/snap/core22/2437/usr/lib/python3.10/html/__pycache__
Edit: /snap/core22/2437/usr/lib/python3.10/html/__pycache__/parser.cpython-310.pyc (11151B)
o
p̦iG @ s d Z ddlZddlZddlmZ dgZedZedZedZ edZ
ed Z ed
Z ed Z
ed Zed
ZedZedejZed 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
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#c @ s e Zd ZdZdZddddZdd Zd d
Zd d Zd
Z dd Z
dd Z dd Z dd Z
dd Zd7ddZdd 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 d
S )8r 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.
)scriptstyleT)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/lib/python3.10/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 )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 s | j }d}t|}||k rU| jr;| js;|d|}|dk r:|dt||d }|dkr8td ||s8n |}n| j
||}|rI| }n| jrNn|}||k ro| jrf| jsf| t
||| n | ||| | ||}||kr{n|j}|d|rt||r| |} n@|d|r| |} n5|d|r| |} n*|d|r| |} n |d |r| |} n|d
|k s|r| d |d
} nn| dk r|sِn|t||rn|d|r|d |kr| d nt||rn| ||d d n~|d|r0|}d D ]}
||
|d
r"|t|
8 } nq| ||d
| nS|d|rB| ||d d nA|||d dkr[| ||d d n(|d |rm| ||d d n|d|r| ||d d nt d|} | || }n|d|rt ||}|r| d d } | !| |" } |d| d
s| d
} | || }q d||d v r| |||d | ||d }ny|d|rMt#||}|r | d
} | $| |" } |d| d
s| d
} | || }q t%||}|r7|r6| ||d kr6|" } | |kr.|} | ||d
}n |d
|k rL| d | ||d
}nnJ d||k s|r||k r| js| jru| jsu| t
||| n | ||| | ||}||d | _ d S )Nr <&" z[\s;] ksuffixnamer
r
r r s
} zHTMLParser.goaheadc C s | j }|||d dksJ d|||d dkr | |S |||d dkr/| |S |||d d krX|d
|d }|d krId S | ||d | |d S | |S )
Nr- r, z+unexpected call to parse_html_declaration()r/ r* r0 z
rc )r check_for_whole_start_tagr tagfind_tolerantr@ rP rN r r attrfind_tolerantr appendstripgetposcountr6 r8 r< rH handle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr# )r rT endposr attrsr@ rX tagmattrnamerest attrvaluerP linenooffsetr
r
r rA ? sX
&(
zHTMLParser.parse_starttagc C s | j }t||}|rU| }|||d }|dkr |d S |dkr?|d|r-|d S |d|r5dS ||kr;|S |d S |dkrEdS |dv rKdS ||krQ|S |d S td )
Nr r /rc r- r4 r
z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZr3 )r locatestarttagend_tolerantr@ rP r> rL )r rT r rr rV nextr
r
r re r s. z$HTMLParser.check_for_whole_start_tagc C s* | j }|||d dksJ dt||d }|s dS | }t||}|sn| jd ur9| ||| |S t||d }|sV|||d dkrQ|d S | |S |
d }| d| }|
| |d S |
d }| jd ur|| jkr| ||| |S |
| | |S ) Nr- r) z unexpected call to parse_endtagr r4 r0 zr )r endendtagr: rP
endtagfindr@ r r< rf r\ rN r r7
handle_endtagr% )r rT r r@ r] namematchtagnamer" r
r
r rB s8
zHTMLParser.parse_endtagc C s | || | | d S r$ )rm r} r rq rp r
r
r rl s z HTMLParser.handle_startendtagc C d S r$ r
r r
r
r rm zHTMLParser.handle_starttagc C r r$ r
)r rq r
r
r r} r zHTMLParser.handle_endtagc C r r$ r
r rZ r
r
r rO r zHTMLParser.handle_charrefc C r r$ r
r r
r
r rR r zHTMLParser.handle_entityrefc C r r$ r
r r
r
r r< r zHTMLParser.handle_datac C r r$ r
r r
r
r rG r zHTMLParser.handle_commentc C r r$ r
)r declr
r
r rJ r zHTMLParser.handle_declc C r r$ r
r r
r
r rK r zHTMLParser.handle_pic C r r$ r
r r
r
r rI r zHTMLParser.unknown_decl)r ) __name__
__module__ __qualname____doc__rn r r r r r r r# r% r rE r\ rD rA re rB rl rm r} rO rR r< rG rJ rK rI r
r
r
r r ? s:
3"( )r r r htmlr __all__r r rS rQ rM r? rF r` commentcloserf rg VERBOSEry r{ r| r r r
r
r
r
s.