Yf?E @ s d Z d d l Z d d l Z d d l Z d d l m Z d g Z e j d Z e j d Z e j d Z
e j d Z e j d Z e j d
Z
e j d Z e j d Z e j d
Z e j d e j Z e j d
Z e j d Z Gd d d e j Z d S)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$([a-zA-Z][^
/> ]*)(?:\s|/(?!>))*z]((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*aF
<[a-zA-Z][^\t\n\r\f />\x00]* # tag name
(?:[\s/]* # optional whitespace before attribute name
(?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name
(?:\s*=+\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\s]* # bare value
)
(?:\s*,)* # possibly followed by a comma
)?(?:\s|/(?!>))*
)*
)?
\s* # trailing whitespace
z#c @ sW e Z d Z d Z d: Z d d d d Z d d Z d
d Z d d
Z d Z d d Z
d d Z d d Z d d Z
d d Z d d d Z d d Z d d Z d d! Z d" d# Z d$ d% Z d& d' Z d( d) Z d* d+ Z d, d- Z d. d/ Z d0 d1 Z d2 d3 Z d4 d5 Z d6 d7 Z d8 d9 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.
scriptstyleconvert_charrefsTc C s | | _ | j d S)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
0/opt/alt/python35/lib64/python3.5/html/parser.py__init__W s zHTMLParser.__init__c C s8 d | _ d | _ t | _ d | _ t j j | d S)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 | | _ | j d d S)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 goahead)r datar
r
r feedh s zHTMLParser.feedc C s | j d d S)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_text)r r
r
r get_starttag_textw s z HTMLParser.get_starttag_textc C s2 | j | _ t j d | j t j | _ 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 | } x| | k r+| j r | j r | j d | } | d k r | j d t | | d } | d k r t j d j | | r P| } n: | j
j | | } | r | j } n | j r P| } | | k r<| j r%| j r%| j t
| | | n | j | | | | j | | } | | k r[P| j } | d | rt j | | r| j | } n | d | r| j | } n | d | r| j | } nm | d | r| j | } nL | d | r| j | } n+ | d
| k rE| j d | d
} n P| d k r| sYP| j d | d
} | d k r| j d | d
} | d k r| d
} n
| d
7} | j r| j r| j t
| | | n | j | | | | j | | } q | d | rt j | | } | r| j d
d }
| j |
| j } | d | d
s| d
} | j | | } q q(d | | d k r| j | | | d
| j | | d
} Pq | d | rt j | | } | rj| j d
}
| j |
| j } | d | d
sU| d
} | j | | } q t j | | } | r| r| j | | d k r| j } | | k r| } | j | | d
} Pq(| d
| k r| j d | j | | d
} q(Pq d s t d q W| r| | k r| j r| j r{| j r{| j t
| | | n | j | | | | j | | } | | d | _ d S)Nr <&" z[\s;]z
r( r( r( )r rS )r check_for_whole_start_tagr tagfind_tolerantr2 r? r; r9 r r attrfind_tolerantr appendstripZgetposcountr) r+ r/ endswithhandle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr! )r r@ endposr attrsr2 rC tagmZattrnamerestZ attrvaluer; linenooffsetr
r
r r3 - sR 00
zHTMLParser.parse_starttagc C s | j } t j | | } | r | j } | | | d } | d k rU | d S| d k r | j d | r{ | d S| j d | r d S| | k r | S| d S| d k r d
S| d k r d S| | k r | S| d St d d S) Nr r /z/>r& r
z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!r( r( r( )r locatestarttagend_tolerantr2 r; r0 r? )r r@ r rb rB nextr
r
r rU ` s. z$HTMLParser.check_for_whole_start_tagc C s | j } | | | d d k s/ t d t j | | d } | sO d S| j } t j | | } | s*| j d k r | j | | | | St j | | d } | s | | | d d k r | d S| j
| S| j d j } | j
d | j } | j | | d S| j d j } | j d k rx| | j k rx| j | | | | S| j | j | j | S) Nr& zr r( )r r? endendtagr- r;
endtagfindr2 r r/ rV rI r9 r r*
handle_endtagr" )r r@ r r2 rJ Z namematchZtagnamer r
r
r r4 s8 &
zHTMLParser.parse_endtagc C s! | j | | | j | d S)N)r] rk )r ra r` r
r
r r\ s z HTMLParser.handle_startendtagc C s d S)Nr
)r ra r` r
r
r r] s zHTMLParser.handle_starttagc C s d S)Nr
)r ra r
r
r rk s zHTMLParser.handle_endtagc C s d S)Nr
)r rD r
r
r r: s zHTMLParser.handle_charrefc C s d S)Nr
)r rD r
r
r r= s zHTMLParser.handle_entityrefc C s d S)Nr
)r r r
r
r r/ s zHTMLParser.handle_datac C s d S)Nr
)r r r
r
r rM s zHTMLParser.handle_commentc C s d S)Nr
)r Zdeclr
r
r rH s zHTMLParser.handle_declc C s d S)Nr
)r r r
r
r rP s zHTMLParser.handle_pic C s d S)Nr
)r r r
r
r unknown_decl s zHTMLParser.unknown_declc C s t j d t d d t | S)NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.
stacklevelr& )warningswarnDeprecationWarningr )r sr
r
r r s
zHTMLParser.unescape)r r ) __name__
__module__ __qualname____doc__r^ r r r r r r r! r" r r7 rI r6 r3 rU r4 r\ r] rk r: r= r/ rM rH rP rl r r
r
r
r r ? s8 z 3 " ( )ru r rn r Zhtmlr __all__r r r> r< r8 r1 rO Z commentcloserV rW VERBOSErg ri rj r r r
r
r
r s(