Skip to content

Added support for 8ch.net and yuki.la in ChanRipper.java #327

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Added support for 8ch.net and yuki.la in ChanRipper.java #327

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 9 additions & 5 deletions src/main/java/com/rarchives/ripme/ripper/rippers/ChanRipper.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,11 @@
public class ChanRipper extends AbstractHTMLRipper {
private static List<ChanSite> explicit_domains = Arrays.asList(
new ChanSite(Arrays.asList("boards.4chan.org"), Arrays.asList("4cdn.org", "is.4chan.org", "is2.4chan.org")),
new ChanSite(Arrays.asList("archive.moe"), Arrays.asList("data.archive.moe")),
new ChanSite(Arrays.asList("4archive.org"), Arrays.asList("imgur.com")),
new ChanSite(Arrays.asList("archive.4plebs.org"), Arrays.asList("img.4plebs.org"))
new ChanSite(Arrays.asList("archive.4plebs.org"), Arrays.asList("img.4plebs.org")),
new ChanSite(Arrays.asList("8ch.net"), Arrays.asList("media.8ch.net")),
new ChanSite(Arrays.asList("yuki.la"), Arrays.asList("ii.yuki.la"))
);

private static List<String> url_piece_blacklist = Arrays.asList(
Expand Down Expand Up @@ -65,7 +68,7 @@ public String getAlbumTitle(URL url) throws MalformedURLException {
// Attempt to use album title as GID
Document doc = getFirstPage();
try {
String subject = doc.select(".post.op > .postinfo > .subject").first().text();
String subject = doc.select(".subject").first().text();
return getHost() + "_" + getGID(url) + "_" + subject;
} catch (NullPointerException e) {
logger.warn("Failed to get thread title from " + url);
Expand All @@ -86,7 +89,8 @@ public boolean canRip(URL url) {
}
}
return url.toExternalForm().contains("/res/") // Most chans
|| url.toExternalForm().contains("/thread/"); // 4chan, archive.moe
|| url.toExternalForm().contains("/thread/") // 4chan, archive.moe
|| url.toExternalForm().contains("/"); // yuki.la, etc
Copy link
Collaborator

@cyian-1756 cyian-1756 Dec 9, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

|| url.toExternalForm().contains("/"); // yuki.la, etc is way to greedy. Try changing it to a regex that will only match yuki.la links.

}

/**
Expand All @@ -104,8 +108,8 @@ public String getGID(URL url) throws MalformedURLException {
Matcher m;

String u = url.toExternalForm();
if (u.contains("/thread/") || u.contains("/res/")) {
p = Pattern.compile("^.*\\.[a-z]{1,3}/[a-zA-Z0-9]+/(thread|res)/([0-9]+)(\\.html|\\.php)?.*$");
if (u.contains("/thread/") || u.contains("/res/") || u.contains("/")) {
p = Pattern.compile("^.*\\.[a-z]{1,3}/[a-zA-Z0-9]+(/thread/|/res/|/)([0-9]+)(\\.html|\\.php)?.*$");
m = p.matcher(u);
if (m.matches()) {
return m.group(2);
Expand Down