import java.util.Collections;
import java.util.List;
import java.util.Map.Entry;
+import java.util.SortedMap;
+import java.util.TreeMap;
import org.jsoup.helper.DataUtil;
import org.jsoup.nodes.Element;
return true;
}
- @Override
- public String getSourceName() {
- return "MangaFox.me";
- }
-
@Override
protected MetaData getMeta() throws IOException {
MetaData meta = new MetaData();
meta.setDate(StringUtils.unhtml(table.get(0).text()).trim());
meta.setTags(explode(table.get(3).text()));
}
- meta.setSource(getSourceName());
+ meta.setSource(getType().getSourceName());
meta.setUrl(getSource().toString());
- meta.setPublisher(getSourceName());
+ meta.setPublisher(getType().getSourceName());
meta.setUuid(getSource().toString());
meta.setLuid("");
meta.setLang("en");
Element doc = getSourceNode();
Element title = doc.getElementsByClass("summary").first();
if (title != null) {
- StringUtils.unhtml(title.text()).trim();
+ return StringUtils.unhtml(title.text()).trim();
}
return null;
protected List<Entry<String, URL>> getChapters(Progress pg) {
List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>();
+ String prefix = null; // each chapter starts with this prefix, then a
+ // chapter number (including "x.5"), then name
+
Element doc = getSourceNode();
for (Element li : doc.getElementsByTag("li")) {
Element el = li.getElementsByTag("h4").first();
url += "/";
}
+ if (prefix == null || !prefix.isEmpty()) {
+ StringBuilder possiblePrefix = new StringBuilder(
+ StringUtils.unhtml(a.text()).trim());
+ while (possiblePrefix.length() > 0) {
+ char car = possiblePrefix.charAt(possiblePrefix
+ .length() - 1);
+ boolean punctuation = (car == '.' || car == ' ');
+ boolean digit = (car >= '0' && car <= '9');
+ if (!punctuation && !digit) {
+ break;
+ }
+
+ possiblePrefix.setLength(possiblePrefix
+ .length() - 1);
+ }
+
+ if (prefix == null) {
+ prefix = possiblePrefix.toString();
+ }
+
+ if (!prefix.equalsIgnoreCase(possiblePrefix
+ .toString())) {
+ prefix = ""; // prefix not ok
+ }
+ }
+
urls.add(new AbstractMap.SimpleEntry<String, URL>(
title, new URL(url)));
} catch (Exception e) {
}
}
- // the chapters are in reversed order
- Collections.reverse(urls);
+ if (prefix != null && !prefix.isEmpty()) {
+ try {
+ // We found a prefix, so everything should be sortable
+ SortedMap<Double, Entry<String, URL>> map = new TreeMap<Double, Entry<String, URL>>();
+ for (Entry<String, URL> entry : urls) {
+ String num = entry.getKey().substring(prefix.length() + 1)
+ .trim();
+ String name = "";
+ int pos = num.indexOf(' ');
+ if (pos >= 0) {
+ name = num.substring(pos).trim();
+ num = num.substring(0, pos).trim();
+ }
+
+ if (!name.isEmpty()) {
+ name = "Tome " + num + ": " + name;
+ } else {
+ name = "Tome " + num;
+ }
+
+ double key = Double.parseDouble(num);
+
+ map.put(key, new AbstractMap.SimpleEntry<String, URL>(name,
+ entry.getValue()));
+ }
+ urls = new ArrayList<Entry<String, URL>>(map.values());
+ } catch (NumberFormatException e) {
+ Instance.getTraceHandler()
+ .error(new IOException(
+ "Cannot find a tome number, revert to default sorting",
+ e));
+ // by default, the chapters are in reversed order
+ Collections.reverse(urls);
+ }
+ } else {
+ // by default, the chapters are in reversed order
+ Collections.reverse(urls);
+ }
return urls;
}
// note: when used, the base URL can be an ad-page
imageIn = openEx(url + "1.html");
imageDoc = DataUtil.load(imageIn, "UTF-8", url + "1.html");
+ } catch (IOException e) {
+ Instance.getTraceHandler().error(
+ new IOException("Cannot get image " + 1 + " of manga", e));
} finally {
- imageIn.close();
+ if (imageIn != null) {
+ imageIn.close();
+ }
}
Element select = imageDoc.getElementsByClass("m").first();
Elements options = select.getElementsByTag("option");
// 2. list them
for (int i = 1; i <= size; i++) {
- if (i > 1) { // because fist one was opened for size
+ if (i > 1) { // because first one was opened for size
try {
imageIn = openEx(url + i + ".html");
imageDoc = DataUtil.load(imageIn, "UTF-8", url + i
+ ".html");
+
+ String linkImage = imageDoc.getElementById("image").absUrl(
+ "src");
+ if (linkImage != null) {
+ builder.append("[");
+ // to help with the retry and the originalUrl, part 1
+ builder.append(withoutQuery(linkImage));
+ builder.append("]<br/>");
+ }
+
+ // to help with the retry and the originalUrl, part 2
+ refresh(linkImage);
+ } catch (IOException e) {
+ Instance.getTraceHandler().error(
+ new IOException("Cannot get image " + i
+ + " of manga", e));
} finally {
- imageIn.close();
+ if (imageIn != null) {
+ imageIn.close();
+ }
}
}
-
- String linkImage = imageDoc.getElementById("image").absUrl("src");
- if (linkImage != null) {
- builder.append("[");
- // to help with the retry and the originalUrl, part 1
- builder.append(withoutQuery(linkImage));
- builder.append("]<br/>");
- }
-
- // to help with the retry and the originalUrl, part 2
- refresh(linkImage);
}
return builder.toString();
}
/**
- * Refresh the {@link URL} by calling {@link MangaFoxNew#openEx(String)}.
+ * Refresh the {@link URL} by calling {@link MangaFox#openEx(String)}.
*
* @param url
* the URL to refresh
*/
private InputStream openEx(String url) throws IOException {
try {
- return Instance.getCache().open(new URL(url), this, true,
- withoutQuery(url));
+ return Instance.getCache().open(new URL(url), withoutQuery(url),
+ this, true);
} catch (Exception e) {
// second chance
try {
} catch (InterruptedException ee) {
}
- return Instance.getCache().open(new URL(url), this, true,
- withoutQuery(url));
+ return Instance.getCache().open(new URL(url), withoutQuery(url),
+ this, true);
}
}
git://git.nikiroo.be / nikiroo-utils.git / blobdiff