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 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905
|
#--
# Copyright (c) 2005 Robert Aman
#
# Permission is hereby granted, free of charge, to any person obtaining
# a copy of this software and associated documentation files (the
# "Software"), to deal in the Software without restriction, including
# without limitation the rights to use, copy, modify, merge, publish,
# distribute, sublicense, and/or sell copies of the Software, and to
# permit persons to whom the Software is furnished to do so, subject to
# the following conditions:
#
# The above copyright notice and this permission notice shall be
# included in all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
#++
require 'rexml/document'
require 'feed_tools/feed_item'
require 'feed_tools/feed_structures'
require 'feed_tools/helpers/retrieval_helper'
require 'feed_tools/helpers/generic_helper'
require 'feed_tools/helpers/xml_helper'
require 'feed_tools/helpers/html_helper'
module FeedTools
# The <tt>FeedTools::Feed</tt> class represents a web feed's structure.
class Feed
# Initialize the feed object
def initialize
super
@cache_object = nil
@http_headers = nil
@xml_document = nil
@feed_data = nil
@feed_data_type = :xml
@root_node = nil
@channel_node = nil
@href = nil
@id = nil
@title = nil
@subtitle = nil
@link = nil
@last_retrieved = nil
@time_to_live = nil
@entries = nil
@live = false
@encoding = nil
@options = nil
@version = FeedTools::FEED_TOOLS_VERSION::STRING
end
# Breaks any references that the feed may be keeping around, thus making
# the job of the garbage collector much, much easier. Call this
# method prior to feeds going out of scope to prevent memory leaks.
def dispose()
self.entries.each do |entry|
entry.instance_variable_set("@root_node", nil)
entry.instance_variable_set("@feed", nil)
entry.instance_variable_set("@parent_feed", nil)
entry.dispose if entry.respond_to?(:dispose)
end
self.entries = []
@cache_object = nil
@http_headers = nil
@xml_document = nil
@feed_data = nil
@feed_data_type = nil
@root_node = nil
@channel_node = nil
@href = nil
@id = nil
@title = nil
@subtitle = nil
@link = nil
@last_retrieved = nil
@time_to_live = nil
@entries = nil
@live = false
@encoding = nil
@options = nil
GC.start()
self
end
# Loads the feed specified by the url, pulling the data from the
# cache if it hasn't expired. Options supplied will override the
# default options.
def Feed.open(href, options={})
FeedTools::GenericHelper.validate_options(
FeedTools.configurations.keys, options.keys)
# clean up the url
href = FeedTools::UriHelper.normalize_url(href)
feed_configurations = FeedTools.configurations.merge(options)
cache_object = nil
deserialized_feed = nil
if feed_configurations[:feed_cache] != nil && FeedTools.feed_cache.nil?
raise(ArgumentError, "There is currently no caching mechanism set. " +
"Cannot retrieve cached feeds.")
elsif feed_configurations[:serialization_enabled] == true
# We've got a caching mechanism available
cache_object = FeedTools.feed_cache.find_by_href(href)
begin
if cache_object != nil && cache_object.serialized != nil
# If we've got a cache hit, deserialize
expired = true
if cache_object.time_to_live == nil
cache_object.time_to_live =
feed_configurations[:default_ttl].to_i
cache_object.save
end
if (cache_object.last_retrieved == nil)
expired = true
elsif (cache_object.time_to_live < 30.minutes)
expired =
(cache_object.last_retrieved + 30.minutes) < Time.now.gmtime
else
expired =
(cache_object.last_retrieved + cache_object.time_to_live) <
Time.now.gmtime
end
if !expired
require 'yaml'
deserialized_feed = YAML.load(cache_object.serialized)
deserialized_feed.cache_object = cache_object
Thread.pass
end
end
rescue Exception
end
end
if deserialized_feed == nil
# create the new feed
feed = FeedTools::Feed.new
feed.configurations = feed_configurations
# load the new feed
feed.href = href
if cache_object != nil
feed.cache_object = cache_object
end
feed.update! unless feed.configurations[:disable_update_from_remote]
Thread.pass
return feed
else
return deserialized_feed
end
end
# Returns the load options for this feed.
def configurations
if @configurations.blank?
@configurations = FeedTools.configurations.dup
end
return @configurations
end
# Sets the load options for this feed.
def configurations=(new_configurations)
@configurations = new_configurations
end
# Loads the feed from the remote url if the feed has expired from the
# cache or cannot be retrieved from the cache for some reason.
def update!
# Don't do anything if this option is set
return if self.configurations[:disable_update_from_remote]
if !FeedTools.feed_cache.nil? &&
!FeedTools.feed_cache.set_up_correctly?
FeedTools.feed_cache.initialize_cache()
end
if !FeedTools.feed_cache.nil? &&
!FeedTools.feed_cache.set_up_correctly?
raise "Your feed cache system is incorrectly set up. " +
"Please see the documentation for more information."
end
if self.http_headers.blank? && !(self.cache_object.nil?) &&
!(self.cache_object.http_headers.nil?)
@http_headers = YAML.load(self.cache_object.http_headers)
@http_headers = {} unless @http_headers.kind_of? Hash
elsif self.http_headers.blank?
@http_headers = {}
end
if self.expired? == false
@live = false
else
load_remote_feed!
# Handle autodiscovery
if self.http_headers['content-type'] =~ /text\/html/ ||
self.http_headers['content-type'] =~ /application\/xhtml\+xml/
autodiscovered_url = nil
['atom', 'rss', 'rdf'].each do |type|
autodiscovered_url =
FeedTools::HtmlHelper.extract_link_by_mime_type(self.feed_data,
"application/#{type}+xml")
break unless autodiscovered_url.nil?
end
if autodiscovered_url != nil
begin
autodiscovered_url = FeedTools::UriHelper.resolve_relative_uri(
autodiscovered_url, [self.href])
rescue Exception
end
if self.href == autodiscovered_url
raise FeedAccessError,
"Autodiscovery loop detected: #{autodiscovered_url}"
end
self.feed_data = nil
self.href = autodiscovered_url
if FeedTools.feed_cache.nil?
self.cache_object = nil
else
self.cache_object =
FeedTools.feed_cache.find_by_href(autodiscovered_url)
end
self.update!
else
html_body = FeedTools::XmlHelper.try_xpaths(self.xml_document, [
"html/body"
])
if html_body != nil
raise FeedAccessError,
"#{self.href} does not appear to be a feed."
end
end
else
ugly_redirect = FeedTools::XmlHelper.try_xpaths(self.xml_document, [
"redirect/newLocation/text()"
], :select_result_value => true)
if !ugly_redirect.blank?
if self.href == ugly_redirect
raise FeedAccessError,
"Ugly redirect loop detected: #{ugly_redirect}"
end
self.feed_data = nil
self.href = ugly_redirect
if FeedTools.feed_cache.nil?
self.cache_object = nil
else
self.cache_object =
FeedTools.feed_cache.find_by_href(ugly_redirect)
end
self.update!
end
end
# Reset everything that needs to be reset.
@xml_document = nil
@encoding_from_feed_data = nil
@root_node = nil
@channel_node = nil
@id = nil
@title = nil
@subtitle = nil
@copyright = nil
@link = nil
@time_to_live = nil
@entries = nil
if self.configurations[:lazy_parsing_enabled] == false
self.full_parse()
end
end
end
# Attempts to load the feed from the remote location. Requires the url
# field to be set. If an etag or the last_modified date has been set,
# attempts to use them to prevent unnecessary reloading of identical
# content.
def load_remote_feed!
@live = true
if self.http_headers.nil? && !(self.cache_object.nil?) &&
!(self.cache_object.http_headers.nil?)
@http_headers = YAML.load(self.cache_object.http_headers)
end
if (self.href =~ /^feed:/) == 0
# Woah, Nelly, how'd that happen? You should've already been
# corrected. So let's fix that url. And please,
# just use less crappy browsers instead of badly defined
# pseudo-protocol hacks.
self.href = FeedTools::UriHelper.normalize_url(self.href)
end
# Find out what method we're going to be using to obtain this feed.
begin
uri = URI.parse(self.href)
rescue URI::InvalidURIError
raise FeedAccessError,
"Cannot retrieve feed using invalid URL: " + self.href.to_s
end
retrieval_method = "http"
case uri.scheme
when "http"
retrieval_method = "http"
when "ftp"
retrieval_method = "ftp"
when "file"
retrieval_method = "file"
when nil
raise FeedAccessError,
"No protocol was specified in the url."
else
raise FeedAccessError,
"Cannot retrieve feed using unrecognized protocol: " + uri.scheme
end
# No need for http headers unless we're actually doing http
if retrieval_method == "http"
begin
@http_response = (FeedTools::RetrievalHelper.http_get(
self.href, :feed_object => self) do |url, response|
# Find out if we've already seen the url we've been
# redirected to.
follow_redirect = true
begin
cached_feed = FeedTools::Feed.open(url,
:disable_update_from_remote => true)
if cached_feed.cache_object != nil &&
cached_feed.cache_object.new_record? != true
if !cached_feed.expired? &&
!cached_feed.http_headers.blank?
# Copy the cached state
self.href = cached_feed.href
@feed_data = cached_feed.feed_data
@feed_data_type = cached_feed.feed_data_type
if @feed_data.blank?
raise "Invalid cache data."
end
@title = nil; self.title
self.href
@link = nil; self.link
self.last_retrieved = cached_feed.last_retrieved
self.http_headers = cached_feed.http_headers
self.cache_object = cached_feed.cache_object
@live = false
follow_redirect = false
end
end
rescue
# If anything goes wrong, ignore it.
end
follow_redirect
end)
case @http_response
when Net::HTTPSuccess
@feed_data = self.http_response.body
@http_headers = {}
self.http_response.each_header do |key, value|
self.http_headers[key.downcase] = value
end
self.last_retrieved = Time.now.gmtime
@live = true
when Net::HTTPNotModified
@http_headers = {}
self.http_response.each_header do |key, value|
self.http_headers[key.downcase] = value
end
self.last_retrieved = Time.now.gmtime
@live = false
else
@live = false
end
rescue Exception => error
@live = false
if self.feed_data.nil?
raise error
end
end
elsif retrieval_method == "https"
# Not supported... yet
elsif retrieval_method == "ftp"
# Not supported... yet
# Technically, CDF feeds are supposed to be able to be accessed
# directly from an ftp server. This is silly, but we'll humor
# Microsoft.
#
# Eventually. If they're lucky. And someone demands it.
elsif retrieval_method == "file"
# Now that we've gone to all that trouble to ensure the url begins
# with 'file://', strip the 'file://' off the front of the url.
file_name = self.href.gsub(/^file:\/\//, "")
if RUBY_PLATFORM =~ /mswin/
file_name = file_name[1..-1] if file_name[0..0] == "/"
end
begin
open(file_name) do |file|
@http_response = nil
@http_headers = {}
@feed_data = file.read
@feed_data_type = :xml
self.last_retrieved = Time.now.gmtime
end
rescue
@live = false
# In this case, pulling from the cache is probably not going
# to help at all, and the use should probably be immediately
# appraised of the problem. Raise the exception.
raise
end
end
unless self.cache_object.nil?
begin
self.save
rescue
end
end
end
# Does a full parse of the feed.
def full_parse
self.href
self.cache_object
self.http_headers
self.encoding
self.feed_data_utf_8
self.xml_document
self.root_node
self.channel_node
self.base_uri
self.feed_type
self.feed_version
self.entries
self.id
self.title
self.subtitle
self.links
self.link
self.icon
self.favicon
self.author
self.publisher
self.time
self.updated
self.published
self.categories
self.images
self.rights
self.time_to_live
self.generator
self.language
self.docs
self.text_input
self.cloud
self.itunes_summary
self.itunes_subtitle
self.itunes_author
self.media_text
self.explicit?
self.entries.each do |entry|
entry.full_parse()
end
nil
end
# Does a full parse, then serializes the feed object directly to the
# cache.
def serialize_to_cache
@cache_object = nil
require 'yaml'
serialized_feed = YAML.dump(self.serializable)
if self.cache_object != nil
begin
self.cache_object.serialized = serialized_feed
self.cache_object.save
rescue Exception
end
end
return nil
end
# Returns a duplicate object suitable for serialization
def serializable
self.full_parse()
entries_to_dump = self.entries
# This prevents errors due to temporarily having feed items with
# multiple parent feeds.
self.entries = []
feed_to_dump = self.dup
feed_to_dump.instance_variable_set("@xml_document", nil)
feed_to_dump.instance_variable_set("@root_node", nil)
feed_to_dump.instance_variable_set("@channel_node", nil)
feed_to_dump.entries = entries_to_dump.collect do |entry|
entry.serializable
end
self.entries = entries_to_dump
feed_to_dump.entries.each do |entry|
entry.instance_variable_set("@root_node", nil)
end
return feed_to_dump
end
# Returns the relevant information from an http request.
def http_response
return @http_response
end
# Returns a hash of the http headers from the response.
def http_headers
if @http_headers.blank?
if !self.cache_object.nil? && !self.cache_object.http_headers.nil?
@http_headers = YAML.load(self.cache_object.http_headers)
@http_headers = {} unless @http_headers.kind_of? Hash
else
@http_headers = {}
end
end
return @http_headers
end
# Returns the encoding that the feed was parsed with
def encoding
if @encoding.blank?
if !self.http_headers.blank?
if self.http_headers['content-type'] =~ /charset=([\w\d-]+)/
@encoding = $1.downcase
else
@encoding = self.encoding_from_feed_data
end
else
@encoding = self.encoding_from_feed_data
end
end
return @encoding
end
# Returns the encoding of feed calculated only from the xml data.
# I.e., the encoding we would come up with if we ignore RFC 3023.
def encoding_from_feed_data
if @encoding_from_feed_data.blank?
raw_data = self.feed_data
return nil if raw_data.nil?
encoding_from_xml_instruct =
raw_data.scan(
/^<\?xml [^>]*encoding="([^\"]*)"[^>]*\?>/
).flatten.first
unless encoding_from_xml_instruct.blank?
encoding_from_xml_instruct.downcase!
end
if encoding_from_xml_instruct.blank?
doc = REXML::Document.new(raw_data)
encoding_from_xml_instruct = doc.encoding.downcase
if encoding_from_xml_instruct == "utf-8"
# REXML has a tendency to report utf-8 overzealously, take with
# grain of salt
encoding_from_xml_instruct = nil
end
else
@encoding_from_feed_data = encoding_from_xml_instruct
end
if encoding_from_xml_instruct.blank?
sniff_table = {
"Lo\247\224" => "ebcdic-cp-us",
"<?xm" => "utf-8"
}
sniff = self.feed_data[0..3]
if sniff_table[sniff] != nil
@encoding_from_feed_data = sniff_table[sniff].downcase
end
else
@encoding_from_feed_data = encoding_from_xml_instruct
end
if @encoding_from_feed_data.blank?
# Safest assumption
@encoding_from_feed_data = "utf-8"
end
end
return @encoding_from_feed_data
end
# Returns the feed's raw data.
def feed_data
if @feed_data.nil?
unless self.cache_object.nil?
@feed_data = self.cache_object.feed_data
end
end
return @feed_data
end
# Sets the feed's data.
def feed_data=(new_feed_data)
for var in self.instance_variables
self.instance_variable_set(var, nil)
end
@http_headers = {}
@feed_data = new_feed_data
unless self.cache_object.nil?
self.cache_object.feed_data = new_feed_data
end
ugly_redirect = FeedTools::XmlHelper.try_xpaths(self.xml_document, [
"redirect/newLocation/text()"
], :select_result_value => true)
if !ugly_redirect.blank?
for var in self.instance_variables
self.instance_variable_set(var, nil)
end
@http_headers = {}
@feed_data = nil
self.href = ugly_redirect
if FeedTools.feed_cache.nil?
self.cache_object = nil
else
begin
self.cache_object =
FeedTools.feed_cache.find_by_href(ugly_redirect)
rescue RuntimeError => error
if error.message =~ /sorry, too many clients already/
warn("There are too many connections to the database open.")
end
raise error
end
end
self.update!
end
# Get these things parsed in the correct order to avoid the retardedly
# painful corecursion issues.
self.href
@links = nil
@link = nil
self.links
self.link
end
# Returns the feed's raw data as utf-8.
def feed_data_utf_8(force_encoding=nil)
if @feed_data_utf_8.nil?
raw_data = self.feed_data
if force_encoding.nil?
use_encoding = self.encoding
else
use_encoding = force_encoding
end
if use_encoding != "utf-8" && use_encoding != nil && raw_data != nil
begin
@feed_data_utf_8 =
Iconv.new('utf-8', use_encoding).iconv(raw_data)
rescue Exception => error
return raw_data
end
else
return self.feed_data
end
end
return @feed_data_utf_8
end
# Returns the data type of the feed
# Possible values:
# * :xml
# * :yaml
# * :text
def feed_data_type
if @feed_data_type.nil?
# Right now, nothing else is supported
@feed_data_type = :xml
end
return @feed_data_type
end
# Sets the feed's data type.
def feed_data_type=(new_feed_data_type)
@feed_data_type = new_feed_data_type
unless self.cache_object.nil?
self.cache_object.feed_data_type = new_feed_data_type
end
if self.feed_data_type != :xml
@xml_document = nil
end
end
# Returns a REXML Document of the feed_data
def xml_document
if @xml_document.nil?
return nil if self.feed_data.blank?
if self.feed_data_type != :xml
@xml_document = nil
else
begin
@xml_document = REXML::Document.new(self.feed_data_utf_8)
rescue Exception
# Something failed, attempt to repair the xml with html5lib.
begin
@xml_document = HTML5::XMLParser.parse(self.feed_data_utf_8)
rescue Exception
# Failed again, give up.
return nil
end
end
end
end
return @xml_document
end
# Returns the first node within the channel_node that matches the xpath
# query.
def find_node(xpath, select_result_value=false)
if self.feed_data_type != :xml
raise "The feed data type is not xml."
end
return FeedTools::XmlHelper.try_xpaths(self.channel_node, [xpath],
:select_result_value => select_result_value)
end
# Returns all nodes within the channel_node that match the xpath query.
def find_all_nodes(xpath, select_result_value=false)
if self.feed_data_type != :xml
raise "The feed data type is not xml."
end
return FeedTools::XmlHelper.try_xpaths_all(self.channel_node, [xpath],
:select_result_value => select_result_value)
end
# Returns the root node of the feed.
def root_node
if @root_node.nil?
# TODO: Fix this so that added content at the end of the file doesn't
# break this stuff.
# E.g.: http://smogzer.tripod.com/smog.rdf
# ===================================================================
begin
if self.xml_document.nil?
return nil
else
@root_node = self.xml_document.root
end
rescue Exception
return nil
end
end
return @root_node
end
# Returns the channel node of the feed.
def channel_node
if @channel_node.nil? && self.root_node != nil
@channel_node = FeedTools::XmlHelper.try_xpaths(self.root_node, [
"channel",
"CHANNEL",
"feedinfo",
"news"
])
if @channel_node == nil
@channel_node = self.root_node
end
end
return @channel_node
end
# The cache object that handles the feed persistence.
def cache_object
if !@href.nil? && @href =~ /^file:\/\//
return nil
end
unless FeedTools.feed_cache.nil?
if @cache_object.nil?
begin
if @href != nil
begin
@cache_object = FeedTools.feed_cache.find_by_href(@href)
rescue RuntimeError => error
if error.message =~ /sorry, too many clients already/
warn("There are too many connections to the database open.")
raise error
else
raise error
end
rescue => error
warn("The feed cache seems to be having trouble with the " +
"find_by_href method. This may cause unexpected results.")
raise error
end
end
if @cache_object.nil?
@cache_object = FeedTools.feed_cache.new
end
rescue
end
end
end
return @cache_object
end
# Sets the cache object for this feed.
#
# This can be any object, but it must accept the following messages:
# href
# href=
# title
# title=
# link
# link=
# feed_data
# feed_data=
# feed_data_type
# feed_data_type=
# etag
# etag=
# last_modified
# last_modified=
# save
def cache_object=(new_cache_object)
@cache_object = new_cache_object
end
# Returns the type of feed
# Possible values:
# "rss", "atom", "cdf", "!okay/news"
def feed_type
if @feed_type.nil?
if self.root_node.nil?
return nil
end
case self.root_node.name.downcase
when "feed"
@feed_type = "atom"
when "rdf:rdf"
@feed_type = "rss"
when "rdf"
@feed_type = "rss"
when "rss"
@feed_type = "rss"
when "channel"
if self.root_node.namespace == FEED_TOOLS_NAMESPACES['rss11']
@feed_type = "rss"
else
@feed_type = "cdf"
end
end
end
return @feed_type
end
# Sets the default feed type
def feed_type=(new_feed_type)
@feed_type = new_feed_type
end
# Returns the version number of the feed type.
# Intentionally does not differentiate between the Netscape and Userland
# versions of RSS 0.91.
def feed_version
if @feed_version.nil?
if self.root_node.nil?
return nil
end
version = nil
begin
version_string = FeedTools::XmlHelper.try_xpaths(self.root_node, [
"@version"
], :select_result_value => true)
unless version_string.nil?
version = version_string.to_f
end
rescue
end
version = nil if version == 0.0
default_namespace = FeedTools::XmlHelper.try_xpaths(self.root_node, [
"@xmlns"
], :select_result_value => true)
case self.feed_type
when "atom"
if default_namespace == FEED_TOOLS_NAMESPACES['atom10']
@feed_version = 1.0
elsif version != nil
@feed_version = version
elsif default_namespace == FEED_TOOLS_NAMESPACES['atom03']
@feed_version = 0.3
end
when "rss"
if default_namespace == FEED_TOOLS_NAMESPACES['rss09']
@feed_version = 0.9
elsif default_namespace == FEED_TOOLS_NAMESPACES['rss10']
@feed_version = 1.0
elsif default_namespace == FEED_TOOLS_NAMESPACES['rss11']
@feed_version = 1.1
elsif version != nil
case version
when 2.1
@feed_version = 2.0
when 2.01
@feed_version = 2.0
else
@feed_version = version
end
end
when "cdf"
@feed_version = 0.4
when "!okay/news"
@feed_version = 1.0
end
end
return @feed_version
end
# Sets the default feed version
def feed_version=(new_feed_version)
@feed_version = new_feed_version
end
# Returns the feed's unique id
def id
if @id.nil?
@id = FeedTools::XmlHelper.select_not_blank([
FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"atom10:id/text()",
"atom03:id/text()",
"atom:id/text()",
"id/text()",
"guid/text()"
], :select_result_value => true),
FeedTools::XmlHelper.try_xpaths(self.root_node, [
"atom10:id/text()",
"atom03:id/text()",
"atom:id/text()",
"id/text()",
"guid/text()"
], :select_result_value => true)
])
end
return @id
end
# Sets the feed's unique id
def id=(new_id)
@id = new_id
end
# Returns the feed url.
def href
if @href_overridden != true || @href.nil?
original_href = @href
override_href = lambda do |current_href|
begin
if current_href.nil? && self.feed_data != nil
# The current url is nil and we have feed data to go on
true
elsif current_href != nil && !(["http", "https"].include?(
URI.parse(current_href.to_s).scheme))
if self.feed_data != nil
# The current url is set, but isn't a http/https url and
# we have feed data to use to replace the current url with
true
else
# The current url is set, but isn't a http/https url but
# we don't have feed data to use to replace the current url
# with so we'll have to wait until we do
false
end
else
# The current url is set to an http/https url and there's
# no compelling reason to override it
false
end
rescue
# Something went wrong, so we should err on the side of caution
# and attempt to override the url
true
end
end
if override_href.call(@href) && self.feed_data != nil
begin
links = FeedTools::GenericHelper.recursion_trap(:feed_href) do
self.links
end
link = FeedTools::GenericHelper.recursion_trap(:feed_href) do
self.link
end
if links != nil
for link_object in links
if link_object.rel == 'self'
if link_object.href != link ||
(link_object.href =~ /xml/ ||
link_object.href =~ /atom/ ||
link_object.href =~ /feed/)
@href = link_object.href
@href_overridden = true
@links = nil
@link = nil
return @href
end
end
end
end
rescue Exception
end
@links = nil
@link = nil
# rdf:about is ordered last because a lot of people put the url to
# the feed inside it instead of a link to their blog.
# Ordering it last gives them as many chances as humanly possible
# for them to redeem themselves. If the link turns out to be the
# same as the blog link, it will be reset to the original value.
@href = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"admin:feed/@rdf:resource",
"admin:feed/@resource",
"feed/@rdf:resource",
"feed/@resource",
"@rdf:about",
"@about",
"newLocation/text()",
"atom10:link[@rel='self']/@href"
], :select_result_value => true) do |result|
override_href.call(FeedTools::UriHelper.normalize_url(result))
end
begin
if !(@href =~ /^file:/) &&
!FeedTools::UriHelper.is_uri?(@href)
@href = FeedTools::UriHelper.resolve_relative_uri(
@href, [self.base_uri])
end
rescue
end
if self.configurations[:url_normalization_enabled]
@href = FeedTools::UriHelper.normalize_url(@href)
end
@href.strip! unless @href.nil?
@href = nil if @href.blank?
@href_overridden = true
if @href == nil
@href = original_href
@href_overridden = false
end
if @href == self.link
@href = original_href
@href_overridden = false
end
if @href_overridden == true
@links = nil
@link = nil
end
end
end
return @href
end
# Sets the feed url and prepares the cache_object if necessary.
def href=(new_href)
@href = FeedTools::UriHelper.normalize_url(new_href)
self.cache_object.href = new_href unless self.cache_object.nil?
end
# Returns the feed title
def title
if @title.nil?
repair_entities = false
title_node = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"atom10:title",
"atom03:title",
"atom:title",
"title",
"dc:title",
"channelTitle",
"TITLE"
])
@title = FeedTools::HtmlHelper.process_text_construct(title_node,
self.feed_type, self.feed_version, [self.base_uri])
if self.feed_type == "atom" ||
self.configurations[:always_strip_wrapper_elements]
@title = FeedTools::HtmlHelper.strip_wrapper_element(@title)
end
@title = nil if @title.blank?
self.cache_object.title = @title unless self.cache_object.nil?
end
return @title
end
# Sets the feed title
def title=(new_title)
@title = new_title
self.cache_object.title = new_title unless self.cache_object.nil?
end
# Returns the feed subtitle
def subtitle
if @subtitle.nil?
subtitle_node = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"atom10:subtitle",
"subtitle",
"atom03:tagline",
"tagline",
"description",
"summary",
"abstract",
"ABSTRACT",
"content:encoded",
"encoded",
"content",
"xhtml:body",
"body",
"xhtml:div",
"div",
"p:payload",
"payload",
"channelDescription",
"blurb",
"info"
])
@subtitle = FeedTools::HtmlHelper.process_text_construct(
subtitle_node, self.feed_type, self.feed_version, [self.base_uri])
if self.feed_type == "atom" ||
self.configurations[:always_strip_wrapper_elements]
@subtitle = FeedTools::HtmlHelper.strip_wrapper_element(@subtitle)
end
if @subtitle.blank?
@subtitle = self.itunes_summary
end
if @subtitle.blank?
@subtitle = self.itunes_subtitle
end
end
return @subtitle
end
# Sets the feed subtitle
def subtitle=(new_subtitle)
@subtitle = new_subtitle
end
# Returns the contents of the itunes:summary element
def itunes_summary
if @itunes_summary.nil?
@itunes_summary = FeedTools::XmlHelper.select_not_blank([
FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"itunes:summary/text()"
], :select_result_value => true),
FeedTools::XmlHelper.try_xpaths(self.root_node, [
"itunes:summary/text()"
], :select_result_value => true)
])
unless @itunes_summary.blank?
@itunes_summary =
FeedTools::HtmlHelper.unescape_entities(@itunes_summary)
@itunes_summary =
FeedTools::HtmlHelper.sanitize_html(@itunes_summary)
@itunes_summary.strip!
else
@itunes_summary = nil
end
end
return @itunes_summary
end
# Sets the contents of the itunes:summary element
def itunes_summary=(new_itunes_summary)
@itunes_summary = new_itunes_summary
end
# Returns the contents of the itunes:subtitle element
def itunes_subtitle
if @itunes_subtitle.nil?
@itunes_subtitle = FeedTools::XmlHelper.select_not_blank([
FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"itunes:subtitle/text()"
], :select_result_value => true),
FeedTools::XmlHelper.try_xpaths(self.root_node, [
"itunes:subtitle/text()"
], :select_result_value => true)
])
unless @itunes_subtitle.blank?
@itunes_subtitle =
FeedTools::HtmlHelper.unescape_entities(@itunes_subtitle)
@itunes_subtitle =
FeedTools::HtmlHelper.sanitize_html(@itunes_subtitle)
@itunes_subtitle.strip!
else
@itunes_subtitle = nil
end
end
return @itunes_subtitle
end
# Sets the contents of the itunes:subtitle element
def itunes_subtitle=(new_itunes_subtitle)
@itunes_subtitle = new_itunes_subtitle
end
# Returns the contents of the media:text element
def media_text
if @media_text.nil?
@media_text = FeedTools::XmlHelper.select_not_blank([
FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"media:text/text()"
], :select_result_value => true),
FeedTools::XmlHelper.try_xpaths(self.root_node, [
"media:text/text()"
], :select_result_value => true)
])
unless @media_text.blank?
@media_text = FeedTools::HtmlHelper.unescape_entities(@media_text)
@media_text = FeedTools::HtmlHelper.sanitize_html(@media_text)
@media_text.strip!
else
@media_text = nil
end
end
return @media_text
end
# Sets the contents of the media:text element
def media_text=(new_media_text)
@media_text = new_media_text
end
# Returns the feed link
def link
if @link.nil?
max_score = 0
for link_object in self.links.reverse
score = 0
next if link_object.href.nil?
if @href != nil && link_object.href == @href
score = score - 2
end
if link_object.type != nil
if (link_object.type =~ /image/ || link_object.type =~ /video/)
score = score - 2
end
if FeedTools::HtmlHelper.xml_type?(link_object.type)
score = score + 1
end
if FeedTools::HtmlHelper.html_type?(link_object.type)
score = score + 2
elsif link_object.type != nil
score = score - 1
end
end
if link_object.rel == "enclosure"
score = score - 2
end
if link_object.rel == "alternate"
score = score + 1
end
if link_object.rel == "self"
score = score - 1
if (link_object.href =~ /xml/ ||
link_object.href =~ /atom/ ||
link_object.href =~ /feed/)
score = score - 1
end
end
if score >= max_score
max_score = score
@link = link_object.href
end
end
if @link.blank?
@link = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"@href",
"@rdf:about",
"@about"
], :select_result_value => true)
end
if @link.blank?
if FeedTools::UriHelper.is_uri?(self.id) &&
(self.id =~ /^http/)
@link = self.id
end
end
if !@link.blank?
@link = FeedTools::HtmlHelper.unescape_entities(@link)
end
@link = nil if @link.blank?
begin
if !(@link =~ /^file:/) &&
!FeedTools::UriHelper.is_uri?(@link)
channel_base_uri = nil
unless self.channel_node.nil?
channel_base_uri = self.channel_node.base_uri
end
@link = FeedTools::UriHelper.resolve_relative_uri(
@link, [channel_base_uri, self.base_uri])
end
rescue
end
if self.configurations[:url_normalization_enabled]
@link = FeedTools::UriHelper.normalize_url(@link)
end
unless self.cache_object.nil?
self.cache_object.link = @link
end
end
return @link
end
# Sets the feed link
def link=(new_link)
@link = new_link
unless self.cache_object.nil?
self.cache_object.link = new_link
end
end
# Returns the links collection
def links
if @links.blank?
@links = []
link_nodes =
FeedTools::XmlHelper.combine_xpaths_all(self.channel_node, [
"atom10:link",
"atom03:link",
"atom:link",
"link",
"channelLink",
"a",
"url",
"href"
])
for link_node in link_nodes
link_object = FeedTools::Link.new
link_object.href = FeedTools::XmlHelper.try_xpaths(link_node, [
"@atom10:href",
"@atom03:href",
"@atom:href",
"@href",
"text()"
], :select_result_value => true)
if link_object.href == "atom10:" ||
link_object.href == "atom03:" ||
link_object.href == "atom:"
link_object.href = FeedTools::XmlHelper.try_xpaths(link_node, [
"@href"
], :select_result_value => true)
end
if link_object.href.nil? && link_node.base_uri != nil
link_object.href = ""
end
begin
if !(link_object.href =~ /^file:/) &&
!FeedTools::UriHelper.is_uri?(link_object.href)
link_object.href = FeedTools::UriHelper.resolve_relative_uri(
link_object.href,
[link_node.base_uri, self.base_uri])
end
rescue
end
if self.configurations[:url_normalization_enabled]
link_object.href =
FeedTools::UriHelper.normalize_url(link_object.href)
end
link_object.href.strip! unless link_object.href.nil?
next if link_object.href.blank?
link_object.hreflang = FeedTools::XmlHelper.try_xpaths(link_node, [
"@atom10:hreflang",
"@atom03:hreflang",
"@atom:hreflang",
"@hreflang"
], :select_result_value => true)
if link_object.hreflang == "atom10:" ||
link_object.hreflang == "atom03:" ||
link_object.hreflang == "atom:"
link_object.hreflang = FeedTools::XmlHelper.try_xpaths(link_node, [
"@hreflang"
], :select_result_value => true)
end
unless link_object.hreflang.nil?
link_object.hreflang = link_object.hreflang.downcase
end
link_object.rel = FeedTools::XmlHelper.try_xpaths(link_node, [
"@atom10:rel",
"@atom03:rel",
"@atom:rel",
"@rel"
], :select_result_value => true)
if link_object.rel == "atom10:" ||
link_object.rel == "atom03:" ||
link_object.rel == "atom:"
link_object.rel = FeedTools::XmlHelper.try_xpaths(link_node, [
"@rel"
], :select_result_value => true)
end
unless link_object.rel.nil?
link_object.rel = link_object.rel.downcase
end
if link_object.rel.nil? && self.feed_type == "atom"
link_object.rel = "alternate"
end
link_object.type = FeedTools::XmlHelper.try_xpaths(link_node, [
"@atom10:type",
"@atom03:type",
"@atom:type",
"@type"
], :select_result_value => true)
if link_object.type == "atom10:" ||
link_object.type == "atom03:" ||
link_object.type == "atom:"
link_object.type = FeedTools::XmlHelper.try_xpaths(link_node, [
"@type"
], :select_result_value => true)
end
unless link_object.type.nil?
link_object.type = link_object.type.downcase
end
link_object.title = FeedTools::XmlHelper.try_xpaths(link_node, [
"@atom10:title",
"@atom03:title",
"@atom:title",
"@title",
"text()"
], :select_result_value => true)
if link_object.title == "atom10:" ||
link_object.title == "atom03:" ||
link_object.title == "atom:"
link_object.title = FeedTools::XmlHelper.try_xpaths(link_node, [
"@title"
], :select_result_value => true)
end
# This catches the ambiguities between atom, rss, and cdf
if link_object.title == link_object.href
link_object.title = nil
end
link_object.length = FeedTools::XmlHelper.try_xpaths(link_node, [
"@atom10:length",
"@atom03:length",
"@atom:length",
"@length"
], :select_result_value => true)
if link_object.length == "atom10:" ||
link_object.length == "atom03:" ||
link_object.length == "atom:"
link_object.length = FeedTools::XmlHelper.try_xpaths(link_node, [
"@length"
], :select_result_value => true)
end
if !link_object.length.nil?
link_object.length = link_object.length.to_i
else
if !link_object.type.nil? && link_object.type[0..4] != "text" &&
link_object.type[-3..-1] != "xml" &&
link_object.href =~ /^http:\/\//
# Retrieve the length with an http HEAD request
else
link_object.length = nil
end
end
@links = [] if @links.nil?
@links << link_object
end
end
return @links
end
# Sets the links collection
def links=(new_links)
@links = new_links
end
# Returns the base uri for the feed, used for resolving relative paths
def base_uri
if @base_uri.nil?
@base_uri = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"@base",
"base/@href",
"base/text()",
"@xml:base"
], :select_result_value => true)
if @base_uri.blank?
begin
@base_uri =
FeedTools::GenericHelper.recursion_trap(:feed_base_uri) do
self.href
end
rescue Exception
end
end
if @base_uri.blank?
@base_uri = FeedTools::XmlHelper.try_xpaths(self.root_node, [
"@xml:base"
], :select_result_value => true)
end
if !@base_uri.blank?
@base_uri = FeedTools::UriHelper.normalize_url(@base_uri)
end
if !@base_uri.blank?
parsed_uri = FeedTools::URI.parse(@base_uri)
# Feedburner is almost never the base uri that was intended
# Use the actual site instead
if parsed_uri.host =~ /feedburner/
site_uri =
FeedTools::GenericHelper.recursion_trap(:feed_base_uri) do
FeedTools::UriHelper.normalize_url(self.link)
end
@base_uri = site_uri if !site_uri.blank?
end
end
end
return @base_uri
end
# Sets the base uri for the feed
def base_uri=(new_base_uri)
@base_uri = new_base_uri
end
# Returns the url to the icon file for this feed.
def icon
if @icon.nil?
icon_node = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"link[@rel='icon']",
"link[@rel='shortcut icon']",
"link[@type='image/x-icon']",
"icon",
"logo[@style='icon']",
"LOGO[@STYLE='ICON']"
])
unless icon_node.nil?
@icon = FeedTools::XmlHelper.try_xpaths(icon_node, [
"@atom10:href",
"@atom03:href",
"@atom:href",
"@href",
"text()"
], :select_result_value => true)
begin
if !(@icon =~ /^file:/) &&
!FeedTools::UriHelper.is_uri?(@icon)
channel_base_uri = nil
unless self.channel_node.nil?
channel_base_uri = self.channel_node.base_uri
end
@icon = FeedTools::UriHelper.resolve_relative_uri(
@icon, [channel_base_uri, self.base_uri])
end
rescue
end
@icon = nil unless FeedTools::UriHelper.is_uri?(@icon)
@icon = nil if @icon.blank?
end
end
return @icon
end
# Returns the favicon url for this feed.
# This method first tries to use the url from the link field instead of
# the feed url, in order to avoid grabbing the favicon for services like
# feedburner.
def favicon
if @favicon.nil?
if !self.link.blank?
begin
link_uri = URI.parse(
FeedTools::UriHelper.normalize_url(self.link))
if link_uri.scheme == "http"
@favicon =
"http://" + link_uri.host + "/favicon.ico"
end
rescue
@favicon = nil
end
if @favicon.nil? && !self.href.blank?
begin
feed_uri = URI.parse(
FeedTools::UriHelper.normalize_url(self.href))
if feed_uri.scheme == "http"
@favicon =
"http://" + feed_uri.host + "/favicon.ico"
end
rescue
@favicon = nil
end
end
else
@favicon = nil
end
end
return @favicon
end
# Returns the feed author
def author
if @author.nil?
@author = FeedTools::Author.new
author_node = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"atom10:author",
"atom03:author",
"atom:author",
"author",
"managingEditor",
"dc:author",
"dc:creator"
])
unless author_node.nil?
@author.raw = FeedTools::XmlHelper.try_xpaths(
author_node, ["text()"], :select_result_value => true)
@author.raw = FeedTools::HtmlHelper.unescape_entities(@author.raw)
unless @author.raw.nil?
raw_scan = @author.raw.scan(
/(.*)\((\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\)/i)
if raw_scan.nil? || raw_scan.size == 0
raw_scan = @author.raw.scan(
/(\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\s*\((.*)\)/i)
unless raw_scan.size == 0
author_raw_pair = raw_scan.first.reverse
end
else
author_raw_pair = raw_scan.first
end
if raw_scan.nil? || raw_scan.size == 0
email_scan = @author.raw.scan(
/\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b/i)
if email_scan != nil && email_scan.size > 0
@author.email = email_scan.first.strip
end
end
unless author_raw_pair.nil? || author_raw_pair.size == 0
@author.name = author_raw_pair.first.strip
@author.email = author_raw_pair.last.strip
else
unless @author.raw.include?("@")
# We can be reasonably sure we are looking at something
# that the creator didn't intend to contain an email address
# if it got through the preceeding regexes and it doesn't
# contain the tell-tale '@' symbol.
@author.name = @author.raw
end
end
end
if @author.name.blank?
@author.name = FeedTools::HtmlHelper.unescape_entities(
FeedTools::XmlHelper.try_xpaths(author_node, [
"atom10:name/text()",
"atom03:name/text()",
"atom:name/text()",
"name/text()",
"@name"
], :select_result_value => true)
)
end
if @author.email.blank?
@author.email = FeedTools::HtmlHelper.unescape_entities(
FeedTools::XmlHelper.try_xpaths(author_node, [
"atom10:email/text()",
"atom03:email/text()",
"atom:email/text()",
"email/text()",
"@email"
], :select_result_value => true)
)
end
if @author.url.blank?
@author.url = FeedTools::HtmlHelper.unescape_entities(
FeedTools::XmlHelper.try_xpaths(author_node, [
"atom10:url/text()",
"atom03:url/text()",
"atom:url/text()",
"url/text()",
"atom10:uri/text()",
"atom03:uri/text()",
"atom:uri/text()",
"uri/text()",
"@href",
"@uri",
"@href"
], :select_result_value => true)
)
end
if @author.name.blank? && !@author.raw.blank? &&
!@author.email.blank?
name_scan = @author.raw.scan(
/"?([^"]*)"? ?[\(<].*#{@author.email}.*[\)>].*/)
if name_scan.flatten.size == 1
@author.name = name_scan.flatten[0].strip
end
if @author.name.blank?
name_scan = @author.raw.scan(
/.*#{@author.email} ?[\(<]"?([^"]*)"?[\)>].*/)
if name_scan.flatten.size == 1
@author.name = name_scan.flatten[0].strip
end
end
end
@author.name = nil if @author.name.blank?
@author.raw = nil if @author.raw.blank?
@author.email = nil if @author.email.blank?
@author.url = nil if @author.url.blank?
if @author.url != nil
begin
if !(@author.url =~ /^file:/) &&
!FeedTools::UriHelper.is_uri?(@author.url)
@author.url = FeedTools::UriHelper.resolve_relative_uri(
@author.url, [author_node.base_uri, self.base_uri])
end
rescue
end
end
if FeedTools::XmlHelper.try_xpaths(author_node,
["@gr:unknown-author"], :select_result_value => true) == "true"
if @author.name == "(author unknown)"
@author.name = nil
end
end
end
# Fallback on the itunes module if we didn't find an author name
begin
@author.name = self.itunes_author if @author.name.nil?
rescue
@author.name = nil
end
end
return @author
end
# Sets the feed author
def author=(new_author)
if new_author.respond_to?(:name) &&
new_author.respond_to?(:email) &&
new_author.respond_to?(:url)
# It's a complete author object, just set it.
@author = new_author
else
# We're not looking at an author object, this is probably a string,
# default to setting the author's name.
if @author.nil?
@author = FeedTools::Author.new
end
@author.name = new_author
end
end
# Returns the feed publisher
def publisher
if @publisher.nil?
@publisher = FeedTools::Author.new
@publisher.raw = FeedTools::HtmlHelper.unescape_entities(
FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"webMaster/text()",
"dc:publisher/text()"
], :select_result_value => true))
unless @publisher.raw.blank?
raw_scan = @publisher.raw.scan(
/(.*)\((\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\)/i)
if raw_scan.nil? || raw_scan.size == 0
raw_scan = @publisher.raw.scan(
/(\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b)\s*\((.*)\)/i)
unless raw_scan.size == 0
publisher_raw_pair = raw_scan.first.reverse
end
else
publisher_raw_pair = raw_scan.first
end
if raw_scan.nil? || raw_scan.size == 0
email_scan = @publisher.raw.scan(
/\b[A-Z0-9._%-\+]+@[A-Z0-9._%-]+\.[A-Z]{2,4}\b/i)
if email_scan != nil && email_scan.size > 0
@publisher.email = email_scan.first.strip
end
end
unless publisher_raw_pair.nil? || publisher_raw_pair.size == 0
@publisher.name = publisher_raw_pair.first.strip
@publisher.email = publisher_raw_pair.last.strip
else
unless @publisher.raw.include?("@")
# We can be reasonably sure we are looking at something
# that the creator didn't intend to contain an email address if
# it got through the preceeding regexes and it doesn't
# contain the tell-tale '@' symbol.
@publisher.name = @publisher.raw
end
end
end
@publisher.name = nil if @publisher.name.blank?
@publisher.raw = nil if @publisher.raw.blank?
@publisher.email = nil if @publisher.email.blank?
@publisher.url = nil if @publisher.url.blank?
if @publisher.url != nil
begin
if !(@publisher.url =~ /^file:/) &&
!FeedTools::UriHelper.is_uri?(@publisher.url)
channel_base_uri = nil
unless self.channel_node.nil?
channel_base_uri = self.channel_node.base_uri
end
@publisher.url = FeedTools::UriHelper.resolve_relative_uri(
@publisher.url, [channel_base_uri, self.base_uri])
end
rescue
end
end
end
return @publisher
end
# Sets the feed publisher
def publisher=(new_publisher)
if new_publisher.respond_to?(:name) &&
new_publisher.respond_to?(:email) &&
new_publisher.respond_to?(:url)
# It's a complete Author object, just set it.
@publisher = new_publisher
else
# We're not looking at an Author object, this is probably a string,
# default to setting the publisher's name.
if @publisher.nil?
@publisher = FeedTools::Author.new
end
@publisher.name = new_publisher
end
end
# Returns the contents of the itunes:author element
#
# Returns any incorrectly placed channel-level itunes:author
# elements. They're actually amazingly common. People don't read specs.
# There is no setter for this, since this is an incorrectly placed
# attribute.
def itunes_author
if @itunes_author.nil?
@itunes_author = FeedTools::HtmlHelper.unescape_entities(
FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"itunes:author/text()"
], :select_result_value => true)
)
@itunes_author = nil if @itunes_author.blank?
end
return @itunes_author
end
# Returns the feed time
def time
if @time.nil?
time_string = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"atom10:updated/text()",
"atom03:updated/text()",
"atom:updated/text()",
"updated/text()",
"atom10:modified/text()",
"atom03:modified/text()",
"atom:modified/text()",
"modified/text()",
"time/text()",
"lastBuildDate/text()",
"atom10:issued/text()",
"atom03:issued/text()",
"atom:issued/text()",
"issued/text()",
"atom10:published/text()",
"atom03:published/text()",
"atom:published/text()",
"published/text()",
"dc:date/text()",
"pubDate/text()",
"date/text()"
], :select_result_value => true)
begin
unless time_string.blank?
@time = Time.parse(time_string).gmtime
else
if self.configurations[:timestamp_estimation_enabled]
@time = Time.now.gmtime
end
end
rescue
if self.configurations[:timestamp_estimation_enabled]
@time = Time.now.gmtime
end
end
end
return @time
end
# Sets the feed time
def time=(new_time)
@time = new_time
end
# Returns the feed updated time
def updated
if @updated.nil?
updated_string = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"atom10:updated/text()",
"atom03:updated/text()",
"atom:updated/text()",
"updated/text()",
"atom10:modified/text()",
"atom03:modified/text()",
"atom:modified/text()",
"modified/text()",
"lastBuildDate/text()"
], :select_result_value => true)
unless updated_string.blank?
@updated = Time.parse(updated_string).gmtime rescue nil
else
@updated = nil
end
end
return @updated
end
# Sets the feed updated time
def updated=(new_updated)
@updated = new_updated
end
# Returns the feed published time
def published
if @published.nil?
published_string =
FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"atom10:published/text()",
"atom03:published/text()",
"atom:published/text()",
"published/text()",
"dc:date/text()",
"pubDate/text()",
"atom10:issued/text()",
"atom03:issued/text()",
"atom:issued/text()",
"issued/text()"
], :select_result_value => true)
unless published_string.blank?
@published = Time.parse(published_string).gmtime rescue nil
else
@published = nil
end
end
return @published
end
# Sets the feed published time
def published=(new_published)
@published = new_published
end
# Returns a list of the feed's categories
def categories
if @categories.nil?
@categories = []
category_nodes =
FeedTools::XmlHelper.try_xpaths_all(self.channel_node, [
"category",
"dc:subject"
])
unless category_nodes.nil?
for category_node in category_nodes
category = FeedTools::Category.new
category.term = FeedTools::XmlHelper.try_xpaths(category_node, [
"@term",
"text()"
], :select_result_value => true)
category.term.strip! unless category.term.blank?
category.label = FeedTools::XmlHelper.try_xpaths(
category_node, ["@label"],
:select_result_value => true)
category.label.strip! unless category.label.blank?
category.scheme = FeedTools::XmlHelper.try_xpaths(category_node, [
"@scheme",
"@domain"
], :select_result_value => true)
category.scheme.strip! unless category.scheme.blank?
@categories << category
end
end
end
return @categories
end
# Returns a list of the feed's images
def images
if @images.nil?
@images = []
image_nodes = FeedTools::XmlHelper.combine_xpaths_all(
self.channel_node, [
"image",
"logo",
"apple-wallpapers:image",
"imageUrl"
]
)
unless image_nodes.blank?
for image_node in image_nodes
image = FeedTools::Image.new
image.href = FeedTools::XmlHelper.try_xpaths(image_node, [
"url/text()",
"@rdf:resource",
"@href",
"text()"
], :select_result_value => true)
if image.href.nil? && image_node.base_uri != nil
image.href = ""
end
begin
if !(image.href =~ /^file:/) &&
!FeedTools::UriHelper.is_uri?(image.href)
image.href = FeedTools::UriHelper.resolve_relative_uri(
image.href, [image_node.base_uri, self.base_uri])
end
rescue
end
if self.configurations[:url_normalization_enabled]
image.href = FeedTools::UriHelper.normalize_url(image.href)
end
image.href.strip! unless image.href.nil?
next if image.href.blank?
image.title = FeedTools::XmlHelper.try_xpaths(image_node,
["title/text()"], :select_result_value => true)
image.title.strip! unless image.title.nil?
image.description = FeedTools::XmlHelper.try_xpaths(image_node,
["description/text()"], :select_result_value => true)
image.description.strip! unless image.description.nil?
image.link = FeedTools::XmlHelper.try_xpaths(image_node,
["link/text()"], :select_result_value => true)
image.link.strip! unless image.link.nil?
image.height = FeedTools::XmlHelper.try_xpaths(image_node,
["height/text()"], :select_result_value => true).to_i
image.height = nil if image.height <= 0
image.width = FeedTools::XmlHelper.try_xpaths(image_node,
["width/text()"], :select_result_value => true).to_i
image.width = nil if image.width <= 0
image.style = FeedTools::XmlHelper.try_xpaths(image_node, [
"style/text()",
"@style"
], :select_result_value => true)
image.style.strip! unless image.style.nil?
image.style.downcase! unless image.style.nil?
@images << image unless image.href.nil?
end
end
for link_object in self.links
if link_object.type != nil && link_object.type =~ /^image/
image = FeedTools::Image.new
image.href = link_object.href
image.title = link_object.title
@images << image unless image.href.nil?
end
end
end
return @images
end
# Returns the feed's copyright information
def rights
if @rights.nil?
repair_entities = false
rights_node = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"atom10:copyright",
"atom03:copyright",
"atom:copyright",
"copyright",
"copyrights",
"dc:rights",
"rights"
])
@rights = FeedTools::HtmlHelper.process_text_construct(rights_node,
self.feed_type, self.feed_version, [self.base_uri])
if self.feed_type == "atom" ||
self.configurations[:always_strip_wrapper_elements]
@rights = FeedTools::HtmlHelper.strip_wrapper_element(@rights)
end
end
return @rights
end
# Sets the feed's rights information
def rights=(new_rights)
@rights = new_rights
end
# Returns the first license link for the feed item.
def license
return self.licenses.first
end
# Returns all licenses linked from this feed item.
def licenses
if @licenses.nil?
@licenses = self.links.select do |link|
link.rel == "license"
end
end
return @licenses
end
# Sets the feed item's licenses.
def licenses=(new_licenses)
@licenses = new_licenses
end
# Returns the number of seconds before the feed should expire
def time_to_live
if @time_to_live.nil?
unless channel_node.nil?
# get the feed time to live from the xml document
update_frequency = FeedTools::XmlHelper.try_xpaths(
self.channel_node,
["syn:updateFrequency/text()"], :select_result_value => true)
if !update_frequency.blank?
update_period = FeedTools::XmlHelper.try_xpaths(
self.channel_node,
["syn:updatePeriod/text()"], :select_result_value => true)
if update_period == "daily"
@time_to_live = update_frequency.to_i.day
elsif update_period == "weekly"
@time_to_live = update_frequency.to_i.week
elsif update_period == "monthly"
@time_to_live = update_frequency.to_i.month
elsif update_period == "yearly"
@time_to_live = update_frequency.to_i.year
else
# hourly
@time_to_live = update_frequency.to_i.hour
end
end
if @time_to_live.nil?
# usually expressed in minutes
update_frequency = FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["ttl/text()"],
:select_result_value => true)
if !update_frequency.blank?
update_span = FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["ttl/@span"],
:select_result_value => true)
if update_span == "seconds"
@time_to_live = update_frequency.to_i
elsif update_span == "minutes"
@time_to_live = update_frequency.to_i.minute
elsif update_span == "hours"
@time_to_live = update_frequency.to_i.hour
elsif update_span == "days"
@time_to_live = update_frequency.to_i.day
elsif update_span == "weeks"
@time_to_live = update_frequency.to_i.week
elsif update_span == "months"
@time_to_live = update_frequency.to_i.month
elsif update_span == "years"
@time_to_live = update_frequency.to_i.year
else
@time_to_live = update_frequency.to_i.minute
end
end
end
if @time_to_live.nil?
@time_to_live = 0
update_frequency_days =
FeedTools::XmlHelper.try_xpaths(self.channel_node,
["schedule/intervaltime/@day"], :select_result_value => true)
update_frequency_hours =
FeedTools::XmlHelper.try_xpaths(self.channel_node,
["schedule/intervaltime/@hour"], :select_result_value => true)
update_frequency_minutes =
FeedTools::XmlHelper.try_xpaths(self.channel_node,
["schedule/intervaltime/@min"], :select_result_value => true)
update_frequency_seconds =
FeedTools::XmlHelper.try_xpaths(self.channel_node,
["schedule/intervaltime/@sec"], :select_result_value => true)
if !update_frequency_days.blank?
@time_to_live = @time_to_live + update_frequency_days.to_i.day
end
if !update_frequency_hours.blank?
@time_to_live = @time_to_live + update_frequency_hours.to_i.hour
end
if !update_frequency_minutes.blank?
@time_to_live = @time_to_live +
update_frequency_minutes.to_i.minute
end
if !update_frequency_seconds.blank?
@time_to_live = @time_to_live + update_frequency_seconds.to_i
end
if @time_to_live == 0
@time_to_live = self.configurations[:default_ttl].to_i
end
end
end
end
if @time_to_live.nil? || @time_to_live == 0
# Default to one hour
@time_to_live = self.configurations[:default_ttl].to_i
elsif self.configurations[:max_ttl] != nil &&
self.configurations[:max_ttl] != 0 &&
@time_to_live >= self.configurations[:max_ttl].to_i
@time_to_live = self.configurations[:max_ttl].to_i
end
@time_to_live = @time_to_live.round
return @time_to_live
end
# Sets the feed time to live
def time_to_live=(new_time_to_live)
@time_to_live = new_time_to_live.round
@time_to_live = 30.minutes if @time_to_live < 30.minutes
end
# Returns the feed's cloud
def cloud
if @cloud.nil?
@cloud = FeedTools::Cloud.new
@cloud.domain = FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["cloud/@domain"],
:select_result_value => true)
@cloud.port = FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["cloud/@port"],
:select_result_value => true)
@cloud.path = FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["cloud/@path"],
:select_result_value => true)
@cloud.register_procedure =
FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["cloud/@registerProcedure"],
:select_result_value => true)
@cloud.protocol =
FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["cloud/@protocol"],
:select_result_value => true)
@cloud.protocol.downcase unless @cloud.protocol.nil?
@cloud.port = @cloud.port.to_s.to_i
@cloud.port = nil if @cloud.port == 0
end
return @cloud
end
# Sets the feed's cloud
def cloud=(new_cloud)
@cloud = new_cloud
end
# Returns the feed's text input field
def text_input
if @text_input.nil?
@text_input = FeedTools::TextInput.new
text_input_node =
FeedTools::XmlHelper.try_xpaths(self.channel_node, ["textInput"])
unless text_input_node.nil?
@text_input.title =
FeedTools::XmlHelper.try_xpaths(text_input_node,
["title/text()"],
:select_result_value => true)
@text_input.description =
FeedTools::XmlHelper.try_xpaths(text_input_node,
["description/text()"],
:select_result_value => true)
@text_input.link =
FeedTools::XmlHelper.try_xpaths(text_input_node,
["link/text()"],
:select_result_value => true)
@text_input.name =
FeedTools::XmlHelper.try_xpaths(text_input_node,
["name/text()"],
:select_result_value => true)
end
end
return @text_input
end
# Returns the feed generator
def generator
if @generator.nil?
@generator = FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["generator/text()"],
:select_result_value => true)
unless @generator.nil?
@generator =
FeedTools::HtmlHelper.convert_html_to_plain_text(@generator)
end
end
return @generator
end
# Sets the feed generator
#
# Note: Setting this variable will NOT cause this to appear in any
# generated output. The generator string is created from the
# <tt>:generator_name</tt> and <tt>:generator_href</tt> configuration
# variables.
def generator=(new_generator)
@generator = new_generator
end
# Returns the feed docs
def docs
if @docs.nil?
@docs = FeedTools::XmlHelper.try_xpaths(
self.channel_node, ["docs/text()"],
:select_result_value => true)
begin
if !(@docs =~ /^file:/) &&
!FeedTools::UriHelper.is_uri?(@docs)
channel_base_uri = nil
unless self.channel_node.nil?
channel_base_uri = self.channel_node.base_uri
end
@docs = FeedTools::UriHelper.resolve_relative_uri(
@docs, [channel_base_uri, self.base_uri])
end
rescue
end
if self.configurations[:url_normalization_enabled]
@docs = FeedTools::UriHelper.normalize_url(@docs)
end
end
return @docs
end
# Sets the feed docs
def docs=(new_docs)
@docs = new_docs
end
# Returns the feed language
def language
if @language.nil?
@language = FeedTools::XmlHelper.select_not_blank([
FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"language/text()",
"dc:language/text()",
"@dc:language",
"@xml:lang",
"xml:lang/text()"
], :select_result_value => true),
FeedTools::XmlHelper.try_xpaths(self.root_node, [
"@xml:lang",
"xml:lang/text()"
], :select_result_value => true)
])
if @language.blank?
@language = "en-us"
end
@language.gsub!(/_/, "-")
@language = @language.downcase
if @language.split('-').size > 1
@language =
"#{@language.split('-').first}-" +
"#{@language.split('-').last.upcase}"
end
end
return @language
end
# Sets the feed language
def language=(new_language)
@language = new_language
end
# Returns true if this feed contains explicit material.
def explicit?
if @explicit.nil?
explicit_string = FeedTools::XmlHelper.try_xpaths(self.channel_node, [
"media:adult/text()",
"itunes:explicit/text()"
], :select_result_value => true)
if explicit_string == "true" || explicit_string == "yes"
@explicit = true
else
@explicit = false
end
end
return @explicit
end
# Sets whether or not the feed contains explicit material
def explicit=(new_explicit)
@explicit = (new_explicit ? true : false)
end
# Returns the feed entries
def entries
if @entries.nil?
raw_entries = FeedTools::XmlHelper.select_not_blank([
FeedTools::XmlHelper.try_xpaths_all(self.channel_node, [
"atom10:entry",
"atom03:entry",
"atom:entry",
"entry"
]),
FeedTools::XmlHelper.try_xpaths_all(self.root_node, [
"rss10:item",
"rss11:items/rss11:item",
"rss11:items/item",
"items/rss11:item",
"items/item",
"item",
"atom10:entry",
"atom03:entry",
"atom:entry",
"entry",
"story"
]),
FeedTools::XmlHelper.try_xpaths_all(self.channel_node, [
"rss10:item",
"rss11:items/rss11:item",
"rss11:items/item",
"items/rss11:item",
"items/item",
"item",
"story"
])
])
# create the individual feed items
@entries = []
unless raw_entries.blank?
for entry_node in raw_entries.reverse
new_entry = FeedItem.new
new_entry.feed_data = entry_node.to_s
new_entry.feed_data_type = self.feed_data_type
new_entry.root_node = entry_node
if new_entry.root_node.namespace.blank?
new_entry.root_node.add_namespace(self.root_node.namespace)
end
@entries << new_entry
end
end
end
# Sort the items
if self.configurations[:entry_sorting_property] == "time"
@entries = @entries.sort do |a, b|
(b.time or Time.utc(1970)) <=> (a.time or Time.utc(1970))
end
elsif self.configurations[:entry_sorting_property] != nil
sorting_property = self.configurations[:entry_sorting_property]
@entries = @entries.sort do |a, b|
eval("a.#{sorting_property}") <=> eval("b.#{sorting_property}")
end
else
return @entries.reverse
end
return @entries
end
# Sets the entries array to a new array.
def entries=(new_entries)
for entry in new_entries
unless entry.kind_of? FeedTools::FeedItem
raise ArgumentError,
"You should only add FeedItem objects to the entries array."
end
end
@entries = new_entries
end
# Syntactic sugar for appending feed items to a feed.
def <<(new_entry)
@entries ||= []
unless new_entry.kind_of? FeedTools::FeedItem
raise ArgumentError,
"You should only add FeedItem objects to the entries array."
end
@entries << new_entry
end
# The time that the feed was last requested from the remote server. Nil
# if it has never been pulled, or if it was created from scratch.
def last_retrieved
unless self.cache_object.nil?
@last_retrieved = self.cache_object.last_retrieved
end
return @last_retrieved
end
# Sets the time that the feed was last updated.
def last_retrieved=(new_last_retrieved)
@last_retrieved = new_last_retrieved
unless self.cache_object.nil?
self.cache_object.last_retrieved = new_last_retrieved
end
end
# True if this feed contains audio content enclosures
def podcast?
podcast = false
self.items.each do |item|
item.enclosures.each do |enclosure|
podcast = true if enclosure.audio?
end
end
return podcast
end
# True if this feed contains video content enclosures
def vidlog?
vidlog = false
self.items.each do |item|
item.enclosures.each do |enclosure|
vidlog = true if enclosure.video?
end
end
return vidlog
end
# True if the feed was not last retrieved from the cache.
def live?
return @live
end
# True if the feed has expired and must be reacquired from the remote
# server.
def expired?
if (self.last_retrieved == nil)
return true
elsif (self.time_to_live < 30.minutes)
return (self.last_retrieved + 30.minutes) < Time.now.gmtime
else
return (self.last_retrieved + self.time_to_live) < Time.now.gmtime
end
end
# Forces this feed to expire.
def expire!
self.last_retrieved = Time.mktime(1970).gmtime
self.save
end
# A hook method that is called during the feed generation process.
# Overriding this method will enable additional content to be
# inserted into the feed.
def build_xml_hook(feed_type, version, xml_builder)
return nil
end
# Generates xml based on the content of the feed
def build_xml(feed_type=(self.feed_type or "atom"), feed_version=nil,
xml_builder=Builder::XmlMarkup.new(
:indent => 2, :escape_attrs => false))
if self.find_node("access:restriction/@relationship").to_s == "deny"
raise StandardError,
"Operation not permitted. This feed denies redistribution."
elsif self.find_node("@indexing:index").to_s == "no"
raise StandardError,
"Operation not permitted. This feed denies redistribution."
end
self.full_parse()
xml_builder.instruct! :xml, :version => "1.0",
:encoding => (self.configurations[:output_encoding] or "utf-8")
if feed_type.nil?
feed_type = self.feed_type
end
if feed_version.nil?
feed_version = self.feed_version
end
if feed_type == "rss" &&
(feed_version == nil || feed_version <= 0.0)
feed_version = 1.0
elsif feed_type == "atom" &&
(feed_version == nil || feed_version <= 0.0)
feed_version = 1.0
end
if feed_type == "rss" &&
(feed_version == 0.9 || feed_version == 1.0 || feed_version == 1.1)
# RDF-based rss format
return xml_builder.tag!("rdf:RDF",
"xmlns" => FEED_TOOLS_NAMESPACES['rss10'],
"xmlns:content" => FEED_TOOLS_NAMESPACES['content'],
"xmlns:rdf" => FEED_TOOLS_NAMESPACES['rdf'],
"xmlns:dc" => FEED_TOOLS_NAMESPACES['dc'],
"xmlns:syn" => FEED_TOOLS_NAMESPACES['syn'],
"xmlns:admin" => FEED_TOOLS_NAMESPACES['admin'],
"xmlns:taxo" => FEED_TOOLS_NAMESPACES['taxo'],
"xmlns:itunes" => FEED_TOOLS_NAMESPACES['itunes'],
"xmlns:media" => FEED_TOOLS_NAMESPACES['media']) do
channel_attributes = {}
unless self.link.nil?
channel_attributes["rdf:about"] =
FeedTools::HtmlHelper.escape_entities(self.link)
end
xml_builder.channel(channel_attributes) do
unless self.title.blank?
xml_builder.title(
FeedTools::HtmlHelper.strip_html_tags(self.title))
else
xml_builder.title
end
unless self.link.blank?
xml_builder.link(self.link)
else
xml_builder.link
end
unless images.blank?
xml_builder.image("rdf:resource" =>
FeedTools::HtmlHelper.escape_entities(
images.first.url))
end
unless description.nil? || description == ""
xml_builder.description(description)
else
xml_builder.description
end
unless self.language.blank?
xml_builder.tag!("dc:language", self.language)
end
unless self.rights.blank?
xml_builder.tag!("dc:rights", self.rights)
end
xml_builder.tag!("syn:updatePeriod", "hourly")
xml_builder.tag!("syn:updateFrequency",
(self.time_to_live / 1.hour).to_s)
xml_builder.tag!("syn:updateBase", Time.mktime(1970).iso8601)
xml_builder.items do
xml_builder.tag!("rdf:Seq") do
unless items.nil?
for item in items
if item.link.nil?
raise "Cannot generate an rdf-based feed with a nil " +
"item link field."
end
xml_builder.tag!("rdf:li", "rdf:resource" =>
FeedTools::HtmlHelper.escape_entities(item.link))
end
end
end
end
xml_builder.tag!(
"admin:generatorAgent",
"rdf:resource" => self.configurations[:generator_href])
build_xml_hook(feed_type, feed_version, xml_builder)
end
unless self.images.blank?
best_image = nil
for image in self.images
if image.link != nil
best_image = image
break
end
end
best_image = self.images.first if best_image.nil?
xml_builder.image("rdf:about" =>
FeedTools::HtmlHelper.escape_entities(best_image.url)) do
if !best_image.title.blank?
xml_builder.title(best_image.title)
elsif !self.title.blank?
xml_builder.title(self.title)
else
xml_builder.title
end
unless best_image.url.blank?
xml_builder.url(best_image.url)
end
if !best_image.link.blank?
xml_builder.link(best_image.link)
elsif !self.link.blank?
xml_builder.link(self.link)
else
xml_builder.link
end
end
end
unless items.nil?
for item in items
item.build_xml(feed_type, feed_version, xml_builder)
end
end
end
elsif feed_type == "rss"
# normal rss format
return xml_builder.rss("version" => "2.0",
"xmlns:content" => FEED_TOOLS_NAMESPACES['content'],
"xmlns:rdf" => FEED_TOOLS_NAMESPACES['rdf'],
"xmlns:dc" => FEED_TOOLS_NAMESPACES['dc'],
"xmlns:taxo" => FEED_TOOLS_NAMESPACES['taxo'],
"xmlns:trackback" => FEED_TOOLS_NAMESPACES['trackback'],
"xmlns:itunes" => FEED_TOOLS_NAMESPACES['itunes'],
"xmlns:media" => FEED_TOOLS_NAMESPACES['media']) do
xml_builder.channel do
unless self.title.blank?
xml_builder.title(
FeedTools::HtmlHelper.strip_html_tags(self.title))
end
unless self.link.blank?
xml_builder.link(link)
end
unless self.description.blank?
xml_builder.description(description)
else
xml_builder.description
end
unless self.author.email.blank?
xml_builder.managingEditor(self.author.email)
end
unless self.publisher.email.blank?
xml_builder.webMaster(self.publisher.email)
end
unless self.published.blank?
xml_builder.pubDate(self.published.rfc822)
end
unless self.updated.blank?
xml_builder.lastBuildDate(self.updated.rfc822)
end
unless self.copyright.blank?
xml_builder.copyright(self.copyright)
end
unless self.language.blank?
xml_builder.language(self.language)
end
xml_builder.ttl((time_to_live / 1.minute).to_s)
xml_builder.generator(
self.configurations[:generator_href])
build_xml_hook(feed_type, feed_version, xml_builder)
unless items.nil?
for item in items
item.build_xml(feed_type, feed_version, xml_builder)
end
end
end
end
elsif feed_type == "atom" && feed_version == 0.3
raise "Atom 0.3 is obsolete."
elsif feed_type == "atom" && feed_version == 1.0
# normal atom format
return xml_builder.feed("xmlns" => FEED_TOOLS_NAMESPACES['atom10'],
"xml:lang" => language) do
unless title.blank?
xml_builder.title(title,
"type" => "html")
end
xml_builder.author do
unless self.author.nil? || self.author.name.nil?
xml_builder.name(self.author.name)
else
xml_builder.name("n/a")
end
unless self.author.nil? || self.author.email.nil?
xml_builder.email(self.author.email)
end
unless self.author.nil? || self.author.url.nil?
xml_builder.uri(self.author.url)
end
end
unless self.href.blank?
xml_builder.link("href" => self.href,
"rel" => "self",
"type" => "application/atom+xml")
end
unless self.link.blank?
xml_builder.link(
"href" =>
FeedTools::HtmlHelper.escape_entities(self.link),
"rel" => "alternate")
end
unless self.subtitle.blank?
xml_builder.subtitle(self.subtitle,
"type" => "html")
end
if self.updated != nil
xml_builder.updated(self.updated.iso8601)
elsif self.time != nil
# Not technically correct, but a heck of a lot better
# than the Time.now fall-back.
xml_builder.updated(self.time.iso8601)
else
xml_builder.updated(Time.now.gmtime.iso8601)
end
unless self.rights.blank?
xml_builder.rights(self.rights)
end
xml_builder.generator(self.configurations[:generator_name] +
" - " + self.configurations[:generator_href])
if self.id != nil
unless FeedTools::UriHelper.is_uri? self.id
if self.link != nil
xml_builder.id(FeedTools::UriHelper.build_urn_uri(self.link))
else
raise "The unique id must be a valid URI."
end
else
xml_builder.id(self.id)
end
elsif self.link != nil
xml_builder.id(FeedTools::UriHelper.build_urn_uri(self.link))
elsif self.url != nil
xml_builder.id(FeedTools::UriHelper.build_urn_uri(self.url))
else
raise "Cannot build feed, missing feed unique id."
end
build_xml_hook(feed_type, feed_version, xml_builder)
unless items.nil?
for item in items
item.build_xml(feed_type, feed_version, xml_builder)
end
end
end
else
raise "Unsupported feed format/version."
end
end
# Persists the current feed state to the cache.
def save
if self.configurations[:feed_cache].nil?
# The cache is disabled for this feed, do nothing.
return
end
if self.feed_data.blank? && self.http_headers.blank?
# There's no data, nothing to save.
return
end
if self.http_headers['content-type'] =~ /text\/html/ ||
self.http_headers['content-type'] =~ /application\/xhtml\+xml/
if self.title.nil? && self.link.nil? && self.entries.blank?
# Don't save html pages to the cache, it messes with
# autodiscovery.
return
end
end
unless self.href =~ /^file:\/\//
if FeedTools.feed_cache.nil?
raise "Caching is currently disabled. Cannot save to cache."
elsif self.href.nil?
raise "The url field must be set to save to the cache."
elsif self.cache_object.nil?
raise "The cache_object is currently nil. Cannot save to cache."
else
self.cache_object.href = self.href
unless self.feed_data.nil?
self.cache_object.title = self.title
self.cache_object.link = self.link
self.cache_object.feed_data = self.feed_data
self.cache_object.feed_data_type = self.feed_data_type.to_s
end
self.cache_object.http_headers = self.http_headers.to_yaml
self.cache_object.last_retrieved = self.last_retrieved
Thread.pass
self.cache_object.save
end
end
end
alias_method :url, :href
alias_method :url=, :href=
alias_method :tagline, :subtitle
alias_method :tagline=, :subtitle=
alias_method :description, :subtitle
alias_method :description=, :subtitle=
alias_method :abstract, :subtitle
alias_method :abstract=, :subtitle=
alias_method :copyright, :rights
alias_method :copyright=, :rights=
alias_method :ttl, :time_to_live
alias_method :ttl=, :time_to_live=
alias_method :guid, :id
alias_method :guid=, :id=
alias_method :items, :entries
alias_method :items=, :entries=
# passes missing methods to the cache_object
def method_missing(msg, *params)
if self.cache_object.nil?
raise NoMethodError, "Invalid method #{msg.to_s}"
end
return self.cache_object.send(msg, params)
end
# passes missing methods to the FeedTools.feed_cache
def Feed.method_missing(msg, *params)
if FeedTools.feed_cache.nil?
raise NoMethodError, "Invalid method Feed.#{msg.to_s}"
end
result = FeedTools.feed_cache.send(msg, params)
if result.kind_of? FeedTools.feed_cache
result = Feed.open(result.url)
end
return result
end
# Returns a simple representation of the feed object's state.
def inspect
return "#<FeedTools::Feed:0x#{self.object_id.to_s(16)} URL:#{self.href}>"
end
# Allows sorting feeds by title
def <=>(other_feed)
return self.title.to_s <=> other_feed.title.to_s
end
end
end
|