| 1 | package be.nikiroo.fanfix.supported; |
| 2 | |
| 3 | import java.io.IOException; |
| 4 | import java.io.UnsupportedEncodingException; |
| 5 | import java.net.MalformedURLException; |
| 6 | import java.net.URL; |
| 7 | import java.net.URLDecoder; |
| 8 | import java.util.AbstractMap; |
| 9 | import java.util.ArrayList; |
| 10 | import java.util.Collections; |
| 11 | import java.util.Date; |
| 12 | import java.util.LinkedList; |
| 13 | import java.util.List; |
| 14 | import java.util.Map.Entry; |
| 15 | |
| 16 | import org.json.JSONArray; |
| 17 | import org.json.JSONException; |
| 18 | import org.json.JSONObject; |
| 19 | import org.jsoup.helper.DataUtil; |
| 20 | import org.jsoup.nodes.Document; |
| 21 | import org.jsoup.nodes.Element; |
| 22 | |
| 23 | import be.nikiroo.fanfix.Instance; |
| 24 | import be.nikiroo.fanfix.bundles.Config; |
| 25 | import be.nikiroo.fanfix.data.MetaData; |
| 26 | import be.nikiroo.utils.Image; |
| 27 | import be.nikiroo.utils.Progress; |
| 28 | import be.nikiroo.utils.StringUtils; |
| 29 | import be.nikiroo.utils.Version; |
| 30 | |
| 31 | /** |
| 32 | * Support class for <a href="http://e621.net/">e621.net</a> and |
| 33 | * <a href="http://e926.net/">e926.net</a>, a Furry website supporting comics, |
| 34 | * including some of MLP. |
| 35 | * <p> |
| 36 | * <a href="http://e926.net/">e926.net</a> only shows the "clean" images and |
| 37 | * comics, but it can be difficult to browse. |
| 38 | * |
| 39 | * @author niki |
| 40 | */ |
| 41 | class E621 extends BasicSupport { |
| 42 | @Override |
| 43 | protected boolean supports(URL url) { |
| 44 | String host = url.getHost(); |
| 45 | if (host.startsWith("www.")) { |
| 46 | host = host.substring("www.".length()); |
| 47 | } |
| 48 | |
| 49 | return ("e621.net".equals(host) || "e926.net".equals(host)) |
| 50 | && (isPool(url) || isSearchOrSet(url)); |
| 51 | } |
| 52 | |
| 53 | @Override |
| 54 | protected boolean isHtml() { |
| 55 | return true; |
| 56 | } |
| 57 | |
| 58 | @Override |
| 59 | protected MetaData getMeta() throws IOException { |
| 60 | MetaData meta = new MetaData(); |
| 61 | |
| 62 | meta.setTitle(getTitle()); |
| 63 | meta.setAuthor(getAuthor()); |
| 64 | meta.setDate(getDate()); |
| 65 | meta.setTags(getTags()); |
| 66 | meta.setSource(getType().getSourceName()); |
| 67 | meta.setUrl(getSource().toString()); |
| 68 | meta.setPublisher(getType().getSourceName()); |
| 69 | meta.setUuid(getSource().toString()); |
| 70 | meta.setLuid(""); |
| 71 | meta.setLang("en"); |
| 72 | meta.setSubject("Furry"); |
| 73 | meta.setType(getType().toString()); |
| 74 | meta.setImageDocument(true); |
| 75 | meta.setCover(getCover()); |
| 76 | meta.setFakeCover(true); |
| 77 | |
| 78 | return meta; |
| 79 | } |
| 80 | |
| 81 | @Override |
| 82 | protected String getDesc() throws IOException { |
| 83 | if (isSearchOrSet(getSource())) { |
| 84 | StringBuilder builder = new StringBuilder(); |
| 85 | builder.append("A collection of images from ") |
| 86 | .append(getSource().getHost()).append("\n") // |
| 87 | .append("\tTime of creation: " |
| 88 | + StringUtils.fromTime(new Date().getTime())) |
| 89 | .append("\n") // |
| 90 | .append("\tTags: ");// |
| 91 | for (String tag : getTags()) { |
| 92 | builder.append("\t\t").append(tag); |
| 93 | } |
| 94 | |
| 95 | return builder.toString(); |
| 96 | } |
| 97 | |
| 98 | if (isPool(getSource())) { |
| 99 | Element el = getSourceNode().getElementById("description"); |
| 100 | if (el != null) { |
| 101 | return el.text(); |
| 102 | } |
| 103 | } |
| 104 | |
| 105 | return null; |
| 106 | } |
| 107 | |
| 108 | @Override |
| 109 | protected List<Entry<String, URL>> getChapters(Progress pg) |
| 110 | throws IOException { |
| 111 | int i = 1; |
| 112 | String jsonUrl = getJsonUrl(); |
| 113 | if (jsonUrl != null) { |
| 114 | for (i = 1; true; i++) { |
| 115 | if (i > 1) { |
| 116 | try { |
| 117 | // The API does not accept more than 2 request per sec, |
| 118 | // and asks us to limit at one per sec when possible |
| 119 | Thread.sleep(1000); |
| 120 | } catch (InterruptedException e) { |
| 121 | } |
| 122 | } |
| 123 | |
| 124 | try { |
| 125 | JSONObject json = getJson(jsonUrl + "&page=" + i, false); |
| 126 | if (!json.has("posts")) |
| 127 | break; |
| 128 | JSONArray posts = json.getJSONArray("posts"); |
| 129 | if (posts.isEmpty()) |
| 130 | break; |
| 131 | } catch (Exception e) { |
| 132 | e.printStackTrace(); |
| 133 | } |
| 134 | } |
| 135 | |
| 136 | // The last page was empty: |
| 137 | i--; |
| 138 | } |
| 139 | |
| 140 | // The pages and images are in reverse order on /posts/ |
| 141 | List<Entry<String, URL>> chapters = new LinkedList<Entry<String, URL>>(); |
| 142 | for (int page = i; page > 0; page--) { |
| 143 | chapters.add(new AbstractMap.SimpleEntry<String, URL>( |
| 144 | "Page " + Integer.toString(i - page + 1), |
| 145 | new URL(jsonUrl + "&page=" + page))); |
| 146 | } |
| 147 | |
| 148 | return chapters; |
| 149 | } |
| 150 | |
| 151 | @Override |
| 152 | protected String getChapterContent(URL chapUrl, int number, Progress pg) |
| 153 | throws IOException { |
| 154 | StringBuilder builder = new StringBuilder(); |
| 155 | |
| 156 | JSONObject json = getJson(chapUrl, false); |
| 157 | JSONArray postsArr = json.getJSONArray("posts"); |
| 158 | |
| 159 | // The pages and images are in reverse order on /posts/ |
| 160 | List<JSONObject> posts = new ArrayList<JSONObject>(postsArr.length()); |
| 161 | for (int i = postsArr.length() - 1; i >= 0; i--) { |
| 162 | Object o = postsArr.get(i); |
| 163 | if (o instanceof JSONObject) |
| 164 | posts.add((JSONObject) o); |
| 165 | } |
| 166 | |
| 167 | for (JSONObject post : posts) { |
| 168 | if (!post.has("file")) |
| 169 | continue; |
| 170 | JSONObject file = post.getJSONObject("file"); |
| 171 | if (!file.has("url")) |
| 172 | continue; |
| 173 | |
| 174 | try { |
| 175 | String url = file.getString("url"); |
| 176 | builder.append("["); |
| 177 | builder.append(url); |
| 178 | builder.append("]<br/>"); |
| 179 | } catch (JSONException e) { |
| 180 | // Can be NULL if filtered |
| 181 | // When the value is NULL, we get an exception |
| 182 | // but the "has" method still returns true |
| 183 | } |
| 184 | } |
| 185 | |
| 186 | return builder.toString(); |
| 187 | } |
| 188 | |
| 189 | @Override |
| 190 | protected URL getCanonicalUrl(URL source) { |
| 191 | // Convert search-pools into proper pools |
| 192 | if (source.getPath().equals("/posts") && source.getQuery() != null |
| 193 | && source.getQuery().startsWith("tags=pool%3A")) { |
| 194 | String poolNumber = source.getQuery() |
| 195 | .substring("tags=pool%3A".length()); |
| 196 | try { |
| 197 | Integer.parseInt(poolNumber); |
| 198 | String base = source.getProtocol() + "://" + source.getHost(); |
| 199 | if (source.getPort() != -1) { |
| 200 | base = base + ":" + source.getPort(); |
| 201 | } |
| 202 | source = new URL(base + "/pools/" + poolNumber); |
| 203 | } catch (NumberFormatException e) { |
| 204 | // Not a simple pool, skip |
| 205 | } catch (MalformedURLException e) { |
| 206 | // Cannot happen |
| 207 | } |
| 208 | } |
| 209 | |
| 210 | if (isSetOriginalUrl(source)) { |
| 211 | try { |
| 212 | Document doc = DataUtil.load(Instance.getInstance().getCache() |
| 213 | .open(source, this, false), "UTF-8", source.toString()); |
| 214 | for (Element shortname : doc |
| 215 | .getElementsByClass("set-shortname")) { |
| 216 | for (Element el : shortname.getElementsByTag("a")) { |
| 217 | if (!el.attr("href").isEmpty()) |
| 218 | return new URL(el.absUrl("href")); |
| 219 | } |
| 220 | } |
| 221 | } catch (IOException e) { |
| 222 | Instance.getInstance().getTraceHandler().error(e); |
| 223 | } |
| 224 | } |
| 225 | |
| 226 | if (isPool(source)) { |
| 227 | try { |
| 228 | return new URL( |
| 229 | source.toString().replace("/pool/show/", "/pools/")); |
| 230 | } catch (MalformedURLException e) { |
| 231 | } |
| 232 | } |
| 233 | |
| 234 | return super.getCanonicalUrl(source); |
| 235 | } |
| 236 | |
| 237 | private String getTitle() { |
| 238 | String title = ""; |
| 239 | |
| 240 | Element el = getSourceNode().getElementsByTag("title").first(); |
| 241 | if (el != null) { |
| 242 | title = el.text().trim(); |
| 243 | } |
| 244 | |
| 245 | for (String s : new String[] { "e621", "-", "e621", "Pool", "-" }) { |
| 246 | if (title.startsWith(s)) { |
| 247 | title = title.substring(s.length()).trim(); |
| 248 | } |
| 249 | if (title.endsWith(s)) { |
| 250 | title = title.substring(0, title.length() - s.length()).trim(); |
| 251 | } |
| 252 | } |
| 253 | |
| 254 | if (isSearchOrSet(getSource())) { |
| 255 | title = title.isEmpty() ? "e621" : "[e621] " + title; |
| 256 | } |
| 257 | |
| 258 | return title; |
| 259 | } |
| 260 | |
| 261 | private String getAuthor() { |
| 262 | List<String> list = new ArrayList<String>(); |
| 263 | String jsonUrl = getJsonUrl(); |
| 264 | if (jsonUrl != null) { |
| 265 | try { |
| 266 | JSONObject json = getJson(jsonUrl, false); |
| 267 | JSONArray posts = json.getJSONArray("posts"); |
| 268 | for (Object obj : posts) { |
| 269 | if (!(obj instanceof JSONObject)) |
| 270 | continue; |
| 271 | |
| 272 | JSONObject post = (JSONObject) obj; |
| 273 | if (!post.has("tags")) |
| 274 | continue; |
| 275 | |
| 276 | JSONObject tags = post.getJSONObject("tags"); |
| 277 | if (!tags.has("artist")) |
| 278 | continue; |
| 279 | |
| 280 | JSONArray artists = tags.getJSONArray("artist"); |
| 281 | for (Object artist : artists) { |
| 282 | if (list.contains(artist.toString())) |
| 283 | continue; |
| 284 | |
| 285 | list.add(artist.toString()); |
| 286 | } |
| 287 | } |
| 288 | } catch (Exception e) { |
| 289 | e.printStackTrace(); |
| 290 | } |
| 291 | } |
| 292 | |
| 293 | StringBuilder builder = new StringBuilder(); |
| 294 | for (String artist : list) { |
| 295 | if (builder.length() > 0) { |
| 296 | builder.append(", "); |
| 297 | } |
| 298 | builder.append(artist); |
| 299 | } |
| 300 | |
| 301 | return builder.toString(); |
| 302 | } |
| 303 | |
| 304 | private String getDate() { |
| 305 | String jsonUrl = getJsonUrl(); |
| 306 | if (jsonUrl != null) { |
| 307 | try { |
| 308 | JSONObject json = getJson(jsonUrl, false); |
| 309 | JSONArray posts = json.getJSONArray("posts"); |
| 310 | for (Object obj : posts) { |
| 311 | if (!(obj instanceof JSONObject)) |
| 312 | continue; |
| 313 | |
| 314 | JSONObject post = (JSONObject) obj; |
| 315 | if (!post.has("created_at")) |
| 316 | continue; |
| 317 | |
| 318 | return post.getString("created_at"); |
| 319 | } |
| 320 | } catch (Exception e) { |
| 321 | e.printStackTrace(); |
| 322 | } |
| 323 | } |
| 324 | |
| 325 | return ""; |
| 326 | } |
| 327 | |
| 328 | // no tags for pools |
| 329 | private List<String> getTags() { |
| 330 | List<String> tags = new ArrayList<String>(); |
| 331 | if (isSearchOrSet(getSource())) { |
| 332 | String str = getTagsFromUrl(getSource()); |
| 333 | for (String tag : str.split("\\+")) { |
| 334 | try { |
| 335 | tags.add(URLDecoder.decode(tag.trim(), "UTF-8").trim()); |
| 336 | } catch (UnsupportedEncodingException e) { |
| 337 | } |
| 338 | } |
| 339 | } |
| 340 | |
| 341 | return tags; |
| 342 | } |
| 343 | |
| 344 | // returns "xxx+ddd+ggg" if "tags=xxx+ddd+ggg" was present in the query |
| 345 | private String getTagsFromUrl(URL url) { |
| 346 | String tags = url == null ? "" : url.getQuery(); |
| 347 | int pos = tags.indexOf("tags="); |
| 348 | |
| 349 | if (pos >= 0) { |
| 350 | tags = tags.substring(pos).substring("tags=".length()); |
| 351 | } else { |
| 352 | return ""; |
| 353 | } |
| 354 | |
| 355 | pos = tags.indexOf('&'); |
| 356 | if (pos > 0) { |
| 357 | tags = tags.substring(0, pos); |
| 358 | } |
| 359 | pos = tags.indexOf('/'); |
| 360 | if (pos > 0) { |
| 361 | tags = tags.substring(0, pos); |
| 362 | } |
| 363 | |
| 364 | return tags; |
| 365 | } |
| 366 | |
| 367 | private Image getCover() throws IOException { |
| 368 | Image image = null; |
| 369 | List<Entry<String, URL>> chapters = getChapters(null); |
| 370 | if (!chapters.isEmpty()) { |
| 371 | URL chap1Url = chapters.get(0).getValue(); |
| 372 | String imgsChap1 = getChapterContent(chap1Url, 1, null); |
| 373 | if (!imgsChap1.isEmpty()) { |
| 374 | imgsChap1 = imgsChap1.split("]")[0].substring(1).trim(); |
| 375 | image = bsImages.getImage(this, new URL(imgsChap1)); |
| 376 | } |
| 377 | } |
| 378 | |
| 379 | return image; |
| 380 | } |
| 381 | |
| 382 | // always /posts.json/ url |
| 383 | private String getJsonUrl() { |
| 384 | String url = null; |
| 385 | if (isSearchOrSet(getSource())) { |
| 386 | url = getSource().toString().replace("/posts", "/posts.json"); |
| 387 | } |
| 388 | |
| 389 | if (isPool(getSource())) { |
| 390 | String poolNumber = getSource().getPath() |
| 391 | .substring("/pools/".length()); |
| 392 | url = "https://e621.net/posts.json" + "?tags=pool%3A" + poolNumber; |
| 393 | } |
| 394 | |
| 395 | if (url != null) { |
| 396 | // Note: one way to override the blacklist |
| 397 | String login = Instance.getInstance().getConfig() |
| 398 | .getString(Config.LOGIN_E621_LOGIN); |
| 399 | String apk = Instance.getInstance().getConfig() |
| 400 | .getString(Config.LOGIN_E621_APIKEY); |
| 401 | |
| 402 | if (login != null && !login.isEmpty() && apk != null |
| 403 | && !apk.isEmpty()) { |
| 404 | url = String.format("%s&login=%s&api_key=%s&_client=%s", url, |
| 405 | login, apk, "fanfix-" + Version.getCurrentVersion()); |
| 406 | } |
| 407 | } |
| 408 | |
| 409 | return url; |
| 410 | } |
| 411 | |
| 412 | // note: will be removed at getCanonicalUrl() |
| 413 | private boolean isSetOriginalUrl(URL originalUrl) { |
| 414 | return originalUrl.getPath().startsWith("/post_sets/"); |
| 415 | } |
| 416 | |
| 417 | private boolean isPool(URL url) { |
| 418 | return url.getPath().startsWith("/pools/") |
| 419 | || url.getPath().startsWith("/pool/show/"); |
| 420 | } |
| 421 | |
| 422 | // set will be renamed into search by canonical url |
| 423 | private boolean isSearchOrSet(URL url) { |
| 424 | return |
| 425 | // search: |
| 426 | (url.getPath().equals("/posts") && url.getQuery().contains("tags=")) |
| 427 | // or set: |
| 428 | || isSetOriginalUrl(url); |
| 429 | } |
| 430 | } |