| 1 | package be.nikiroo.fanfix.supported; |
| 2 | |
| 3 | import java.io.IOException; |
| 4 | import java.io.InputStream; |
| 5 | import java.net.MalformedURLException; |
| 6 | import java.net.URL; |
| 7 | import java.util.ArrayList; |
| 8 | import java.util.Date; |
| 9 | import java.util.HashMap; |
| 10 | import java.util.List; |
| 11 | import java.util.Map; |
| 12 | import java.util.Scanner; |
| 13 | import java.util.Map.Entry; |
| 14 | |
| 15 | import org.json.JSONException; |
| 16 | import org.json.JSONObject; |
| 17 | import org.jsoup.helper.DataUtil; |
| 18 | import org.jsoup.nodes.Document; |
| 19 | import org.jsoup.nodes.Element; |
| 20 | import org.jsoup.nodes.Node; |
| 21 | |
| 22 | import be.nikiroo.fanfix.Instance; |
| 23 | import be.nikiroo.fanfix.bundles.StringId; |
| 24 | import be.nikiroo.fanfix.data.Chapter; |
| 25 | import be.nikiroo.fanfix.data.MetaData; |
| 26 | import be.nikiroo.fanfix.data.Story; |
| 27 | import be.nikiroo.utils.Progress; |
| 28 | import be.nikiroo.utils.StringUtils; |
| 29 | |
| 30 | /** |
| 31 | * This class is the base class used by the other support classes. It can be |
| 32 | * used outside of this package, and have static method that you can use to get |
| 33 | * access to the correct support class. |
| 34 | * <p> |
| 35 | * It will be used with 'resources' (usually web pages or files). |
| 36 | * |
| 37 | * @author niki |
| 38 | */ |
| 39 | public abstract class BasicSupport { |
| 40 | private Document sourceNode; |
| 41 | private URL source; |
| 42 | private SupportType type; |
| 43 | private URL currentReferer; // with only one 'r', as in 'HTTP'... |
| 44 | |
| 45 | static protected BasicSupportHelper bsHelper = new BasicSupportHelper(); |
| 46 | static protected BasicSupportImages bsImages = new BasicSupportImages(); |
| 47 | static protected BasicSupportPara bsPara = new BasicSupportPara(new BasicSupportHelper(), new BasicSupportImages()); |
| 48 | |
| 49 | /** |
| 50 | * Check if the given resource is supported by this {@link BasicSupport}. |
| 51 | * |
| 52 | * @param url |
| 53 | * the resource to check for |
| 54 | * |
| 55 | * @return TRUE if it is |
| 56 | */ |
| 57 | protected abstract boolean supports(URL url); |
| 58 | |
| 59 | /** |
| 60 | * Return TRUE if the support will return HTML encoded content values for |
| 61 | * the chapters content. |
| 62 | * |
| 63 | * @return TRUE for HTML |
| 64 | */ |
| 65 | protected abstract boolean isHtml(); |
| 66 | |
| 67 | /** |
| 68 | * Return the {@link MetaData} of this story. |
| 69 | * |
| 70 | * @return the associated {@link MetaData}, never NULL |
| 71 | * |
| 72 | * @throws IOException |
| 73 | * in case of I/O error |
| 74 | */ |
| 75 | protected abstract MetaData getMeta() throws IOException; |
| 76 | |
| 77 | /** |
| 78 | * Return the story description. |
| 79 | * |
| 80 | * @return the description |
| 81 | * |
| 82 | * @throws IOException |
| 83 | * in case of I/O error |
| 84 | */ |
| 85 | protected abstract String getDesc() throws IOException; |
| 86 | |
| 87 | /** |
| 88 | * Return the list of chapters (name and resource). |
| 89 | * <p> |
| 90 | * Can be NULL if this {@link BasicSupport} do no use chapters. |
| 91 | * |
| 92 | * @param pg |
| 93 | * the optional progress reporter |
| 94 | * |
| 95 | * @return the chapters or NULL |
| 96 | * |
| 97 | * @throws IOException |
| 98 | * in case of I/O error |
| 99 | */ |
| 100 | protected abstract List<Entry<String, URL>> getChapters(Progress pg) |
| 101 | throws IOException; |
| 102 | |
| 103 | /** |
| 104 | * Return the content of the chapter (possibly HTML encoded, if |
| 105 | * {@link BasicSupport#isHtml()} is TRUE). |
| 106 | * |
| 107 | * @param chapUrl |
| 108 | * the chapter {@link URL} |
| 109 | * @param number |
| 110 | * the chapter number |
| 111 | * @param pg |
| 112 | * the optional progress reporter |
| 113 | * |
| 114 | * @return the content |
| 115 | * |
| 116 | * @throws IOException |
| 117 | * in case of I/O error |
| 118 | */ |
| 119 | protected abstract String getChapterContent(URL chapUrl, int number, |
| 120 | Progress pg) throws IOException; |
| 121 | |
| 122 | /** |
| 123 | * Return the list of cookies (values included) that must be used to |
| 124 | * correctly fetch the resources. |
| 125 | * <p> |
| 126 | * You are expected to call the super method implementation if you override |
| 127 | * it. |
| 128 | * |
| 129 | * @return the cookies |
| 130 | */ |
| 131 | public Map<String, String> getCookies() { |
| 132 | return new HashMap<String, String>(); |
| 133 | } |
| 134 | |
| 135 | /** |
| 136 | * OAuth authorisation (aka, "bearer XXXXXXX"). |
| 137 | * |
| 138 | * @return the OAuth string |
| 139 | */ |
| 140 | public String getOAuth() { |
| 141 | return null; |
| 142 | } |
| 143 | |
| 144 | /** |
| 145 | * Return the canonical form of the main {@link URL}. |
| 146 | * |
| 147 | * @param source |
| 148 | * the source {@link URL}, which can be NULL |
| 149 | * |
| 150 | * @return the canonical form of this {@link URL} or NULL if the source was |
| 151 | * NULL |
| 152 | */ |
| 153 | protected URL getCanonicalUrl(URL source) { |
| 154 | return source; |
| 155 | } |
| 156 | |
| 157 | /** |
| 158 | * The main {@link Node} for this {@link Story}. |
| 159 | * |
| 160 | * @return the node |
| 161 | */ |
| 162 | protected Element getSourceNode() { |
| 163 | return sourceNode; |
| 164 | } |
| 165 | |
| 166 | /** |
| 167 | * The main {@link URL} for this {@link Story}. |
| 168 | * |
| 169 | * @return the URL |
| 170 | */ |
| 171 | protected URL getSource() { |
| 172 | return source; |
| 173 | } |
| 174 | |
| 175 | /** |
| 176 | * The current referer {@link URL} (only one 'r', as in 'HTML'...), i.e., |
| 177 | * the current {@link URL} we work on. |
| 178 | * |
| 179 | * @return the referer |
| 180 | */ |
| 181 | public URL getCurrentReferer() { |
| 182 | return currentReferer; |
| 183 | } |
| 184 | |
| 185 | /** |
| 186 | * The current referer {@link URL} (only one 'r', as in 'HTML'...), i.e., |
| 187 | * the current {@link URL} we work on. |
| 188 | * |
| 189 | * @param currentReferer |
| 190 | * the new referer |
| 191 | */ |
| 192 | protected void setCurrentReferer(URL currentReferer) { |
| 193 | this.currentReferer = currentReferer; |
| 194 | } |
| 195 | |
| 196 | /** |
| 197 | * The support type. |
| 198 | * |
| 199 | * @return the type |
| 200 | */ |
| 201 | public SupportType getType() { |
| 202 | return type; |
| 203 | } |
| 204 | |
| 205 | /** |
| 206 | * The support type. |
| 207 | * |
| 208 | * @param type |
| 209 | * the new type |
| 210 | */ |
| 211 | protected void setType(SupportType type) { |
| 212 | this.type = type; |
| 213 | } |
| 214 | |
| 215 | /** |
| 216 | * Open an input link that will be used for the support. |
| 217 | * <p> |
| 218 | * Can return NULL, in which case you are supposed to work without a source |
| 219 | * node. |
| 220 | * |
| 221 | * @param source |
| 222 | * the source {@link URL} |
| 223 | * |
| 224 | * @return the {@link InputStream} |
| 225 | * |
| 226 | * @throws IOException |
| 227 | * in case of I/O error |
| 228 | */ |
| 229 | protected Document loadDocument(URL source) throws IOException { |
| 230 | String url = getCanonicalUrl(source).toString(); |
| 231 | return DataUtil.load(Instance.getInstance().getCache().open(source, this, false), "UTF-8", url.toString()); |
| 232 | } |
| 233 | |
| 234 | /** |
| 235 | * Log into the support (can be a no-op depending upon the support). |
| 236 | * |
| 237 | * @throws IOException |
| 238 | * in case of I/O error |
| 239 | */ |
| 240 | protected void login() throws IOException { |
| 241 | } |
| 242 | |
| 243 | /** |
| 244 | * Now that we have processed the {@link Story}, close the resources if any. |
| 245 | */ |
| 246 | protected void close() { |
| 247 | setCurrentReferer(null); |
| 248 | } |
| 249 | |
| 250 | /** |
| 251 | * Process the given story resource into a partially filled {@link Story} |
| 252 | * object containing the name and metadata. |
| 253 | * |
| 254 | * @param getDesc |
| 255 | * retrieve the description of the story, or not |
| 256 | * @param pg |
| 257 | * the optional progress reporter |
| 258 | * |
| 259 | * @return the {@link Story}, never NULL |
| 260 | * |
| 261 | * @throws IOException |
| 262 | * in case of I/O error |
| 263 | */ |
| 264 | protected Story processMeta(boolean getDesc, Progress pg) |
| 265 | throws IOException { |
| 266 | if (pg == null) { |
| 267 | pg = new Progress(); |
| 268 | } else { |
| 269 | pg.setMinMax(0, 100); |
| 270 | } |
| 271 | |
| 272 | pg.setProgress(30); |
| 273 | |
| 274 | Story story = new Story(); |
| 275 | MetaData meta = getMeta(); |
| 276 | if (meta.getCreationDate() == null |
| 277 | || meta.getCreationDate().trim().isEmpty()) { |
| 278 | meta.setCreationDate(bsHelper |
| 279 | .formatDate(StringUtils.fromTime(new Date().getTime()))); |
| 280 | } |
| 281 | story.setMeta(meta); |
| 282 | pg.put("meta", meta); |
| 283 | |
| 284 | pg.setProgress(50); |
| 285 | |
| 286 | if (meta.getCover() == null) { |
| 287 | meta.setCover(bsHelper.getDefaultCover(meta.getSubject())); |
| 288 | } |
| 289 | |
| 290 | pg.setProgress(60); |
| 291 | |
| 292 | if (getDesc) { |
| 293 | String descChapterName = Instance.getInstance().getTrans().getString(StringId.DESCRIPTION); |
| 294 | story.getMeta().setResume(bsPara.makeChapter(this, source, 0, descChapterName, // |
| 295 | getDesc(), isHtml(), null)); |
| 296 | } |
| 297 | |
| 298 | pg.done(); |
| 299 | return story; |
| 300 | } |
| 301 | |
| 302 | /** |
| 303 | * Utility method to convert the given URL into a JSON object. |
| 304 | * <p> |
| 305 | * Note that this method expects small JSON files (everything is copied into |
| 306 | * memory at least twice). |
| 307 | * |
| 308 | * @param url |
| 309 | * the URL to parse |
| 310 | * @param stable |
| 311 | * TRUE for more stable resources, FALSE when they often change |
| 312 | * |
| 313 | * @return the JSON object |
| 314 | * |
| 315 | * @throws IOException |
| 316 | * in case of I/O error |
| 317 | */ |
| 318 | protected JSONObject getJson(String url, boolean stable) |
| 319 | throws IOException { |
| 320 | try { |
| 321 | return getJson(new URL(url), stable); |
| 322 | } catch (MalformedURLException e) { |
| 323 | throw new IOException("Malformed URL: " + url, e); |
| 324 | } |
| 325 | } |
| 326 | |
| 327 | /** |
| 328 | * Utility method to convert the given URL into a JSON object. |
| 329 | * <p> |
| 330 | * Note that this method expects small JSON files (everything is copied into |
| 331 | * memory at least twice). |
| 332 | * |
| 333 | * @param url |
| 334 | * the URL to parse |
| 335 | * @param stable |
| 336 | * TRUE for more stable resources, FALSE when they often change |
| 337 | * |
| 338 | * @return the JSON object |
| 339 | * |
| 340 | * @throws IOException |
| 341 | * in case of I/O error |
| 342 | */ |
| 343 | protected JSONObject getJson(URL url, boolean stable) throws IOException { |
| 344 | InputStream in = Instance.getInstance().getCache().open(url, null, |
| 345 | stable); |
| 346 | try { |
| 347 | Scanner scan = new Scanner(in); |
| 348 | scan.useDelimiter("\0"); |
| 349 | try { |
| 350 | return new JSONObject(scan.next()); |
| 351 | } catch (JSONException e) { |
| 352 | throw new IOException(e); |
| 353 | } finally { |
| 354 | scan.close(); |
| 355 | } |
| 356 | } finally { |
| 357 | in.close(); |
| 358 | } |
| 359 | } |
| 360 | |
| 361 | /** |
| 362 | * Process the given story resource into a fully filled {@link Story} |
| 363 | * object. |
| 364 | * |
| 365 | * @param pg |
| 366 | * the optional progress reporter |
| 367 | * |
| 368 | * @return the {@link Story}, never NULL |
| 369 | * |
| 370 | * @throws IOException |
| 371 | * in case of I/O error |
| 372 | */ |
| 373 | // TODO: ADD final when BasicSupport_Deprecated is gone |
| 374 | public Story process(Progress pg) throws IOException { |
| 375 | setCurrentReferer(source); |
| 376 | login(); |
| 377 | sourceNode = loadDocument(source); |
| 378 | |
| 379 | try { |
| 380 | Story story = doProcess(pg); |
| 381 | |
| 382 | // Check for "no chapters" stories |
| 383 | if (story.getChapters().isEmpty() |
| 384 | && story.getMeta().getResume() != null |
| 385 | && !story.getMeta().getResume().getParagraphs().isEmpty()) { |
| 386 | Chapter resume = story.getMeta().getResume(); |
| 387 | resume.setName(""); |
| 388 | resume.setNumber(1); |
| 389 | story.getChapters().add(resume); |
| 390 | story.getMeta().setWords(resume.getWords()); |
| 391 | |
| 392 | String descChapterName = Instance.getInstance().getTrans() |
| 393 | .getString(StringId.DESCRIPTION); |
| 394 | resume = new Chapter(0, descChapterName); |
| 395 | story.getMeta().setResume(resume); |
| 396 | } |
| 397 | |
| 398 | return story; |
| 399 | } finally { |
| 400 | close(); |
| 401 | } |
| 402 | } |
| 403 | |
| 404 | /** |
| 405 | * Actual processing step, without the calls to other methods. |
| 406 | * <p> |
| 407 | * Will convert the story resource into a fully filled {@link Story} object. |
| 408 | * |
| 409 | * @param pg |
| 410 | * the optional progress reporter |
| 411 | * |
| 412 | * @return the {@link Story}, never NULL |
| 413 | * |
| 414 | * @throws IOException |
| 415 | * in case of I/O error |
| 416 | */ |
| 417 | protected Story doProcess(Progress pg) throws IOException { |
| 418 | if (pg == null) { |
| 419 | pg = new Progress(); |
| 420 | } else { |
| 421 | pg.setMinMax(0, 100); |
| 422 | } |
| 423 | |
| 424 | pg.setName("Initialising"); |
| 425 | |
| 426 | pg.setProgress(1); |
| 427 | Progress pgMeta = new Progress(); |
| 428 | pg.addProgress(pgMeta, 10); |
| 429 | Story story = processMeta(true, pgMeta); |
| 430 | pgMeta.done(); // 10% |
| 431 | pg.put("meta", story.getMeta()); |
| 432 | |
| 433 | Progress pgGetChapters = new Progress(); |
| 434 | pg.addProgress(pgGetChapters, 10); |
| 435 | story.setChapters(new ArrayList<Chapter>()); |
| 436 | List<Entry<String, URL>> chapters = getChapters(pgGetChapters); |
| 437 | pgGetChapters.done(); // 20% |
| 438 | |
| 439 | if (chapters != null) { |
| 440 | Progress pgChaps = new Progress("Extracting chapters", 0, |
| 441 | chapters.size() * 300); |
| 442 | pg.addProgress(pgChaps, 80); |
| 443 | |
| 444 | long words = 0; |
| 445 | int i = 1; |
| 446 | for (Entry<String, URL> chap : chapters) { |
| 447 | pgChaps.setName("Extracting chapter " + i); |
| 448 | URL chapUrl = chap.getValue(); |
| 449 | String chapName = chap.getKey(); |
| 450 | if (chapUrl != null) { |
| 451 | setCurrentReferer(chapUrl); |
| 452 | } |
| 453 | |
| 454 | pgChaps.setProgress(i * 100); |
| 455 | Progress pgGetChapterContent = new Progress(); |
| 456 | Progress pgMakeChapter = new Progress(); |
| 457 | pgChaps.addProgress(pgGetChapterContent, 100); |
| 458 | pgChaps.addProgress(pgMakeChapter, 100); |
| 459 | |
| 460 | String content = getChapterContent(chapUrl, i, |
| 461 | pgGetChapterContent); |
| 462 | pgGetChapterContent.done(); |
| 463 | Chapter cc = bsPara.makeChapter(this, chapUrl, i, |
| 464 | chapName, content, isHtml(), pgMakeChapter); |
| 465 | pgMakeChapter.done(); |
| 466 | |
| 467 | words += cc.getWords(); |
| 468 | story.getChapters().add(cc); |
| 469 | |
| 470 | i++; |
| 471 | } |
| 472 | |
| 473 | story.getMeta().setWords(words); |
| 474 | |
| 475 | pgChaps.setName("Extracting chapters"); |
| 476 | pgChaps.done(); |
| 477 | } |
| 478 | |
| 479 | pg.done(); |
| 480 | |
| 481 | return story; |
| 482 | } |
| 483 | |
| 484 | /** |
| 485 | * Create a chapter from the given data. |
| 486 | * |
| 487 | * @param source |
| 488 | * the source URL for this content, which can be used to try and |
| 489 | * find images if images are present in the format [image-url] |
| 490 | * @param number |
| 491 | * the chapter number (0 = description) |
| 492 | * @param name |
| 493 | * the chapter name |
| 494 | * @param content |
| 495 | * the content of the chapter |
| 496 | * |
| 497 | * @return the {@link Chapter}, never NULL |
| 498 | * |
| 499 | * @throws IOException |
| 500 | * in case of I/O error |
| 501 | */ |
| 502 | public Chapter makeChapter(URL source, int number, String name, |
| 503 | String content) throws IOException { |
| 504 | return bsPara.makeChapter(this, source, number, name, |
| 505 | content, isHtml(), null); |
| 506 | } |
| 507 | |
| 508 | /** |
| 509 | * Return a {@link BasicSupport} implementation supporting the given |
| 510 | * resource if possible. |
| 511 | * |
| 512 | * @param url |
| 513 | * the story resource |
| 514 | * |
| 515 | * @return an implementation that supports it, or NULL |
| 516 | */ |
| 517 | public static BasicSupport getSupport(URL url) { |
| 518 | if (url == null) { |
| 519 | return null; |
| 520 | } |
| 521 | |
| 522 | // TEXT and INFO_TEXT always support files (not URLs though) |
| 523 | for (SupportType type : SupportType.values()) { |
| 524 | if (type != SupportType.TEXT && type != SupportType.INFO_TEXT) { |
| 525 | BasicSupport support = getSupport(type, url); |
| 526 | if (support != null && support.supports(url)) { |
| 527 | return support; |
| 528 | } |
| 529 | } |
| 530 | } |
| 531 | |
| 532 | for (SupportType type : new SupportType[] { SupportType.INFO_TEXT, |
| 533 | SupportType.TEXT }) { |
| 534 | BasicSupport support = getSupport(type, url); |
| 535 | if (support != null && support.supports(url)) { |
| 536 | return support; |
| 537 | } |
| 538 | } |
| 539 | |
| 540 | return null; |
| 541 | } |
| 542 | |
| 543 | /** |
| 544 | * Return a {@link BasicSupport} implementation supporting the given type. |
| 545 | * |
| 546 | * @param type |
| 547 | * the type, must not be NULL |
| 548 | * @param url |
| 549 | * the {@link URL} to support (can be NULL to get an |
| 550 | * "abstract support"; if not NULL, will be used as the source |
| 551 | * URL) |
| 552 | * |
| 553 | * @return an implementation that supports it, or NULL |
| 554 | */ |
| 555 | public static BasicSupport getSupport(SupportType type, URL url) { |
| 556 | BasicSupport support = null; |
| 557 | |
| 558 | switch (type) { |
| 559 | case EPUB: |
| 560 | support = new Epub(); |
| 561 | break; |
| 562 | case INFO_TEXT: |
| 563 | support = new InfoText(); |
| 564 | break; |
| 565 | case FIMFICTION: |
| 566 | try { |
| 567 | // Can fail if no client key or NO in options |
| 568 | support = new FimfictionApi(); |
| 569 | } catch (IOException e) { |
| 570 | support = new Fimfiction(); |
| 571 | } |
| 572 | break; |
| 573 | case FANFICTION: |
| 574 | support = new Fanfiction(); |
| 575 | break; |
| 576 | case TEXT: |
| 577 | support = new Text(); |
| 578 | break; |
| 579 | case MANGAHUB: |
| 580 | support = new MangaHub(); |
| 581 | break; |
| 582 | case E621: |
| 583 | support = new E621(); |
| 584 | break; |
| 585 | case YIFFSTAR: |
| 586 | support = new YiffStar(); |
| 587 | break; |
| 588 | case E_HENTAI: |
| 589 | support = new EHentai(); |
| 590 | break; |
| 591 | case MANGA_LEL: |
| 592 | support = new MangaLel(); |
| 593 | break; |
| 594 | case CBZ: |
| 595 | support = new Cbz(); |
| 596 | break; |
| 597 | case HTML: |
| 598 | support = new Html(); |
| 599 | break; |
| 600 | } |
| 601 | |
| 602 | if (support != null) { |
| 603 | support.setType(type); |
| 604 | support.source = support.getCanonicalUrl(url); |
| 605 | } |
| 606 | |
| 607 | return support; |
| 608 | } |
| 609 | } |