| 1 | package be.nikiroo.fanfix.supported; |
| 2 | |
| 3 | import java.awt.image.BufferedImage; |
| 4 | import java.io.IOException; |
| 5 | import java.io.InputStream; |
| 6 | import java.net.MalformedURLException; |
| 7 | import java.net.URL; |
| 8 | import java.util.ArrayList; |
| 9 | import java.util.List; |
| 10 | import java.util.Map.Entry; |
| 11 | import java.util.Scanner; |
| 12 | |
| 13 | import be.nikiroo.fanfix.Instance; |
| 14 | import be.nikiroo.fanfix.data.Chapter; |
| 15 | import be.nikiroo.fanfix.data.MetaData; |
| 16 | import be.nikiroo.fanfix.data.Story; |
| 17 | import be.nikiroo.utils.Progress; |
| 18 | import be.nikiroo.utils.StringUtils; |
| 19 | |
| 20 | /** |
| 21 | * Support class for <a href="https://e-hentai.org/">e-hentai.org</a>, a website |
| 22 | * supporting mostly but not always NSFW comics, including some of MLP. |
| 23 | * |
| 24 | * @author niki |
| 25 | */ |
| 26 | class EHentai extends BasicSupport { |
| 27 | @Override |
| 28 | public String getSourceName() { |
| 29 | return "e-hentai.org"; |
| 30 | } |
| 31 | |
| 32 | @Override |
| 33 | protected MetaData getMeta(URL source, InputStream in) throws IOException { |
| 34 | MetaData meta = new MetaData(); |
| 35 | |
| 36 | meta.setTitle(getTitle(reset(in))); |
| 37 | meta.setAuthor(getAuthor(reset(in))); |
| 38 | meta.setDate(getDate(reset(in))); |
| 39 | meta.setTags(getTags(reset(in))); |
| 40 | meta.setSource(getSourceName()); |
| 41 | meta.setUrl(source.toString()); |
| 42 | meta.setPublisher(getSourceName()); |
| 43 | meta.setUuid(source.toString()); |
| 44 | meta.setLuid(""); |
| 45 | meta.setLang(getLang(reset(in))); |
| 46 | meta.setSubject("Hentai"); |
| 47 | meta.setType(getType().toString()); |
| 48 | meta.setImageDocument(true); |
| 49 | meta.setCover(getCover(source, reset(in))); |
| 50 | meta.setFakeCover(true); |
| 51 | |
| 52 | return meta; |
| 53 | } |
| 54 | |
| 55 | @Override |
| 56 | public Story process(URL url, Progress pg) throws IOException { |
| 57 | // There is no chapters on e621, just pagination... |
| 58 | Story story = super.process(url, pg); |
| 59 | |
| 60 | Chapter only = new Chapter(1, null); |
| 61 | for (Chapter chap : story) { |
| 62 | only.getParagraphs().addAll(chap.getParagraphs()); |
| 63 | } |
| 64 | |
| 65 | story.getChapters().clear(); |
| 66 | story.getChapters().add(only); |
| 67 | |
| 68 | return story; |
| 69 | } |
| 70 | |
| 71 | @Override |
| 72 | protected boolean supports(URL url) { |
| 73 | return "e-hentai.org".equals(url.getHost()); |
| 74 | } |
| 75 | |
| 76 | @Override |
| 77 | protected boolean isHtml() { |
| 78 | return true; |
| 79 | } |
| 80 | |
| 81 | private BufferedImage getCover(URL source, InputStream in) { |
| 82 | BufferedImage author = null; |
| 83 | String coverLine = getKeyLine(in, "<div id=\"gd1\"", " url(", ")"); |
| 84 | if (coverLine != null) { |
| 85 | coverLine = StringUtils.unhtml(coverLine).trim(); |
| 86 | author = getImage(this, source, coverLine); |
| 87 | } |
| 88 | |
| 89 | return author; |
| 90 | } |
| 91 | |
| 92 | private String getAuthor(InputStream in) { |
| 93 | String author = null; |
| 94 | |
| 95 | List<String> tagsAuthor = getTagsAuthor(in); |
| 96 | if (!tagsAuthor.isEmpty()) { |
| 97 | author = tagsAuthor.get(0); |
| 98 | } |
| 99 | |
| 100 | return author; |
| 101 | } |
| 102 | |
| 103 | private String getLang(InputStream in) { |
| 104 | String lang = null; |
| 105 | |
| 106 | String langLine = getKeyLine(in, "class=\"gdt1\">Language", |
| 107 | "class=\"gdt2\"", "</td>"); |
| 108 | if (langLine != null) { |
| 109 | langLine = StringUtils.unhtml(langLine).trim(); |
| 110 | if (langLine.equalsIgnoreCase("English")) { |
| 111 | lang = "EN"; |
| 112 | } else if (langLine.equalsIgnoreCase("Japanese")) { |
| 113 | lang = "JP"; |
| 114 | } else if (langLine.equalsIgnoreCase("French")) { |
| 115 | lang = "FR"; |
| 116 | } else { |
| 117 | // TODO find the code? |
| 118 | lang = langLine; |
| 119 | } |
| 120 | } |
| 121 | |
| 122 | return lang; |
| 123 | } |
| 124 | |
| 125 | private String getDate(InputStream in) { |
| 126 | String date = null; |
| 127 | |
| 128 | String dateLine = getKeyLine(in, "class=\"gdt1\">Posted", |
| 129 | "class=\"gdt2\"", "</td>"); |
| 130 | if (dateLine != null) { |
| 131 | dateLine = StringUtils.unhtml(dateLine).trim(); |
| 132 | if (dateLine.length() > 10) { |
| 133 | dateLine = dateLine.substring(0, 10).trim(); |
| 134 | } |
| 135 | |
| 136 | date = dateLine; |
| 137 | } |
| 138 | |
| 139 | return date; |
| 140 | } |
| 141 | |
| 142 | private List<String> getTags(InputStream in) { |
| 143 | List<String> tags = new ArrayList<String>(); |
| 144 | List<String> tagsAuthor = getTagsAuthor(in); |
| 145 | |
| 146 | for (int i = 1; i < tagsAuthor.size(); i++) { |
| 147 | tags.add(tagsAuthor.get(i)); |
| 148 | } |
| 149 | |
| 150 | return tags; |
| 151 | } |
| 152 | |
| 153 | private List<String> getTagsAuthor(InputStream in) { |
| 154 | List<String> tags = new ArrayList<String>(); |
| 155 | String tagLine = getKeyLine(in, "<meta name=\"description\"", "Tags: ", |
| 156 | null); |
| 157 | if (tagLine != null) { |
| 158 | for (String tag : tagLine.split(",")) { |
| 159 | String candi = tag.trim(); |
| 160 | if (!candi.isEmpty() && !tags.contains(candi)) { |
| 161 | tags.add(candi); |
| 162 | } |
| 163 | } |
| 164 | } |
| 165 | |
| 166 | return tags; |
| 167 | } |
| 168 | |
| 169 | private String getTitle(InputStream in) { |
| 170 | String siteName = " - E-Hentai Galleries"; |
| 171 | |
| 172 | String title = getLine(in, "<title>", 0); |
| 173 | if (title != null) { |
| 174 | title = StringUtils.unhtml(title).trim(); |
| 175 | if (title.endsWith(siteName)) { |
| 176 | title = title.substring(0, title.length() - siteName.length()) |
| 177 | .trim(); |
| 178 | } |
| 179 | } |
| 180 | |
| 181 | return title; |
| 182 | } |
| 183 | |
| 184 | @Override |
| 185 | protected String getDesc(URL source, InputStream in) throws IOException { |
| 186 | String desc = null; |
| 187 | |
| 188 | String descLine = getKeyLine(in, "Uploader Comment", null, |
| 189 | "<div class=\"c7\""); |
| 190 | if (descLine != null) { |
| 191 | desc = StringUtils.unhtml(descLine); |
| 192 | } |
| 193 | |
| 194 | return desc; |
| 195 | } |
| 196 | |
| 197 | @Override |
| 198 | protected List<Entry<String, URL>> getChapters(URL source, InputStream in, |
| 199 | Progress pg) throws IOException { |
| 200 | List<Entry<String, URL>> urls = new ArrayList<Entry<String, URL>>(); |
| 201 | int last = 0; // no pool/show when only one page, first page == page 0 |
| 202 | |
| 203 | @SuppressWarnings("resource") |
| 204 | Scanner scan = new Scanner(in, "UTF-8"); |
| 205 | scan.useDelimiter(">"); |
| 206 | while (scan.hasNext()) { |
| 207 | String line = scan.next(); |
| 208 | if (line.contains(source.toString())) { |
| 209 | String page = line.substring(line.indexOf(source.toString())); |
| 210 | String pkey = "?p="; |
| 211 | if (page.contains(pkey)) { |
| 212 | page = page.substring(page.indexOf(pkey) + pkey.length()); |
| 213 | String number = ""; |
| 214 | while (!page.isEmpty() && page.charAt(0) >= '0' |
| 215 | && page.charAt(0) <= '9') { |
| 216 | number += page.charAt(0); |
| 217 | page = page.substring(1); |
| 218 | } |
| 219 | if (number.isEmpty()) { |
| 220 | number = "0"; |
| 221 | } |
| 222 | |
| 223 | int current = Integer.parseInt(number); |
| 224 | if (last < current) { |
| 225 | last = current; |
| 226 | } |
| 227 | } |
| 228 | } |
| 229 | } |
| 230 | |
| 231 | for (int i = 0; i <= last; i++) { |
| 232 | final String key = Integer.toString(i + 1); |
| 233 | final URL value = new URL(source.toString() + "?p=" + i); |
| 234 | urls.add(new Entry<String, URL>() { |
| 235 | @Override |
| 236 | public URL setValue(URL value) { |
| 237 | return null; |
| 238 | } |
| 239 | |
| 240 | @Override |
| 241 | public URL getValue() { |
| 242 | return value; |
| 243 | } |
| 244 | |
| 245 | @Override |
| 246 | public String getKey() { |
| 247 | return key; |
| 248 | } |
| 249 | }); |
| 250 | } |
| 251 | |
| 252 | return urls; |
| 253 | } |
| 254 | |
| 255 | @Override |
| 256 | protected String getChapterContent(URL source, InputStream in, int number, |
| 257 | Progress pg) throws IOException { |
| 258 | String staticSite = "https://e-hentai.org/s/"; |
| 259 | List<URL> pages = new ArrayList<URL>(); |
| 260 | |
| 261 | @SuppressWarnings("resource") |
| 262 | Scanner scan = new Scanner(in, "UTF-8"); |
| 263 | scan.useDelimiter("\""); |
| 264 | while (scan.hasNext()) { |
| 265 | String line = scan.next(); |
| 266 | if (line.startsWith(staticSite)) { |
| 267 | try { |
| 268 | pages.add(new URL(line)); |
| 269 | } catch (MalformedURLException e) { |
| 270 | Instance.getTraceHandler().error(new IOException( |
| 271 | "Parsing error, a link is not correctly parsed: " |
| 272 | + line, e)); |
| 273 | } |
| 274 | } |
| 275 | } |
| 276 | |
| 277 | if (pg == null) { |
| 278 | pg = new Progress(); |
| 279 | } |
| 280 | pg.setMinMax(0, pages.size()); |
| 281 | pg.setProgress(0); |
| 282 | |
| 283 | StringBuilder builder = new StringBuilder(); |
| 284 | |
| 285 | for (URL page : pages) { |
| 286 | InputStream pageIn = Instance.getCache().open(page, this, false); |
| 287 | try { |
| 288 | String link = getKeyLine(pageIn, "id=\"img\"", "src=\"", "\""); |
| 289 | if (link != null && !link.isEmpty()) { |
| 290 | builder.append("["); |
| 291 | builder.append(link); |
| 292 | builder.append("]<br/>"); |
| 293 | } |
| 294 | pg.add(1); |
| 295 | } finally { |
| 296 | if (pageIn != null) { |
| 297 | pageIn.close(); |
| 298 | } |
| 299 | } |
| 300 | } |
| 301 | |
| 302 | pg.done(); |
| 303 | return builder.toString(); |
| 304 | } |
| 305 | } |