/usr/lib/python3/dist-packages/lxml/html/__pycache__
Edit: /usr/lib/python3/dist-packages/lxml/html/__pycache__/html5parser.cpython-310.pyc (6393B)
o
;/b! @ sn d Z ddlZddlZddlmZ ddlmZ ddlm Z ddl
m Z m Z m
Z
zeZW n
ey7 eefZY nw zddlmZ W n eyO ddlmZ Y nw zddlmZ W n eyg ddlmZ Y nw G d d
d
eZzdd lmZ W n ey Y n w 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 @ e Zd ZdZdddZdS )r z*An html5lib HTML parser with lxml as tree.Fc K t j| f|td| d S N)stricttree) _HTMLParser__init__r selfr
kwargs r 7/usr/lib/python3/dist-packages/lxml/html/html5parser.pyr zHTMLParser.__init__NF__name__
__module__ __qualname____doc__r r r r r r r ) XHTMLParserc @ r
)r z+An html5lib XHTML Parser with lxml as tree.Fc K r r ) _XHTMLParserr r r r r r r * r zXHTMLParser.__init__Nr r r r r r r ' r r c C s( | |}|d ur |S | dt|f S )Nz{%s}%s)findr )r tagelemr r r _find_tag0 s
r# c C s^ t | ts td|du rt}i }|du r t | tr d}|dur$||d< |j| fi | S )z
Parse a whole document into a string.
If `guess_charset` is true, or if the input is not Unicode but a
byte string, the `chardet` library will perform charset guessing
on the string.
string requiredNT
useChardet)
isinstance_strings TypeError html_parserbytesparsegetroot)html
guess_charsetparseroptionsr r r document_fromstring7 s
r1 Fc C s t | ts td|du rt}i }|du r t | tr d}|dur$||d< |j| dfi |}|rKt |d trK|rK|d rHtd|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.
r$ NFr% divr zThere is leading text: %r) r& r' r( r) r*
parseFragmentstripr ParserError)r- no_leading_textr. r/ r0 childrenr r r fragments_fromstringO s$
r8 c C s t | ts tdt|}t| ||| d}|r;t |ts d}t|}|r9t |d tr4|d |_|d= || |S |sBt dt
|dkrMt d|d }|j ra|j rat 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.
r$ )r. r/ r6 r2 r zNo elements found zMultiple elements foundz Element followed by text: %rN)
r& r' r( boolr8 r textextendr r5 lentailr4 )r-
create_parentr. r/ accept_leading_textelementsnew_rootresultr r r fragment_fromstringq s4
rD c C s t | ts tdt| ||d}| dd }t |tr!|dd}| }|ds1|dr3|S t |d }t
|r>|S t |d
}t
|d kra|j rQ|j sa|d j
r]|d j
sa|d
S t|rjd|_|S d|_|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.
r$ )r/ r. N2 asciireplacez
r r! )r- r. r/ docstartrH rI r r r
fromstring s4
rR c C s~ |du rt }t| ts| }|du rd}nt| r#t| }|du r"d}n t| d}|du r.d}i }|r6||d< |j|fi |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).
NFTrbr% )r) r& r' _looks_like_urlr openr+ )filename_url_or_filer. r/ fpr0 r r r r+ s&
r+ c C s< t | d }|s
dS tjdkr |tjv r t|dkr dS dS )Nr Fwin32r9 T)r sysplatformstring
ascii_lettersr= )strschemer r r rT s
rT )NN)FNN)$r rY r[ html5libr r html5lib.treebuilders.etree_lxmlr lxmlr lxml.htmlr r r
basestringr' NameErrorr* r] urllib2r ImportErrorurllib.requestr urllib.parser r xhtml_parserr# r1 r8 rD rR r+ rT r) r r r r sT
"
,
6$