3
sjI @ s d Z ddlZddlZddlZddlmZ dgZejdZejdZ ejdZ
ejdZ ejd Z ejd
Z
ejd Zejd Zejd
ZejdejZejd
ZejdZG 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 comma
)?(?:\s|/(?!>))*
)*
)?
\s* # trailing whitespace
z#</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>c @ s e Zd ZdZd:ZddddZdd Zd
d Zd d
ZdZ dd Z
dd Z dd Z dd Z
dd Zd;ddZd d Zd d Zd d! Zd"d# Zd$d% Zd&d' Zd(d) Zd*d+ Zd,d- Zd.d/ Zd0d1 Zd2d3 Zd4d5 Z d6d7 Z d8d9 Z dS )<r aE Find tags and other markup and call handler functions.
Usage:
p = HTMLParser()
p.feed(data)
...
p.close()
Start tags are handled by calling self.handle_starttag() or
self.handle_startendtag(); end tags by self.handle_endtag(). The
data between tags is passed from the parser to the derived class
by calling self.handle_data() with the data as argument (the data
may be split up in arbitrary chunks). If convert_charrefs is
True the character references are converted automatically to the
corresponding Unicode character (and self.handle_data() is no
longer split in chunks), otherwise they are passed by calling
self.handle_entityref() or self.handle_charref() with the string
containing respectively the named or numeric reference as the
argument.
scriptstyleT)convert_charrefsc C s || _ | j dS )zInitialize and reset this instance.
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
N)r reset)selfr r
/usr/lib64/python3.6/parser.py__init__W s zHTMLParser.__init__c C s: d| _ d| _t| _d| _g | _d| _d| _tj j
| dS )z1Reset this instance. Loses all unprocessed data. z???Nr ) rawdatalasttaginteresting_normal interesting
cdata_elem_pending _pending_len_parse_threshold _markupbase
ParserBaser )r r
r
r r ` s zHTMLParser.resetc C s | j t|7 _ | j | jk r,| jj| n~| jsB| j|7 _n,| jj| | jdj| j7 _| jj d| _ t| j}| jd t| j|k rd| _n t| j| _dS )zFeed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
r
r r N) r lenr r appendr joincleargoahead)r datanr
r
r feedk s
zHTMLParser.feedc C s: | j r,| jdj| j 7 _| j j d| _| jd dS )zHandle any buffered data.r
r r N)r r r r r r )r r
r
r close s
zHTMLParser.closeNc C s | j S )z)Return full source of start tag: '<...>'.)_HTMLParser__starttag_text)r r
r
r get_starttag_text s z HTMLParser.get_starttag_textc C s$ |j | _tjd| 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 sZ | j }d}t|}x||k r| jr|| j r||jd|}|dk r|jdt||d }|dkrvtjdj || rvP |}n(| j
j ||}|r|j }n | jrP |}||k r| jr| j r| j t
||| n| j ||| | j||}||krP |j}|d|rLtj||r&| j|} n|d|r>| j|} nl|d|rV| j|} nT|d|rn| j|} n<|d |r| j|} n$|d
|k r| j d |d
} nP | dk r>|sP |jd |d
} | dk r|jd|d
} | dk r|d
} n| d
7 } | jr,| j r,| j t
||| n| j ||| | j|| }q|d |rtj||}|r|j d
d }
| j|
|j } |d| d
s| d
} | j|| }qn:d||d kr| j |||d
| j||d
}P q|d|rtj||}|rP|jd
}
| j |
|j } |d| d
sB| d
} | j|| }qt j||}|r|r|j ||d kr|j } | |kr|} | j||d
}P n,|d
|k r| j d | j||d
}nP qdst dqW |rH||k rH| j rH| jr*| j r*| j t
||| n| j ||| | j||}||d | _ d S )Nr <&" z[\s;]z</z<!--z<?z<!r r z&# ;zinteresting.search() lied) r r r r findrfindmaxr% r& searchr start handle_datar Z updatepos
startswith starttagopenmatchparse_starttag parse_endtag
parse_commentparse_piparse_html_declarationcharrefgrouphandle_charrefend entityrefhandle_entityref
incompleteAssertionError) r rB r ir jZampposr9 r7 knamer
r
r r s
zHTMLParser.goaheadc C s | j }|||d dks"td|||d dkr@| j|S |||d dkr^| j|S |||d j d kr|jd
|d }|d krd
S | j||d | |d S | j|S d S )Nr. z<!z+unexpected call to parse_html_declaration() z<!-- z<![ z <!doctyper r r0 r0 )r rF r< Zparse_marked_sectionr$ r1 handle_declparse_bogus_comment)r rG r gtposr
r
r r> s
z!HTMLParser.parse_html_declarationr c C s` | j }|||d dks"td|jd|d }|dkr>d S |rX| j||d | |d S )
Nr. <!</z"unexpected call to parse_comment()r r )rQ rR r0 r0 )r rF r1 handle_comment)r rG Zreportr posr
r
r rO 1 s z HTMLParser.parse_bogus_commentc C sd | j }|||d dks"tdtj||d }|s:dS |j }| j||d | |j }|S )Nr. z<?z unexpected call to parse_pi()r r0 )r rF picloser4 r5 handle_pirB )r rG r r9 rH r
r
r r= = s zHTMLParser.parse_pic C s d | _ | j|}|dk r |S | j}||| | _ g }tj||d }|sPtd|j }|jdj | _ }x||k r0t
j||}|sP |jddd\} }
} |
sd } n^| d d d ko| d d kn p| d d d ko| d d kn r| dd
} | rt | } |j | j | f |j }qnW ||| j
} | dkr| j \}
}d
| j kr|
| j jd
}
t| j | j jd
}n|t| j }| j||| |S | jd r| j|| n"| j|| || jkr| j| |S )Nr r z#unexpected call to parse_starttag()r. rL '"r />
r0 r0 r0 )r rY )r" check_for_whole_start_tagr tagfind_tolerantr9 rF rB r@ r$ r attrfind_tolerantr r stripZgetposcountr r2 r6 endswithhandle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr) )r rG endposr attrsr9 rI tagmZattrnamerestZ attrvaluerB linenooffsetr
r
r r: I sR
(*
zHTMLParser.parse_starttagc C s | j }tj||}|r|j }|||d }|dkr>|d S |dkr~|jd|rZ|d S |jd|rjd S ||krv|S |d S |dkrd
S |dkrd S ||kr|S |d S tdd S ) Nr r /z/>r. r
z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!r0 r0 r0 )r locatestarttagend_tolerantr9 rB r7 rF )r rG r rg rH nextr
r
r r[ | s. z$HTMLParser.check_for_whole_start_tagc C s2 | j }|||d dks"tdtj||d }|s:dS |j }tj||}|s| jd k rr| j||| |S t j||d }|s|||d dkr|d S | j
|S |j dj }|j
d|j }| j| |d S |j dj }| jd k r|| jkr| j||| |S | j|j | j |S ) Nr. z</z unexpected call to parse_endtagr rL z</>r r0 )r rF endendtagr4 rB
endtagfindr9 r r6 r\ rO r@ r$ r1
handle_endtagr* )r rG r r9 rP Z namematchZtagnamer( r
r
r r; s8
zHTMLParser.parse_endtagc C s | j || | j| d S )N)rb rp )r rf re r
r
r ra s z HTMLParser.handle_startendtagc C s d S )Nr
)r rf re r
r
r rb s zHTMLParser.handle_starttagc C s d S )Nr
)r rf r
r
r rp s zHTMLParser.handle_endtagc C s d S )Nr
)r rJ r
r
r rA s zHTMLParser.handle_charrefc C s d S )Nr
)r rJ r
r
r rD s zHTMLParser.handle_entityrefc C s d S )Nr
)r r r
r
r r6 s zHTMLParser.handle_datac C s d S )Nr
)r r r
r
r rS s zHTMLParser.handle_commentc C s d S )Nr
)r Zdeclr
r
r rN s zHTMLParser.handle_declc C s d S )Nr
)r r r
r
r rV s zHTMLParser.handle_pic C s d S )Nr
)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 r )r ) __name__
__module__ __qualname____doc__rc r r r r! r" r# r) r* r r> rO r= r: r[ r; ra rb rp rA rD r6 rS rN rV rq r r
r
r
r r ? s8 z
3"()rz r% rs r Zhtmlr __all__r& r rE rC r? r8 rU Z commentcloser\ r] VERBOSErl rn ro r r r
r
r
r <module> s(