Added VK ripper

This commit is contained in:
4pr0n 2014-04-05 13:44:43 -07:00
parent e0275949f7
commit d51ad485f6
4 changed files with 194 additions and 1 deletions

2
.gitignore vendored
View File

@ -4,3 +4,5 @@ ripme.log
rips/
.history
ripme.jar.update
*.swp
ripme.jar

View File

@ -4,7 +4,7 @@
<groupId>com.rarchives.ripme</groupId>
<artifactId>ripme</artifactId>
<packaging>jar</packaging>
<version>1.0.2</version>
<version>1.0.3</version>
<name>ripme</name>
<url>http://rip.rarchives.com</url>
<properties>

View File

@ -0,0 +1,158 @@
package com.rarchives.ripme.ripper.rippers;
import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.apache.log4j.Logger;
import org.json.JSONArray;
import org.json.JSONObject;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import com.rarchives.ripme.ripper.AbstractRipper;
public class VkRipper extends AbstractRipper {
private static final String DOMAIN = "vk.com",
HOST = "vk";
private static final Logger logger = Logger.getLogger(SeeniveRipper.class);
public VkRipper(URL url) throws IOException {
super(url);
}
@Override
public boolean canRip(URL url) {
return url.getHost().endsWith(DOMAIN);
}
@Override
public URL sanitizeURL(URL url) throws MalformedURLException {
return url;
}
@Override
public void rip() throws IOException {
Map<String,String> photoIDsToURLs = new HashMap<String,String>();
int offset = 0;
while (true) {
logger.info(" Retrieving " + this.url);
// al=1&offset=80&part=1
Map<String,String> postData = new HashMap<String,String>();
postData.put("al", "1");
postData.put("offset", Integer.toString(offset));
postData.put("part", "1");
Document doc = Jsoup.connect(this.url.toExternalForm())
.header("Referer", this.url.toExternalForm())
.ignoreContentType(true)
.userAgent(USER_AGENT)
.timeout(5000)
.data(postData)
.post();
String body = doc.toString();
if (!body.contains("<div")) {
break;
}
body = body.substring(body.indexOf("<div"));
doc = Jsoup.parseBodyFragment(body);
List<Element> elements = doc.select("a");
Set<String> photoIDsToGet = new HashSet<String>();
for (Element a : elements) {
if (!a.attr("onclick").contains("showPhoto('")) {
logger.error("a: " + a);
continue;
}
String photoID = a.attr("onclick");
photoID = photoID.substring(photoID.indexOf("showPhoto('") + "showPhoto('".length());
photoID = photoID.substring(0, photoID.indexOf("'"));
if (!photoIDsToGet.contains(photoID)) {
photoIDsToGet.add(photoID);
}
}
for (String photoID : photoIDsToGet) {
if (!photoIDsToURLs.containsKey(photoID)) {
try {
photoIDsToURLs.putAll(getPhotoIDsToURLs(photoID));
} catch (IOException e) {
logger.error("Exception while retrieving photo id " + photoID, e);
continue;
}
}
if (!photoIDsToURLs.containsKey(photoID)) {
logger.error("Could not find URL for photo ID: " + photoID);
continue;
}
String url = photoIDsToURLs.get(photoID);
addURLToDownload(new URL(url));
}
logger.info("Received " + elements.size() + " elements");
if (elements.size() < 40) {
break;
}
offset += elements.size();
}
waitForThreads();
}
private Map<String,String> getPhotoIDsToURLs(String photoID) throws IOException {
Map<String,String> photoIDsToURLs = new HashMap<String,String>();
Map<String,String> postData = new HashMap<String,String>();
// act=show&al=1&list=album45506334_172415053&module=photos&photo=45506334_304658196
postData.put("list", getGID(this.url));
postData.put("act", "show");
postData.put("al", "1");
postData.put("module", "photos");
postData.put("photo", photoID);
Document doc = Jsoup
.connect("https://vk.com/al_photos.php")
.header("Referer", this.url.toExternalForm())
.ignoreContentType(true)
.userAgent(USER_AGENT)
.timeout(5000)
.data(postData)
.post();
String jsonString = doc.toString();
jsonString = jsonString.substring(jsonString.indexOf("<!json>") + "<!json>".length());
jsonString = jsonString.substring(0, jsonString.indexOf("<!>"));
JSONArray json = new JSONArray(jsonString);
for (int i = 0; i < json.length(); i++) {
JSONObject jsonImage = json.getJSONObject(i);
for (String key : new String[] {"z_src", "y_src", "x_src"}) {
if (!jsonImage.has(key)) {
continue;
}
photoIDsToURLs.put(jsonImage.getString("id"), jsonImage.getString(key));
break;
}
}
return photoIDsToURLs;
}
@Override
public String getHost() {
return HOST;
}
@Override
public String getGID(URL url) throws MalformedURLException {
Pattern p = Pattern.compile("^https?://(www\\.)?vk\\.com/(photos|album)([a-zA-Z0-9_]{1,}).*$");
Matcher m = p.matcher(url.toExternalForm());
if (!m.matches()) {
throw new MalformedURLException("Expected format: http://vk.com/album#### or vk.com/photos####");
}
int count = m.groupCount();
return m.group(count - 1) + m.group(count);
}
}

View File

@ -0,0 +1,33 @@
package com.rarchives.ripme.tst.ripper.rippers;
import java.io.IOException;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
import com.rarchives.ripme.ripper.rippers.VkRipper;
public class VkRipperTest extends RippersTest {
public void testVkAlbum() throws IOException {
if (!DOWNLOAD_CONTENT) {
return;
}
List<URL> contentURLs = new ArrayList<URL>();
contentURLs.add(new URL("https://vk.com/album45506334_172415053"));
//contentURLs.add(new URL("https://vk.com/album45506334_0"));
//contentURLs.add(new URL("https://vk.com/photos45506334"));
for (URL url : contentURLs) {
try {
VkRipper ripper = new VkRipper(url);
ripper.rip();
assert(ripper.getWorkingDir().listFiles().length > 1);
deleteDir(ripper.getWorkingDir());
} catch (Exception e) {
e.printStackTrace();
fail("Error while ripping URL " + url + ": " + e.getMessage());
}
}
}
}