1
import HTMLParser as _HTMLParser
5
class HTMLParser(_HTMLParser.HTMLParser):
7
Patched version of stdlib's HTMLParser with patch from:
8
http://bugs.python.org/issue670664
11
_HTMLParser.HTMLParser.__init__(self)
14
def set_cdata_mode(self, tag):
16
self.interesting = _HTMLParser.interesting_cdata
17
except AttributeError:
18
self.interesting = re.compile(r'</\s*%s\s*>' % tag.lower(), re.I)
19
self.cdata_tag = tag.lower()
21
def clear_cdata_mode(self):
22
self.interesting = _HTMLParser.interesting_normal
25
# Internal -- handle starttag, return end or -1 if not terminated
26
def parse_starttag(self, i):
27
self.__starttag_text = None
28
endpos = self.check_for_whole_start_tag(i)
31
rawdata = self.rawdata
32
self.__starttag_text = rawdata[i:endpos]
34
# Now parse the data between i+1 and j into a tag and attrs
36
match = _HTMLParser.tagfind.match(rawdata, i + 1)
37
assert match, 'unexpected call to parse_starttag()'
39
self.lasttag = tag = rawdata[i + 1:k].lower()
42
m = _HTMLParser.attrfind.match(rawdata, k)
45
attrname, rest, attrvalue = m.group(1, 2, 3)
48
elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
49
attrvalue[:1] == '"' == attrvalue[-1:]:
50
attrvalue = attrvalue[1:-1]
51
attrvalue = self.unescape(attrvalue)
52
attrs.append((attrname.lower(), attrvalue))
55
end = rawdata[k:endpos].strip()
56
if end not in (">", "/>"):
57
lineno, offset = self.getpos()
58
if "\n" in self.__starttag_text:
59
lineno = lineno + self.__starttag_text.count("\n")
60
offset = len(self.__starttag_text) \
61
- self.__starttag_text.rfind("\n")
63
offset = offset + len(self.__starttag_text)
64
self.error("junk characters in start tag: %r"
65
% (rawdata[k:endpos][:20],))
66
if end.endswith('/>'):
67
# XHTML-style empty tag: <span attr="value" />
68
self.handle_startendtag(tag, attrs)
70
self.handle_starttag(tag, attrs)
71
if tag in self.CDATA_CONTENT_ELEMENTS:
72
self.set_cdata_mode(tag) # <--------------------------- Changed
75
# Internal -- parse endtag, return end or -1 if incomplete
76
def parse_endtag(self, i):
77
rawdata = self.rawdata
78
assert rawdata[i:i + 2] == "</", "unexpected call to parse_endtag"
79
match = _HTMLParser.endendtag.search(rawdata, i + 1) # >
83
match = _HTMLParser.endtagfind.match(rawdata, i) # </ + tag + >
85
if self.cdata_tag is not None: # *** add ***
86
self.handle_data(rawdata[i:j]) # *** add ***
87
return j # *** add ***
88
self.error("bad end tag: %r" % (rawdata[i:j],))
89
# --- changed start ---------------------------------------------------
90
tag = match.group(1).strip()
91
if self.cdata_tag is not None:
92
if tag.lower() != self.cdata_tag:
93
self.handle_data(rawdata[i:j])
95
# --- changed end -----------------------------------------------------
96
self.handle_endtag(tag.lower())
97
self.clear_cdata_mode()