Mercurial > cpython-lru_cache-weakref

annotate Lib/HTMLParser.py @ 20354:fdc1914406e2 legacy-trunk

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Updated, and added a very terse description of PyMac_SetConsoleHandler().
author Jack Jansen <jack.jansen@cwi.nl>
date Tue, 09 Oct 2001 23:14:06 +0000
parents 299f5fcb0ba8
children 1acc4ba73b9d
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
1 """A parser for HTML and XHTML."""
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
2
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
3 # This file is based on sgmllib.py, but the API is slightly different.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
4
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
5 # XXX There should be a way to distinguish between PCDATA (parsed
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
6 # character data -- the normal case), RCDATA (replaceable character
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
7 # data -- only char and entity references and end tags are special)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
8 # and CDATA (character data -- only end tags are special).
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
9
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
10
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
11 import markupbase
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
12 import re
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
13 import string
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
14
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
15 # Regular expressions used for parsing
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
16
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
17 interesting_normal = re.compile('[&<]')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
18 interesting_cdata = re.compile(r'<(/|\Z)')
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
19 incomplete = re.compile('&[a-zA-Z#]')
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
20
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
21 entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
22 charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
23
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
24 starttagopen = re.compile('<[a-zA-Z]')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
25 piclose = re.compile('>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
26 endtagopen = re.compile('</')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
27 commentclose = re.compile(r'--\s*>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
28 tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
29 attrfind = re.compile(
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
30 r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
31 r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./:;+*%?!&$\(\)_#=~]*))?')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
32
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
33 locatestarttagend = re.compile(r"""
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
34 <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
35 (?:\s+ # whitespace before attribute name
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
36 (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
37 (?:\s*=\s* # value indicator
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
38 (?:'[^']*' # LITA-enclosed value
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
39 |\"[^\"]*\" # LIT-enclosed value
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
40 |[^'\">\s]+ # bare value
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
41 )
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
42 )?
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
43 )
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
44 )*
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
45 \s* # trailing whitespace
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
46 """, re.VERBOSE)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
47 endendtag = re.compile('>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
48 endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
49
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
50
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
51 class HTMLParseError(Exception):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
52 """Exception raised for all parse errors."""
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
53
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
54 def __init__(self, msg, position=(None, None)):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
55 assert msg
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
56 self.msg = msg
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
57 self.lineno = position[0]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
58 self.offset = position[1]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
59
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
60 def __str__(self):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
61 result = self.msg
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
62 if self.lineno is not None:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
63 result = result + ", at line %d" % self.lineno
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
64 if self.offset is not None:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
65 result = result + ", column %d" % (self.offset + 1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
66 return result
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
67
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
68
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
69 class HTMLParser(markupbase.ParserBase):
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
70 """Find tags and other markup and call handler functions.
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
71
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
72 Usage:
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
73 p = HTMLParser()
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
74 p.feed(data)
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
75 ...
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
76 p.close()
17932
ce7f0e380830 Removed incorrect comment left over from sgmllib.py.
Guido van Rossum <guido@python.org>
parents: 17853
diff changeset
77
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
78 Start tags are handled by calling self.handle_starttag() or
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
79 self.handle_startendtag(); end tags by self.handle_endtag(). The
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
80 data between tags is passed from the parser to the derived class
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
81 by calling self.handle_data() with the data as argument (the data
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
82 may be split up in arbitrary chunks). Entity references are
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
83 passed by calling self.handle_entityref() with the entity
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
84 reference as the argument. Numeric character references are
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
85 passed to self.handle_charref() with the string containing the
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
86 reference as the argument.
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
87 """
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
88
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
89 CDATA_CONTENT_ELEMENTS = ("script", "style")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
90
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
91
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
92 def __init__(self):
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
93 """Initialize and reset this instance."""
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
94 self.reset()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
95
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
96 def reset(self):
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
97 """Reset this instance. Loses all unprocessed data."""
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
98 self.rawdata = ''
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
99 self.stack = []
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
100 self.lasttag = '???'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
101 self.interesting = interesting_normal
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
102 markupbase.ParserBase.reset(self)
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
103
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
104 def feed(self, data):
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
105 """Feed data to the parser.
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
106
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
107 Call this as often as you want, with as little or as much text
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
108 as you want (may include '\n').
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
109 """
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
110 self.rawdata = self.rawdata + data
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
111 self.goahead(0)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
112
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
113 def close(self):
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
114 """Handle any buffered data."""
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
115 self.goahead(1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
116
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
117 def error(self, message):
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
118 raise HTMLParseError(message, self.getpos())
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
119
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
120 __starttag_text = None
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
121
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
122 def get_starttag_text(self):
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
123 """Return full source of start tag: '<...>'."""
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
124 return self.__starttag_text
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
125
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
126 def set_cdata_mode(self):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
127 self.interesting = interesting_cdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
128
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
129 def clear_cdata_mode(self):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
130 self.interesting = interesting_normal
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
131
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
132 # Internal -- handle data as far as reasonable. May leave state
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
133 # and data to be processed by a subsequent call. If 'end' is
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
134 # true, force handling all data as if followed by EOF marker.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
135 def goahead(self, end):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
136 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
137 i = 0
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
138 n = len(rawdata)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
139 while i < n:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
140 match = self.interesting.search(rawdata, i) # < or &
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
141 if match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
142 j = match.start()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
143 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
144 j = n
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
145 if i < j: self.handle_data(rawdata[i:j])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
146 i = self.updatepos(i, j)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
147 if i == n: break
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
148 if rawdata[i] == '<':
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
149 if starttagopen.match(rawdata, i): # < + letter
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
150 k = self.parse_starttag(i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
151 elif endtagopen.match(rawdata, i): # </
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
152 k = self.parse_endtag(i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
153 if k >= 0:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
154 self.clear_cdata_mode()
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
155 elif rawdata.startswith("<!--", i): # <!--
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
156 k = self.parse_comment(i)
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
157 elif rawdata.startswith("<?", i): # <?
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
158 k = self.parse_pi(i)
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
159 elif rawdata.startswith("<!", i): # <!
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
160 k = self.parse_declaration(i)
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
161 elif (i + 1) < n:
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18984
diff changeset
162 self.handle_data("<")
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18984
diff changeset
163 k = i + 1
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
164 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
165 break
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
166 if k < 0:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
167 if end:
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
168 self.error("EOF in middle of construct")
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
169 break
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
170 i = self.updatepos(i, k)
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
171 elif rawdata[i:i+2] == "&#":
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
172 match = charref.match(rawdata, i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
173 if match:
18984
00935031b373 Change some comments into docstrings.
Fred Drake <fdrake@acm.org>
parents: 17934
diff changeset
174 name = match.group()[2:-1]
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
175 self.handle_charref(name)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
176 k = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
177 if rawdata[k-1] != ';':
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18984
diff changeset
178 k = k - 1
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
179 i = self.updatepos(i, k)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
180 continue
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
181 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
182 break
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
183 elif rawdata[i] == '&':
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
184 match = entityref.match(rawdata, i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
185 if match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
186 name = match.group(1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
187 self.handle_entityref(name)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
188 k = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
189 if rawdata[k-1] != ';':
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18984
diff changeset
190 k = k - 1
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
191 i = self.updatepos(i, k)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
192 continue
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18984
diff changeset
193 match = incomplete.match(rawdata, i)
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18984
diff changeset
194 if match:
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
195 # match.group() will contain at least 2 chars
19410
c403af003884 Deal more appropriately with bare ampersands and pointy brackets; this
Fred Drake <fdrake@acm.org>
parents: 18984
diff changeset
196 rest = rawdata[i:]
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
197 if end and match.group() == rest:
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
198 self.error("EOF in middle of entity or char ref")
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
199 # incomplete
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
200 break
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
201 elif (i + 1) < n:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
202 # not the end of the buffer, and can't be confused
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
203 # with some other construct
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
204 self.handle_data("&")
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
205 i = self.updatepos(i, i + 1)
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
206 else:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
207 break
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
208 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
209 assert 0, "interesting.search() lied"
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
210 # end while
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
211 if end and i < n:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
212 self.handle_data(rawdata[i:n])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
213 i = self.updatepos(i, n)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
214 self.rawdata = rawdata[i:]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
215
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
216 # Internal -- parse comment, return end or -1 if not terminated
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
217 def parse_comment(self, i, report=1):
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
218 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
219 assert rawdata[i:i+4] == '<!--', 'unexpected call to parse_comment()'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
220 match = commentclose.search(rawdata, i+4)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
221 if not match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
222 return -1
19682
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
223 if report:
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
224 j = match.start()
8dfb13a4e175 Added reasonable parsing of the DOCTYPE declaration, fixed edge cases
Fred Drake <fdrake@acm.org>
parents: 19410
diff changeset
225 self.handle_comment(rawdata[i+4: j])
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
226 j = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
227 return j
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
228
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
229 # Internal -- parse processing instr, return end or -1 if not terminated
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
230 def parse_pi(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
231 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
232 assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
233 match = piclose.search(rawdata, i+2) # >
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
234 if not match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
235 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
236 j = match.start()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
237 self.handle_pi(rawdata[i+2: j])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
238 j = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
239 return j
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
240
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
241 # Internal -- handle starttag, return end or -1 if not terminated
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
242 def parse_starttag(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
243 self.__starttag_text = None
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
244 endpos = self.check_for_whole_start_tag(i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
245 if endpos < 0:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
246 return endpos
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
247 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
248 self.__starttag_text = rawdata[i:endpos]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
249
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
250 # Now parse the data between i+1 and j into a tag and attrs
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
251 attrs = []
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
252 match = tagfind.match(rawdata, i+1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
253 assert match, 'unexpected call to parse_starttag()'
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
254 k = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
255 self.lasttag = tag = string.lower(rawdata[i+1:k])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
256
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
257 while k < endpos:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
258 m = attrfind.match(rawdata, k)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
259 if not m:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
260 break
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
261 attrname, rest, attrvalue = m.group(1, 2, 3)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
262 if not rest:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
263 attrvalue = None
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
264 elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
265 attrvalue[:1] == '"' == attrvalue[-1:]:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
266 attrvalue = attrvalue[1:-1]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
267 attrvalue = self.unescape(attrvalue)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
268 attrs.append((string.lower(attrname), attrvalue))
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
269 k = m.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
270
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
271 end = string.strip(rawdata[k:endpos])
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
272 if end not in (">", "/>"):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
273 lineno, offset = self.getpos()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
274 if "\n" in self.__starttag_text:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
275 lineno = lineno + string.count(self.__starttag_text, "\n")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
276 offset = len(self.__starttag_text) \
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
277 - string.rfind(self.__starttag_text, "\n")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
278 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
279 offset = offset + len(self.__starttag_text)
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
280 self.error("junk characters in start tag: %s"
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
281 % `rawdata[k:endpos][:20]`)
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
282 if end[-2:] == '/>':
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
283 # XHTML-style empty tag: <span attr="value" />
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
284 self.handle_startendtag(tag, attrs)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
285 else:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
286 self.handle_starttag(tag, attrs)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
287 if tag in self.CDATA_CONTENT_ELEMENTS:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
288 self.set_cdata_mode()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
289 return endpos
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
290
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
291 # Internal -- check to see if we have a complete starttag; return end
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
292 # or -1 if incomplete.
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
293 def check_for_whole_start_tag(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
294 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
295 m = locatestarttagend.match(rawdata, i)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
296 if m:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
297 j = m.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
298 next = rawdata[j:j+1]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
299 if next == ">":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
300 return j + 1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
301 if next == "/":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
302 s = rawdata[j:j+2]
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
303 if s == "/>":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
304 return j + 2
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
305 if s == "/":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
306 # buffer boundary
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
307 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
308 # else bogus input
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
309 self.updatepos(i, j + 1)
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
310 self.error("malformed empty start tag")
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
311 if next == "":
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
312 # end of input
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
313 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
314 if next in ("abcdefghijklmnopqrstuvwxyz=/"
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
315 "ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
316 # end of input in or before attribute value, or we have the
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
317 # '/' from a '/>' ending
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
318 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
319 self.updatepos(i, j)
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
320 self.error("malformed start tag")
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
321 raise AssertionError("we should not get here!")
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
322
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
323 # Internal -- parse endtag, return end or -1 if incomplete
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
324 def parse_endtag(self, i):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
325 rawdata = self.rawdata
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
326 assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
327 match = endendtag.search(rawdata, i+1) # >
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
328 if not match:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
329 return -1
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
330 j = match.end()
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
331 match = endtagfind.match(rawdata, i) # </ + tag + >
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
332 if not match:
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
333 self.error("bad end tag: %s" % `rawdata[i:j]`)
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
334 tag = match.group(1)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
335 self.handle_endtag(string.lower(tag))
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
336 return j
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
337
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
338 # Overridable -- finish processing of start+end tag: <tag.../>
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
339 def handle_startendtag(self, tag, attrs):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
340 self.handle_starttag(tag, attrs)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
341 self.handle_endtag(tag)
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
342
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
343 # Overridable -- handle start tag
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
344 def handle_starttag(self, tag, attrs):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
345 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
346
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
347 # Overridable -- handle end tag
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
348 def handle_endtag(self, tag):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
349 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
350
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
351 # Overridable -- handle character reference
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
352 def handle_charref(self, name):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
353 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
354
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
355 # Overridable -- handle entity reference
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
356 def handle_entityref(self, name):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
357 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
358
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
359 # Overridable -- handle data
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
360 def handle_data(self, data):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
361 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
362
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
363 # Overridable -- handle comment
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
364 def handle_comment(self, data):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
365 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
366
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
367 # Overridable -- handle declaration
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
368 def handle_decl(self, decl):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
369 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
370
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
371 # Overridable -- handle processing instruction
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
372 def handle_pi(self, data):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
373 pass
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
374
20067
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
375 def unknown_decl(self, data):
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
376 self.error("unknown declaration: " + `data`)
299f5fcb0ba8 Re-factor the HTMLParser class to use the new markupbase.ParserBase class.
Fred Drake <fdrake@acm.org>
parents: 19953
diff changeset
377
17853
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
378 # Internal -- helper to remove special character quoting
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
379 def unescape(self, s):
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
380 if '&' not in s:
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
381 return s
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
382 s = string.replace(s, "&lt;", "<")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
383 s = string.replace(s, "&gt;", ">")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
384 s = string.replace(s, "&apos;", "'")
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
385 s = string.replace(s, "&quot;", '"')
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
386 s = string.replace(s, "&amp;", "&") # Must be last
055fc046e080 A much improved HTML parser -- a replacement for sgmllib. The API is
Guido van Rossum <guido@python.org>
parents:
diff changeset
387 return s