1 package be
.nikiroo
.fanfix
.supported
;
3 import java
.io
.IOException
;
4 import java
.io
.InputStream
;
5 import java
.net
.MalformedURLException
;
7 import java
.util
.ArrayList
;
9 import java
.util
.HashMap
;
10 import java
.util
.List
;
12 import java
.util
.Scanner
;
13 import java
.util
.Map
.Entry
;
15 import org
.json
.JSONObject
;
16 import org
.jsoup
.helper
.DataUtil
;
17 import org
.jsoup
.nodes
.Document
;
18 import org
.jsoup
.nodes
.Element
;
19 import org
.jsoup
.nodes
.Node
;
21 import be
.nikiroo
.fanfix
.Instance
;
22 import be
.nikiroo
.fanfix
.bundles
.StringId
;
23 import be
.nikiroo
.fanfix
.data
.Chapter
;
24 import be
.nikiroo
.fanfix
.data
.MetaData
;
25 import be
.nikiroo
.fanfix
.data
.Story
;
26 import be
.nikiroo
.utils
.Progress
;
27 import be
.nikiroo
.utils
.StringUtils
;
30 * This class is the base class used by the other support classes. It can be
31 * used outside of this package, and have static method that you can use to get
32 * access to the correct support class.
34 * It will be used with 'resources' (usually web pages or files).
38 public abstract class BasicSupport
{
39 private Document sourceNode
;
41 private SupportType type
;
42 private URL currentReferer
; // with only one 'r', as in 'HTTP'...
44 static protected BasicSupportHelper bsHelper
= new BasicSupportHelper();
45 static protected BasicSupportImages bsImages
= new BasicSupportImages();
46 static protected BasicSupportPara bsPara
= new BasicSupportPara(new BasicSupportHelper(), new BasicSupportImages());
49 * Check if the given resource is supported by this {@link BasicSupport}.
52 * the resource to check for
54 * @return TRUE if it is
56 protected abstract boolean supports(URL url
);
59 * Return TRUE if the support will return HTML encoded content values for
60 * the chapters content.
62 * @return TRUE for HTML
64 protected abstract boolean isHtml();
67 * Return the {@link MetaData} of this story.
69 * @return the associated {@link MetaData}, never NULL
72 * in case of I/O error
74 protected abstract MetaData
getMeta() throws IOException
;
77 * Return the story description.
79 * @return the description
82 * in case of I/O error
84 protected abstract String
getDesc() throws IOException
;
87 * Return the list of chapters (name and resource).
89 * Can be NULL if this {@link BasicSupport} do no use chapters.
92 * the optional progress reporter
94 * @return the chapters or NULL
97 * in case of I/O error
99 protected abstract List
<Entry
<String
, URL
>> getChapters(Progress pg
)
103 * Return the content of the chapter (possibly HTML encoded, if
104 * {@link BasicSupport#isHtml()} is TRUE).
107 * the chapter {@link URL}
111 * the optional progress reporter
113 * @return the content
115 * @throws IOException
116 * in case of I/O error
118 protected abstract String
getChapterContent(URL chapUrl
, int number
,
119 Progress pg
) throws IOException
;
122 * Return the list of cookies (values included) that must be used to
123 * correctly fetch the resources.
125 * You are expected to call the super method implementation if you override
128 * @return the cookies
130 public Map
<String
, String
> getCookies() {
131 return new HashMap
<String
, String
>();
135 * OAuth authorisation (aka, "bearer XXXXXXX").
137 * @return the OAuth string
139 public String
getOAuth() {
144 * Return the canonical form of the main {@link URL}.
147 * the source {@link URL}, which can be NULL
149 * @return the canonical form of this {@link URL} or NULL if the source was
152 protected URL
getCanonicalUrl(URL source
) {
157 * The main {@link Node} for this {@link Story}.
161 protected Element
getSourceNode() {
166 * The main {@link URL} for this {@link Story}.
170 protected URL
getSource() {
175 * The current referer {@link URL} (only one 'r', as in 'HTML'...), i.e.,
176 * the current {@link URL} we work on.
178 * @return the referer
180 public URL
getCurrentReferer() {
181 return currentReferer
;
185 * The current referer {@link URL} (only one 'r', as in 'HTML'...), i.e.,
186 * the current {@link URL} we work on.
188 * @param currentReferer
191 protected void setCurrentReferer(URL currentReferer
) {
192 this.currentReferer
= currentReferer
;
200 public SupportType
getType() {
210 protected void setType(SupportType type
) {
215 * Open an input link that will be used for the support.
217 * Can return NULL, in which case you are supposed to work without a source
221 * the source {@link URL}
223 * @return the {@link InputStream}
225 * @throws IOException
226 * in case of I/O error
228 protected Document
loadDocument(URL source
) throws IOException
{
229 String url
= getCanonicalUrl(source
).toString();
230 return DataUtil
.load(Instance
.getInstance().getCache().open(source
, this, false), "UTF-8", url
.toString());
234 * Log into the support (can be a no-op depending upon the support).
236 * @throws IOException
237 * in case of I/O error
239 protected void login() throws IOException
{
243 * Now that we have processed the {@link Story}, close the resources if any.
245 protected void close() {
246 setCurrentReferer(null);
250 * Process the given story resource into a partially filled {@link Story}
251 * object containing the name and metadata.
254 * retrieve the description of the story, or not
256 * the optional progress reporter
258 * @return the {@link Story}, never NULL
260 * @throws IOException
261 * in case of I/O error
263 protected Story
processMeta(boolean getDesc
, Progress pg
)
268 pg
.setMinMax(0, 100);
273 Story story
= new Story();
274 MetaData meta
= getMeta();
275 if (meta
.getCreationDate() == null
276 || meta
.getCreationDate().trim().isEmpty()) {
277 meta
.setCreationDate(bsHelper
278 .formatDate(StringUtils
.fromTime(new Date().getTime())));
281 pg
.put("meta", meta
);
285 if (meta
.getCover() == null) {
286 meta
.setCover(bsHelper
.getDefaultCover(meta
.getSubject()));
292 String descChapterName
= Instance
.getInstance().getTrans().getString(StringId
.DESCRIPTION
);
293 story
.getMeta().setResume(bsPara
.makeChapter(this, source
, 0, descChapterName
, //
294 getDesc(), isHtml(), null));
302 * Utility method to convert the given URL into a JSON object.
304 * Note that this method expects small JSON files (everything is copied into
305 * memory at least twice).
310 * TRUE for more stable resources, FALSE when they often change
312 * @return the JSON object
314 * @throws IOException
315 * in case of I/O error
317 protected JSONObject
getJson(String url
, boolean stable
)
320 return getJson(new URL(url
), stable
);
321 } catch (MalformedURLException e
) {
322 throw new IOException("Malformed URL: " + url
, e
);
327 * Utility method to convert the given URL into a JSON object.
329 * Note that this method expects small JSON files (everything is copied into
330 * memory at least twice).
335 * TRUE for more stable resources, FALSE when they often change
337 * @return the JSON object
339 * @throws IOException
340 * in case of I/O error
342 protected JSONObject
getJson(URL url
, boolean stable
) throws IOException
{
343 InputStream in
= Instance
.getInstance().getCache().open(url
, null,
346 Scanner scan
= new Scanner(in
);
347 scan
.useDelimiter("\0");
349 return new JSONObject(scan
.next());
359 * Process the given story resource into a fully filled {@link Story}
363 * the optional progress reporter
365 * @return the {@link Story}, never NULL
367 * @throws IOException
368 * in case of I/O error
370 // TODO: ADD final when BasicSupport_Deprecated is gone
371 public Story
process(Progress pg
) throws IOException
{
372 setCurrentReferer(source
);
374 sourceNode
= loadDocument(source
);
377 return doProcess(pg
);
384 * Actual processing step, without the calls to other methods.
386 * Will convert the story resource into a fully filled {@link Story} object.
389 * the optional progress reporter
391 * @return the {@link Story}, never NULL
393 * @throws IOException
394 * in case of I/O error
396 protected Story
doProcess(Progress pg
) throws IOException
{
400 pg
.setMinMax(0, 100);
403 pg
.setName("Initialising");
406 Progress pgMeta
= new Progress();
407 pg
.addProgress(pgMeta
, 10);
408 Story story
= processMeta(true, pgMeta
);
409 pgMeta
.done(); // 10%
410 pg
.put("meta", story
.getMeta());
412 Progress pgGetChapters
= new Progress();
413 pg
.addProgress(pgGetChapters
, 10);
414 story
.setChapters(new ArrayList
<Chapter
>());
415 List
<Entry
<String
, URL
>> chapters
= getChapters(pgGetChapters
);
416 pgGetChapters
.done(); // 20%
418 if (chapters
!= null) {
419 Progress pgChaps
= new Progress("Extracting chapters", 0,
420 chapters
.size() * 300);
421 pg
.addProgress(pgChaps
, 80);
425 for (Entry
<String
, URL
> chap
: chapters
) {
426 pgChaps
.setName("Extracting chapter " + i
);
427 URL chapUrl
= chap
.getValue();
428 String chapName
= chap
.getKey();
429 if (chapUrl
!= null) {
430 setCurrentReferer(chapUrl
);
433 pgChaps
.setProgress(i
* 100);
434 Progress pgGetChapterContent
= new Progress();
435 Progress pgMakeChapter
= new Progress();
436 pgChaps
.addProgress(pgGetChapterContent
, 100);
437 pgChaps
.addProgress(pgMakeChapter
, 100);
439 String content
= getChapterContent(chapUrl
, i
,
440 pgGetChapterContent
);
441 pgGetChapterContent
.done();
442 Chapter cc
= bsPara
.makeChapter(this, chapUrl
, i
,
443 chapName
, content
, isHtml(), pgMakeChapter
);
444 pgMakeChapter
.done();
446 words
+= cc
.getWords();
447 story
.getChapters().add(cc
);
448 story
.getMeta().setWords(words
);
453 pgChaps
.setName("Extracting chapters");
463 * Create a chapter from the given data.
466 * the source URL for this content, which can be used to try and
467 * find images if images are present in the format [image-url]
469 * the chapter number (0 = description)
473 * the content of the chapter
474 * @return the {@link Chapter}
476 * @throws IOException
477 * in case of I/O error
479 public Chapter
makeChapter(URL source
, int number
, String name
,
480 String content
) throws IOException
{
481 return bsPara
.makeChapter(this, source
, number
, name
,
482 content
, isHtml(), null);
486 * Return a {@link BasicSupport} implementation supporting the given
487 * resource if possible.
492 * @return an implementation that supports it, or NULL
494 public static BasicSupport
getSupport(URL url
) {
499 // TEXT and INFO_TEXT always support files (not URLs though)
500 for (SupportType type
: SupportType
.values()) {
501 if (type
!= SupportType
.TEXT
&& type
!= SupportType
.INFO_TEXT
) {
502 BasicSupport support
= getSupport(type
, url
);
503 if (support
!= null && support
.supports(url
)) {
509 for (SupportType type
: new SupportType
[] { SupportType
.INFO_TEXT
,
510 SupportType
.TEXT
}) {
511 BasicSupport support
= getSupport(type
, url
);
512 if (support
!= null && support
.supports(url
)) {
521 * Return a {@link BasicSupport} implementation supporting the given type.
524 * the type, must not be NULL
526 * the {@link URL} to support (can be NULL to get an
527 * "abstract support"; if not NULL, will be used as the source
530 * @return an implementation that supports it, or NULL
532 public static BasicSupport
getSupport(SupportType type
, URL url
) {
533 BasicSupport support
= null;
537 support
= new Epub();
540 support
= new InfoText();
544 // Can fail if no client key or NO in options
545 support
= new FimfictionApi();
546 } catch (IOException e
) {
547 support
= new Fimfiction();
551 support
= new Fanfiction();
554 support
= new Text();
557 support
= new MangaHub();
560 support
= new E621();
563 support
= new YiffStar();
566 support
= new EHentai();
569 support
= new MangaLel();
575 support
= new Html();
579 if (support
!= null) {
580 support
.setType(type
);
581 support
.source
= support
.getCanonicalUrl(url
);