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

Merge pull request #99 from cyian-1756/chan.sankakucomplex

Browse Source 
Fixed sankakucomplex ripper
This commit is contained in:
cyian-1756 2017-10-16 17:13:33 -04:00 committed by GitHub
commit cb55415c28
1 changed files with 22 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
src/main/java/com/rarchives/ripme/ripper/rippers/SankakuComplexRipper.java
View File

@ -43,7 +43,7 @@ public class SankakuComplexRipper extends AbstractHTMLRipper {
Matcher m = p.matcher(url.toExternalForm()); Matcher m = p.matcher(url.toExternalForm());
if (m.matches()) { if (m.matches()) {
try { try {
return URLDecoder.decode(m.group(1), "UTF-8"); return URLDecoder.decode(m.group(2), "UTF-8");
} catch (UnsupportedEncodingException e) { } catch (UnsupportedEncodingException e) {
throw new MalformedURLException("Cannot decode tag name '" + m.group(1) + "'"); throw new MalformedURLException("Cannot decode tag name '" + m.group(1) + "'");
} }
@ -68,31 +68,39 @@ public class SankakuComplexRipper extends AbstractHTMLRipper {
List<String> imageURLs = new ArrayList<String>(); List<String> imageURLs = new ArrayList<String>();
// Image URLs are basically thumbnail URLs with a different domain, a simple // Image URLs are basically thumbnail URLs with a different domain, a simple
// path replacement, and a ?xxxxxx post ID at the end (obtainable from the href) // path replacement, and a ?xxxxxx post ID at the end (obtainable from the href)
for (Element thumbSpan : doc.select("div.content > div > span.thumb")) { for (Element thumbSpan : doc.select("div.content > div > span.thumb > a")) {
String postId = thumbSpan.attr("id").replaceAll("p", ""); String postLink = thumbSpan.attr("href");
Element thumb = thumbSpan.getElementsByTag("img").first(); try {
String image = thumb.attr("abs:src") // Get the page the full sized image is on
.replace(".sankakucomplex.com/data/preview", Document subPage = Http.url("https://chan.sankakucomplex.com" + postLink).get();
"s.sankakucomplex.com/data") + "?" + postId; logger.info("Checking page " + "https://chan.sankakucomplex.com" + postLink);
imageURLs.add(image); imageURLs.add("https:" + subPage.select("div[id=post-content] > a > img").attr("src"));
} catch (IOException e) {
logger.warn("Error while loading page " + postLink, e);
continue;
}
} }
return imageURLs; return imageURLs;
} }
@Override @Override
public void downloadURL(URL url, int index) { public void downloadURL(URL url, int index) {
// Mock up the URL of the post page based on the post ID at the end of the URL. sleep(8000);
String postId = url.toExternalForm().replaceAll(".*\\?", ""); addURLToDownload(url, getPrefix(index));
addURLToDownload(url, postId + "_", "", "", null);
} }
@Override @Override
public Document getNextPage(Document doc) throws IOException { public Document getNextPage(Document doc) throws IOException {
Element pagination = doc.select("div.pagination").first(); Element pagination = doc.select("div.pagination").first();
if (pagination.hasAttr("next-page-url")) { if (pagination.hasAttr("next-page-url")) {
return Http.url(pagination.attr("abs:next-page-url")).cookies(cookies).get(); String nextPage = pagination.attr("abs:next-page-url");
} else { // Only logged in users can see past page 25
return null; // Trying to rip page 26 will throw a no images found error
if (nextPage.contains("page=26") == false) {
logger.info("Getting next page: " + pagination.attr("abs:next-page-url"));
return Http.url(pagination.attr("abs:next-page-url")).cookies(cookies).get();
}
} }
throw new IOException("No more pages");
} }
} }