Source

pyquery / pyquery / pyquery.py

   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
#-*- coding:utf-8 -*-
#
# Copyright (C) 2008 - Olivier Lauzanne <olauzanne@gmail.com>
#
# Distributed under the BSD license, see LICENSE.txt
from .cssselectpatch import JQueryTranslator
from copy import deepcopy
from lxml import etree
import lxml.html
import sys

PY3k = sys.version_info >= (3,)

if PY3k:
    from urllib.request import urlopen
    from urllib.parse import urlencode
    from urllib.parse import urljoin
    basestring = (str, bytes)
    unicode = str
else:
    from urllib2 import urlopen  # NOQA
    from urllib import urlencode  # NOQA
    from urlparse import urljoin  # NOQA


def func_globals(f):
    return f.__globals__ if PY3k else f.func_globals


def func_code(f):
    return f.__code__ if PY3k else f.func_code


def fromstring(context, parser=None, custom_parser=None):
    """use html parser if we don't have clean xml
    """
    if hasattr(context, 'read') and hasattr(context.read, '__call__'):
        meth = 'parse'
    else:
        meth = 'fromstring'
    if custom_parser is None:
        if parser is None:
            try:
                result = getattr(etree, meth)(context)
            except etree.XMLSyntaxError:
                result = getattr(lxml.html, meth)(context)
            if isinstance(result, etree._ElementTree):
                return [result.getroot()]
            else:
                return [result]
        elif parser == 'xml':
            custom_parser = getattr(etree, meth)
        elif parser == 'html':
            custom_parser = getattr(lxml.html, meth)
        elif parser == 'soup':
            from  lxml.html import soupparser
            custom_parser = getattr(soupparser, meth)
        elif parser == 'html_fragments':
            custom_parser = lxml.html.fragments_fromstring
        else:
            ValueError('No such parser: "%s"' % parser)

    result = custom_parser(context)
    if type(result) is list:
        return result
    elif isinstance(result, etree._ElementTree):
        return [result.getroot()]
    else:
        return [result]


def callback(func, *args):
    return func(*args[:func_code(func).co_argcount])


class NoDefault(object):
    def __repr__(self):
        """clean representation in Sphinx"""
        return '<NoDefault>'

no_default = NoDefault()
del NoDefault


class FlexibleElement(object):
    """property to allow a flexible api"""
    def __init__(self, pget, pset=no_default, pdel=no_default):
        self.pget = pget
        self.pset = pset
        self.pdel = pdel

    def __get__(self, instance, klass):
        class _element(object):
            """real element to support set/get/del attr and item and js call
            style"""
            def __call__(prop, *args, **kwargs):
                return self.pget(instance, *args, **kwargs)
            __getattr__ = __getitem__ = __setattr__ = __setitem__ = __call__

            def __delitem__(prop, name):
                if self.pdel is not no_default:
                    return self.pdel(instance, name)
                else:
                    raise NotImplementedError()
            __delattr__ = __delitem__

            def __repr__(prop):
                return '<flexible_element %s>' % self.pget.__name__
        return _element()

    def __set__(self, instance, value):
        if self.pset is not no_default:
            self.pset(instance, value)
        else:
            raise NotImplementedError()


class PyQuery(list):
    """The main class
    """
    def __init__(self, *args, **kwargs):
        html = None
        elements = []
        self._base_url = None
        self.parser = kwargs.get('parser', None)
        if 'parser' in kwargs:
            del kwargs['parser']

        if len(args) >= 1 and \
           (not PY3k and isinstance(args[0], basestring) or \
            PY3k and isinstance(args[0], str)) and \
           args[0].startswith('http://'):
            kwargs['url'] = args[0]
            if len(args) >= 2:
                kwargs['data'] = args[1]
            args = []

        if 'parent' in kwargs:
            self._parent = kwargs.pop('parent')
        else:
            self._parent = no_default

        if 'css_translator' in kwargs:
            self._translator = kwargs.pop('css_translator')
        elif self.parser in ('xml',):
            self._translator = JQueryTranslator(xhtml=True)
        elif self._parent is not no_default:
            self._translator = self._parent._translator
        else:
            self._translator = JQueryTranslator(xhtml=False)

        namespaces = kwargs.get('namespaces', {})
        if 'namespaces' in kwargs:
            del kwargs['namespaces']

        if kwargs:
            # specific case to get the dom
            if 'filename' in kwargs:
                fd = open(kwargs['filename'])
                html = fd.read()
                fd.close()
            elif 'url' in kwargs:
                url = kwargs.pop('url')
                if 'opener' in kwargs:
                    opener = kwargs.pop('opener')
                    html = opener(url)
                else:
                    method = kwargs.get('method')
                    data = kwargs.get('data')
                    if type(data) in (dict, list, tuple):
                        data = urlencode(data)

                    if isinstance(method, basestring) and \
                       method.lower() == 'get' and data:
                        if '?' not in url:
                            url += '?'
                        elif url[-1] not in ('?', '&'):
                            url += '&'
                        url += data
                        data = None

                    if data and PY3k:
                        data = data.encode('utf-8')

                    html = urlopen(url, data)
                    if not self.parser:
                        self.parser = 'html'
                self._base_url = url
            else:
                raise ValueError('Invalid keyword arguments %s' % kwargs)
            elements = fromstring(html, self.parser)
        else:
            # get nodes

            # determine context and selector if any
            selector = context = no_default
            length = len(args)
            if length == 1:
                context = args[0]
            elif length == 2:
                selector, context = args
            else:
                raise ValueError("You can't do that." +\
                        " Please, provide arguments")

            # get context
            if isinstance(context, basestring):
                try:
                    elements = fromstring(context, self.parser)
                except Exception:
                    raise
                    raise ValueError(repr(context))
            elif isinstance(context, self.__class__):
                # copy
                elements = context[:]
            elif isinstance(context, list):
                elements = context
            elif isinstance(context, etree._Element):
                elements = [context]

            # select nodes
            if elements and selector is not no_default:
                xpath = self._css_to_xpath(selector)
                results = [tag.xpath(xpath, namespaces=namespaces) \
                                                    for tag in elements]
                # Flatten the results
                elements = []
                for r in results:
                    elements.extend(r)

        list.__init__(self, elements)

    def _css_to_xpath(self, selector, prefix='descendant-or-self::'):
        selector = selector.replace('[@', '[')
        return self._translator.css_to_xpath(selector, prefix)

    def __call__(self, *args, **kwargs):
        """return a new PyQuery instance
        """
        length = len(args)
        if length == 0:
            raise ValueError('You must provide at least a selector')
        if args[0] == '':
            return self.__class__([])
        if len(args) == 1 and \
           isinstance(args[0], str) and \
           not args[0].startswith('<'):
            args += (self,)
        result = self.__class__(*args, parent=self, **kwargs)
        return result

    # keep original list api prefixed with _
    _append = list.append
    _extend = list.extend

    # improve pythonic api
    def __add__(self, other):
        assert isinstance(other, self.__class__)
        return self.__class__(self[:] + other[:])

    def extend(self, other):
        """Extend with anoter PyQuery object"""
        assert isinstance(other, self.__class__)
        self._extend(other[:])

    def items(self, selector=None):
        """Iter over elements. Return PyQuery objects:

            >>> d = PyQuery('<div><span>foo</span><span>bar</span></div>')
            >>> [i.text() for i in d.items('span')]
            ['foo', 'bar']
            >>> [i.text() for i in d('span').items()]
            ['foo', 'bar']
        """
        elems = selector and self(selector) or self
        for elem in elems:
            yield self.__class__(elem)

    def __str__(self):
        """xml representation of current nodes::

            >>> xml = PyQuery(
            ...   '<script><![[CDATA[ ]></script>', parser='html_fragments')
            >>> print(str(xml))
            <script>&lt;![[CDATA[ ]&gt;</script>

        """
        if PY3k:
            return ''.join([etree.tostring(e, encoding=str) for e in self])
        else:
            return ''.join([etree.tostring(e) for e in self])

    def __unicode__(self):
        """xml representation of current nodes"""
        return unicode('').join([etree.tostring(e, encoding=unicode) \
                                                        for e in self])

    def __html__(self):
        """html representation of current nodes::

            >>> html = PyQuery(
            ...   '<script><![[CDATA[ ]></script>', parser='html_fragments')
            >>> print(html.__html__())
            <script><![[CDATA[ ]></script>

        """
        return unicode('').join([lxml.html.tostring(e, encoding=unicode) \
                                                            for e in self])

    def __repr__(self):
        r = []
        try:
            for el in self:
                c = el.get('class')
                c = c and '.' + '.'.join(c.split(' ')) or ''
                id = el.get('id')
                id = id and '#' + id or ''
                r.append('<%s%s%s>' % (el.tag, id, c))
            return '[' + (', '.join(r)) + ']'
        except AttributeError:
            if PY3k:
                return list.__repr__(self)
            else:
                for el in self:
                    if isinstance(el, unicode):
                        r.append(el.encode('utf-8'))
                    else:
                        r.append(el)
                return repr(r)

    @property
    def root(self):
        """return the xml root element
        """
        if self._parent is not no_default:
            return self._parent.getroottree()
        return self[0].getroottree()

    @property
    def encoding(self):
        """return the xml encoding of the root element
        """
        root = self.root
        if root is not None:
            return self.root.docinfo.encoding

    ##############
    # Traversing #
    ##############

    def _filter_only(self, selector, elements, reverse=False, unique=False):
        """Filters the selection set only, as opposed to also including
           descendants.
        """
        if selector is None:
            results = elements
        else:
            xpath = self._css_to_xpath(selector, 'self::')
            results = []
            for tag in elements:
                results.extend(tag.xpath(xpath))
        if reverse:
            results.reverse()
        if unique:
            result_list = results
            results = []
            for item in result_list:
                if not item in results:
                    results.append(item)
        return self.__class__(results, **dict(parent=self))

    def parent(self, selector=None):
        return self._filter_only(
                   selector,
                   [e.getparent() for e in self if e.getparent() is not None],
                   unique=True)

    def prev(self, selector=None):
        return self._filter_only(
               selector,
               [e.getprevious() for e in self if e.getprevious() is not None])

    def next(self, selector=None):
        return self._filter_only(
               selector,
               [e.getnext() for e in self if e.getnext() is not None])

    def _traverse(self, method):
        for e in self:
            current = getattr(e, method)()
            while current is not None:
                yield current
                current = getattr(current, method)()

    def _traverse_parent_topdown(self):
        for e in self:
            this_list = []
            current = e.getparent()
            while current is not None:
                this_list.append(current)
                current = current.getparent()
            this_list.reverse()
            for j in this_list:
                yield j

    def _nextAll(self):
        return [e for e in self._traverse('getnext')]

    def nextAll(self, selector=None):
        """
        >>> h = '<span><p class="hello">Hi</p><p>Bye</p><img scr=""/></span>'
        >>> d = PyQuery(h)
        >>> d('p:last').nextAll()
        [<img>]
        """
        return self._filter_only(selector, self._nextAll())

    def _prevAll(self):
        return [e for e in self._traverse('getprevious')]

    def prevAll(self, selector=None):
        """
        >>> h = '<span><p class="hello">Hi</p><p>Bye</p><img scr=""/></span>'
        >>> d = PyQuery(h)
        >>> d('p:last').prevAll()
        [<p.hello>]
        """
        return self._filter_only(selector, self._prevAll(), reverse=True)

    def siblings(self, selector=None):
        """
         >>> h = '<span><p class="hello">Hi</p><p>Bye</p><img scr=""/></span>'
         >>> d = PyQuery(h)
         >>> d('.hello').siblings()
         [<p>, <img>]
         >>> d('.hello').siblings('img')
         [<img>]

        """
        return self._filter_only(selector, self._prevAll() + self._nextAll())

    def parents(self, selector=None):
        """
        >>> d = PyQuery('<span><p class="hello">Hi</p><p>Bye</p></span>')
        >>> d('p').parents()
        [<span>]
        >>> d('.hello').parents('span')
        [<span>]
        >>> d('.hello').parents('p')
        []
        """
        return self._filter_only(
                selector,
                [e for e in self._traverse_parent_topdown()],
                unique=True
            )

    def children(self, selector=None):
        """Filter elements that are direct children of self using optional
        selector:

            >>> d = PyQuery('<span><p class="hello">Hi</p><p>Bye</p></span>')
            >>> d
            [<span>]
            >>> d.children()
            [<p.hello>, <p>]
            >>> d.children('.hello')
            [<p.hello>]
        """
        elements = [child for tag in self for child in tag.getchildren()]
        return self._filter_only(selector, elements)

    def closest(self, selector=None):
        """
        >>> d = PyQuery(
        ...  '<div class="hello"><p>This is a '
        ...  '<strong class="hello">test</strong></p></div>')
        >>> d('strong').closest('div')
        [<div.hello>]
        >>> d('strong').closest('.hello')
        [<strong.hello>]
        >>> d('strong').closest('form')
        []
        """
        result = []
        for current in self:
            while current is not None and \
                  not self.__class__(current).is_(selector):
                current = current.getparent()
            if current is not None:
                result.append(current)
        return self.__class__(result, **dict(parent=self))

    def contents(self):
        """
        Return contents (with text nodes):

            >>> d = PyQuery('hello <b>bold</b>')
            >>> d.contents()  # doctest: +ELLIPSIS
            ['hello ', <Element b at ...>]
        """
        results = []
        for elem in self:
            results.extend(elem.xpath('child::text()|child::*'))
        return self.__class__(results, **dict(parent=self))

    def filter(self, selector):
        """Filter elements in self using selector (string or function):

            >>> d = PyQuery('<p class="hello">Hi</p><p>Bye</p>')
            >>> d('p')
            [<p.hello>, <p>]
            >>> d('p').filter('.hello')
            [<p.hello>]
            >>> d('p').filter(lambda i: i == 1)
            [<p>]
            >>> d('p').filter(lambda i: PyQuery(this).text() == 'Hi')
            [<p.hello>]
        """
        if not hasattr(selector, '__call__'):
            return self._filter_only(selector, self)
        else:
            elements = []
            try:
                for i, this in enumerate(self):
                    func_globals(selector)['this'] = this
                    if callback(selector, i):
                        elements.append(this)
            finally:
                f_globals = func_globals(selector)
                if 'this' in f_globals:
                    del f_globals['this']
            return self.__class__(elements, **dict(parent=self))

    def not_(self, selector):
        """Return elements that don't match the given selector:

            >>> d = PyQuery('<p class="hello">Hi</p><p>Bye</p><div></div>')
            >>> d('p').not_('.hello')
            [<p>]
        """
        exclude = set(self.__class__(selector, self))
        return self.__class__([e for e in self if e not in exclude],
                              **dict(parent=self))

    def is_(self, selector):
        """Returns True if selector matches at least one current element, else
        False:

            >>> d = PyQuery('<p class="hello">Hi</p><p>Bye</p><div></div>')
            >>> d('p').eq(0).is_('.hello')
            True

            >>> d('p').eq(1).is_('.hello')
            False

        ..
        """
        return bool(self.__class__(selector, self))

    def find(self, selector):
        """Find elements using selector traversing down from self:

            >>> m = '<p><span><em>Whoah!</em></span></p><p><em> there</em></p>'
            >>> d = PyQuery(m)
            >>> d('p').find('em')
            [<em>, <em>]
            >>> d('p').eq(1).find('em')
            [<em>]
        """
        xpath = self._css_to_xpath(selector)
        results = [child.xpath(xpath) for tag in self \
                        for child in tag.getchildren()]
        # Flatten the results
        elements = []
        for r in results:
            elements.extend(r)
        return self.__class__(elements, **dict(parent=self))

    def eq(self, index):
        """Return PyQuery of only the element with the provided index::

            >>> d = PyQuery('<p class="hello">Hi</p><p>Bye</p><div></div>')
            >>> d('p').eq(0)
            [<p.hello>]
            >>> d('p').eq(1)
            [<p>]
            >>> d('p').eq(2)
            []

        ..
        """
        # Use slicing to silently handle out of bounds indexes
        items = self[index:index + 1]
        return self.__class__(items, **dict(parent=self))

    def each(self, func):
        """apply func on each nodes
        """
        try:
            for i, element in enumerate(self):
                func_globals(func)['this'] = element
                if callback(func, i, element) == False:
                    break
        finally:
            f_globals = func_globals(func)
            if 'this' in f_globals:
                del f_globals['this']
        return self

    def map(self, func):
        """Returns a new PyQuery after transforming current items with func.

        func should take two arguments - 'index' and 'element'.  Elements can
        also be referred to as 'this' inside of func::

            >>> d = PyQuery('<p class="hello">Hi there</p><p>Bye</p><br />')
            >>> d('p').map(lambda i, e: PyQuery(e).text())
            ['Hi there', 'Bye']

            >>> d('p').map(lambda i, e: len(PyQuery(this).text()))
            [8, 3]

            >>> d('p').map(lambda i, e: PyQuery(this).text().split())
            ['Hi', 'there', 'Bye']

        """
        items = []
        try:
            for i, element in enumerate(self):
                func_globals(func)['this'] = element
                result = callback(func, i, element)
                if result is not None:
                    if not isinstance(result, list):
                        items.append(result)
                    else:
                        items.extend(result)
        finally:
            f_globals = func_globals(func)
            if 'this' in f_globals:
                del f_globals['this']
        return self.__class__(items, **dict(parent=self))

    @property
    def length(self):
        return len(self)

    def size(self):
        return len(self)

    def end(self):
        """Break out of a level of traversal and return to the parent level.

            >>> m = '<p><span><em>Whoah!</em></span></p><p><em> there</em></p>'
            >>> d = PyQuery(m)
            >>> d('p').eq(1).find('em').end().end()
            [<p>, <p>]
        """
        return self._parent

    ##############
    # Attributes #
    ##############
    def attr(self, *args, **kwargs):
        """Attributes manipulation
        """

        mapping = {'class_': 'class', 'for_': 'for'}

        attr = value = no_default
        length = len(args)
        if length == 1:
            attr = args[0]
            attr = mapping.get(attr, attr)
        elif length == 2:
            attr, value = args
            attr = mapping.get(attr, attr)
        elif kwargs:
            attr = {}
            for k, v in kwargs.items():
                attr[mapping.get(k, k)] = v
        else:
            raise ValueError('Invalid arguments %s %s' % (args, kwargs))

        if not self:
            return None
        elif isinstance(attr, dict):
            for tag in self:
                for key, value in attr.items():
                    tag.set(key, value)
        elif value is no_default:
            return self[0].get(attr)
        elif value is None or value == '':
            return self.removeAttr(attr)
        else:
            for tag in self:
                tag.set(attr, value)
        return self

    def removeAttr(self, name):
        """Remove an attribute::

            >>> d = PyQuery('<div id="myid"></div>')
            >>> d.removeAttr('id')
            [<div>]

        ..
        """
        for tag in self:
            del tag.attrib[name]
        return self

    attr = FlexibleElement(pget=attr, pdel=removeAttr)

    #######
    # CSS #
    #######
    def height(self, value=no_default):
        """set/get height of element
        """
        return self.attr('height', value)

    def width(self, value=no_default):
        """set/get width of element
        """
        return self.attr('width', value)

    def hasClass(self, name):
        """Return True if element has class::

            >>> d = PyQuery('<div class="myclass"></div>')
            >>> d.hasClass('myclass')
            True

        ..
        """
        return self.is_('.%s' % name)

    def addClass(self, value):
        """Add a css class to elements::

            >>> d = PyQuery('<div></div>')
            >>> d.addClass('myclass')
            [<div.myclass>]

        ..
        """
        for tag in self:
            values = value.split(' ')
            classes = (tag.get('class') or '').split()
            classes += [v for v in values if v not in classes]
            tag.set('class', ' '.join(classes))
        return self

    def removeClass(self, value):
        """Remove a css class to elements::

            >>> d = PyQuery('<div class="myclass"></div>')
            >>> d.removeClass('myclass')
            [<div>]

        ..
        """
        for tag in self:
            values = value.split(' ')
            classes = set((tag.get('class') or '').split())
            classes.difference_update(values)
            classes.difference_update([''])
            tag.set('class', ' '.join(classes))
        return self

    def toggleClass(self, value):
        """Toggle a css class to elements

            >>> d = PyQuery('<div></div>')
            >>> d.toggleClass('myclass')
            [<div.myclass>]

        """
        for tag in self:
            values = value.split(' ')
            classes = (tag.get('class') or '').split()
            values_to_add = [v for v in values if v not in classes]
            values_to_del = [v for v in values if v in classes]
            classes = [v for v in classes if v not in values_to_del]
            classes += values_to_add
            tag.set('class', ' '.join(classes))
        return self

    def css(self, *args, **kwargs):
        """css attributes manipulation
        """

        attr = value = no_default
        length = len(args)
        if length == 1:
            attr = args[0]
        elif length == 2:
            attr, value = args
        elif kwargs:
            attr = kwargs
        else:
            raise ValueError('Invalid arguments %s %s' % (args, kwargs))

        if isinstance(attr, dict):
            for tag in self:
                stripped_keys = [key.strip().replace('_', '-')
                                 for key in attr.keys()]
                current = [el.strip()
                           for el in (tag.get('style') or '').split(';')
                           if el.strip()
                           and not el.split(':')[0].strip() in stripped_keys]
                for key, value in attr.items():
                    key = key.replace('_', '-')
                    current.append('%s: %s' % (key, value))
                tag.set('style', '; '.join(current))
        elif isinstance(value, basestring):
            attr = attr.replace('_', '-')
            for tag in self:
                current = [el.strip()
                           for el in (tag.get('style') or '').split(';')
                           if el.strip()
                              and not el.split(':')[0].strip() == attr.strip()]
                current.append('%s: %s' % (attr, value))
                tag.set('style', '; '.join(current))
        return self

    css = FlexibleElement(pget=css, pset=css)

    ###################
    # CORE UI EFFECTS #
    ###################
    def hide(self):
        """remove display:none to elements style

            >>> print(PyQuery('<div style="display:none;"/>').hide())
            <div style="display: none"/>

        """
        return self.css('display', 'none')

    def show(self):
        """add display:block to elements style

            >>> print(PyQuery('<div />').show())
            <div style="display: block"/>

        """
        return self.css('display', 'block')

    ########
    # HTML #
    ########
    def val(self, value=no_default):
        """Set the attribute value::

            >>> d = PyQuery('<input />')
            >>> d.val('Youhou')
            [<input>]

        Get the attribute value::

            >>> d.val()
            'Youhou'

        """
        return self.attr('value', value) or None

    def html(self, value=no_default, **kwargs):
        """Get or set the html representation of sub nodes.

        Get the text value::

            >>> d = PyQuery('<div><span>toto</span></div>')
            >>> print(d.html())
            <span>toto</span>

        Extra args are passed to ``lxml.etree.tostring::

            >>> d = PyQuery('<div><span></span></div>')
            >>> print(d.html())
            <span/>
            >>> print(d.html(method='html'))
            <span></span>

        Set the text value::

            >>> d.html('<span>Youhou !</span>')
            [<div>]
            >>> print(d)
            <div><span>Youhou !</span></div>
        """
        if value is no_default:
            if not self:
                return None
            tag = self[0]
            children = tag.getchildren()
            if not children:
                return tag.text
            html = tag.text or ''
            if 'encoding' not in kwargs:
                kwargs['encoding'] = unicode
            html += unicode('').join([etree.tostring(e, **kwargs) \
                                                  for e in children])
            return html
        else:
            if isinstance(value, self.__class__):
                new_html = unicode(value)
            elif isinstance(value, basestring):
                new_html = value
            elif not value:
                new_html = ''
            else:
                raise ValueError(type(value))

            for tag in self:
                for child in tag.getchildren():
                    tag.remove(child)
                root = fromstring(
                            unicode('<root>') + new_html + unicode('</root>'),
                            self.parser)[0]
                children = root.getchildren()
                if children:
                    tag.extend(children)
                tag.text = root.text
                tag.tail = root.tail
        return self

    def outerHtml(self):
        """Get the html representation of the first selected element::

            >>> d = PyQuery('<div><span class="red">toto</span> rocks</div>')
            >>> print(d('span'))
            <span class="red">toto</span> rocks
            >>> print(d('span').outerHtml())
            <span class="red">toto</span>

            >>> S = PyQuery('<p>Only <b>me</b> & myself</p>')
            >>> print(S('b').outerHtml())
            <b>me</b>

        ..
        """

        if not self:
            return None
        e0 = self[0]
        if e0.tail:
            e0 = deepcopy(e0)
            e0.tail = ''
        return lxml.html.tostring(e0, encoding=unicode)

    def text(self, value=no_default):
        """Get or set the text representation of sub nodes.

        Get the text value::

            >>> doc = PyQuery('<div><span>toto</span><span>tata</span></div>')
            >>> print(doc.text())
            toto tata

        Set the text value::

            >>> doc.text('Youhou !')
            [<div>]
            >>> print(doc)
            <div>Youhou !</div>

        """

        if value is no_default:
            if not self:
                return None

            text = []

            def add_text(tag, no_tail=False):
                if tag.text and not isinstance(tag, lxml.etree._Comment):
                    text.append(tag.text)
                for child in tag.getchildren():
                    add_text(child)
                if not no_tail and tag.tail:
                    text.append(tag.tail)

            for tag in self:
                add_text(tag, no_tail=True)
            return ' '.join([t.strip() for t in text if t.strip()])

        for tag in self:
            for child in tag.getchildren():
                tag.remove(child)
            tag.text = value
        return self

    ################
    # Manipulating #
    ################

    def _get_root(self, value):
        if  isinstance(value, basestring):
            root = fromstring(unicode('<root>') + value + unicode('</root>'),
                              self.parser)[0]
        elif isinstance(value, etree._Element):
            root = self.__class__(value)
        elif isinstance(value, PyQuery):
            root = value
        else:
            raise TypeError(
            'Value must be string, PyQuery or Element. Got %r' % value)
        if hasattr(root, 'text') and isinstance(root.text, basestring):
            root_text = root.text
        else:
            root_text = ''
        return root, root_text

    def append(self, value):
        """append value to each nodes
        """
        root, root_text = self._get_root(value)
        for i, tag in enumerate(self):
            if len(tag) > 0:  # if the tag has children
                last_child = tag[-1]
                if not last_child.tail:
                    last_child.tail = ''
                last_child.tail += root_text
            else:
                if not tag.text:
                    tag.text = ''
                tag.text += root_text
            if i > 0:
                root = deepcopy(list(root))
            tag.extend(root)
            root = tag[-len(root):]
        return self

    def appendTo(self, value):
        """append nodes to value
        """
        value.append(self)
        return self

    def prepend(self, value):
        """prepend value to nodes
        """
        root, root_text = self._get_root(value)
        for i, tag in enumerate(self):
            if not tag.text:
                tag.text = ''
            if len(root) > 0:
                root[-1].tail = tag.text
                tag.text = root_text
            else:
                tag.text = root_text + tag.text
            if i > 0:
                root = deepcopy(list(root))
            tag[:0] = root
            root = tag[:len(root)]
        return self

    def prependTo(self, value):
        """prepend nodes to value
        """
        value.prepend(self)
        return self

    def after(self, value):
        """add value after nodes
        """
        root, root_text = self._get_root(value)
        for i, tag in enumerate(self):
            if not tag.tail:
                tag.tail = ''
            tag.tail += root_text
            if i > 0:
                root = deepcopy(list(root))
            parent = tag.getparent()
            index = parent.index(tag) + 1
            parent[index:index] = root
            root = parent[index:len(root)]
        return self

    def insertAfter(self, value):
        """insert nodes after value
        """
        value.after(self)
        return self

    def before(self, value):
        """insert value before nodes
        """
        root, root_text = self._get_root(value)
        for i, tag in enumerate(self):
            previous = tag.getprevious()
            if previous != None:
                if not previous.tail:
                    previous.tail = ''
                previous.tail += root_text
            else:
                parent = tag.getparent()
                if not parent.text:
                    parent.text = ''
                parent.text += root_text
            if i > 0:
                root = deepcopy(list(root))
            parent = tag.getparent()
            index = parent.index(tag)
            parent[index:index] = root
            root = parent[index:len(root)]
        return self

    def insertBefore(self, value):
        """insert nodes before value
        """
        value.before(self)
        return self

    def wrap(self, value):
        """A string of HTML that will be created on the fly and wrapped around
        each target:

            >>> d = PyQuery('<span>youhou</span>')
            >>> d.wrap('<div></div>')
            [<div>]
            >>> print(d)
            <div><span>youhou</span></div>

        """
        assert isinstance(value, basestring)
        value = fromstring(value)[0]
        nodes = []
        for tag in self:
            wrapper = deepcopy(value)
            # FIXME: using iterchildren is probably not optimal
            if not wrapper.getchildren():
                wrapper.append(deepcopy(tag))
            else:
                childs = [c for c in wrapper.iterchildren()]
                child = childs[-1]
                child.append(deepcopy(tag))
            nodes.append(wrapper)

            parent = tag.getparent()
            if parent is not None:
                for t in parent.iterchildren():
                    if t is tag:
                        t.addnext(wrapper)
                        parent.remove(t)
                        break
        self[:] = nodes
        return self

    def wrapAll(self, value):
        """Wrap all the elements in the matched set into a single wrapper
        element::

            >>> d = PyQuery('<div><span>Hey</span><span>you !</span></div>')
            >>> print(d('span').wrapAll('<div id="wrapper"></div>'))
            <div id="wrapper"><span>Hey</span><span>you !</span></div>

        ..
        """
        if not self:
            return self

        assert isinstance(value, basestring)
        value = fromstring(value)[0]
        wrapper = deepcopy(value)
        if not wrapper.getchildren():
            child = wrapper
        else:
            childs = [c for c in wrapper.iterchildren()]
            child = childs[-1]

        replace_childs = True
        parent = self[0].getparent()
        if parent is None:
            parent = no_default

        # add nodes to wrapper and check parent
        for tag in self:
            child.append(deepcopy(tag))
            if tag.getparent() is not parent:
                replace_childs = False

        # replace nodes i parent if possible
        if parent is not no_default and replace_childs:
            childs = [c for c in parent.iterchildren()]
            if len(childs) == len(self):
                for tag in self:
                    parent.remove(tag)
                parent.append(wrapper)

        self[:] = [wrapper]
        return self

    def replaceWith(self, value):
        """replace nodes by value
        """
        if hasattr(value, '__call__'):
            for i, element in enumerate(self):
                self.__class__(element).before(
                        value(i, element) + (element.tail or ''))
                parent = element.getparent()
                parent.remove(element)
        else:
            for tag in self:
                self.__class__(tag).before(value + (tag.tail or ''))
                parent = tag.getparent()
                parent.remove(tag)
        return self

    def replaceAll(self, expr):
        """replace nodes by expr
        """
        if self._parent is no_default:
            raise ValueError(
                    'replaceAll can only be used with an object with parent')
        self._parent(expr).replaceWith(self)
        return self

    def clone(self):
        """return a copy of nodes
        """
        return PyQuery([deepcopy(tag) for tag in self])

    def empty(self):
        """remove nodes content
        """
        for tag in self:
            tag.text = None
            tag[:] = []
        return self

    def remove(self, expr=no_default):
        """Remove nodes:

         >>> h = '<div>Maybe <em>she</em> does <strong>NOT</strong> know</div>'
         >>> d = PyQuery(h)
         >>> d('strong').remove()
         [<strong>]
         >>> print(d)
         <div>Maybe <em>she</em> does   know</div>
        """
        if expr is no_default:
            for tag in self:
                parent = tag.getparent()
                if parent is not None:
                    if tag.tail:
                        prev = tag.getprevious()
                        if prev is None:
                            if not parent.text:
                                parent.text = ''
                            parent.text += ' ' + tag.tail
                        else:
                            if not prev.tail:
                                prev.tail = ''
                            prev.tail += ' ' + tag.tail
                    parent.remove(tag)
        else:
            results = self.__class__(expr, self)
            results.remove()
        return self

    class Fn(object):
        """Hook for defining custom function (like the jQuery.fn):

        .. sourcecode:: python

         >>> fn = lambda: this.map(lambda i, el: PyQuery(this).outerHtml())
         >>> PyQuery.fn.listOuterHtml = fn
         >>> S = PyQuery(
         ...   '<ol>   <li>Coffee</li>   <li>Tea</li>   <li>Milk</li>   </ol>')
         >>> S('li').listOuterHtml()
         ['<li>Coffee</li>', '<li>Tea</li>', '<li>Milk</li>']

        """
        def __setattr__(self, name, func):
            def fn(self, *args):
                func_globals(func)['this'] = self
                return func(*args)
            fn.__name__ = name
            setattr(PyQuery, name, fn)
    fn = Fn()

    #####################################################
    # Additional methods that are not in the jQuery API #
    #####################################################

    @property
    def base_url(self):
        """Return the url of current html document or None if not available.
        """
        if self._base_url is not None:
            return self._base_url
        if self._parent is not no_default:
            return self._parent.base_url

    def make_links_absolute(self, base_url=None):
        """Make all links absolute.
        """
        if base_url is None:
            base_url = self.base_url
            if base_url is None:
                raise ValueError('You need a base URL to make your links'
                 'absolute. It can be provided by the base_url parameter.')

        self('a').each(lambda: self(this).attr('href', urljoin(base_url, self(this).attr('href')))) # NOQA
        return self
Tip: Filter by directory path e.g. /media app.js to search for public/media/app.js.
Tip: Use camelCasing e.g. ProjME to search for ProjectModifiedEvent.java.
Tip: Filter by extension type e.g. /repo .js to search for all .js files in the /repo directory.
Tip: Separate your search with spaces e.g. /ssh pom.xml to search for src/ssh/pom.xml.
Tip: Use ↑ and ↓ arrow keys to navigate and return to view the file.
Tip: You can also navigate files with Ctrl+j (next) and Ctrl+k (previous) and view the file with Ctrl+o.
Tip: You can also navigate files with Alt+j (next) and Alt+k (previous) and view the file with Alt+o.