a  zeC@sdZddlZddlZddlmZdgZedZedZedZ edZ ed Z ed Z ed Z ed Zed ZedejZed ZedZGdddejZdS)zA 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 space )?(?:\s|/(?!>))* )* )? \s* # trailing whitespace z#c@seZdZdZdZddddZddZd d Zd d Zd Z ddZ ddZ ddZ ddZ ddZd7ddZddZddZdd Zd!d"Zd#d$Zd%d&Zd'd(Zd)d*Zd+d,Zd-d.Zd/d0Zd1d2Zd3d4Zd5d6Zd S)8raEFind tags and other markup and call handler functions. Usage: p = HTMLParser() p.feed(data) ... p.close() Start tags are handled by calling self.handle_starttag() or self.handle_startendtag(); end tags by self.handle_endtag(). The data between tags is passed from the parser to the derived class by calling self.handle_data() with the data as argument (the data may be split up in arbitrary chunks). If convert_charrefs is True the character references are converted automatically to the corresponding Unicode character (and self.handle_data() is no longer split in chunks), otherwise they are passed by calling self.handle_entityref() or self.handle_charref() with the string containing respectively the named or numeric reference as the argument. )ZscriptstyleT)convert_charrefscCs||_|dS)zInitialize and reset this instance. If convert_charrefs is True (the default), all character references are automatically converted to the corresponding Unicode characters. N)rreset)selfrr ?/opt/bitninja-python-dojo/embedded/lib/python3.9/html/parser.py__init__VszHTMLParser.__init__cCs(d|_d|_t|_d|_tj|dS)z1Reset this instance. Loses all unprocessed data.z???N)rawdatalasttaginteresting_normal interesting cdata_elem _markupbase ParserBaserrr r r r_s zHTMLParser.resetcCs|j||_|ddS)zFeed data to the parser. Call this as often as you want, with as little or as much text as you want (may include '\n'). rN)r goaheadrdatar r r feedgs zHTMLParser.feedcCs|ddS)zHandle any buffered data.N)rrr r r closepszHTMLParser.closeNcCs|jS)z)Return full source of start tag: '<...>'.)_HTMLParser__starttag_textrr r r get_starttag_textvszHTMLParser.get_starttag_textcCs$||_td|jtj|_dS)Nz )lowerrrecompileIr)relemr r r set_cdata_modezs zHTMLParser.set_cdata_modecCst|_d|_dSN)rrrrr r r clear_cdata_mode~szHTMLParser.clear_cdata_modec CsJ|j}d}t|}||kr|jrv|jsv|d|}|dkr|dt||d}|dkrptd ||spq|}n*|j ||}|r| }n|jrq|}||kr|jr|js| t |||n| ||||||}||krq|j}|d|rJt||r"||} n|d|r:||} nn|d|rR||} nV|d|rj||} n>|d |r||} n&|d |kr| d|d } nq| dkr<|sq|d |d } | dkr|d|d } | dkr|d } n| d 7} |jr*|js*| t ||| n| ||| ||| }q|d |rt||}|r|d d} || |} |d| d s| d } ||| }qnr injZampposr5r3knamer r r rs                                    zHTMLParser.goaheadcCs|j}|||ddkr$||S|||ddkrB||S|||ddkr|d|d}|dkrvdS|||d ||d S||SdS) Nr(z)rrBr r5rDr r r r9 szHTMLParser.parse_picCsd|_||}|dkr|S|j}||||_g}t||d}|}|d|_}||kr t ||}|s~q |ddd\} } } | sd} nZ| dddkr| ddksn| dddkr| ddkrnn | dd} | rt | } | | | f|}q`||| } | dvr| \} }d |jvrz| |jd } t|j|jd }n|t|j}|||||S| d r|||n"|||||jvr|||S) Nrrr)rH'r*")r/> rT)rcheck_for_whole_start_tagr tagfind_tolerantr5r>r<rrattrfind_tolerantrappendstripZgetposcountr,r.r2endswithhandle_startendtaghandle_starttagCDATA_CONTENT_ELEMENTSr")rrBendposr attrsr5rEtagmattrnamerestZ attrvaluer>linenooffsetr r r r6,sX   &            zHTMLParser.parse_starttagcCs|j}t||}|r|}|||d}|dkr>|dS|dkr~|d|rZ|dS|d|rjdS||krv|S|dS|dkrdS|dvrdS||kr|S|dStd dS) Nrr/rTr)r*r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r locatestarttagend_tolerantr5r>r3AssertionError)rrBr rcrDnextr r r rV_s.   z$HTMLParser.check_for_whole_start_tagcCs|j}t||d}|sdS|}t||}|s|jdurV|||||St||d}|s|||ddkr|dS| |S| d }| d|}| ||dS| d }|jdur||jkr|||||S| |||S)Nrr*r)rHzr)r endendtagr0r> endtagfindr5rr2rWrKr<rr- handle_endtagr$)rrBr r5rLZ namematchZtagnamer!r r r r7s6       zHTMLParser.parse_endtagcCs|||||dSr#)r^rnrrbrar r r r]s zHTMLParser.handle_startendtagcCsdSr#r ror r r r^szHTMLParser.handle_starttagcCsdSr#r )rrbr r r rnszHTMLParser.handle_endtagcCsdSr#r rrFr r r r=szHTMLParser.handle_charrefcCsdSr#r rpr r r r@szHTMLParser.handle_entityrefcCsdSr#r rr r r r2szHTMLParser.handle_datacCsdSr#r rr r r rMszHTMLParser.handle_commentcCsdSr#r )rZdeclr r r rJszHTMLParser.handle_declcCsdSr#r rr r r rQszHTMLParser.handle_picCsdSr#r rr r r unknown_declszHTMLParser.unknown_decl)r)__name__ __module__ __qualname____doc__r_r rrrrrr"r$rr:rKr9r6rVr7r]r^rnr=r@r2rMrJrQrqr r r r r>s6  z  3"()rurrZhtmlr__all__rrrAr?r;r4rPZ commentcloserWrXVERBOSErirlrmrrr r r r s*