mirror/ripme
1
0
Fork 0
mirror of https://github.com/RipMeApp/ripme.git synced 2025-09-03 02:42:47 +02:00
Code Issues Releases Wiki Activity

Fix #1868 Imagebam Error : Change Layout

Browse Source
This commit is contained in:
Stilgar
2021-05-20 16:16:32 +02:00
parent 3c4e303358
commit c14d068f09
1 changed files with 9 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/main/java/com/rarchives/ripme/ripper/rippers/ImagebamRipper.java
View File

@@ -11,6 +11,8 @@ import java.util.ArrayList;
import java.util.List; import java.util.List;
import java.util.regex.Matcher; import java.util.regex.Matcher;
import java.util.regex.Pattern; import java.util.regex.Pattern;
import org.apache.commons.lang.StringUtils;
import org.jsoup.nodes.Document; import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element; import org.jsoup.nodes.Element;
import org.jsoup.select.Elements; import org.jsoup.select.Elements;
@@ -80,7 +82,7 @@ public class ImagebamRipper extends AbstractHTMLRipper {
@Override @Override
public List<String> getURLsFromPage(Document doc) { public List<String> getURLsFromPage(Document doc) {
List<String> imageURLs = new ArrayList<>(); List<String> imageURLs = new ArrayList<>();
for (Element thumb : doc.select("div > a[target=_blank]:not(.footera)")) { for (Element thumb : doc.select("div > a[class=thumbnail]:not(.footera)")) {
imageURLs.add(thumb.attr("href")); imageURLs.add(thumb.attr("href"));
} }
return imageURLs; return imageURLs;
@@ -97,15 +99,12 @@ public class ImagebamRipper extends AbstractHTMLRipper {
public String getAlbumTitle(URL url) throws MalformedURLException { public String getAlbumTitle(URL url) throws MalformedURLException {
try { try {
// Attempt to use album title as GID // Attempt to use album title as GID
Elements elems = getFirstPage().select("legend"); Elements elems = getFirstPage().select("[id=gallery-name]");
String title = elems.first().text(); String title = elems.first().text();
LOGGER.info("Title text: '" + title + "'"); LOGGER.info("Title text: '" + title + "'");
Pattern p = Pattern.compile("^(.*)\\s\\d* image.*$"); if (StringUtils.isNotBlank(title)) {
Matcher m = p.matcher(title); return getHost() + "_" + getGID(url) + " (" + title + ")";
if (m.matches()) {
return getHost() + "_" + getGID(url) + " (" + m.group(1).trim() + ")";
} }
LOGGER.info("Doesn't match " + p.pattern());
} catch (Exception e) { } catch (Exception e) {
// Fall back to default album naming convention // Fall back to default album naming convention
LOGGER.warn("Failed to get album title from " + url, e); LOGGER.warn("Failed to get album title from " + url, e);
@@ -143,14 +142,9 @@ public class ImagebamRipper extends AbstractHTMLRipper {
Elements metaTags = doc.getElementsByTag("meta"); Elements metaTags = doc.getElementsByTag("meta");
String imgsrc = "";//initialize, so no NullPointerExceptions should ever happen. String imgsrc = "";//initialize, so no NullPointerExceptions should ever happen.
Elements elem = doc.select("img[class*=main-image]");
for (Element metaTag: metaTags) { if ((elem != null) && (elem.size() > 0)) {
//the direct link to the image seems to always be linked in the <meta> part of the html. imgsrc = elem.first().attr("src");
if (metaTag.attr("property").equals("og:image")) {
imgsrc = metaTag.attr("content");
LOGGER.info("Found URL " + imgsrc);
break;//only one (useful) image possible for an "image page".
}
} }
//for debug, or something goes wrong. //for debug, or something goes wrong.