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