PNG  IHDRxsBIT|d pHYs+tEXtSoftwarewww.inkscape.org<,tEXtComment File Manager

File Manager

Path: /opt/cloudlinux/venv/lib/python3.11/site-packages/lxml/html/

Viewing File: html5parser.py

"""
An interface to html5lib that mimics the lxml.html interface.
"""
import sys
import string

from html5lib import HTMLParser as _HTMLParser
from html5lib.treebuilders.etree_lxml import TreeBuilder
from lxml import etree
from lxml.html import Element, XHTML_NAMESPACE, _contains_block_level_tag

# python3 compatibility
try:
    _strings = basestring
except NameError:
    _strings = (bytes, str)
try:
    from urllib2 import urlopen
except ImportError:
    from urllib.request import urlopen
try:
    from urlparse import urlparse
except ImportError:
    from urllib.parse import urlparse


class HTMLParser(_HTMLParser):
    """An html5lib HTML parser with lxml as tree."""

    def __init__(self, strict=False, **kwargs):
        _HTMLParser.__init__(self, strict=strict, tree=TreeBuilder, **kwargs)


try:
    from html5lib import XHTMLParser as _XHTMLParser
except ImportError:
    pass
else:
    class XHTMLParser(_XHTMLParser):
        """An html5lib XHTML Parser with lxml as tree."""

        def __init__(self, strict=False, **kwargs):
            _XHTMLParser.__init__(self, strict=strict, tree=TreeBuilder, **kwargs)

    xhtml_parser = XHTMLParser()


def _find_tag(tree, tag):
    elem = tree.find(tag)
    if elem is not None:
        return elem
    return tree.find('{%s}%s' % (XHTML_NAMESPACE, tag))


def document_fromstring(html, guess_charset=None, parser=None):
    """
    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.
    """
    if not isinstance(html, _strings):
        raise TypeError('string required')

    if parser is None:
        parser = html_parser

    options = {}
    if guess_charset is None and isinstance(html, bytes):
        # html5lib does not accept useChardet as an argument, if it
        # detected the html argument would produce unicode objects.
        guess_charset = True
    if guess_charset is not None:
        options['useChardet'] = guess_charset
    return parser.parse(html, **options).getroot()


def fragments_fromstring(html, no_leading_text=False,
                         guess_charset=None, parser=None):
    """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.
    """
    if not isinstance(html, _strings):
        raise TypeError('string required')

    if parser is None:
        parser = html_parser

    options = {}
    if guess_charset is None and isinstance(html, bytes):
        # html5lib does not accept useChardet as an argument, if it
        # detected the html argument would produce unicode objects.
        guess_charset = False
    if guess_charset is not None:
        options['useChardet'] = guess_charset
    children = parser.parseFragment(html, 'div', **options)
    if children and isinstance(children[0], _strings):
        if no_leading_text:
            if children[0].strip():
                raise etree.ParserError('There is leading text: %r' %
                                        children[0])
            del children[0]
    return children


def fragment_fromstring(html, create_parent=False,
                        guess_charset=None, parser=None):
    """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.
    """
    if not isinstance(html, _strings):
        raise TypeError('string required')

    accept_leading_text = bool(create_parent)

    elements = fragments_fromstring(
        html, guess_charset=guess_charset, parser=parser,
        no_leading_text=not accept_leading_text)

    if create_parent:
        if not isinstance(create_parent, _strings):
            create_parent = 'div'
        new_root = Element(create_parent)
        if elements:
            if isinstance(elements[0], _strings):
                new_root.text = elements[0]
                del elements[0]
            new_root.extend(elements)
        return new_root

    if not elements:
        raise etree.ParserError('No elements found')
    if len(elements) > 1:
        raise etree.ParserError('Multiple elements found')
    result = elements[0]
    if result.tail and result.tail.strip():
        raise etree.ParserError('Element followed by text: %r' % result.tail)
    result.tail = None
    return result


def fromstring(html, guess_charset=None, parser=None):
    """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.
    """
    if not isinstance(html, _strings):
        raise TypeError('string required')
    doc = document_fromstring(html, parser=parser,
                              guess_charset=guess_charset)

    # document starts with doctype or <html>, full document!
    start = html[:50]
    if isinstance(start, bytes):
        # Allow text comparison in python3.
        # Decode as ascii, that also covers latin-1 and utf-8 for the
        # characters we need.
        start = start.decode('ascii', 'replace')

    start = start.lstrip().lower()
    if start.startswith('<html') or start.startswith('<!doctype'):
        return doc

    head = _find_tag(doc, 'head')

    # if the head is not empty we have a full document
    if len(head):
        return doc

    body = _find_tag(doc, 'body')

    # The body has just one element, so it was probably a single
    # element passed in
    if (len(body) == 1 and (not body.text or not body.text.strip())
        and (not body[-1].tail or not body[-1].tail.strip())):
        return body[0]

    # Now we have a body which represents a bunch of tags which have the
    # content that was passed in.  We will create a fake container, which
    # is the body tag, except <body> implies too much structure.
    if _contains_block_level_tag(body):
        body.tag = 'div'
    else:
        body.tag = 'span'
    return body


def parse(filename_url_or_file, guess_charset=None, parser=None):
    """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).
    """
    if parser is None:
        parser = html_parser
    if not isinstance(filename_url_or_file, _strings):
        fp = filename_url_or_file
        if guess_charset is None:
            # assume that file-like objects return Unicode more often than bytes
            guess_charset = False
    elif _looks_like_url(filename_url_or_file):
        fp = urlopen(filename_url_or_file)
        if guess_charset is None:
            # assume that URLs return bytes
            guess_charset = True
    else:
        fp = open(filename_url_or_file, 'rb')
        if guess_charset is None:
            guess_charset = True

    options = {}
    # html5lib does not accept useChardet as an argument, if it
    # detected the html argument would produce unicode objects.
    if guess_charset:
        options['useChardet'] = guess_charset
    return parser.parse(fp, **options)


def _looks_like_url(str):
    scheme = urlparse(str)[0]
    if not scheme:
        return False
    elif (sys.platform == 'win32' and
            scheme in string.ascii_letters
            and len(scheme) == 1):
        # looks like a 'normal' absolute path
        return False
    else:
        return True


html_parser = HTMLParser()
b IDATxytVսϓ22 A@IR :hCiZ[v*E:WũZA ^dQeQ @ !jZ'>gsV仿$|?g)&x-EIENT ;@xT.i%-X}SvS5.r/UHz^_$-W"w)Ɗ/@Z &IoX P$K}JzX:;` &, ŋui,e6mX ԵrKb1ԗ)DADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADADA݀!I*]R;I2$eZ#ORZSrr6mteffu*((Pu'v{DIߔ4^pIm'77WEEE;vƎ4-$]'RI{\I&G :IHJ DWBB=\WR޽m o$K(V9ABB.}jѢv`^?IOȅ} ڶmG}T#FJ`56$-ھ}FI&v;0(h;Б38CӧOWf!;A i:F_m9s&|q%=#wZprrrla A &P\\СC[A#! {olF} `E2}MK/vV)i{4BffV\|ۭX`b@kɶ@%i$K z5zhmX[IXZ` 'b%$r5M4º/l ԃߖxhʔ)[@=} K6IM}^5k㏷݆z ΗÿO:gdGBmyT/@+Vɶ纽z񕏵l.y޴it뭷zV0[Y^>Wsqs}\/@$(T7f.InݺiR$푔n.~?H))\ZRW'Mo~v Ov6oԃxz! S,&xm/yɞԟ?'uaSѽb,8GלKboi&3t7Y,)JJ c[nzӳdE&KsZLӄ I?@&%ӟ۶mSMMњ0iؐSZ,|J+N ~,0A0!5%Q-YQQa3}$_vVrf9f?S8`zDADADADADADADADADAdqP,تmMmg1V?rSI꒟]u|l RCyEf٢9 jURbztѰ!m5~tGj2DhG*{H9)꒟ר3:(+3\?/;TUݭʴ~S6lڧUJ*i$d(#=Yݺd{,p|3B))q:vN0Y.jkק6;SɶVzHJJЀ-utѹսk>QUU\޲~]fFnK?&ߡ5b=z9)^|u_k-[y%ZNU6 7Mi:]ۦtk[n X(e6Bb."8cۭ|~teuuw|ήI-5"~Uk;ZicEmN/:]M> cQ^uiƞ??Ңpc#TUU3UakNwA`:Y_V-8.KKfRitv޲* 9S6ֿj,ՃNOMߤ]z^fOh|<>@Å5 _/Iu?{SY4hK/2]4%it5q]GGe2%iR| W&f*^]??vq[LgE_3f}Fxu~}qd-ږFxu~I N>\;͗O֊:̗WJ@BhW=y|GgwܷH_NY?)Tdi'?խwhlmQi !SUUsw4kӺe4rfxu-[nHtMFj}H_u~w>)oV}(T'ebʒv3_[+vn@Ȭ\S}ot}w=kHFnxg S 0eޢm~l}uqZfFoZuuEg `zt~? b;t%>WTkķh[2eG8LIWx,^\thrl^Ϊ{=dž<}qV@ ⠨Wy^LF_>0UkDuʫuCs$)Iv:IK;6ֲ4{^6եm+l3>݆uM 9u?>Zc }g~qhKwڭeFMM~pМuqǿz6Tb@8@Y|jx](^]gf}M"tG -w.@vOqh~/HII`S[l.6nØXL9vUcOoB\xoǤ'T&IǍQw_wpv[kmO{w~>#=P1Pɞa-we:iǏlHo׈꒟f9SzH?+shk%Fs:qVhqY`jvO'ρ?PyX3lх]˾uV{ݞ]1,MzYNW~̈́ joYn}ȚF߾׮mS]F z+EDxm/d{F{-W-4wY듏:??_gPf ^3ecg ҵs8R2מz@TANGj)}CNi/R~}c:5{!ZHӋӾ6}T]G]7W6^n 9*,YqOZj:P?Q DFL|?-^.Ɵ7}fFh׶xe2Pscz1&5\cn[=Vn[ĶE鎀uˌd3GII k;lNmشOuuRVfBE]ۣeӶu :X-[(er4~LHi6:Ѻ@ԅrST0trk%$Č0ez" *z"T/X9|8.C5Feg}CQ%͞ˣJvL/?j^h&9xF`њZ(&yF&Iݻfg#W;3^{Wo^4'vV[[K';+mӍִ]AC@W?1^{එyh +^]fm~iԵ]AB@WTk̏t uR?l.OIHiYyԶ]Aˀ7c:q}ힽaf6Z~қm(+sK4{^6}T*UUu]n.:kx{:2 _m=sAߤU@?Z-Vކеz왍Nэ{|5 pڶn b p-@sPg]0G7fy-M{GCF'%{4`=$-Ge\ eU:m+Zt'WjO!OAF@ik&t݆ϥ_ e}=]"Wz_.͜E3leWFih|t-wZۍ-uw=6YN{6|} |*={Ѽn.S.z1zjۻTH]흾 DuDvmvK.`V]yY~sI@t?/ϓ. m&["+P?MzovVЫG3-GRR[(!!\_,^%?v@ҵő m`Y)tem8GMx.))A]Y i`ViW`?^~!S#^+ѽGZj?Vģ0.))A꨷lzL*]OXrY`DBBLOj{-MH'ii-ϰ ok7^ )쭡b]UXSְmռY|5*cֽk0B7镹%ڽP#8nȎq}mJr23_>lE5$iwui+ H~F`IjƵ@q \ @#qG0".0" l`„.0! ,AQHN6qzkKJ#o;`Xv2>,tێJJ7Z/*A .@fفjMzkg @TvZH3Zxu6Ra'%O?/dQ5xYkU]Rֽkق@DaS^RSּ5|BeHNN͘p HvcYcC5:y #`οb;z2.!kr}gUWkyZn=f Pvsn3p~;4p˚=ē~NmI] ¾ 0lH[_L hsh_ғߤc_њec)g7VIZ5yrgk̞W#IjӪv>՞y睝M8[|]\շ8M6%|@PZڨI-m>=k='aiRo-x?>Q.}`Ȏ:Wsmu u > .@,&;+!!˱tﭧDQwRW\vF\~Q7>spYw$%A~;~}6¾ g&if_=j,v+UL1(tWake:@Ș>j$Gq2t7S?vL|]u/ .(0E6Mk6hiۺzښOrifޱxm/Gx> Lal%%~{lBsR4*}{0Z/tNIɚpV^#Lf:u@k#RSu =S^ZyuR/.@n&΃z~B=0eg뺆#,Þ[B/?H uUf7y Wy}Bwegל`Wh(||`l`.;Ws?V@"c:iɍL֯PGv6zctM̠':wuW;d=;EveD}9J@B(0iհ bvP1{\P&G7D޴Iy_$-Qjm~Yrr&]CDv%bh|Yzni_ˆR;kg}nJOIIwyuL}{ЌNj}:+3Y?:WJ/N+Rzd=hb;dj͒suݔ@NKMԄ jqzC5@y°hL m;*5ezᕏ=ep XL n?מ:r`۵tŤZ|1v`V뽧_csج'ߤ%oTuumk%%%h)uy]Nk[n 'b2 l.=͜E%gf$[c;s:V-͞WߤWh-j7]4=F-X]>ZLSi[Y*We;Zan(ӇW|e(HNNP5[= r4tP &0<pc#`vTNV GFqvTi*Tyam$ߏWyE*VJKMTfFw>'$-ؽ.Ho.8c"@DADADADADADADADADA~j*֘,N;Pi3599h=goضLgiJ5փy~}&Zd9p֚ e:|hL``b/d9p? fgg+%%hMgXosج, ΩOl0Zh=xdjLmhݻoO[g_l,8a]٭+ӧ0$I]c]:粹:Teꢢ"5a^Kgh,&= =՟^߶“ߢE ܹS J}I%:8 IDAT~,9/ʃPW'Mo}zNƍ쨓zPbNZ~^z=4mswg;5 Y~SVMRXUյڱRf?s:w ;6H:ºi5-maM&O3;1IKeamZh͛7+##v+c ~u~ca]GnF'ټL~PPPbn voC4R,ӟgg %hq}@#M4IÇ Oy^xMZx ) yOw@HkN˖-Sǎmb]X@n+i͖!++K3gd\$mt$^YfJ\8PRF)77Wא!Cl$i:@@_oG I{$# 8磌ŋ91A (Im7֭>}ߴJq7ޗt^ -[ԩSj*}%]&' -ɓ'ꫯVzzvB#;a 7@GxI{j޼ƌ.LÇWBB7`O"I$/@R @eee@۷>}0,ɒ2$53Xs|cS~rpTYYY} kHc %&k.], @ADADADADADADADADA@lT<%''*Lo^={رc5h %$+CnܸQ3fҥK}vUVVs9G R,_{xˇ3o߾;TTTd}馛]uuuG~iԩ@4bnvmvfϞ /Peeeq}}za I~,誫{UWW뮻}_~YƍSMMMYχ֝waw\ďcxꩧtEƍկ_?۷5@u?1kNׯWzz/wy>}zj3 k(ٺuq_Zvf̘:~ ABQ&r|!%KҥKgԞ={<_X-z !CyFUUz~ ABQIIIjݺW$UXXDٳZ~ ABQƍecW$<(~<RSSvZujjjԧOZQu@4 8m&&&jԩg$ď1h ͟?_{768@g =@`)))5o6m3)ѣƌJ;wҿUTT /KZR{~a=@0o<*狔iFɶ[ˎ;T]]OX@?K.ۈxN pppppppppppppppppPfl߾] ,{ァk۶mڿo5BTӦMӴiӴ|r DB2e|An!Dy'tkΝ[A $***t5' "!駟oaDnΝ:t֭[gDШQ06qD;@ x M6v(PiizmZ4ew"@̴ixf [~-Fٱc&IZ2|n!?$@{[HTɏ#@hȎI# _m(F /6Z3z'\r,r!;w2Z3j=~GY7"I$iI.p_"?pN`y DD?: _  Gÿab7J !Bx@0 Bo cG@`1C[@0G @`0C_u V1 aCX>W ` | `!<S `"<. `#c`?cAC4 ?c p#~@0?:08&_MQ1J h#?/`7;I  q 7a wQ A 1 Hp !#<8/#@1Ul7=S=K.4Z?E_$i@!1!E4?`P_  @Bă10#: "aU,xbFY1 [n|n #'vEH:`xb #vD4Y hi.i&EΖv#O H4IŶ}:Ikh @tZRF#(tXҙzZ ?I3l7q@õ|ۍ1,GpuY Ꮿ@hJv#xxk$ v#9 5 }_$c S#=+"K{F*m7`#%H:NRSp6I?sIՖ{Ap$I$I:QRv2$Z @UJ*$]<FO4IENDB`