File "parser.cpython-37.pyc"

Full Path: /home/attunedd/public_html/byp/izo/con7ext_sym404/rintoar.txt/opt/alt/python37/lib64/python3.7/html/__pycache__/parser.cpython-37.pyc
File size: 10.84 KB
MIME-type: text/x-bytecode.python
Charset: 8 bit

B

 f9E@sdZd
dl
Z
d
dlZd
dlZd
dlmZ
dg
Ze
d
Ze
d
Z	e
d
Z
e
d
Ze
d	
Ze
d

Z
e
d
Ze
d
Ze
d

Ze
de
jZe
d

Ze
d
ZGdddejZdS)zA parser for HTML and XHTML.N)
unescape
HTMLParserz[&<]z
&[a-zA-Z#]z%&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]z)&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]z	<[a-zA-Z]
>z--\s*>z+([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*z]((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*aF
  <[a-zA-Z][^\t\n\r\f />\x00]*       # tag name
  (?:[\s/]*                          # optional whitespace before attribute name
    (?:(?<=['"\s/])[^\s/>][^\s/=>]*  # attribute name
      (?:\s*=+\s*                    # value indicator
        (?:'[^']*'                   # LITA-enclosed value
          |"[^"]*"                   # LIT-enclosed value
          |(?!['"])[^>\s]*           # bare value
         )
         (?:\s*,)*                   # possibly followed by a comma
       )?(?:\s|/(?!>))*
     )*
   )?
  \s*                                # trailing whitespace
z#</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>c@seZ
dZd
ZdZdd
ddZddZd	d
ZddZd
Z	ddZ
ddZddZddZ
ddZd9dd
ZddZddZdd Zd!d"Zd#d$Zd%d&Zd'd(Zd)d*Zd+d,Zd-d.Zd/d0Zd1d2Zd3d4Zd5d6Zd7d8Zd
S):raEFind tags and other markup and call handler functions.

    Usage:
        p = HTMLParser()
        p.feed(data)
        ...
        p.close()

    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).  If convert_charrefs is
    True the character references are converted automatically to the
    corresponding Unicode character (and self.handle_data() is no
    longer split in chunks), otherwise they are passed by calling
    self.handle_entityref() or self.handle_charref() with the string
    containing respectively the named or numeric reference as the
    argument.
    )ZscriptZstyleT)
convert_charrefsc

Cs|
|_|

d
S)zInitialize and reset this instance.

        If convert_charrefs is True (the default), all character references
        are automatically converted to the corresponding Unicode characters.
        N)rreset)selfrr0/opt/alt/python37/lib64/python3.7/html/parser.py__init__Ws
zHTMLParser.__init__c

Cs(d
|_d|_
t|_d|_tj|

dS)z1Reset this instance.  Loses all unprocessed data.z???N)rawdatalasttaginteresting_normalinteresting
cdata_elem_markupbase
ParserBaser)
rrrr	r`s




zHTMLParser.resetcCs|j|
|_|
d


dS)zFeed data to the parser.

        Call this as often as you want, with as little or as much text
        as you want (may include '\n').
        r
N)rgoahead)rdatarrr	feedhs
zHTMLParser.feedc

Cs|d


dS)zHandle any buffered data.
N)
r)
rrrr	closeqszHTMLParser.closeNc


Cs|jS)
z)Return full source of start tag: '<...>'.)
_HTMLParser__starttag_text)
rrrr	get_starttag_textwszHTMLParser.get_starttag_textcCs$|
|_
td
|j
tj|_dS)Nz</\s*%s\s*>)lowerrrecompile
Ir)relemrrr	set_cdata_mode{s


zHTMLParser.set_cdata_modec

Cst|_
d|_dS)
N)rrr)
rrrr	clear_cdata_modes

zHTMLParser.clear_cdata_modecCsN|j}d
}t
|
}x||kr|jrx|jsx|d|}|d
kr|dt||d}|d
krrtd
	||srP|}n(|j
	||}|r|}n|jrP|}||kr|jr|js|t
|||


n||||

|||}||krP|j}|d|rDt||
r ||
}	n|d|
r8||
}	nl|d|
rP||
}	nT|d|
rh||
}	n<|d	|
r||
}	n$|d
|k
r|d

|d
}	nP|	d
kr6|

sP|d|d
}	|	d
k
r|d|d
}	|	d
k
r|d
}	n|	d
7}	|jr$|js$|t
|||	


n||||	

|||	}q|d|rt||}|r|d
d}
||


|}	|d|	d
s|	d
}	|||	}qn:d||dkr||||d


|||d
}Pq|d|rt||}|rH|d

}
||


|}	|d|	d
s:|	d
}	|||	}qt||}|r|
r|||dkr|}	|	|k
r|}	|||d
}Pn,|d
|kr|d

|||d
}nPqd
std

qW|
r<||kr<|js<|jr|js|t
|||


n||||

|||}||d|_dS)Nr

<
&"z[\s;]z</z<!--z<?z<!rrz&#
;zinteresting.search() lied)rlenrrfindrfindmaxrrsearchrstarthandle_datarZ	updatepos
startswithstarttagopenmatchparse_starttagparse_endtag
parse_commentparse_piparse_html_declarationcharrefgrouphandle_charrefend	entityrefhandle_entityref
incompleteAssertionError)rr9r
i
n
jZampposr0r.
knamerrr	rs




























































































zHTMLParser.goaheadcCs|j}||
|
d
dks"t
d

||
|
ddkr@||

S||
|
ddkr^||

S||
|
dd	kr|d
|
d}|dkrdS|||
d
|

|dS||

SdS)
Nr$z<!z+unexpected call to parse_html_declaration()z<!--z<![	z	<!doctyperr%r)rr=r3Zparse_marked_sectionrr(handle_declparse_bogus_comment)rr>rgtposrrr	r5
s










z!HTMLParser.parse_html_declarationrcCs`|j}||
|
d
dks"t
d

|d|
d
}|dkr>dS|rX|||
d
|

|dS)Nr$)z<!z</z"unexpected call to parse_comment()rr%r)rr=r(handle_comment)rr>Zreportrposrrr	rG
s






zHTMLParser.parse_bogus_commentcCsd|j}||
|
d
dks"t
d

t||
d
}|s:dS|}|||
d
|

|}|S)Nr$z<?zunexpected call to parse_pi()r%)rr=picloser+r,	handle_pir9)rr>rr0r@rrr	r4!
s








zHTMLParser.parse_picCs
d|_|
|

}|d
kr|S|j}||
||_g}t||
d}|sPtd

|}|d
|_	}x||k
r.t
||}|sP|ddd\}	}
}|
sd}n\|dddkr|ddksn
|dddkr|ddk
rn
n|dd}|
rt|
}||	|f

|}qnW|||
}|d	k
r|\}
}d
|jk
r|
|jd

}
t|j
|jd

}n|t|j
}|||
|

|S|d

r|||
n"|||
||jk
r||

|S)Nr
rz#unexpected call to parse_starttag()r$rD
'r%
")rz/>

z/>)rcheck_for_whole_start_tagrtagfind_tolerantr0r=r9r7rr
attrfind_tolerantrappendstripZgetposcountr'r)r-endswithhandle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr)rr>endposrattrsr0rAtag
mZattrnamerestZ	attrvaluer9linenooffsetrrr	r1-
sR


















&
*


















zHTMLParser.parse_starttagcCs|j}t
||
}|r|}|||d
}|dkr>|d
S|dkr~|d|rZ|dS|d|rjdS||
krv|S|
d
S|dkrdS|dkrdS||
kr|S|
d
Std	

dS)
Nrr
/z/>r$r%rz6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)rlocatestarttagend_tolerantr0r9r.r=)rr>rr]r@nextrrr	rP`
s.
















z$HTMLParser.check_for_whole_start_tagcCs.
|j}||
|
d
dks"t
d

t||
d}|s:dS|}t||
}|s|jdk	rr|||
|

|St	||
d
}|s||
|
ddkr|
dS|
|

S|d
}|
d|}||

|dS|d
}|jdk	
r||jk
r|||
|

|S||

|
|S)	Nr$z</zunexpected call to parse_endtagrr%rDz</>r)rr=	endendtagr+r9
endtagfindr0rr-rQrGr7rr(
handle_endtagr )rr>rr0rHZ	namematchZtagnamerrrr	r2
s8

























zHTMLParser.parse_endtagcCs||
|
|
|


dS)
N)rXrf)rr\r[rrr	rW
s

zHTMLParser.handle_startendtagc
CsdS)
Nr)rr\r[rrr	rX
s
zHTMLParser.handle_starttagc
CsdS)
Nr)rr\rrr	rf
s
zHTMLParser.handle_endtagc
CsdS)
Nr)rrBrrr	r8
s
zHTMLParser.handle_charrefc
CsdS)
Nr)rrBrrr	r;
s
zHTMLParser.handle_entityrefc
CsdS)
Nr)rrrrr	r-
s
zHTMLParser.handle_datac
CsdS)
Nr)rrrrr	rI
s
zHTMLParser.handle_commentc
CsdS)
Nr)rZdeclrrr	rF
s
zHTMLParser.handle_declc
CsdS)
Nr)rrrrr	rL
s
zHTMLParser.handle_pic
CsdS)
Nr)rrrrr	unknown_decl
s
zHTMLParser.unknown_declcCstj
d
tdd
t|

S)NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.r$)

stacklevel)warningswarnDeprecationWarningr)r
srrr	r
s


zHTMLParser.unescape)
r)__name__
__module____qualname____doc__rYr
rrrrrrr rr5rGr4r1rPr2rWrXrfr8r;r-rIrFrLrgrrrrr	r?s8		z
3"()rprrirZhtmlr__all__rrr<r:r6r/rKZcommentcloserQrRVERBOSErbrdrerrrrrr	<module>
s(