/usr/lib64/python2.6/site-packages/lxml/html
Edit: /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyc (5870B)
Ńň
ŞJc @ s& d Z d d k Z d d k l Z l Z d d k l Z d d k l
Z
l Z d d k l
Z
y
e Z Wn e j
o e e f Z n Xd e f d YZ d e f d
YZ d Z e d d Z e e d d
Z e e d d Z e d d Z e d d Z e Z e Z d S( s
An interface to html5lib.
i˙˙˙˙N( t
HTMLParsert XHTMLParser( t etree( t _contains_block_level_tagt XHTML_NAMESPACE( t TreeBuilderR c B s e Z d Z e d Z RS( s* An html5lib HTML parser with lxml as tree.c C s t i | d | d t d S( Nt strictt tree( t _HTMLParsert __init__R ( t selfR ( ( s; /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyR s ( t __name__t
__module__t __doc__t FalseR ( ( ( s; /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyR s R c B s e Z d Z e d Z RS( s+ An html5lib XHTML Parser with lxml as tree.c C s t i | d | d t d S( NR R ( t _XHTMLParserR R ( R
R ( ( s; /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyR s ( R R R
R R ( ( ( s; /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyR s c C s8 | i | } | d j o | S| i d t | f S( Ns {%s}%s( t findt NoneR ( R t tagt elem( ( s; /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyt _find_tag s
c C sP t | t p t d n | d j o
t } n | i | d | i S( s% Parse a whole document into a string.s string requiredt
useChardetN( t
isinstancet _stringst TypeErrorR t html_parsert parset getroot( t htmlt
guess_charsett parser( ( s; /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyt document_fromstring' s
c C s° t | t p t d n | d j o
t } n | i | d d | } | oV t | d t oB | o7 | d i o t i d | d n | d =qŹ 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.
s string requiredt divR i s There is leading text: %rN( R R R R R t
parseFragmentt stripR t ParserError( R t no_leading_textR R t children( ( s; /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyt fragments_fromstring2 s
c C së t | t p t d n | o$ | p d } d | | | f } n t | t | | } | p t i d n t | d j o t i d n | d } | i o* | i i o t i d | i n d | _ | S(
s Parses 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.
s string requiredR s <%s>%ss No elements foundi s Multiple elements foundi s Element followed by text: %rN( R R R R& t TrueR R# t lent tailR" R ( R t
create_parentR R t containerR% t result( ( s; /usr/lib64/python2.6/site-packages/lxml/html/html5parser.pyt fragment_fromstringN s
c C s& t | t p t d n t | d | d | } | d i i } | i d p | i d o | St | d } t | o | St | d } t | d j oI | i p | i i
o- | d
i p | d
i i
o | d St | o
d | _
n
d
| _
| S( sü Parse 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)
s string requiredR R i2 s
s*
*