Warning: session_start(): Session cannot be started after headers have already been sent in /home/tvrreohg/public_html/manga.php on line 13
3
'Y! $ @ sp d Z ddlZddlZddlmZ ddlmZ ddlm Z ddl
m Z m Z m
Z
yeZW n ek
rp eefZY nX yddlmZ W n ek
r ddlmZ Y nX yddlmZ W n ek
r ddlmZ Y nX G d d
d
eZydd lmZ W n ek
r Y nX G d d
d
eZe Zdd Z d ddZ d ddZ d ddZ d ddZ d!ddZ!dd Z"e Z#dS )"z?
An interface to html5lib that mimics the lxml.html interface.
N)
HTMLParser) TreeBuilder)etree)ElementXHTML_NAMESPACE_contains_block_level_tag)urlopen)urlparsec @ s e Zd ZdZdddZdS )r z*An html5lib HTML parser with lxml as tree.Fc K s t j| f|td| d S )N)stricttree) _HTMLParser__init__r )selfr
kwargs r #/usr/lib64/python3.6/html5parser.pyr
s zHTMLParser.__init__N)F)__name__
__module__ __qualname____doc__r
r r r r r s r ) XHTMLParserc @ s e Zd ZdZdddZdS )r z+An html5lib XHTML Parser with lxml as tree.Fc K s t j| f|td| d S )N)r
r ) _XHTMLParserr
r )r r
r r r r r
* s zXHTMLParser.__init__N)F)r r r r r
r r r r r ' s r c C s( | j |}|d k r|S | j dt|f S )Nz{%s}%s)findr )r tagelemr r r _find_tag0 s
r c C sZ t | tstd|dkr t}i }|dkr8t | tr8d}|dk rH||d< |j| f|j S )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_charsetparseroptionsr r r document_fromstring7 s
r' Fc C s t | tstd|dkr t}i }|dkr8t | tr8d}|dk rH||d< |j| df|}|rt |d tr|r|d j rtjd|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 requiredNFr divr zThere is leading text: %r) r r r r r! Z
parseFragmentstripr ParserError)r# no_leading_textr$ r% r& Zchildrenr r r fragments_fromstringO s"
r, c C s t | tstdt|}t| ||| d}|rvt |ts>d}t|}|rrt |d trh|d |_|d= |j| |S |stj dt
|dkrtj d|d }|j r|j j rtj d|j d |_ |S )
a 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.
zstring required)r$ r% r+ r( r zNo elements found zMultiple elements foundz Element followed by text: %rN)
r r r boolr, r textextendr r* lentailr) )r# Z
create_parentr$ r% Zaccept_leading_textelementsZnew_rootresultr r r fragment_fromstringq s2
r5 c C s t | tstdt| ||d}| dd }t |trB|jdd}|j j }|jdsb|jdrf|S t |d }t
|r||S t |d
}t
|d kr|j s|j j r|d j
s|d j
j r|d S t|rd
|_nd|_|S )a 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.
zstring required)r% r$ N2 asciireplacez sF
!
+
6
$