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
.AbstractMap
;
8 import java
.util
.ArrayList
;
11 import java
.util
.Map
.Entry
;
12 import java
.util
.Scanner
;
14 import be
.nikiroo
.fanfix
.Instance
;
15 import be
.nikiroo
.fanfix
.data
.Chapter
;
16 import be
.nikiroo
.fanfix
.data
.MetaData
;
17 import be
.nikiroo
.fanfix
.data
.Story
;
18 import be
.nikiroo
.utils
.Image
;
19 import be
.nikiroo
.utils
.Progress
;
20 import be
.nikiroo
.utils
.StringUtils
;
23 * Support class for <a href="https://e-hentai.org/">e-hentai.org</a>, a website
24 * supporting mostly but not always NSFW comics, including some of MLP.
28 class EHentai
extends BasicSupport_Deprecated
{
30 protected MetaData
getMeta(URL source
, InputStream in
) throws IOException
{
31 MetaData meta
= new MetaData();
33 meta
.setTitle(getTitle(reset(in
)));
34 meta
.setAuthor(getAuthor(reset(in
)));
35 meta
.setDate(getDate(reset(in
)));
36 meta
.setTags(getTags(reset(in
)));
37 meta
.setUrl(source
.toString());
38 meta
.setUuid(source
.toString());
40 meta
.setLang(getLang(reset(in
)));
41 meta
.setSubject("Hentai");
42 meta
.setImageDocument(true);
43 meta
.setCover(getCover(source
, reset(in
)));
44 meta
.setFakeCover(true);
50 public Story
process(URL url
, Progress pg
) throws IOException
{
51 // There is no chapters on e621, just pagination...
52 Story story
= super.process(url
, pg
);
54 Chapter only
= new Chapter(1, "");
55 for (Chapter chap
: story
) {
56 only
.getParagraphs().addAll(chap
.getParagraphs());
59 story
.getChapters().clear();
60 story
.getChapters().add(only
);
66 protected boolean supports(URL url
) {
67 return "e-hentai.org".equals(url
.getHost());
71 protected boolean isHtml() {
76 public Map
<String
, String
> getCookies() {
77 Map
<String
, String
> cookies
= super.getCookies();
78 cookies
.put("nw", "1");
82 private Image
getCover(URL source
, InputStream in
) {
84 String coverLine
= getKeyLine(in
, "<div id=\"gd1\"", " url(", ")");
85 if (coverLine
!= null) {
86 coverLine
= StringUtils
.unhtml(coverLine
).trim();
87 author
= getImage(this, source
, coverLine
);
93 private String
getAuthor(InputStream in
) {
96 List
<String
> tagsAuthor
= getTagsAuthor(in
);
97 if (!tagsAuthor
.isEmpty()) {
98 author
= tagsAuthor
.get(0);
104 private String
getLang(InputStream in
) {
107 String langLine
= getKeyLine(in
, "class=\"gdt1\">Language",
108 "class=\"gdt2\"", "</td>");
109 if (langLine
!= null) {
110 langLine
= StringUtils
.unhtml(langLine
).trim();
111 if (langLine
.equalsIgnoreCase("English")) {
113 } else if (langLine
.equalsIgnoreCase("Japanese")) {
115 } else if (langLine
.equalsIgnoreCase("French")) {
118 // TODO find the code for other languages?
126 private String
getDate(InputStream in
) {
129 String dateLine
= getKeyLine(in
, "class=\"gdt1\">Posted",
130 "class=\"gdt2\"", "</td>");
131 if (dateLine
!= null) {
132 dateLine
= StringUtils
.unhtml(dateLine
).trim();
133 if (dateLine
.length() > 10) {
134 dateLine
= dateLine
.substring(0, 10).trim();
143 private List
<String
> getTags(InputStream in
) {
144 List
<String
> tags
= new ArrayList
<String
>();
145 List
<String
> tagsAuthor
= getTagsAuthor(in
);
147 for (int i
= 1; i
< tagsAuthor
.size(); i
++) {
148 tags
.add(tagsAuthor
.get(i
));
154 private List
<String
> getTagsAuthor(InputStream in
) {
155 List
<String
> tags
= new ArrayList
<String
>();
156 String tagLine
= getKeyLine(in
, "<meta name=\"description\"", "Tags: ",
158 if (tagLine
!= null) {
159 for (String tag
: tagLine
.split(",")) {
160 String candi
= tag
.trim();
161 if (!candi
.isEmpty() && !tags
.contains(candi
)) {
170 private String
getTitle(InputStream in
) {
171 String siteName
= " - E-Hentai Galleries";
173 String title
= getLine(in
, "<title>", 0);
175 title
= StringUtils
.unhtml(title
).trim();
176 if (title
.endsWith(siteName
)) {
177 title
= title
.substring(0, title
.length() - siteName
.length())
186 protected String
getDesc(URL source
, InputStream in
) throws IOException
{
189 String descLine
= getKeyLine(in
, "Uploader Comment", null,
190 "<div class=\"c7\"");
191 if (descLine
!= null) {
192 desc
= StringUtils
.unhtml(descLine
);
199 protected List
<Entry
<String
, URL
>> getChapters(URL source
, InputStream in
,
200 Progress pg
) throws IOException
{
201 List
<Entry
<String
, URL
>> urls
= new ArrayList
<Entry
<String
, URL
>>();
202 int last
= 0; // no pool/show when only one page, first page == page 0
204 @SuppressWarnings("resource")
205 Scanner scan
= new Scanner(in
, "UTF-8");
206 scan
.useDelimiter(">");
207 while (scan
.hasNext()) {
208 String line
= scan
.next();
209 if (line
.contains(source
.toString())) {
210 String page
= line
.substring(line
.indexOf(source
.toString()));
212 if (page
.contains(pkey
)) {
213 page
= page
.substring(page
.indexOf(pkey
) + pkey
.length());
215 while (!page
.isEmpty() && page
.charAt(0) >= '0'
216 && page
.charAt(0) <= '9') {
217 number
+= page
.charAt(0);
218 page
= page
.substring(1);
220 if (number
.isEmpty()) {
224 int current
= Integer
.parseInt(number
);
225 if (last
< current
) {
232 for (int i
= 0; i
<= last
; i
++) {
233 urls
.add(new AbstractMap
.SimpleEntry
<String
, URL
>(Integer
234 .toString(i
+ 1), new URL(source
.toString() + "?p=" + i
)));
241 protected String
getChapterContent(URL source
, InputStream in
, int number
,
242 Progress pg
) throws IOException
{
243 String staticSite
= "https://e-hentai.org/s/";
244 List
<URL
> pages
= new ArrayList
<URL
>();
246 @SuppressWarnings("resource")
247 Scanner scan
= new Scanner(in
, "UTF-8");
248 scan
.useDelimiter("\"");
249 while (scan
.hasNext()) {
250 String line
= scan
.next();
251 if (line
.startsWith(staticSite
)) {
253 pages
.add(new URL(line
));
254 } catch (MalformedURLException e
) {
255 Instance
.getInstance().getTraceHandler()
256 .error(new IOException("Parsing error, a link is not correctly parsed: " + line
, e
));
264 pg
.setMinMax(0, pages
.size());
267 StringBuilder builder
= new StringBuilder();
269 for (URL page
: pages
) {
270 InputStream pageIn
= Instance
.getInstance().getCache().open(page
, this, false);
272 String link
= getKeyLine(pageIn
, "id=\"img\"", "src=\"", "\"");
273 if (link
!= null && !link
.isEmpty()) {
275 builder
.append(link
);
276 builder
.append("]<br/>");
280 if (pageIn
!= null) {
287 return builder
.toString();