Gurkengewuerz/ImgScroll
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Eroshare can now rip profiles (Fixes #465) (#578)

Browse Source
This commit is contained in:
cyian-1756 2017-06-15 15:21:08 -04:00 committed by metaprime
parent 6443240901
commit 128d384d29
1 changed files with 92 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
src/main/java/com/rarchives/ripme/ripper/rippers/EroShareRipper.java
View File

@ -9,6 +9,7 @@ import java.io.IOException;
import java.net.MalformedURLException;
import java.net.URL;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
@ -17,8 +18,10 @@ import org.jsoup.Connection.Response;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.jsoup.Connection.Method;
import com.rarchives.ripme.ripper.AbstractHTMLRipper;
import com.rarchives.ripme.ui.RipStatusMessage.STATUS;
import com.rarchives.ripme.utils.Http;
/**
@ -27,6 +30,7 @@ import com.rarchives.ripme.utils.Http;
*/
public class EroShareRipper extends AbstractHTMLRipper {
public EroShareRipper (URL url) throws IOException {
super(url);
}
@ -45,9 +49,47 @@ public class EroShareRipper extends AbstractHTMLRipper {
public void downloadURL(URL url, int index){
addURLToDownload(url);
}
@Override
public boolean canRip(URL url) {
Pattern p = Pattern.compile("^https?://[w.]*eroshare.com/([a-zA-Z0-9\\-_]+)/?$");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
return true;
}
Pattern pa = Pattern.compile("^https?://[w.]*eroshare.com/u/([a-zA-Z0-9\\-_]+)/?$");
Matcher ma = pa.matcher(url.toExternalForm());
if (ma.matches()) {
return true;
}
return false;
}
public boolean is_profile(URL url) {
Pattern pa = Pattern.compile("^https?://[w.]*eroshare.com/u/([a-zA-Z0-9\\-_]+)/?$");
Matcher ma = pa.matcher(url.toExternalForm());
if (ma.matches()) {
return true;
}
return false;
}
@Override
public Document getNextPage(Document doc) throws IOException {
// Find next page
String nextUrl = "";
Element elem = doc.select("li.next > a").first();
logger.info(elem);
nextUrl = elem.attr("href");
if (nextUrl == "") {
throw new IOException("No more pages");
}
return Http.url("https://eroshare.com" + nextUrl).get();
}
@Override
public String getAlbumTitle(URL url) throws MalformedURLException {
if (is_profile(url) == false) {
try {
// Attempt to use album title as GID
Element titleElement = getFirstPage().select("meta[property=og:title]").first();
@ -60,6 +102,8 @@ public class EroShareRipper extends AbstractHTMLRipper {
}
return super.getAlbumTitle(url);
}
return url.toExternalForm().split("/u/")[1];
}
@Override
@ -83,6 +127,26 @@ public class EroShareRipper extends AbstractHTMLRipper {
URLs.add(videoURL);
}
}
// Profile videos
Elements links = doc.select("div.item-container > a.item");
for (Element link : links){
Document video_page;
try {
video_page = Http.url("https://eroshare.com" + link.attr("href")).get();
} catch(IOException e) {
logger.warn("Failed to log link in Jsoup");
video_page = null;
e.printStackTrace();
}
Elements profile_vids = video_page.getElementsByTag("video");
for (Element vid : profile_vids){
if (vid.hasClass("album-video")){
Elements source = vid.getElementsByTag("source");
String videoURL = source.first().attr("src");
URLs.add(videoURL);
}
}
}
return URLs;
}
@ -105,6 +169,13 @@ public class EroShareRipper extends AbstractHTMLRipper {
if (m.matches()) {
return m.group(1);
}
Pattern pa = Pattern.compile("^https?://[w.]*eroshare.com/u/([a-zA-Z0-9\\-_]+)/?$");
Matcher ma = pa.matcher(url.toExternalForm());
if (ma.matches()) {
return m.group(1) + "_profile";
}
throw new MalformedURLException("eroshare album not found in " + url + ", expected https://eroshare.com/album");
}
@ -139,3 +210,4 @@ public class EroShareRipper extends AbstractHTMLRipper {
return URLs;
}
}