X-Git-Url: http://git.nikiroo.be/?p=nikiroo-utils.git;a=blobdiff_plain;f=supported%2FE621.java;h=f1660e18cb34a9da6373ac03e6918ccc630ff25f;hp=dfa9e5ed6a60e4694fc8494dcf196b4328259ee6;hb=2e1300b9580ae1b6dded5a734c617a66a116c16d;hpb=669a62833b4458bad0772debdd06921080500221 diff --git a/supported/E621.java b/supported/E621.java index dfa9e5e..f1660e1 100644 --- a/supported/E621.java +++ b/supported/E621.java @@ -9,22 +9,25 @@ import java.net.URLDecoder; import java.util.AbstractMap; import java.util.ArrayList; import java.util.Collections; +import java.util.Date; import java.util.LinkedList; import java.util.List; import java.util.Map.Entry; -import java.util.Scanner; + +import org.jsoup.helper.DataUtil; +import org.jsoup.nodes.Document; +import org.jsoup.nodes.Element; 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.IOUtils; import be.nikiroo.utils.Image; import be.nikiroo.utils.Progress; import be.nikiroo.utils.StringUtils; /** - * Support class for e621.net and e926.net, a Furry website supporting comics, + * Support class for e621.net and + * e926.net, a Furry website supporting comics, * including some of MLP. *

* e926.net only shows the "clean" images and @@ -32,335 +35,226 @@ import be.nikiroo.utils.StringUtils; * * @author niki */ -class E621 extends BasicSupport_Deprecated { +class E621 extends BasicSupport { + @Override + protected boolean supports(URL url) { + String host = url.getHost(); + if (host.startsWith("www.")) { + host = host.substring("www.".length()); + } + + return ("e621.net".equals(host) || "e926.net".equals(host)) && (isPool(url) || isSearchOrSet(url)); + } + @Override - protected MetaData getMeta(URL source, InputStream in) throws IOException { + protected boolean isHtml() { + return true; + } + + @Override + protected MetaData getMeta() throws IOException { MetaData meta = new MetaData(); - meta.setTitle(getTitle(reset(in))); - meta.setAuthor(getAuthor(source, reset(in))); + meta.setTitle(getTitle()); + meta.setAuthor(getAuthor()); meta.setDate(""); - meta.setTags(getTags(source, reset(in), false)); + meta.setTags(getTags()); meta.setSource(getType().getSourceName()); - meta.setUrl(source.toString()); + meta.setUrl(getSource().toString()); meta.setPublisher(getType().getSourceName()); - meta.setUuid(source.toString()); + meta.setUuid(getSource().toString()); meta.setLuid(""); meta.setLang("en"); meta.setSubject("Furry"); meta.setType(getType().toString()); meta.setImageDocument(true); - meta.setCover(getCover(source, reset(in))); + meta.setCover(getCover()); meta.setFakeCover(true); return meta; } - private List getTags(URL source, InputStream in, boolean authors) { - List tags = new ArrayList(); - - 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, Progress pg) throws IOException { - // There is no chapters on e621, just pagination... - Story story = super.process(url, pg); + protected String getDesc() throws IOException { + if (isSearchOrSet(getSource())) { + StringBuilder builder = new StringBuilder(); + builder.append("A collection of images from ").append(getSource().getHost()).append("\n") // + .append("\tTime of creation: " + StringUtils.fromTime(new Date().getTime())).append("\n") // + .append("\tTags: ");// + for (String tag : getTags()) { + builder.append("\t\t").append(tag); + } - Chapter only = new Chapter(1, null); - for (Chapter chap : story) { - only.getParagraphs().addAll(chap.getParagraphs()); + return builder.toString(); } - story.getChapters().clear(); - story.getChapters().add(only); - - return story; - } - - @Override - protected boolean supports(URL url) { - String host = url.getHost(); - if (host.startsWith("www.")) { - host = host.substring("www.".length()); + if (isPool(getSource())) { + Element el = getSourceNode().getElementById("description"); + if (el != null) { + return el.text(); + } } - return ("e621.net".equals(host) || "e926.net".equals(host)) - && (isPool(url) || isSearch(url)); + return null; } @Override - protected boolean isHtml() { - return true; - } - - private Image getCover(URL source, InputStream in) throws IOException { - URL urlForCover = source; - if (isPool(source)) { - urlForCover = new URL(source.toString() + "?page=1"); - } - - String images = getChapterContent(urlForCover, in, 1, null); - if (!images.isEmpty()) { - int pos = images.indexOf("
"); - if (pos >= 0) { - images = images.substring(1, pos - 1); - return getImage(this, null, images); - } + protected List> getChapters(Progress pg) throws IOException { + if (isPool(getSource())) { + String baseUrl = "https://e621.net/" + getSource().getPath() + "?page="; + return getChapters(getSource(), pg, baseUrl, ""); + } else if (isSearchOrSet(getSource())) { + String baseUrl = "https://e621.net/posts/?page="; + String search = "&tags=" + getTagsFromUrl(getSource()); + return getChapters(getSource(), pg, baseUrl, search); } - return null; + return new LinkedList>(); } - 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); - } + private List> getChapters(URL source, Progress pg, String baseUrl, String parameters) + throws IOException { + List> urls = new ArrayList>(); - return builder.toString(); + if (source.getHost().contains("e926")) { + baseUrl = baseUrl.replace("e621", "e926"); } - String author = getLine(in, "href=\"/post/show/", 0); - if (author != null) { - String key = "href=\""; - int pos = author.indexOf(key); - if (pos >= 0) { - author = author.substring(pos + key.length()); - pos = author.indexOf("\""); - if (pos >= 0) { - author = author.substring(0, pos - 1); - String page = source.getProtocol() + "://" - + source.getHost() + author; - try { - 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("= 0) { - author = author.substring(pos); - pos = author.indexOf(""); - if (pos >= 0) { - author = author.substring(0, pos); - return StringUtils.unhtml(author); - } - } - } - } finally { - pageIn.close(); - } - } catch (Exception e) { - // No author found + for (int i = 1; true; i++) { + URL url = new URL(baseUrl + i + parameters); + try { + InputStream pageI = Instance.getInstance().getCache().open(url, this, false); + try { + if (IOUtils.readSmallStream(pageI).contains("Nobody here but us chickens!")) { + break; } + urls.add(new AbstractMap.SimpleEntry("Page " + Integer.toString(i), url)); + } finally { + pageI.close(); } + } catch (Exception e) { + break; } } - return null; + // They are sorted in reverse order on the website + Collections.reverse(urls); + return urls; } - private String getTitle(InputStream in) { - String title = getLine(in, "", 0); - if (title != null) { - int pos = title.indexOf('>'); - if (pos >= 0) { - title = title.substring(pos + 1); - pos = title.indexOf('<'); - if (pos >= 0) { - title = title.substring(0, pos); - } - } - - if (title.startsWith("Pool:")) { - title = title.substring("Pool:".length()); - } - - title = StringUtils.unhtml(title).trim(); + @Override + protected String getChapterContent(URL chapUrl, int number, Progress pg) throws IOException { + StringBuilder builder = new StringBuilder(); + Document chapterNode = loadDocument(chapUrl); + for (Element el : chapterNode.getElementsByTag("article")) { + builder.append("["); + builder.append(el.attr("data-file-url")); + builder.append("]<br/>"); } - return title; + return builder.toString(); } @Override - protected String getDesc(URL source, InputStream in) throws IOException { - String desc = getLine(in, "margin-bottom: 2em;", 0); - - if (desc != null) { - StringBuilder builder = new StringBuilder(); - - boolean inTags = false; - for (char car : desc.toCharArray()) { - if ((inTags && car == '>') || (!inTags && car == '<')) { - inTags = !inTags; - } - - if (inTags) { - builder.append(car); + protected URL getCanonicalUrl(URL source) { + if (isSetOriginalUrl(source)) { + try { + Document doc = DataUtil.load(Instance.getInstance().getCache().open(source, this, false), "UTF-8", source.toString()); + for (Element shortname : doc.getElementsByClass("set-shortname")) { + for (Element el : shortname.getElementsByTag("a")) { + if (!el.attr("href").isEmpty()) + return new URL(el.absUrl("href")); + } } + } catch (IOException e) { + Instance.getInstance().getTraceHandler().error(e); } - - return builder.toString().trim(); } - return null; - } - - @Override - 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); + try { + return new URL(source.toString().replace("/pool/show/", "/pools/")); + } catch (MalformedURLException e) { + } } - return new LinkedList<Entry<String, URL>>(); + return super.getCanonicalUrl(source); } - private List<Entry<String, URL>> getChaptersSearch(URL source, - InputStream in, Progress pg) throws IOException { - List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>(); + // returns "xxx+ddd+ggg" if "tags=xxx+ddd+ggg" was present in the query + private String getTagsFromUrl(URL url) { + String tags = url == null ? "" : url.getQuery(); + int pos = tags.indexOf("tags="); - String search = source.getPath(); - if (search.endsWith("/")) { - search = search.substring(0, search.length() - 1); + if (pos >= 0) { + tags = tags.substring(pos).substring("tags=".length()); + } else { + return ""; } - int pos = search.lastIndexOf('/'); - if (pos >= 0) { - search = search.substring(pos + 1); + pos = tags.indexOf('&'); + if (pos > 0) { + tags = tags.substring(0, pos); + } + pos = tags.indexOf('/'); + if (pos > 0) { + tags = tags.substring(0, pos); } - String baseUrl = "https://e621.net/post/index/"; - if (source.getHost().contains("e926")) { - baseUrl = baseUrl.replace("e621", "e926"); + return tags; + } + + private String getTitle() { + String title = ""; + + Element el = getSourceNode().getElementsByTag("title").first(); + if (el != null) { + title = el.text().trim(); } - 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>("Page " - + Integer.toString(i), url)); - } finally { - pageI.close(); - } - } catch (Exception e) { - break; + for (String s : new String[] { "e621", "-", "e621" }) { + if (title.startsWith(s)) { + title = title.substring(s.length()).trim(); + } + if (title.endsWith(s)) { + title = title.substring(0, title.length() - s.length()).trim(); } + } - // They are sorted in reverse order on the website - Collections.reverse(urls); - return urls; + if (isSearchOrSet(getSource())) { + title = title.isEmpty() ? "e621" : "[e621] " + title; + } + return title; } - 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 - - @SuppressWarnings("resource") - Scanner scan = new Scanner(in, "UTF-8"); - scan.useDelimiter("\\n"); - while (scan.hasNext()) { - String line = scan.next(); - for (int pos = line.indexOf(source.getPath()); pos >= 0; pos = line - .indexOf(source.getPath(), pos + source.getPath().length())) { - int equalPos = line.indexOf("=", pos); - int quotePos = line.indexOf("\"", pos); - if (equalPos >= 0 && quotePos > equalPos) { - String snum = line.substring(equalPos + 1, quotePos); - try { - int num = Integer.parseInt(snum); - if (num > last) { - last = num; - } - } catch (NumberFormatException e) { + private String getAuthor() throws IOException { + StringBuilder builder = new StringBuilder(); + + if (isSearchOrSet(getSource())) { + for (Element el : getSourceNode().getElementsByClass("search-tag")) { + if (el.attr("itemprop").equals("author")) { + if (builder.length() > 0) { + builder.append(", "); } + builder.append(el.text().trim()); } } } - for (int i = 1; i <= last; i++) { - urls.add(new AbstractMap.SimpleEntry<String, URL>(Integer - .toString(i), new URL(source.toString() + "?page=" + i))); - } + if (isPool(getSource())) { + String desc = getDesc(); + String descL = desc.toLowerCase(); - return urls; - } - - @Override - 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")) { - staticSite = staticSite.replace("e621", "e926"); - } + if (descL.startsWith("by:") || descL.startsWith("by ")) { + desc = desc.substring(3).trim(); + desc = desc.split("\n")[0]; - String key = staticSite + "/data/preview/"; - - @SuppressWarnings("resource") - Scanner scan = new Scanner(in, "UTF-8"); - scan.useDelimiter("\\n"); - while (scan.hasNext()) { - String line = scan.next(); - 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); - if (endPos >= 0) { - String id = line.substring(pos + key.length(), endPos); - id = staticSite + "/data/" + id; - - int dotPos = id.lastIndexOf("."); - if (dotPos >= 0) { - id = id.substring(0, dotPos); - builder.append("["); - builder.append(id); - builder.append("]<br/>"); - } - } + String tab[] = desc.split(" "); + for (int i = 0; i < Math.min(tab.length, 5); i++) { + if (tab[i].startsWith("http")) + break; + builder.append(" ").append(tab[i]); } } } @@ -368,42 +262,52 @@ class E621 extends BasicSupport_Deprecated { return builder.toString(); } - @Override - protected URL getCanonicalUrl(URL source) { - if (isSearch(source)) { - // /post?tags=tag1+tag2 -> ../post/index/1/tag1%32tag2 - String key = "?tags="; - if (source.toString().contains(key)) { - int pos = source.toString().indexOf(key); - String tags = source.toString().substring(pos + key.length()); - tags = tags.replace("+", "%20"); - - String base = source.toString().substring(0, pos); - if (!base.endsWith("/")) { - base += "/"; - } - if (base.endsWith("/search/")) { - base = base.substring(0, base.indexOf("/search/") + 1); - } - + // no tags for pools + private List<String> getTags() { + List<String> tags = new ArrayList<String>(); + if (isSearchOrSet(getSource())) { + String str = getTagsFromUrl(getSource()); + for (String tag : str.split("\\+")) { try { - return new URL(base + "index/1/" + tags); - } catch (MalformedURLException e) { - Instance.getTraceHandler().error(e); + tags.add(URLDecoder.decode(tag.trim(), "UTF-8").trim()); + } catch (UnsupportedEncodingException e) { } } } - return super.getCanonicalUrl(source); + return tags; + } + + private Image getCover() throws IOException { + Image image = null; + List<Entry<String, URL>> chapters = getChapters(null); + if (!chapters.isEmpty()) { + URL chap1Url = chapters.get(0).getValue(); + String imgsChap1 = getChapterContent(chap1Url, 1, null); + if (!imgsChap1.isEmpty()) { + imgsChap1 = imgsChap1.split("]")[0].substring(1).trim(); + image = bsImages.getImage(this, new URL(imgsChap1)); + } + } + + return image; + } + + // note: will be removed at getCanonicalUrl() + private boolean isSetOriginalUrl(URL originalUrl) { + return originalUrl.getPath().startsWith("/post_sets/"); } private boolean isPool(URL url) { - return url.getPath().startsWith("/pool/"); + return url.getPath().startsWith("/pools/") || url.getPath().startsWith("/pool/show/"); } - private boolean isSearch(URL url) { - return url.getPath().startsWith("/post/index/") - || (url.getPath().equals("/post/search") && url.getQuery() - .startsWith("tags=")); + // set will be renamed into search by canonical url + private boolean isSearchOrSet(URL url) { + return + // search: + (url.getPath().equals("/posts") && url.getQuery().contains("tags=")) + // or set: + || isSetOriginalUrl(url); } }