mirror/ripme
1
0
Fork 0
mirror of https://github.com/RipMeApp/ripme.git synced 2025-08-10 16:04:19 +02:00
Code Issues Releases Wiki Activity

Update CfakeRipper to new site format (Fixes #2116) (#2117)

Browse Source
This commit is contained in:
metaprime
2025-04-19 19:41:46 -07:00
committed by GitHub
parent f480583d9a
commit 46ac407c14
2 changed files with 74 additions and 61 deletions
Download Patch File Download Diff File Expand all files Collapse all files

129
src/main/java/com/rarchives/ripme/ripper/rippers/CfakeRipper.java
View File

@@ -10,80 +10,89 @@ import java.util.regex.Pattern;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import com.rarchives.ripme.ripper.AbstractHTMLRipper;
import com.rarchives.ripme.utils.Http;
public class CfakeRipper extends AbstractHTMLRipper {
public CfakeRipper(URL url) throws IOException {
super(url);
super(url);
}
@Override
public String getHost() {
return "cfake";
@Override
public String getHost() {
return "cfake";
}
@Override
public String getDomain() {
return "cfake.com";
}
@Override
public String getGID(URL url) throws MalformedURLException {
Pattern p = Pattern.compile("https?://cfake\\.com/images/celebrity/([a-zA-Z1-9_-]*)/\\d+/?$");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
return m.group(1);
}
throw new MalformedURLException("Expected cfake URL format: " +
"cfake.com/images/celebrity/MODEL/ID - got " + url + " instead");
}
@Override
public Document getFirstPage() throws IOException {
// "url" is an instance field of the superclass
return Http.url(url).get();
}
@Override
public Document getNextPage(Document doc) throws IOException {
Element elem = doc.select("div#wrapper_path div#content_path div#num_page").last();
if (elem == null) {
throw new IOException("No more pages (cannot find nav)");
}
@Override
public String getDomain() {
return "cfake.com";
Element nextAnchor = elem.select("a").first();
if (nextAnchor == null) {
throw new IOException("No more pages (cannot find anchor)");
}
@Override
public String getGID(URL url) throws MalformedURLException {
Pattern p = Pattern.compile("https?://cfake\\.com/picture/([a-zA-Z1-9_-]*)/\\d+/?$");
Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) {
return m.group(1);
}
throw new MalformedURLException("Expected cfake URL format: " +
"cfake.com/picture/MODEL/ID - got " + url + " instead");
Elements nextSpans = nextAnchor.select("span");
if (nextSpans.isEmpty()) {
// This is the expected case that we're done iterating.
throw new IOException("No more pages (last page)");
}
@Override
public Document getFirstPage() throws IOException {
// "url" is an instance field of the superclass
return Http.url(url).get();
}
// Use the nextAnchor (parent of the span) for the URL
String nextPage = nextAnchor.attr("href");
@Override
public Document getNextPage(Document doc) throws IOException {
// We use comic-nav-next to the find the next page
Element elem = doc.select("td > div.next > a").first();
if (elem == null) {
throw new IOException("No more pages");
}
String nextPage = elem.attr("href");
// Some times this returns a empty string
// This for stops that
if (nextPage.equals("")) {
return null;
}
else {
return Http.url("http://cfake.com" + nextPage).get();
}
}
@Override
public List<String> getURLsFromPage(Document doc) {
List<String> result = new ArrayList<>();
for (Element el : doc.select("table.display > tbody > tr > td > table > tbody > tr > td > a")) {
if (el.attr("href").contains("upload")) {
return result;
} else {
String imageSource = el.select("img").attr("src");
// We remove the .md from images so we download the full size image
// not the thumbnail ones
imageSource = imageSource.replace("thumbs", "photos");
result.add("http://cfake.com" + imageSource);
}
}
return result;
}
@Override
public void downloadURL(URL url, int index) {
addURLToDownload(url, getPrefix(index));
// Sometimes this returns an empty string; this stops that
if (nextPage.equals("")) {
return null;
} else {
return Http.url("https://cfake.com" + nextPage).get();
}
}
@Override
public List<String> getURLsFromPage(Document doc) {
List<String> result = new ArrayList<>();
for (Element el : doc.select("div#media_content .responsive .gallery > a img")) {
// Convert found src value e.g. /medias/thumbs/2025/17358722979850276d_cfake.jpg
// to photo src value e.g.
// https://cfake.com/medias/photos/2025/17358722979850276d_cfake.jpg
String imageSource = el.attr("src");
imageSource = imageSource.replace("thumbs", "photos");
result.add("https://cfake.com" + imageSource);
}
return result;
}
@Override
public void downloadURL(URL url, int index) {
addURLToDownload(url, getPrefix(index));
}
}

6
src/test/java/com/rarchives/ripme/tst/ripper/rippers/CfakeRipperTest.java
View File

@@ -4,11 +4,15 @@ import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import org.junit.jupiter.api.Test;
import com.rarchives.ripme.ripper.rippers.CfakeRipper;
public class CfakeRipperTest extends RippersTest {
@Test
public void testRip() throws IOException, URISyntaxException {
CfakeRipper ripper = new CfakeRipper(new URI("http://cfake.com/picture/Zooey_Deschanel/1264").toURL());
CfakeRipper ripper = new CfakeRipper(
new URI("https://cfake.com/images/celebrity/Zooey_Deschanel/1264").toURL());
testRipper(ripper);
}
}