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 | package Torello.HTML; import java.io.*; import java.util.Vector; import java.net.URL; import Torello.JavaDoc.StaticFunctional; import Torello.JavaDoc.JDHeaderBackgroundImg; import Torello.JavaDoc.Excuse; import Torello.Java.UnreachableError; /** * Java HTML's flagship-parser class for converting HTML web-pages into plain Java {@code Vector's} * of {@link HTMLNode}. * * <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE> * * @see Scrape#getHTML(BufferedReader, int, int) * @see Scrape#getHTML(BufferedReader, String, String) * @see HTMLPageMWT */ @StaticFunctional(Excused="parser", Excuses=Excuse.SINGLETON) @JDHeaderBackgroundImg public class HTMLPage { private HTMLPage() { } /** * A function-pointer / lambda-target that (could) potentially be used to replace this * library's current regular-expression based parser with something possibly faster or even * more efficient. * * <BR /><BR /><EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_PARSER> * @see #parser */ @FunctionalInterface public static interface Parser { /** * Parse html source-text into a {@code Vector<HTMLNode>}. * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_HTML> * @param eliminateHTMLTags <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_ELIM_HT> * @param rawHTMLFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RAW_HTML> * <BR /><BR /><B STYLE='color:red;'>NOTE:</B> If you have decided to implement a parser, * and you wish to ingore this parameter (and don't want to output such a file) - <I>it is * (hopefully) obvious that you may skip this step!</I> * @param matchesFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_MATCHES_F> * <BR /><BR /><B>NOTE:</B> <I>As above,</I> you may skip implementing this. * @param justTextFile <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_JUST_TEXT> * <BR /><BR /><B>NOTE:</B> <I>As above,</I> you may skip implementing this. * @return <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RETURN> * @throws IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> */ public Vector<HTMLNode> parse( CharSequence html, boolean eliminateHTMLTags, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException; } /** * 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 Parser * @see Parser#parse */ public static Parser parser = Torello.HTML.HelperPackages.parse.ParserRE::parsePageTokens; // ******************************************************************************************** // ******************************************************************************************** // These 6 functions presume that the HTML source needs to be downloaded & read from a URL // ******************************************************************************************** // ******************************************************************************************** /** * Convenience Method. * <BR />Accepts: {@code URL} * <BR />Passes null to parameters * {@code startTag, endTag, rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(BufferedReader, boolean, * String, String, String, String, String)} * <BR />And Invokes: {@link Scrape#openConn(URL)} */ public static Vector<HTMLNode> getPageTokens (URL url, boolean eliminateHTMLTags) throws IOException { return getPageTokens (Scrape.openConn(url), eliminateHTMLTags, null, null, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code URL} * <BR />And-Accepts: {@code 'startTag'} and {@code 'endTag'} * <BR />Passes null to parameters {@code rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(BufferedReader, boolean, * String, String, String, String, String)} * <BR />And Invokes: {@link Scrape#openConn(URL)} */ public static Vector<HTMLNode> getPageTokens (URL url, boolean eliminateHTMLTags, String startTag, String endTag) throws IOException { return getPageTokens (Scrape.openConn(url), eliminateHTMLTags, startTag, endTag, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code URL} * <BR />And-Accepts: {@code 'startLineNum'} and {@code 'endLineNum'} * <BR />Passes null to parameters {@code rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(BufferedReader, boolean, * int, int, String, String, String)} * <BR />And Invokes: {@link Scrape#openConn(URL)} */ public static Vector<HTMLNode> getPageTokens (URL url, boolean eliminateHTMLTags, int startLineNum, int endLineNum) throws IOException { return getPageTokens (Scrape.openConn(url), eliminateHTMLTags, startLineNum, endLineNum, null, null, null); } /** * Convenience Method. * <BR />Accepts: {@code URL} * <BR />Passes null to {@code startTag} & {@code endTag} parameters. * <BR />Invokes: {@link #getPageTokens(BufferedReader, boolean, * String, String, String, String, String)} * <BR />And Invokes: {@link Scrape#openConn(URL)} */ public static Vector<HTMLNode> getPageTokens( URL url, boolean eliminateHTMLTags, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { return getPageTokens( Scrape.openConn(url), eliminateHTMLTags, null, null, rawHTMLFile, matchesFile, justTextFile ); } /** * Convenience Method. * <BR />Accepts: {@code URL} * <BR />And-Accepts: {@code 'startTag'} and {@code 'endTag'} * <BR />Invokes: {@link #getPageTokens(BufferedReader, boolean, * String, String, String, String, String)} * <BR />And Invokes: {@link Scrape#openConn(URL)} */ public static Vector<HTMLNode> getPageTokens( URL url, boolean eliminateHTMLTags, String startTag, String endTag, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { return getPageTokens( Scrape.openConn(url), eliminateHTMLTags, startTag, endTag, rawHTMLFile, matchesFile, justTextFile ); } /** * Convenience Method. * <BR />Accepts: {@code URL} * <BR />And-Accepts: {@code 'startLineNum'} and {@code 'endLineNum'} * <BR />Invokes: {@link #getPageTokens(BufferedReader, boolean, * int, int, String, String, String)} * <BR />And Invokes: {@link Scrape#openConn(URL)} */ public static Vector<HTMLNode> getPageTokens( URL url, boolean eliminateHTMLTags, int startLineNum, int endLineNum, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { return getPageTokens( Scrape.openConn(url), eliminateHTMLTags, startLineNum, endLineNum, rawHTMLFile, matchesFile, justTextFile ); } // ******************************************************************************************** // ******************************************************************************************** // These 6 functions presume that the HTML source is from a CharSequence // ******************************************************************************************** // ******************************************************************************************** /** * Parses and Vectorizes HTML from a {@code CharSequence} (usually a {@code String}) source. * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_HTML> * @param eliminateHTMLTags <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_ELIM_HT> * @return <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_RETURN> * <BR /><BR /><B><SPAN STYLE="color: red;">NOTE:</B></SPAN> This method does not throw any * checked-exceptions, there is no Input-Output involved here, it is strictly a computational * method that neither invokes the file-system, nor the web. */ public static Vector<HTMLNode> getPageTokens (CharSequence html, boolean eliminateHTMLTags) // NO IOException... NO I/O! { try { return parser.parse(html, eliminateHTMLTags, null, null, null); } // This should never happen, when reading from a 'String' rather than a URL, or // BufferedReader ==> IOException will not be thrown. catch (IOException ioe) { throw new UnreachableError(ioe); } } /** * Convenience Method. * <BR />Accepts: {@code CharSequence} * <BR />And-Accepts: {@code 'startTag'} and {@code 'endTag'} * <BR />Passes null to parameters {@code rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(CharSequence, boolean, * String, String, String, String, String)} * <BR />Catches: {@code IOException} <B>{@code ==>}</B> No HTTP-I/O, so an IOException isn't * possible! */ public static Vector<HTMLNode> getPageTokens (CharSequence html, boolean eliminateHTMLTags, String startTag, String endTag) // NO IOException... NO I/O! { try { return getPageTokens(html, eliminateHTMLTags, startTag, endTag, null, null, null); } // This should never happen, when reading from a 'String' rather than a URL, or // BufferedReader ==> IOException will not be thrown. catch (IOException ioe) { throw new UnreachableError(ioe); } } /** * Convenience Method. * <BR />Accepts: {@code CharSequence} * <BR />And-Accepts: {@code 'startLineNum'} and {@code 'endLineNum'} * <BR />Passes null to parameters {@code rawHTMLFile, matchesFile & justTextFile}. * <BR />Invokes: {@link #getPageTokens(CharSequence, boolean, * int, int, String, String, String)} * <BR />Catches: {@code IOException} <B>{@code ==>}</B> No HTTP-I/O, so an IOException isn't * possible! */ public static Vector<HTMLNode> getPageTokens (CharSequence html, boolean eliminateHTMLTags, int startLineNum, int endLineNum) // NO IOException... NO I/O! { try { return getPageTokens (html, eliminateHTMLTags, startLineNum, endLineNum, null, null, null); } // This should never happen, when reading from a 'String' rather than a URL, or // BufferedReader ==> IOException will not be thrown. catch (IOException ioe) { throw new UnreachableError(ioe); } } /** * Parses and Vectorizes HTML from a {@code CharSequence} (usually a {@code String}) source. * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_HTML> * @param eliminateHTMLTags <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_ELIM_HT> * @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 IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> */ public static Vector<HTMLNode> getPageTokens( CharSequence html, boolean eliminateHTMLTags, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { return parser.parse(html, eliminateHTMLTags, rawHTMLFile, matchesFile, justTextFile); } /** * Parses and Vectorizes HTML from a {@code CharSequence} (usually a {@code String}) source. * @param html <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_HTML> * @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 IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> * @throws ScrapeException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_SCEX2> */ public static Vector<HTMLNode> getPageTokens( CharSequence html, boolean eliminateHTMLTags, String startTag, String endTag, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { String htmlStr = html.toString(); int sPos = htmlStr.indexOf(startTag); if (sPos == -1) throw new IllegalArgumentException ("Passed String-Parameter 'startTag' [" + startTag + "] was not found in HTML."); int ePos = htmlStr.indexOf(endTag, sPos); if (ePos == -1) throw new IllegalArgumentException ("Passed String-Parameter 'endTag' [" + endTag + "] was not found in HTML."); ePos += endTag.length(); return parser.parse( htmlStr.substring(sPos, ePos), eliminateHTMLTags, rawHTMLFile, matchesFile, justTextFile ); } /** * Convenience Method. * <BR />Accepts: {@code CharSequence} * <BR />And-Accepts: {@code 'startLineNum'} and {@code 'endLineNum'} * <BR />Invokes: {@link #getPageTokens(BufferedReader, boolean, * int, int, String, String, String)} */ public static Vector<HTMLNode> getPageTokens( CharSequence html, boolean eliminateHTMLTags, int startLineNum, int endLineNum, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { return getPageTokens( new BufferedReader(new StringReader(html.toString())), eliminateHTMLTags, startLineNum, endLineNum, 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(BufferedReader, boolean, * String, String, String, String, String)} */ public static Vector<HTMLNode> getPageTokens (BufferedReader br, boolean eliminateHTMLTags) throws IOException { return getPageTokens(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(BufferedReader, boolean, * String, String, String, String, String)} */ public static Vector<HTMLNode> getPageTokens (BufferedReader br, boolean eliminateHTMLTags, String startTag, String endTag) throws IOException { return getPageTokens(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(BufferedReader, boolean, * int, int, String, String, String)} */ public static Vector<HTMLNode> getPageTokens (BufferedReader br, boolean eliminateHTMLTags, int startLineNum, int endLineNum) throws IOException { return getPageTokens(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(BufferedReader, boolean, * String, String, String, String, String)} */ public static Vector<HTMLNode> getPageTokens( BufferedReader br, boolean eliminateHTMLTags, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { return getPageTokens (br, eliminateHTMLTags, null, null, rawHTMLFile, matchesFile, justTextFile); } // ******************************************************************************************** // ******************************************************************************************** // // ******************************************************************************************** // ******************************************************************************************** /** * Parses and Vectorizes HTML from a {@code BufferedReader} source. * @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 IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> * @throws ScrapeException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_SCEX2> */ public static Vector<HTMLNode> getPageTokens( BufferedReader br, boolean eliminateHTMLTags, String startTag, String endTag, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { return parser.parse( Scrape.getHTML(br, startTag, endTag), eliminateHTMLTags, rawHTMLFile, matchesFile, justTextFile ); } /** * Parses and Vectorizes HTML from a {@code BufferedReader} source. * @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 IOException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IOEX> * @throws IllegalArgumentException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_IAEX> * @throws ScrapeException <EMBED CLASS='external-html' DATA-FILE-ID=HTML_PAGE_SCEX1> */ public static Vector<HTMLNode> getPageTokens( BufferedReader br, boolean eliminateHTMLTags, int startLineNum, int endLineNum, String rawHTMLFile, String matchesFile, String justTextFile ) throws IOException { return parser.parse( Scrape.getHTML(br, startLineNum, endLineNum), eliminateHTMLTags, rawHTMLFile, matchesFile, justTextFile ); } } |