Beautiful Soup Elixir and Tonic The Screen-Scraper Friend http www cru

   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
"""Beautiful Soup
Elixir and Tonic
"The Screen-Scraper's Friend"
http://www.crummy.com/software/BeautifulSoup/
Beautiful Soup parses a (possibly invalid) XML or HTML document into a
tree representation. It provides methods and Pythonic idioms that make
it easy to navigate, search, and modify the tree.
A well-formed XML/HTML document yields a well-formed data
structure. An ill-formed XML/HTML document yields a correspondingly
ill-formed data structure. If your document is only locally
well-formed, you can use this library to find and process the
well-formed part of it.
Beautiful Soup works with Python 2.2 and up. It has no external
dependencies, but you'll have more success at converting data to UTF-8
if you also install these three packages:
* chardet, for auto-detecting character encodings
http://chardet.feedparser.org/
* cjkcodecs and iconv_codec, which add more encodings to the ones supported
by stock Python.
http://cjkpython.i18n.org/
Beautiful Soup defines classes for two main parsing strategies:
* BeautifulStoneSoup, for parsing XML, SGML, or your domain-specific
language that kind of looks like XML.
* BeautifulSoup, for parsing run-of-the-mill HTML code, be it valid
or invalid. This class has web browser-like heuristics for
obtaining a sensible parse tree in the face of common HTML errors.
Beautiful Soup also defines a class (UnicodeDammit) for autodetecting
the encoding of an HTML or XML document, and converting it to
Unicode. Much of this code is taken from Mark Pilgrim's Universal Feed Parser.
For more than you ever wanted to know about Beautiful Soup, see the
documentation:
http://www.crummy.com/software/BeautifulSoup/documentation.html
Here, have some legalese:
Copyright (c) 2004-2008, Leonard Richardson
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following
disclaimer in the documentation and/or other materials provided
with the distribution.
* Neither the name of the the Beautiful Soup Consortium and All
Night Kosher Bakery nor the names of its contributors may be
used to endorse or promote products derived from this software
without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE, DAMMIT.
"""
from __future__ import generators
__author__ = "Leonard Richardson (leonardr@segfault.org)"
__version__ = "3.0.7"
__copyright__ = "Copyright (c) 2004-2008 Leonard Richardson"
__license__ = "New-style BSD"
from sgmllib import SGMLParser, SGMLParseError
import codecs
import markupbase
import types
import re
import sgmllib
try:
from htmlentitydefs import name2codepoint
except ImportError:
name2codepoint = {}
#These hacks make Beautiful Soup able to parse XML with namespaces
sgmllib.tagfind = re.compile('[a-zA-Z][-_.:a-zA-Z0-9]*')
markupbase._declname_match = re.compile(r'[a-zA-Z][-_.:a-zA-Z0-9]*\s*').match
DEFAULT_OUTPUT_ENCODING = "utf-8"
# First, the classes that represent markup elements.
class PageElement:
"""Contains the navigational information for some part of the page
(either a tag or a piece of text)"""
def setup(self, parent=None, previous=None):
"""Sets up the initial relations between this element and
other elements."""
self.parent = parent
self.previous = previous
self.next = None
self.previousSibling = None
self.nextSibling = None
if self.parent and self.parent.contents:
self.previousSibling = self.parent.contents[-1]
self.previousSibling.nextSibling = self
def replaceWith(self, replaceWith):
oldParent = self.parent
myIndex = self.parent.contents.index(self)
if hasattr(replaceWith, 'parent') and replaceWith.parent == self.parent:
# We're replacing this element with one of its siblings.
index = self.parent.contents.index(replaceWith)
if index and index < myIndex:
# Furthermore, it comes before this element. That
# means that when we extract it, the index of this
# element will change.
myIndex = myIndex - 1
self.extract()
oldParent.insert(myIndex, replaceWith)
def extract(self):
"""Destructively rips this element out of the tree."""
if self.parent:
try:
self.parent.contents.remove(self)
except ValueError:
pass
#Find the two elements that would be next to each other if
#this element (and any children) hadn't been parsed. Connect
#the two.
lastChild = self._lastRecursiveChild()
nextElement = lastChild.next
if self.previous:
self.previous.next = nextElement
if nextElement:
nextElement.previous = self.previous
self.previous = None
lastChild.next = None
self.parent = None
if self.previousSibling:
self.previousSibling.nextSibling = self.nextSibling
if self.nextSibling:
self.nextSibling.previousSibling = self.previousSibling
self.previousSibling = self.nextSibling = None
return self
def _lastRecursiveChild(self):
"Finds the last element beneath this object to be parsed."
lastChild = self
while hasattr(lastChild, 'contents') and lastChild.contents:
lastChild = lastChild.contents[-1]
return lastChild
def insert(self, position, newChild):
if (isinstance(newChild, basestring)
or isinstance(newChild, unicode)) \
and not isinstance(newChild, NavigableString):
newChild = NavigableString(newChild)
position = min(position, len(self.contents))
if hasattr(newChild, 'parent') and newChild.parent != None:
# We're 'inserting' an element that's already one
# of this object's children.
if newChild.parent == self:
index = self.find(newChild)
if index and index < position:
# Furthermore we're moving it further down the
# list of this object's children. That means that
# when we extract this element, our target index
# will jump down one.
position = position - 1
newChild.extract()
newChild.parent = self
previousChild = None
if position == 0:
newChild.previousSibling = None
newChild.previous = self
else:
previousChild = self.contents[position-1]
newChild.previousSibling = previousChild
newChild.previousSibling.nextSibling = newChild
newChild.previous = previousChild._lastRecursiveChild()
if newChild.previous:
newChild.previous.next = newChild
newChildsLastElement = newChild._lastRecursiveChild()
if position >= len(self.contents):
newChild.nextSibling = None
parent = self
parentsNextSibling = None
while not parentsNextSibling:
parentsNextSibling = parent.nextSibling
parent = parent.parent
if not parent: # This is the last element in the document.
break
if parentsNextSibling:
newChildsLastElement.next = parentsNextSibling
else:
newChildsLastElement.next = None
else:
nextChild = self.contents[position]
newChild.nextSibling = nextChild
if newChild.nextSibling:
newChild.nextSibling.previousSibling = newChild
newChildsLastElement.next = nextChild
if newChildsLastElement.next:
newChildsLastElement.next.previous = newChildsLastElement
self.contents.insert(position, newChild)
def append(self, tag):
"""Appends the given tag to the contents of this tag."""
self.insert(len(self.contents), tag)
def findNext(self, name=None, attrs={}, text=None, **kwargs):
"""Returns the first item that matches the given criteria and
appears after this Tag in the document."""
return self._findOne(self.findAllNext, name, attrs, text, **kwargs)
def findAllNext(self, name=None, attrs={}, text=None, limit=None,
**kwargs):
"""Returns all items that match the given criteria and appear
after this Tag in the document."""
return self._findAll(name, attrs, text, limit, self.nextGenerator,
**kwargs)
def findNextSibling(self, name=None, attrs={}, text=None, **kwargs):
"""Returns the closest sibling to this Tag that matches the
given criteria and appears after this Tag in the document."""
return self._findOne(self.findNextSiblings, name, attrs, text,
**kwargs)
def findNextSiblings(self, name=None, attrs={}, text=None, limit=None,
**kwargs):
"""Returns the siblings of this Tag that match the given
criteria and appear after this Tag in the document."""
return self._findAll(name, attrs, text, limit,
self.nextSiblingGenerator, **kwargs)
fetchNextSiblings = findNextSiblings # Compatibility with pre-3.x
def findPrevious(self, name=None, attrs={}, text=None, **kwargs):
"""Returns the first item that matches the given criteria and
appears before this Tag in the document."""
return self._findOne(self.findAllPrevious, name, attrs, text, **kwargs)
def findAllPrevious(self, name=None, attrs={}, text=None, limit=None,
**kwargs):
"""Returns all items that match the given criteria and appear
before this Tag in the document."""
return self._findAll(name, attrs, text, limit, self.previousGenerator,
**kwargs)
fetchPrevious = findAllPrevious # Compatibility with pre-3.x
def findPreviousSibling(self, name=None, attrs={}, text=None, **kwargs):
"""Returns the closest sibling to this Tag that matches the
given criteria and appears before this Tag in the document."""
return self._findOne(self.findPreviousSiblings, name, attrs, text,
**kwargs)
def findPreviousSiblings(self, name=None, attrs={}, text=None,
limit=None, **kwargs):
"""Returns the siblings of this Tag that match the given
criteria and appear before this Tag in the document."""
return self._findAll(name, attrs, text, limit,
self.previousSiblingGenerator, **kwargs)
fetchPreviousSiblings = findPreviousSiblings # Compatibility with pre-3.x
def findParent(self, name=None, attrs={}, **kwargs):
"""Returns the closest parent of this Tag that matches the given
criteria."""
# NOTE: We can't use _findOne because findParents takes a different
# set of arguments.
r = None
l = self.findParents(name, attrs, 1)
if l:
r = l[0]
return r
def findParents(self, name=None, attrs={}, limit=None, **kwargs):
"""Returns the parents of this Tag that match the given
criteria."""
return self._findAll(name, attrs, None, limit, self.parentGenerator,
**kwargs)
fetchParents = findParents # Compatibility with pre-3.x
#These methods do the real heavy lifting.
def _findOne(self, method, name, attrs, text, **kwargs):
r = None
l = method(name, attrs, text, 1, **kwargs)
if l:
r = l[0]
return r
def _findAll(self, name, attrs, text, limit, generator, **kwargs):
"Iterates over a generator looking for things that match."
if isinstance(name, SoupStrainer):
strainer = name
else:
# Build a SoupStrainer
strainer = SoupStrainer(name, attrs, text, **kwargs)
results = ResultSet(strainer)
g = generator()
while True:
try:
i = g.next()
except StopIteration:
break
if i:
found = strainer.search(i)
if found:
results.append(found)
if limit and len(results) >= limit:
break
return results
#These Generators can be used to navigate starting from both
#NavigableStrings and Tags.
def nextGenerator(self):
i = self
while i:
i = i.next
yield i
def nextSiblingGenerator(self):
i = self
while i:
i = i.nextSibling
yield i
def previousGenerator(self):
i = self
while i:
i = i.previous
yield i
def previousSiblingGenerator(self):
i = self
while i:
i = i.previousSibling
yield i
def parentGenerator(self):
i = self
while i:
i = i.parent
yield i
# Utility methods
def substituteEncoding(self, str, encoding=None):
encoding = encoding or "utf-8"
return str.replace("%SOUP-ENCODING%", encoding)
def toEncoding(self, s, encoding=None):
"""Encodes an object to a string in some encoding, or to Unicode.
."""
if isinstance(s, unicode):
if encoding:
s = s.encode(encoding)
elif isinstance(s, str):
if encoding:
s = s.encode(encoding)
else:
s = unicode(s)
else:
if encoding:
s = self.toEncoding(str(s), encoding)
else:
s = unicode(s)
return s
class NavigableString(unicode, PageElement):
def __new__(cls, value):
"""Create a new NavigableString.
When unpickling a NavigableString, this method is called with
the string in DEFAULT_OUTPUT_ENCODING. That encoding needs to be
passed in to the superclass's __new__ or the superclass won't know
how to handle non-ASCII characters.
"""
if isinstance(value, unicode):
return unicode.__new__(cls, value)
return unicode.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
def __getnewargs__(self):
return (NavigableString.__str__(self),)
def __getattr__(self, attr):
"""text.string gives you text. This is for backwards
compatibility for Navigable*String, but for CData* it lets you
get the string without the CData wrapper."""
if attr == 'string':
return self
else:
raise AttributeError, "'%s' object has no attribute '%s'" % (self.__class__.__name__, attr)
def __unicode__(self):
return str(self).decode(DEFAULT_OUTPUT_ENCODING)
def __str__(self, encoding=DEFAULT_OUTPUT_ENCODING):
if encoding:
return self.encode(encoding)
else:
return self
class CData(NavigableString):
def __str__(self, encoding=DEFAULT_OUTPUT_ENCODING):
return "<![CDATA[%s]]>" % NavigableString.__str__(self, encoding)
class ProcessingInstruction(NavigableString):
def __str__(self, encoding=DEFAULT_OUTPUT_ENCODING):
output = self
if "%SOUP-ENCODING%" in output:
output = self.substituteEncoding(output, encoding)
return "<?%s?>" % self.toEncoding(output, encoding)
class Comment(NavigableString):
def __str__(self, encoding=DEFAULT_OUTPUT_ENCODING):
return "<!--%s-->" % NavigableString.__str__(self, encoding)
class Declaration(NavigableString):
def __str__(self, encoding=DEFAULT_OUTPUT_ENCODING):
return "<!%s>" % NavigableString.__str__(self, encoding)
class Tag(PageElement):
"""Represents a found HTML tag with its attributes and contents."""
def _invert(h):
"Cheap function to invert a hash."
i = {}
for k,v in h.items():
i[v] = k
return i
XML_ENTITIES_TO_SPECIAL_CHARS = { "apos" : "'",
"quot" : '"',
"amp" : "&",
"lt" : "<",
"gt" : ">" }
XML_SPECIAL_CHARS_TO_ENTITIES = _invert(XML_ENTITIES_TO_SPECIAL_CHARS)
def _convertEntities(self, match):
"""Used in a call to re.sub to replace HTML, XML, and numeric
entities with the appropriate Unicode characters. If HTML
entities are being converted, any unrecognized entities are
escaped."""
x = match.group(1)
if self.convertHTMLEntities and x in name2codepoint:
return unichr(name2codepoint[x])
elif x in self.XML_ENTITIES_TO_SPECIAL_CHARS:
if self.convertXMLEntities:
return self.XML_ENTITIES_TO_SPECIAL_CHARS[x]
else:
return u'&%s;' % x
elif len(x) > 0 and x[0] == '#':
# Handle numeric entities
if len(x) > 1 and x[1] == 'x':
return unichr(int(x[2:], 16))
else:
return unichr(int(x[1:]))
elif self.escapeUnrecognizedEntities:
return u'&amp;%s;' % x
else:
return u'&%s;' % x
def __init__(self, parser, name, attrs=None, parent=None,
previous=None):
"Basic constructor."
# We don't actually store the parser object: that lets extracted
# chunks be garbage-collected
self.parserClass = parser.__class__
self.isSelfClosing = parser.isSelfClosingTag(name)
self.name = name
if attrs == None:
attrs = []
self.attrs = attrs
self.contents = []
self.setup(parent, previous)
self.hidden = False
self.containsSubstitutions = False
self.convertHTMLEntities = parser.convertHTMLEntities
self.convertXMLEntities = parser.convertXMLEntities
self.escapeUnrecognizedEntities = parser.escapeUnrecognizedEntities
# Convert any HTML, XML, or numeric entities in the attribute values.
convert = lambda(k, val): (k,
re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);",
self._convertEntities,
val))
self.attrs = map(convert, self.attrs)
def get(self, key, default=None):
"""Returns the value of the 'key' attribute for the tag, or
the value given for 'default' if it doesn't have that
attribute."""
return self._getAttrMap().get(key, default)
def has_key(self, key):
return self._getAttrMap().has_key(key)
def __getitem__(self, key):
"""tag[key] returns the value of the 'key' attribute for the tag,
and throws an exception if it's not there."""
return self._getAttrMap()[key]
def __iter__(self):
"Iterating over a tag iterates over its contents."
return iter(self.contents)
def __len__(self):
"The length of a tag is the length of its list of contents."
return len(self.contents)
def __contains__(self, x):
return x in self.contents
def __nonzero__(self):
"A tag is non-None even if it has no contents."
return True
def __setitem__(self, key, value):
"""Setting tag[key] sets the value of the 'key' attribute for the
tag."""
self._getAttrMap()
self.attrMap[key] = value
found = False
for i in range(0, len(self.attrs)):
if self.attrs[i][0] == key:
self.attrs[i] = (key, value)
found = True
if not found:
self.attrs.append((key, value))
self._getAttrMap()[key] = value
def __delitem__(self, key):
"Deleting tag[key] deletes all 'key' attributes for the tag."
for item in self.attrs:
if item[0] == key:
self.attrs.remove(item)
#We don't break because bad HTML can define the same
#attribute multiple times.
self._getAttrMap()
if self.attrMap.has_key(key):
del self.attrMap[key]
def __call__(self, *args, **kwargs):
"""Calling a tag like a function is the same as calling its
findAll() method. Eg. tag('a') returns a list of all the A tags
found within this tag."""
return apply(self.findAll, args, kwargs)
def __getattr__(self, tag):
#print "Getattr %s.%s" % (self.__class__, tag)
if len(tag) > 3 and tag.rfind('Tag') == len(tag)-3:
return self.find(tag[:-3])
elif tag.find('__') != 0:
return self.find(tag)
raise AttributeError, "'%s' object has no attribute '%s'" % (self.__class__, tag)
def __eq__(self, other):
"""Returns true iff this tag has the same name, the same attributes,
and the same contents (recursively) as the given tag.
NOTE: right now this will return false if two tags have the
same attributes in a different order. Should this be fixed?"""
if not hasattr(other, 'name') or not hasattr(other, 'attrs') or not hasattr(other, 'contents') or self.name != other.name or self.attrs != other.attrs or len(self) != len(other):
return False
for i in range(0, len(self.contents)):
if self.contents[i] != other.contents[i]:
return False
return True
def __ne__(self, other):
"""Returns true iff this tag is not identical to the other tag,
as defined in __eq__."""
return not self == other
def __repr__(self, encoding=DEFAULT_OUTPUT_ENCODING):
"""Renders this tag as a string."""
return self.__str__(encoding)
def __unicode__(self):
return self.__str__(None)
BARE_AMPERSAND_OR_BRACKET = re.compile("([<>]|"
+ "&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)"
+ ")")
def _sub_entity(self, x):
"""Used with a regular expression to substitute the
appropriate XML entity for an XML special character."""
return "&" + self.XML_SPECIAL_CHARS_TO_ENTITIES[x.group(0)[0]] + ";"
def __str__(self, encoding=DEFAULT_OUTPUT_ENCODING,
prettyPrint=False, indentLevel=0):
"""Returns a string or Unicode representation of this tag and
its contents. To get Unicode, pass None for encoding.
NOTE: since Python's HTML parser consumes whitespace, this
method is not certain to reproduce the whitespace present in
the original string."""
encodedName = self.toEncoding(self.name, encoding)
attrs = []
if self.attrs:
for key, val in self.attrs:
fmt = '%s="%s"'
if isString(val):
if self.containsSubstitutions and '%SOUP-ENCODING%' in val:
val = self.substituteEncoding(val, encoding)
# The attribute value either:
#
# * Contains no embedded double quotes or single quotes.
# No problem: we enclose it in double quotes.
# * Contains embedded single quotes. No problem:
# double quotes work here too.
# * Contains embedded double quotes. No problem:
# we enclose it in single quotes.
# * Embeds both single _and_ double quotes. This
# can't happen naturally, but it can happen if
# you modify an attribute value after parsing
# the document. Now we have a bit of a
# problem. We solve it by enclosing the
# attribute in single quotes, and escaping any
# embedded single quotes to XML entities.
if '"' in val:
fmt = "%s='%s'"
if "'" in val:
# TODO: replace with apos when
# appropriate.
val = val.replace("'", "&squot;")
# Now we're okay w/r/t quotes. But the attribute
# value might also contain angle brackets, or
# ampersands that aren't part of entities. We need
# to escape those to XML entities too.
val = self.BARE_AMPERSAND_OR_BRACKET.sub(self._sub_entity, val)
attrs.append(fmt % (self.toEncoding(key, encoding),
self.toEncoding(val, encoding)))
close = ''
closeTag = ''
if self.isSelfClosing:
close = ' /'
else:
closeTag = '</%s>' % encodedName
indentTag, indentContents = 0, 0
if prettyPrint:
indentTag = indentLevel
space = (' ' * (indentTag-1))
indentContents = indentTag + 1
contents = self.renderContents(encoding, prettyPrint, indentContents)
if self.hidden:
s = contents
else:
s = []
attributeString = ''
if attrs:
attributeString = ' ' + ' '.join(attrs)
if prettyPrint:
s.append(space)
s.append('<%s%s%s>' % (encodedName, attributeString, close))
if prettyPrint:
s.append("\n")
s.append(contents)
if prettyPrint and contents and contents[-1] != "\n":
s.append("\n")
if prettyPrint and closeTag:
s.append(space)
s.append(closeTag)
if prettyPrint and closeTag and self.nextSibling:
s.append("\n")
s = ''.join(s)
return s
def decompose(self):
"""Recursively destroys the contents of this tree."""
contents = [i for i in self.contents]
for i in contents:
if isinstance(i, Tag):
i.decompose()
else:
i.extract()
self.extract()
def prettify(self, encoding=DEFAULT_OUTPUT_ENCODING):
return self.__str__(encoding, True)
def renderContents(self, encoding=DEFAULT_OUTPUT_ENCODING,
prettyPrint=False, indentLevel=0):
"""Renders the contents of this tag as a string in the given
encoding. If encoding is None, returns a Unicode string.."""
s=[]
for c in self:
text = None
if isinstance(c, NavigableString):
text = c.__str__(encoding)
elif isinstance(c, Tag):
s.append(c.__str__(encoding, prettyPrint, indentLevel))
if text and prettyPrint:
text = text.strip()
if text:
if prettyPrint:
s.append(" " * (indentLevel-1))
s.append(text)
if prettyPrint:
s.append("\n")
return ''.join(s)
#Soup methods
def find(self, name=None, attrs={}, recursive=True, text=None,
**kwargs):
"""Return only the first child of this Tag matching the given
criteria."""
r = None
l = self.findAll(name, attrs, recursive, text, 1, **kwargs)
if l:
r = l[0]
return r
findChild = find
def findAll(self, name=None, attrs={}, recursive=True, text=None,
limit=None, **kwargs):
"""Extracts a list of Tag objects that match the given
criteria. You can specify the name of the Tag and any
attributes you want the Tag to have.
The value of a key-value pair in the 'attrs' map can be a
string, a list of strings, a regular expression object, or a
callable that takes a string and returns whether or not the
string matches for some custom definition of 'matches'. The
same is true of the tag name."""
generator = self.recursiveChildGenerator
if not recursive:
generator = self.childGenerator
return self._findAll(name, attrs, text, limit, generator, **kwargs)
findChildren = findAll
# Pre-3.x compatibility methods
first = find
fetch = findAll
def fetchText(self, text=None, recursive=True, limit=None):
return self.findAll(text=text, recursive=recursive, limit=limit)
def firstText(self, text=None, recursive=True):
return self.find(text=text, recursive=recursive)
#Private methods
def _getAttrMap(self):
"""Initializes a map representation of this tag's attributes,
if not already initialized."""
if not getattr(self, 'attrMap'):
self.attrMap = {}
for (key, value) in self.attrs:
self.attrMap[key] = value
return self.attrMap
#Generator methods
def childGenerator(self):
for i in range(0, len(self.contents)):
yield self.contents[i]
raise StopIteration
def recursiveChildGenerator(self):
stack = [(self, 0)]
while stack:
tag, start = stack.pop()
if isinstance(tag, Tag):
for i in range(start, len(tag.contents)):
a = tag.contents[i]
yield a
if isinstance(a, Tag) and tag.contents:
if i < len(tag.contents) - 1:
stack.append((tag, i+1))
stack.append((a, 0))
break
raise StopIteration
# Next, a couple classes to represent queries and their results.
class SoupStrainer:
"""Encapsulates a number of ways of matching a markup element (tag or
text)."""
def __init__(self, name=None, attrs={}, text=None, **kwargs):
self.name = name
if isString(attrs):
kwargs['class'] = attrs
attrs = None
if kwargs:
if attrs:
attrs = attrs.copy()
attrs.update(kwargs)
else:
attrs = kwargs
self.attrs = attrs
self.text = text
def __str__(self):
if self.text:
return self.text
else:
return "%s|%s" % (self.name, self.attrs)
def searchTag(self, markupName=None, markupAttrs={}):
found = None
markup = None
if isinstance(markupName, Tag):
markup = markupName
markupAttrs = markup
callFunctionWithTagData = callable(self.name) \
and not isinstance(markupName, Tag)
if (not self.name) \
or callFunctionWithTagData \
or (markup and self._matches(markup, self.name)) \
or (not markup and self._matches(markupName, self.name)):
if callFunctionWithTagData:
match = self.name(markupName, markupAttrs)
else:
match = True
markupAttrMap = None
for attr, matchAgainst in self.attrs.items():
if not markupAttrMap:
if hasattr(markupAttrs, 'get'):
markupAttrMap = markupAttrs
else:
markupAttrMap = {}
for k,v in markupAttrs:
markupAttrMap[k] = v
attrValue = markupAttrMap.get(attr)
if not self._matches(attrValue, matchAgainst):
match = False
break
if match:
if markup:
found = markup
else:
found = markupName
return found
def search(self, markup):
#print 'looking for %s in %s' % (self, markup)
found = None
# If given a list of items, scan it for a text element that
# matches.
if isList(markup) and not isinstance(markup, Tag):
for element in markup:
if isinstance(element, NavigableString) \
and self.search(element):
found = element
break
# If it's a Tag, make sure its name or attributes match.
# Don't bother with Tags if we're searching for text.
elif isinstance(markup, Tag):
if not self.text:
found = self.searchTag(markup)
# If it's text, make sure the text matches.
elif isinstance(markup, NavigableString) or \
isString(markup):
if self._matches(markup, self.text):
found = markup
else:
raise Exception, "I don't know how to match against a %s" \
% markup.__class__
return found
def _matches(self, markup, matchAgainst):
#print "Matching %s against %s" % (markup, matchAgainst)
result = False
if matchAgainst == True and type(matchAgainst) == types.BooleanType:
result = markup != None
elif callable(matchAgainst):
result = matchAgainst(markup)
else:
#Custom match methods take the tag as an argument, but all
#other ways of matching match the tag name as a string.
if isinstance(markup, Tag):
markup = markup.name
if markup and not isString(markup):
markup = unicode(markup)
#Now we know that chunk is either a string, or None.
if hasattr(matchAgainst, 'match'):
# It's a regexp object.
result = markup and matchAgainst.search(markup)
elif isList(matchAgainst):
result = markup in matchAgainst
elif hasattr(matchAgainst, 'items'):
result = markup.has_key(matchAgainst)
elif matchAgainst and isString(markup):
if isinstance(markup, unicode):
matchAgainst = unicode(matchAgainst)
else:
matchAgainst = str(matchAgainst)
if not result:
result = matchAgainst == markup
return result
class ResultSet(list):
"""A ResultSet is just a list that keeps track of the SoupStrainer
that created it."""
def __init__(self, source):
list.__init__([])
self.source = source
# Now, some helper functions.
def isList(l):
"""Convenience method that works with all 2.x versions of Python
to determine whether or not something is listlike."""
return hasattr(l, '__iter__') \
or (type(l) in (types.ListType, types.TupleType))
def isString(s):
"""Convenience method that works with all 2.x versions of Python
to determine whether or not something is stringlike."""
try:
return isinstance(s, unicode) or isinstance(s, basestring)
except NameError:
return isinstance(s, str)
def buildTagMap(default, *args):
"""Turns a list of maps, lists, or scalars into a single map.
Used to build the SELF_CLOSING_TAGS, NESTABLE_TAGS, and
NESTING_RESET_TAGS maps out of lists and partial maps."""
built = {}
for portion in args:
if hasattr(portion, 'items'):
#It's a map. Merge it.
for k,v in portion.items():
built[k] = v
elif isList(portion):
#It's a list. Map each item to the default.
for k in portion:
built[k] = default
else:
#It's a scalar. Map it to the default.
built[portion] = default
return built
# Now, the parser classes.
class BeautifulStoneSoup(Tag, SGMLParser):
"""This class contains the basic parser and search code. It defines
a parser that knows nothing about tag behavior except for the
following:
You can't close a tag without closing all the tags it encloses.
That is, "<foo><bar></foo>" actually means
"<foo><bar></bar></foo>".
[Another possible explanation is "<foo><bar /></foo>", but since
this class defines no SELF_CLOSING_TAGS, it will never use that
explanation.]
This class is useful for parsing XML or made-up markup languages,
or when BeautifulSoup makes an assumption counter to what you were
expecting."""
SELF_CLOSING_TAGS = {}
NESTABLE_TAGS = {}
RESET_NESTING_TAGS = {}
QUOTE_TAGS = {}
PRESERVE_WHITESPACE_TAGS = []
MARKUP_MASSAGE = [(re.compile('(<[^<>]*)/>'),
lambda x: x.group(1) + ' />'),
(re.compile('<!\s+([^<>]*)>'),
lambda x: '<!' + x.group(1) + '>')
]
ROOT_TAG_NAME = u'[document]'
HTML_ENTITIES = "html"
XML_ENTITIES = "xml"
XHTML_ENTITIES = "xhtml"
# TODO: This only exists for backwards-compatibility
ALL_ENTITIES = XHTML_ENTITIES
# Used when determining whether a text node is all whitespace and
# can be replaced with a single space. A text node that contains
# fancy Unicode spaces (usually non-breaking) should be left
# alone.
STRIP_ASCII_SPACES = { 9: None, 10: None, 12: None, 13: None, 32: None, }
def __init__(self, markup="", parseOnlyThese=None, fromEncoding=None,
markupMassage=True, smartQuotesTo=XML_ENTITIES,
convertEntities=None, selfClosingTags=None, isHTML=False):
"""The Soup object is initialized as the 'root tag', and the
provided markup (which can be a string or a file-like object)
is fed into the underlying parser.
sgmllib will process most bad HTML, and the BeautifulSoup
class has some tricks for dealing with some HTML that kills
sgmllib, but Beautiful Soup can nonetheless choke or lose data
if your data uses self-closing tags or declarations
incorrectly.
By default, Beautiful Soup uses regexes to sanitize input,
avoiding the vast majority of these problems. If the problems
don't apply to you, pass in False for markupMassage, and
you'll get better performance.
The default parser massage techniques fix the two most common
instances of invalid HTML that choke sgmllib:
<br/> (No space between name of closing tag and tag close)
<! --Comment--> (Extraneous whitespace in declaration)
You can pass in a custom list of (RE object, replace method)
tuples to get Beautiful Soup to scrub your input the way you
want."""
self.parseOnlyThese = parseOnlyThese
self.fromEncoding = fromEncoding
self.smartQuotesTo = smartQuotesTo
self.convertEntities = convertEntities
# Set the rules for how we'll deal with the entities we
# encounter
if self.convertEntities:
# It doesn't make sense to convert encoded characters to
# entities even while you're converting entities to Unicode.
# Just convert it all to Unicode.
self.smartQuotesTo = None
if convertEntities == self.HTML_ENTITIES:
self.convertXMLEntities = False
self.convertHTMLEntities = True
self.escapeUnrecognizedEntities = True
elif convertEntities == self.XHTML_ENTITIES:
self.convertXMLEntities = True
self.convertHTMLEntities = True
self.escapeUnrecognizedEntities = False
elif convertEntities == self.XML_ENTITIES:
self.convertXMLEntities = True
self.convertHTMLEntities = False
self.escapeUnrecognizedEntities = False
else:
self.convertXMLEntities = False
self.convertHTMLEntities = False
self.escapeUnrecognizedEntities = False
self.instanceSelfClosingTags = buildTagMap(None, selfClosingTags)
SGMLParser.__init__(self)
if hasattr(markup, 'read'): # It's a file-type object.
markup = markup.read()
self.markup = markup
self.markupMassage = markupMassage
try:
self._feed(isHTML=isHTML)
except StopParsing:
pass
self.markup = None # The markup can now be GCed
def convert_charref(self, name):
"""This method fixes a bug in Python's SGMLParser."""
try:
n = int(name)
except ValueError:
return
if not 0 <= n <= 127 : # ASCII ends at 127, not 255
return
return self.convert_codepoint(n)
def _feed(self, inDocumentEncoding=None, isHTML=False):
# Convert the document to Unicode.
markup = self.markup
if isinstance(markup, unicode):
if not hasattr(self, 'originalEncoding'):
self.originalEncoding = None
else:
dammit = UnicodeDammit\
(markup, [self.fromEncoding, inDocumentEncoding],
smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
markup = dammit.unicode
self.originalEncoding = dammit.originalEncoding
self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
if markup:
if self.markupMassage:
if not isList(self.markupMassage):
self.markupMassage = self.MARKUP_MASSAGE
for fix, m in self.markupMassage:
markup = fix.sub(m, markup)
# TODO: We get rid of markupMassage so that the
# soup object can be deepcopied later on. Some
# Python installations can't copy regexes. If anyone
# was relying on the existence of markupMassage, this
# might cause problems.
del(self.markupMassage)
self.reset()
SGMLParser.feed(self, markup)
# Close out any unfinished strings and close all the open tags.
self.endData()
while self.currentTag.name != self.ROOT_TAG_NAME:
self.popTag()
def __getattr__(self, methodName):
"""This method routes method call requests to either the SGMLParser
superclass or the Tag superclass, depending on the method name."""
#print "__getattr__ called on %s.%s" % (self.__class__, methodName)
if methodName.find('start_') == 0 or methodName.find('end_') == 0 \
or methodName.find('do_') == 0:
return SGMLParser.__getattr__(self, methodName)
elif methodName.find('__') != 0:
return Tag.__getattr__(self, methodName)
else:
raise AttributeError
def isSelfClosingTag(self, name):
"""Returns true iff the given string is the name of a
self-closing tag according to this parser."""
return self.SELF_CLOSING_TAGS.has_key(name) \
or self.instanceSelfClosingTags.has_key(name)
def reset(self):
Tag.__init__(self, self, self.ROOT_TAG_NAME)
self.hidden = 1
SGMLParser.reset(self)
self.currentData = []
self.currentTag = None
self.tagStack = []
self.quoteStack = []
self.pushTag(self)
def popTag(self):
tag = self.tagStack.pop()
# Tags with just one string-owning child get the child as a
# 'string' property, so that soup.tag.string is shorthand for
# soup.tag.contents[0]
if len(self.currentTag.contents) == 1 and \
isinstance(self.currentTag.contents[0], NavigableString):
self.currentTag.string = self.currentTag.contents[0]
#print "Pop", tag.name
if self.tagStack:
self.currentTag = self.tagStack[-1]
return self.currentTag
def pushTag(self, tag):
#print "Push", tag.name
if self.currentTag:
self.currentTag.contents.append(tag)
self.tagStack.append(tag)
self.currentTag = self.tagStack[-1]
def endData(self, containerClass=NavigableString):
if self.currentData:
currentData = u''.join(self.currentData)
if (currentData.translate(self.STRIP_ASCII_SPACES) == '' and
not set([tag.name for tag in self.tagStack]).intersection(
self.PRESERVE_WHITESPACE_TAGS)):
if '\n' in currentData:
currentData = '\n'
else:
currentData = ' '
self.currentData = []
if self.parseOnlyThese and len(self.tagStack) <= 1 and \
(not self.parseOnlyThese.text or \
not self.parseOnlyThese.search(currentData)):
return
o = containerClass(currentData)
o.setup(self.currentTag, self.previous)
if self.previous:
self.previous.next = o
self.previous = o
self.currentTag.contents.append(o)
def _popToTag(self, name, inclusivePop=True):
"""Pops the tag stack up to and including the most recent
instance of the given tag. If inclusivePop is false, pops the tag
stack up to but *not* including the most recent instqance of
the given tag."""
#print "Popping to %s" % name
if name == self.ROOT_TAG_NAME:
return
numPops = 0
mostRecentTag = None
for i in range(len(self.tagStack)-1, 0, -1):
if name == self.tagStack[i].name:
numPops = len(self.tagStack)-i
break
if not inclusivePop:
numPops = numPops - 1
for i in range(0, numPops):
mostRecentTag = self.popTag()
return mostRecentTag
def _smartPop(self, name):
"""We need to pop up to the previous tag of this type, unless
one of this tag's nesting reset triggers comes between this
tag and the previous tag of this type, OR unless this tag is a
generic nesting trigger and another generic nesting trigger
comes between this tag and the previous tag of this type.
Examples:
<p>Foo<b>Bar *<p>* should pop to 'p', not 'b'.
<p>Foo<table>Bar *<p>* should pop to 'table', not 'p'.
<p>Foo<table><tr>Bar *<p>* should pop to 'tr', not 'p'.
<li><ul><li> *<li>* should pop to 'ul', not the first 'li'.
<tr><table><tr> *<tr>* should pop to 'table', not the first 'tr'
<td><tr><td> *<td>* should pop to 'tr', not the first 'td'
"""
nestingResetTriggers = self.NESTABLE_TAGS.get(name)
isNestable = nestingResetTriggers != None
isResetNesting = self.RESET_NESTING_TAGS.has_key(name)
popTo = None
inclusive = True
for i in range(len(self.tagStack)-1, 0, -1):
p = self.tagStack[i]
if (not p or p.name == name) and not isNestable:
#Non-nestable tags get popped to the top or to their
#last occurance.
popTo = name
break
if (nestingResetTriggers != None
and p.name in nestingResetTriggers) \
or (nestingResetTriggers == None and isResetNesting
and self.RESET_NESTING_TAGS.has_key(p.name)):
#If we encounter one of the nesting reset triggers
#peculiar to this tag, or we encounter another tag
#that causes nesting to reset, pop up to but not
#including that tag.
popTo = p.name
inclusive = False
break
p = p.parent
if popTo:
self._popToTag(popTo, inclusive)
def unknown_starttag(self, name, attrs, selfClosing=0):
#print "Start tag %s: %s" % (name, attrs)
if self.quoteStack:
#This is not a real tag.
#print "<%s> is not real!" % name
attrs = ''.join(map(lambda(x, y): ' %s="%s"' % (x, y), attrs))
self.handle_data('<%s%s>' % (name, attrs))
return
self.endData()
if not self.isSelfClosingTag(name) and not selfClosing:
self._smartPop(name)
if self.parseOnlyThese and len(self.tagStack) <= 1 \
and (self.parseOnlyThese.text or not self.parseOnlyThese.searchTag(name, attrs)):
return
tag = Tag(self, name, attrs, self.currentTag, self.previous)
if self.previous:
self.previous.next = tag
self.previous = tag
self.pushTag(tag)
if selfClosing or self.isSelfClosingTag(name):
self.popTag()
if name in self.QUOTE_TAGS:
#print "Beginning quote (%s)" % name
self.quoteStack.append(name)
self.literal = 1
return tag
def unknown_endtag(self, name):
#print "End tag %s" % name
if self.quoteStack and self.quoteStack[-1] != name:
#This is not a real end tag.
#print "</%s> is not real!" % name
self.handle_data('</%s>' % name)
return
self.endData()
self._popToTag(name)
if self.quoteStack and self.quoteStack[-1] == name:
self.quoteStack.pop()
self.literal = (len(self.quoteStack) > 0)
def handle_data(self, data):
self.currentData.append(data)
def _toStringSubclass(self, text, subclass):
"""Adds a certain piece of text to the tree as a NavigableString
subclass."""
self.endData()
self.handle_data(text)
self.endData(subclass)
def handle_pi(self, text):
"""Handle a processing instruction as a ProcessingInstruction
object, possibly one with a %SOUP-ENCODING% slot into which an
encoding will be plugged later."""
if text[:3] == "xml":
text = u"xml version='1.0' encoding='%SOUP-ENCODING%'"
self._toStringSubclass(text, ProcessingInstruction)
def handle_comment(self, text):
"Handle comments as Comment objects."
self._toStringSubclass(text, Comment)
def handle_charref(self, ref):
"Handle character references as data."
if self.convertEntities:
data = unichr(int(ref))
else:
data = '&#%s;' % ref
self.handle_data(data)
def handle_entityref(self, ref):
"""Handle entity references as data, possibly converting known
HTML and/or XML entity references to the corresponding Unicode
characters."""
data = None
if self.convertHTMLEntities:
try:
data = unichr(name2codepoint[ref])
except KeyError:
pass
if not data and self.convertXMLEntities:
data = self.XML_ENTITIES_TO_SPECIAL_CHARS.get(ref)
if not data and self.convertHTMLEntities and \
not self.XML_ENTITIES_TO_SPECIAL_CHARS.get(ref):
# TODO: We've got a problem here. We're told this is
# an entity reference, but it's not an XML entity
# reference or an HTML entity reference. Nonetheless,
# the logical thing to do is to pass it through as an
# unrecognized entity reference.
#
# Except: when the input is "&carol;" this function
# will be called with input "carol". When the input is
# "AT&T", this function will be called with input
# "T". We have no way of knowing whether a semicolon
# was present originally, so we don't know whether
# this is an unknown entity or just a misplaced
# ampersand.
#
# The more common case is a misplaced ampersand, so I
# escape the ampersand and omit the trailing semicolon.
data = "&amp;%s" % ref
if not data:
# This case is different from the one above, because we
# haven't already gone through a supposedly comprehensive
# mapping of entities to Unicode characters. We might not
# have gone through any mapping at all. So the chances are
# very high that this is a real entity, and not a
# misplaced ampersand.
data = "&%s;" % ref
self.handle_data(data)
def handle_decl(self, data):
"Handle DOCTYPEs and the like as Declaration objects."
self._toStringSubclass(data, Declaration)
def parse_declaration(self, i):
"""Treat a bogus SGML declaration as raw data. Treat a CDATA
declaration as a CData object."""
j = None
if self.rawdata[i:i+9] == '<![CDATA[':
k = self.rawdata.find(']]>', i)
if k == -1:
k = len(self.rawdata)
data = self.rawdata[i+9:k]
j = k+3
self._toStringSubclass(data, CData)
else:
try:
j = SGMLParser.parse_declaration(self, i)
except SGMLParseError:
toHandle = self.rawdata[i:]
self.handle_data(toHandle)
j = i + len(toHandle)
return j
class BeautifulSoup(BeautifulStoneSoup):
"""This parser knows the following facts about HTML:
* Some tags have no closing tag and should be interpreted as being
closed as soon as they are encountered.
* The text inside some tags (ie. 'script') may contain tags which
are not really part of the document and which should be parsed
as text, not tags. If you want to parse the text as tags, you can
always fetch it and parse it explicitly.
* Tag nesting rules:
Most tags can't be nested at all. For instance, the occurance of
a <p> tag should implicitly close the previous <p> tag.
<p>Para1<p>Para2
should be transformed into:
<p>Para1</p><p>Para2
Some tags can be nested arbitrarily. For instance, the occurance
of a <blockquote> tag should _not_ implicitly close the previous
<blockquote> tag.
Alice said: <blockquote>Bob said: <blockquote>Blah
should NOT be transformed into:
Alice said: <blockquote>Bob said: </blockquote><blockquote>Blah
Some tags can be nested, but the nesting is reset by the
interposition of other tags. For instance, a <tr> tag should
implicitly close the previous <tr> tag within the same <table>,
but not close a <tr> tag in another table.
<table><tr>Blah<tr>Blah
should be transformed into:
<table><tr>Blah</tr><tr>Blah
but,
<tr>Blah<table><tr>Blah
should NOT be transformed into
<tr>Blah<table></tr><tr>Blah
Differing assumptions about tag nesting rules are a major source
of problems with the BeautifulSoup class. If BeautifulSoup is not
treating as nestable a tag your page author treats as nestable,
try ICantBelieveItsBeautifulSoup, MinimalSoup, or
BeautifulStoneSoup before writing your own subclass."""
def __init__(self, *args, **kwargs):
if not kwargs.has_key('smartQuotesTo'):
kwargs['smartQuotesTo'] = self.HTML_ENTITIES
kwargs['isHTML'] = True
BeautifulStoneSoup.__init__(self, *args, **kwargs)
SELF_CLOSING_TAGS = buildTagMap(None,
['br' , 'hr', 'input', 'img', 'meta',
'spacer', 'link', 'frame', 'base'])
PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea'])
QUOTE_TAGS = {'script' : None, 'textarea' : None}
#According to the HTML standard, each of these inline tags can
#contain another tag of the same type. Furthermore, it's common
#to actually use these tags this way.
NESTABLE_INLINE_TAGS = ['span', 'font', 'q', 'object', 'bdo', 'sub', 'sup',
'center']
#According to the HTML standard, these block tags can contain
#another tag of the same type. Furthermore, it's common
#to actually use these tags this way.
NESTABLE_BLOCK_TAGS = ['blockquote', 'div', 'fieldset', 'ins', 'del']
#Lists can contain other lists, but there are restrictions.
NESTABLE_LIST_TAGS = { 'ol' : [],
'ul' : [],
'li' : ['ul', 'ol'],
'dl' : [],
'dd' : ['dl'],
'dt' : ['dl'] }
#Tables can contain other tables, but there are restrictions.
NESTABLE_TABLE_TAGS = {'table' : [],
'tr' : ['table', 'tbody', 'tfoot', 'thead'],
'td' : ['tr'],
'th' : ['tr'],
'thead' : ['table'],
'tbody' : ['table'],
'tfoot' : ['table'],
}
NON_NESTABLE_BLOCK_TAGS = ['address', 'form', 'p', 'pre']
#If one of these tags is encountered, all tags up to the next tag of
#this type are popped.
RESET_NESTING_TAGS = buildTagMap(None, NESTABLE_BLOCK_TAGS, 'noscript',
NON_NESTABLE_BLOCK_TAGS,
NESTABLE_LIST_TAGS,
NESTABLE_TABLE_TAGS)
NESTABLE_TAGS = buildTagMap([], NESTABLE_INLINE_TAGS, NESTABLE_BLOCK_TAGS,
NESTABLE_LIST_TAGS, NESTABLE_TABLE_TAGS)
# Used to detect the charset in a META tag; see start_meta
CHARSET_RE = re.compile("((^|;)\s*charset=)([^;]*)", re.M)
def start_meta(self, attrs):
"""Beautiful Soup can detect a charset included in a META tag,
try to convert the document to that charset, and re-parse the
document from the beginning."""
httpEquiv = None
contentType = None
contentTypeIndex = None
tagNeedsEncodingSubstitution = False
for i in range(0, len(attrs)):
key, value = attrs[i]
key = key.lower()
if key == 'http-equiv':
httpEquiv = value
elif key == 'content':
contentType = value
contentTypeIndex = i
if httpEquiv and contentType: # It's an interesting meta tag.
match = self.CHARSET_RE.search(contentType)
if match:
if (self.declaredHTMLEncoding is not None or
self.originalEncoding == self.fromEncoding):
# An HTML encoding was sniffed while converting
# the document to Unicode, or an HTML encoding was
# sniffed during a previous pass through the
# document, or an encoding was specified
# explicitly and it worked. Rewrite the meta tag.
def rewrite(match):
return match.group(1) + "%SOUP-ENCODING%"
newAttr = self.CHARSET_RE.sub(rewrite, contentType)
attrs[contentTypeIndex] = (attrs[contentTypeIndex][0],
newAttr)
tagNeedsEncodingSubstitution = True
else:
# This is our first pass through the document.
# Go through it again with the encoding information.
newCharset = match.group(3)
if newCharset and newCharset != self.originalEncoding:
self.declaredHTMLEncoding = newCharset
self._feed(self.declaredHTMLEncoding)
raise StopParsing
pass
tag = self.unknown_starttag("meta", attrs)
if tag and tagNeedsEncodingSubstitution:
tag.containsSubstitutions = True
class StopParsing(Exception):
pass
class ICantBelieveItsBeautifulSoup(BeautifulSoup):
"""The BeautifulSoup class is oriented towards skipping over
common HTML errors like unclosed tags. However, sometimes it makes
errors of its own. For instance, consider this fragment:
<b>Foo<b>Bar</b></b>
This is perfectly valid (if bizarre) HTML. However, the
BeautifulSoup class will implicitly close the first b tag when it
encounters the second 'b'. It will think the author wrote
"<b>Foo<b>Bar", and didn't close the first 'b' tag, because
there's no real-world reason to bold something that's already
bold. When it encounters '</b></b>' it will close two more 'b'
tags, for a grand total of three tags closed instead of two. This
can throw off the rest of your document structure. The same is
true of a number of other tags, listed below.
It's much more common for someone to forget to close a 'b' tag
than to actually use nested 'b' tags, and the BeautifulSoup class
handles the common case. This class handles the not-co-common
case: where you can't believe someone wrote what they did, but
it's valid HTML and BeautifulSoup screwed up by assuming it
wouldn't be."""
I_CANT_BELIEVE_THEYRE_NESTABLE_INLINE_TAGS = \
['em', 'big', 'i', 'small', 'tt', 'abbr', 'acronym', 'strong',
'cite', 'code', 'dfn', 'kbd', 'samp', 'strong', 'var', 'b',
'big']
I_CANT_BELIEVE_THEYRE_NESTABLE_BLOCK_TAGS = ['noscript']
NESTABLE_TAGS = buildTagMap([], BeautifulSoup.NESTABLE_TAGS,
I_CANT_BELIEVE_THEYRE_NESTABLE_BLOCK_TAGS,
I_CANT_BELIEVE_THEYRE_NESTABLE_INLINE_TAGS)
class MinimalSoup(BeautifulSoup):
"""The MinimalSoup class is for parsing HTML that contains
pathologically bad markup. It makes no assumptions about tag
nesting, but it does know which tags are self-closing, that
<script> tags contain Javascript and should not be parsed, that
META tags may contain encoding information, and so on.
This also makes it better for subclassing than BeautifulStoneSoup
or BeautifulSoup."""
RESET_NESTING_TAGS = buildTagMap('noscript')
NESTABLE_TAGS = {}
class BeautifulSOAP(BeautifulStoneSoup):
"""This class will push a tag with only a single string child into
the tag's parent as an attribute. The attribute's name is the tag
name, and the value is the string child. An example should give
the flavor of the change:
<foo><bar>baz</bar></foo>
=>
<foo bar="baz"><bar>baz</bar></foo>
You can then access fooTag['bar'] instead of fooTag.barTag.string.
This is, of course, useful for scraping structures that tend to
use subelements instead of attributes, such as SOAP messages. Note
that it modifies its input, so don't print the modified version
out.
I'm not sure how many people really want to use this class; let me
know if you do. Mainly I like the name."""
def popTag(self):
if len(self.tagStack) > 1:
tag = self.tagStack[-1]
parent = self.tagStack[-2]
parent._getAttrMap()
if (isinstance(tag, Tag) and len(tag.contents) == 1 and
isinstance(tag.contents[0], NavigableString) and
not parent.attrMap.has_key(tag.name)):
parent[tag.name] = tag.contents[0]
BeautifulStoneSoup.popTag(self)
#Enterprise class names! It has come to our attention that some people
#think the names of the Beautiful Soup parser classes are too silly
#and "unprofessional" for use in enterprise screen-scraping. We feel
#your pain! For such-minded folk, the Beautiful Soup Consortium And
#All-Night Kosher Bakery recommends renaming this file to
#"RobustParser.py" (or, in cases of extreme enterprisiness,
#"RobustParserBeanInterface.class") and using the following
#enterprise-friendly class aliases:
class RobustXMLParser(BeautifulStoneSoup):
pass
class RobustHTMLParser(BeautifulSoup):
pass
class RobustWackAssHTMLParser(ICantBelieveItsBeautifulSoup):
pass
class RobustInsanelyWackAssHTMLParser(MinimalSoup):
pass
class SimplifyingSOAPParser(BeautifulSOAP):
pass
######################################################
#
# Bonus library: Unicode, Dammit
#
# This class forces XML data into a standard format (usually to UTF-8
# or Unicode). It is heavily based on code from Mark Pilgrim's
# Universal Feed Parser. It does not rewrite the XML or HTML to
# reflect a new encoding: that happens in BeautifulStoneSoup.handle_pi
# (XML) and BeautifulSoup.start_meta (HTML).
# Autodetects character encodings.
# Download from http://chardet.feedparser.org/
try:
import chardet
# import chardet.constants
# chardet.constants._debug = 1
except ImportError:
chardet = None
# cjkcodecs and iconv_codec make Python know about more character encodings.
# Both are available from http://cjkpython.i18n.org/
# They're built in if you use Python 2.4.
try:
import cjkcodecs.aliases
except ImportError:
pass
try:
import iconv_codec
except ImportError:
pass
class UnicodeDammit:
"""A class for detecting the encoding of a *ML document and
converting it to a Unicode string. If the source encoding is
windows-1252, can replace MS smart quotes with their HTML or XML
equivalents."""
# This dictionary maps commonly seen values for "charset" in HTML
# meta tags to the corresponding Python codec names. It only covers
# values that aren't in Python's aliases and can't be determined
# by the heuristics in find_codec.
CHARSET_ALIASES = { "macintosh" : "mac-roman",
"x-sjis" : "shift-jis" }
def __init__(self, markup, overrideEncodings=[],
smartQuotesTo='xml', isHTML=False):
self.declaredHTMLEncoding = None
self.markup, documentEncoding, sniffedEncoding = \
self._detectEncoding(markup, isHTML)
self.smartQuotesTo = smartQuotesTo
self.triedEncodings = []
if markup == '' or isinstance(markup, unicode):
self.originalEncoding = None
self.unicode = unicode(markup)
return
u = None
for proposedEncoding in overrideEncodings:
u = self._convertFrom(proposedEncoding)
if u: break
if not u:
for proposedEncoding in (documentEncoding, sniffedEncoding):
u = self._convertFrom(proposedEncoding)
if u: break
# If no luck and we have auto-detection library, try that:
if not u and chardet and not isinstance(self.markup, unicode):
u = self._convertFrom(chardet.detect(self.markup)['encoding'])
# As a last resort, try utf-8 and windows-1252:
if not u:
for proposed_encoding in ("utf-8", "windows-1252"):
u = self._convertFrom(proposed_encoding)
if u: break
self.unicode = u
if not u: self.originalEncoding = None
def _subMSChar(self, orig):
"""Changes a MS smart quote character to an XML or HTML
entity."""
sub = self.MS_CHARS.get(orig)
if type(sub) == types.TupleType:
if self.smartQuotesTo == 'xml':
sub = '&#x%s;' % sub[1]
else:
sub = '&%s;' % sub[0]
return sub
def _convertFrom(self, proposed):
proposed = self.find_codec(proposed)
if not proposed or proposed in self.triedEncodings:
return None
self.triedEncodings.append(proposed)
markup = self.markup
# Convert smart quotes to HTML if coming from an encoding
# that might have them.
if self.smartQuotesTo and proposed.lower() in("windows-1252",
"iso-8859-1",
"iso-8859-2"):
markup = re.compile("([\x80-\x9f])").sub \
(lambda(x): self._subMSChar(x.group(1)),
markup)
try:
# print "Trying to convert document to %s" % proposed
u = self._toUnicode(markup, proposed)
self.markup = u
self.originalEncoding = proposed
except Exception, e:
# print "That didn't work!"
# print e
return None
#print "Correct encoding: %s" % proposed
return self.markup
def _toUnicode(self, data, encoding):
'''Given a string and its encoding, decodes the string into Unicode.
%encoding is a string recognized by encodings.aliases'''
# strip Byte Order Mark (if present)
if (len(data) >= 4) and (data[:2] == '\xfe\xff') \
and (data[2:4] != '\x00\x00'):
encoding = 'utf-16be'
data = data[2:]
elif (len(data) >= 4) and (data[:2] == '\xff\xfe') \
and (data[2:4] != '\x00\x00'):
encoding = 'utf-16le'
data = data[2:]
elif data[:3] == '\xef\xbb\xbf':
encoding = 'utf-8'
data = data[3:]
elif data[:4] == '\x00\x00\xfe\xff':
encoding = 'utf-32be'
data = data[4:]
elif data[:4] == '\xff\xfe\x00\x00':
encoding = 'utf-32le'
data = data[4:]
newdata = unicode(data, encoding)
return newdata
def _detectEncoding(self, xml_data, isHTML=False):
"""Given a document, tries to detect its XML encoding."""
xml_encoding = sniffed_xml_encoding = None
try:
if xml_data[:4] == '\x4c\x6f\xa7\x94':
# EBCDIC
xml_data = self._ebcdic_to_ascii(xml_data)
elif xml_data[:4] == '\x00\x3c\x00\x3f':
# UTF-16BE
sniffed_xml_encoding = 'utf-16be'
xml_data = unicode(xml_data, 'utf-16be').encode('utf-8')
elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') \
and (xml_data[2:4] != '\x00\x00'):
# UTF-16BE with BOM
sniffed_xml_encoding = 'utf-16be'
xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8')
elif xml_data[:4] == '\x3c\x00\x3f\x00':
# UTF-16LE
sniffed_xml_encoding = 'utf-16le'
xml_data = unicode(xml_data, 'utf-16le').encode('utf-8')
elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and \
(xml_data[2:4] != '\x00\x00'):
# UTF-16LE with BOM
sniffed_xml_encoding = 'utf-16le'
xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8')
elif xml_data[:4] == '\x00\x00\x00\x3c':
# UTF-32BE
sniffed_xml_encoding = 'utf-32be'
xml_data = unicode(xml_data, 'utf-32be').encode('utf-8')
elif xml_data[:4] == '\x3c\x00\x00\x00':
# UTF-32LE
sniffed_xml_encoding = 'utf-32le'
xml_data = unicode(xml_data, 'utf-32le').encode('utf-8')
elif xml_data[:4] == '\x00\x00\xfe\xff':
# UTF-32BE with BOM
sniffed_xml_encoding = 'utf-32be'
xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8')
elif xml_data[:4] == '\xff\xfe\x00\x00':
# UTF-32LE with BOM
sniffed_xml_encoding = 'utf-32le'
xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8')
elif xml_data[:3] == '\xef\xbb\xbf':
# UTF-8 with BOM
sniffed_xml_encoding = 'utf-8'
xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8')
else:
sniffed_xml_encoding = 'ascii'
pass
except:
xml_encoding_match = None
xml_encoding_match = re.compile(
'^<\?.*encoding=[\'"](.*?)[\'"].*\?>').match(xml_data)
if not xml_encoding_match and isHTML:
regexp = re.compile('<\s*meta[^>]+charset=([^>]*?)[;\'">]', re.I)
xml_encoding_match = regexp.search(xml_data)
if xml_encoding_match is not None:
xml_encoding = xml_encoding_match.groups()[0].lower()
if isHTML:
self.declaredHTMLEncoding = xml_encoding
if sniffed_xml_encoding and \
(xml_encoding in ('iso-10646-ucs-2', 'ucs-2', 'csunicode',
'iso-10646-ucs-4', 'ucs-4', 'csucs4',
'utf-16', 'utf-32', 'utf_16', 'utf_32',
'utf16', 'u16')):
xml_encoding = sniffed_xml_encoding
return xml_data, xml_encoding, sniffed_xml_encoding
def find_codec(self, charset):
return self._codec(self.CHARSET_ALIASES.get(charset, charset)) \
or (charset and self._codec(charset.replace("-", ""))) \
or (charset and self._codec(charset.replace("-", "_"))) \
or charset
def _codec(self, charset):
if not charset: return charset
codec = None
try:
codecs.lookup(charset)
codec = charset
except (LookupError, ValueError):
pass
return codec
EBCDIC_TO_ASCII_MAP = None
def _ebcdic_to_ascii(self, s):
c = self.__class__
if not c.EBCDIC_TO_ASCII_MAP:
emap = (0,1,2,3,156,9,134,127,151,141,142,11,12,13,14,15,
16,17,18,19,157,133,8,135,24,25,146,143,28,29,30,31,
128,129,130,131,132,10,23,27,136,137,138,139,140,5,6,7,
144,145,22,147,148,149,150,4,152,153,154,155,20,21,158,26,
32,160,161,162,163,164,165,166,167,168,91,46,60,40,43,33,
38,169,170,171,172,173,174,175,176,177,93,36,42,41,59,94,
45,47,178,179,180,181,182,183,184,185,124,44,37,95,62,63,
186,187,188,189,190,191,192,193,194,96,58,35,64,39,61,34,
195,97,98,99,100,101,102,103,104,105,196,197,198,199,200,
201,202,106,107,108,109,110,111,112,113,114,203,204,205,
206,207,208,209,126,115,116,117,118,119,120,121,122,210,
211,212,213,214,215,216,217,218,219,220,221,222,223,224,
225,226,227,228,229,230,231,123,65,66,67,68,69,70,71,72,
73,232,233,234,235,236,237,125,74,75,76,77,78,79,80,81,
82,238,239,240,241,242,243,92,159,83,84,85,86,87,88,89,
90,244,245,246,247,248,249,48,49,50,51,52,53,54,55,56,57,
250,251,252,253,254,255)
import string
c.EBCDIC_TO_ASCII_MAP = string.maketrans( \
''.join(map(chr, range(256))), ''.join(map(chr, emap)))
return s.translate(c.EBCDIC_TO_ASCII_MAP)
MS_CHARS = { '\x80' : ('euro', '20AC'),
'\x81' : ' ',
'\x82' : ('sbquo', '201A'),
'\x83' : ('fnof', '192'),
'\x84' : ('bdquo', '201E'),
'\x85' : ('hellip', '2026'),
'\x86' : ('dagger', '2020'),
'\x87' : ('Dagger', '2021'),
'\x88' : ('circ', '2C6'),
'\x89' : ('permil', '2030'),
'\x8A' : ('Scaron', '160'),
'\x8B' : ('lsaquo', '2039'),
'\x8C' : ('OElig', '152'),
'\x8D' : '?',
'\x8E' : ('#x17D', '17D'),
'\x8F' : '?',
'\x90' : '?',
'\x91' : ('lsquo', '2018'),
'\x92' : ('rsquo', '2019'),
'\x93' : ('ldquo', '201C'),
'\x94' : ('rdquo', '201D'),
'\x95' : ('bull', '2022'),
'\x96' : ('ndash', '2013'),
'\x97' : ('mdash', '2014'),
'\x98' : ('tilde', '2DC'),
'\x99' : ('trade', '2122'),
'\x9a' : ('scaron', '161'),
'\x9b' : ('rsaquo', '203A'),
'\x9c' : ('oelig', '153'),
'\x9d' : '?',
'\x9e' : ('#x17E', '17E'),
'\x9f' : ('Yuml', ''),}
#######################################################################
#By default, act as an HTML pretty-printer.
if __name__ == '__main__':
import sys
soup = BeautifulSoup(sys.stdin)
print soup.prettify()