diff options
Diffstat (limited to 'module/lib/BeautifulSoup.py')
-rw-r--r-- | module/lib/BeautifulSoup.py | 57 |
1 files changed, 29 insertions, 28 deletions
diff --git a/module/lib/BeautifulSoup.py b/module/lib/BeautifulSoup.py index 55567f588..9f61c3ca0 100644 --- a/module/lib/BeautifulSoup.py +++ b/module/lib/BeautifulSoup.py @@ -483,15 +483,15 @@ class Tag(PageElement): def _invert(h): "Cheap function to invert a hash." i = {} - for k,v in h.items(): + for k, v in h.items(): i[v] = k return i - XML_ENTITIES_TO_SPECIAL_CHARS = { "apos" : "'", - "quot" : '"', - "amp" : "&", - "lt" : "<", - "gt" : ">" } + XML_ENTITIES_TO_SPECIAL_CHARS = {"apos": "'", + "quot": '"', + "amp": "&", + "lt": "<", + "gt": ">"} XML_SPECIAL_CHARS_TO_ENTITIES = _invert(XML_ENTITIES_TO_SPECIAL_CHARS) @@ -929,7 +929,7 @@ class SoupStrainer: markupAttrMap = markupAttrs else: markupAttrMap = {} - for k,v in markupAttrs: + for k, v in markupAttrs: markupAttrMap[k] = v attrValue = markupAttrMap.get(attr) if not self._matches(attrValue, matchAgainst): @@ -1018,7 +1018,7 @@ def buildTagMap(default, *args): for portion in args: if hasattr(portion, 'items'): #It's a map. Merge it. - for k,v in portion.items(): + for k, v in portion.items(): built[k] = v elif hasattr(portion, '__iter__'): # is a list #It's a list. Map each item to the default. @@ -1150,7 +1150,7 @@ class BeautifulStoneSoup(Tag, SGMLParser): n = int(name) except ValueError: return - if not 0 <= n <= 127 : # ASCII ends at 127, not 255 + if not 0 <= n <= 127: # ASCII ends at 127, not 255 return return self.convert_codepoint(n) @@ -1758,7 +1758,7 @@ class UnicodeDammit: # meta tags to the corresponding Python codec names. It only covers # values that aren't in Python's aliases and can't be determined # by the heuristics in find_codec. - CHARSET_ALIASES = { "macintosh" : "mac-roman", + CHARSET_ALIASES = {"macintosh": "mac-roman", "x-sjis" : "shift-jis" } def __init__(self, markup, overrideEncodings=[], @@ -1947,23 +1947,23 @@ class UnicodeDammit: def _ebcdic_to_ascii(self, s): c = self.__class__ if not c.EBCDIC_TO_ASCII_MAP: - emap = (0,1,2,3,156,9,134,127,151,141,142,11,12,13,14,15, - 16,17,18,19,157,133,8,135,24,25,146,143,28,29,30,31, - 128,129,130,131,132,10,23,27,136,137,138,139,140,5,6,7, - 144,145,22,147,148,149,150,4,152,153,154,155,20,21,158,26, - 32,160,161,162,163,164,165,166,167,168,91,46,60,40,43,33, - 38,169,170,171,172,173,174,175,176,177,93,36,42,41,59,94, - 45,47,178,179,180,181,182,183,184,185,124,44,37,95,62,63, - 186,187,188,189,190,191,192,193,194,96,58,35,64,39,61,34, - 195,97,98,99,100,101,102,103,104,105,196,197,198,199,200, - 201,202,106,107,108,109,110,111,112,113,114,203,204,205, - 206,207,208,209,126,115,116,117,118,119,120,121,122,210, - 211,212,213,214,215,216,217,218,219,220,221,222,223,224, - 225,226,227,228,229,230,231,123,65,66,67,68,69,70,71,72, - 73,232,233,234,235,236,237,125,74,75,76,77,78,79,80,81, - 82,238,239,240,241,242,243,92,159,83,84,85,86,87,88,89, - 90,244,245,246,247,248,249,48,49,50,51,52,53,54,55,56,57, - 250,251,252,253,254,255) + emap = (0, 1, 2, 3, 156, 9, 134, 127, 151, 141, 142, 11, 12, 13, 14, 15, + 16, 17, 18, 19, 157, 133, 8, 135, 24, 25, 146, 143, 28, 29, 30, 31, + 128, 129, 130, 131, 132, 10, 23, 27, 136, 137, 138, 139, 140, 5, 6, 7, + 144, 145, 22, 147, 148, 149, 150, 4, 152, 153, 154, 155, 20, 21, 158, 26, + 32, 160, 161, 162, 163, 164, 165, 166, 167, 168, 91, 46, 60, 40, 43, 33, + 38, 169, 170, 171, 172, 173, 174, 175, 176, 177, 93, 36, 42, 41, 59, 94, + 45, 47, 178, 179, 180, 181, 182, 183, 184, 185, 124, 44, 37, 95, 62, 63, + 186, 187, 188, 189, 190, 191, 192, 193, 194, 96, 58, 35, 64, 39, 61, 34, + 195, 97, 98, 99, 100, 101, 102, 103, 104, 105, 196, 197, 198, 199, 200, + 201, 202, 106, 107, 108, 109, 110, 111, 112, 113, 114, 203, 204, 205, + 206, 207, 208, 209, 126, 115, 116, 117, 118, 119, 120, 121, 122, 210, + 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, + 225, 226, 227, 228, 229, 230, 231, 123, 65, 66, 67, 68, 69, 70, 71, 72, + 73, 232, 233, 234, 235, 236, 237, 125, 74, 75, 76, 77, 78, 79, 80, 81, + 82, 238, 239, 240, 241, 242, 243, 92, 159, 83, 84, 85, 86, 87, 88, 89, + 90, 244, 245, 246, 247, 248, 249, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, + 250, 251, 252, 253, 254, 255) import string c.EBCDIC_TO_ASCII_MAP = string.maketrans( \ ''.join(map(chr, range(256))), ''.join(map(chr, emap))) @@ -2000,7 +2000,8 @@ class UnicodeDammit: '\x9c' : ('oelig', '153'), '\x9d' : '?', '\x9e' : ('#x17E', '17E'), - '\x9f' : ('Yuml', ''),} + '\x9f' : ('Yuml', '') + } ####################################################################### |