File: //proc/2/cwd/lib64/python2.7/site-packages/lxml/html/html5parser.pyc
�
�'�Yc @ s� d Z d d l Z d d l Z d d l m Z d d l m Z d d l m Z d d l
m Z m Z m
Z
y
e Z Wn e k
r� e e f Z n Xy d d l m Z Wn! e k
r� d d l m Z n Xy d d l m Z Wn! e k
rd d l m Z n Xd e f d
� � YZ y d d l m Z Wn e k
rAn Xd e f d
� � YZ e � Z d � Z d d d � Z e d d d � Z e d d d � Z! d d d � Z" d d d � Z# d � Z$ e � Z% d S( s?
An interface to html5lib that mimics the lxml.html interface.
i����N( t
HTMLParser( t TreeBuilder( t etree( t Elementt XHTML_NAMESPACEt _contains_block_level_tag( t urlopen( t urlparseR c B s e Z d Z e d � Z RS( s* An html5lib HTML parser with lxml as tree.c K s t j | d | d t | �d S( Nt strictt tree( t _HTMLParsert __init__R ( t selfR t kwargs( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR s ( t __name__t
__module__t __doc__t FalseR ( ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR s ( t XHTMLParserR c B s e Z d Z e d � Z RS( s+ An html5lib XHTML Parser with lxml as tree.c K s t j | d | d t | �d S( NR R ( t _XHTMLParserR R ( R R R
( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR * s ( R R R R R ( ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR ' s c C s6 | j | � } | d k r | S| j d t | f � S( Ns {%s}%s( t findt NoneR ( R t tagt elem( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt _find_tag0 s c C s� t | t � s t d � � n | d k r3 t } n i } | d k r] t | t � r] t } n | d k rv | | d <n | j | | � j � S( s�
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.
s string requiredt
useChardetN( t
isinstancet _stringst TypeErrorR t html_parsert bytest Truet parset getroot( t htmlt
guess_charsett parsert options( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt document_fromstring7 s
c C s� t | t � s t d � � n | d k r3 t } n i } | d k r] t | t � r] t } n | d k rv | | d <n | j | d | � } | r� t | d t � r� | r� | d j � r� t j
d | d � � 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, the `chardet` library will perform charset
guessing on the string.
s string requiredR t divi s There is leading text: %rN( R R R R R R R t
parseFragmentt stripR t ParserError( R" t no_leading_textR# R$ R% t children( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt fragments_fromstringO s"
c C s; t | t � s t d � � n t | � } t | d | d | d | �} | r� t | t � sg d } n t | � } | r� t | d t � r� | d | _ | d =n | j | � n | S| s� t j d � � n t
| � d k r� t j d � � n | d } | j r.| j j � r.t j d
| j � � 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. In
this case, leading or trailing text is allowed.
If `guess_charset` is true, the `chardet` library will perform charset
guessing on the string.
s string requiredR# R$ R+ R' i s No elements foundi s Multiple elements founds Element followed by text: %rN( R R R t boolR- R t textt extendR R* t lent tailR) R ( R" t
create_parentR# R$ t accept_leading_textt elementst new_roott result( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt fragment_fromstringq s2
c C sA t | t � s t d � � n t | d | d | �} | d } t | t � rd | j d d � } n | j � j � } | j d � s� | j d � r� | St | d � } t
| � r� | St | d
� } t
| � d k r | j s� | j j � r | d j
s| d j
j � r | d
St | � r4d | _ n d | _ | S( s� 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)
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.
s string requiredR$ R# i2 t asciit replaces <htmls <!doctypet headt bodyi i����i R' t span( R R R R& R t decodet lstript lowert
startswithR R1 R/ R) R2 R R ( R" R# R$ t doct startR; R< ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt
fromstring� s*
," c C s� | d k r t } n t | t � sB | } | d k r� t } q� nT t | � rr t | � } | d k r� t } q� n$ t | d � } | d k r� t } n i } | r� | | d <n | j | | � S( s* Parse a filename, URL, or file-like object into an HTML document
tree. Note: this returns a tree, not an element. Use
``parse(...).getroot()`` to get the document root.
If ``guess_charset`` is true, the ``useChardet`` option is passed into
html5lib to enable character detection. This option is on by default
when parsing from URLs, off by default when parsing from file(-like)
objects (which tend to return Unicode more often than not), and on by
default when parsing from a file path (which is read in binary mode).
t rbR N(
R R R R R t _looks_like_urlR R t openR ( t filename_url_or_fileR# R$ t fpR% ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyR � s"
c C sV t | � d } | s t St j d k rN | t j k rN t | � d k rN t St Sd S( Ni t win32i ( R R t syst platformt stringt
ascii_lettersR1 R ( t strt scheme( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyRF � s (& R RK RM t html5libR R
t html5lib.treebuilders.etree_lxmlR t lxmlR t lxml.htmlR R R t
basestringR t NameErrorR RO t urllib2R t ImportErrort urllib.requestR t urllib.parseR R t xhtml_parserR R R& R R- R8 RD R RF R ( ( ( s; /usr/lib64/python2.7/site-packages/lxml/html/html5parser.pyt <module> sF
!+6$