"""A parser for HTML and XHTML."""
# This file is based on sgmllib.py, but the API is slightly different.
# XXX There should be a way to distinguish between PCDATA (parsed
# character data -- the normal case), RCDATA (replaceable character
# data -- only char and entity references and end tags are special)
# and CDATA (character data -- only end tags are special).
# Regular expressions used for parsing
interesting_normal
= re
.compile('[&<]')
interesting_cdata
= re
.compile(r
'<(/|\Z)')
incomplete
= re
.compile('&[a-zA-Z#]')
entityref
= re
.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
charref
= re
.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
starttagopen
= re
.compile('<[a-zA-Z]')
piclose
= re
.compile('>')
commentclose
= re
.compile(r
'--\s*>')
tagfind
= re
.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
r
'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
r
'(\'[^
\']*\'|
"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?')
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
(?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
(?:\s*=\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|\"[^\"]*\" # LIT-enclosed value
\s* # trailing whitespace
endendtag = re.compile('>')
endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
class HTMLParseError(Exception):
"""Exception raised for all parse errors."""
def __init__(self, msg, position=(None, None)):
self.lineno = position[0]
self.offset = position[1]
if self.lineno is not None:
result = result + ", at line
%d" % self.lineno
if self.offset is not None:
result = result + ", column
%d" % (self.offset + 1)
class HTMLParser(markupbase.ParserBase):
"""Find tags and other markup and call handler functions.
Start tags are handled by calling self.handle_starttag() or
self.handle_startendtag(); end tags by self.handle_endtag(). The
data between tags is passed from the parser to the derived class
by calling self.handle_data() with the data as argument (the data
may be split up in arbitrary chunks). Entity references are
passed by calling self.handle_entityref() with the entity
reference as the argument. Numeric character references are
passed to self.handle_charref() with the string containing the
reference as the argument.
CDATA_CONTENT_ELEMENTS = ("script
", "style
")
"""Initialize and reset this instance."""
"""Reset this instance. Loses all unprocessed data."""
self.interesting = interesting_normal
markupbase.ParserBase.reset(self)
"""Feed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
self.rawdata = self.rawdata + data
"""Handle any buffered data."""
def error(self, message):
raise HTMLParseError(message, self.getpos())
def get_starttag_text(self):
"""Return full source of start tag: '<...>'."""
return self.__starttag_text
def set_cdata_mode(self):
self.interesting = interesting_cdata
def clear_cdata_mode(self):
self.interesting = interesting_normal
# Internal -- handle data as far as reasonable. May leave state
# and data to be processed by a subsequent call. If 'end' is
# true, force handling all data as if followed by EOF marker.
match = self.interesting.search(rawdata, i) # < or &
if i < j: self.handle_data(rawdata[i:j])
startswith = rawdata.startswith
if starttagopen.match(rawdata, i): # < + letter
k = self.parse_starttag(i)
elif startswith("</", i):
elif startswith("<!--", i):
k = self.parse_comment(i)
elif startswith("<?
", i):
elif startswith("<!", i):
k = self.parse_declaration(i)
self.error("EOF
in middle of construct
")
elif startswith("&#", i):
match
= charref
.match(rawdata
, i
)
name
= match
.group()[2:-1]
self
.handle_charref(name
)
if not startswith(';', k
-1):
match
= entityref
.match(rawdata
, i
)
self
.handle_entityref(name
)
if not startswith(';', k
-1):
match
= incomplete
.match(rawdata
, i
)
# match.group() will contain at least 2 chars
if end
and match
.group() == rawdata
[i
:]:
self
.error("EOF in middle of entity or char ref")
# not the end of the buffer, and can't be confused
# with some other construct
i
= self
.updatepos(i
, i
+ 1)
assert 0, "interesting.search() lied"
self
.handle_data(rawdata
[i
:n
])
self
.rawdata
= rawdata
[i
:]
# Internal -- parse processing instr, return end or -1 if not terminated
assert rawdata
[i
:i
+2] == '<?', 'unexpected call to parse_pi()'
match
= piclose
.search(rawdata
, i
+2) # >
self
.handle_pi(rawdata
[i
+2: j
])
# Internal -- handle starttag, return end or -1 if not terminated
def parse_starttag(self
, i
):
self
.__starttag
_text
= None
endpos
= self
.check_for_whole_start_tag(i
)
self
.__starttag
_text
= rawdata
[i
:endpos
]
# Now parse the data between i+1 and j into a tag and attrs
match
= tagfind
.match(rawdata
, i
+1)
assert match
, 'unexpected call to parse_starttag()'
self
.lasttag
= tag
= rawdata
[i
+1:k
].lower()
m
= attrfind
.match(rawdata
, k
)
attrname
, rest
, attrvalue
= m
.group(1, 2, 3)
elif attrvalue
[:1] == '\'' == attrvalue
[-1:] or \
attrvalue
[:1] == '"' == attrvalue
[-1:]:
attrvalue
= attrvalue
[1:-1]
attrvalue
= self
.unescape(attrvalue
)
attrs
.append((attrname
.lower(), attrvalue
))
end
= rawdata
[k
:endpos
].strip()
if end
not in (">", "/>"):
lineno
, offset
= self
.getpos()
if "\n" in self
.__starttag
_text
:
lineno
= lineno
+ self
.__starttag
_text
.count("\n")
offset
= len(self
.__starttag
_text
) \
- self
.__starttag
_text
.rfind("\n")
offset
= offset
+ len(self
.__starttag
_text
)
self
.error("junk characters in start tag: %r"
% (rawdata
[k
:endpos
][:20],))
# XHTML-style empty tag: <span attr="value" />
self
.handle_startendtag(tag
, attrs
)
self
.handle_starttag(tag
, attrs
)
if tag
in self
.CDATA_CONTENT_ELEMENTS
:
# Internal -- check to see if we have a complete starttag; return end
def check_for_whole_start_tag(self
, i
):
m
= locatestarttagend
.match(rawdata
, i
)
if rawdata
.startswith("/>", j
):
if rawdata
.startswith("/", j
):
self
.error("malformed empty start tag")
if next
in ("abcdefghijklmnopqrstuvwxyz=/"
"ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
# end of input in or before attribute value, or we have the
self
.error("malformed start tag")
raise AssertionError("we should not get here!")
# Internal -- parse endtag, return end or -1 if incomplete
def parse_endtag(self
, i
):
assert rawdata
[i
:i
+2] == "</", "unexpected call to parse_endtag"
match
= endendtag
.search(rawdata
, i
+1) # >
match
= endtagfind
.match(rawdata
, i
) # </ + tag + >
self
.error("bad end tag: %r" % (rawdata
[i
:j
],))
self
.handle_endtag(tag
.lower())
# Overridable -- finish processing of start+end tag: <tag.../>
def handle_startendtag(self
, tag
, attrs
):
self
.handle_starttag(tag
, attrs
)
# Overridable -- handle start tag
def handle_starttag(self
, tag
, attrs
):
# Overridable -- handle end tag
def handle_endtag(self
, tag
):
# Overridable -- handle character reference
def handle_charref(self
, name
):
# Overridable -- handle entity reference
def handle_entityref(self
, name
):
# Overridable -- handle data
def handle_data(self
, data
):
# Overridable -- handle comment
def handle_comment(self
, data
):
# Overridable -- handle declaration
def handle_decl(self
, decl
):
# Overridable -- handle processing instruction
def handle_pi(self
, data
):
def unknown_decl(self
, data
):
self
.error("unknown declaration: %r" % (data
,))
# Internal -- helper to remove special character quoting
s
= s
.replace("<", "<")
s
= s
.replace(">", ">")
s
= s
.replace("'", "'")
s
= s
.replace(""", '"')
s
= s
.replace("&", "&") # Must be last