import java.io.IOException;
import java.io.InputStream;
+import java.io.UnsupportedEncodingException;
import java.net.URL;
+import java.net.URLDecoder;
+import java.net.URLEncoder;
+import java.util.AbstractMap;
import java.util.ArrayList;
+import java.util.LinkedList;
import java.util.List;
+import java.util.AbstractMap.SimpleEntry;
import java.util.Map.Entry;
import java.util.Scanner;
import be.nikiroo.fanfix.Instance;
import be.nikiroo.fanfix.data.Chapter;
+import be.nikiroo.fanfix.data.MetaData;
import be.nikiroo.fanfix.data.Story;
+import be.nikiroo.utils.Image;
+import be.nikiroo.utils.Progress;
import be.nikiroo.utils.StringUtils;
/**
*
* @author niki
*/
-class E621 extends BasicSupport {
+class E621 extends BasicSupport_Deprecated {
@Override
public String getSourceName() {
return "e621.net";
}
@Override
- public boolean isImageDocument(URL source, InputStream in) {
- return true;
+ 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(source, reset(in), false));
+ 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(true);
+ meta.setCover(getCover(source, reset(in)));
+ meta.setFakeCover(true);
+
+ return meta;
+ }
+
+ private List<String> getTags(URL source, InputStream in, boolean authors) {
+ List<String> tags = new ArrayList<String>();
+
+ if (isSearch(source)) {
+ String tagLine = getLine(in, "id=\"tag-sidebar\"", 1);
+ if (tagLine != null) {
+ String key = "href=\"";
+ for (int pos = tagLine.indexOf(key); pos >= 0; pos = tagLine
+ .indexOf(key, pos + 1)) {
+ int end = tagLine.indexOf("\"", pos + key.length());
+ if (end >= 0) {
+ String href = tagLine.substring(pos, end);
+ String subkey;
+ if (authors)
+ subkey = "?name=";
+ else
+ subkey = "?title=";
+ if (href.contains(subkey)) {
+ String tag = href.substring(href.indexOf(subkey)
+ + subkey.length());
+ try {
+ tags.add(URLDecoder.decode(tag, "UTF-8"));
+ } catch (UnsupportedEncodingException e) {
+ // supported JVMs must have UTF-8 support
+ e.printStackTrace();
+ }
+ }
+ }
+ }
+
+ }
+ }
+
+ return tags;
}
@Override
- public Story process(URL url) throws IOException {
+ public Story process(URL url, Progress pg) throws IOException {
// There is no chapters on e621, just pagination...
- Story story = super.process(url);
+ Story story = super.process(url, pg);
Chapter only = new Chapter(1, null);
for (Chapter chap : story) {
}
return ("e621.net".equals(host) || "e926.net".equals(host))
- && url.getPath().startsWith("/pool/");
+ && (isPool(url) || isSearch(url));
}
@Override
return true;
}
- @Override
- protected String getAuthor(URL source, InputStream in) throws IOException {
+ private Image getCover(URL source, InputStream in) throws IOException {
+ // No cover on searches (/post/)
+ if (isSearch(source))
+ return null;
+
+ String images = getChapterContent(new URL(source.toString() + "?page="
+ + 1), in, 1, null);
+ if (!images.isEmpty()) {
+ int pos = images.indexOf("<br/>");
+ if (pos >= 0) {
+ images = images.substring(1, pos - 1);
+ return getImage(this, null, images);
+ }
+ }
+
+ return null;
+ }
+
+ private String getAuthor(URL source, InputStream in) {
+ if (isSearch(source)) {
+ StringBuilder builder = new StringBuilder();
+ for (String author : getTags(source, in, true)) {
+ if (builder.length() > 0)
+ builder.append(", ");
+ builder.append(author);
+ }
+
+ return builder.toString();
+ }
+
String author = getLine(in, "href=\"/post/show/", 0);
if (author != null) {
String key = "href=\"";
author = author.substring(0, pos - 1);
String page = source.getProtocol() + "://"
+ source.getHost() + author;
- InputStream pageIn = Instance.getCache().open(
- new URL(page), this, false);
try {
- key = "class=\"tag-type-artist\"";
- author = getLine(pageIn, key, 0);
- if (author != null) {
- pos = author.indexOf("<a href=\"");
- if (pos >= 0) {
- author = author.substring(pos);
- pos = author.indexOf("</a>");
+ InputStream pageIn = Instance.getCache().open(
+ new URL(page), this, false);
+ try {
+ key = "class=\"tag-type-artist\"";
+ author = getLine(pageIn, key, 0);
+ if (author != null) {
+ pos = author.indexOf("<a href=\"");
if (pos >= 0) {
- author = author.substring(0, pos);
- return StringUtils.unhtml(author);
+ author = author.substring(pos);
+ pos = author.indexOf("</a>");
+ if (pos >= 0) {
+ author = author.substring(0, pos);
+ return StringUtils.unhtml(author);
+ }
}
}
+ } finally {
+ pageIn.close();
}
- } finally {
- pageIn.close();
+ } catch (Exception e) {
+ // No author found
}
}
}
return null;
}
- @Override
- protected String getDate(URL source, InputStream in) throws IOException {
- return null;
- }
-
- @Override
- protected String getSubject(URL source, InputStream in) throws IOException {
- return null;
- }
-
- @Override
- protected URL getCover(URL source, InputStream in) throws IOException {
- return null;
- }
-
- @Override
- protected String getTitle(URL source, InputStream in) throws IOException {
+ private String getTitle(InputStream in) {
String title = getLine(in, "<title>", 0);
if (title != null) {
int pos = title.indexOf('>');
title = title.substring("Pool:".length());
}
- title = title.trim();
+ title = StringUtils.unhtml(title).trim();
}
return title;
}
@Override
- protected List<Entry<String, URL>> getChapters(URL source, InputStream in)
- throws IOException {
+ protected List<Entry<String, URL>> getChapters(URL source, InputStream in,
+ Progress pg) throws IOException {
+ if (isPool(source)) {
+ return getChaptersPool(source, in, pg);
+ } else if (isSearch(source)) {
+ return getChaptersSearch(source, in, pg);
+ }
+
+ return new LinkedList<Entry<String, URL>>();
+ }
+
+ private List<Entry<String, URL>> getChaptersSearch(URL source,
+ InputStream in, Progress pg) throws IOException {
+ List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>();
+
+ String search = source.getPath();
+ if (search.endsWith("/")) {
+ search = search.substring(0, search.length() - 1);
+ }
+
+ int pos = search.lastIndexOf('/');
+ if (pos >= 0) {
+ search = search.substring(pos + 1);
+ }
+
+ String baseUrl = "https://e621.net/post/index/";
+ if (source.getHost().contains("e926")) {
+ baseUrl = baseUrl.replace("e621", "e926");
+ }
+
+ for (int i = 1; true; i++) {
+ URL url = new URL(baseUrl + i + "/" + search + "/");
+ try {
+ InputStream pageI = Instance.getCache().open(url, this, false);
+ try {
+ if (getLine(pageI, "No posts matched your search.", 0) != null)
+ break;
+ urls.add(new AbstractMap.SimpleEntry<String, URL>(Integer
+ .toString(i), url));
+ } finally {
+ pageI.close();
+ }
+ } catch (Exception e) {
+ break;
+ }
+ }
+
+ return urls;
+ }
+
+ private List<Entry<String, URL>> getChaptersPool(URL source,
+ InputStream in, Progress pg) throws IOException {
List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>();
int last = 1; // no pool/show when only one page
}
for (int i = 1; i <= last; i++) {
- final String key = Integer.toString(i);
- final URL value = new URL(source.toString() + "?page=" + i);
- urls.add(new Entry<String, URL>() {
- public URL setValue(URL value) {
- return null;
- }
-
- public URL getValue() {
- return value;
- }
-
- public String getKey() {
- return key;
- }
- });
+ urls.add(new AbstractMap.SimpleEntry<String, URL>(Integer
+ .toString(i), new URL(source.toString() + "?page=" + i)));
}
return urls;
}
@Override
- protected String getChapterContent(URL source, InputStream in, int number)
- throws IOException {
+ protected String getChapterContent(URL source, InputStream in, int number,
+ Progress pg) throws IOException {
StringBuilder builder = new StringBuilder();
String staticSite = "https://static1.e621.net";
if (source.getHost().contains("e926")) {
scan.useDelimiter("\\n");
while (scan.hasNext()) {
String line = scan.next();
- if (line.contains("class=\"preview\"")) {
+ if (line.contains("class=\"preview")) {
for (int pos = line.indexOf(key); pos >= 0; pos = line.indexOf(
key, pos + key.length())) {
int endPos = line.indexOf("\"", pos);
id = id.substring(0, dotPos);
builder.append("[");
builder.append(id);
- builder.append("]\n");
+ builder.append("]<br/>");
}
}
}
return builder.toString();
}
+
+ private boolean isPool(URL url) {
+ return url.getPath().startsWith("/pool/");
+ }
+
+ private boolean isSearch(URL url) {
+ return url.getPath().startsWith("/post/index/");
+ }
}
git://git.nikiroo.be / nikiroo-utils.git / blobdiff