U Å:âe9Eã@sÀdZddlZddlZddlZddlmZdgZe d¡Ze d¡Z e d¡Z e d¡Z e d ¡Z e d ¡Z e d ¡Ze d ¡Ze d ¡Ze dej¡Ze d ¡Ze d¡ZGdd„dejƒZdS)zA parser for HTML and XHTML.éN)ÚunescapeÚ 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]ú>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@sèeZdZdZdZddœdd„Zdd„Zd d „Zd d „Zd Z dd„Z dd„Z dd„Z dd„Z dd„Zd9dd„Zdd„Zdd„Zdd „Zd!d"„Zd#d$„Zd%d&„Zd'd(„Zd)d*„Zd+d,„Zd-d.„Zd/d0„Zd1d2„Zd3d4„Zd5d6„Zd7d8„Zd S):raEFind tags and other markup and call handler functions. Usage: p = HTMLParser() p.feed(data) ... p.close() Start tags are handled by calling self.handle_starttag() or self.handle_startendtag(); end tags by self.handle_endtag(). The data between tags is passed from the parser to the derived class by calling self.handle_data() with the data as argument (the data may be split up in arbitrary chunks). If convert_charrefs is True the character references are converted automatically to the corresponding Unicode character (and self.handle_data() is no longer split in chunks), otherwise they are passed by calling self.handle_entityref() or self.handle_charref() with the string containing respectively the named or numeric reference as the argument. )ZscriptÚstyleT)Úconvert_charrefscCs||_| ¡dS)zÆInitialize and reset this instance. If convert_charrefs is True (the default), all character references are automatically converted to the corresponding Unicode characters. N)rÚreset)Úselfr©r ú0/usr/local/python38/lib/python3.8/html/parser.pyÚ__init__WszHTMLParser.__init__cCs(d|_d|_t|_d|_tj |¡dS)z1Reset this instance. Loses all unprocessed data.Úz???N)ÚrawdataÚlasttagÚinteresting_normalÚ interestingÚ cdata_elemÚ _markupbaseÚ ParserBaser©rr r r r`s zHTMLParser.resetcCs|j||_| d¡dS)z‘Feed data to the parser. Call this as often as you want, with as little or as much text as you want (may include '\n'). rN)r Úgoahead©rÚdatar r r Úfeedhs zHTMLParser.feedcCs| d¡dS)zHandle any buffered data.éN)rrr r r ÚcloseqszHTMLParser.closeNcCs|jS)z)Return full source of start tag: '<...>'.)Ú_HTMLParser__starttag_textrr r r Úget_starttag_textwszHTMLParser.get_starttag_textcCs$| ¡|_t d|jtj¡|_dS)Nz )ÚlowerrÚreÚcompileÚIr)rÚelemr r r Úset_cdata_mode{s zHTMLParser.set_cdata_modecCst|_d|_dS©N)rrrrr r r Úclear_cdata_modeszHTMLParser.clear_cdata_modec CsX|j}d}t|ƒ}||krè|jrv|jsv| d|¡}|dkr | dt||dƒ¡}|dkrpt d¡  ||¡spqè|}n*|j   ||¡}|r’|  ¡}n|jrœqè|}||krÞ|jrÌ|jsÌ|  t |||…ƒ¡n|  |||…¡| ||¡}||kröqè|j}|d|ƒrJt ||¡r"| |¡} n†|d|ƒr:| |¡} nn|d|ƒrR| |¡} nV|d|ƒrj| |¡} n>|d |ƒr‚| |¡} n&|d |krè|  d¡|d } nqè| dkr<|s¼qè| d |d ¡} | dkrú| d|d ¡} | dkr|d } n| d 7} |jr*|js*|  t ||| …ƒ¡n|  ||| …¡| || ¡}q|d |ƒrðt ||¡}|r²| ¡d d…} | | ¡| ¡} |d| d ƒs¢| d } | || ¡}qndS|rX| ||d|…¡|dS)Nr,)r+r(z"unexpected call to parse_comment()rr-r)r rEr0Úhandle_comment)rrFZreportr Úposr r r rOszHTMLParser.parse_bogus_commentcCsd|j}|||d…dks"tdƒ‚t ||d¡}|s:dS| ¡}| ||d|…¡| ¡}|S)Nr,r*zunexpected call to parse_pi()r-)r rEÚpicloser3r4Ú handle_pirA)rrFr r8rHr r r r<!szHTMLParser.parse_picCsìd|_| |¡}|dkr|S|j}|||…|_g}t ||d¡}|sPtdƒ‚| ¡}| d¡ ¡|_ }||kr.t  ||¡}|sŠq.| ddd¡\} } } | s¨d} n\| dd…dkrÌ| dd…ksøn| dd…dkrô| dd…krnn | dd…} | rt | ƒ} |  |  ¡| f¡| ¡}ql|||…  ¡} | d kr¬| ¡\} }d |jkrˆ| |j d ¡} t|jƒ|j d ¡}n|t|jƒ}| |||…¡|S|  d ¡rÆ| ||¡n"| ||¡||jkrè| |¡|S) Nrrz#unexpected call to parse_starttag()r,rLú'r-ú")rú/>Ú rW)rÚcheck_for_whole_start_tagr Útagfind_tolerantr8rErAr?rrÚattrfind_tolerantrÚappendÚstripZgetposÚcountr/r1r5ÚendswithÚhandle_startendtagÚhandle_starttagÚCDATA_CONTENT_ELEMENTSr")rrFÚendposr Úattrsr8rIÚtagÚmÚattrnameÚrestZ attrvaluerAÚlinenoÚoffsetr r r r9-s\    & ÿ ÿ       ÿ    zHTMLParser.parse_starttagcCs¶|j}t ||¡}|rª| ¡}|||d…}|dkr>|dS|dkr~| d|¡rZ|dS| d|¡rjdS||krv|S|dS|dkrŠdS|dkr–dS||kr¢|S|dStd ƒ‚dS) Nrrú/rWr,r-r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r Úlocatestarttagend_tolerantr8rAr6rE)rrFr rfrHÚnextr r r rY`s.   z$HTMLParser.check_for_whole_start_tagcCs.|j}|||d…dks"tdƒ‚t ||d¡}|s:dS| ¡}t ||¡}|sÜ|jdk rr| |||…¡|St  ||d¡}|s¬|||d…dkr¢|dS|  |¡S|  d¡  ¡}|  d| ¡¡}| |¡|dS|  d¡  ¡}|jdk r||jkr| |||…¡|S| |¡| ¡|S) Nr,r(zunexpected call to parse_endtagrr-rLzr)r rEÚ endendtagr3rAÚ endtagfindr8rr5rZrOr?rr0Ú handle_endtagr$)rrFr r8rPZ namematchZtagnamer!r r r r:‚s8       zHTMLParser.parse_endtagcCs| ||¡| |¡dSr#)rarp©rrerdr r r r`ªs zHTMLParser.handle_startendtagcCsdSr#r rqr r r ra¯szHTMLParser.handle_starttagcCsdSr#r )rrer r r rp³szHTMLParser.handle_endtagcCsdSr#r ©rrJr r r r@·szHTMLParser.handle_charrefcCsdSr#r rrr r r rC»szHTMLParser.handle_entityrefcCsdSr#r rr r r r5¿szHTMLParser.handle_datacCsdSr#r rr r r rQÃszHTMLParser.handle_commentcCsdSr#r )rZdeclr r r rNÇszHTMLParser.handle_declcCsdSr#r rr r r rTËszHTMLParser.handle_picCsdSr#r rr r r Ú unknown_declÎszHTMLParser.unknown_declcCstjdtddt|ƒS)NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.r,)Ú stacklevel)ÚwarningsÚwarnÚDeprecationWarningr)rÚsr r r rÒs þzHTMLParser.unescape)r)Ú__name__Ú __module__Ú __qualname__Ú__doc__rbr rrrrrr"r$rr=rOr<r9rYr:r`rarpr@rCr5rQrNrTrsrr r r r r?s8  z  3"()r|rrurZhtmlrÚ__all__rrrDrBr>r7rSZ commentcloserZr[ÚVERBOSErlrnrorrr r r r Ús,          ÿò