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
e�Zydd lmZ W n ek
�r Y nX G d d
� d
e�Ze� Zdd� Z d dd�Z d dd�Z d dd�Z d dd�Z d!dd�Z!dd � Z"e� Z#dS )"z?
An interface to html5lib that mimics the lxml.html interface.
� N)�
HTMLParser)� TreeBuilder)�etree)�Element�XHTML_NAMESPACE�_contains_block_level_tag)�urlopen)�urlparsec @ s e Zd ZdZddd�ZdS )r z*An html5lib HTML parser with lxml as tree.Fc K s t j| f|td�|�� d S )N)�strict�tree)� _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 ZdZddd�ZdS )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 �tag�elemr r r � _find_tag0 s
r c C sZ t | t�std��|dkr t}i }|dkr8t | t�r8d}|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_parser�bytes�parseZgetroot)�html�
guess_charset�parser�optionsr r r �document_fromstring7 s
r' Fc C s� t | t�std��|dkr t}i }|dkr8t | t�r8d}|dk rH||d< |j| df|�}|r�t |d t�r�|r�|d j� r�tjd|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
parseFragment�stripr � ParserError)r# �no_leading_textr$ r% r& Zchildrenr r r �fragments_fromstringO s"
r, c C s� t | t�std��t|�}t| ||| d�}|rvt |t�s>d}t|�}|rrt |d t�rh|d |_|d= |j|� |S |s�tj d��t
|�dkr�tj d��|d }|j r�|j j � r�tj 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 �text�extendr r* �len�tailr) )r# Z
create_parentr$ r% Zaccept_leading_text�elementsZnew_root�resultr r r �fragment_fromstringq s2
r5 c C s� t | t�std��t| ||d�}| dd� }t |t�rB|jdd�}|j� j� }|jd�sb|jd�rf|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|�r�d
|_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$ N�2 �ascii�replacez<htmlz <!doctype�head�bodyr- r r( �span���r< )r r r r' r! �decode�lstrip�lower�
startswithr r1 r/ r) r2 r r )r# r$ r% �doc�startr9 r: r r r �
fromstring� s*
rC c C sz |dkr t }t| t�s(| }|dkr\d}n4t| �rFt| �}|dkr\d}nt| d�}|dkr\d}i }|rl||d< |j|f|�S )a* 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).
NFT�rbr )r r r �_looks_like_urlr �openr" )Zfilename_url_or_filer$ r% �fpr& r r r r" � s"
r" c C s@ t | �d }|sdS tjdkr8|tjkr8t|�dkr8dS dS d S )Nr FZwin32r- T)r �sys�platform�stringZ
ascii_lettersr1 )�str�schemer r r rE � s
rE )NN)FNN)FNN)NN)NN)$r rH rJ Zhtml5libr r Z html5lib.treebuilders.etree_lxmlr Zlxmlr Z lxml.htmlr r r Z
basestringr � NameErrorr! rK Zurllib2r � ImportErrorZurllib.requestr Z urllib.parser r Z xhtml_parserr r' r, r5 rC r" rE r r r r r �<module> sF
!
+
6
$