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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 | package Torello.HTML.Tools.NewsSite; import Torello.HTML.*; import Torello.HTML.NodeSearch.*; import Torello.HTML.Tools.NewsSite.*; import Torello.Java.*; import Torello.Languages.LC; import java.util.*; import java.util.regex.*; import java.net.URL; import java.io.*; /** * This class is nothing more than an 'Example Class' that contains some foreign-language * based news web-pages, from both overseas and from Latin America. * * <BR /><BR /><EMBED CLASS='external-html' DATA-FILE-ID=NEWS_SITES> */ public class NewsSites { private NewsSites() { } @SuppressWarnings("unchecked") private static final Hashtable<String, Vector<URL>> newsPaperSections = (Hashtable<String, Vector<URL>>) LFEC.readObjectFromFile_JAR (NewsSite.class, "data-files/SectionURLs.htdat", true, Hashtable.class); /** * This example will run the news-site scrape on the Chinese Government News Article * Carousel. * * <BR /><BR /><B><SPAN STYLE="color: red;">IMPORTANT NOTE:</B></SPAN> This will method will * create a directory called <B>"cnb"</B> on your file-system where it will write the contents * of (most likely) 15 news-paper articles to disk as HTML files. * * The output log generated by this method may be viewed here: * <BR /><BR /><B><CODE><A HREF='doc-files/Logs/Gov.CN.log.html'> * Gov.CN.log.html</A></B></CODE> * * @throws IOException This throws for IO errors that may occur when reading the web-server, * or when saving the web-pages or images to the file-system. * * @see FileRW#delTree(String, boolean, Appendable) * @see NewsSite * @see FileRW#writeFile(CharSequence, String) * @see C#toHTML(String, boolean, boolean, boolean) */ public static void runExample() throws IOException { StorageWriter log = new StorageWriter(); // This directory will contain ".dat" files that are simply "Serialized" HTML Vectors. // Each ".dat" file will contain precisely one HTML page. final String dataFilesDir = "cnb" + File.separator + "articleData" + File.separator; // This directory will contain sub-directories with ".html" files (and image-files) // for each news-article that is saved / downloaded. final String htmlFilesDir = "cnb" + File.separator + "articleHTML" + File.separator; // This CLEARS WHATEVE DATA IS CURRENTLY IN THE DIRECTORY (by deleting all its contents) // The following code is the same as the UNIX Shell Command: // rm -r cnb/articleData/ // mkdir cnb/articleData FileRW.delTree(dataFilesDir, true, log); // The following code is the same as the UNIX Shell Command: // rm -r cnb/articleHTML/ // mkdir cnb/articleHTML FileRW.delTree(htmlFilesDir, true, log); // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // Previous Download Data Erased (if any), Start today's News-Site Scrape // *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** // Use the "GovCNCarousel" instance that is created in this class as a NewsSite NewsSite ns = NewsSites.GovCNCarousel; // Call the "Scrape URLs" class to retrieve all of the available newspaper articles // on the Java-Script "Article Carousel" Again, the "Article Carousel" is just this // little widget at the top of the page that rotates (usually) five hilited / emphasized // news-article links for today Vector<Vector<String>> articleURLs = ScrapeURLs.get(ns, log); // This is usually not very important if only a small number of articles are being // scraped. When downloading hundreds of articles - being able to pause if there is a // web-site IOError (And restart) is very important. // // The standard factory-generated "getFSInstance" creates a small file on the file-system // for saving the "Download State" while downloading... Pause pause = Pause.getFSInstance("cnb" + File.separator + "state.dat"); pause.initialize(); // The "Scraped Articles" will be sent to the directory named by "dataFilesDir" // Using the File-System to save these articles is the default-factory means for // saving article-data. Writing a customized "ScapedArticleReceiver" to do anything // from saving article-data to a Data-Base up to and including e-mailing article data // is possible using a self-written "ScrapedArticleReceiver" ScrapedArticleReceiver receiver = ScrapedArticleReceiver.saveToFS(dataFilesDir); // This will download each of the article's from their web-page URL. The web-page // article URL's were retrieved by "Scraped URLs". The saved HTML (as HTML Vectors) // is sent to the "Article Receiver" (defined in the previous step). These news articles // are saved as ".dat" since they are serialized java-objects. // // Explaining some "unnamed parameters" passed to the method invocation below: // // true: [skipArticlesWithoutPhotos] Skips Mandarin Chinese Newspaper Articles that do not // include at least one photo. Photos usually help when reading foreign news articles. // null: [bannerAndAdFinder] Some sites include images for Facebook links or advertising. // Gov.CN usually doesn't have these, but occasionally there are extraneous links. // for the purposes of this example, this parameter is ignored, and passed null. // false: [keepOriginalPageHTML] The "Complete Page" - content before the Article Body is // extracted from the Article Web-Page is not saved. This can occasionally be useful // if the HTML <HEAD>...</HEAD> has JSON or React-JS data to extract. ScrapeArticles.download (receiver, articleURLs, ns.articleGetter, true, null, false, pause, log); // Now this will convert each of the ".dat" files to an ".html" file - and also it // will download the pictures / image included in the article. // // Explaining some "unnamed parameters" passed to the method invocation below: // // true: [cleanIt] This runs some basic HTML remove operations. The best way to see // what the parameter "cleanIt" asks to have removed is to view the class "ToHTML" // null: [HTMLModifier] Cleaning up other extraneous links and content in an newspaper // article body like advertising or links to other articles is usually necessary. // Anywhere between 1 and 10 lines of NodeSearch Removal Operations will get rid of // unnecessary HTML. For the purposes of this example, such a cleaning operation is // not done here - although the final articles do include some "links to other // articles" that is not "CLEANED" like it should be. ToHTML.convert(dataFilesDir, htmlFilesDir, true, null, log); // NOTE: The log of running this command on Debian UNIX / LINUX may be viewed in the // JavaDoc Comments in the top of this method. If this method is run in an MS-DOS // or Windows Environment, there will be no screen colors available to view. FileRW.writeFile( C.toHTML(log.getString(), true, true, true), "cnb" + File.separator + "Gov.CN.log.html" ); } /** * Prints the contents of the Data File. Invoking this command allows a programmer to see * which "sub-sections" are ascribed to each of the different news-paper definitions in this * class. Each "sub-section" is nothing more than a {@code URL}-branch of the primary web * site {@code URL}. * * <DIV CLASS="HTML">{@code * <!-- If the following were the primary news-site --> * http://news.baidu.com * * <!-- This would be a "sub-section" of the primary site --> * http://news.baidu.com/sports * }</DIV> * * <BR /><BR />Can be called from the command line. * <BR /><BR />If a single command-line argument is passed to {@code "argv[0]"}, the contents * of the "Sections URL Data File" will be output to a text-file that is named using the * {@code String} passed to {@code "argv[0]"}. * * @param argv These are the command line arguments passed by the JRE to this method. * @throws IOException If there are any problems while attempting to save the output to the * the output file (if one was named / requested). */ public static void main(String[] argv) throws IOException { // Uncomment this line to run the example code (instead of section-data print) // runExample(); System.exit(0); // The data-file is loaded into private field "newsPaperSections" // This private field is a Hashtable<String, Vector<URL>>. Convert each of // these sections so that they may be printed to terminal and maybe to a text // file. StringBuilder sb = new StringBuilder(); for (String newspaper : newsPaperSections.keySet()) { sb.append(newspaper + '\n'); for (URL section : newsPaperSections.get(newspaper)) sb.append(section.toString() + '\n'); sb.append("\n\n***************************************************\n\n"); } String s = sb.toString(); System.out.println(s); // If there is a command-line parameter, it shall be interpreted a file-name. // The contents of the "sections data-file" (as text) will be written a file on the // file-system using the String-value of "argv[0]" as the name of the output-filename. if (argv.length == 1) FileRW.writeFile(s, argv[0]); } // URLFilter.regexKEEP(Pattern.compile("^http.+baidu\\.com\\/s\\?id=\\d+$"))); // ArticleGet.usual(TextComparitor.CN_CI, "article-content")); /** * The News Site at address: <CODE><A HREF="https://www.abc.es/" TARGET=_blank> * "https://www.abc.es/"</A></CODE> is slightly more complicated when retrieving News-Article * Links. * * <BR /><BR />Notice that each newspaper article {@code URL}-link is "wrapped" in an HTML * {@code '<ARTICLE>...</ARTICLE>'} Element. * * <BR /><BR />If this code were translated into an "XPath Query" or "CSS Selector", it would * read: <B>{@code article a}</B>. Specifically it says to find all {@code 'Anchor'} elements * that are descendants of {@code 'Article'} Elements. * * @see TagNodeFindL1Inclusive#all(Vector, String) * @see TagNodeGet#first(Vector, int, int, TC, String[]) * @see TagNode#AV(String) */ public static Vector<String> ABC_LINKS_GETTER(URL url, Vector<HTMLNode> page) { Vector<String> ret = new Vector<>(); TagNode tn; String urlStr; // Links are kept inside <ARTICLE> ... </ARTICLE> on the main / section page. for (DotPair article : TagNodeFindL1Inclusive.all(page, "article")) // Now find the <A HREF=...> ... </A> if ((tn = TagNodeGet.first(page, article.start, article.end, TC.OpeningTags, "a")) != null) if ((urlStr = tn.AV("href")) != null) ret.add(urlStr); return ret; } /** * This is the {@code NewsSite} definition for the Newspaper located at: * <CODE><A HREF="https://www.abc.es/" TARGET=_blank>https://www.abc.es/</A></CODE>. * * <BR /><BR /><TABLE CLASS=JDBriefTable> * <TR><TH>Parameter</TH> <TH>Significance</TH></TR> * <TR><TD>Newspaper Name</TD> <TD>ABC España</TD></TR> * <TR><TD>Country of Origin</TD> <TD>Spain</TD></TR> * <TR><TD>Website URL</TD> <TD>{@code https://abc.es}</TD></TR> * <TR><TD>Newspaper Printing Language</TD> <TD>Spanish</TD></TR> * </TABLE> * * <BR /><TABLE CLASS=NEWSSITE> * <TR><TH>Parameter</TH><TH>Purpose</TH><TH>Value</TH></TR> * <TR> <TD>Newspaper Article Groups / Sections</TD> * <TD>Scrape Sections</TD> * <TD><I>Retrieved from Data File</I></TD> * </TR> * <TR> <TD><B>{@link StrFilter}</B></TD> * <TD>News Web-Site Section-Page Aritlce-Link ({@code <A HREF=...>}) Filter</TD> * <TD>{@code 'HREF'} must end with {@code '.html'} * <BR />See: {@link StrFilter#comparitor(TextComparitor, String[])} * <BR />See: {@link TextComparitor#EW_CI} * </TD> * </TR> * <TR> <TD><B>{@link LinksGet}</B></TD> * <TD>Used to <B><I>manually</I></B> retrieve Article-Link {@code URL's}</TD> * <TD>Invokes method {@link #ABC_LINKS_GETTER(URL, Vector)}</TD> * </TR> * <TR> <TD><B>{@link ArticleGet}</B></TD> * <TD>Retrieves Article-Body Content from an Article-Link Web-Page</TD> * <TD>{@code <MAIN>...</MAIN>}<BR />See: {@link ArticleGet#usual(String)}</TD> * </TR> * </TABLE> * * <BR />View a copy of the logs that are generated from using this {@code NewsSite} instance. * <BR /><BR /><UL CLASS=JDUL> * <LI> <CODE><B><A HREF='doc-files/Logs/ABC.ES-ScrapeURLs.html'> * ABC.ES ScrapeURLs LOG</A></B></CODE> * </LI> * <LI> {@code ScrapeArticles} * <BR /><B>IMPORTANT NOTE:</B> Though {@code ScrapeURL's} code <I>will check for * duplicate {@code URL's}</I> that may be returned <I>within any given-section</I>, * {@code Article URL's} may be repeated among the different sections of the newspaper. * Since the {@code URL}-scrape returned nearly 3,000 articles, the log of * an {@code Article} scrape is not included here. Proper duplicate {@code URL} checking * code has obviously been written, but would be too complicated to show in this example. * </LI> * </UL> * * <EMBED CLASS='external-html' DATA-FILE-ID=NEWS_STE_CHANGE> */ public static final NewsSite ABCES = new NewsSite ( "ABC España", Country.Spain, "https://www.abc.es/", LC.ES, "ABC is a Spanish national daily newspaper. It is the third largest general-interest " + "newspaper in Spain, and the oldest newspaper still operating in Madrid.", newsPaperSections.get("ABCES"), StrFilter.comparitor(TextComparitor.EW_CI, ".html"), NewsSites::ABC_LINKS_GETTER, ArticleGet.usual("main"), null /* bannerAndAdFinder */ ); /** * This is the {@code NewsSite} definition for the Newspaper located at: * <CODE><A HREF="https://www.elpulso.mx/" TARGET=_blank>https://www.elpulso.mx/</A></CODE>. * * <BR /><BR /><TABLE CLASS=JDBriefTable> * <TR><TH>Parameter</TH> <TH>Significance</TH></TR> * <TR><TD>Newspaper Name</TD> <TD>El Pulso, México</TD></TR> * <TR><TD>Country of Origin</TD> <TD>México</TD></TR> * <TR><TD>Website URL</TD> <TD>{@code https://elpulso.mx}</TD></TR> * <TR><TD>Newspaper Printing Language</TD> <TD>Spanish</TD></TR> * </TABLE> * * <BR /><TABLE CLASS=NEWSSITE> * <TR><TH>Parameter</TH><TH>Purpose</TH><TH>Value</TH></TR> * <TR> <TD>Newspaper Article Groups / Sections</TD> * <TD>Scrape Sections</TD> * <TD><I>Retrieved from Data File</I></TD> * </TR> * <TR> <TD><B>{@link StrFilter}</B></TD> * <TD>News Web-Site Section-Page Aritlce-Link ({@code <A HREF=...>}) Filter</TD> * <TD>{@code HREF} must match: {@code http://some.domain/YYYY/MM/DD/<article-name>/}</TD> * </TR> * <TR> <TD><B>{@link LinksGet}</B></TD> * <TD>Used to <B><I>manually</I></B> retrieve Article-Link {@code URL's}</TD> * <TD><B>{@code null}</B>. Retrieves <B><I>all</I></B> Anchor-Links on a Section-Page. * Note that {@code URL's} must still pass the previous {@code StrFilter} (above) * in order to be parsed as {@link Article}'s. * </TD> * </TR> * <TR> <TD><B>{@link ArticleGet}</B></TD> * <TD>Retrieves Article-Body Content from an Article-Link Web-Page</TD> * <TD>{@code <DIV CLASS="entry-content">...</DIV>} * <BR />See: {@link ArticleGet#usual(TextComparitor, String[])} * <BR />See: {@link TextComparitor#C} * </TD> * </TR> * </TABLE> */ public static final NewsSite Pulso = new NewsSite ( "El Pulso, México", Country.Mexico, "https://elpulso.mx", LC.ES, "El Pulso newspaper is Spanish language newspaper in Mexico. It is showing breaking " + "news, " + "headlines, kids news, tourism news, entertainment news, study news, industrial news, " + "economical news, health & beauty news, crime news, career news, Travel news, " + "diet & fitness news, Top stories, special news, celebrity news.", newsPaperSections.get("PULSO"), StrFilter.regExKEEP(Pattern.compile( "^https?:\\/{2}.*?\\/\\d{4}\\/\\d{2}\\/\\d{2}\\/[\\w-]{10,}\\/$" ), false), null /* LinksGet */, ArticleGet.usual(TextComparitor.C, "entry-content"), null /* bannerAndAddFinder */ ); /** * The News Site at address: <CODE><A HREF="https://www.ElNacional.com/" TARGET=_blank> * "https://www.ElNacional.com/"</A></CODE> is slightly more complicated when retrieving * News-Article Links. * * <BR /><BR />Notice that each newspaper article {@code URL}-link is "wrapped" in an HTML * {@code '<DIV CLASS="td-module-thumb">...</DIV>'} Element. * * <BR /><BR />If this code were translated into an "XPath Query" or "CSS Selector", it would * read: <B>{@code div.td-module-thumb a}</B>. Specifically it says to find all * {@code 'Anchor'} elements that are descendants of {@code 'DIV'} Elements where said * Divider's CSS {@code CLASS} contains {@code 'td-module-thumb'}. * * @see InnerTagFindInclusive#all(Vector, String, String, TextComparitor, String[]) * @see TagNodeGet#first(Vector, int, int, TC, String[]) * @see TagNode#AV(String) */ public static Vector<String> EL_NACIONAL_LINKS_GETTER(URL url, Vector<HTMLNode> page) { Vector<String> ret = new Vector<>(); TagNode tn; String urlStr; // Links are kept inside <DIV CLASS=td-module-thumb> ... </DIV> on the main / section page. for (DotPair article : InnerTagFindInclusive.all (page, "div", "class", TextComparitor.C, "td-module-thumb")) // Now find the <A HREF=...> ... </A> if ((tn = TagNodeGet.first (page, article.start, article.end, TC.OpeningTags, "a")) != null) if ((urlStr = tn.AV("href")) != null) ret.add(urlStr); return ret; } /** * This is the {@code NewsSite} definition for the Newspaper located at: * <CODE><A HREF="https://www.elnacional.com/" TARGET=_blank> * https://www.elnacional.com/</A></CODE>. * * <BR /><BR /><TABLE CLASS=JDBriefTable> * <TR><TH>Parameter</TH> <TH>Significance</TH></TR> * <TR><TD>Newspaper Name</TD> <TD>El Nacional</TD></TR> * <TR><TD>Country of Origin</TD> <TD>Venezuela</TD></TR> * <TR><TD>Website URL</TD> <TD>{@code https://elnacional.com}</TD></TR> * <TR><TD>Newspaper Printing Language</TD> <TD>Spanish</TD></TR> * </TABLE> * * <BR /><TABLE CLASS=NEWSSITE> * <TR><TH>Parameter</TH><TH>Purpose</TH><TH>Value</TH></TR> * <TR> <TD>Newspaper Article Groups / Sections</TD> * <TD>Scrape Sections</TD> * <TD><I>Retrieved from Data File</I></TD> * </TR> * <TR> <TD><B>{@link URLFilter}</B></TD> * <TD>News Web-Site Section-Page Aritlce-Link ({@code <A HREF=...>}) Filter</TD> * <TD><B>{@code null}</B>. The {@code LinksGet} provided here will only return valid * {@code Article URL's}, so there is no need for a {@code URLFilter}. * </TD> * </TR> * <TR> <TD><B>{@link LinksGet}</B></TD> * <TD>Used to <B><I>manually</I></B> retrieve Article-Link {@code URL's}</TD> * <TD>Invokes method {@link #EL_NACIONAL_LINKS_GETTER(URL, Vector)}</TD> * </TR> * <TR> <TD><B>{@link ArticleGet}</B></TD> * <TD>Retrieves Article-Body Content from an Article-Link Web-Page</TD> * <TD>{@code <ARTICLE>...</ARTICLE>}<BR />See: {@link ArticleGet#usual(String)}</TD> * </TR> * </TABLE> * * <BR />View a copy of the logs that are generated from using this {@code NewsSite}. * <BR /><BR /><UL CLASS=JDUL> * <LI> <CODE><B><A HREF='doc-files/Logs/ElNacional-ScrapeURLs.html'> * El Nacional ScrapeURLs LOG</A></B></CODE> * </LI> * <LI> <CODE><B><A HREF='doc-files/Logs/ElNacional-ScrapeArticles.html'> * El Nacional ScrapeArticles LOG</A></B></CODE> * </LI> * </UL> * * <EMBED CLASS='external-html' DATA-FILE-ID=NEWS_STE_CHANGE> */ public static final NewsSite ElNacional = new NewsSite ( "El Nacional", Country.Venezuela, "https://elnacional.com", LC.ES, "El Nacional is a Venezuelan publishing company under the name C.A. Editorial " + "El Nacional, " + "most widely known for its El Nacional newspaper and website. It, along with Últimas " + "Noticias and El Universal, are the most widely read and circulated daily national " + "newspapers in the country, and it has an average of more than 80,000 papers distributed " + "daily and 170,000 copies on weekends.", newsPaperSections.get("ElNacional"), (URLFilter) null, /* The LinksGetter will only return valid Anchor's */ NewsSites::EL_NACIONAL_LINKS_GETTER, ArticleGet.usual("article"), null /* bannerAndAdFinder */ ); /** * The News Site at address: <CODE><A HREF="https://www.ElEspectador.com/" TARGET=_blank> * "https://www.ElEspectador.com/"</A></CODE> is slightly more complicated when retrieving * News-Article Links. * * <BR /><BR />Notice that each newspaper article {@code URL}-link is "wrapped" in an HTML * {@code '<DIV CLASS="Card ...">...</DIV>'} Element. * * <BR /><BR />If this code were translated into an "XPath Query" or "CSS Selector", it would * read: <B>{@code div.Card a.card-link}</B>. Specifically it says to find all * {@code 'Anchor'} elements whose CSS {@code Class} contains {@code 'card-link'} and which * are descendants of {@code 'DIV'} Elements where said Divider's * CSS {@code CLASS} contains {@code 'Card'}. * * @see InnerTagFindInclusive#all(Vector, String, String, TextComparitor, String[]) * @see InnerTagGet#first(Vector, int, int, String, String, TextComparitor, String[]) * @see TagNode#AV(String) */ public static Vector<String> EL_ESPECTADOR_LINKS_GETTER(URL url, Vector<HTMLNode> page) { Vector<String> ret = new Vector<>(); TagNode tn; String urlStr; // Links are kept inside <DIV CLASS="Card ..."> ... </DIV> on the main / section page. for (DotPair article : InnerTagFindInclusive.all (page, "div", "class", TextComparitor.C, "Card")) // Now find the <A CLASS="card-link" HREF=...> ... </A> if ((tn = InnerTagGet.first (page, article.start, article.end, "a", "class", TextComparitor.C, "card-link")) != null) if ((urlStr = tn.AV("href")) != null) ret.add(urlStr); return ret; } /** * This is the {@code NewsSite} definition for the Newspaper located at: * <CODE><A HREF="https://www.elespectador.com/" TARGET=_blank> * https://www.elespectador.com/</A></CODE>. * * <BR /><BR /><TABLE CLASS=JDBriefTable> * <TR><TH>Parameter</TH> <TH>Significance</TH></TR> * <TR><TD>Newspaper Name</TD> <TD>El Espectador</TD></TR> * <TR><TD>Country of Origin</TD> <TD>Columbia</TD></TR> * <TR><TD>Website URL</TD> <TD>{@code https://elespectador.com}</TD></TR> * <TR><TD>Newspaper Printing Language</TD> <TD>Spanish</TD></TR> * </TABLE> * * <BR /><TABLE CLASS=NEWSSITE> * <TR><TH>Parameter</TH><TH>Purpose</TH><TH>Value</TH></TR> * <TR> <TD>Newspaper Article Groups / Sections</TD> * <TD>Scrape Sections</TD> * <TD><I>Retrieved from Data File</I></TD> * </TR> * <TR> <TD><B>{@link StrFilter}</B></TD> * <TD>News Web-Site Section-Page Aritlce-Link ({@code <A HREF=...>}) Filter</TD> * <TD>{@code HREF} must end with a forward-slash {@code '/'} character. * <BR />See: {@link TextComparitor#ENDS_WITH} * </TD> * </TR> * <TR> <TD><B>{@link LinksGet}</B></TD> * <TD>Used to <B><I>manually</I></B> retrieve Article-Link {@code URL's}</TD> * <TD>Invokes method {@link #EL_NACIONAL_LINKS_GETTER(URL, Vector)}</TD> * </TR> * <TR> <TD><B>{@link ArticleGet}</B></TD> * <TD>Retrieves Article-Body Content from an Article-Link Web-Page</TD> * <TD>{@code <DIV CLASS="l-main">...</DIV>} * <BR />See: {@link ArticleGet#usual(TextComparitor, String[])} * <BR />See: {@link TextComparitor#C} * </TD> * </TR> * </TABLE> * * <BR />View a copy of the logs that are generated from using this {@code NewsSite}. * <BR /><BR /><UL CLASS=JDUL> * <LI> <CODE><B><A HREF='doc-files/Logs/ElEspectador-ScrapeURLs.html'> * El Espectador ScrapeURLs LOG</A></B></CODE> * </LI> * <LI> <CODE><B><A HREF='doc-files/Logs/ElEspectador-ScrapeArticles.html'> * El Espectador ScrapeArticles LOG</A></B></CODE> * </LI> * </UL> * * <EMBED CLASS='external-html' DATA-FILE-ID=NEWS_STE_CHANGE> */ public static final NewsSite ElEspectador = new NewsSite ( "El Espectador, Columbia", Country.Colombia, "https://elespectador.com", LC.ES, "El Espectador (meaning \"The Spectator\") is a newspaper with national circulation " + "within " + "Colombia, founded by Fidel Cano Gutiérrez on 22 March 1887 in Medellín and published " + "since 1915 in Bogotá. It changed from a daily to a weekly edition in 2001, following a " + "financial crisis, and became a daily again on 11 May 2008, a comeback which had been " + "long rumoured, in tabloid format (28 x 39.5 cm). From 1997 to 2011 its main shareholder " + "was Julio Mario Santo Domingo.", newsPaperSections.get("ElEspectador"), StrFilter.comparitor(TextComparitor.ENDS_WITH, "/"), NewsSites::EL_ESPECTADOR_LINKS_GETTER, ArticleGet.usual("article"), null /* bannerAndAdFinder */ ); /** * The News Site at address: <CODE><A HREF="https://www.gov.cn/" TARGET=_blank> * "https://www.gov.cn/"</A></CODE> has a Java-Script "Links Carousel". Essentially, there * is a section with "Showcased News Articles" that are intended to be emphasize anywhere * between four and eight primary articles. * * <BR /><BR />This Links-Carousel is wrapped in an HTML Divider Element as below: * {@code <DIV CLASS="slider-carousel">}. * * <BR /><BR />If this code were translated into an "XPath Query" or "CSS Selector", it would * read: <B>{@code div[class=slider-carousel] a}</B>. Specifically it says to find all * {@code 'Anchor'} elements that are descendants of {@code '<DIV CLASS="slider-carousel">'} * Elements. * * @see InnerTagGetInclusive#first(Vector, String, String, TextComparitor, String[]) * @see TagNodeGet#all(Vector, TC, String[]) * @see TagNode#AV(String) */ public static Vector<String> GOVCN_CAROUSEL_LINKS_GETTER(URL url, Vector<HTMLNode> page) { Vector<String> ret = new Vector<>(); String urlStr; // Find the first <DIV CLASS="slider-carousel"> ... </DIV> section Vector<HTMLNode> carouselDIV = InnerTagGetInclusive.first (page, "div", "class", TextComparitor.CN_CI, "slider-carousel"); // Retrieve any HTML Anchor <A HREF=...> ... </A> found within the contents of the // Divider. for (TagNode tn: TagNodeGet.all(carouselDIV, TC.OpeningTags, "a")) if ((urlStr = tn.AV("href")) != null) ret.add(urlStr); return ret; }; /** * This is the {@code NewsSite} definition for the Newspaper located at: * <CODE><A HREF="https://www.gov.cn/" TARGET=_blank> * https://www.gov.cn/</A></CODE>. * * <BR /><BR />The "Carousels" are just the emphasized or "HiLighted" links that are * on three separate pages. There is a complete-link {@code NewsSite} definition that * will retrieve all links - <I>not just the links hilited by the carousel.</I> * * <BR /><BR /><TABLE CLASS=JDBriefTable> * <TR><TH>Parameter</TH> <TH>Significance</TH></TR> * <TR><TD>Newspaper Name</TD> <TD>Chinese Government Web Portal</TD></TR> * <TR><TD>Country of Origin</TD> <TD>People's Republic of China</TD></TR> * <TR><TD>Website URL</TD> <TD>{@code https://gov.cn}</TD></TR> * <TR><TD>Newspaper Printing Language</TD> <TD>Mandarin Chinese</TD></TR> * </TABLE> * * <BR /><TABLE CLASS=NEWSSITE> * <TR><TH>Parameter</TH><TH>Purpose</TH><TH>Value</TH></TR> * <TR> <TD>Newspaper Article Groups / Sections</TD> * <TD>Scrape Sections</TD> * <TD><I>Retrieved from Data File</I></TD> * </TR> * <TR> <TD><B>{@link StrFilter}</B></TD> * <TD>News Web-Site Section-Page Aritlce-Link ({@code <A HREF=...>}) Filter</TD> * <TD>{@code HREF} must match: * {@code "^http://www.gov.cn/(?:.+?/)?\\d{4}-\\d{2}/\\d{2}/(?:.+?/)?content_\\d+.htm(?:l)?(#\\d+)?"} * </TD> * </TR> * <TR> <TD><B>{@link LinksGet}</B></TD> * <TD>Used to <B><I>manually</I></B> retrieve Article-Link {@code URL's}</TD> * <TD>Invokes method {@link #GOVCN_CAROUSEL_LINKS_GETTER(URL, Vector)}</TD> * </TR> * <TR> <TD><B>{@link ArticleGet}</B></TD> * <TD>Retrieves Article-Body Content from an Article-Link Web-Page</TD> * <TD>{@code <DIV CLASS="article ...">...</DIV>} * <BR />See: {@link ArticleGet#usual(TextComparitor, String[])} * <BR />See: {@link TextComparitor#C} * </TD> * </TR> * </TABLE> * * <BR />View a copy of the logs that are generated from using this {@code NewsSite}. * <BR /><BR /><UL CLASS=JDUL> * <LI> <CODE><B><A HREF='doc-files/Logs/GovCNCarousel-ScrapeURLs.html'> * Gov.CN Carousel ScrapeURLs LOG</A></B></CODE> * </LI> * <LI> <CODE><B><A HREF='doc-files/Logs/GovCNCarousel-ScrapeArticles.html'> * Gov.CN Carousel ScrapeArticles LOG</A></B></CODE> * </LI> * </UL> * * <EMBED CLASS='external-html' DATA-FILE-ID=NEWS_STE_CHANGE> */ public static final NewsSite GovCNCarousel = new NewsSite ( "Chinese Government Web Portal", Country.China, "https://gov.cn/", LC.ZH_CN, "The Chinese Government Sponsored Web-Site", newsPaperSections.get("GovCNCarousel"), StrFilter.regExKEEP(Pattern.compile( "^http://www.gov.cn/(?:.+?/)?\\d{4}-\\d{2}/\\d{2}/(?:.+?/)?" + "content_\\d+.htm(?:l)?(#\\d+)?" ), false), NewsSites::GOVCN_CAROUSEL_LINKS_GETTER, ArticleGet.usual(TextComparitor.C, "article"), null /* bannerAndAddFinder */ ); /** * This is the {@code NewsSite} definition for the Newspaper located at: * <CODE><A HREF="https://www.gov.cn/" TARGET=_blank> * https://www.gov.cn/</A></CODE>. * * <BR /><BR />This version of the "Gov.CN" website will scour a larger set of section * {@code URL's}, and will not limit the returned Article-Links to just those found on the * java-script carousel. The Java-Script Carousel will almost always have a total of five * news-article links available. This definition of {@code 'NewsSite'} may return up to * thirty to forty different articles per news-section. * * <BR /><BR /><TABLE CLASS=JDBriefTable> * <TR><TH>Parameter</TH> <TH>Significance</TH></TR> * <TR><TD>Newspaper Name</TD> <TD>Chinese Government Web Portal</TD></TR> * <TR><TD>Country of Origin</TD> <TD>People's Republic of China</TD></TR> * <TR><TD>Website URL</TD> <TD>{@code https://gov.cn}</TD></TR> * <TR><TD>Newspaper Printing Language</TD> <TD>Mandarin Chinese</TD></TR> * </TABLE> * * <BR /><TABLE CLASS=NEWSSITE> * <TR><TH>Parameter</TH><TH>Purpose</TH><TH>Value</TH></TR> * <TR> <TD>Newspaper Article Groups / Sections</TD> * <TD>Scrape Sections</TD> * <TD><I>Retrieved from Data File</I></TD> * </TR> * <TR> <TD><B>{@link StrFilter}</B></TD> * <TD>News Web-Site Section-Page Aritlce-Link ({@code <A HREF=...>}) Filter</TD> * <TD>{@code HREF} must match: * {@code "^http://www.gov.cn/(?:.+?/)?\\d{4}-\\d{2}/\\d{2}/(?:.+?/)?content_\\d+.htm(?:l)?(#\\d+)?"} * </TD> * </TR> * <TR> <TD><B>{@link LinksGet}</B></TD> * <TD>Used to <B><I>manually</I></B> retrieve Article-Link {@code URL's}</TD> * <TD><B>{@code null}</B>. Retrieves <B><I>all</I></B> Anchor-Links on a Section-Page. * Note that {@code URL's} must still pass the previous {@code StrFilter} (above) * in order to be parsed as {@link Article}'s. * </TD> * </TR> * <TR> <TD><B>{@link ArticleGet}</B></TD> * <TD>Retrieves Article-Body Content from an Article-Link Web-Page</TD> * <TD>{@code <DIV CLASS="article ...">...</DIV>} * <BR />See: {@link ArticleGet#usual(TextComparitor, String[])} * <BR />See: {@link TextComparitor#C} * </TD> * </TR> * </TABLE> * * <BR />View a copy of the logs that are generated from using this {@code NewsSite}. * <BR /><BR /><UL CLASS=JDUL> * <LI> <CODE><B><A HREF='doc-files/Logs/GovCN-ScrapeURLs.html'> * Gov.CN ScrapeURLs LOG</A></B></CODE> * </LI> * <LI> <CODE><B><A HREF='doc-files/Logs/GovCN-ScrapeArticles.html'> * Gov.CN ScrapeArticles LOG</A></B></CODE> * </LI> * </UL> * * <EMBED CLASS='external-html' DATA-FILE-ID=NEWS_STE_CHANGE> */ public static final NewsSite GovCN = new NewsSite ( "Chinese Government Web Portal", Country.China, "https://gov.cn/", LC.ZH_CN, "The Chinese Government Sponsored Web-Site", newsPaperSections.get("GovCN"), StrFilter.regExKEEP(Pattern.compile( "^http://www.gov.cn/(?:.+?/)?\\d{4}-\\d{2}/\\d{2}/(?:.+?/)?" + "content_\\d+.htm(?:l)?(#\\d+)?" ), false), null, ArticleGet.usual(TextComparitor.C, "article"), null /* bannerAndAddFinder */ ); } |