MANGAFOX,
/** Furry website with comics support */
E621,
+ /** Furry website with stories */
+ YIFFSTAR,
/** CBZ files */
CBZ,
/** HTML files */
return new HashMap<String, String>();
}
+ /**
+ * Return the canonical form of the main {@link URL}.
+ *
+ * @param source
+ * the source {@link URL}
+ *
+ * @return the canonical form of this {@link URL}
+ *
+ * @throws IOException
+ * in case of I/O error
+ */
+ public URL getCanonicalUrl(URL source) throws IOException {
+ return source;
+ }
+
/**
* Process the given story resource into a partially filled {@link Story}
* object containing the name and metadata, except for the description.
*/
protected Story processMeta(URL url, boolean close, boolean getDesc)
throws IOException {
+ url = getCanonicalUrl(url);
+
+ setCurrentReferer(url);
+
in = openInput(url);
if (in == null) {
return null;
in.close();
}
}
+
+ setCurrentReferer(null);
}
}
pg.setMinMax(0, 100);
}
- setCurrentReferer(url);
-
+ url = getCanonicalUrl(url);
pg.setProgress(1);
try {
Story story = processMeta(url, false, true);
return null;
}
+ setCurrentReferer(url);
+
story.setChapters(new ArrayList<Chapter>());
List<Entry<String, URL>> chapters = getChapters(url, getInput());
in.close();
}
- currentReferer = null;
+ setCurrentReferer(null);
}
}
/**
- * The support type.$
+ * The support type.
*
* @return the type
*/
/**
* Return the list of supported image extensions.
*
+ * @param emptyAllowed
+ * TRUE to allow an empty extension on first place, which can be
+ * used when you may already have an extension in your input but
+ * are not sure about it
+ *
* @return the extensions
*/
static String[] getImageExt(boolean emptyAllowed) {
}
}
+ /**
+ * Check if the given resource can be a local image or a remote image, then
+ * refresh the cache with it if it is.
+ *
+ * @param source
+ * the story source
+ * @param line
+ * the resource to check
+ *
+ * @return the image if found, or NULL
+ *
+ */
static BufferedImage getImage(BasicSupport support, URL source, String line) {
URL url = getImageUrl(support, source, line);
if (url != null) {
return Instance.getCache().open(source, this, false);
}
+ /**
+ * Reset the given {@link InputStream} and return it.
+ *
+ * @param in
+ * the {@link InputStream} to reset
+ *
+ * @return the same {@link InputStream} after reset
+ */
protected InputStream reset(InputStream in) {
try {
in.reset();
* paragraphs (quotes or not)).
*
* @param para
- * the paragraph to requotify (not necessaraly a quote)
+ * the paragraph to requotify (not necessarily a quote)
*
* @return the correctly (or so we hope) quotified paragraphs
*/
}
/**
- * Remove the HTML from the inpit <b>if</b> {@link BasicSupport#isHtml()} is
+ * Remove the HTML from the input <b>if</b> {@link BasicSupport#isHtml()} is
* true.
*
* @param input
return new MangaFox().setType(type);
case E621:
return new E621().setType(type);
+ case YIFFSTAR:
+ return new YiffStar().setType(type);
case CBZ:
return new Cbz().setType(type);
case HTML:
package be.nikiroo.fanfix.supported;
import java.io.File;
-import java.io.FileInputStream;
import java.io.IOException;
-import java.io.InputStream;
import java.net.MalformedURLException;
import java.net.URISyntaxException;
import java.net.URL;
-import java.util.List;
-import java.util.Map.Entry;
-
-import be.nikiroo.fanfix.data.MetaData;
-import be.nikiroo.utils.MarkableFileInputStream;
/**
* Support class for HTML files created with this program (as we need some
* @author niki
*/
class Html extends InfoText {
- private URL fakeSource;
-
@Override
public String getSourceName() {
return "html";
}
@Override
- protected MetaData getMeta(URL source, InputStream in) throws IOException {
- return super.getMeta(fakeSource, in);
- }
-
- @Override
- protected String getDesc(URL source, InputStream in) throws IOException {
- return super.getDesc(fakeSource, in);
- }
-
- @Override
- protected List<Entry<String, URL>> getChapters(URL source, InputStream in)
- throws IOException {
- return super.getChapters(fakeSource, in);
- }
-
- @Override
- protected String getChapterContent(URL source, InputStream in, int number)
- throws IOException {
- return super.getChapterContent(fakeSource, in, number);
- }
-
- @Override
- protected InputStream openInput(URL source) throws IOException {
- try {
- File fakeFile = new File(source.toURI()); // "story/index.html"
- fakeFile = new File(fakeFile.getParent()); // "story"
- fakeFile = new File(fakeFile, fakeFile.getName()); // "story/story"
- fakeSource = fakeFile.toURI().toURL();
- return new MarkableFileInputStream(new FileInputStream(fakeFile));
- } catch (URISyntaxException e) {
- throw new IOException(
- "file not supported (maybe not created with this program or corrupt)",
- e);
- } catch (MalformedURLException e) {
- throw new IOException("file not supported (bad URL)", e);
+ public URL getCanonicalUrl(URL source) throws IOException {
+ if (source.toString().endsWith(File.separator + "index.html")) {
+ try {
+ File fakeFile = new File(source.toURI()); // "story/index.html"
+ fakeFile = new File(fakeFile.getParent()); // "story"
+ fakeFile = new File(fakeFile, fakeFile.getName()); // "story/story"
+ return fakeFile.toURI().toURL();
+ } catch (URISyntaxException e) {
+ throw new IOException(
+ "file not supported (maybe not created with this program or corrupt)",
+ e);
+ }
}
+
+ return source;
}
}
--- /dev/null
+package be.nikiroo.fanfix.supported;
+
+import java.awt.image.BufferedImage;
+import java.io.IOException;
+import java.io.InputStream;
+import java.net.URL;
+import java.util.ArrayList;
+import java.util.List;
+import java.util.Map;
+import java.util.Map.Entry;
+import java.util.Scanner;
+
+import be.nikiroo.fanfix.Instance;
+import be.nikiroo.fanfix.data.MetaData;
+import be.nikiroo.utils.StringUtils;
+
+/**
+ * Support class for <a href="https://sofurry.com/">SoFurry.com</a>, a Furry
+ * website supporting images and stories (we only retrieve the stories).
+ *
+ * @author niki
+ */
+class YiffStar extends BasicSupport {
+
+ @Override
+ public String getSourceName() {
+ return "YiffStar";
+ }
+
+ @Override
+ protected MetaData getMeta(URL source, InputStream in) throws IOException {
+ MetaData meta = new MetaData();
+
+ meta.setTitle(getTitle(reset(in)));
+ meta.setAuthor(getAuthor(source, reset(in)));
+ meta.setDate("");
+ meta.setTags(getTags(reset(in)));
+ meta.setSource(getSourceName());
+ meta.setUrl(source.toString());
+ meta.setPublisher(getSourceName());
+ meta.setUuid(source.toString());
+ meta.setLuid("");
+ meta.setLang("EN");
+ meta.setSubject("Furry");
+ meta.setType(getType().toString());
+ meta.setImageDocument(false);
+ meta.setCover(getCover(source, reset(in)));
+
+ return meta;
+ }
+
+ @Override
+ protected boolean supports(URL url) {
+ String host = url.getHost();
+ if (host.startsWith("www.")) {
+ host = host.substring("www.".length());
+ }
+
+ return "sofurry.com".equals(host);
+ }
+
+ @Override
+ protected boolean isHtml() {
+ return true;
+ }
+
+ @Override
+ public Map<String, String> getCookies() {
+ // TODO
+ // Cookies will actually be retained by the cache manager once logged in
+ // But we need to connect here and notify the cache manager
+
+ return super.getCookies();
+ }
+
+ @Override
+ public URL getCanonicalUrl(URL source) throws IOException {
+ if (source.getPath().startsWith("/view")) {
+ InputStream in = Instance.getCache().open(source, this, false);
+ String line = getLine(in, "/browse/folder/", 0);
+ String[] tab = line.split("\"");
+ if (tab.length > 1) {
+ String groupUrl = source.getProtocol() + "://"
+ + source.getHost() + tab[1];
+ return new URL(groupUrl);
+ }
+ }
+
+ return super.getCanonicalUrl(source);
+ }
+
+ private List<String> getTags(InputStream in) {
+ List<String> tags = new ArrayList<String>();
+
+ String line = getLine(in, "class=\"sf-story-big-tags", 0);
+ if (line != null) {
+ String[] tab = StringUtils.unhtml(line).split(",");
+ for (String possibleTag : tab) {
+ String tag = possibleTag.trim();
+ if (!tag.isEmpty() && !tag.equals("...") && !tags.contains(tag)) {
+ tags.add(tag);
+ }
+ }
+ }
+
+ return tags;
+ }
+
+ private BufferedImage getCover(URL source, InputStream in)
+ throws IOException {
+
+ List<Entry<String, URL>> chaps = getChapters(source, in);
+ if (!chaps.isEmpty()) {
+ in = Instance.getCache().open(chaps.get(0).getValue(), this, true);
+ String line = getLine(in, " name=\"og:image\"", 0);
+ if (line != null) {
+ int pos = -1;
+ for (int i = 0; i < 3; i++) {
+ pos = line.indexOf('"', pos + 1);
+ }
+
+ if (pos >= 0) {
+ line = line.substring(pos + 1);
+ pos = line.indexOf('"');
+ if (pos >= 0) {
+ line = line.substring(0, pos);
+ if (line.contains("/thumb?")) {
+ line = line.replace("/thumb?",
+ "/auxiliaryContent?type=25&");
+ return getImage(this, null, line);
+ }
+ }
+ }
+ }
+ }
+
+ return null;
+ }
+
+ private String getAuthor(URL source, InputStream in) throws IOException {
+ String author = getLine(in, "class=\"onlinestatus", 0);
+ if (author != null) {
+ return StringUtils.unhtml(author).trim();
+ }
+
+ return null;
+ }
+
+ private String getTitle(InputStream in) throws IOException {
+ String title = getLine(in, "class=\"sflabel pagetitle", 0);
+ if (title != null) {
+ if (title.contains("(series)")) {
+ title = title.replace("(series)", "");
+ }
+ return StringUtils.unhtml(title).trim();
+ }
+
+ return null;
+ }
+
+ @Override
+ protected String getDesc(URL source, InputStream in) throws IOException {
+ return null; // TODO: no description at all? Cannot find one...
+ }
+
+ @Override
+ protected List<Entry<String, URL>> getChapters(URL source, InputStream in)
+ throws IOException {
+ List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>();
+
+ @SuppressWarnings("resource")
+ Scanner scan = new Scanner(in, "UTF-8");
+ scan.useDelimiter("\\n");
+ while (scan.hasNext()) {
+ String line = scan.next();
+ if (line.contains("\"/view/") && line.contains("title=")) {
+ String[] tab = line.split("\"");
+ if (tab.length > 5) {
+ String link = tab[5];
+ if (link.startsWith("/")) {
+ link = source.getProtocol() + "://" + source.getHost()
+ + link;
+ }
+ final URL value = new URL(link);
+ final String key = StringUtils.unhtml(line).trim();
+ urls.add(new Entry<String, URL>() {
+ public URL setValue(URL value) {
+ return null;
+ }
+
+ public URL getValue() {
+ return value;
+ }
+
+ public String getKey() {
+ return key;
+ }
+ });
+ }
+ }
+ }
+
+ return urls;
+ }
+
+ @Override
+ protected String getChapterContent(URL source, InputStream in, int number)
+ throws IOException {
+ StringBuilder builder = new StringBuilder();
+
+ String startAt = "id=\"sfContentBody";
+ String endAt = "id=\"recommendationArea";
+ boolean ok = false;
+
+ @SuppressWarnings("resource")
+ Scanner scan = new Scanner(in, "UTF-8");
+ scan.useDelimiter("\\n");
+ while (scan.hasNext()) {
+ String line = scan.next();
+ if (!ok && line.contains(startAt)) {
+ ok = true;
+ } else if (ok && line.contains(endAt)) {
+ ok = false;
+ break;
+ }
+
+ if (ok) {
+ builder.append(line);
+ builder.append('\n');
+ }
+ }
+
+ return builder.toString();
+ }
+}
git://git.nikiroo.be / fanfix.git / commitdiff