Magento 2是当前全球最 流行的电子商务系统，有着完善的销售策略和更强的安全机制，如果你没有使用它，赶快让它给你带来更大的利润吧。
接下来我我将为大家讲述如何在Magento 2中获取其他网站的信息，此篇教程仅供学习使用，禁止商业用途，禁止非法用途，在此声明。
如何使用Magento 2,他是什么？
有了解Magento 1的用户，对Magento 2并不陌生，如果你没有使用过Magento 1,不了解Magento 2不要紧张不必担心，Magento 2其实和Magento 1是完全不同的版本，里面的目录结构和代码的使用完成改变，采用了PHP7.0以上的版本，运行的Magento 2的系统中，性能方面比起Magento 1有了巨大的飞跃和更大的提升。你可以 直接学习Magento 2如果你是小白，你可以从Magento 2教程基础学习，如果安装Magento 2(麦进斗)，你可以点击这里，查看教程。
Magento2教程中使用代码采集网站信息
接下来我将为大家讲述如何在Magento 2中使用代码采集网站信息，我们首先需要创建Magento 2的模块，要知道Magento 2的开发都是以模块进行的开发，一个模块或者插件是一个大的主题功能，所以我们需要创建自己的模块。创建模块这里我就不再多讲，不知道如何创建的，请查看怎么在Magento 2中创建控制器controller
1.接下来创建好模块了我们就在controller里面引入我们需要的类，即使
| 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 | <?php /** * @WEBSITE https://www.sky8g.com */ namespace Sky8g\Hello\Controller\Test; use Sky8g\Hello\Helper\Data; class Index extends \Magento\Framework\App\Action\Action { protected $_coreRegistry; protected $_pageFactory; protected $_helper; protected $_storeManager; public function __construct( \Magento\Framework\App\Action\Context $context, \Magento\Framework\Registry $registry, \Magento\Store\Model\StoreManagerInterface $storeManager, Data $helper, \Magento\Framework\View\Result\PageFactory $pageFactory) { $this->_pageFactory = $pageFactory; $this->_coreRegistry = $registry; $this->_storeManager = $storeManager; $this->_helper = $helper; return parent::__construct($context); } public function execute() { $path = $this->getRoot().'/sky8g/simple_html_dom.php'; include($path); $webSite='https://你要采集的域名.com/page/1/'; $classAttr='page-numbers'; $imageType='jpg'; $arr = []; $firstPortHref = null; $siteUrl =[]; $aEleArr = file_get_html( $webSite )->find('a'); //find all link foreach($aEleArr as $e){ if( strpos ($e->class,$classAttr) !== false){ $href = trim( $e->href ,'/'); $lastPortHref = basename( $e->href ); if (is_numeric ($lastPortHref ) ) { $arr[] = $lastPortHref ; } } if( $e == end( $aEleArr ) ){ $firstPortHref = reset(explode( '1' , $webSite )); for ( $i = min($arr) - 1; $i <= max($arr); $i++) { $siteUrl[] = $firstPortHref.$i ; } } } foreach ( $siteUrl as $key => $value) { $html = file_get_html( $value ); foreach($html->find('div.single-photo-thumb a[rel="bookmark"]') as $e) { $downlaodAHtml = file_get_html( $e->href ); foreach ($downlaodAHtml -> find('a[title="Download the free photo"]') as $k => $v) { if( preg_match('/\.('.$imageType.')/', $v->href ) ){ //echo $v->href.'<br>';; $imgUrl = $v->href; $pathToFile = $this->getRoot().'/sky8g/test/picture'; $this->saveImage($imgUrl,$pathToFile,false); } } } } } protected function getRoot(){ return $this->_objectManager->get( \Magento\Framework\Filesystem\DirectoryList::class)->getRoot(); } protected function saveImage($imgUrl,$pathToFile,$isFile=true){ if ( !preg_match("/\.(jpg|png|gif|jpeg|css|js|mp3|wav|swf|mov|doc|pdf|xls|ppt|docx|pptx|xlsx|ico|woff|woff2|otf|svg|ttf)/", $imgUrl ) ) return false; $content = file_get_contents($imgUrl ); if ($content === false) return false; $fileName = basename($pathToFile); if($isFile){ $folders = explode('/', str_replace('/' . $fileName, '', $pathToFile)); }else{ $fileNewName = trim($pathToFile,"/")."/".basename($imgUrl); $folders = explode('/', $pathToFile); } $currentFolder = ''; foreach ($folders as $folder) { $currentFolder .= $folder . DIRECTORY_SEPARATOR; if (!file_exists($currentFolder)) { mkdir($currentFolder, 0755); } } if($isFile){ return file_put_contents($pathToFile , $content) ? true : false; }else{ $fileNewName = str_replace('域名','picture',$fileNewName); if(!is_file($fileNewName)){ return file_put_contents($fileNewName, $content) ? true : false; }else{ return false; } } } } |
2.第二步在你的根目录下创建sky8g目录，在目录sky8g下面创建simple_html_dom.php文件，把下面的代码写入文件里面
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 | <?php define('HDOM_TYPE_ELEMENT', 1); define('HDOM_TYPE_COMMENT', 2); define('HDOM_TYPE_TEXT', 3); define('HDOM_TYPE_ENDTAG', 4); define('HDOM_TYPE_ROOT', 5); define('HDOM_TYPE_UNKNOWN', 6); define('HDOM_QUOTE_DOUBLE', 0); define('HDOM_QUOTE_SINGLE', 1); define('HDOM_QUOTE_NO', 3); define('HDOM_INFO_BEGIN', 0); define('HDOM_INFO_END', 1); define('HDOM_INFO_QUOTE', 2); define('HDOM_INFO_SPACE', 3); define('HDOM_INFO_TEXT', 4); define('HDOM_INFO_INNER', 5); define('HDOM_INFO_OUTER', 6); define('HDOM_INFO_ENDSPACE',7); define('DEFAULT_TARGET_CHARSET', 'UTF-8'); define('DEFAULT_BR_TEXT', "\r\n"); define('DEFAULT_SPAN_TEXT', " "); define('MAX_FILE_SIZE', 600000); /** Contents between curly braces "{" and "}" are interpreted as text */ define('HDOM_SMARTY_AS_TEXT', 1); // helper functions // ----------------------------------------------------------------------------- // get html dom from file // $maxlen is defined in the code as PHP_STREAM_COPY_ALL which is defined as -1. function file_get_html($url, $use_include_path = false, $context=null, $offset = 0, $maxLen=-1, $lowercase = true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) { // Ensure maximum length is greater than zero if($maxLen <= 0) { $maxLen = MAX_FILE_SIZE; } // We DO force the tags to be terminated. $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText); // For sourceforge users: uncomment the next line and comment the retrieve_url_contents line 2 lines down if it is not already done. $contents = file_get_contents($url, $use_include_path, $context, $offset, $maxLen); // Paperg - use our own mechanism for getting the contents as we want to control the timeout. //$contents = retrieve_url_contents($url); if (empty($contents) || strlen($contents) > $maxLen) { return false; } // The second parameter can force the selectors to all be lowercase. $dom->load($contents, $lowercase, $stripRN); return $dom; } // get html dom from string function str_get_html($str, $lowercase=true, $forceTagsClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) { $dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $stripRN, $defaultBRText, $defaultSpanText); if (empty($str) || strlen($str) > MAX_FILE_SIZE) { $dom->clear(); return false; } $dom->load($str, $lowercase, $stripRN); return $dom; } // dump html dom tree function dump_html_tree($node, $show_attr=true, $deep=0) { $node->dump($node); } /** * simple html dom node * PaperG - added ability for "find" routine to lowercase the value of the selector. * PaperG - added $tag_start to track the start position of the tag in the total byte index * * @package PlaceLocalInclude */ class simple_html_dom_node { /** * Node type * * Default is {@see HDOM_TYPE_TEXT} * * @var int */ public $nodetype = HDOM_TYPE_TEXT; /** * Tag name * * Default is 'text' * * @var string */ public $tag = 'text'; /** * List of attributes * * @var array */ public $attr = array(); /** * List of child node objects * * @var array */ public $children = array(); public $nodes = array(); /** * The parent node object * * @var object|null */ public $parent = null; // The "info" array - see HDOM_INFO_... for what each element contains. public $_ = array(); /** * Start position of the tag in the document * * @var int */ public $tag_start = 0; /** * The DOM object * * @var object|null */ private $dom = null; /** * Construct new node object * * Adds itself to the list of DOM Nodes {@see simple_html_dom::$nodes} */ function __construct($dom) { $this->dom = $dom; $dom->nodes[] = $this; } function __destruct() { $this->clear(); } function __toString() { return $this->outertext(); } // clean up memory due to php5 circular references memory leak... function clear() { $this->dom = null; $this->nodes = null; $this->parent = null; $this->children = null; } // dump node's tree function dump($show_attr=true, $deep=0) { $lead = str_repeat(' ', $deep); echo $lead.$this->tag; if ($show_attr && count($this->attr)>0) { echo '('; foreach ($this->attr as $k=>$v) echo "[$k]=>\"".$this->$k.'", '; echo ')'; } echo "\n"; if ($this->nodes) { foreach ($this->nodes as $c) { $c->dump($show_attr, $deep+1); } } } // Debugging function to dump a single dom node with a bunch of information about it. function dump_node($echo=true) { $string = $this->tag; if (count($this->attr)>0) { $string .= '('; foreach ($this->attr as $k=>$v) { $string .= "[$k]=>\"".$this->$k.'", '; } $string .= ')'; } if (count($this->_)>0) { $string .= ' $_ ('; foreach ($this->_ as $k=>$v) { if (is_array($v)) { $string .= "[$k]=>("; foreach ($v as $k2=>$v2) { $string .= "[$k2]=>\"".$v2.'", '; } $string .= ")"; } else { $string .= "[$k]=>\"".$v.'", '; } } $string .= ")"; } if (isset($this->text)) { $string .= " text: (" . $this->text . ")"; } $string .= " HDOM_INNER_INFO: '"; if (isset($node->_[HDOM_INFO_INNER])) { $string .= $node->_[HDOM_INFO_INNER] . "'"; } else { $string .= ' NULL '; } $string .= " children: " . count($this->children); $string .= " nodes: " . count($this->nodes); $string .= " tag_start: " . $this->tag_start; $string .= "\n"; if ($echo) { echo $string; return; } else { return $string; } } /** * Return or set parent node * * @param object|null $parent (optional) The parent node, `null` to return * the current parent node. * @return object|null The parent node */ function parent($parent=null) { // I am SURE that this doesn't work properly. // It fails to unset the current node from it's current parents nodes or children list first. if ($parent !== null) { $this->parent = $parent; $this->parent->nodes[] = $this; $this->parent->children[] = $this; } return $this->parent; } /** * @return bool True if the node has at least one child node */ function has_child() { return !empty($this->children); } /** * Get child node at specified index * * @param int $idx The index of the child node to return, `-1` to return all * child nodes. * @return object|array|null The child node at the specified index, all child * nodes or null if the index is invalid. */ function children($idx=-1) { if ($idx===-1) { return $this->children; } if (isset($this->children[$idx])) { return $this->children[$idx]; } return null; } /** * Get first child node * * @return object|null The first child node or null if the current node has * no child nodes. * * @todo Use `empty()` instead of `count()` to improve performance on large * arrays. */ function first_child() { if (count($this->children)>0) { return $this->children[0]; } return null; } /** * Get last child node * * @return object|null The last child node or null if the current node has * no child nodes. * * @todo Use `end()` to slightly improve performance on large arrays. */ function last_child() { if (($count=count($this->children))>0) { return $this->children[$count-1]; } return null; } /** * Get next sibling node * * @return object|null The sibling node or null if the current node has no * sibling nodes. */ function next_sibling() { if ($this->parent===null) { return null; } $idx = 0; $count = count($this->parent->children); while ($idx<$count && $this!==$this->parent->children[$idx]) { ++$idx; } if (++$idx>=$count) { return null; } return $this->parent->children[$idx]; } /** * Get previous sibling node * * @return object|null The sibling node or null if the current node has no * sibling nodes. */ function prev_sibling() { if ($this->parent===null) return null; $idx = 0; $count = count($this->parent->children); while ($idx<$count && $this!==$this->parent->children[$idx]) ++$idx; if (--$idx<0) return null; return $this->parent->children[$idx]; } /** * Traverse ancestors to the first matching tag. * * @param string $tag Tag to find * @return object|null First matching node in the DOM tree or null if no * match was found. * * @todo Null is returned implicitly by calling ->parent on the root node. * This behaviour could change at any time, rendering this function invalid. */ function find_ancestor_tag($tag) { global $debug_object; if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } // Start by including ourselves in the comparison. $returnDom = $this; while (!is_null($returnDom)) { if (is_object($debug_object)) { $debug_object->debug_log(2, "Current tag is: " . $returnDom->tag); } if ($returnDom->tag == $tag) { break; } $returnDom = $returnDom->parent; } return $returnDom; } /** * Get node's inner text (everything inside the opening and closing tags) * * @return string */ function innertext() { if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); $ret = ''; foreach ($this->nodes as $n) $ret .= $n->outertext(); return $ret; } /** * Get node's outer text (everything including the opening and closing tags) * * @return string */ function outertext() { global $debug_object; if (is_object($debug_object)) { $text = ''; if ($this->tag == 'text') { if (!empty($this->text)) { $text = " with text: " . $this->text; } } $debug_object->debug_log(1, 'Innertext of tag: ' . $this->tag . $text); } if ($this->tag==='root') return $this->innertext(); // trigger callback if ($this->dom && $this->dom->callback!==null) { call_user_func_array($this->dom->callback, array($this)); } if (isset($this->_[HDOM_INFO_OUTER])) return $this->_[HDOM_INFO_OUTER]; if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); // render begin tag if ($this->dom && $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]) { $ret = $this->dom->nodes[$this->_[HDOM_INFO_BEGIN]]->makeup(); } else { $ret = ""; } // render inner text if (isset($this->_[HDOM_INFO_INNER])) { // If it's a br tag... don't return the HDOM_INNER_INFO that we may or may not have added. if ($this->tag != "br") { $ret .= $this->_[HDOM_INFO_INNER]; } } else { if ($this->nodes) { foreach ($this->nodes as $n) { $ret .= $this->convert_text($n->outertext()); } } } // render end tag if (isset($this->_[HDOM_INFO_END]) && $this->_[HDOM_INFO_END]!=0) $ret .= '</'.$this->tag.'>'; return $ret; } /** * Get node's plain text (everything excluding all tags) * * @return string */ function text() { if (isset($this->_[HDOM_INFO_INNER])) return $this->_[HDOM_INFO_INNER]; switch ($this->nodetype) { case HDOM_TYPE_TEXT: return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); case HDOM_TYPE_COMMENT: return ''; case HDOM_TYPE_UNKNOWN: return ''; } if (strcasecmp($this->tag, 'script')===0) return ''; if (strcasecmp($this->tag, 'style')===0) return ''; $ret = ''; // In rare cases, (always node type 1 or HDOM_TYPE_ELEMENT - observed for some span tags, and some p tags) $this->nodes is set to NULL. // NOTE: This indicates that there is a problem where it's set to NULL without a clear happening. // WHY is this happening? if (!is_null($this->nodes)) { foreach ($this->nodes as $n) { // Start paragraph after a blank line if ($n->tag == 'p') { $ret .= "\n\n"; } $ret .= $this->convert_text($n->text()); // If this node is a span... add a space at the end of it so multiple spans don't run into each other. This is plaintext after all. if ($n->tag == "span") { $ret .= $this->dom->default_span_text; } } } return trim($ret); } /** * Get node's xml text (inner text as a CDATA section) * * @return string */ function xmltext() { $ret = $this->innertext(); $ret = str_ireplace('<![CDATA[', '', $ret); $ret = str_replace(']]>', '', $ret); return $ret; } // build node's text with tag function makeup() { // text, comment, unknown if (isset($this->_[HDOM_INFO_TEXT])) return $this->dom->restore_noise($this->_[HDOM_INFO_TEXT]); $ret = '<'.$this->tag; $i = -1; foreach ($this->attr as $key=>$val) { ++$i; // skip removed attribute if ($val===null || $val===false) continue; $ret .= $this->_[HDOM_INFO_SPACE][$i][0]; //no value attr: nowrap, checked selected... if ($val===true) $ret .= $key; else { switch ($this->_[HDOM_INFO_QUOTE][$i]) { case HDOM_QUOTE_DOUBLE: $quote = '"'; break; case HDOM_QUOTE_SINGLE: $quote = '\''; break; default: $quote = ''; } $ret .= $key.$this->_[HDOM_INFO_SPACE][$i][1].'='.$this->_[HDOM_INFO_SPACE][$i][2].$quote.$val.$quote; } } $ret = $this->dom->restore_noise($ret); return $ret . $this->_[HDOM_INFO_ENDSPACE] . '>'; } // find elements by css selector //PaperG - added ability for find to lowercase the value of the selector. function find($selector, $idx=null, $lowercase=false) { $selectors = $this->parse_selector($selector); if (($count=count($selectors))===0) return array(); $found_keys = array(); // find each selector for ($c=0; $c<$count; ++$c) { // The change on the below line was documented on the sourceforge code tracker id 2788009 // used to be: if (($levle=count($selectors[0]))===0) return array(); if (($levle=count($selectors[$c]))===0) return array(); if (!isset($this->_[HDOM_INFO_BEGIN])) return array(); $head = array($this->_[HDOM_INFO_BEGIN]=>1); // handle descendant selectors, no recursive! for ($l=0; $l<$levle; ++$l) { $ret = array(); foreach ($head as $k=>$v) { $n = ($k===-1) ? $this->dom->root : $this->dom->nodes[$k]; //PaperG - Pass this optional parameter on to the seek function. $n->seek($selectors[$c][$l], $ret, $lowercase); } $head = $ret; } foreach ($head as $k=>$v) { if (!isset($found_keys[$k])) { $found_keys[$k] = 1; } } } // sort keys ksort($found_keys); $found = array(); foreach ($found_keys as $k=>$v) $found[] = $this->dom->nodes[$k]; // return nth-element or array if (is_null($idx)) return $found; else if ($idx<0) $idx = count($found) + $idx; return (isset($found[$idx])) ? $found[$idx] : null; } // seek for given conditions // PaperG - added parameter to allow for case insensitive testing of the value of a selector. protected function seek($selector, &$ret, $lowercase=false) { global $debug_object; if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } list($tag, $key, $val, $exp, $no_key) = $selector; // xpath index if ($tag && $key && is_numeric($key)) { $count = 0; foreach ($this->children as $c) { if ($tag==='*' || $tag===$c->tag) { if (++$count==$key) { $ret[$c->_[HDOM_INFO_BEGIN]] = 1; return; } } } return; } $end = (!empty($this->_[HDOM_INFO_END])) ? $this->_[HDOM_INFO_END] : 0; if ($end==0) { $parent = $this->parent; while (!isset($parent->_[HDOM_INFO_END]) && $parent!==null) { $end -= 1; $parent = $parent->parent; } $end += $parent->_[HDOM_INFO_END]; } for ($i=$this->_[HDOM_INFO_BEGIN]+1; $i<$end; ++$i) { $node = $this->dom->nodes[$i]; $pass = true; if ($tag==='*' && !$key) { if (in_array($node, $this->children, true)) $ret[$i] = 1; continue; } // compare tag if ($tag && $tag!=$node->tag && $tag!=='*') {$pass=false;} // compare key if ($pass && $key) { if ($no_key) { if (isset($node->attr[$key])) $pass=false; } else { if (($key != "plaintext") && !isset($node->attr[$key])) $pass=false; } } // compare value if ($pass && $key && $val && $val!=='*') { // If they have told us that this is a "plaintext" search then we want the plaintext of the node - right? if ($key == "plaintext") { // $node->plaintext actually returns $node->text(); $nodeKeyValue = $node->text(); } else { // this is a normal search, we want the value of that attribute of the tag. $nodeKeyValue = $node->attr[$key]; } if (is_object($debug_object)) {$debug_object->debug_log(2, "testing node: " . $node->tag . " for attribute: " . $key . $exp . $val . " where nodes value is: " . $nodeKeyValue);} //PaperG - If lowercase is set, do a case insensitive test of the value of the selector. if ($lowercase) { $check = $this->match($exp, strtolower($val), strtolower($nodeKeyValue)); } else { $check = $this->match($exp, $val, $nodeKeyValue); } if (is_object($debug_object)) {$debug_object->debug_log(2, "after match: " . ($check ? "true" : "false"));} // handle multiple class if (!$check && strcasecmp($key, 'class')===0) { foreach (explode(' ',$node->attr[$key]) as $k) { // Without this, there were cases where leading, trailing, or double spaces lead to our comparing blanks - bad form. if (!empty($k)) { if ($lowercase) { $check = $this->match($exp, strtolower($val), strtolower($k)); } else { $check = $this->match($exp, $val, $k); } if ($check) break; } } } if (!$check) $pass = false; } if ($pass) $ret[$i] = 1; unset($node); } // It's passed by reference so this is actually what this function returns. if (is_object($debug_object)) {$debug_object->debug_log(1, "EXIT - ret: ", $ret);} } protected function match($exp, $pattern, $value) { global $debug_object; if (is_object($debug_object)) {$debug_object->debug_log_entry(1);} switch ($exp) { case '=': return ($value===$pattern); case '!=': return ($value!==$pattern); case '^=': return preg_match("/^".preg_quote($pattern,'/')."/", $value); case '$=': return preg_match("/".preg_quote($pattern,'/')."$/", $value); case '*=': if ($pattern[0]=='/') { return preg_match($pattern, $value); } return preg_match("/".$pattern."/i", $value); } return false; } protected function parse_selector($selector_string) { global $debug_object; if (is_object($debug_object)) {$debug_object->debug_log_entry(1);} // pattern of CSS selectors, modified from mootools // Paperg: Add the colon to the attrbute, so that it properly finds <tag attr:ibute="something" > like google does. // Note: if you try to look at this attribute, yo MUST use getAttribute since $dom->x:y will fail the php syntax check. // Notice the \[ starting the attbute? and the @? following? This implies that an attribute can begin with an @ sign that is not captured. // This implies that an html attribute specifier may start with an @ sign that is NOT captured by the expression. // farther study is required to determine of this should be documented or removed. // $pattern = "/([\w-:\*]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; $pattern = "/([\w:\*-]*)(?:\#([\w-]+)|\.([\w-]+))?(?:\[@?(!?[\w:-]+)(?:([!*^$]?=)[\"']?(.*?)[\"']?)?\])?([\/, ]+)/is"; preg_match_all($pattern, trim($selector_string).' ', $matches, PREG_SET_ORDER); if (is_object($debug_object)) {$debug_object->debug_log(2, "Matches Array: ", $matches);} $selectors = array(); $result = array(); //print_r($matches); foreach ($matches as $m) { $m[0] = trim($m[0]); if ($m[0]==='' || $m[0]==='/' || $m[0]==='//') continue; // for browser generated xpath if ($m[1]==='tbody') continue; list($tag, $key, $val, $exp, $no_key) = array($m[1], null, null, '=', false); if (!empty($m[2])) {$key='id'; $val=$m[2];} if (!empty($m[3])) {$key='class'; $val=$m[3];} if (!empty($m[4])) {$key=$m[4];} if (!empty($m[5])) {$exp=$m[5];} if (!empty($m[6])) {$val=$m[6];} // convert to lowercase if ($this->dom->lowercase) {$tag=strtolower($tag); $key=strtolower($key);} //elements that do NOT have the specified attribute if (isset($key[0]) && $key[0]==='!') {$key=substr($key, 1); $no_key=true;} $result[] = array($tag, $key, $val, $exp, $no_key); if (trim($m[7])===',') { $selectors[] = $result; $result = array(); } } if (count($result)>0) $selectors[] = $result; return $selectors; } function __get($name) { if (isset($this->attr[$name])) { return $this->convert_text($this->attr[$name]); } switch ($name) { case 'outertext': return $this->outertext(); case 'innertext': return $this->innertext(); case 'plaintext': return $this->text(); case 'xmltext': return $this->xmltext(); default: return array_key_exists($name, $this->attr); } } function __set($name, $value) { global $debug_object; if (is_object($debug_object)) {$debug_object->debug_log_entry(1);} switch ($name) { case 'outertext': return $this->_[HDOM_INFO_OUTER] = $value; case 'innertext': if (isset($this->_[HDOM_INFO_TEXT])) return $this->_[HDOM_INFO_TEXT] = $value; return $this->_[HDOM_INFO_INNER] = $value; } if (!isset($this->attr[$name])) { $this->_[HDOM_INFO_SPACE][] = array(' ', '', ''); $this->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE; } $this->attr[$name] = $value; } function __isset($name) { switch ($name) { case 'outertext': return true; case 'innertext': return true; case 'plaintext': return true; } //no value attr: nowrap, checked selected... return (array_key_exists($name, $this->attr)) ? true : isset($this->attr[$name]); } function __unset($name) { if (isset($this->attr[$name])) unset($this->attr[$name]); } // PaperG - Function to convert the text from one character set to another if the two sets are not the same. function convert_text($text) { global $debug_object; if (is_object($debug_object)) {$debug_object->debug_log_entry(1);} $converted_text = $text; $sourceCharset = ""; $targetCharset = ""; if ($this->dom) { $sourceCharset = strtoupper($this->dom->_charset); $targetCharset = strtoupper($this->dom->_target_charset); } if (is_object($debug_object)) {$debug_object->debug_log(3, "source charset: " . $sourceCharset . " target charaset: " . $targetCharset);} if (!empty($sourceCharset) && !empty($targetCharset) && (strcasecmp($sourceCharset, $targetCharset) != 0)) { // Check if the reported encoding could have been incorrect and the text is actually already UTF-8 if ((strcasecmp($targetCharset, 'UTF-8') == 0) && ($this->is_utf8($text))) { $converted_text = $text; } else { $converted_text = iconv($sourceCharset, $targetCharset, $text); } } // Lets make sure that we don't have that silly BOM issue with any of the utf-8 text we output. if ($targetCharset == 'UTF-8') { if (substr($converted_text, 0, 3) == "\xef\xbb\xbf") { $converted_text = substr($converted_text, 3); } if (substr($converted_text, -3) == "\xef\xbb\xbf") { $converted_text = substr($converted_text, 0, -3); } } return $converted_text; } /** * Returns true if $string is valid UTF-8 and false otherwise. * * @param mixed $str String to be tested * @return boolean */ static function is_utf8($str) { $c=0; $b=0; $bits=0; $len=strlen($str); for($i=0; $i<$len; $i++) { $c=ord($str[$i]); if($c > 128) { if(($c >= 254)) return false; elseif($c >= 252) $bits=6; elseif($c >= 248) $bits=5; elseif($c >= 240) $bits=4; elseif($c >= 224) $bits=3; elseif($c >= 192) $bits=2; else return false; if(($i+$bits) > $len) return false; while($bits > 1) { $i++; $b=ord($str[$i]); if($b < 128 || $b > 191) return false; $bits--; } } } return true; } /* function is_utf8($string) { //this is buggy return (utf8_encode(utf8_decode($string)) == $string); } */ /** * Function to try a few tricks to determine the displayed size of an img on the page. * NOTE: This will ONLY work on an IMG tag. Returns FALSE on all other tag types. * * @author John Schlick * @version April 19 2012 * @return array an array containing the 'height' and 'width' of the image on the page or -1 if we can't figure it out. */ function get_display_size() { global $debug_object; $width = -1; $height = -1; if ($this->tag !== 'img') { return false; } // See if there is aheight or width attribute in the tag itself. if (isset($this->attr['width'])) { $width = $this->attr['width']; } if (isset($this->attr['height'])) { $height = $this->attr['height']; } // Now look for an inline style. if (isset($this->attr['style'])) { // Thanks to user gnarf from stackoverflow for this regular expression. $attributes = array(); preg_match_all("/([\w-]+)\s*:\s*([^;]+)\s*;?/", $this->attr['style'], $matches, PREG_SET_ORDER); foreach ($matches as $match) { $attributes[$match[1]] = $match[2]; } // If there is a width in the style attributes: if (isset($attributes['width']) && $width == -1) { // check that the last two characters are px (pixels) if (strtolower(substr($attributes['width'], -2)) == 'px') { $proposed_width = substr($attributes['width'], 0, -2); // Now make sure that it's an integer and not something stupid. if (filter_var($proposed_width, FILTER_VALIDATE_INT)) { $width = $proposed_width; } } } // If there is a width in the style attributes: if (isset($attributes['height']) && $height == -1) { // check that the last two characters are px (pixels) if (strtolower(substr($attributes['height'], -2)) == 'px') { $proposed_height = substr($attributes['height'], 0, -2); // Now make sure that it's an integer and not something stupid. if (filter_var($proposed_height, FILTER_VALIDATE_INT)) { $height = $proposed_height; } } } } // Future enhancement: // Look in the tag to see if there is a class or id specified that has a height or width attribute to it. // Far future enhancement // Look at all the parent tags of this image to see if they specify a class or id that has an img selector that specifies a height or width // Note that in this case, the class or id will have the img subselector for it to apply to the image. // ridiculously far future development // If the class or id is specified in a SEPARATE css file thats not on the page, go get it and do what we were just doing for the ones on the page. $result = array('height' => $height, 'width' => $width); return $result; } // camel naming conventions function getAllAttributes() {return $this->attr;} function getAttribute($name) {return $this->__get($name);} function setAttribute($name, $value) {$this->__set($name, $value);} function hasAttribute($name) {return $this->__isset($name);} function removeAttribute($name) {$this->__set($name, null);} function getElementById($id) {return $this->find("#$id", 0);} function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);} function getElementByTagName($name) {return $this->find($name, 0);} function getElementsByTagName($name, $idx=null) {return $this->find($name, $idx);} function parentNode() {return $this->parent();} function childNodes($idx=-1) {return $this->children($idx);} function firstChild() {return $this->first_child();} function lastChild() {return $this->last_child();} function nextSibling() {return $this->next_sibling();} function previousSibling() {return $this->prev_sibling();} function hasChildNodes() {return $this->has_child();} function nodeName() {return $this->tag;} function appendChild($node) {$node->parent($this); return $node;} } /** * simple html dom parser * Paperg - in the find routine: allow us to specify that we want case insensitive testing of the value of the selector. * Paperg - change $size from protected to public so we can easily access it * Paperg - added ForceTagsClosed in the constructor which tells us whether we trust the html or not. Default is to NOT trust it. * * @package PlaceLocalInclude */ class simple_html_dom { /** * The root node of the document * * @var object */ public $root = null; /** * List of nodes in the current DOM * * @var array */ public $nodes = array(); /** * Callback function to run for each element in the DOM. * * @var callable|null */ public $callback = null; /** * Indicates how tags and attributes are matched * * @var bool When set to **true** tags and attributes will be converted to * lowercase before matching. */ public $lowercase = false; /** * Original document size * * Holds the original document size. * * @var int */ public $original_size; /** * Current document size * * Holds the current document size. The document size is determined by the * string length of ({@see simple_html_dom::$doc}). * * _Note_: Using this variable is more efficient than calling `strlen($doc)` * * @var int * */ public $size; /** * Current position in the document * * @var int */ protected $pos; /** * The document * * @var string */ protected $doc; /** * Current character * * Holds the current character at position {@see simple_html_dom::$pos} in * the document {@see simple_html_dom::$doc} * * _Note_: Using this variable is more efficient than calling `substr($doc, $pos, 1)` * * @var string */ protected $char; protected $cursor; /** * Parent node of the next node detected by the parser * * @var object */ protected $parent; protected $noise = array(); /** * Tokens considered blank in HTML * * @var string */ protected $token_blank = " \t\r\n"; /** * Tokens to identify the equal sign for attributes, stopping either at the * closing tag ("/" i.e. "<html />") or the end of an opening tag (">" i.e. * "<html>") * * @var string */ protected $token_equal = ' =/>'; /** * Tokens to identify the end of a tag name. A tag name either ends on the * ending slash ("/" i.e. "<html/>") or whitespace ("\s\r\n\t") * * @var string */ protected $token_slash = " />\r\n\t"; /** * Tokens to identify the end of an attribute * * @var string */ protected $token_attr = ' >'; // Note that this is referenced by a child node, and so it needs to be public for that node to see this information. public $_charset = ''; public $_target_charset = ''; /** * Innertext for <br> elements * * @var string */ protected $default_br_text = ""; /** * Suffix for <span> elements * * @var string */ public $default_span_text = ""; /** * Defines a list of self-closing tags (Void elements) according to the HTML * Specification * * _Remarks_: * - Use `isset()` instead of `in_array()` on array elements to boost * performance about 30% * - Sort elements by name for better readability! * * @link https://www.w3.org/TR/html HTML Specification * @link https://www.w3.org/TR/html/syntax.html#void-elements Void elements */ protected $self_closing_tags = array( 'area'=>1, 'base'=>1, 'br'=>1, 'col'=>1, 'embed'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'link'=>1, 'meta'=>1, 'param'=>1, 'source'=>1, 'track'=>1, 'wbr'=>1 ); /** * Defines a list of tags which - if closed - close all optional closing * elements within if they haven't been closed yet. (So, an element where * neither opening nor closing tag is omissible consistently closes every * optional closing element within) * * _Remarks_: * - Use `isset()` instead of `in_array()` on array elements to boost * performance about 30% * - Sort elements by name for better readability! */ protected $block_tags = array( 'body'=>1, 'div'=>1, 'form'=>1, 'root'=>1, 'span'=>1, 'table'=>1 ); /** * Defines elements whose end tag is omissible. * * * key = Name of an element whose end tag is omissible. * * value = Names of elements whose end tag is omissible, that are closed * by the current element. * * _Remarks_: * - Use `isset()` instead of `in_array()` on array elements to boost * performance about 30% * - Sort elements by name for better readability! * * **Example** * * An `li` element’s end tag may be omitted if the `li` element is immediately * followed by another `li` element. To do that, add following element to the * array: * * ```php * 'li' => array('li'), * ``` * * With this, the following two examples are considered equal. Note that the * second example is missing the closing tags on `li` elements. * * ```html * <ul><li>First Item</li><li>Second Item</li></ul> * ``` * * <ul><li>First Item</li><li>Second Item</li></ul> * * ```html * <ul><li>First Item<li>Second Item</ul> * ``` * * <ul><li>First Item<li>Second Item</ul> * * @var array A two-dimensional array where the key is the name of an * element whose end tag is omissible and the value is an array of elements * whose end tag is omissible, that are closed by the current element. * * @link https://www.w3.org/TR/html/syntax.html#optional-tags Optional tags * * @todo The implementation of optional closing tags doesn't work in all cases * because it only consideres elements who close other optional closing * tags, not taking into account that some (non-blocking) tags should close * these optional closing tags. For example, the end tag for "p" is omissible * and can be closed by an "address" element, whose end tag is NOT omissible. * Currently a "p" element without closing tag stops at the next "p" element * or blocking tag, even if it contains other elements. * * @todo Known sourceforge issue #2977341 * B tags that are not closed cause us to return everything to the end of * the document. */ protected $optional_closing_tags = array( 'b'=>array('b'=>1), // Not optional, see https://www.w3.org/TR/html/textlevel-semantics.html#the-b-element 'dd'=>array('dd'=>1, 'dt'=>1), 'dl'=>array('dd'=>1, 'dt'=>1), // Not optional, see https://www.w3.org/TR/html/grouping-content.html#the-dl-element 'dt'=>array('dd'=>1, 'dt'=>1), 'li'=>array('li'=>1), 'optgroup'=>array('optgroup'=>1, 'option'=>1), 'option'=>array('optgroup'=>1, 'option'=>1), 'p'=>array('p'=>1), 'rp'=>array('rp'=>1, 'rt'=>1), 'rt'=>array('rp'=>1, 'rt'=>1), 'td'=>array('td'=>1, 'th'=>1), 'th'=>array('td'=>1, 'th'=>1), 'tr'=>array('td'=>1, 'th'=>1, 'tr'=>1), ); function __construct($str=null, $lowercase=true, $forceTagsClosed=true, $target_charset=DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT, $options=0) { if ($str) { if (preg_match("/^http:\/\//i",$str) || is_file($str)) { $this->load_file($str); } else { $this->load($str, $lowercase, $stripRN, $defaultBRText, $defaultSpanText, $options); } } // Forcing tags to be closed implies that we don't trust the html, but it can lead to parsing errors if we SHOULD trust the html. if (!$forceTagsClosed) { $this->optional_closing_array=array(); } $this->_target_charset = $target_charset; } function __destruct() { $this->clear(); } // load html from string function load($str, $lowercase=true, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT, $options=0) { global $debug_object; // prepare $this->prepare($str, $lowercase, $defaultBRText, $defaultSpanText); // Per sourceforge http://sourceforge.net/tracker/?func=detail&aid=2949097&group_id=218559&atid=1044037 // Script tags removal now preceeds style tag removal. // strip out <script> tags $this->remove_noise("'<\s*script[^>]*[^/]>(.*?)<\s*/\s*script\s*>'is"); $this->remove_noise("'<\s*script\s*>(.*?)<\s*/\s*script\s*>'is"); // strip out the \r \n's if we are told to. if ($stripRN) { $this->doc = str_replace("\r", " ", $this->doc); $this->doc = str_replace("\n", " ", $this->doc); // set the length of content since we have changed it. $this->size = strlen($this->doc); } // strip out cdata $this->remove_noise("'<!\[CDATA\[(.*?)\]\]>'is", true); // strip out comments $this->remove_noise("'<!--(.*?)-->'is"); // strip out <style> tags $this->remove_noise("'<\s*style[^>]*[^/]>(.*?)<\s*/\s*style\s*>'is"); $this->remove_noise("'<\s*style\s*>(.*?)<\s*/\s*style\s*>'is"); // strip out preformatted tags $this->remove_noise("'<\s*(?:code)[^>]*>(.*?)<\s*/\s*(?:code)\s*>'is"); // strip out server side scripts $this->remove_noise("'(<\?)(.*?)(\?>)'s", true); if($options & HDOM_SMARTY_AS_TEXT) { // Strip Smarty scripts $this->remove_noise("'(\{\w)(.*?)(\})'s", true); } // parsing $this->parse(); // end $this->root->_[HDOM_INFO_END] = $this->cursor; $this->parse_charset(); // make load function chainable return $this; } // load html from file function load_file() { $args = func_get_args(); if($doc = call_user_func_array('file_get_contents', $args) !== false) { $this->load($doc, true); } else { return false; } } /** * Set the callback function * * @param callable $function_name Callback function to run for each element * in the DOM. * @return void */ function set_callback($function_name) { $this->callback = $function_name; } /** * Remove callback function * * @return void */ function remove_callback() { $this->callback = null; } // save dom as string function save($filepath='') { $ret = $this->root->innertext(); if ($filepath!=='') file_put_contents($filepath, $ret, LOCK_EX); return $ret; } // find dom node by css selector // Paperg - allow us to specify that we want case insensitive testing of the value of the selector. function find($selector, $idx=null, $lowercase=false) { return $this->root->find($selector, $idx, $lowercase); } // clean up memory due to php5 circular references memory leak... function clear() { foreach ($this->nodes as $n) {$n->clear(); $n = null;} // This add next line is documented in the sourceforge repository. 2977248 as a fix for ongoing memory leaks that occur even with the use of clear. if (isset($this->children)) foreach ($this->children as $n) {$n->clear(); $n = null;} if (isset($this->parent)) {$this->parent->clear(); unset($this->parent);} if (isset($this->root)) {$this->root->clear(); unset($this->root);} unset($this->doc); unset($this->noise); } function dump($show_attr=true) { $this->root->dump($show_attr); } // prepare HTML data and init everything protected function prepare($str, $lowercase=true, $defaultBRText=DEFAULT_BR_TEXT, $defaultSpanText=DEFAULT_SPAN_TEXT) { $this->clear(); $this->doc = trim($str); $this->size = strlen($this->doc); $this->original_size = $this->size; // Save the original size of the html that we got in. It might be useful to someone. $this->pos = 0; $this->cursor = 1; $this->noise = array(); $this->nodes = array(); $this->lowercase = $lowercase; $this->default_br_text = $defaultBRText; $this->default_span_text = $defaultSpanText; $this->root = new simple_html_dom_node($this); $this->root->tag = 'root'; $this->root->_[HDOM_INFO_BEGIN] = -1; $this->root->nodetype = HDOM_TYPE_ROOT; $this->parent = $this->root; if ($this->size>0) $this->char = $this->doc[0]; } /** * Parse HTML content * * @return bool True on success */ protected function parse() { while (true) { // Read next tag if there is no text between current position and the // next opening tag. if (($s = $this->copy_until_char('<'))==='') { if($this->read_tag()) { continue; } else { return true; } } // Add a text node for text between tags $node = new simple_html_dom_node($this); ++$this->cursor; $node->_[HDOM_INFO_TEXT] = $s; $this->link_nodes($node, false); } } // PAPERG - dkchou - added this to try to identify the character set of the page we have just parsed so we know better how to spit it out later. // NOTE: IF you provide a routine called get_last_retrieve_url_contents_content_type which returns the CURLINFO_CONTENT_TYPE from the last curl_exec // (or the content_type header from the last transfer), we will parse THAT, and if a charset is specified, we will use it over any other mechanism. protected function parse_charset() { global $debug_object; $charset = null; if (function_exists('get_last_retrieve_url_contents_content_type')) { $contentTypeHeader = get_last_retrieve_url_contents_content_type(); $success = preg_match('/charset=(.+)/', $contentTypeHeader, $matches); if ($success) { $charset = $matches[1]; if (is_object($debug_object)) {$debug_object->debug_log(2, 'header content-type found charset of: ' . $charset);} } } if (empty($charset)) { $el = $this->root->find('meta[http-equiv=Content-Type]',0, true); if (!empty($el)) { $fullvalue = $el->content; if (is_object($debug_object)) {$debug_object->debug_log(2, 'meta content-type tag found' . $fullvalue);} if (!empty($fullvalue)) { $success = preg_match('/charset=(.+)/i', $fullvalue, $matches); if ($success) { $charset = $matches[1]; } else { // If there is a meta tag, and they don't specify the character set, research says that it's typically ISO-8859-1 if (is_object($debug_object)) {$debug_object->debug_log(2, 'meta content-type tag couldn\'t be parsed. using iso-8859 default.');} $charset = 'ISO-8859-1'; } } } } // If we couldn't find a charset above, then lets try to detect one based on the text we got... if (empty($charset)) { // Use this in case mb_detect_charset isn't installed/loaded on this machine. $charset = false; if (function_exists('mb_detect_encoding')) { // Have php try to detect the encoding from the text given to us. $charset = mb_detect_encoding($this->doc . "ascii", $encoding_list = array( "UTF-8", "CP1252" ) ); if (is_object($debug_object)) {$debug_object->debug_log(2, 'mb_detect found: ' . $charset);} } // and if this doesn't work... then we need to just wrongheadedly assume it's UTF-8 so that we can move on - cause this will usually give us most of what we need... if ($charset === false) { if (is_object($debug_object)) {$debug_object->debug_log(2, 'since mb_detect failed - using default of utf-8');} $charset = 'UTF-8'; } } // Since CP1252 is a superset, if we get one of it's subsets, we want it instead. if ((strtolower($charset) == strtolower('ISO-8859-1')) || (strtolower($charset) == strtolower('Latin1')) || (strtolower($charset) == strtolower('Latin-1'))) { if (is_object($debug_object)) {$debug_object->debug_log(2, 'replacing ' . $charset . ' with CP1252 as its a superset');} $charset = 'CP1252'; } if (is_object($debug_object)) {$debug_object->debug_log(1, 'EXIT - ' . $charset);} return $this->_charset = $charset; } /** * Parse tag from current document position. * * @return bool True if a tag was found, false otherwise */ protected function read_tag() { // Set end position if no further tags found if ($this->char!=='<') { $this->root->_[HDOM_INFO_END] = $this->cursor; return false; } $begin_tag_pos = $this->pos; $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next // end tag if ($this->char==='/') { $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next // Skip whitespace in end tags (i.e. in "</ html>") $this->skip($this->token_blank); $tag = $this->copy_until_char('>'); // Skip attributes in end tags if (($pos = strpos($tag, ' '))!==false) $tag = substr($tag, 0, $pos); $parent_lower = strtolower($this->parent->tag); $tag_lower = strtolower($tag); // The end tag is supposed to close the parent tag. Handle situations // when it doesn't if ($parent_lower!==$tag_lower) { // Parent tag does not have to be closed necessarily (optional closing tag) // Current tag is a block tag, so it may close an ancestor if (isset($this->optional_closing_tags[$parent_lower]) && isset($this->block_tags[$tag_lower])) { $this->parent->_[HDOM_INFO_END] = 0; $org_parent = $this->parent; // Traverse ancestors to find a matching opening tag // Stop at root node while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower) $this->parent = $this->parent->parent; // If we don't have a match add current tag as text node if (strtolower($this->parent->tag)!==$tag_lower) { $this->parent = $org_parent; // restore origonal parent if ($this->parent->parent) $this->parent = $this->parent->parent; $this->parent->_[HDOM_INFO_END] = $this->cursor; return $this->as_text_node($tag); } } // Grandparent exists and current tag is a block tag, so our parent doesn't have an end tag else if (($this->parent->parent) && isset($this->block_tags[$tag_lower])) { $this->parent->_[HDOM_INFO_END] = 0; // No end tag $org_parent = $this->parent; // Traverse ancestors to find a matching opening tag // Stop at root node while (($this->parent->parent) && strtolower($this->parent->tag)!==$tag_lower) $this->parent = $this->parent->parent; // If we don't have a match add current tag as text node if (strtolower($this->parent->tag)!==$tag_lower) { $this->parent = $org_parent; // restore origonal parent $this->parent->_[HDOM_INFO_END] = $this->cursor; return $this->as_text_node($tag); } } // Grandparent exists and current tag closes it else if (($this->parent->parent) && strtolower($this->parent->parent->tag)===$tag_lower) { $this->parent->_[HDOM_INFO_END] = 0; $this->parent = $this->parent->parent; } else // Random tag, add as text node return $this->as_text_node($tag); } // Set end position of parent tag to current cursor position $this->parent->_[HDOM_INFO_END] = $this->cursor; if ($this->parent->parent) $this->parent = $this->parent->parent; $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next return true; } // start tag $node = new simple_html_dom_node($this); $node->_[HDOM_INFO_BEGIN] = $this->cursor; ++$this->cursor; $tag = $this->copy_until($this->token_slash); // Get tag name $node->tag_start = $begin_tag_pos; // doctype, cdata & comments... // <!DOCTYPE html> // <![CDATA[ ... ]]> // <!-- Comment --> if (isset($tag[0]) && $tag[0]==='!') { $node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until_char('>'); if (isset($tag[2]) && $tag[1]==='-' && $tag[2]==='-') { // Comment ("<!--") $node->nodetype = HDOM_TYPE_COMMENT; $node->tag = 'comment'; } else { // Could be doctype or CDATA but we don't care $node->nodetype = HDOM_TYPE_UNKNOWN; $node->tag = 'unknown'; } if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>'; $this->link_nodes($node, true); $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next return true; } // The start tag cannot contain another start tag, if so add as text // i.e. "<<html>" if ($pos=strpos($tag, '<')!==false) { $tag = '<' . substr($tag, 0, -1); $node->_[HDOM_INFO_TEXT] = $tag; $this->link_nodes($node, false); $this->char = $this->doc[--$this->pos]; // prev return true; } // Handle invalid tag names (i.e. "<html#doc>") if (!preg_match("/^\w[\w:-]*$/", $tag)) { $node->_[HDOM_INFO_TEXT] = '<' . $tag . $this->copy_until('<>'); // Next char is the beginning of a new tag, don't touch it. if ($this->char==='<') { $this->link_nodes($node, false); return true; } // Next char closes current tag, add and be done with it. if ($this->char==='>') $node->_[HDOM_INFO_TEXT].='>'; $this->link_nodes($node, false); $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next return true; } // begin tag, add new node $node->nodetype = HDOM_TYPE_ELEMENT; $tag_lower = strtolower($tag); $node->tag = ($this->lowercase) ? $tag_lower : $tag; // handle optional closing tags if (isset($this->optional_closing_tags[$tag_lower]) ) { // Traverse ancestors to close all optional closing tags while (isset($this->optional_closing_tags[$tag_lower][strtolower($this->parent->tag)])) { $this->parent->_[HDOM_INFO_END] = 0; $this->parent = $this->parent->parent; } $node->parent = $this->parent; } $guard = 0; // prevent infinity loop $space = array($this->copy_skip($this->token_blank), '', ''); // [0] Space between tag and first attribute // attributes do { // Everything until the first equal sign should be the attribute name $name = $this->copy_until($this->token_equal); if ($name==='' && $this->char!==null && $space[0]==='') { break; } if ($guard===$this->pos) // Escape infinite loop { $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next continue; } $guard = $this->pos; // handle endless '<' if ($this->pos>=$this->size-1 && $this->char!=='>') { // Out of bounds before the tag ended $node->nodetype = HDOM_TYPE_TEXT; $node->_[HDOM_INFO_END] = 0; $node->_[HDOM_INFO_TEXT] = '<'.$tag . $space[0] . $name; $node->tag = 'text'; $this->link_nodes($node, false); return true; } // handle mismatch '<' if ($this->doc[$this->pos-1]=='<') { // Attributes cannot start after opening tag $node->nodetype = HDOM_TYPE_TEXT; $node->tag = 'text'; $node->attr = array(); $node->_[HDOM_INFO_END] = 0; $node->_[HDOM_INFO_TEXT] = substr($this->doc, $begin_tag_pos, $this->pos-$begin_tag_pos-1); $this->pos -= 2; $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next $this->link_nodes($node, false); return true; } if ($name!=='/' && $name!=='') { // this is a attribute name $space[1] = $this->copy_skip($this->token_blank); // [1] Whitespace after attribute name $name = $this->restore_noise($name); // might be a noisy name if ($this->lowercase) $name = strtolower($name); if ($this->char==='=') { // attribute with value $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next $this->parse_attr($node, $name, $space); // get attribute value } else { //no value attr: nowrap, checked selected... $node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO; $node->attr[$name] = true; if ($this->char!='>') $this->char = $this->doc[--$this->pos]; // prev } $node->_[HDOM_INFO_SPACE][] = $space; $space = array($this->copy_skip($this->token_blank), '', ''); // prepare for next attribute } else // no more attributes break; } while ($this->char!=='>' && $this->char!=='/'); // go until the tag ended $this->link_nodes($node, true); $node->_[HDOM_INFO_ENDSPACE] = $space[0]; // handle empty tags (i.e. "<div/>") if ($this->copy_until_char('>')==='/') { $node->_[HDOM_INFO_ENDSPACE] .= '/'; $node->_[HDOM_INFO_END] = 0; } else { // reset parent if (!isset($this->self_closing_tags[strtolower($node->tag)])) $this->parent = $node; } $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next // If it's a BR tag, we need to set it's text to the default text. // This way when we see it in plaintext, we can generate formatting that the user wants. // since a br tag never has sub nodes, this works well. if ($node->tag == "br") { $node->_[HDOM_INFO_INNER] = $this->default_br_text; } return true; } /** * Parse attribute from current document position * * @param object $node Node for the attributes * @param string $name Name of the current attribute * @param array $space Array for spacing information * @return void */ protected function parse_attr($node, $name, &$space) { // Per sourceforge: http://sourceforge.net/tracker/?func=detail&aid=3061408&group_id=218559&atid=1044037 // If the attribute is already defined inside a tag, only pay attention to the first one as opposed to the last one. // https://stackoverflow.com/a/26341866 if (isset($node->attr[$name])) { return; } $space[2] = $this->copy_skip($this->token_blank); // [2] Whitespace between "=" and the value switch ($this->char) { case '"': // value is anything between double quotes $node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_DOUBLE; $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next $node->attr[$name] = $this->restore_noise($this->copy_until_char('"')); $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next break; case '\'': // value is anything between single quotes $node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_SINGLE; $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next $node->attr[$name] = $this->restore_noise($this->copy_until_char('\'')); $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next break; default: // value is anything until the first space or end tag $node->_[HDOM_INFO_QUOTE][] = HDOM_QUOTE_NO; $node->attr[$name] = $this->restore_noise($this->copy_until($this->token_attr)); } // PaperG: Attributes should not have \r or \n in them, that counts as html whitespace. $node->attr[$name] = str_replace("\r", "", $node->attr[$name]); $node->attr[$name] = str_replace("\n", "", $node->attr[$name]); // PaperG: If this is a "class" selector, lets get rid of the preceeding and trailing space since some people leave it in the multi class case. if ($name == "class") { $node->attr[$name] = trim($node->attr[$name]); } } /** * Link node to parent node * * @param object $node Node to link to parent * @param bool $is_child True if the node is a child of parent * @return void */ // link node's parent protected function link_nodes(&$node, $is_child) { $node->parent = $this->parent; $this->parent->nodes[] = $node; if ($is_child) { $this->parent->children[] = $node; } } /** * Add tag as text node to current node * * @param string $tag Tag name * @return bool True on success */ protected function as_text_node($tag) { $node = new simple_html_dom_node($this); ++$this->cursor; $node->_[HDOM_INFO_TEXT] = '</' . $tag . '>'; $this->link_nodes($node, false); $this->char = (++$this->pos<$this->size) ? $this->doc[$this->pos] : null; // next return true; } /** * Seek from the current document position to the first occurrence of a * character not defined by the provided string. Update the current document * position to the new position. * * @param string $chars A string containing every allowed character. * @return void */ protected function skip($chars) { $this->pos += strspn($this->doc, $chars, $this->pos); $this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next } /** * Copy substring from the current document position to the first occurrence * of a character not defined by the provided string. * * @param string $chars A string containing every allowed character. * @return string Substring from the current document position to the first * occurrence of a character not defined by the provided string. */ protected function copy_skip($chars) { $pos = $this->pos; $len = strspn($this->doc, $chars, $pos); $this->pos += $len; $this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next if ($len===0) return ''; return substr($this->doc, $pos, $len); } /** * Copy substring from the current document position to the first occurrence * of any of the provided characters. * * @param string $chars A string containing every character to stop at. * @return string Substring from the current document position to the first * occurrence of any of the provided characters. */ protected function copy_until($chars) { $pos = $this->pos; $len = strcspn($this->doc, $chars, $pos); $this->pos += $len; $this->char = ($this->pos<$this->size) ? $this->doc[$this->pos] : null; // next return substr($this->doc, $pos, $len); } /** * Copy substring from the current document position to the first occurrence * of the provided string. * * @param string $char The string to stop at. * @return string Substring from the current document position to the first * occurrence of the provided string. */ protected function copy_until_char($char) { if ($this->char===null) return ''; if (($pos = strpos($this->doc, $char, $this->pos))===false) { $ret = substr($this->doc, $this->pos, $this->size-$this->pos); $this->char = null; $this->pos = $this->size; return $ret; } if ($pos===$this->pos) return ''; $pos_old = $this->pos; $this->char = $this->doc[$pos]; $this->pos = $pos; return substr($this->doc, $pos_old, $pos-$pos_old); } /** * Remove noise from HTML content * * Noise is stored to {@see simple_html_dom::$noise} * * @param string $pattern The regex pattern used for finding noise * @param bool $remove_tag True to remove the entire match. Default is false * to only remove the captured data. */ protected function remove_noise($pattern, $remove_tag=false) { global $debug_object; if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } $count = preg_match_all($pattern, $this->doc, $matches, PREG_SET_ORDER|PREG_OFFSET_CAPTURE); for ($i=$count-1; $i>-1; --$i) { $key = '___noise___'.sprintf('% 5d', count($this->noise)+1000); if (is_object($debug_object)) { $debug_object->debug_log(2, 'key is: ' . $key); } $idx = ($remove_tag) ? 0 : 1; // 0 = entire match, 1 = submatch $this->noise[$key] = $matches[$i][$idx][0]; $this->doc = substr_replace($this->doc, $key, $matches[$i][$idx][1], strlen($matches[$i][$idx][0])); } // reset the length of content $this->size = strlen($this->doc); if ($this->size>0) { $this->char = $this->doc[0]; } } /** * Restore noise to HTML content * * Noise is restored from {@see simple_html_dom::$noise} * * @param string $text A subset of HTML containing noise * @return string The same content with noise restored */ function restore_noise($text) { global $debug_object; if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } while (($pos=strpos($text, '___noise___'))!==false) { // Sometimes there is a broken piece of markup, and we don't GET the pos+11 etc... token which indicates a problem outside of us... if (strlen($text) > $pos+15) { // todo: "___noise___1000" (or any number with four or more digits) in the DOM causes an infinite loop which could be utilized by malicious software $key = '___noise___'.$text[$pos+11].$text[$pos+12].$text[$pos+13].$text[$pos+14].$text[$pos+15]; if (is_object($debug_object)) { $debug_object->debug_log(2, 'located key of: ' . $key); } if (isset($this->noise[$key])) { $text = substr($text, 0, $pos).$this->noise[$key].substr($text, $pos+16); } else { // do this to prevent an infinite loop. $text = substr($text, 0, $pos).'UNDEFINED NOISE FOR KEY: '.$key . substr($text, $pos+16); } } else { // There is no valid key being given back to us... We must get rid of the ___noise___ or we will have a problem. $text = substr($text, 0, $pos).'NO NUMERIC NOISE KEY' . substr($text, $pos+11); } } return $text; } // Sometimes we NEED one of the noise elements. function search_noise($text) { global $debug_object; if (is_object($debug_object)) { $debug_object->debug_log_entry(1); } foreach($this->noise as $noiseElement) { if (strpos($noiseElement, $text)!==false) { return $noiseElement; } } } function __toString() { return $this->root->innertext(); } function __get($name) { switch ($name) { case 'outertext': return $this->root->innertext(); case 'innertext': return $this->root->innertext(); case 'plaintext': return $this->root->text(); case 'charset': return $this->_charset; case 'target_charset': return $this->_target_charset; } } // camel naming conventions function childNodes($idx=-1) {return $this->root->childNodes($idx);} function firstChild() {return $this->root->first_child();} function lastChild() {return $this->root->last_child();} function createElement($name, $value=null) {return @str_get_html("<$name>$value</$name>")->first_child();} function createTextNode($value) {return @end(str_get_html($value)->nodes);} function getElementById($id) {return $this->find("#$id", 0);} function getElementsById($id, $idx=null) {return $this->find("#$id", $idx);} function getElementByTagName($name) {return $this->find($name, 0);} function getElementsByTagName($name, $idx=-1) {return $this->find($name, $idx);} function loadFile() {$args = func_get_args();$this->load_file($args);} } ?> |
好了保存，访问你controller路由就能采集你想采集的网站了，本代码里面根据需要可以自行修改。请注意，不要非法用途。