/opt/alt/python311/lib64/python3.11/html/__pycache__
Edit: /opt/alt/python311/lib64/python3.11/html/__pycache__/parser.cpython-311.opt-1.pyc (24193B)
CM@ V d Z ddlZddlZddlmZ dgZ ej d Z ej d Z ej d Z ej d Z
ej d Z ej d
Z ej d Z
ej d Z ej d
Z ej d Z ej dej Z ej dej Z ej dej Z ej d Z ej d Z G d dej ZdS )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
z--!?>z-?>z0([a-zA-Z][^\t\n\r\f />]*)(?:[\t\n\r\f ]|/(?!>))*a{
(
(?<=['"\t\n\r\f /])[^\t\n\r\f />][^\t\n\r\f /=>]* # attribute name
)
([\t\n\r\f ]*=[\t\n\r\f ]* # value indicator
('[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\t\n\r\f ]* # bare value
)
)?
(?:[\t\n\r\f ]|/(?!>))* # possibly followed by a space
a
[a-zA-Z][^\t\n\r\f />]* # tag name
[\t\n\r\f /]* # optional whitespace before attribute name
(?:(?<=['"\t\n\r\f /])[^\t\n\r\f />][^\t\n\r\f /=>]* # attribute name
(?:[\t\n\r\f ]*=[\t\n\r\f ]* # value indicator
(?:'[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\t\n\r\f ]* # bare value
)
)?
[\t\n\r\f /]* # possibly followed by a space
)*
>?
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#c e Zd ZdZdZdZddddZd Zd Zd
Z d Z
d Z dd
dZ d Z
d$dZd Zd Zd$dZd%dZd Zd Zd Zd Zd Zd Zd Zd Zd Zd Z d Z d! Z d" Z d# 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.
)scriptstylexmpiframenoembednoframes)textareatitleTF)convert_charrefs scriptingc J || _ || _ | dS )az Initialize and reset this instance.
If convert_charrefs is true (the default), all character references
are automatically converted to the corresponding Unicode characters.
If *scripting* is false (the default), the content of the
``noscript`` element is parsed normally; if it's true,
it's returned as is without being parsed.
N)r r reset)selfr r s 2/opt/alt/python311/lib64/python3.11/html/parser.py__init__zHTMLParser.__init__v s$ !1 "
c d| _ d| _ t | _ d| _ d| _ d| _ g | _ d| _ d| _ t j | dS )z1Reset this instance. Loses all unprocessed data. z???NTr )
rawdatalasttaginteresting_normal interesting
cdata_elem_support_cdata
_escapable_pending _pending_len_parse_threshold _markupbase
ParserBaser r s r r zHTMLParser.reset sb - "
! $$T*****r c R | xj t | z
c_ | j | j k r | j | dS | j s| xj |z
c_ n[| j | | xj d | j z
c_ | j d| _ t | j }| d t | j |k r d| _ dS t | j | _ dS )zFeed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
r r r N) r" lenr# r! appendr joincleargoahead)r datans r feedzHTMLParser.feed s
SYY& t 4 4 4 M & & & & &=
& $
$$T***
6 66
##%%% !D DL!!A LLOOO4< 1$$()%%% ),DL(9(9%%%r c | j rH| xj d | j z
c_ | j d| _ | d dS )zHandle any buffered data.r r r N)r! r r* r+ r" r, r& s r closezHTMLParser.close sY = " LLBGGDM 2 2 2LL M ! ! ! !D Qr Nc | j S )z)Return full source of start tag: '<...>'.)_HTMLParser__starttag_textr& s r get_starttag_textz HTMLParser.get_starttag_text s ##r escapablec | | _ || _ | j dk rt j d | _ d S |rB| j s;t j d| j z t j t j z | _ d S t j d| j z t j t j z | _ d S )N plaintextz\Zz&|])z])) lowerr r recompiler r
IGNORECASEASCII)r elemr6 s r set_cdata_modezHTMLParser.set_cdata_mode s **,,# ?k ) ) !z% 0 0D
Bt 4 B !z*Dt*V*,-*@ B BD "z*BT_*T*,-*@ B BD r c : t | _ d | _ d| _ d S )NT)r r r r r& s r clear_cdata_modezHTMLParser.clear_cdata_mode s - r c || _ dS )a Enable or disable support of the CDATA sections.
If enabled, "<[CDATA[" starts a CDATA section which ends with "]]>".
If disabled, "<[CDATA[" starts a bogus comments which ends with ">".
This method is not called by default. Its purpose is to be called
in custom handle_starttag() and handle_endtag() methods, with
value that depends on the adjusted current node.
See https://html.spec.whatwg.org/multipage/parsing.html#markup-declaration-open-state
for details.
N)r )r flags r _set_support_cdataz HTMLParser._set_support_cdata s #r c
| j }d}t | }||k rI| j r}| j sv| d| }|dk rY| dt
||dz
}|dk r*t j d || sn|}n=| j
|| }|r| }n | j rn|}||k rV| j r2| j r+|
t ||| n |
||| | || }||k rn|j } |d| rt" || r| | } n |d| r| | } n |d| r| | } nl |d| r| | } nJ |d | r| | } n(|d
z |k s|r|
d |d
z } nn| dk r|snt" || rn |d| r_|d z |k r|
d nt0 || rnd| ||d z d nB |d| rU|}d D ]/}
| |
|d
z r|t |
z } n0| ||d
z | n |d| r(| j r!| ||dz d n|||dz dk r!| ||d z d ni |d | r!| ||d z d n< |d| r!| ||d z d ntA d |} | || }n# |d| rtB || }|rq|" d d } | # | |$ } |d| d
z
s| d
z
} | || }d||d v r9|
|||d z | ||d z }nI |d| r5tJ || }|rj|" d
} | & | |$ } |d| d
z
s| d
z
} | || }tN || }|rX|rU|" ||d k r5|$ } | |k r|} | ||d
z }n@|d
z |k r/|
d | ||d
z }nn||k I|rr||k rl| j r2| j r+|
t ||| n |
||| | || }||d | _ d S )Nr <&" z [\t\n\r\f ;]z >w O O $ A (//;;
AA A1uu( 3T_ 3$$Xgacl%;%;<<<<$$WQqS\222q!$$AAvvu +Jz#q!! \
6 %%gq11 ++A..AA Za(( ))!,,AA Z**
**1--AA Za((
a((AA Za(( 33A66AA!eq[[C[$$S)))AAAq55 #))'155 H #D!,, H q5A:: , ,T 2 2 2 2 ' - -gq 9 9 ? ! / /!
> > > >#FA.. H &8 & &F & / /! < < & !S[[ 0 % & ++GAaCEN;;;;#K33
H8K
H ))'!A#$$-8888 1Q3 --//;>> ((1 7777#D!,, H ++GAaCDDM::::#D!,, H wqstt}5555 ,-F G GGANN1a((D!$$ +
6
gq11 ;;==2.D''--- A%:c1Q3// " E q!,,A gabbk)) ((1Q3 888 NN1ac 2 2C##
6!33 ;;q>>D))$/// A%:c1Q3// " E q!,,A "((!44 5u{{}} ; ; !IIKK 66 !A NN1a!e 4 4!eq[[ $$S))) q!a%00AAs !eez %1q55$
/
/ '!A#,!7!78888 1 ...q!$$A qrr{ r c ( | j }|||dz dk r| | S |||dz dk rM| j rF| d|dz }|dk rdS | ||dz | |dz S |||dz d k rF| d
|dz }|dk rdS | ||d z | |d z S |||dz d
k ry| d
|dz }|dk rdS ||d z
dk r$| ||dz |d z
n | ||d z | |d z S | | S )NrL rI rO rM z]]>r rQ rN rP r rJ r zV # #%%a(( (
QqsU^{
*
*t/B
* UAaC((A1uur gac1fo . . .q5L
QqsU^
!
!
#
#{
2
2LLac**E{{r WQqSY / 0 0 07N
QqsU^u
$
$ S!A#&&A1uurqs|s""!!'!A#qs("34444##GAaCFO444q5L++A.. .r c ( | j }t ||dz }|s"t ||dz }|sdS |r4| }| ||dz | | S )NrL rQ )r commentcloserV commentabruptcloser\ rW rc rl )r rp reportr r\ rq s r r_ zHTMLParser.parse_comment s , ##GQqS11 &,,Wac::E
r 1
A !Q 0 0 0yy{{r r c | j }| d|dz }|dk rdS |r | ||dz | |dz S )Nr rJ rQ r )r rS rc )r rp r} r poss r rx z HTMLParser.parse_bogus_comment sb , ll3!$$ "992 2 !C 0 1 1 1Qwr c | j }t ||dz }|sdS | }| ||dz | | }|S )NrJ rQ )r picloserV rW rg rl r rp r r\ rq s r r` zHTMLParser.parse_pi sj ,w!,, 2 KKMM wqsAv''' IIKKr c d | _ | | }|dk r|S | j }||| | _ g }t ||dz }| }| d x| _ }||k rt || }|sn| ddd \ } }
} |
sd } nI| d d dcxk r| dd k s"n | d d dcxk r| dd k r
n n
| dd } | rt | } | | | f | }||k ||| } | dvr |
||| |S | d r| || nj| || || j v s| j r|d
k s|d k r| |d
n || j v r| |d
|S )Nr r rJ rN 'rQ ")r />r noscriptr8 Fr5 T)r3 check_for_whole_start_tagr tagfind_tolerantr\ rl rj r9 r attrfind_tolerantr r) striprX rd handle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr r? RCDATA_CONTENT_ELEMENTS)
r rp endposr attrsr\ rs tagmattrnamerest attrvaluerl s
r r] zHTMLParser.parse_starttag s $ //22 A::M, &qx 0 &&w!44 IIKK "[[^^ 1 1 3 33 s&jj!''33A
()1a(8(8 %HdI
, 2A2 $8888)BCC.88882A2 #7777233 77777 %adO
0 $Y / / LL(..**I6 7 7 7A &jj ah %%'' k ! ! WQvX . / / /M <<
9 # #C / / / / e , , ,t222 3$':$5$5{""##C5#9999444##C4#888
r c | j }t ||dz }| }||dz
dk rdS |S )Nr r rQ )r locatetagendr\ rl r s r r z$HTMLParser.check_for_whole_start_tag sL , ""7AaC00 IIKK 1Q3<3 2r c F | j }| d|dz dk rdS t || s.||dz |dz dk r|dz S | | S t
||dz }| }||dz
dk rdS t ||dz }| d }|
| | |S )Nr rJ r rQ rN r ) r rS rb r\ rx r rl r rj r9
handle_endtagrA )r rp r r\ rq r s r r^ zHTMLParser.parse_endtag s , <<QqS ! !A % %2 ++ 3qs1Q3w 3&&s
//222 ""7AaC00 IIKK 1Q3<3 2 !&&w!44kk!nn""$$ 3 r c \ | || | | d S N)r r r r r s r r z HTMLParser.handle_startendtag
s2 S%((( 3 r c d S r r s r r zHTMLParser.handle_starttag r c d S r r )r r s r r zHTMLParser.handle_endtag r r c d S r r r ru s r rk zHTMLParser.handle_charref r r c d S r r r s r rn zHTMLParser.handle_entityref r r c d S r r r r- s r rX zHTMLParser.handle_data" r r c d S r r r s r rc zHTMLParser.handle_comment& r r c d S r r )r decls r rf zHTMLParser.handle_decl* r r c d S r r r s r rg zHTMLParser.handle_pi. r r c d S r r r s r re zHTMLParser.unknown_decl1 r r )T)r )!__name__
__module__ __qualname____doc__r r r r r/ r1 r3 r4 r? rA rD r, ra r_ rx r` r] r r^ r r r rk rn rX rc rf rg re r r r r r Z s 0 Y 3+/5 + + + : : :< O$ $ $ 16
B
B
B
B
B
# # # # G# G# G#X / / /D . . .d <
r )r r: r$ htmlr __all__r; r ro rm ri r[ rb r r{ r| r VERBOSEr r locatestarttagend_tolerant endendtag
endtagfindr% r r r r
r s " "
. RZ''
RZ
%
%
BJ> ? ?
"*@
A
Arz+&&
RZ
%
%
"*S//rz(## RZ'' 2: QRR BJ Z rz
Z
(RZ ) Z
BJsOO
RZ>
?
?
X
X
X
X
X
' X
X
X
X
X
r