Merge pull request #7 from RipMeApp/master

Sync

README.md

@@ -36,6 +36,9 @@ For information about running the `.jar` file, see [the How To Run wiki](https:/
 
 * Quickly downloads all images in an online album (see supported sites below)
 * Easily re-rip albums to fetch new content
+* Built in updater
+* Can rip images from tumblr in the size they were uploaded in [See here for how to enable](https://github.com/RipMeApp/ripme/wiki/Config-options#tumblrget_raw_image)
+* Skips already downloaded images by default
 
 ## [List of Supported Sites](https://github.com/ripmeapp/ripme/wiki/Supported-Sites)
 

pom.xml

@@ -4,7 +4,7 @@
   <groupId>com.rarchives.ripme</groupId>
   <artifactId>ripme</artifactId>
   <packaging>jar</packaging>
-  <version>1.7.24</version>
+  <version>1.7.27</version>
   <name>ripme</name>
   <url>http://rip.rarchives.com</url>
   <properties>

ripme.json

@@ -1,6 +1,9 @@
 {
-    "latestVersion": "1.7.24",
+    "latestVersion": "1.7.27",
     "changeList": [
+        "1.7.27: IG ripper can now rip from tags; fixed json parsing issues",
+        "1.7.26: fixed instagram ripper",
+        "1.7.25: Fixed instagram ripper; Added an option to use short names for 8muses; Added tsuminoRipper; Added support for incase.buttsmithy.com",
         "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",

src/main/java/com/rarchives/ripme/ripper/AbstractRipper.java

@@ -174,7 +174,7 @@ public abstract class AbstractRipper
      *      URL of the file
      * @param saveAs
      *      Path of the local file to save the content to.
-     * @return True on success, flase on failure.
+     * @return True on success, false on failure.
      */
     public abstract boolean addURLToDownload(URL url, File saveAs);
 
@@ -206,11 +206,13 @@ public abstract class AbstractRipper
      *      The HTTP referrer to use while downloading this file.
      * @param cookies
      *      The cookies to send to the server while downloading this file.
+     * @param fileName
+     *      The name that file will be written to
      * @return 
      *      True if downloaded successfully
      *      False if failed to download
      */
-    protected boolean addURLToDownload(URL url, String prefix, String subdirectory, String referrer, Map<String, String> cookies) {
+    protected boolean addURLToDownload(URL url, String prefix, String subdirectory, String referrer, Map<String, String> cookies, String fileName) {
         // Don't re-add the url if it was downloaded in a previous rip
         if (Utils.getConfigBoolean("remember.url_history", true) && !isThisATest()) {
             if (hasDownloadedURL(url.toExternalForm())) {
@@ -225,9 +227,18 @@ public abstract class AbstractRipper
             logger.debug("Ripper has been stopped");
             return false;
         }
-        logger.debug("url: " + url + ", prefix: " + prefix + ", subdirectory" + subdirectory + ", referrer: " + referrer + ", cookies: " + cookies);
+        logger.debug("url: " + url + ", prefix: " + prefix + ", subdirectory" + subdirectory + ", referrer: " + referrer + ", cookies: " + cookies + ", fileName: " + fileName);
-        String saveAs = url.toExternalForm();
+        String saveAs;
+        if (fileName != null) {
+            saveAs = fileName;
+            // Get the extension of the file
+            String extension = url.toExternalForm().substring(url.toExternalForm().lastIndexOf(".") + 1);
+            saveAs = saveAs + "." + extension;
+        } else {
+            saveAs = url.toExternalForm();
             saveAs = saveAs.substring(saveAs.lastIndexOf('/')+1);
+        }
+
         if (saveAs.indexOf('?') >= 0) { saveAs = saveAs.substring(0, saveAs.indexOf('?')); }
         if (saveAs.indexOf('#') >= 0) { saveAs = saveAs.substring(0, saveAs.indexOf('#')); }
         if (saveAs.indexOf('&') >= 0) { saveAs = saveAs.substring(0, saveAs.indexOf('&')); }
@@ -274,7 +285,11 @@ public abstract class AbstractRipper
      * @return True on success, flase on failure.
      */
     protected boolean addURLToDownload(URL url, String prefix, String subdirectory) {
-        return addURLToDownload(url, prefix, subdirectory, null, null);
+        return addURLToDownload(url, prefix, subdirectory, null, null, null);
+    }
+
+    protected boolean addURLToDownload(URL url, String prefix, String subdirectory, String referrer, Map<String, String> cookies) {
+        return addURLToDownload(url, prefix, subdirectory, referrer, cookies, null);
     }
 
     /**
@@ -290,6 +305,8 @@ public abstract class AbstractRipper
         // Use empty subdirectory
         return addURLToDownload(url, prefix, "");
     }
+
+
     /**
      * Waits for downloading threads to complete.
      */

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

@@ -11,6 +11,7 @@ import java.util.Map;
 import java.util.regex.Matcher;
 import java.util.regex.Pattern;
 
+import com.rarchives.ripme.utils.Utils;
 import org.jsoup.Connection.Response;
 import org.jsoup.nodes.Document;
 import org.jsoup.nodes.Element;
@@ -125,7 +126,11 @@ public class EightmusesRipper extends AbstractHTMLRipper {
                         logger.info("Retrieving full-size image location from " + imageHref);
                         image = getFullSizeImage(imageHref);
                         URL imageUrl = new URL(image);
-                        addURLToDownload(imageUrl, getPrefix(x), getSubdir(page.select("title").text()), this.url.toExternalForm(), cookies);
+                        if (Utils.getConfigBoolean("8muses.use_short_names", false)) {
+                            addURLToDownload(imageUrl, getPrefixShort(x), getSubdir(page.select("title").text()), this.url.toExternalForm(), cookies, "");
+                        } else {
+                            addURLToDownload(imageUrl, getPrefixLong(x), getSubdir(page.select("title").text()), this.url.toExternalForm(), cookies);
+                        }
                         // X is our page index
                         x++;
 
@@ -178,8 +183,11 @@ public class EightmusesRipper extends AbstractHTMLRipper {
         addURLToDownload(url, getPrefix(index), "", this.url.toExternalForm(), cookies);
     }
 
-    @Override
+    public String getPrefixLong(int index) {
-    public String getPrefix(int index) {
         return String.format("%03d_", index);
     }
+
+    public String getPrefixShort(int index) {
+        return String.format("%03d", index);
+    }
 }

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

@@ -1,8 +1,11 @@
 package com.rarchives.ripme.ripper.rippers;
 
+import java.io.BufferedReader;
 import java.io.IOException;
+import java.io.InputStreamReader;
 import java.net.MalformedURLException;
 import java.net.URL;
+import java.net.URLConnection;
 import java.time.*;
 import java.time.format.DateTimeFormatter;
 import java.util.ArrayList;
@@ -25,6 +28,9 @@ import com.rarchives.ripme.utils.Utils;
 
 public class InstagramRipper extends AbstractHTMLRipper {
     String nextPageID = "";
+    private String qHash;
+    private  boolean rippingTag = false;
+    private String tagName;
 
     private String userID;
 
@@ -130,13 +136,31 @@ public class InstagramRipper extends AbstractHTMLRipper {
         p = Pattern.compile("^https?://www.instagram.com/explore/tags/([^/]+)/?");
         m = p.matcher(url.toExternalForm());
         if (m.matches()) {
+            rippingTag = true;
+            tagName = m.group(1);
             return m.group(1);
         }
 
         throw new MalformedURLException("Unable to find user in " + url);
     }
 
+    private String stripHTMLTags(String t) {
+        t = t.replaceAll("<html>\n" +
+                " <head></head>\n" +
+                " <body>", "");
+        t.replaceAll("</body>\n" +
+                "</html>", "");
+        t = t.replaceAll("\n", "");
+        t = t.replaceAll("=\"\"", "");
+        return t;
+    }
+
+
     private JSONObject getJSONFromPage(Document firstPage) throws IOException {
+        // Check if this page is HTML + JSON or jsut json
+        if (!firstPage.html().contains("window._sharedData =")) {
+            return new JSONObject(stripHTMLTags(firstPage.html()));
+        }
         String jsonText = "";
         try {
             for (Element script : firstPage.select("script[type=text/javascript]")) {
@@ -153,8 +177,10 @@ public class InstagramRipper extends AbstractHTMLRipper {
 
     @Override
     public Document getFirstPage() throws IOException {
-        userID = getGID(url);
+        Document p = Http.url(url).get();
-        return Http.url(url).get();
+        // Get the query hash so we can download the next page
+        qHash = getQHash(p);
+        return p;
     }
 
     private String getVideoFromPage(String videoID) {
@@ -210,25 +236,41 @@ public class InstagramRipper extends AbstractHTMLRipper {
 
         if (!url.toExternalForm().contains("/p/")) {
             JSONArray datas = new JSONArray();
+            if (!rippingTag) {
+                // This first try only works on data from the first page
                 try {
                     JSONArray profilePage = json.getJSONObject("entry_data").getJSONArray("ProfilePage");
-                datas = profilePage.getJSONObject(0).getJSONObject("user").getJSONObject("media").getJSONArray("nodes");
+                    userID = profilePage.getJSONObject(0).getString("logging_page_id").replaceAll("profilePage_", "");
+                    datas = profilePage.getJSONObject(0).getJSONObject("graphql").getJSONObject("user")
+                            .getJSONObject("edge_owner_to_timeline_media").getJSONArray("edges");
                 } catch (JSONException e) {
-                // Handle hashtag pages
+                    datas = json.getJSONObject("data").getJSONObject("user")
-                datas = json.getJSONObject("entry_data").getJSONArray("TagPage").getJSONObject(0)
+                            .getJSONObject("edge_owner_to_timeline_media").getJSONArray("edges");
-                        .getJSONObject("tag").getJSONObject("media").getJSONArray("nodes");
+                }
+            } else {
+                try {
+                    JSONArray tagPage = json.getJSONObject("entry_data").getJSONArray("TagPage");
+                    datas = tagPage.getJSONObject(0).getJSONObject("graphql").getJSONObject("hashtag")
+                            .getJSONObject("edge_hashtag_to_media").getJSONArray("edges");
+                } catch (JSONException e) {
+                    datas = json.getJSONObject("data").getJSONObject("hashtag").getJSONObject("edge_hashtag_to_media")
+                            .getJSONArray("edges");
+                }
             }
             for (int i = 0; i < datas.length(); i++) {
                 JSONObject data = (JSONObject) datas.get(i);
-                Long epoch = data.getLong("date");
+                data = data.getJSONObject("node");
+                Long epoch = data.getLong("taken_at_timestamp");
                 Instant instant = Instant.ofEpochSecond(epoch);
                 String image_date = DateTimeFormatter.ofPattern("yyyy_MM_dd_hh:mm_").format(ZonedDateTime.ofInstant(instant, ZoneOffset.UTC));
+                // It looks like tag pages don't have the __typename key
+                if (!rippingTag) {
                     if (data.getString("__typename").equals("GraphSidecar")) {
                         try {
-                        Document slideShowDoc = Http.url(new URL ("https://www.instagram.com/p/" + data.getString("code"))).get();
+                            Document slideShowDoc = Http.url(new URL("https://www.instagram.com/p/" + data.getString("shortcode"))).get();
                             List<String> toAdd = getPostsFromSinglePage(slideShowDoc);
-                        for (int slideShowInt=0; slideShowInt<toAdd.size(); slideShowInt++) {
+                            for (int slideShowInt = 0; slideShowInt < toAdd.size(); slideShowInt++) {
-                            addURLToDownload(new URL(toAdd.get(slideShowInt)), image_date + data.getString("code"));
+                                addURLToDownload(new URL(toAdd.get(slideShowInt)), image_date + data.getString("shortcode"));
                             }
                         } catch (MalformedURLException e) {
                             logger.error("Unable to download slide show, URL was malformed");
@@ -236,6 +278,7 @@ public class InstagramRipper extends AbstractHTMLRipper {
                             logger.error("Unable to download slide show");
                         }
                     }
+                }
                 try {
                     if (!data.getBoolean("is_video")) {
                         if (imageURLs.size() == 0) {
@@ -246,9 +289,9 @@ public class InstagramRipper extends AbstractHTMLRipper {
                         addURLToDownload(new URL(getOriginalUrl(data.getString("thumbnail_src"))), image_date);
                     } else {
                         if (!Utils.getConfigBoolean("instagram.download_images_only", false)) {
-                            addURLToDownload(new URL(getVideoFromPage(data.getString("code"))), image_date);
+                            addURLToDownload(new URL(getVideoFromPage(data.getString("shortcode"))), image_date);
                         } else {
-                            sendUpdate(RipStatusMessage.STATUS.DOWNLOAD_WARN, "Skipping video " + data.getString("code"));
+                            sendUpdate(RipStatusMessage.STATUS.DOWNLOAD_WARN, "Skipping video " + data.getString("shortcode"));
                         }
                     }
                 } catch (MalformedURLException e) {
@@ -274,19 +317,13 @@ public class InstagramRipper extends AbstractHTMLRipper {
     public Document getNextPage(Document doc) throws IOException {
         Document toreturn;
         if (!nextPageID.equals("") && !isThisATest()) {
-            if (url.toExternalForm().contains("/tags/")) {
+            if (rippingTag) {
                 try {
-                    // Sleep for a while to avoid a ban
                     sleep(2500);
-                    if (url.toExternalForm().substring(url.toExternalForm().length() - 1).equals("/")) {
+                     toreturn = Http.url("https://www.instagram.com/graphql/query/?query_hash=" + qHash +
-                        toreturn = Http.url(url.toExternalForm() + "?max_id=" + nextPageID).get();
+                                     "&variables={\"tag_name\":\"" + tagName + "\",\"first\":4,\"after\":\"" + nextPageID + "\"}").ignoreContentType().get();
-                    } else {
+                    // Sleep for a while to avoid a ban
-                        toreturn = Http.url(url.toExternalForm() + "/?max_id=" + nextPageID).get();
-                    }
                     logger.info(toreturn.html());
-                    if (!hasImage(toreturn)) {
-                        throw new IOException("No more pages");
-                    }
                     return toreturn;
 
                 } catch (IOException e) {
@@ -297,8 +334,9 @@ public class InstagramRipper extends AbstractHTMLRipper {
             try {
                 // Sleep for a while to avoid a ban
                 sleep(2500);
-                toreturn = Http.url("https://www.instagram.com/" + userID + "/?max_id=" + nextPageID).get();
+                toreturn = Http.url("https://www.instagram.com/graphql/query/?query_hash=" + qHash + "&variables=" +
-                if (!hasImage(toreturn)) {
+                        "{\"id\":\"" + userID + "\",\"first\":100,\"after\":\"" + nextPageID + "\"}").ignoreContentType().get();
+                if (!pageHasImages(toreturn)) {
                     throw new IOException("No more pages");
                 }
                 return toreturn;
@@ -315,20 +353,56 @@ public class InstagramRipper extends AbstractHTMLRipper {
         addURLToDownload(url);
     }
 
-    private boolean hasImage(Document doc) {
+    private boolean pageHasImages(Document doc) {
-        try {
+        logger.info("BAD DATA: " + stripHTMLTags(doc.html()));
-            JSONObject json = getJSONFromPage(doc);
+        JSONObject json = new JSONObject(stripHTMLTags(doc.html()));
-            JSONArray profilePage = json.getJSONObject("entry_data").getJSONArray("ProfilePage");
+        int numberOfImages = json.getJSONObject("data").getJSONObject("user")
-            JSONArray datas = profilePage.getJSONObject(0).getJSONObject("user").getJSONObject("media").getJSONArray("nodes");
+                .getJSONObject("edge_owner_to_timeline_media").getJSONArray("edges").length();
-            logger.info(datas.length());
+        if (numberOfImages == 0) {
-            if (datas.length() == 0) {
             return false;
         }
         return true;
-        } catch (IOException e) {
-            return false;
     }
 
+    private String getQHash(Document doc) {
+        String jsFileURL = "https://www.instagram.com" + doc.select("link[rel=preload]").attr("href");
+        StringBuilder sb = new StringBuilder();
+        Document jsPage;
+        try {
+            // We can't use Jsoup here because it won't download a non-html file larger than a MB
+            // even if you set maxBodySize to 0
+            URLConnection connection = new URL(jsFileURL).openConnection();
+            BufferedReader in = new BufferedReader(new InputStreamReader(connection.getInputStream()));
+            String line;
+            while ((line = in.readLine()) != null) {
+                sb.append(line);
+            }
+            in.close();
+
+        } catch (MalformedURLException e) {
+            logger.info("Unable to get query_hash, " + jsFileURL + " is a malformed URL");
+            return null;
+        } catch (IOException e) {
+            logger.info("Unable to get query_hash");
+            logger.info(e.getMessage());
+            return null;
+        }
+        if (!rippingTag) {
+            Pattern jsP = Pattern.compile("o},queryId:.([a-zA-Z0-9]+).");
+            Matcher m = jsP.matcher(sb.toString());
+            if (m.find()) {
+                return m.group(1);
+            }
+        } else {
+            Pattern jsP = Pattern.compile("return e.tagMedia.byTagName.get\\(t\\).pagination},queryId:.([a-zA-Z0-9]+).");
+            Matcher m = jsP.matcher(sb.toString());
+            if (m.find()) {
+                return m.group(1);
+            }
+        }
+        logger.info("Could not find query_hash on " + jsFileURL);
+        return null;
+
     }
 
 }

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

@@ -0,0 +1,108 @@
+package com.rarchives.ripme.ripper.rippers;
+
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.net.URLEncoder;
+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 com.rarchives.ripme.ui.RipStatusMessage;
+import org.json.JSONArray;
+import org.json.JSONObject;
+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 TsuminoRipper extends AbstractHTMLRipper {
+    private Map<String,String> cookies = new HashMap<>();
+
+    public TsuminoRipper(URL url) throws IOException {
+        super(url);
+    }
+
+    private JSONArray getPageUrls() {
+        String postURL = "http://www.tsumino.com/Read/Load";
+        try {
+            // This sessionId will expire and need to be replaced
+            cookies.put("ASP.NET_SessionId","c4rbzccf0dvy3e0cloolmlkq");
+            logger.info(cookies);
+            Document doc = Jsoup.connect(postURL).data("q", getAlbumID()).userAgent(USER_AGENT).cookies(cookies).referrer("http://www.tsumino.com/Read/View/" + getAlbumID()).post();
+            String jsonInfo = doc.html().replaceAll("<html>","").replaceAll("<head></head>", "").replaceAll("<body>", "").replaceAll("</body>", "")
+                    .replaceAll("</html>", "").replaceAll("\n", "");
+            logger.info(jsonInfo);
+            JSONObject json = new JSONObject(jsonInfo);
+            logger.info(json.getJSONArray("reader_page_urls"));
+            return json.getJSONArray("reader_page_urls");
+        } catch (IOException e) {
+            logger.info(e);
+            sendUpdate(RipStatusMessage.STATUS.DOWNLOAD_ERRORED, "Unable to download album, please compete the captcha at http://www.tsumino.com/Read/Auth/"
+                    + getAlbumID() + " and try again");
+            return null;
+        }
+    }
+
+    @Override
+    public String getHost() {
+        return "tsumino";
+    }
+
+    @Override
+    public String getDomain() {
+        return "tsumino.com";
+    }
+
+    @Override
+    public String getGID(URL url) throws MalformedURLException {
+        Pattern p = Pattern.compile("https?://www.tsumino.com/Book/Info/([0-9]+)/([a-zA-Z0-9_-]*)");
+        Matcher m = p.matcher(url.toExternalForm());
+        if (m.matches()) {
+            return m.group(1) + "_" + m.group(2);
+        }
+        throw new MalformedURLException("Expected tsumino URL format: " +
+                "tsumino.com/Book/Info/ID/TITLE - got " + url + " instead");
+    }
+
+    private String getAlbumID() {
+        Pattern p = Pattern.compile("https?://www.tsumino.com/Book/Info/([0-9]+)/\\S*");
+        Matcher m = p.matcher(url.toExternalForm());
+        if (m.matches()) {
+            return m.group(1);
+        }
+        return null;
+    }
+
+    @Override
+    public Document getFirstPage() throws IOException {
+        Connection.Response resp = Http.url(url).response();
+        cookies.putAll(resp.cookies());
+        logger.info(resp.parse());
+        return resp.parse();
+    }
+
+    @Override
+    public List<String> getURLsFromPage(Document doc) {
+        JSONArray imageIds = getPageUrls();
+        List<String> result = new ArrayList<>();
+        for (int i = 0; i < imageIds.length(); i++) {
+            result.add("http://www.tsumino.com/Image/Object?name=" + URLEncoder.encode(imageIds.getString(i)));
+        }
+
+        return result;
+    }
+
+    @Override
+    public void downloadURL(URL url, int index) {
+        sleep(1000);
+        addURLToDownload(url, getPrefix(index));
+    }
+}

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

@@ -37,6 +37,7 @@ public class WordpressComicRipper extends AbstractHTMLRipper {
     private static List<String> explicit_domains = Arrays.asList(
         "www.totempole666.com",
         "buttsmithy.com",
+        "incase.buttsmithy.com",
         "themonsterunderthebed.net",
         "prismblush.com",
         "www.konradokonski.com",
@@ -87,6 +88,12 @@ public class WordpressComicRipper extends AbstractHTMLRipper {
                 return true;
             }
 
+            Pattern buttsmithyIncasePat = Pattern.compile("https?://incase.buttsmithy.com/comic/([a-zA-Z0-9_-]*)/?$");
+            Matcher buttsmithyIncaseMat = buttsmithyIncasePat.matcher(url.toExternalForm());
+            if (buttsmithyIncaseMat.matches()) {
+                return true;
+            }
+
             Pattern theMonsterUnderTheBedPat = Pattern.compile("https?://themonsterunderthebed.net/\\?comic=([a-zA-Z0-9_-]*)/?$");
             Matcher theMonsterUnderTheBedMat = theMonsterUnderTheBedPat.matcher(url.toExternalForm());
             if (theMonsterUnderTheBedMat.matches()) {
@@ -178,6 +185,12 @@ public class WordpressComicRipper extends AbstractHTMLRipper {
             return getHost() + "_" + prismblushMat.group(1);
         }
 
+        Pattern buttsmithyIncasePat = Pattern.compile("https?://incase.buttsmithy.com/comic/([a-zA-Z0-9_-]*)/?$");
+        Matcher buttsmithyIncaseMat = buttsmithyIncasePat.matcher(url.toExternalForm());
+        if (buttsmithyIncaseMat.matches()) {
+            return getHost() + "_" + buttsmithyIncaseMat.group(1).replaceAll("-page-\\d", "").replaceAll("-pg-\\d", "");
+        }
+
         Pattern comicsxxxPat = Pattern.compile("https?://comics-xxx.com/([a-zA-Z0-9_\\-]*)/?$");
         Matcher comicsxxxMat = comicsxxxPat.matcher(url.toExternalForm());
         if (comicsxxxMat.matches()) {

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 = "1.7.24";
+    private static final String DEFAULT_VERSION = "1.7.27";
     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";