509318396 ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ ­ 3 'Y!$@spdZddlZddlZddlmZddlmZddlm Z ddl m Z m Z m Z yeZWnek rpeefZYnXyddlmZWn ek rddlmZYnXyddlmZWn ek rddlmZYnXGd d d eZydd lmZWnek r YnXGd d d eZeZddZdddZdddZdddZd ddZ d!ddZ!ddZ"eZ#dS)"z? An interface to html5lib that mimics the lxml.html interface. N) HTMLParser) TreeBuilder)etree)ElementXHTML_NAMESPACE_contains_block_level_tag)urlopen)urlparsec@seZdZdZdddZdS)rz*An html5lib HTML parser with lxml as tree.FcKstj|f|td|dS)N)stricttree) _HTMLParser__init__r)selfr kwargsr#/usr/lib64/python3.6/html5parser.pyr szHTMLParser.__init__N)F)__name__ __module__ __qualname____doc__r rrrrrsr) XHTMLParserc@seZdZdZdddZdS)rz+An html5lib XHTML Parser with lxml as tree.FcKstj|f|td|dS)N)r r ) _XHTMLParserr r)rr rrrrr *szXHTMLParser.__init__N)F)rrrrr rrrrr'srcCs(|j|}|dk r|S|jdt|fS)Nz{%s}%s)findr)r tagelemrrr _find_tag0s rcCsZt|tstd|dkrt}i}|dkr8t|tr8d}|dk rH||d<|j|f|jS)z Parse a whole document into a string. If `guess_charset` is true, or if the input is not Unicode but a byte string, the `chardet` library will perform charset guessing on the string. zstring requiredNT useChardet) isinstance_strings TypeError html_parserbytesparseZgetroot)html guess_charsetparseroptionsrrrdocument_fromstring7s r'FcCst|tstd|dkrt}i}|dkr8t|tr8d}|dk rH||d<|j|df|}|rt|dtr|r|djrtjd|d|d=|S)a`Parses several HTML elements, returning a list of elements. The first item in the list may be a string. If no_leading_text is true, then it will be an error if there is leading text, and it will always be a list of only elements. If `guess_charset` is true, the `chardet` library will perform charset guessing on the string. zstring requiredNFrdivrzThere is leading text: %r) rrrr r!Z parseFragmentstripr ParserError)r#no_leading_textr$r%r&Zchildrenrrrfragments_fromstringOs"   r,cCst|tstdt|}t|||| d}|rvt|ts>d}t|}|rrt|dtrh|d|_|d=|j||S|stj dt |dkrtj d|d}|j r|j j rtj d|j d |_ |S) aParses a single HTML element; it is an error if there is more than one element, or if anything but whitespace precedes or follows the element. If 'create_parent' is true (or is a tag name) then a parent node will be created to encapsulate the HTML in a single element. In this case, leading or trailing text is allowed. If `guess_charset` is true, the `chardet` library will perform charset guessing on the string. zstring required)r$r%r+r(rzNo elements foundzMultiple elements foundzElement followed by text: %rN) rrrboolr,rtextextendrr*lentailr))r#Z create_parentr$r%Zaccept_leading_textelementsZnew_rootresultrrrfragment_fromstringqs2        r5cCst|tstdt|||d}|dd}t|trB|jdd}|jj}|jdsb|jdrf|St |d }t |r||St |d }t |d kr|j s|j j r|dj s|dj j r|d St|rd |_nd|_|S)aParse the html, returning a single element/document. This tries to minimally parse the chunk of text, without knowing if it is a fragment or a document. 'base_url' will set the document's base_url attribute (and the tree's docinfo.URL) If `guess_charset` is true, or if the input is not Unicode but a byte string, the `chardet` library will perform charset guessing on the string. zstring required)r%r$N2asciireplacezsF     ! + 6 $