPage(Document doc, List<String> results) {
+        // The category page looks a lot like the structure of a user page,
+        // so processUserPage is written to be compatible with both.
+        doc.select(".post-items-holder img").forEach(e -> {
+            String imgSrc = e.attr("src");
+
+            // Skip the user profile picture thumbnail insets
+            if (imgSrc.endsWith("-thumbnail-icon.jpg")) {
+                return;
+            }
+
+            // Replace -thumbnail.jpg with .mp4
+            String videoSrc = imgSrc.replace("-thumbnail.jpg", ".mp4");
+            results.add(videoSrc);
+        });
+    }
+
+    void processCategoryPage(Document doc, List<String> results) {
+        logger.info("Processing category page: " + url);
+        processUserOrCategoryPage(doc, results);
+    }
+
+    void processUserPage(Document doc, List<String> results) {
+        logger.info("Processing user page: " + url);
+        processUserOrCategoryPage(doc, results);
+    }
+
+    void processPostPage(Document doc, List<String> results) {
+        logger.info("Processing post page: " + url);
+        doc.select("video source").forEach(video -> {
+            results.add(video.attr("src"));
+        });
+    }
+
+    @Override
+    public List<String> getURLsFromPage(Document doc) {
+        List<String> results = new ArrayList<>();
+        Matcher m;
+
+        m = CATEGORY_PATTERN.matcher(url.toExternalForm());
+        if (m.matches()) {
+            processCategoryPage(doc, results);
+        }
+
+        m = USER_PATTERN.matcher(url.toExternalForm());
+        if (m.matches()) {
+            processUserPage(doc, results);
+        }
+
+        m = POST_PATTERN.matcher(url.toExternalForm());
+        if (m.matches()) {
+            processPostPage(doc, results);
+        }
+
+        return results;
+    }
+
+    private Document getDocument(String url, int retries) throws IOException {
+        return Http.url(url).userAgent(USER_AGENT).retries(retries).get();
+    }
+
+    private Document getDocument(String url) throws IOException {
+        return getDocument(url, 1);
+    }
+
+    @Override
+    public Document getNextPage(Document page) throws IOException {
+        logger.info("Getting next page for url: " + url);
+        Elements next = page.select("a.next");
+        if (!next.isEmpty()) {
+            String href = next.attr("href");
+            logger.info("Found next page: " + href);
+            return getDocument(href);
+        } else {
+            logger.info("No more pages");
+            throw new IOException("No more pages.");
+        }
+    }
+
+    @Override
+    public void downloadURL(URL url, int index) {
+        sleep(2000);
+        addURLToDownload(url, getPrefix(index));
+    }
+}

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

@@ -0,0 +1,162 @@
+package com.rarchives.ripme.tst.ripper.rippers;
+
+import java.io.IOException;
+import java.net.URI;
+import java.net.URISyntaxException;
+import java.net.URL;
+
+import org.jsoup.nodes.Document;
+import org.junit.jupiter.api.Assertions;
+import org.junit.jupiter.api.Tag;
+import org.junit.jupiter.api.Test;
+
+import com.rarchives.ripme.ripper.AbstractRipper;
+import com.rarchives.ripme.ripper.rippers.FapwizRipper;
+import com.rarchives.ripme.utils.Http;
+import com.rarchives.ripme.utils.Utils;
+
+public class FapwizRipperTest extends RippersTest {
+    @Test
+    @Tag("flaky") // It seems like fetching the document within the test can be flaky.
+    public void testGetNextPage_NoNextPage() throws IOException, URISyntaxException {
+        URL url = new URI("https://fapwiz.com/alison-esha/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+
+        Document firstPage = Http.url(url).userAgent(AbstractRipper.USER_AGENT).retries(1).get();
+        try {
+            ripper.getNextPage(firstPage);
+            // If we don't throw, we failed the text because there *was* a next
+            // page even though there shouldn't be.
+            Assertions.fail();
+        } catch (IOException exception) {
+            Assertions.assertTrue(true);
+        }
+    }
+
+    @Test
+    @Tag("flaky") // It seems like fetching the document within the test can be flaky.
+    public void testGetNextPage_HasNextPage() throws IOException, URISyntaxException {
+        URL url = new URI("https://fapwiz.com/miaipanema/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+
+        Document firstPage = Http.url(url).userAgent(AbstractRipper.USER_AGENT).retries(1).get();
+        try {
+            Document doc = ripper.getNextPage(firstPage);
+            Assertions.assertNotNull(doc);
+        } catch (IOException exception) {
+            // We should have found a next page but didn't.
+            Assertions.fail();
+        }
+    }
+
+    @Test
+    public void testRipPost() throws IOException, URISyntaxException {
+        URL url = new URI("https://fapwiz.com/petiteasiantravels/riding-at-9-months-pregnant/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        testRipper(ripper);
+    }
+
+    @Test
+    public void testRipPostWithNumbersInUsername1() throws IOException, URISyntaxException {
+        URL url = new URI("https://fapwiz.com/desperate_bug_7776/lets-be-friends-that-secretly-fuck-thanks/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        testRipper(ripper);
+    }
+
+    @Test
+    public void testRipPostWithEmojiInShortUrl() throws IOException, URISyntaxException {
+        URL url = new URI("https://fapwiz.com/miaipanema/my-grip-needs-a-name-%f0%9f%a4%ad%f0%9f%91%87%f0%9f%8f%bc/")
+                .toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        testRipper(ripper);
+    }
+
+    @Test
+    public void testRipPostWithEmojiInLongUrlAtEnd() throws IOException, URISyntaxException {
+        URL url = new URI(
+                "https://fapwiz.com/bimeat1998/just-imagine-youre-out-with-your-girl-and-your-buddies-and-then-she-makes-this-move-%f0%9f%98%8d/")
+                .toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        testRipper(ripper);
+    }
+
+    @Test
+    public void testRipPostWithEmojiInLongUrlInTheMiddle() throws IOException, URISyntaxException {
+        URL url = new URI(
+                "https://fapwiz.com/miaipanema/new-pov-couch-sex-with-perfect-cumshot-on-my-ass-%f0%9f%92%a6-you-know-where-to-get-it-%f0%9f%94%97%f0%9f%92%96/")
+                .toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        testRipper(ripper);
+    }
+
+    // TODO Test rip user
+
+    // TODO Test rip category
+
+    @Test
+    public void testPostGetGID1_Simple() throws IOException, URISyntaxException {
+        URL url = new URI("https://fapwiz.com/petiteasiantravels/riding-at-9-months-pregnant/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        Assertions.assertEquals("post_petiteasiantravels_riding-at-9-months-pregnant", ripper.getGID(url));
+    }
+
+    // Test Post pages GetGID
+
+    @Test
+    public void testPostGetGID2_WithEmojiInLongUrlInTheMiddle() throws IOException, URISyntaxException {
+        URL url = new URI(
+                "https://fapwiz.com/miaipanema/new-pov-couch-sex-with-perfect-cumshot-on-my-ass-%f0%9f%92%a6-you-know-where-to-get-it-%f0%9f%94%97%f0%9f%92%96/")
+                .toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+
+        // In this case the filesystem safe version of the GID is
+        // "post_miaipanema_new-pov-couch-sex-with-perfect-cumshot-on-my-ass-f09f92a6-you-know-where-to-"
+        // but the GID doesn't truncate and doesn't remove non-filesystem-safe
+        // characters.
+        String gid = ripper.getGID(url);
+        Assertions.assertEquals(
+                "post_miaipanema_new-pov-couch-sex-with-perfect-cumshot-on-my-ass-%f0%9f%92%a6-you-know-where-to-get-it-%f0%9f%94%97%f0%9f%92%96",
+                gid);
+
+        // Test directory name on disk (filesystem safe sanitized as the ripper will
+        // do).
+        String directoryName = Utils.filesystemSafe(ripper.getHost() + "_" + gid);
+        Assertions.assertEquals(
+                "fapwiz_post_miaipanema_new-pov-couch-sex-with-perfect-cumshot-on-my-ass-f09f92a6-you-know-where-to-",
+                directoryName);
+    }
+
+    // Test User pages GetGID
+
+    @Test
+    public void testUserGetGID1_Simple() throws IOException, URISyntaxException {
+        // Test a "simple" username that is all letters.
+        URL url = new URI("https://fapwiz.com/petiteasiantravels/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        Assertions.assertEquals("user_petiteasiantravels", ripper.getGID(url));
+    }
+
+    @Test
+    public void testUserGetGID2_Numbers() throws IOException, URISyntaxException {
+        // Test a more complex username that contains numbers.
+        URL url = new URI("https://fapwiz.com/bimeat1998/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        Assertions.assertEquals("user_bimeat1998", ripper.getGID(url));
+    }
+
+    @Test
+    public void testUserGetGID3_HyphensAndNumbers() throws IOException, URISyntaxException {
+        // Test a more complex username that contains hyphens and numbers.
+        URL url = new URI("https://fapwiz.com/used-airport-4076/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        Assertions.assertEquals("user_used-airport-4076", ripper.getGID(url));
+    }
+
+    @Test
+    public void testUserGetGID4_Underscores() throws IOException, URISyntaxException {
+        // Test a more complex username that contains underscores.
+        URL url = new URI("https://fapwiz.com/desperate_bug_7776/").toURL();
+        FapwizRipper ripper = new FapwizRipper(url);
+        Assertions.assertEquals("user_desperate_bug_7776", ripper.getGID(url));
+    }
+}