ó ø°äRc@sÑdZddlZddlZddlmZddlmZddlm Z ddl m Z m Z m Z y eZWnek r“eefZnXyddlmZWn!ek rËddlmZnXyddlmZWn!ek rddlmZnXd efd „ƒYZydd lmZWnek rAn Xd efd „ƒYZeƒZd„Zedd„Ze e dd„Z!e e dd„Z"edd„Z#edd„Z$d„Z%eƒZ&dS(s? An interface to html5lib that mimics the lxml.html interface. iÿÿÿÿN(t HTMLParser(t TreeBuilder(tetree(t_contains_block_level_tagtXHTML_NAMESPACEtElement(turlopen(turlparseRcBseZdZed„ZRS(s*An html5lib HTML parser with lxml as tree.cKs tj|d|dt|dS(Ntstrictttree(t _HTMLParsert__init__R(tselfRtkwargs((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pyR s(t__name__t __module__t__doc__tFalseR (((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pyRs(t XHTMLParserRcBseZdZed„ZRS(s+An html5lib XHTML Parser with lxml as tree.cKs tj|d|dt|dS(NRR (t _XHTMLParserR R(R RR ((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pyR +s(RRRRR (((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pyR(scCs6|j|ƒ}|dk r|S|jdt|fƒS(Ns{%s}%s(tfindtNoneR(R ttagtelem((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pyt _find_tag1s cCsLt|tƒstdƒ‚n|dkr3t}n|j|d|ƒjƒS(s%Parse a whole document into a string.sstring requiredt useChardetN(t isinstancet_stringst TypeErrorRt html_parsertparsetgetroot(thtmlt guess_charsettparser((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pytdocument_fromstring8s   cCs¥t|tƒstdƒ‚n|dkr3t}n|j|dd|ƒ}|r¡t|dtƒr¡|r¡|djƒr”tjd|dƒ‚n|d=q¡n|S(s”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` and the text was not unicode but a bytestring, the `chardet` library will perform charset guessing on the string. sstring requiredtdivRisThere is leading text: %rN( RRRRRt parseFragmenttstripRt ParserError(R tno_leading_textR!R"tchildren((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pytfragments_fromstringCs     cCs;t|tƒstdƒ‚nt|ƒ}t|d|d|d| ƒ}|r·t|tƒsgd}nt|ƒ}|r³t|dtƒr£|d|_|d=n|j|ƒn|S|sÏtj dƒ‚nt |ƒdkrótj d ƒ‚n|d}|j r.|j j ƒr.tj d |j ƒ‚nd |_ |S( sXParses 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. sstring requiredR!R"R(R$isNo elements foundisMultiple elements foundsElement followed by text: %rN(RRRtboolR*RttexttextendRR'tlenttailR&R(R t create_parentR!R"taccept_leading_texttelementstnew_roottresult((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pytfragment_fromstring_s2         cCst|tƒstdƒ‚nt|d|d|ƒ}|d jƒjƒ}|jdƒsj|jdƒrn|St|dƒ}t|ƒr|St|dƒ}t|ƒd krò|j sÈ|j j ƒ rò|d j sê|d j j ƒ rò|d St |ƒr d |_ n d |_ |S(süParse 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) sstring requiredR"R!i2sRR@R(((s9/usr/lib/python2.7/dist-packages/lxml/html/html5parser.pytsF          (*