PageRenderTime 65ms CodeModel.GetById 30ms RepoModel.GetById 0ms app.codeStats 1ms

/dev-python/beautifulsoup/files/beautifulsoup-3.1.0.1-python-3.patch

https://bitbucket.org/lmnd/gx86-cropped
Patch | 949 lines | 852 code | 97 blank | 0 comment | 0 complexity | b0ffeb7348e51767ac952290916a24f9 MD5 | raw file
Possible License(s): LGPL-2.1, LGPL-2.0, GPL-3.0, GPL-2.0, LGPL-3.0, MIT, AGPL-3.0, CC-BY-SA-4.0, Apache-2.0, AGPL-1.0, Unlicense, BitTorrent-1.0, BSD-3-Clause, MPL-2.0-no-copyleft-exception, CC-BY-SA-3.0 
    

  1. --- BeautifulSoup.py
    2. 

  2. +++ BeautifulSoup.py
    3. 

  3. @@ -76,7 +76,7 @@
    4. 

  4.  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE, DAMMIT.
    5. 

  5.  
    6. 

  6.  """
    7. 

  7. -from __future__ import generators
    8. 

  8. +
    9. 

  9.  
    10. 

  10.  __author__ = "Leonard Richardson (leonardr@segfault.org)"
    11. 

  11.  __version__ = "3.1.0.1"
    12. 

  12. @@ -84,12 +84,12 @@
    13. 

  13.  __license__ = "New-style BSD"
    14. 

  14.  
    15. 

  15.  import codecs
    16. 

  16. -import markupbase
    17. 

  17. +import _markupbase
    18. 

  18.  import types
    19. 

  19.  import re
    20. 

  20. -from HTMLParser import HTMLParser, HTMLParseError
    21. 

  21. +from html.parser import HTMLParser, HTMLParseError
    22. 

  22.  try:
    23. 

  23. -    from htmlentitydefs import name2codepoint
    24. 

  24. +    from html.entities import name2codepoint
    25. 

  25.  except ImportError:
    26. 

  26.      name2codepoint = {}
    27. 

  27.  try:
    28. 

  28. @@ -98,18 +98,18 @@
    29. 

  29.      from sets import Set as set
    30. 

  30.  
    31. 

  31.  #These hacks make Beautiful Soup able to parse XML with namespaces
    32. 

  32. -markupbase._declname_match = re.compile(r'[a-zA-Z][-_.:a-zA-Z0-9]*\s*').match
    33. 

  33. +_markupbase._declname_match = re.compile(r'[a-zA-Z][-_.:a-zA-Z0-9]*\s*').match
    34. 

  34.  
    35. 

  35.  DEFAULT_OUTPUT_ENCODING = "utf-8"
    36. 

  36.  
    37. 

  37.  # First, the classes that represent markup elements.
    38. 

  38.  
    39. 

  39. -def sob(unicode, encoding):
    40. 

  40. +def sob(str, encoding):
    41. 

  41.      """Returns either the given Unicode string or its encoding."""
    42. 

  42.      if encoding is None:
    43. 

  43. -        return unicode
    44. 

  44. +        return str
    45. 

  45.      else:
    46. 

  46. -        return unicode.encode(encoding)
    47. 

  47. +        return str.encode(encoding)
    48. 

  48.  
    49. 

  49.  class PageElement:
    50. 

  50.      """Contains the navigational information for some part of the page
    51. 

  51. @@ -178,8 +178,8 @@
    52. 

  52.          return lastChild
    53. 

  53.  
    54. 

  54.      def insert(self, position, newChild):
    55. 

  55. -        if (isinstance(newChild, basestring)
    56. 

  56. -            or isinstance(newChild, unicode)) \
    57. 

  57. +        if (isinstance(newChild, str)
    58. 

  58. +            or isinstance(newChild, str)) \
    59. 

  59.              and not isinstance(newChild, NavigableString):
    60. 

  60.              newChild = NavigableString(newChild)
    61. 

  61.  
    62. 

  62. @@ -334,7 +334,7 @@
    63. 

  63.          g = generator()
    64. 

  64.          while True:
    65. 

  65.              try:
    66. 

  66. -                i = g.next()
    67. 

  67. +                i = g.__next__()
    68. 

  68.              except StopIteration:
    69. 

  69.                  break
    70. 

  70.              if i:
    71. 

  71. @@ -385,22 +385,22 @@
    72. 

  72.      def toEncoding(self, s, encoding=None):
    73. 

  73.          """Encodes an object to a string in some encoding, or to Unicode.
    74. 

  74.          ."""
    75. 

  75. -        if isinstance(s, unicode):
    76. 

  76. +        if isinstance(s, str):
    77. 

  77.              if encoding:
    78. 

  78.                  s = s.encode(encoding)
    79. 

  79.          elif isinstance(s, str):
    80. 

  80.              if encoding:
    81. 

  81.                  s = s.encode(encoding)
    82. 

  82.              else:
    83. 

  83. -                s = unicode(s)
    84. 

  84. +                s = str(s)
    85. 

  85.          else:
    86. 

  86.              if encoding:
    87. 

  87.                  s  = self.toEncoding(str(s), encoding)
    88. 

  88.              else:
    89. 

  89. -                s = unicode(s)
    90. 

  90. +                s = str(s)
    91. 

  91.          return s
    92. 

  92.  
    93. 

  93. -class NavigableString(unicode, PageElement):
    94. 

  94. +class NavigableString(str, PageElement):
    95. 

  95.  
    96. 

  96.      def __new__(cls, value):
    97. 

  97.          """Create a new NavigableString.
    98. 

  98. @@ -410,12 +410,12 @@
    99. 

  99.          passed in to the superclass's __new__ or the superclass won't know
    100. 

  100.          how to handle non-ASCII characters.
    101. 

  101.          """
    102. 

  102. -        if isinstance(value, unicode):
    103. 

  103. -            return unicode.__new__(cls, value)
    104. 

  104. -        return unicode.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
    105. 

  105. +        if isinstance(value, str):
    106. 

  106. +            return str.__new__(cls, value)
    107. 

  107. +        return str.__new__(cls, value, DEFAULT_OUTPUT_ENCODING)
    108. 

  108.  
    109. 

  109.      def __getnewargs__(self):
    110. 

  110. -        return (unicode(self),)
    111. 

  111. +        return (str(self),)
    112. 

  112.  
    113. 

  113.      def __getattr__(self, attr):
    114. 

  114.          """text.string gives you text. This is for backwards
    115. 

  115. @@ -424,7 +424,7 @@
    116. 

  116.          if attr == 'string':
    117. 

  117.              return self
    118. 

  118.          else:
    119. 

  119. -            raise AttributeError, "'%s' object has no attribute '%s'" % (self.__class__.__name__, attr)
    120. 

  120. +            raise AttributeError("'%s' object has no attribute '%s'" % (self.__class__.__name__, attr))
    121. 

  121.  
    122. 

  122.      def encode(self, encoding=DEFAULT_OUTPUT_ENCODING):
    123. 

  123.          return self.decode().encode(encoding)
    124. 

  124. @@ -435,23 +435,23 @@
    125. 

  125.  class CData(NavigableString):
    126. 

  126.  
    127. 

  127.      def decodeGivenEventualEncoding(self, eventualEncoding):
    128. 

  128. -        return u'<![CDATA[' + self + u']]>'
    129. 

  129. +        return '<![CDATA[' + self + ']]>'
    130. 

  130.  
    131. 

  131.  class ProcessingInstruction(NavigableString):
    132. 

  132.  
    133. 

  133.      def decodeGivenEventualEncoding(self, eventualEncoding):
    134. 

  134.          output = self
    135. 

  135. -        if u'%SOUP-ENCODING%' in output:
    136. 

  136. +        if '%SOUP-ENCODING%' in output:
    137. 

  137.              output = self.substituteEncoding(output, eventualEncoding)
    138. 

  138. -        return u'<?' + output + u'?>'
    139. 

  139. +        return '<?' + output + '?>'
    140. 

  140.  
    141. 

  141.  class Comment(NavigableString):
    142. 

  142.      def decodeGivenEventualEncoding(self, eventualEncoding):
    143. 

  143. -        return u'<!--' + self + u'-->'
    144. 

  144. +        return '<!--' + self + '-->'
    145. 

  145.  
    146. 

  146.  class Declaration(NavigableString):
    147. 

  147.      def decodeGivenEventualEncoding(self, eventualEncoding):
    148. 

  148. -        return u'<!' + self + u'>'
    149. 

  149. +        return '<!' + self + '>'
    150. 

  150.  
    151. 

  151.  class Tag(PageElement):
    152. 

  152.  
    153. 

  153. @@ -460,7 +460,7 @@
    154. 

  154.      def _invert(h):
    155. 

  155.          "Cheap function to invert a hash."
    156. 

  156.          i = {}
    157. 

  157. -        for k,v in h.items():
    158. 

  158. +        for k,v in list(h.items()):
    159. 

  159.              i[v] = k
    160. 

  160.          return i
    161. 

  161.  
    162. 

  162. @@ -479,23 +479,23 @@
    163. 

  163.          escaped."""
    164. 

  164.          x = match.group(1)
    165. 

  165.          if self.convertHTMLEntities and x in name2codepoint:
    166. 

  166. -            return unichr(name2codepoint[x])
    167. 

  167. +            return chr(name2codepoint[x])
    168. 

  168.          elif x in self.XML_ENTITIES_TO_SPECIAL_CHARS:
    169. 

  169.              if self.convertXMLEntities:
    170. 

  170.                  return self.XML_ENTITIES_TO_SPECIAL_CHARS[x]
    171. 

  171.              else:
    172. 

  172. -                return u'&%s;' % x
    173. 

  173. +                return '&%s;' % x
    174. 

  174.          elif len(x) > 0 and x[0] == '#':
    175. 

  175.              # Handle numeric entities
    176. 

  176.              if len(x) > 1 and x[1] == 'x':
    177. 

  177. -                return unichr(int(x[2:], 16))
    178. 

  178. +                return chr(int(x[2:], 16))
    179. 

  179.              else:
    180. 

  180. -                return unichr(int(x[1:]))
    181. 

  181. +                return chr(int(x[1:]))
    182. 

  182.  
    183. 

  183.          elif self.escapeUnrecognizedEntities:
    184. 

  184. -            return u'&amp;%s;' % x
    185. 

  185. +            return '&amp;%s;' % x
    186. 

  186.          else:
    187. 

  187. -            return u'&%s;' % x
    188. 

  188. +            return '&%s;' % x
    189. 

  189.  
    190. 

  190.      def __init__(self, parser, name, attrs=None, parent=None,
    191. 

  191.                   previous=None):
    192. 

  192. @@ -524,7 +524,7 @@
    193. 

  193.                  return kval
    194. 

  194.              return (k, re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);",
    195. 

  195.                                self._convertEntities, val))
    196. 

  196. -        self.attrs = map(convert, self.attrs)
    197. 

  197. +        self.attrs = list(map(convert, self.attrs))
    198. 

  198.  
    199. 

  199.      def get(self, key, default=None):
    200. 

  200.          """Returns the value of the 'key' attribute for the tag, or
    201. 

  201. @@ -533,7 +533,7 @@
    202. 

  202.          return self._getAttrMap().get(key, default)
    203. 

  203.  
    204. 

  204.      def has_key(self, key):
    205. 

  205. -        return self._getAttrMap().has_key(key)
    206. 

  206. +        return key in self._getAttrMap()
    207. 

  207.  
    208. 

  208.      def __getitem__(self, key):
    209. 

  209.          """tag[key] returns the value of the 'key' attribute for the tag,
    210. 

  210. @@ -551,7 +551,7 @@
    211. 

  211.      def __contains__(self, x):
    212. 

  212.          return x in self.contents
    213. 

  213.  
    214. 

  214. -    def __nonzero__(self):
    215. 

  215. +    def __bool__(self):
    216. 

  216.          "A tag is non-None even if it has no contents."
    217. 

  217.          return True
    218. 

  218.  
    219. 

  219. @@ -577,14 +577,14 @@
    220. 

  220.                  #We don't break because bad HTML can define the same
    221. 

  221.                  #attribute multiple times.
    222. 

  222.              self._getAttrMap()
    223. 

  223. -            if self.attrMap.has_key(key):
    224. 

  224. +            if key in self.attrMap:
    225. 

  225.                  del self.attrMap[key]
    226. 

  226.  
    227. 

  227.      def __call__(self, *args, **kwargs):
    228. 

  228.          """Calling a tag like a function is the same as calling its
    229. 

  229.          findAll() method. Eg. tag('a') returns a list of all the A tags
    230. 

  230.          found within this tag."""
    231. 

  231. -        return apply(self.findAll, args, kwargs)
    232. 

  232. +        return self.findAll(*args, **kwargs)
    233. 

  233.  
    234. 

  234.      def __getattr__(self, tag):
    235. 

  235.          #print "Getattr %s.%s" % (self.__class__, tag)
    236. 

  236. @@ -592,7 +592,7 @@
    237. 

  237.              return self.find(tag[:-3])
    238. 

  238.          elif tag.find('__') != 0:
    239. 

  239.              return self.find(tag)
    240. 

  240. -        raise AttributeError, "'%s' object has no attribute '%s'" % (self.__class__, tag)
    241. 

  241. +        raise AttributeError("'%s' object has no attribute '%s'" % (self.__class__, tag))
    242. 

  242.  
    243. 

  243.      def __eq__(self, other):
    244. 

  244.          """Returns true iff this tag has the same name, the same attributes,
    245. 

  245. @@ -868,7 +868,7 @@
    246. 

  246.          if isinstance(markupName, Tag):
    247. 

  247.              markup = markupName
    248. 

  248.              markupAttrs = markup
    249. 

  249. -        callFunctionWithTagData = callable(self.name) \
    250. 

  250. +        callFunctionWithTagData = hasattr(self.name, '__call__') \
    251. 

  251.                                  and not isinstance(markupName, Tag)
    252. 

  252.  
    253. 

  253.          if (not self.name) \
    254. 

  254. @@ -880,7 +880,7 @@
    255. 

  255.              else:
    256. 

  256.                  match = True
    257. 

  257.                  markupAttrMap = None
    258. 

  258. -                for attr, matchAgainst in self.attrs.items():
    259. 

  259. +                for attr, matchAgainst in list(self.attrs.items()):
    260. 

  260.                      if not markupAttrMap:
    261. 

  261.                           if hasattr(markupAttrs, 'get'):
    262. 

  262.                              markupAttrMap = markupAttrs
    263. 

  263. @@ -921,16 +921,16 @@
    264. 

  264.              if self._matches(markup, self.text):
    265. 

  265.                  found = markup
    266. 

  266.          else:
    267. 

  267. -            raise Exception, "I don't know how to match against a %s" \
    268. 

  268. -                  % markup.__class__
    269. 

  269. +            raise Exception("I don't know how to match against a %s" \
    270. 

  270. +                  % markup.__class__)
    271. 

  271.          return found
    272. 

  272.  
    273. 

  273.      def _matches(self, markup, matchAgainst):
    274. 

  274.          #print "Matching %s against %s" % (markup, matchAgainst)
    275. 

  275.          result = False
    276. 

  276. -        if matchAgainst == True and type(matchAgainst) == types.BooleanType:
    277. 

  277. +        if matchAgainst == True and type(matchAgainst) == bool:
    278. 

  278.              result = markup != None
    279. 

  279. -        elif callable(matchAgainst):
    280. 

  280. +        elif hasattr(matchAgainst, '__call__'):
    281. 

  281.              result = matchAgainst(markup)
    282. 

  282.          else:
    283. 

  283.              #Custom match methods take the tag as an argument, but all
    284. 

  284. @@ -938,7 +938,7 @@
    285. 

  285.              if isinstance(markup, Tag):
    286. 

  286.                  markup = markup.name
    287. 

  287.              if markup is not None and not isString(markup):
    288. 

  288. -                markup = unicode(markup)
    289. 

  289. +                markup = str(markup)
    290. 

  290.              #Now we know that chunk is either a string, or None.
    291. 

  291.              if hasattr(matchAgainst, 'match'):
    292. 

  292.                  # It's a regexp object.
    293. 

  293. @@ -947,10 +947,10 @@
    294. 

  294.                    and (markup is not None or not isString(matchAgainst))):
    295. 

  295.                  result = markup in matchAgainst
    296. 

  296.              elif hasattr(matchAgainst, 'items'):
    297. 

  297. -                result = markup.has_key(matchAgainst)
    298. 

  298. +                result = matchAgainst in markup
    299. 

  299.              elif matchAgainst and isString(markup):
    300. 

  300. -                if isinstance(markup, unicode):
    301. 

  301. -                    matchAgainst = unicode(matchAgainst)
    302. 

  302. +                if isinstance(markup, str):
    303. 

  303. +                    matchAgainst = str(matchAgainst)
    304. 

  304.                  else:
    305. 

  305.                      matchAgainst = str(matchAgainst)
    306. 

  306.  
    307. 

  307. @@ -971,13 +971,13 @@
    308. 

  308.      """Convenience method that works with all 2.x versions of Python
    309. 

  309.      to determine whether or not something is listlike."""
    310. 

  310.      return ((hasattr(l, '__iter__') and not isString(l))
    311. 

  311. -            or (type(l) in (types.ListType, types.TupleType)))
    312. 

  312. +            or (type(l) in (list, tuple)))
    313. 

  313.  
    314. 

  314.  def isString(s):
    315. 

  315.      """Convenience method that works with all 2.x versions of Python
    316. 

  316.      to determine whether or not something is stringlike."""
    317. 

  317.      try:
    318. 

  318. -        return isinstance(s, unicode) or isinstance(s, basestring)
    319. 

  319. +        return isinstance(s, str) or isinstance(s, str)
    320. 

  320.      except NameError:
    321. 

  321.          return isinstance(s, str)
    322. 

  322.  
    323. 

  323. @@ -989,7 +989,7 @@
    324. 

  324.      for portion in args:
    325. 

  325.          if hasattr(portion, 'items'):
    326. 

  326.              #It's a map. Merge it.
    327. 

  327. -            for k,v in portion.items():
    328. 

  328. +            for k,v in list(portion.items()):
    329. 

  329.                  built[k] = v
    330. 

  330.          elif isList(portion) and not isString(portion):
    331. 

  331.              #It's a list. Map each item to the default.
    332. 

  332. @@ -1034,7 +1034,7 @@
    333. 

  333.          object, possibly one with a %SOUP-ENCODING% slot into which an
    334. 

  334.          encoding will be plugged later."""
    335. 

  335.          if text[:3] == "xml":
    336. 

  336. -            text = u"xml version='1.0' encoding='%SOUP-ENCODING%'"
    337. 

  337. +            text = "xml version='1.0' encoding='%SOUP-ENCODING%'"
    338. 

  338.          self._toStringSubclass(text, ProcessingInstruction)
    339. 

  339.  
    340. 

  340.      def handle_comment(self, text):
    341. 

  341. @@ -1044,7 +1044,7 @@
    342. 

  342.      def handle_charref(self, ref):
    343. 

  343.          "Handle character references as data."
    344. 

  344.          if self.soup.convertEntities:
    345. 

  345. -            data = unichr(int(ref))
    346. 

  346. +            data = chr(int(ref))
    347. 

  347.          else:
    348. 

  348.              data = '&#%s;' % ref
    349. 

  349.          self.handle_data(data)
    350. 

  350. @@ -1056,7 +1056,7 @@
    351. 

  351.          data = None
    352. 

  352.          if self.soup.convertHTMLEntities:
    353. 

  353.              try:
    354. 

  354. -                data = unichr(name2codepoint[ref])
    355. 

  355. +                data = chr(name2codepoint[ref])
    356. 

  356.              except KeyError:
    357. 

  357.                  pass
    358. 

  358.  
    359. 

  359. @@ -1147,7 +1147,7 @@
    360. 

  360.                         lambda x: '<!' + x.group(1) + '>')
    361. 

  361.                        ]
    362. 

  362.  
    363. 

  363. -    ROOT_TAG_NAME = u'[document]'
    364. 

  364. +    ROOT_TAG_NAME = '[document]'
    365. 

  365.  
    366. 

  366.      HTML_ENTITIES = "html"
    367. 

  367.      XML_ENTITIES = "xml"
    368. 

  368. @@ -1236,14 +1236,14 @@
    369. 

  369.      def _feed(self, inDocumentEncoding=None, isHTML=False):
    370. 

  370.          # Convert the document to Unicode.
    371. 

  371.          markup = self.markup
    372. 

  372. -        if isinstance(markup, unicode):
    373. 

  373. +        if isinstance(markup, str):
    374. 

  374.              if not hasattr(self, 'originalEncoding'):
    375. 

  375.                  self.originalEncoding = None
    376. 

  376.          else:
    377. 

  377.              dammit = UnicodeDammit\
    378. 

  378.                       (markup, [self.fromEncoding, inDocumentEncoding],
    379. 

  379.                        smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
    380. 

  380. -            markup = dammit.unicode
    381. 

  381. +            markup = dammit.str
    382. 

  382.              self.originalEncoding = dammit.originalEncoding
    383. 

  383.              self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
    384. 

  384.          if markup:
    385. 

  385. @@ -1269,8 +1269,8 @@
    386. 

  386.      def isSelfClosingTag(self, name):
    387. 

  387.          """Returns true iff the given string is the name of a
    388. 

  388.          self-closing tag according to this parser."""
    389. 

  389. -        return self.SELF_CLOSING_TAGS.has_key(name) \
    390. 

  390. -               or self.instanceSelfClosingTags.has_key(name)
    391. 

  391. +        return name in self.SELF_CLOSING_TAGS \
    392. 

  392. +               or name in self.instanceSelfClosingTags
    393. 

  393.  
    394. 

  394.      def reset(self):
    395. 

  395.          Tag.__init__(self, self, self.ROOT_TAG_NAME)
    396. 

  396. @@ -1305,7 +1305,7 @@
    397. 

  397.  
    398. 

  398.      def endData(self, containerClass=NavigableString):
    399. 

  399.          if self.currentData:
    400. 

  400. -            currentData = u''.join(self.currentData)
    401. 

  401. +            currentData = ''.join(self.currentData)
    402. 

  402.              if (currentData.translate(self.STRIP_ASCII_SPACES) == '' and
    403. 

  403.                  not set([tag.name for tag in self.tagStack]).intersection(
    404. 

  404.                      self.PRESERVE_WHITESPACE_TAGS)):
    405. 

  405. @@ -1368,7 +1368,7 @@
    406. 

  406.  
    407. 

  407.          nestingResetTriggers = self.NESTABLE_TAGS.get(name)
    408. 

  408.          isNestable = nestingResetTriggers != None
    409. 

  409. -        isResetNesting = self.RESET_NESTING_TAGS.has_key(name)
    410. 

  410. +        isResetNesting = name in self.RESET_NESTING_TAGS
    411. 

  411.          popTo = None
    412. 

  412.          inclusive = True
    413. 

  413.          for i in range(len(self.tagStack)-1, 0, -1):
    414. 

  414. @@ -1381,7 +1381,7 @@
    415. 

  415.              if (nestingResetTriggers != None
    416. 

  416.                  and p.name in nestingResetTriggers) \
    417. 

  417.                  or (nestingResetTriggers == None and isResetNesting
    418. 

  418. -                    and self.RESET_NESTING_TAGS.has_key(p.name)):
    419. 

  419. +                    and p.name in self.RESET_NESTING_TAGS):
    420. 

  420.  
    421. 

  421.                  #If we encounter one of the nesting reset triggers
    422. 

  422.                  #peculiar to this tag, or we encounter another tag
    423. 

  423. @@ -1399,7 +1399,7 @@
    424. 

  424.          if self.quoteStack:
    425. 

  425.              #This is not a real tag.
    426. 

  426.              #print "<%s> is not real!" % name
    427. 

  427. -            attrs = ''.join(map(lambda(x, y): ' %s="%s"' % (x, y), attrs))
    428. 

  428. +            attrs = ''.join([' %s="%s"' % (x_y[0], x_y[1]) for x_y in attrs])
    429. 

  429.              self.handle_data('<%s%s>' % (name, attrs))
    430. 

  430.              return
    431. 

  431.          self.endData()
    432. 

  432. @@ -1493,7 +1493,7 @@
    433. 

  433.      BeautifulStoneSoup before writing your own subclass."""
    434. 

  434.  
    435. 

  435.      def __init__(self, *args, **kwargs):
    436. 

  436. -        if not kwargs.has_key('smartQuotesTo'):
    437. 

  437. +        if 'smartQuotesTo' not in kwargs:
    438. 

  438.              kwargs['smartQuotesTo'] = self.HTML_ENTITIES
    439. 

  439.          kwargs['isHTML'] = True
    440. 

  440.          BeautifulStoneSoup.__init__(self, *args, **kwargs)
    441. 

  441. @@ -1677,7 +1677,7 @@
    442. 

  442.              parent._getAttrMap()
    443. 

  443.              if (isinstance(tag, Tag) and len(tag.contents) == 1 and
    444. 

  444.                  isinstance(tag.contents[0], NavigableString) and
    445. 

  445. -                not parent.attrMap.has_key(tag.name)):
    446. 

  446. +                tag.name not in parent.attrMap):
    447. 

  447.                  parent[tag.name] = tag.contents[0]
    448. 

  448.          BeautifulStoneSoup.popTag(self)
    449. 

  449.  
    450. 

  450. @@ -1751,9 +1751,9 @@
    451. 

  451.                       self._detectEncoding(markup, isHTML)
    452. 

  452.          self.smartQuotesTo = smartQuotesTo
    453. 

  453.          self.triedEncodings = []
    454. 

  454. -        if markup == '' or isinstance(markup, unicode):
    455. 

  455. +        if markup == '' or isinstance(markup, str):
    456. 

  456.              self.originalEncoding = None
    457. 

  457. -            self.unicode = unicode(markup)
    458. 

  458. +            self.str = str(markup)
    459. 

  459.              return
    460. 

  460.  
    461. 

  461.          u = None
    462. 

  462. @@ -1766,7 +1766,7 @@
    463. 

  463.                  if u: break
    464. 

  464.  
    465. 

  465.          # If no luck and we have auto-detection library, try that:
    466. 

  466. -        if not u and chardet and not isinstance(self.markup, unicode):
    467. 

  467. +        if not u and chardet and not isinstance(self.markup, str):
    468. 

  468.              u = self._convertFrom(chardet.detect(self.markup)['encoding'])
    469. 

  469.  
    470. 

  470.          # As a last resort, try utf-8 and windows-1252:
    471. 

  471. @@ -1775,7 +1775,7 @@
    472. 

  472.                  u = self._convertFrom(proposed_encoding)
    473. 

  473.                  if u: break
    474. 

  474.  
    475. 

  475. -        self.unicode = u
    476. 

  476. +        self.str = u
    477. 

  477.          if not u: self.originalEncoding = None
    478. 

  478.  
    479. 

  479.      def _subMSChar(self, match):
    480. 

  480. @@ -1783,7 +1783,7 @@
    481. 

  481.          entity."""
    482. 

  482.          orig = match.group(1)
    483. 

  483.          sub = self.MS_CHARS.get(orig)
    484. 

  484. -        if type(sub) == types.TupleType:
    485. 

  485. +        if type(sub) == tuple:
    486. 

  486.              if self.smartQuotesTo == 'xml':
    487. 

  487.                  sub = '&#x'.encode() + sub[1].encode() + ';'.encode()
    488. 

  488.              else:
    489. 

  489. @@ -1804,7 +1804,7 @@
    490. 

  490.          if self.smartQuotesTo and proposed.lower() in("windows-1252",
    491. 

  491.                                                        "iso-8859-1",
    492. 

  492.                                                        "iso-8859-2"):
    493. 

  493. -            smart_quotes_re = "([\x80-\x9f])"
    494. 

  494. +            smart_quotes_re = b"([\x80-\x9f])"
    495. 

  495.              smart_quotes_compiled = re.compile(smart_quotes_re)
    496. 

  496.              markup = smart_quotes_compiled.sub(self._subMSChar, markup)
    497. 

  497.  
    498. 

  498. @@ -1813,7 +1813,7 @@
    499. 

  499.              u = self._toUnicode(markup, proposed)
    500. 

  500.              self.markup = u
    501. 

  501.              self.originalEncoding = proposed
    502. 

  502. -        except Exception, e:
    503. 

  503. +        except Exception as e:
    504. 

  504.              # print "That didn't work!"
    505. 

  505.              # print e
    506. 

  506.              return None
    507. 

  507. @@ -1842,7 +1842,7 @@
    508. 

  508.          elif data[:4] == '\xff\xfe\x00\x00':
    509. 

  509.              encoding = 'utf-32le'
    510. 

  510.              data = data[4:]
    511. 

  511. -        newdata = unicode(data, encoding)
    512. 

  512. +        newdata = str(data, encoding)
    513. 

  513.          return newdata
    514. 

  514.  
    515. 

  515.      def _detectEncoding(self, xml_data, isHTML=False):
    516. 

  516. @@ -1855,41 +1855,41 @@
    517. 

  517.              elif xml_data[:4] == '\x00\x3c\x00\x3f':
    518. 

  518.                  # UTF-16BE
    519. 

  519.                  sniffed_xml_encoding = 'utf-16be'
    520. 

  520. -                xml_data = unicode(xml_data, 'utf-16be').encode('utf-8')
    521. 

  521. +                xml_data = str(xml_data, 'utf-16be').encode('utf-8')
    522. 

  522.              elif (len(xml_data) >= 4) and (xml_data[:2] == '\xfe\xff') \
    523. 

  523.                       and (xml_data[2:4] != '\x00\x00'):
    524. 

  524.                  # UTF-16BE with BOM
    525. 

  525.                  sniffed_xml_encoding = 'utf-16be'
    526. 

  526. -                xml_data = unicode(xml_data[2:], 'utf-16be').encode('utf-8')
    527. 

  527. +                xml_data = str(xml_data[2:], 'utf-16be').encode('utf-8')
    528. 

  528.              elif xml_data[:4] == '\x3c\x00\x3f\x00':
    529. 

  529.                  # UTF-16LE
    530. 

  530.                  sniffed_xml_encoding = 'utf-16le'
    531. 

  531. -                xml_data = unicode(xml_data, 'utf-16le').encode('utf-8')
    532. 

  532. +                xml_data = str(xml_data, 'utf-16le').encode('utf-8')
    533. 

  533.              elif (len(xml_data) >= 4) and (xml_data[:2] == '\xff\xfe') and \
    534. 

  534.                       (xml_data[2:4] != '\x00\x00'):
    535. 

  535.                  # UTF-16LE with BOM
    536. 

  536.                  sniffed_xml_encoding = 'utf-16le'
    537. 

  537. -                xml_data = unicode(xml_data[2:], 'utf-16le').encode('utf-8')
    538. 

  538. +                xml_data = str(xml_data[2:], 'utf-16le').encode('utf-8')
    539. 

  539.              elif xml_data[:4] == '\x00\x00\x00\x3c':
    540. 

  540.                  # UTF-32BE
    541. 

  541.                  sniffed_xml_encoding = 'utf-32be'
    542. 

  542. -                xml_data = unicode(xml_data, 'utf-32be').encode('utf-8')
    543. 

  543. +                xml_data = str(xml_data, 'utf-32be').encode('utf-8')
    544. 

  544.              elif xml_data[:4] == '\x3c\x00\x00\x00':
    545. 

  545.                  # UTF-32LE
    546. 

  546.                  sniffed_xml_encoding = 'utf-32le'
    547. 

  547. -                xml_data = unicode(xml_data, 'utf-32le').encode('utf-8')
    548. 

  548. +                xml_data = str(xml_data, 'utf-32le').encode('utf-8')
    549. 

  549.              elif xml_data[:4] == '\x00\x00\xfe\xff':
    550. 

  550.                  # UTF-32BE with BOM
    551. 

  551.                  sniffed_xml_encoding = 'utf-32be'
    552. 

  552. -                xml_data = unicode(xml_data[4:], 'utf-32be').encode('utf-8')
    553. 

  553. +                xml_data = str(xml_data[4:], 'utf-32be').encode('utf-8')
    554. 

  554.              elif xml_data[:4] == '\xff\xfe\x00\x00':
    555. 

  555.                  # UTF-32LE with BOM
    556. 

  556.                  sniffed_xml_encoding = 'utf-32le'
    557. 

  557. -                xml_data = unicode(xml_data[4:], 'utf-32le').encode('utf-8')
    558. 

  558. +                xml_data = str(xml_data[4:], 'utf-32le').encode('utf-8')
    559. 

  559.              elif xml_data[:3] == '\xef\xbb\xbf':
    560. 

  560.                  # UTF-8 with BOM
    561. 

  561.                  sniffed_xml_encoding = 'utf-8'
    562. 

  562. -                xml_data = unicode(xml_data[3:], 'utf-8').encode('utf-8')
    563. 

  563. +                xml_data = str(xml_data[3:], 'utf-8').encode('utf-8')
    564. 

  564.              else:
    565. 

  565.                  sniffed_xml_encoding = 'ascii'
    566. 

  566.                  pass
    567. 

  567. @@ -1954,41 +1954,41 @@
    568. 

  568.                      250,251,252,253,254,255)
    569. 

  569.              import string
    570. 

  570.              c.EBCDIC_TO_ASCII_MAP = string.maketrans( \
    571. 

  571. -            ''.join(map(chr, range(256))), ''.join(map(chr, emap)))
    572. 

  572. +            ''.join(map(chr, list(range(256)))), ''.join(map(chr, emap)))
    573. 

  573.          return s.translate(c.EBCDIC_TO_ASCII_MAP)
    574. 

  574.  
    575. 

  575. -    MS_CHARS = { '\x80' : ('euro', '20AC'),
    576. 

  576. -                 '\x81' : ' ',
    577. 

  577. -                 '\x82' : ('sbquo', '201A'),
    578. 

  578. -                 '\x83' : ('fnof', '192'),
    579. 

  579. -                 '\x84' : ('bdquo', '201E'),
    580. 

  580. -                 '\x85' : ('hellip', '2026'),
    581. 

  581. -                 '\x86' : ('dagger', '2020'),
    582. 

  582. -                 '\x87' : ('Dagger', '2021'),
    583. 

  583. -                 '\x88' : ('circ', '2C6'),
    584. 

  584. -                 '\x89' : ('permil', '2030'),
    585. 

  585. -                 '\x8A' : ('Scaron', '160'),
    586. 

  586. -                 '\x8B' : ('lsaquo', '2039'),
    587. 

  587. -                 '\x8C' : ('OElig', '152'),
    588. 

  588. -                 '\x8D' : '?',
    589. 

  589. -                 '\x8E' : ('#x17D', '17D'),
    590. 

  590. -                 '\x8F' : '?',
    591. 

  591. -                 '\x90' : '?',
    592. 

  592. -                 '\x91' : ('lsquo', '2018'),
    593. 

  593. -                 '\x92' : ('rsquo', '2019'),
    594. 

  594. -                 '\x93' : ('ldquo', '201C'),
    595. 

  595. -                 '\x94' : ('rdquo', '201D'),
    596. 

  596. -                 '\x95' : ('bull', '2022'),
    597. 

  597. -                 '\x96' : ('ndash', '2013'),
    598. 

  598. -                 '\x97' : ('mdash', '2014'),
    599. 

  599. -                 '\x98' : ('tilde', '2DC'),
    600. 

  600. -                 '\x99' : ('trade', '2122'),
    601. 

  601. -                 '\x9a' : ('scaron', '161'),
    602. 

  602. -                 '\x9b' : ('rsaquo', '203A'),
    603. 

  603. -                 '\x9c' : ('oelig', '153'),
    604. 

  604. -                 '\x9d' : '?',
    605. 

  605. -                 '\x9e' : ('#x17E', '17E'),
    606. 

  606. -                 '\x9f' : ('Yuml', ''),}
    607. 

  607. +    MS_CHARS = { b'\x80' : ('euro', '20AC'),
    608. 

  608. +                 b'\x81' : ' ',
    609. 

  609. +                 b'\x82' : ('sbquo', '201A'),
    610. 

  610. +                 b'\x83' : ('fnof', '192'),
    611. 

  611. +                 b'\x84' : ('bdquo', '201E'),
    612. 

  612. +                 b'\x85' : ('hellip', '2026'),
    613. 

  613. +                 b'\x86' : ('dagger', '2020'),
    614. 

  614. +                 b'\x87' : ('Dagger', '2021'),
    615. 

  615. +                 b'\x88' : ('circ', '2C6'),
    616. 

  616. +                 b'\x89' : ('permil', '2030'),
    617. 

  617. +                 b'\x8A' : ('Scaron', '160'),
    618. 

  618. +                 b'\x8B' : ('lsaquo', '2039'),
    619. 

  619. +                 b'\x8C' : ('OElig', '152'),
    620. 

  620. +                 b'\x8D' : '?',
    621. 

  621. +                 b'\x8E' : ('#x17D', '17D'),
    622. 

  622. +                 b'\x8F' : '?',
    623. 

  623. +                 b'\x90' : '?',
    624. 

  624. +                 b'\x91' : ('lsquo', '2018'),
    625. 

  625. +                 b'\x92' : ('rsquo', '2019'),
    626. 

  626. +                 b'\x93' : ('ldquo', '201C'),
    627. 

  627. +                 b'\x94' : ('rdquo', '201D'),
    628. 

  628. +                 b'\x95' : ('bull', '2022'),
    629. 

  629. +                 b'\x96' : ('ndash', '2013'),
    630. 

  630. +                 b'\x97' : ('mdash', '2014'),
    631. 

  631. +                 b'\x98' : ('tilde', '2DC'),
    632. 

  632. +                 b'\x99' : ('trade', '2122'),
    633. 

  633. +                 b'\x9a' : ('scaron', '161'),
    634. 

  634. +                 b'\x9b' : ('rsaquo', '203A'),
    635. 

  635. +                 b'\x9c' : ('oelig', '153'),
    636. 

  636. +                 b'\x9d' : '?',
    637. 

  637. +                 b'\x9e' : ('#x17E', '17E'),
    638. 

  638. +                 b'\x9f' : ('Yuml', ''),}
    639. 

  639.  
    640. 

  640.  #######################################################################
    641. 

  641.  
    642. 

  642. @@ -1997,4 +1997,4 @@
    643. 

  643.  if __name__ == '__main__':
    644. 

  644.      import sys
    645. 

  645.      soup = BeautifulSoup(sys.stdin)
    646. 

  646. -    print soup.prettify()
    647. 

  647. +    print(soup.prettify())
    648. 

  648. --- BeautifulSoupTests.py
    649. 

  649. +++ BeautifulSoupTests.py
    650. 

  650. @@ -82,7 +82,7 @@
    651. 

  651.      def testFindAllText(self):
    652. 

  652.          soup = BeautifulSoup("<html>\xbb</html>")
    653. 

  653.          self.assertEqual(soup.findAll(text=re.compile('.*')),
    654. 

  654. -                         [u'\xbb'])
    655. 

  655. +                         ['\xbb'])
    656. 

  656.  
    657. 

  657.      def testFindAllByRE(self):
    658. 

  658.          import re
    659. 

  659. @@ -215,7 +215,7 @@
    660. 

  660.          soup = BeautifulSoup(self.x, parseOnlyThese=strainer)
    661. 

  661.          self.assertEquals(len(soup), 10)
    662. 

  662.  
    663. 

  663. -        strainer = SoupStrainer(text=lambda(x):x[8]=='3')
    664. 

  664. +        strainer = SoupStrainer(text=lambda x:x[8]=='3')
    665. 

  665.          soup = BeautifulSoup(self.x, parseOnlyThese=strainer)
    666. 

  666.          self.assertEquals(len(soup), 3)
    667. 

  667.  
    668. 

  668. @@ -256,7 +256,7 @@
    669. 

  669.          self.assertEqual(copied.decode(), self.soup.decode())
    670. 

  670.  
    671. 

  671.      def testUnicodePickle(self):
    672. 

  672. -        import cPickle as pickle
    673. 

  673. +        import pickle as pickle
    674. 

  674.          html = "<b>" + chr(0xc3) + "</b>"
    675. 

  675.          soup = BeautifulSoup(html)
    676. 

  676.          dumped = pickle.dumps(soup, pickle.HIGHEST_PROTOCOL)
    677. 

  677. @@ -586,23 +586,23 @@
    678. 

  678.          self.assertEquals(soup.decode(), "<<sacr&eacute; bleu!>>")
    679. 

  679.  
    680. 

  680.          soup = BeautifulStoneSoup(text, convertEntities=htmlEnt)
    681. 

  681. -        self.assertEquals(soup.decode(), u"<<sacr\xe9 bleu!>>")
    682. 

  682. +        self.assertEquals(soup.decode(), "<<sacr\xe9 bleu!>>")
    683. 

  683.  
    684. 

  684.          # Make sure the "XML", "HTML", and "XHTML" settings work.
    685. 

  685.          text = "&lt;&trade;&apos;"
    686. 

  686.          soup = BeautifulStoneSoup(text, convertEntities=xmlEnt)
    687. 

  687. -        self.assertEquals(soup.decode(), u"<&trade;'")
    688. 

  688. +        self.assertEquals(soup.decode(), "<&trade;'")
    689. 

  689.  
    690. 

  690.          soup = BeautifulStoneSoup(text, convertEntities=htmlEnt)
    691. 

  691. -        self.assertEquals(soup.decode(), u"<\u2122&apos;")
    692. 

  692. +        self.assertEquals(soup.decode(), "<\u2122&apos;")
    693. 

  693.  
    694. 

  694.          soup = BeautifulStoneSoup(text, convertEntities=xhtmlEnt)
    695. 

  695. -        self.assertEquals(soup.decode(), u"<\u2122'")
    696. 

  696. +        self.assertEquals(soup.decode(), "<\u2122'")
    697. 

  697.  
    698. 

  698.      def testNonBreakingSpaces(self):
    699. 

  699.          soup = BeautifulSoup("<a>&nbsp;&nbsp;</a>",
    700. 

  700.                               convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
    701. 

  701. -        self.assertEquals(soup.decode(), u"<a>\xa0\xa0</a>")
    702. 

  702. +        self.assertEquals(soup.decode(), "<a>\xa0\xa0</a>")
    703. 

  703.  
    704. 

  704.      def testWhitespaceInDeclaration(self):
    705. 

  705.          self.assertSoupEquals('<! DOCTYPE>', '<!DOCTYPE>')
    706. 

  706. @@ -617,27 +617,27 @@
    707. 

  707.          self.assertSoupEquals('<b>hello&nbsp;there</b>')
    708. 

  708.  
    709. 

  709.      def testEntitiesInAttributeValues(self):
    710. 

  710. -        self.assertSoupEquals('<x t="x&#241;">', '<x t="x\xc3\xb1"></x>',
    711. 

  711. +        self.assertSoupEquals('<x t="x&#241;">', b'<x t="x\xc3\xb1"></x>',
    712. 

  712.                                encoding='utf-8')
    713. 

  713. -        self.assertSoupEquals('<x t="x&#xf1;">', '<x t="x\xc3\xb1"></x>',
    714. 

  714. +        self.assertSoupEquals('<x t="x&#xf1;">', b'<x t="x\xc3\xb1"></x>',
    715. 

  715.                                encoding='utf-8')
    716. 

  716.  
    717. 

  717.          soup = BeautifulSoup('<x t="&gt;&trade;">',
    718. 

  718.                               convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
    719. 

  719. -        self.assertEquals(soup.decode(), u'<x t="&gt;\u2122"></x>')
    720. 

  720. +        self.assertEquals(soup.decode(), '<x t="&gt;\u2122"></x>')
    721. 

  721.  
    722. 

  722.          uri = "http://crummy.com?sacr&eacute;&amp;bleu"
    723. 

  723.          link = '<a href="%s"></a>' % uri
    724. 

  724.  
    725. 

  725.          soup = BeautifulSoup(link, convertEntities=BeautifulSoup.HTML_ENTITIES)
    726. 

  726.          self.assertEquals(soup.decode(),
    727. 

  727. -                          link.replace("&eacute;", u"\xe9"))
    728. 

  728. +                          link.replace("&eacute;", "\xe9"))
    729. 

  729.  
    730. 

  730.          uri = "http://crummy.com?sacr&eacute;&bleu"
    731. 

  731.          link = '<a href="%s"></a>' % uri
    732. 

  732.          soup = BeautifulSoup(link, convertEntities=BeautifulSoup.HTML_ENTITIES)
    733. 

  733.          self.assertEquals(soup.a['href'],
    734. 

  734. -                          uri.replace("&eacute;", u"\xe9"))
    735. 

  735. +                          uri.replace("&eacute;", "\xe9"))
    736. 

  736.  
    737. 

  737.      def testNakedAmpersands(self):
    738. 

  738.          html = {'convertEntities':BeautifulStoneSoup.HTML_ENTITIES}
    739. 

  739. @@ -663,13 +663,13 @@
    740. 

  740.      smart quote fixes."""
    741. 

  741.  
    742. 

  742.      def testUnicodeDammitStandalone(self):
    743. 

  743. -        markup = "<foo>\x92</foo>"
    744. 

  744. +        markup = b"<foo>\x92</foo>"
    745. 

  745.          dammit = UnicodeDammit(markup)
    746. 

  746. -        self.assertEquals(dammit.unicode, "<foo>&#x2019;</foo>")
    747. 

  747. +        self.assertEquals(dammit.str, "<foo>&#x2019;</foo>")
    748. 

  748.  
    749. 

  749. -        hebrew = "\xed\xe5\xec\xf9"
    750. 

  750. +        hebrew = b"\xed\xe5\xec\xf9"
    751. 

  751.          dammit = UnicodeDammit(hebrew, ["iso-8859-8"])
    752. 

  752. -        self.assertEquals(dammit.unicode, u'\u05dd\u05d5\u05dc\u05e9')
    753. 

  753. +        self.assertEquals(dammit.str, '\u05dd\u05d5\u05dc\u05e9')
    754. 

  754.          self.assertEquals(dammit.originalEncoding, 'iso-8859-8')
    755. 

  755.  
    756. 

  756.      def testGarbageInGarbageOut(self):
    757. 

  757. @@ -677,13 +677,13 @@
    758. 

  758.          asciiSoup = BeautifulStoneSoup(ascii)
    759. 

  759.          self.assertEquals(ascii, asciiSoup.decode())
    760. 

  760.  
    761. 

  761. -        unicodeData = u"<foo>\u00FC</foo>"
    762. 

  762. +        unicodeData = "<foo>\u00FC</foo>"
    763. 

  763.          utf8 = unicodeData.encode("utf-8")
    764. 

  764. -        self.assertEquals(utf8, '<foo>\xc3\xbc</foo>')
    765. 

  765. +        self.assertEquals(utf8, b'<foo>\xc3\xbc</foo>')
    766. 

  766.  
    767. 

  767.          unicodeSoup = BeautifulStoneSoup(unicodeData)
    768. 

  768.          self.assertEquals(unicodeData, unicodeSoup.decode())
    769. 

  769. -        self.assertEquals(unicodeSoup.foo.string, u'\u00FC')
    770. 

  770. +        self.assertEquals(unicodeSoup.foo.string, '\u00FC')
    771. 

  771.  
    772. 

  772.          utf8Soup = BeautifulStoneSoup(utf8, fromEncoding='utf-8')
    773. 

  773.          self.assertEquals(utf8, utf8Soup.encode('utf-8'))
    774. 

  774. @@ -696,18 +696,18 @@
    775. 

  775.  
    776. 

  776.      def testHandleInvalidCodec(self):
    777. 

  777.          for bad_encoding in ['.utf8', '...', 'utF---16.!']:
    778. 

  778. -            soup = BeautifulSoup(u"Räksmörgås".encode("utf-8"),
    779. 

  779. +            soup = BeautifulSoup("Räksmörgås".encode("utf-8"),
    780. 

  780.                                   fromEncoding=bad_encoding)
    781. 

  781.              self.assertEquals(soup.originalEncoding, 'utf-8')
    782. 

  782.  
    783. 

  783.      def testUnicodeSearch(self):
    784. 

  784. -        html = u'<html><body><h1>Räksmörgås</h1></body></html>'
    785. 

  785. +        html = '<html><body><h1>Räksmörgås</h1></body></html>'
    786. 

  786.          soup = BeautifulSoup(html)
    787. 

  787. -        self.assertEqual(soup.find(text=u'Räksmörgås'),u'Räksmörgås')
    788. 

  788. +        self.assertEqual(soup.find(text='Räksmörgås'),'Räksmörgås')
    789. 

  789.  
    790. 

  790.      def testRewrittenXMLHeader(self):
    791. 

  791. -        euc_jp = '<?xml version="1.0 encoding="euc-jp"?>\n<foo>\n\xa4\xb3\xa4\xec\xa4\xcfEUC-JP\xa4\xc7\xa5\xb3\xa1\xbc\xa5\xc7\xa5\xa3\xa5\xf3\xa5\xb0\xa4\xb5\xa4\xec\xa4\xbf\xc6\xfc\xcb\xdc\xb8\xec\xa4\xce\xa5\xd5\xa5\xa1\xa5\xa4\xa5\xeb\xa4\xc7\xa4\xb9\xa1\xa3\n</foo>\n'
    792. 

  792. -        utf8 = "<?xml version='1.0' encoding='utf-8'?>\n<foo>\n\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafEUC-JP\xe3\x81\xa7\xe3\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n</foo>\n"
    793. 

  793. +        euc_jp = b'<?xml version="1.0 encoding="euc-jp"?>\n<foo>\n\xa4\xb3\xa4\xec\xa4\xcfEUC-JP\xa4\xc7\xa5\xb3\xa1\xbc\xa5\xc7\xa5\xa3\xa5\xf3\xa5\xb0\xa4\xb5\xa4\xec\xa4\xbf\xc6\xfc\xcb\xdc\xb8\xec\xa4\xce\xa5\xd5\xa5\xa1\xa5\xa4\xa5\xeb\xa4\xc7\xa4\xb9\xa1\xa3\n</foo>\n'
    794. 

  794. +        utf8 = b"<?xml version='1.0' encoding='utf-8'?>\n<foo>\n\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafEUC-JP\xe3\x81\xa7\xe3\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n</foo>\n"
    795. 

  795.          soup = BeautifulStoneSoup(euc_jp)
    796. 

  796.          if soup.originalEncoding != "euc-jp":
    797. 

  797.              raise Exception("Test failed when parsing euc-jp document. "
    798. 

  798. @@ -718,12 +718,12 @@
    799. 

  799.          self.assertEquals(soup.originalEncoding, "euc-jp")
    800. 

  800.          self.assertEquals(soup.renderContents('utf-8'), utf8)
    801. 

  801.  
    802. 

  802. -        old_text = "<?xml encoding='windows-1252'><foo>\x92</foo>"
    803. 

  803. +        old_text = b"<?xml encoding='windows-1252'><foo>\x92</foo>"
    804. 

  804.          new_text = "<?xml version='1.0' encoding='utf-8'?><foo>&rsquo;</foo>"
    805. 

  805.          self.assertSoupEquals(old_text, new_text)
    806. 

  806.  
    807. 

  807.      def testRewrittenMetaTag(self):
    808. 

  808. -        no_shift_jis_html = '''<html><head>\n<meta http-equiv="Content-language" content="ja" /></head><body><pre>\n\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n</pre></body></html>'''
    809. 

  809. +        no_shift_jis_html = b'''<html><head>\n<meta http-equiv="Content-language" content="ja" /></head><body><pre>\n\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n</pre></body></html>'''
    810. 

  810.          soup = BeautifulSoup(no_shift_jis_html)
    811. 

  811.  
    812. 

  812.          # Beautiful Soup used to try to rewrite the meta tag even if the
    813. 

  813. @@ -733,16 +733,16 @@
    814. 

  814.          soup = BeautifulSoup(no_shift_jis_html, parseOnlyThese=strainer)
    815. 

  815.          self.assertEquals(soup.contents[0].name, 'pre')
    816. 

  816.  
    817. 

  817. -        meta_tag = ('<meta content="text/html; charset=x-sjis" '
    818. 

  818. -                    'http-equiv="Content-type" />')
    819. 

  819. +        meta_tag = (b'<meta content="text/html; charset=x-sjis" '
    820. 

  820. +                    b'http-equiv="Content-type" />')
    821. 

  821.          shift_jis_html = (
    822. 

  822. -            '<html><head>\n%s\n'
    823. 

  823. -            '<meta http-equiv="Content-language" content="ja" />'
    824. 

  824. -            '</head><body><pre>\n'
    825. 

  825. -            '\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
    826. 

  826. -            '\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
    827. 

  827. -            '\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n'
    828. 

  828. -            '</pre></body></html>') % meta_tag
    829. 

  829. +            b'<html><head>\n' + meta_tag + b'\n'
    830. 

  830. +            b'<meta http-equiv="Content-language" content="ja" />'
    831. 

  831. +            b'</head><body><pre>\n'
    832. 

  832. +            b'\x82\xb1\x82\xea\x82\xcdShift-JIS\x82\xc5\x83R\x81[\x83f'
    833. 

  833. +            b'\x83B\x83\x93\x83O\x82\xb3\x82\xea\x82\xbd\x93\xfa\x96{\x8c'
    834. 

  834. +            b'\xea\x82\xcc\x83t\x83@\x83C\x83\x8b\x82\xc5\x82\xb7\x81B\n'
    835. 

  835. +            b'</pre></body></html>')
    836. 

  836.          soup = BeautifulSoup(shift_jis_html)
    837. 

  837.          if soup.originalEncoding != "shift-jis":
    838. 

  838.              raise Exception("Test failed when parsing shift-jis document "
    839. 

  839. @@ -755,59 +755,59 @@
    840. 

  840.          content_type_tag = soup.meta['content']
    841. 

  841.          self.assertEquals(content_type_tag[content_type_tag.find('charset='):],
    842. 

  842.                            'charset=%SOUP-ENCODING%')
    843. 

  843. -        content_type = str(soup.meta)
    844. 

  844. +        content_type = soup.meta.decode()
    845. 

  845.          index = content_type.find('charset=')
    846. 

  846.          self.assertEqual(content_type[index:index+len('charset=utf8')+1],
    847. 

  847.                           'charset=utf-8')
    848. 

  848.          content_type = soup.meta.encode('shift-jis')
    849. 

  849. -        index = content_type.find('charset=')
    850. 

  850. +        index = content_type.find(b'charset=')
    851. 

  851.          self.assertEqual(content_type[index:index+len('charset=shift-jis')],
    852. 

  852.                           'charset=shift-jis'.encode())
    853. 

  853.  
    854. 

  854.          self.assertEquals(soup.encode('utf-8'), (
    855. 

  855. -                '<html><head>\n'
    856. 

  856. -                '<meta content="text/html; charset=utf-8" '
    857. 

  857. -                'http-equiv="Content-type" />\n'
    858. 

  858. -                '<meta http-equiv="Content-language" content="ja" />'
    859. 

  859. -                '</head><body><pre>\n'
    860. 

  860. -                '\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafShift-JIS\xe3\x81\xa7\xe3'
    861. 

  861. -                '\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3'
    862. 

  862. -                '\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6'
    863. 

  863. -                '\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3'
    864. 

  864. -                '\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n'
    865. 

  865. -                '</pre></body></html>'))
    866. 

  866. +                b'<html><head>\n'
    867. 

  867. +                b'<meta content="text/html; charset=utf-8" '
    868. 

  868. +                b'http-equiv="Content-type" />\n'
    869. 

  869. +                b'<meta http-equiv="Content-language" content="ja" />'
    870. 

  870. +                b'</head><body><pre>\n'
    871. 

  871. +                b'\xe3\x81\x93\xe3\x82\x8c\xe3\x81\xafShift-JIS\xe3\x81\xa7\xe3'
    872. 

  872. +                b'\x82\xb3\xe3\x83\xbc\xe3\x83\x87\xe3\x82\xa3\xe3\x83\xb3\xe3'
    873. 

  873. +                b'\x82\xb0\xe3\x81\x95\xe3\x82\x8c\xe3\x81\x9f\xe6\x97\xa5\xe6'
    874. 

  874. +                b'\x9c\xac\xe8\xaa\x9e\xe3\x81\xae\xe3\x83\x95\xe3\x82\xa1\xe3'
    875. 

  875. +                b'\x82\xa4\xe3\x83\xab\xe3\x81\xa7\xe3\x81\x99\xe3\x80\x82\n'
    876. 

  876. +                b'</pre></body></html>'))
    877. 

  877.          self.assertEquals(soup.encode("shift-jis"),
    878. 

  878.                            shift_jis_html.replace('x-sjis'.encode(),
    879. 

  879.                                                   'shift-jis'.encode()))
    880. 

  880.  
    881. 

  881. -        isolatin = """<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>"""
    882. 

  882. +        isolatin = b"""<html><meta http-equiv="Content-type" content="text/html; charset=ISO-Latin-1" />Sacr\xe9 bleu!</html>"""
    883. 

  883.          soup = BeautifulSoup(isolatin)
    884. 

  884.  
    885. 

  885.          utf8 = isolatin.replace("ISO-Latin-1".encode(), "utf-8".encode())
    886. 

  886. -        utf8 = utf8.replace("\xe9", "\xc3\xa9")
    887. 

  887. +        utf8 = utf8.replace(b"\xe9", b"\xc3\xa9")
    888. 

  888.          self.assertSoupEquals(soup.encode("utf-8"), utf8, encoding='utf-8')
    889. 

  889.  
    890. 

  890.      def testHebrew(self):
    891. 

  891. -        iso_8859_8= '<HEAD>\n<TITLE>Hebrew (ISO 8859-8) in Visual Directionality</TITLE>\n\n\n\n</HEAD>\n<BODY>\n<H1>Hebrew (ISO 8859-8) in Visual Directionality</H1>\n\xed\xe5\xec\xf9\n</BODY>\n'
    892. 

  892. -        utf8 = '<head>\n<title>Hebrew (ISO 8859-8) in Visual Directionality</title>\n</head>\n<body>\n<h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\n\xd7\x9d\xd7\x95\xd7\x9c\xd7\xa9\n</body>\n'
    893. 

  893. +        iso_8859_8= b'<HEAD>\n<TITLE>Hebrew (ISO 8859-8) in Visual Directionality</TITLE>\n\n\n\n</HEAD>\n<BODY>\n<H1>Hebrew (ISO 8859-8) in Visual Directionality</H1>\n\xed\xe5\xec\xf9\n</BODY>\n'
    894. 

  894. +        utf8 = b'<head>\n<title>Hebrew (ISO 8859-8) in Visual Directionality</title>\n</head>\n<body>\n<h1>Hebrew (ISO 8859-8) in Visual Directionality</h1>\n\xd7\x9d\xd7\x95\xd7\x9c\xd7\xa9\n</body>\n'
    895. 

  895.          soup = BeautifulStoneSoup(iso_8859_8, fromEncoding="iso-8859-8")
    896. 

  896.          self.assertEquals(soup.encode('utf-8'), utf8)
    897. 

  897.  
    898. 

  898.      def testSmartQuotesNotSoSmartAnymore(self):
    899. 

  899. -        self.assertSoupEquals("\x91Foo\x92 <!--blah-->",
    900. 

  900. +        self.assertSoupEquals(b"\x91Foo\x92 <!--blah-->",
    901. 

  901.                                '&lsquo;Foo&rsquo; <!--blah-->')
    902. 

  902.  
    903. 

  903.      def testDontConvertSmartQuotesWhenAlsoConvertingEntities(self):
    904. 

  904. -        smartQuotes = "Il a dit, \x8BSacr&eacute; bl&#101;u!\x9b"
    905. 

  905. +        smartQuotes = b"Il a dit, \x8BSacr&eacute; bl&#101;u!\x9b"
    906. 

  906.          soup = BeautifulSoup(smartQuotes)
    907. 

  907.          self.assertEquals(soup.decode(),
    908. 

  908.                            'Il a dit, &lsaquo;Sacr&eacute; bl&#101;u!&rsaquo;')
    909. 

  909.          soup = BeautifulSoup(smartQuotes, convertEntities="html")
    910. 

  910.          self.assertEquals(soup.encode('utf-8'),
    911. 

  911. -                          'Il a dit, \xe2\x80\xb9Sacr\xc3\xa9 bleu!\xe2\x80\xba')
    912. 

  912. +                          b'Il a dit, \xe2\x80\xb9Sacr\xc3\xa9 bleu!\xe2\x80\xba')
    913. 

  913.  
    914. 

  914.      def testDontSeeSmartQuotesWhereThereAreNone(self):
    915. 

  915. -        utf_8 = "\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
    916. 

  916. +        utf_8 = b"\343\202\261\343\203\274\343\202\277\343\202\244 Watch"
    917. 

  917.          self.assertSoupEquals(utf_8, encoding='utf-8')
    918. 

  918.  
    919. 

  919.  
    920. 

  920. --- setup.py
    921. 

  921. +++ setup.py
    922. 

  922. @@ -19,19 +19,19 @@
    923. 

  923.  suite = loader.loadTestsFromModule(BeautifulSoupTests)
    924. 

  924.  suite.run(result)
    925. 

  925.  if not result.wasSuccessful():
    926. 

  926. -    print "Unit tests have failed!"
    927. 

  927. +    print("Unit tests have failed!")
    928. 

  928.      for l in result.errors, result.failures:
    929. 

  929.          for case, error in l:
    930. 

  930. -            print "-" * 80
    931. 

  931. +            print("-" * 80)
    932. 

  932.              desc = case.shortDescription()
    933. 

  933.              if desc:
    934. 

  934. -                print desc
    935. 

  935. -            print error        
    936. 

  936. -    print '''If you see an error like: "'ascii' codec can't encode character...", see\nthe Beautiful Soup documentation:\n http://www.crummy.com/software/BeautifulSoup/documentation.html#Why%20can't%20Beautiful%20Soup%20print%20out%20the%20non-ASCII%20characters%20I%20gave%20it?'''
    937. 

  937. -    print "This might or might not be a problem depending on what you plan to do with\nBeautiful Soup."
    938. 

  938. +                print(desc)
    939. 

  939. +            print(error)        
    940. 

  940. +    print('''If you see an error like: "'ascii' codec can't encode character...", see\nthe Beautiful Soup documentation:\n http://www.crummy.com/software/BeautifulSoup/documentation.html#Why%20can't%20Beautiful%20Soup%20print%20out%20the%20non-ASCII%20characters%20I%20gave%20it?''')
    941. 

  941. +    print("This might or might not be a problem depending on what you plan to do with\nBeautiful Soup.")
    942. 

  942.      if sys.argv[1] == 'sdist':
    943. 

  943. -        print
    944. 

  944. -        print "I'm not going to make a source distribution since the tests don't pass."
    945. 

  945. +        print()
    946. 

  946. +        print("I'm not going to make a source distribution since the tests don't pass.")
    947. 

  947.          sys.exit(1)
    948. 

  948.  
    949. 

  949.  setup(name="BeautifulSoup",
    950. 

  950.