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
|
'''HTML parser, built from standard lib's sgmllib.
Tag names are normalised to upper case, the usual HTML fashion.
'''
from sgmllib import SGMLParser
from xml.dom import core
from xml.dom.builder import Builder
import string
class HtmlBuilder(SGMLParser, Builder):
from htmlentitydefs import entitydefs
def __init__(self):
SGMLParser.__init__(self)
Builder.__init__(self)
self.empties = [
'META', 'BASE', 'LINK',
'HR', 'BR',
'IMG', 'PARAM',
'INPUT', 'OPTION', 'ISINDEX'
]
list = ('OL', 'UL', 'DL')
heading = ('H1', 'H2', 'H3', 'H4', 'H5', 'H6')
blocks = ('P', 'ADDRESS', 'BLOCKQUOTE', 'FORM', 'TABLE', 'PRE') + \
heading # + list
self.infer_ends = {
'P': blocks,
'LI': ('LI',),
'DT': ('DT',),
'DD': ('DT', 'DD'),
'TR': ('TR',),
'TH': ('TH', 'TD', 'TR'),
'TD': ('TH', 'TD', 'TR'),
}
def unknown_starttag(self, tag, attrs):
tag = string.upper(tag)
#print 'starting', tag
attributes = {}
for k, v in attrs:
attributes[string.upper(k)] = v
#print self.stack
while self.stack:
if self.infer_ends.has_key(self.stack[-1]):
if tag in self.infer_ends[self.stack[-1]]:
#print tag, 'ending', self.stack[-1]
Builder.endElement(self, self.stack[-1])
del self.stack[-1]
#print self.stack
else:
break
else:
break
#print self.stack
Builder.startElement(self, tag, attributes)
if not tag in self.empties:
self.stack.append(tag)
else:
Builder.endElement(self, tag)
def unknown_endtag(self, tag):
tag = string.upper(tag)
#print 'ending', tag
while self.stack:
if tag in self.empties:
continue
start_tag = self.stack[-1]
del self.stack[-1]
Builder.endElement(self, start_tag)
if start_tag == tag:
break
def handle_data(self, s):
#print `s`
Builder.text(self, s)
# Test.
if __name__ == '__main__':
import sys
b = HtmlBuilder()
b.feed(open(sys.argv[1]).read())
b.close()
# print b.document
# print b.document.documentElement
from writer import HtmlLineariser
w = HtmlLineariser()
print w.linearise(b.document)
|
