1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | package Torello.HTML; import java.io.*; import java.util.Vector; import java.net.URL; import Torello.HTML.HTMLPage.Parser; import java.util.concurrent.*; import java.util.concurrent.locks.*; import Torello.JavaDoc.JDHeaderBackgroundImg; import Torello.JavaDoc.StaticFunctional; import Torello.JavaDoc.Excuse; /** * A carbon-copy of class {@link HTMLPage}, augmented with a mechanism for setting <B>a timeout</B> * so that when scraping web-pages and {@code URL's} from servers that might have a tendency to hang, * freeze, or delay - the Java Virtual Machine can skip and move-on when that timeout expires. * * <BR /><BR /> * <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_MWT> * <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE> * * @see Scrape#getHTML(BufferedReader, int, int) * @see Scrape#getHTML(BufferedReader, String, String) * @see HTMLPage */ @StaticFunctional(Excused="parser", Excuses=Excuse.SINGLETON) @JDHeaderBackgroundImg public class HTMLPageMWT { private HTMLPageMWT() { } /** * If needing to "swap a proprietary parser" comes up, this is possible. * It just needs to accept the same parameters as the current parser, and produce a * {@code Vector<HTMLNode>.} This is not an advised step to take, but if an alternative * parser has been tested and happens to be generating different results, it can be easily * 'swapped out' for the one used now. * @see HTMLPage.Parser * @see HTMLPage.Parser#parse(CharSequence, boolean, String, String, String) */ public static Parser parser = Torello.HTML.HelperPackages.parse.ParserRE::parsePageTokens; // ******************************************************************************************** // ******************************************************************************************** // These 6 functions presume that the HTML source is from a URL // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Accepts: {@code URL} and Time-Out Parameters {@code 'timeout' & 'unit'} * <BR />Passes null to parameters * {@code startTag, endTag, rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(long, TimeUnit, URL, boolean, String, String, * String, String, String)} */ public static Vector<HTMLNode> getPageTokens (long timeout, TimeUnit unit, URL url, boolean eliminateHTMLTags) throws IOException, InterruptedException { return getPageTokens(timeout, unit, url, eliminateHTMLTags, null, null, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code URL} and Time-Out Parameters {@code 'timeout' & 'unit'} * <BR />And-Accepts: {@code 'startTag'} and {@code 'endTag'} * <BR />Passes null to parameters {@code rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(long, TimeUnit, URL, boolean, String, String, * String, String, String)} */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, URL url, boolean eliminateHTMLTags, String startTag, String endTag ) throws IOException, InterruptedException { return getPageTokens (timeout, unit, url, eliminateHTMLTags, startTag, endTag, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code URL} and Time-Out Parameters {@code 'timeout' & 'unit'} * <BR />And-Accepts: {@code 'startLineNum'} and {@code 'endLineNum'} * <BR />Passes null to parameters {@code rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(long, TimeUnit, URL, boolean, int, int, * String, String, String)} */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, URL url, boolean eliminateHTMLTags, int startLineNum, int endLineNum ) throws IOException, InterruptedException { return getPageTokens (timeout, unit, url, eliminateHTMLTags, startLineNum, endLineNum, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code URL} and Time-Out Parameters {@code 'timeout' & 'unit'} * <BR />Passes null to {@code startTag} & {@code endTag} parameters. * <BR />Invokes: {@link #getPageTokens(long, TimeUnit, URL, boolean, String, String, * String, String, String)} */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, URL url, boolean eliminateHTMLTags, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException, InterruptedException { return getPageTokens( timeout, unit, url, eliminateHTMLTags, null, null, rawHTMLFile, matchesFile, justTextFile ); } // ******************************************************************************************** // ******************************************************************************************** // The next 6 functions presume that the input is from a BufferedReader // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Accepts: {@code BufferedReader} * <BR />Passes null to parameters * {@code startTag, endTag, rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(long, TimeUnit, BufferedReader, boolean, * String, String, String, String, String)} */ public static Vector<HTMLNode> getPageTokens (long timeout, TimeUnit unit, BufferedReader br, boolean eliminateHTMLTags) throws IOException, InterruptedException { return getPageTokens (timeout, unit, br, eliminateHTMLTags, null, null, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code BufferedReader} * <BR />And-Accepts: {@code 'startTag'} and {@code 'endTag'} * <BR />Passes null to parameters {@code rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(long, TimeUnit, BufferedReader, boolean, * String, String, String, String, String)} */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, BufferedReader br, boolean eliminateHTMLTags, String startTag, String endTag ) throws IOException, InterruptedException { return getPageTokens (timeout, unit, br, eliminateHTMLTags, startTag, endTag, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code BufferedReader} * <BR />And-Accepts: {@code 'startLineNum'} and {@code 'endLineNum'} * <BR />Passes null to parameters {@code rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(long, TimeUnit, BufferedReader, boolean, * int, int, String, String, String)} */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, BufferedReader br, boolean eliminateHTMLTags, int startLineNum, int endLineNum ) throws IOException, InterruptedException { return getPageTokens (timeout, unit, br, eliminateHTMLTags, startLineNum, endLineNum, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code BufferedReader} * <BR />Passes null to {@code startTag} & {@code endTag} parameters. * <BR />Invokes: {@link #getPageTokens(long, TimeUnit, BufferedReader, boolean, * String, String, String, String, String)} */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, BufferedReader br, boolean eliminateHTMLTags, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException, InterruptedException { return getPageTokens (timeout, unit, br, eliminateHTMLTags, null, null, rawHTMLFile, matchesFile, justTextFile); } // ******************************************************************************************** // ******************************************************************************************** // * Receives a "pre-instantiated" BufferedReader for the HTML Source parameter // ******************************************************************************************** // ******************************************************************************************** private static final ExecutorService executor = Executors.newCachedThreadPool(); private static final Lock lock = new ReentrantLock(); /** * If this class has been used to make "multi-threaded" calls that use a Time-Out wait-period, * you might see your Java-Program hang for a few seconds when you would expect it to exit back * to your O.S. normally. * * <BR /><BR /><B>Max Wait Time</B> operates by building a "Timeout & Monitor" thread, and * therefore when a program you have written yourself reaches the end of its code, <I><B>if you * have performed any Internet-Downloads using {@code class HTMLPageMWT}</B></I>, then your * program <I>might not exit immediately,</I> but rather sit at the command-prompt for anywhere * between 10 and 30 seconds before this Timeout-Thread, created in class HTMLPageMWT, dies. * * <BR /><BR /><B CLASS=JDDescLabel>Multi-Threaded:</B> * * <BR />You may also immediately terminate any additional threads that were started by using * this method. */ public static void shutdownMWTThreads() { executor.shutdownNow(); } /** * Parses and Vectorizes HTML from a {@code BufferedReader} source. * Spawns a <I>monitor-thread</I> that stops the download if a * certain, user-specified, time-limit is exceeded. * @param timeout <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_TIMEOUT> * @param unit <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_UNIT> * @param br <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_BR> * @param eliminateHTMLTags <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_ELIM_HT> * @param startTag <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_START_TAG> * @param endTag <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_END_TAG> * @param rawHTMLFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RAW_HTML> * @param matchesFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_MATCHES_F> * @param justTextFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_JUST_TEXT> * @return <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RETURN> * @throws ScrapeException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_SCEX2> * @throws IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> * @throws InterruptedException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IEX> * @throws RejectedExecutionException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_REEX> */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, BufferedReader br, boolean eliminateHTMLTags, String startTag, String endTag, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException, InterruptedException { Callable<Vector<HTMLNode>> threadDownloader = new Callable<Vector<HTMLNode>>() { public Vector<HTMLNode> call() throws Exception { return parser.parse( Scrape.getHTML(br, startTag, endTag), eliminateHTMLTags, rawHTMLFile, matchesFile, justTextFile ); } }; lock.lock(); Future<Vector<HTMLNode>> future = executor.submit(threadDownloader); lock.unlock(); try { return future.get(timeout, unit); } catch (TimeoutException e) { return null; } catch (ExecutionException e) { Throwable originalException = e.getCause(); if (originalException == null) throw new RejectedExecutionException( "An Execution Exception was thrown, but it did provide a cause throwable " + "(e.getCause() returned null). See this exception's getCause() method to " + "view the ExecutionException that has occurred.", e ); if (originalException instanceof IOException) throw (IOException) originalException; if (originalException instanceof RuntimeException) throw (RuntimeException) originalException; throw new RejectedExecutionException( "An Execution Exception occurred, but it was neither a RuntimeException, " + "nor IOException. See this exception's getCause() method to view the " + "underlying error that has occurred.", originalException ); } } /** * Parses and Vectorizes HTML from a {@code BufferedReader} source. * Spawns a <I>monitor-thread</I> that stops the download if a * certain, user-specified, time-limit is exceeded. * @param timeout <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_TIMEOUT> * @param unit <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_UNIT> * @param br <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_BR> * @param eliminateHTMLTags <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_ELIM_HT> * @param startLineNum <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_START_LN> * @param endLineNum <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_END_LN> * @param rawHTMLFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RAW_HTML> * @param matchesFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_MATCHES_F> * @param justTextFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_JUST_TEXT> * @return <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RETURN> * @throws IllegalArgumentException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IAEX> * @throws ScrapeException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_SCEX1> * @throws IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> * @throws InterruptedException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IEX> * @throws RejectedExecutionException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_REEX> */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, BufferedReader br, boolean eliminateHTMLTags, int startLineNum, int endLineNum, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException, InterruptedException { Callable<Vector<HTMLNode>> threadDownloader = new Callable<Vector<HTMLNode>>() { public Vector<HTMLNode> call() throws Exception { return parser.parse( Scrape.getHTML(br, startLineNum, endLineNum), eliminateHTMLTags, rawHTMLFile, matchesFile, justTextFile ); } }; lock.lock(); Future<Vector<HTMLNode>> future = executor.submit(threadDownloader); lock.unlock(); try { return future.get(timeout, unit); } catch (TimeoutException e) { return null; } catch (ExecutionException e) { Throwable originalException = e.getCause(); if (originalException == null) throw new RejectedExecutionException( "An Execution Exception was thrown, but it did provide a cause throwable " + "(e.getCause() returned null). See this exception's getCause() method to " + "view the ExecutionException has that occurred.", e ); if (originalException instanceof IOException) throw (IOException) originalException; if (originalException instanceof RuntimeException) throw (RuntimeException) originalException; throw new RejectedExecutionException( "An Execution Exception occurred, but it was neither a RuntimeException, nor " + "IOException. See this exception's getCause() method to view the underlying " + "error that has occurred.", originalException ); } } // ******************************************************************************************** // ******************************************************************************************** // Receives a java.net.URL for the HTML Source parameter -- that could Timeout/Hang // ******************************************************************************************** // ******************************************************************************************** // It must be opened within the Multi-Threaded "Timeout" code (and therefore requires a second // version of these two methods - where Scrape.openConn(url) is *inside* the monitored // downloading thread. /** * Parses and Vectorizes HTML from a URL source. * Spawns a <I>monitor-thread</I> that stops the download if a certain, user-specified, * time-limit is exceeded. * @param timeout <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_TIMEOUT> * @param unit <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_UNIT> * @param url <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_URL> * @param eliminateHTMLTags <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_ELIM_HT> * @param startTag <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_START_TAG> * @param endTag <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_END_TAG> * @param rawHTMLFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RAW_HTML> * @param matchesFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_MATCHES_F> * @param justTextFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_JUST_TEXT> * @return <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RETURN> * @throws ScrapeException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_SCEX2> * @throws IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> * @throws InterruptedException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IEX> * @throws RejectedExecutionException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_REEX> */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, URL url, boolean eliminateHTMLTags, String startTag, String endTag, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException, InterruptedException { Callable<Vector<HTMLNode>> threadDownloader = new Callable<Vector<HTMLNode>>() { public Vector<HTMLNode> call() throws Exception { return parser.parse( Scrape.getHTML(Scrape.openConn(url), startTag, endTag), eliminateHTMLTags, rawHTMLFile, matchesFile, justTextFile ); } }; lock.lock(); Future<Vector<HTMLNode>> future = executor.submit(threadDownloader); lock.unlock(); try { return future.get(timeout, unit); } catch (TimeoutException e) { return null; } catch (ExecutionException e) { Throwable originalException = e.getCause(); if (originalException == null) throw new RejectedExecutionException( "An Execution Exception was thrown, but it did provide a cause throwable " + "(e.getCause() returned null). See this exception's getCause() method to " + "view the ExecutionException that has occurred.", e ); if (originalException instanceof IOException) throw (IOException) originalException; if (originalException instanceof RuntimeException) throw (RuntimeException) originalException; throw new RejectedExecutionException( "An Execution Exception occurred, but it was neither a RuntimeException, " + "nor IOException. See this exception's getCause() method to view the " + "underlying error that has occurred.", originalException ); } } /** * Parses and Vectorizes HTML from a URL source. * Spawns a <I>monitor-thread</I> that stops the download if a certain, user-specified, * time-limit is exceeded. * @param timeout <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_TIMEOUT> * @param unit <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_UNIT> * @param url <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_URL> * @param eliminateHTMLTags <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_ELIM_HT> * @param startLineNum <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_START_LN> * @param endLineNum <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_END_LN> * @param rawHTMLFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RAW_HTML> * @param matchesFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_MATCHES_F> * @param justTextFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_JUST_TEXT> * @return <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RETURN> * @throws IllegalArgumentException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IAEX> * @throws ScrapeException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_SCEX1> * @throws IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> * @throws InterruptedException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IEX> * @throws RejectedExecutionException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_REEX> */ public static Vector<HTMLNode> getPageTokens( long timeout, TimeUnit unit, URL url, boolean eliminateHTMLTags, int startLineNum, int endLineNum, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException, InterruptedException { Callable<Vector<HTMLNode>> threadDownloader = new Callable<Vector<HTMLNode>>() { public Vector<HTMLNode> call() throws Exception { return parser.parse( Scrape.getHTML(Scrape.openConn(url), startLineNum, endLineNum), eliminateHTMLTags, rawHTMLFile, matchesFile, justTextFile ); } }; lock.lock(); Future<Vector<HTMLNode>> future = executor.submit(threadDownloader); lock.unlock(); try { return future.get(timeout, unit); } catch (TimeoutException e) { return null; } catch (ExecutionException e) { Throwable originalException = e.getCause(); if (originalException == null) throw new RejectedExecutionException( "An Execution Exception was thrown, but it did provide a cause throwable " + "(e.getCause() returned null). See this exception's getCause() method to " + "view the ExecutionException has that occurred.", e ); if (originalException instanceof IOException) throw (IOException) originalException; if (originalException instanceof RuntimeException) throw (RuntimeException) originalException; throw new RejectedExecutionException( "An Execution Exception occurred, but it was neither a RuntimeException, nor " + "IOException. See this exception's getCause() method to view the underlying " + "error that has occurred.", originalException ); } } } |