B j9C\u3ã @s˜dZdZdgZddlmZyddlmZWn2ek r\ZzGdd„deƒZWddZ[XYnXddl Z ddl Z e j dd …\Z Z Ze d ko˜e d ko˜ed kZe d ko¨e d kZe d ko¸e d kZdd lmZmZmZmZmZdd lmZmZddlmZmZmZdZGdd„deƒZ Gdd„deƒZ!e d kr”e d kr”es”ddl"Z"e" #d¡Z$e$e!_$e" #de"j%¡Z&e&e _&ddlm'Z'm(Z(dd„Z)dd„Z*e)e _)e*e _*dZdS)zCUse the HTMLParser library to parse HTML files that aren't too bad.ZMITÚHTMLParserTreeBuilderé)Ú HTMLParser)ÚHTMLParseErrorc@s eZdZdS)rN)Ú__name__Ú __module__Ú __qualname__©rrú6lib/python3.7/site-packages/bs4/builder/_htmlparser.pyrsrNééé)ÚCDataÚCommentÚ DeclarationÚDoctypeÚProcessingInstruction)ÚEntitySubstitutionÚ UnicodeDammit)ÚHTMLÚHTMLTreeBuilderÚSTRICTz html.parserc@speZdZdd„Zdd„Zdd„Zddd „Zdd d „Zd d „Zdd„Z dd„Z dd„Z dd„Z dd„Z dd„ZdS)ÚBeautifulSoupHTMLParsercOstj|f|ž|Žg|_dS)N)rÚ__init__Úalready_closed_empty_element)ÚselfÚargsÚkwargsrrr r9s z BeautifulSoupHTMLParser.__init__cCst |¡dS)aiIn Python 3, HTMLParser subclasses must implement error(), although this requirement doesn't appear to be documented. In Python 2, HTMLParser implements error() as raising an exception. In any event, this method is called only on very strange markup and our best strategy is to pretend it didn't happen and keep going. N)ÚwarningsÚwarn)rÚmsgrrr ÚerrorEs zBeautifulSoupHTMLParser.errorcCs|j||dd}| |¡dS)NF)Úhandle_empty_element)Úhandle_starttagÚ handle_endtag)rÚnameÚattrsÚtagrrr Úhandle_startendtagPsz*BeautifulSoupHTMLParser.handle_startendtagTc Csli}x(|D] \}}|dkrd}|||<d}q W|j |dd|¡}|rh|jrh|rh|j|dd|j |¡dS)NÚz""F)Úcheck_already_closed)Úsoupr"Zis_empty_elementr#rÚappend) rr$r%r!Z attr_dictÚkeyÚvalueÚ attrvaluer&rrr r"[s z'BeautifulSoupHTMLParser.handle_starttagcCs,|r||jkr|j |¡n |j |¡dS)N)rÚremover*r#)rr$r)rrr r#wsz%BeautifulSoupHTMLParser.handle_endtagcCs|j |¡dS)N)r*Ú handle_data)rÚdatarrr r0‚sz#BeautifulSoupHTMLParser.handle_datac Csî| d¡rt| d¡dƒ}n$| d¡r8t| d¡dƒ}nt|ƒ}d}|dkr xR|jjdfD]B}|sdqZyt|gƒ |¡}WqZtk rš}zWdd}~XYqZXqZW|sØy t|ƒ}Wn&t t fk rÖ}zWdd}~XYnX|pÞd}|  |¡dS)NÚxéÚXéz windows-1252u�) Ú startswithÚintÚlstripr*Úoriginal_encodingÚ bytearrayÚdecodeÚUnicodeDecodeErrorÚchrÚ ValueErrorÚ OverflowErrorr0)rr$Z real_namer1ÚencodingÚerrr Úhandle_charref…s*   z&BeautifulSoupHTMLParser.handle_charrefcCs0tj |¡}|dk r|}nd|}| |¡dS)Nz&%s)rZHTML_ENTITY_TO_CHARACTERÚgetr0)rr$Ú characterr1rrr Úhandle_entityref¦s  z(BeautifulSoupHTMLParser.handle_entityrefcCs&|j ¡|j |¡|j t¡dS)N)r*ÚendDatar0r)rr1rrr Úhandle_comment³s  z&BeautifulSoupHTMLParser.handle_commentcCsN|j ¡| d¡r&|tdƒd…}n |dkr2d}|j |¡|j t¡dS)NzDOCTYPE ZDOCTYPEr()r*rFr6Úlenr0r)rr1rrr Ú handle_decl¸s   z#BeautifulSoupHTMLParser.handle_declcCsN| ¡ d¡r$t}|tdƒd…}nt}|j ¡|j |¡|j |¡dS)NzCDATA[)Úupperr6r rHrr*rFr0)rr1Úclsrrr Ú unknown_declÂs  z$BeautifulSoupHTMLParser.unknown_declcCs&|j ¡|j |¡|j t¡dS)N)r*rFr0r)rr1rrr Ú handle_piÌs  z!BeautifulSoupHTMLParser.handle_piN)T)T)rrrrr r'r"r#r0rBrErGrIrLrMrrrr r7s    !   rc@s<eZdZdZdZeZeeegZ dd„Z d dd„Z dd „Z dS) rFTcOs*trtsd|d<trd|d<||f|_dS)NFÚstrictZconvert_charrefs)ÚCONSTRUCTOR_TAKES_STRICTÚ CONSTRUCTOR_STRICT_IS_DEPRECATEDÚ"CONSTRUCTOR_TAKES_CONVERT_CHARREFSÚ parser_args)rrrrrr rÙs zHTMLParserTreeBuilder.__init__NccsNt|tƒr|dddfVdS||g}t||d|d}|j|j|j|jfVdS)z¸ :return: A 4-tuple (markup, original encoding, encoding declared within markup, whether any characters had to be replaced with REPLACEMENT CHARACTER). NFT)Zis_htmlÚexclude_encodings)Ú isinstanceÚstrrÚmarkupr9Zdeclared_html_encodingZcontains_replacement_characters)rrVZuser_specified_encodingZdocument_declared_encodingrSZ try_encodingsZdammitrrr Úprepare_markupàs z$HTMLParserTreeBuilder.prepare_markupc Csr|j\}}t||Ž}|j|_y| |¡| ¡Wn4tk rf}zt tdƒ¡|‚Wdd}~XYnXg|_ dS)Na*Python's built-in HTMLParser cannot parse the given document. This is not a bug in Beautiful Soup. The best solution is to install an external parser (lxml or html5lib), and use Beautiful Soup with that parser. See http://www.crummy.com/software/BeautifulSoup/bs4/doc/#installing-a-parser for help.) rRrr*ÚfeedÚcloserrrÚRuntimeWarningr)rrVrrÚparserrArrr rXòs    zHTMLParserTreeBuilder.feed)NNN) rrrZis_xmlZ picklableÚ HTMLPARSERÚNAMErrZfeaturesrrWrXrrrr rÒs  zQ\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?aê <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name (?:\s+ # whitespace before attribute name (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name (?:\s*=\s* # value indicator (?:'[^']*' # LITA-enclosed value |\"[^\"]*\" # LIT-enclosed value |[^'\">\s]+ # bare value ) )? ) )* \s* # trailing whitespace )ÚtagfindÚattrfindcCs6d|_| |¡}|dkr|S|j}|||…|_g}t ||d¡}|sPtdƒ‚| ¡}||d|… ¡|_}xÜ||krN|j r’t  ||¡}n t  ||¡}|s¤P|  ddd¡\} } } | sÂd} n`| dd…dkrè| dd…ksn| dd…dkr| dd…kr"nn | dd…} | r2|  | ¡} | |  ¡| f¡| ¡}qtW|||… ¡} | d krö| ¡\} }d |jkrª| |j d ¡} t|jƒ|j d ¡}n|t|jƒ}|j rà| d |||…dd …f¡| |||…¡|S|  d ¡r| ||¡n"| ||¡||jkr2| |¡|S)Nréz#unexpected call to parse_starttag()r r ú'éÿÿÿÿú")ú>z/>Ú z junk characters in start tag: %réz/>)Z__starttag_textZcheck_for_whole_start_tagÚrawdatar^ÚmatchÚAssertionErrorÚendÚlowerZlasttagrNr_Úattrfind_tolerantÚgroupZunescaper+ÚstripZgetposÚcountrHÚrfindr r0Úendswithr'r"ZCDATA_CONTENT_ELEMENTSÚset_cdata_mode)rÚiÚendposrgr%rhÚkr&ÚmZattrnameÚrestr.rjÚlinenoÚoffsetrrr Úparse_starttags\    (,          rzcCs$| ¡|_t d|jtj¡|_dS)Nz )rkZ cdata_elemÚreÚcompileÚIZ interesting)rÚelemrrr rrTs rrT)+Ú__doc__Z __license__Ú__all__Z html.parserrrÚ ImportErrorrAÚ ExceptionÚsysrÚ version_infoÚmajorÚminorÚreleaserOrPrQZ bs4.elementr rrrrZ bs4.dammitrrZ bs4.builderrrrr\rrr{r|rlÚVERBOSEZlocatestarttagendr^r_rzrrrrrr ÚsD " 2 7