B °-_9Eã@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 comma )?(?:\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$„Zd%d&„Zd'd(„Zd)d*„Zd+d,„Zd-d.„Zd/d0„Zd1d2„Zd3d4„Zd5d6„Zd7d8„Zd S):raEFind tags and other markup and call handler functions. Usage: p = HTMLParser() p.feed(data) ... p.close() Start tags are handled by calling self.handle_starttag() or self.handle_startendtag(); end tags by self.handle_endtag(). The data between tags is passed from the parser to the derived class by calling self.handle_data() with the data as argument (the data may be split up in arbitrary chunks). If convert_charrefs is True the character references are converted automatically to the corresponding Unicode character (and self.handle_data() is no longer split in chunks), otherwise they are passed by calling self.handle_entityref() or self.handle_charref() with the string containing respectively the named or numeric reference as the argument. )ZscriptZstyleT)Úconvert_charrefscCs||_| ¡dS)zÆInitialize and reset this instance. If convert_charrefs is True (the default), all character references are automatically converted to the corresponding Unicode characters. N)rÚreset)Úselfr©rú!/usr/lib/python3.7/html/parser.pyÚ__init__WszHTMLParser.__init__cCs(d|_d|_t|_d|_tj |¡dS)z1Reset this instance. Loses all unprocessed data.Úz???N)ÚrawdataÚlasttagÚinteresting_normalÚ interestingÚ cdata_elemÚ _markupbaseÚ ParserBaser)rrrr r`s zHTMLParser.resetcCs|j||_| d¡dS)z‘Feed data to the parser. Call this as often as you want, with as little or as much text as you want (may include '\n'). rN)r Úgoahead)rÚdatarrr Úfeedhs zHTMLParser.feedcCs| d¡dS)zHandle any buffered data.éN)r)rrrr ÚcloseqszHTMLParser.closeNcCs|jS)z)Return full source of start tag: '<...>'.)Ú_HTMLParser__starttag_text)rrrr Úget_starttag_textwszHTMLParser.get_starttag_textcCs$| ¡|_t d|jtj¡|_dS)Nz )ÚlowerrÚreÚcompileÚIr)rÚelemrrr Úset_cdata_mode{s zHTMLParser.set_cdata_modecCst|_d|_dS)N)rrr)rrrr Úclear_cdata_modeszHTMLParser.clear_cdata_modec CsN|j}d}t|ƒ}xÈ||krÜ|jrx|jsx| d|¡}|dkr | dt||dƒ¡}|dkrrt d¡  ||¡srP|}n(|j   ||¡}|r”|  ¡}n |jrœP|}||krÞ|jrÌ|jsÌ|  t |||…ƒ¡n|  |||…¡| ||¡}||krôP|j}|d|ƒrDt ||¡r | |¡} n„|d|ƒr8| |¡} nl|d|ƒrP| |¡} nT|d|ƒrh| |¡} n<|d |ƒr€| |¡} n$|d |kr¢|  d¡|d } nP| dkr6|s¶P| d |d ¡} | dkrô| d|d ¡} | dkrü|d } n| d 7} |jr$|js$|  t ||| …ƒ¡n|  ||| …¡| || ¡}q|d |ƒrèt ||¡}|r¬| ¡d d…} | | ¡| ¡} |d| d ƒsœ| d } | || ¡}qn:d||d…krä|  |||d …¡| ||d ¡}Pq|d|ƒrÎt ||¡}|rH| d ¡} | | ¡| ¡} |d| d ƒs:| d } | || ¡}qt ||¡}|r |rœ| ¡||d…krœ| ¡} | |krŒ|} | ||d ¡}Pn,|d |krÊ|  d¡| ||d ¡}nPqdstdƒ‚qW|r<||kr<|js<|jr|js|  t |||…ƒ¡n|  |||…¡| ||¡}||d…|_dS)Nrú<ú&é"z[\s;]zr Úgtposrrr r5s  z!HTMLParser.parse_html_declarationrcCs`|j}|||d…dks"tdƒ‚| d|d¡}|dkr>dS|rX| ||d|…¡|dS)Nr$)zZreportr Úposrrr rGszHTMLParser.parse_bogus_commentcCsd|j}|||d…dks"tdƒ‚t ||d¡}|s:dS| ¡}| ||d|…¡| ¡}|S)Nr$zr r0r@rrr r4!szHTMLParser.parse_picCsîd|_| |¡}|dkr|S|j}|||…|_g}t ||d¡}|sPtdƒ‚| ¡}| d¡ ¡|_ }xÂ||kr.t  ||¡}|sŠP| ddd¡\} } } | s¨d} n\| dd…dkrÌ| dd…ksøn| dd…dkrô| dd…krnn | dd…} | rt | ƒ} |  |  ¡| f¡| ¡}qnW|||…  ¡} | d kr®| ¡\} }d |jkrŠ| |j d ¡} t|jƒ|j d ¡}n|t|jƒ}| |||…¡|S|  d ¡rÈ| ||¡n"| ||¡||jkrê| |¡|S) Nrrz#unexpected call to parse_starttag()r$rDú'r%ú")rz/>Ú z/>)rÚcheck_for_whole_start_tagr Útagfind_tolerantr0r=r9r7rr Úattrfind_tolerantrÚappendÚstripZgetposÚcountr'r)r-ÚendswithÚhandle_startendtagÚhandle_starttagÚCDATA_CONTENT_ELEMENTSr)rr>Úendposr Úattrsr0rAÚtagÚmZattrnameÚrestZ attrvaluer9ÚlinenoÚoffsetrrr r1-sR    &*         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/z/>r$r%r z6abcdefghijklmnopqrstuvwxyz=/ABCDEFGHIJKLMNOPQRSTUVWXYZzwe should not get here!)r Úlocatestarttagend_tolerantr0r9r.r=)rr>r r]r@Únextrrr rP`s.   z$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$zr)r r=Ú endendtagr+r9Ú endtagfindr0rr-rQrGr7rr(Ú handle_endtagr )rr>r r0rHZ namematchZtagnamerrrr r2‚s8       zHTMLParser.parse_endtagcCs| ||¡| |¡dS)N)rXrf)rr\r[rrr rWªs zHTMLParser.handle_startendtagcCsdS)Nr)rr\r[rrr rX¯szHTMLParser.handle_starttagcCsdS)Nr)rr\rrr rf³szHTMLParser.handle_endtagcCsdS)Nr)rrBrrr r8·szHTMLParser.handle_charrefcCsdS)Nr)rrBrrr r;»szHTMLParser.handle_entityrefcCsdS)Nr)rrrrr r-¿szHTMLParser.handle_datacCsdS)Nr)rrrrr rIÃszHTMLParser.handle_commentcCsdS)Nr)rZdeclrrr rFÇszHTMLParser.handle_declcCsdS)Nr)rrrrr rLËszHTMLParser.handle_picCsdS)Nr)rrrrr Ú unknown_declÎszHTMLParser.unknown_declcCstjdtddt|ƒS)NzZThe unescape method is deprecated and will be removed in 3.5, use html.unescape() instead.r$)Ú stacklevel)ÚwarningsÚwarnÚDeprecationWarningr)rÚsrrr rÒs zHTMLParser.unescape)r)Ú__name__Ú __module__Ú __qualname__Ú__doc__rYr rrrrrrr rr5rGr4r1rPr2rWrXrfr8r;r-rIrFrLrgrrrrr r?s8  z  3"()rprrirZhtmlrÚ__all__rrr<r:r6r/rKZ commentcloserQrRÚVERBOSErbrdrerrrrrr Ús(