File "parser.cpython-38.pyc"
Full Path: /home/attunedd/public_html/byp/izo/con7ext_sym404/rintoar.txt/lib64/python3.8/html/__pycache__/parser.cpython-38.pyc
File size: 10.94 KB
MIME-type: text/x-bytecode.python
Charset: 8 bit
U
e5d9E @ s d Z ddlZddlZddlZddlmZ dgZedZedZ edZ
edZ ed Z ed
Z
ed Zed Zed
ZedejZed
ZedZG dd dejZdS )z A 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 space
)?(?:\s|/(?!>))*
)*
)?
\s* # trailing whitespace
z#</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>c @ s e Zd ZdZdZddddZdd Zd d
Zd d Zd
Z dd Z
dd Z dd Z dd Z
dd Zd9ddZdd Zd d Zd d Zd!d" Zd#d$ Zd%d& Zd'd( Zd)d* Zd+d, Zd-d. Zd/d0 Zd1d2 Zd3d4 Z d5d6 Z d7d8 Z d
S ):r aE Find 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 C s || _ | dS )zInitialize and reset this instance.
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
N)r reset)selfr r #/usr/lib64/python3.8/html/parser.py__init__W s zHTMLParser.__init__c C s( d| _ d| _t| _d| _tj| dS )z1Reset this instance. Loses all unprocessed data. z???N)rawdatalasttaginteresting_normal interesting
cdata_elem _markupbase
ParserBaser r r r r r ` s
zHTMLParser.resetc C s | 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 goaheadr datar r r feedh s zHTMLParser.feedc C s | d dS )zHandle any buffered data. N)r r r r r closeq s zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)_HTMLParser__starttag_textr r r r get_starttag_textw s z HTMLParser.get_starttag_textc C s$ | | _td| j tj| _d S )Nz </\s*%s\s*>)lowerr recompileIr )r elemr r r set_cdata_mode{ s
zHTMLParser.set_cdata_modec C s t | _d | _d S N)r r r r r r r clear_cdata_mode s zHTMLParser.clear_cdata_modec C sX | j }d}t|}||k r| jrv| jsv|d|}|dk r|dt||d }|dkrptd ||spq|}n*| j
||}|r| }n| jrq|}||k r| jr| js| t
||| n| ||| | ||}||krq|j}|d|rJt||r"| |} n|d|r:| |} nn|d|rR| |} nV|d|rj| |} n>|d |r| |} n&|d
|k r| d |d
} nq| dk r<|sq|d |d
} | dk r|d|d
} | dk r|d
} n| d
7 } | jr*| js*| t
||| n| ||| | || }q|d |rt||}|r| d
d }
| |
| } |d| d
s| d
} | || }qn<d||d kr| |||d
| ||d
}qq|d|rt||}|rP|d
}
| |
| } |d| d
sB| d
} | || }qt ||}|r|r| ||d kr| } | |kr|} | ||d
}qn.|d
|k r| d | ||d
}nqqdst dq|rF||k rF| jsF| jr(| js(| t
||| n| ||| | ||}||d | _ d S )Nr <&" z[\s;]</<!--<?<!r r z&# ;zinteresting.search() lied) r lenr r findrfindmaxr r searchr start handle_datar Z updatepos
startswith starttagopenmatchparse_starttag parse_endtag
parse_commentparse_piparse_html_declarationcharrefgrouphandle_charrefend entityrefhandle_entityref
incompleteAssertionError) r r@ r injZampposr7 r5 knamer r r r s
zHTMLParser.goaheadc C s | j }|||d dks"td|||d dkr@| |S |||d dkr^| |S |||d d kr|d
|d }|d krd S | ||d | |d S | |S d S )
Nr+ r* z+unexpected call to parse_html_declaration() r( z<![ z <!doctyper r, r )r rD r: Zparse_marked_sectionr r/ handle_declparse_bogus_comment)r rE r gtposr r r r< s
z!HTMLParser.parse_html_declarationr c C s` | j }|||d dks"td|d|d }|dkr>dS |rX| ||d | |d S )Nr+ )r* r' z"unexpected call to parse_comment()r r, r )r rD r/ handle_comment)r rE Zreportr posr r r rN s z HTMLParser.parse_bogus_commentc C sd | j }|||d dks"tdt||d }|s:dS | }| ||d | | }|S )Nr+ r) z unexpected call to parse_pi()r, )r rD picloser2 r3 handle_pir@ )r rE r r7 rG r r r r; ! s zHTMLParser.parse_pic C s d | _ | |}|dk r |S | j}||| | _ g }t||d }|sPtd| }|d | _ }||k r.t
||}|sq.|ddd\} }
} |
sd } n\| d d d kr| dd ksn | d d d kr| dd krn n | dd } | rt | } | | | f | }ql|||
} | d kr| \}
}d
| j kr|
| j d
}
t| j | j d
}n|t| j }| ||| |S | d r| || n"| || || jkr| | |S ) Nr r z#unexpected call to parse_starttag()r+ rK 'r, ")r />
rV )r check_for_whole_start_tagr tagfind_tolerantr7 rD r@ r> r r
attrfind_tolerantr appendstripZgetposcountr. r0 r4 endswithhandle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr! )r rE endposr attrsr7 rH tagmattrnamerestZ attrvaluer@ linenooffsetr r r r8 - s\
&
zHTMLParser.parse_starttagc C s | j }t||}|r| }|||d }|dkr>|d S |dkr~|d|rZ|d S |d|rjdS ||krv|S |d S |dkrdS |dkrdS ||kr|S |d S td d S )
Nr r /rV r+ r, r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r locatestarttagend_tolerantr7 r@ r5 rD )r rE r re rG nextr r r rX ` s. z$HTMLParser.check_for_whole_start_tagc C s. | j }|||d dks"tdt||d }|s:dS | }t||}|s| jd k rr| ||| |S t ||d }|s|||d dkr|d S |
|S | d }|
d| }| | |d S | d }| jd k r|| jkr| ||| |S | | | |S ) Nr+ r' z unexpected call to parse_endtagr r, rK z</>r )r rD endendtagr2 r@
endtagfindr7 r r4 rY rN r> r r/
handle_endtagr# )r rE r r7 rO Z namematchZtagnamer r r r r9 s8
zHTMLParser.parse_endtagc C s | || | | d S r" )r` ro r rd rc r r r r_ s z HTMLParser.handle_startendtagc C s d S r" r rp r r r r` s zHTMLParser.handle_starttagc C s d S r" r )r rd r r r ro s zHTMLParser.handle_endtagc C s d S r" r r rI r r r r? s zHTMLParser.handle_charrefc C s d S r" r rq r r r rB s zHTMLParser.handle_entityrefc C s d S r" r r r r r r4 s zHTMLParser.handle_datac C s d S r" r r r r r rP s zHTMLParser.handle_commentc C s d S r" r )r Zdeclr r r rM s zHTMLParser.handle_declc C s d S r" r r r r r rS s zHTMLParser.handle_pic C s d S r" r r r r r unknown_decl s zHTMLParser.unknown_declc C s t jdtdd t|S )NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.r+ )
stacklevel)warningswarnDeprecationWarningr )r sr r r r s
zHTMLParser.unescape)r ) __name__
__module__ __qualname____doc__ra r
r r r r r r! r# r r< rN r; r8 rX r9 r_ r` ro r? rB r4 rP rM rS rr r r r r r r ? s8 z
3"()r{ r rt r Zhtmlr __all__r r rC rA r= r6 rR Z commentcloserY rZ VERBOSErk rm rn r r r r r r <module> s,