Wj 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. Zy)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 ZdZdZdZddd fd
Z fdZd 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 xZ!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 ^ t | || _ || _ | j y)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)super__init__r r reset)selfr r __class__s $/usr/lib64/python3.12/html/parser.pyr zHTMLParser.__init__v s( 0 "
c d| _ d| _ t | _ d| _ d| _ d| _ g | _ d| _ d| _ t | - y)z1Reset this instance. Loses all unprocessed data. z???NTr ) rawdatalasttaginteresting_normal interesting
cdata_elem_support_cdata
_escapable_pending _pending_len_parse_thresholdr r )r r s r r zHTMLParser.reset sO - "
!
r c | xj t | z
c_ | j | j k r | j j | y| j s| xj
|z
c_ nc| j j | | xj
dj
| j z
c_ | j j d| _ t | j
}| j d t | j
|k rd| _ yt | j
| _ y)zFeed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
r r r N) r$ lenr% r# appendr joincleargoahead)r datans r feedzHTMLParser.feed s
SY& t 4 4 4 MM &== $
$$T*
66
##% !D DLL!A LLO4<< 1$()% ),DLL(9%r c | j rO| xj dj | j z
c_ | j j d| _ | j d y)zHandle any buffered data.r r r N)r# r r) r* r$ r+ r s r closezHTMLParser.close sG == LLBGGDMM 2 2L MM ! !D Qr Nc | j S )z)Return full source of start tag: '<...>'.)_HTMLParser__starttag_textr0 s r get_starttag_textz HTMLParser.get_starttag_text s ###r escapablec |j | _ || _ | j dk( rt j d | _ y |rT| j sHt j d| j z t j t j z | _ y t j d| j z t j t j z | _ y )N plaintextz\Zz&|])z])) lowerr r" recompiler r
IGNORECASEASCII)r elemr6 s r set_cdata_modezHTMLParser.set_cdata_mode s **,# ??k ) !zz% 0D
t 4 4 !zz*Dt*V*,--*@ BD "zz*BT__*T*,--*@ BD r c 6 t | _ d | _ d| _ y )NT)r r r r" r0 s r clear_cdata_modezHTMLParser.clear_cdata_mode s - r c || _ y)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 r9| j rq| j se|j d| }|dk r|j dt
||dz
}|dk\ r't j d j || sn|}n?| j j || }|r|j }n| j rn|}||k rJ| j r*| j r | j t ||| n| j ||| | j || }||k( rn|j } |d| r=t" j% || r| j' | } n |d| r| j) | } nt |d| r| j+ | } nY |d| r| j- | } n> |d | r| j/ | } n#|d
z |k s|r| j d |d
z } nnH| dk rl|sn>t" j% || rnN |d| rK|d z |k( r| j d n*t0 j% || rn| j3 ||d z d n |d| rF|}d D ]' }
|j5 |
|d
z s|t |
z } n | j3 ||d
z | n |d| r$| j6 r| j9 ||dz d n~|||dz j; dk( r| j= ||d z d nM |d | r| j3 ||d z d n, |d| r| j? ||d z d n tA d |} | j || }n |d| rtB j% || }|rY|jE d d } | jG | |jI } |d| d
z
s| d
z
} | j || }d||d v r,| j |||d z | j ||d z }n |d| rtJ j% || }|rW|jE d
} | jM | |jI } |d| d
z
s| d
z
} | j || }tN j% || }|rE|rB|jE ||d k( r,|jI } | |k r|} | j ||d
z }n>|d
z |k r'| j d | j ||d
z }nnJ d ||k r9|ra||k r\| j r*| j r | j t ||| n| j ||| | j || }||d | _ y )Nr <&" z [\t\n\r\f ;] >w O A ((//;
A A1u((T__$$Xgal%;<$$WQq\2q!$AAvu ++J#q! %%gq1 ++A.A a( ))!,A * **1-A a(
a(A a( 33A6A!eq[C$$S)AAq5 #))'15 #D!, q5A: , ,T 2 ' - -gq 9 ! / /!
>#FA. &8F & / /! < !S[ 0 % '9 ++GAaCN;#K38K8K ))'!A#$-8 1Q3 --/;> ((1 7#D!, ++GAaCDM:#D!, wqst}5 ,-F GGANN1a(D!$
gq1 ;;=2.D''- A%c1Q3/ E q!,A gabk) ((1Q3 8 NN1ac 2C#!3 ;;q>D))$/ A%c1Q3/ E q!,A "((!4u{{} ; !IIK 6 !A NN1a!e 4!eq[ $$S) q!a%0A555qw !ez 1q5$$ '!A,!78 1 .q!$A qr{ r c | j }|||dz dk( sJ d |||dz dk( r| j | S |||dz dk( rC| j r7|j d|dz }|d k ry
| j ||d z | |d z S |||dz j d k( r7|j d
|dz }|d
k( ry
| j
||dz | |dz S |||d z dk( ra|j d
|d z }|d k ry
||dz
dk( r | j ||d z |dz
|dz S | j ||dz | |dz S | j | S )NrM rL z+unexpected call to parse_html_declaration()rO rJ rR rP z]]>r rT rQ rS r r zV #%%a( (
Qqs^{
*t/B/B UAaC(A1u gac1o .q5L
Qqs^
!
!
#{
2LLac*E{ WQqS / 07N
Qqs^u
$ S!A#&A1uqs|s"!!'!A#qs"34 q5L ##GAaCO4q5L++A. .r c , | j }|j d| sJ d t j ||dz }|s t j ||dz }|sy|r'|j
}| j ||dz | |j S )NrJ "unexpected call to parse_comment()rO rT ) r r] commentcloserY commentabruptcloser_ rZ rf ro )r rs reportr r_ rt s r rb zHTMLParser.parse_comment s ,,!!&!,R.RR, ##GQqS1&,,Wac:E
A !Q 0yy{r c | j }|||dz dv sJ d |j d|dz }|dk( ry|r| j ||dz | |dz S )NrM )rL rI r~ r rT r )r rV rf )r rs r r poss r r{ z HTMLParser.parse_bogus_comment su ,,q1~ - C 1B C-ll3!$ "9 !C 0 1Qwr c | j }|||dz dk( sJ d t j ||dz }|sy|j }| j ||dz | |j }|S )NrM rK z unexpected call to parse_pi()rT )r picloserY rZ rj ro r rs r r_ rt s r rc zHTMLParser.parse_pi st ,,q1~%F'FF%w!, KKM wqsA' IIKr c d | _ | j | }|dk r|S | j }||| | _ g }t j ||dz }|sJ d |j }|j
d j x| _ }||k rt j || }|sn|j
ddd \ } }
} |
sd } n,| d d dcxk( r| dd k( sn | d d dcxk( r| dd k( rn n| dd } | r t | } |j | j | f |j }||k r||| j } | d vr| j ||| |S | j d
r| j || |S | j! || || j" v s| j$ r|d k( s|d k( r| j' |d
|S || j( v r| j' |d |S )Nr r z#unexpected call to parse_starttag()rM rQ 'rT ")r />r noscriptr8 Fr5 T)r3 check_for_whole_start_tagr tagfind_tolerantr_ ro rm r9 r attrfind_tolerantr r( stripr[ rg handle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr r? RCDATA_CONTENT_ELEMENTS)
r rs endposr attrsr_ rv tagmattrnamerest attrvaluero s
r r` zHTMLParser.parse_starttag s $ //2 A:M,, &q 0 &&w!4;;;u IIK "[[^ 1 1 33 s&j!''3A()1a(8 %HdI 2A $8)BC.82A #723 7 %aO $Y / LL(..*I6 7A &j a %%' k ! WQv . /M << # #C /
e ,t222 C:$5{"##C5#9
444##C4#8
r c | j }t j ||dz }|sJ |j }||dz
dk7 ry|S )Nr r rT )r locatetagendr_ ro r s r r z$HTMLParser.check_for_whole_start_tag sK ,, ""7AaC0 u IIK 1Q3<3 r c | j }|||dz dk( sJ d |j d|dz dk ryt j || s$||dz |dz dk( r|dz S | j | S t
j ||dz }|sJ |j
}||dz
dk7 ryt j ||dz }|sJ |j d j }| j | | j |S ) NrM rI z unexpected call to parse_endtagr r rT rQ r ) r rV re r_ r{ r ro r rm r9
handle_endtagrA )r rs r r_ rt r s r ra zHTMLParser.parse_endtag s ,,q1~%H'HH% <<QqS !A % +qs1Q3 3&s
//22 ""7AaC0 u IIK 1Q3<3 !&&w!4 ukk!n""$ 3 r c J | j || | j | y N)r r r r r s r r z HTMLParser.handle_startendtag s S%( 3 r c y r r s r r zHTMLParser.handle_starttag r c y r r )r r s r r zHTMLParser.handle_endtag r r c y r r r rx s r rn zHTMLParser.handle_charref r r c y r r r s r rq zHTMLParser.handle_entityref r r c y r r r r, s r r[ zHTMLParser.handle_data# r r c y r r r s r rf zHTMLParser.handle_comment' r r c y r r )r decls r ri zHTMLParser.handle_decl+ r r c y r r r s r rj zHTMLParser.handle_pi/ r r c y r r r s r rh zHTMLParser.unknown_decl2 r r )T)r )"__name__
__module__ __qualname____doc__r r r r r. r1 r3 r4 r? rA rD r+ rd rb r{ rc r` r ra r r r rn rq r[ rf ri rj rh
__classcell__)r s @r r r Z s 0 Y 3+/5
:< O$ 16
B
# G#X /D .d<
r )r r: _markupbasehtmlr __all__r; r rr rp rl r^ re r r r r VERBOSEr r locatestarttagend_tolerant endendtag
endtagfind
ParserBaser r r r r s[ "
. RZZ'
RZZ
%
BJJ> ?
"**@
Arzz+&
RZZ
%
"**S/rzz(# RZZ' 2:: QR BJJ ZZ rzz
ZZ
(RZZ ) ZZ
BJJsO
RZZ>
?
Y
'' Y
r