Merge #428 from kas-luthor/fix-299: Rewritten E621 ripper

This commit is contained in:
metaprime 2017-03-02 01:30:09 -08:00 committed by GitHub
commit ec565c3864
2 changed files with 171 additions and 60 deletions

View File

@ -6,10 +6,12 @@ import com.rarchives.ripme.ripper.DownloadThreadPool;
import com.rarchives.ripme.utils.Http; import com.rarchives.ripme.utils.Http;
import com.rarchives.ripme.utils.Utils; import com.rarchives.ripme.utils.Utils;
import java.io.IOException; import java.io.IOException;
import java.io.UnsupportedEncodingException;
import java.net.MalformedURLException; import java.net.MalformedURLException;
import java.net.URI; import java.net.URI;
import java.net.URISyntaxException; import java.net.URISyntaxException;
import java.net.URL; import java.net.URL;
import java.net.URLDecoder;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.List; import java.util.List;
import java.util.logging.Level; import java.util.logging.Level;
@ -24,12 +26,10 @@ import org.jsoup.select.Elements;
* *
* @author * @author
*/ */
public class E621Ripper extends AbstractHTMLRipper{ public class E621Ripper extends AbstractHTMLRipper {
private static Pattern gidPattern=null; public static final int POOL_IMAGES_PER_PAGE = 24;
private static Pattern gidPattern2=null;
private static Pattern gidPatternPool=null;
private DownloadThreadPool e621ThreadPool=new DownloadThreadPool("e621"); private DownloadThreadPool e621ThreadPool = new DownloadThreadPool("e621");
public E621Ripper(URL url) throws IOException { public E621Ripper(URL url) throws IOException {
super(url); super(url);
@ -52,19 +52,37 @@ public class E621Ripper extends AbstractHTMLRipper{
@Override @Override
public Document getFirstPage() throws IOException { public Document getFirstPage() throws IOException {
if(url.getPath().startsWith("/pool/show/")) if (url.getPath().startsWith("/pool/show/")) {
return Http.url("https://e621.net/pool/show/"+getTerm(url)).get(); return Http.url("https://e621.net/pool/show/" + getTerm(url)).get();
else } else {
return Http.url("https://e621.net/post/index/1/"+getTerm(url)).get(); return Http.url("https://e621.net/post/index/1/" + getTerm(url)).get();
}
} }
@Override @Override
public List<String> getURLsFromPage(Document page) { public List<String> getURLsFromPage(Document page) {
Elements elements=page.select("#post-list .thumb a,#pool-show .thumb a"); Elements elements = page.select("#post-list .thumb a,#pool-show .thumb a");
List<String> res=new ArrayList<String>(elements.size()); List<String> res = new ArrayList<String>(elements.size());
for(Element e:elements){ if (page.getElementById("pool-show") != null) {
res.add(e.absUrl("href")+"#"+e.child(0).attr("id").substring(1)); int index = 0;
Element e = page.getElementById("paginator");
if (e != null) {
e = e.getElementsByClass("current").first();
if (e != null) {
index = (Integer.parseInt(e.text()) - 1) * POOL_IMAGES_PER_PAGE;
}
}
for (Element e_ : elements) {
res.add(e_.absUrl("href") + "#" + ++index);
}
} else {
for (Element e : elements) {
res.add(e.absUrl("href") + "#" + e.child(0).attr("id").substring(1));
}
} }
return res; return res;
@ -72,9 +90,10 @@ public class E621Ripper extends AbstractHTMLRipper{
@Override @Override
public Document getNextPage(Document page) throws IOException { public Document getNextPage(Document page) throws IOException {
for(Element e:page.select("#paginator a")){ for (Element e : page.select("#paginator a")) {
if(e.attr("rel").equals("next")) if (e.attr("rel").equals("next")) {
return Http.url(e.absUrl("href")).get(); return Http.url(e.absUrl("href")).get();
}
} }
return null; return null;
@ -85,9 +104,17 @@ public class E621Ripper extends AbstractHTMLRipper{
e621ThreadPool.addThread(new Thread(new Runnable() { e621ThreadPool.addThread(new Thread(new Runnable() {
public void run() { public void run() {
try { try {
Document page=Http.url(url).get(); Document page = Http.url(url).get();
Element e = page.getElementById("image");
if (e != null) {
addURLToDownload(new URL(e.absUrl("src")), Utils.getConfigBoolean("download.save_order", true) ? url.getRef() + "-" : "");
} else if ((e = page.select(".content object>param[name=\"movie\"]").first()) != null) {
addURLToDownload(new URL(e.absUrl("value")), Utils.getConfigBoolean("download.save_order", true) ? url.getRef() + "-" : "");
} else {
Logger.getLogger(E621Ripper.class.getName()).log(Level.WARNING, "Unsupported media type - please report to program author: " + url.toString());
}
addURLToDownload(new URL(page.getElementById("image").absUrl("src")),Utils.getConfigBoolean("download.save_order",true)?url.getRef()+"-":"");
} catch (IOException ex) { } catch (IOException ex) {
Logger.getLogger(E621Ripper.class.getName()).log(Level.SEVERE, null, ex); Logger.getLogger(E621Ripper.class.getName()).log(Level.SEVERE, null, ex);
} }
@ -95,48 +122,60 @@ public class E621Ripper extends AbstractHTMLRipper{
})); }));
} }
private String getTerm(URL url) throws MalformedURLException{ private String getTerm(URL url) throws MalformedURLException {
if(gidPattern==null) String query = url.getQuery();
gidPattern=Pattern.compile("^https?://(www\\.)?e621\\.net/post/index/[^/]+/([a-zA-Z0-9$_.+!*'(),%-]+)(/.*)?(#.*)?$");
if(gidPatternPool==null)
gidPatternPool=Pattern.compile("^https?://(www\\.)?e621\\.net/pool/show/([a-zA-Z0-9$_.+!*'(),%-]+)(\\?.*)?(/.*)?(#.*)?$");
Matcher m = gidPattern.matcher(url.toExternalForm()); if (query != null) {
if(m.matches()) return Utils.parseUrlQuery(query, "tags");
return m.group(2); }
m = gidPatternPool.matcher(url.toExternalForm()); if (query == null) {
if(m.matches()) if ((query = url.getPath()).startsWith("/post/index/")) {
return m.group(2); query = query.substring(12);
throw new MalformedURLException("Expected e621.net URL format: e621.net/post/index/1/searchterm - got "+url+" instead"); int pos = query.indexOf('/');
if (pos == -1) {
return null;
}
// skip page number
query = query.substring(pos + 1);
if (query.endsWith("/")) {
query = query.substring(0, query.length() - 1);
}
try {
return URLDecoder.decode(query, "UTF-8");
} catch (UnsupportedEncodingException e) {
// Shouldn't happen since UTF-8 is required to be supported
throw new RuntimeException(e);
}
} else if (query.startsWith("/pool/show/")) {
query = query.substring(11);
if (query.endsWith("/")) {
query = query.substring(0, query.length() - 1);
}
return query;
}
}
return null;
} }
@Override @Override
public String getGID(URL url) throws MalformedURLException { public String getGID(URL url) throws MalformedURLException {
try { String prefix = "";
String prefix=""; if (url.getPath().startsWith("/pool/show/")) {
if(url.getPath().startsWith("/pool/show/")) prefix = "pool_";
prefix="pool_"; } else {
prefix = "term_";
return Utils.filesystemSafe(prefix+new URI(getTerm(url)).getPath());
} catch (URISyntaxException ex) {
Logger.getLogger(PahealRipper.class.getName()).log(Level.SEVERE, null, ex);
} }
throw new MalformedURLException("Expected e621.net URL format: e621.net/post/index/1/searchterm - got "+url+" instead"); return Utils.filesystemSafe(prefix + getTerm(url));
}
@Override
public URL sanitizeURL(URL url) throws MalformedURLException {
if(gidPattern2==null)
gidPattern2=Pattern.compile("^https?://(www\\.)?e621\\.net/post/search\\?tags=([a-zA-Z0-9$_.+!*'(),%-]+)(/.*)?(#.*)?$");
Matcher m = gidPattern2.matcher(url.toExternalForm());
if(m.matches())
return new URL("https://e621.net/post/index/1/"+m.group(2).replace("+","%20"));
return url;
} }
} }

View File

@ -3,13 +3,16 @@ package com.rarchives.ripme.utils;
import java.io.File; import java.io.File;
import java.io.IOException; import java.io.IOException;
import java.io.InputStream; import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.lang.reflect.Constructor; import java.lang.reflect.Constructor;
import java.net.URISyntaxException; import java.net.URISyntaxException;
import java.net.URL; import java.net.URL;
import java.net.URLDecoder; import java.net.URLDecoder;
import java.util.ArrayList; import java.util.ArrayList;
import java.util.Enumeration; import java.util.Enumeration;
import java.util.HashMap;
import java.util.List; import java.util.List;
import java.util.Map;
import java.util.jar.JarEntry; import java.util.jar.JarEntry;
import java.util.jar.JarFile; import java.util.jar.JarFile;
@ -387,4 +390,73 @@ public class Utils {
} }
return result; return result;
} }
/**
* Parses an URL query
*
* @param query
* The query part of an URL
* @return The map of all query parameters
*/
public static Map<String,String> parseUrlQuery(String query) {
Map<String,String> res = new HashMap<String, String>();
if (query.equals("")){
return res;
}
String[] parts = query.split("&");
int pos;
try {
for (String part : parts) {
if ((pos = part.indexOf('=')) >= 0){
res.put(URLDecoder.decode(part.substring(0, pos), "UTF-8"), URLDecoder.decode(part.substring(pos + 1), "UTF-8"));
}else{
res.put(URLDecoder.decode(part, "UTF-8"), "");
}
}
} catch (UnsupportedEncodingException e) {
// Shouldn't happen since UTF-8 is required to be supported
throw new RuntimeException(e);
}
return res;
}
/**
* Parses an URL query and returns the requested parameter's value
*
* @param query
* The query part of an URL
* @param key
* The key whose value is requested
* @return The associated value or null if key wasn't found
*/
public static String parseUrlQuery(String query, String key) {
if (query.equals("")){
return null;
}
String[] parts = query.split("&");
int pos;
try {
for (String part : parts) {
if ((pos = part.indexOf('=')) >= 0) {
if (URLDecoder.decode(part.substring(0, pos), "UTF-8").equals(key)){
return URLDecoder.decode(part.substring(pos + 1), "UTF-8");
}
} else if (URLDecoder.decode(part, "UTF-8").equals(key)) {
return "";
}
}
} catch (UnsupportedEncodingException e) {
// Shouldn't happen since UTF-8 is required to be supported
throw new RuntimeException(e);
}
return null;
}
} }