....................................../////.===Shadow-Here===./////................................................ > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < > < ------------------------------------------------------------------------------------------------------------------- /////////////////////////////////////////////////////////////////////////////////////////////////////////////////// RIFF¤ WEBPVP8 ˜ ðÑ *ôô>‘HŸK¥¤"§£±¨àð enü¹%½_F‘åè¿2ºQú³íªú`N¿­3ÿƒügµJžaÿ¯ÿ°~¼ÎùnúîÞÖô•òíôÁÉß®Sm¥Ü/ ‡ó˜f£Ùà<˜„xëJ¢Ù€SO3x<ªÔ©4¿+ç¶A`q@Ì“Úñè™ÍÿJÌ´ª-˜ÆtÊÛL]Ïq*‘Ý”ì#ŸÌÏãY]@ê`¿ /ªfkØB4·®£ó z—Üw¥Pxù–ÞLШKÇN¾AkÙTf½è'‰g gÆv›Øuh~ a˜Z— ïj*á¥t d£“uÒ ¨`K˜¹ßþ]b>˜]_ÏÔ6W—è2r4x•íÖ…"ƒÖNîä!¦å Ú}ýxGøÌ —@ ;ÆÚŠ=ɾ1ý8lªË¥ô ^yf®Œ¢u&2©nÙÇ›ñÂñŒ³ aPo['½»øFùà­+4ê“$!lövlüÞ=;N®3ð‚õ›DÉKòÞ>ÄÍ ¥ˆuߤ#ˆ$6ù™¥îŠ‡y’ÍB¼ çxÛ;X"WL£R÷͝*ó-¶Zu}º.s¸sšXqù–DþÿvªhüïwyŸ ¯é³lÀ:KCûÄ£Ëá\…­ ~—ýóî ¼ûûÜTÓüÇy…ŽÆvc»¾×U ñ¸žþоP÷¦ó:Ò¨¨5;Ð#&#ÖúñläÿÁœ GxÉ­/ñ‡áQðìYÉtÒwŽ¼GÔ´zàÒò ð*ëzƒ•4~H]Ø‹f ñÓÈñ`NåWçs'ÆÏW^ø¹!XžµmQ5ÃËoLœÎ: ÞËÍ¥J ù…î èo£ßPÎñ¶ž8.Œ]ʵ~5›ÙË-ù*8ÙÖß±~ ©¹rÓê‚j¶d¸{^Q'˜±Crß ÚH—#¥¥QlÀ×ëã‡DÜ«èî þ&Çæžî;ŽÏºò6ÒLÃXy&ZŒ'j‚¢Ù€IßÚù+–MGi‰*jE€‘JcÜ ÓÌ EÏÚj]o˜ Þr <¾U ûŪæÍ/šÝH¥˜b”¼ ÁñßX GP›ï2›4WŠÏà×£…íÓk†¦H·ÅíMh–*nó÷à]ÁjCº€b7<ب‹¨5車bp2:Á[UªM„QŒçiNMa#<5›áËó¸HýÊ"…×Éw¹¦ì2º–x<›»a±¸3Weü®FÝ⑱ö–î–³|LPÈ~çð~Çå‡|º kD¢µÏàÆAI %1À% ¹Ò – ”ϝS¦‰4&¶£°à Öý”û_Ò Áw°A«Å€?mÇÛgHÉ/8)á¾ÛìáöŽP í¨PŸNÙµº¦‡§Ùš"ÿ«>+ªÕ`Ê÷‡‚ß Õû˜þãÇ-PÍ.¾XV‘€ dÜ"þ4¹ ±Oú‘©t¥¦FªÄÃÄ•b‚znýu½—#cDs˜ÃiÑOˆñ×QO=*IAÊ,¶ŽZƒ;‡wøXè%EÐk:F±Ú” .Ѽ+Áu&Ç`."pÈÉw o&¿dE6‘’EqTuK@Ì¥ã™À(Êk(h‰,H}RÀIXÛš3µ1©_OqÚÒJAñ$ÊÙÜ;D3çŒ[þùœh¬Ã³™ö6ç†NY".Ú‰ï[ªŸŒ '²Ð öø_¨ÂÉ9u鶳ÒŠõTàîMØ#û¯gN‡bÙ놚X„ö …ÉeüÌ^J ‹€.œ$Æ)βÄeæW#óüßĺŸ€ ÀzwV 9oä»f4V*uB «Ë†¹ì¯žR霓æHXa=&“I4K;¯ç‹h×·"UŠ~<•â•ªVêª&ÍSÃÆÅ?ÔqÎ*mTM ˜›µwêd#[C¡©§‘D<©àb†–ÁœøvH/,í:¯( ²£|4-„Æövv„Yͼ™^Á$ˆ„¢Û[6yB.åH*V¨æ?$=˜Ñ€•î¦ñ·­(VlŸ‘ nÀt8W÷´Bûba?q9ú¶Xƒl«ÿ\ù¶’þòUÐj/õ¢Ìµ³g$ƒÎR!¸»|Oߍë’BhîÚÑ¢ñåŒJ„®„£2Ð3•ô02Nt…!£Í]Ïc½Qÿ?ˆ<&ÃA¾Ú,JˆijÌ#5yz„‰Î|ÊŽ5QÏ:‹ÐaóVÔxW—CpeÏzÐïíçôÿÅ_[hãsÐ_/ŽTÝ?BîˆííV$<¿i>²F¬_Eß¿ †bÊŒº­ÿ®Z H“C}”¬,Mp ý/Bá£w>˜YV°aƒúh+cŠ- r/[%|üUMHäQ°X»|û/@|°¥Ð !BÔ Ç¢Ä©š+Õì D«7ìN¶ŽðÔ " ƶ’ÖçtA‰Û×}{tþz­¾GÍ›k¹OEJR$ Â׃ «ëÁ"oÉôž$oUK(Ä)Ãz³Ê-‹êN[Ò3Œñbï8P 4ƒ×q¢bo|?<ÛX¬òÄÍ°L–±›(™ûG?ýË©ÚÄ–ÂDØÐ_Ç¡ô ¾–ÄÏø ×e8Ë©$ÄF¹Å‹ì[©óìl:F¾f´‹‹Xì²ï®\¬ôùƒ ÿat¥óèÒùHß0äe‚;ü×h:ÆWðHž=Ã8骣"kœ'Y?³}Tûè€>?0l›e1Lòñ„aæKÆw…hÖŠùW…ÈÆÄ0ši·›[pcwËþñiêíY/~-Á5˜!¿†A›™Mÿþ(±“t@â“ö2­´TG5yé]çå僳 .·ÍïçÝ7UÚ±Ð/Nè»,_Ï ùdj7\ï Wì4›„»c¸àešg#ÒÊ⥭áØo5‘?ÌdÝô¯ ¹kzsƒ=´#ëÉK›Ø´±-¥eW?‡çßtòTã…$Ý+qÿ±ƒ÷_3Ô¥í÷:æ–ž<·Ö‡‰Å¢ š‡%Ô—utÌÈìðžgÖÀz²À—ï÷Óîäõ{K'´È÷³yaÏÁjƒô}ž§®æÊydÕÈë5¯èˆõvÕ©ã*çD„ “z„Ó‡^^xÂ3M§A´JG‚öï 3W'ˆ.OvXè¡ÊÕª?5º7†˜(˜Ç¶#çê’¶!ÌdZK§æ 0fãaN]òY³RV ™î$®K2R¨`W!1Ôó\;Ý ýB%qæK•&ÓÈe9È0êI±žeŸß -ú@žQr¦ ö4»M¼Áè¹µmw 9 EÆE_°2ó„ŸXKWÁ×Hóì^´²GѝF©óäR†¦‰ç"V»eØ<3ùd3ÿÚ¤Žú“Gi" —‘_ÙËÎ~Üö¯¥½Î»üŸEÚŽåmÞþí ;ÞólËΦMzA"Âf(´òá;Éï(/7½ûñÌ­cïÕçлþÝz¾-ÍvÑ“pH­–ðÓj$¸Äû¤‚‘ãUBË-n“2åPkS5&‹Â|+g^œ®Ì͆d!OïäîU«c;{Û!ÅŽ«ëZ9Ókóˆ]¯ƒ›né `ÇÒ+tÆš (ØKá¾—=3œ®•vuMñg²\ï Ec€ 05±d™‡×iÇ×›UúvÌ¢£Èþ¡ÕØô¶ßÎA"ß±#Ö²ˆÊŸ¦*Ä~ij|àø.-¼'»Ú¥£h ofº¦‡VsR=N½„Î v˜Z*SÌ{=jÑB‹tê…;’HžH¯8–îDù8ñ¢|Q•bÛçš–‹m³“ê¨ åÏ^m¬Žãþ©ïêO‡½6] µÆ„Ooòü ²x}N¦Ë3ïé¿»€›HA˜m%çÞ/¿í7Fø“‹léUk)É°Œµ8Q8›:ÀŠeT*šõ~ôڝG6 ¢}`ùH­–”¡k ‰P1>š†®9z11!X wKfmÁ¦xÑ,N1Q”–æB¶M…ÒÃv6SMˆhU¬ÊPŽï‘öj=·CŒ¯u¹ƒVIЃsx4’ömÛýc塶7ßŠß 57^\wÒÐÆ k§h,Œý î«q^R½3]J¸ÇðN ‚çU¬ôº^Áì} ³f©Õœ§ˆã:FÄÈ‚é(€™?àýÓüè1Gô£¼éj‚OÅñ  #>×—ßtà 0G¥Åa뀐kßhc™À_ÉñÞ#±)GD" YîäË-ÿÙ̪ ¹™a¯´¢E\ÝÒö‚;™„ë]_ p8‰o¡ñ+^÷ 3‘'dT4œŽ ðVë½° :¬víÑ«£tßÚS-3¶“þ2 †üüʨòrš¹M{É_¤`Û¨0ìjœøJ‡:÷ÃáZ˜†@GP&œÑDGÏs¡þ¦þDGú‘1Yá9Ôþ¼ ûø…§÷8&–ÜÑnÄ_m®^üÆ`;ÉVÁJ£?â€-ßê}suÍ2sõA NÌúA磸‘îÿÚ»ƒìö·á¿±tÑÐ"Tÿü˜[@/äj¬€uüªìù¥Ý˜á8Ý´sõj 8@rˆð äþZÇD®ÿUÏ2ùôõrBzÆÏÞž>Ì™xœ“ wiÎ×7_… ¸ \#€MɁV¶¥üÕÿPÔ9Z‡ø§É8#H:ƒ5ÀÝå9ÍIŒ5åKÙŠ÷qÄ>1AÈøžj"µÂд/ªnÀ qªã}"iŸBå˜ÓÛŽ¦…&ݧ;G@—³b¯“•"´4í¨ôM¨åñC‹ïùÉó¯ÓsSH2Ý@ßáM‡ˆKÀªÛUeø/4\gnm¥‹ŸŒ qÄ b9ÞwÒNÏ_4Ég³ú=܆‚´ •â¥õeíþkjz>éÚyU«Íӝ݃6"8/ø{=Ô¢»G¥ äUw°W«,ô—¿ãㆅү¢³xŠUû™yŒ (øSópÐ 9\åTâ»—*oG$/×ÍT†Y¿1¤Þ¢_‡ ¼ „±ÍçèSaÓ 3ÛMÁBkxs‰’R/¡¤ˆÙçª(*õ„üXÌ´ƒ E§´¬EF"Ù”R/ÐNyÆÂ^°?™6¡œïJ·±$§?º>ÖüœcNÌù¯G ‹ñ2ŠBB„^·úìaz¨k:#¨Æ¨8LÎõލ£^§S&cŒÐU€ü(‡F±Š¼&P>8ÙÁ ‰ p5?0ÊƃZl¸aô š¼¡}gÿ¶zÆC²¹¬ÎÖG*HB¡O<º2#ñŒAƒ–¡B˜´É$¥›É:FÀÔx¾u?XÜÏÓvN©RS{2ʈãk9rmP¼Qq̳ è¼ÐFׄ^¡Öì fE“F4A…!ì/…¦Lƒ… … $%´¾yã@CI¬ á—3PþBÏNÿ<ý°4Ü ËÃ#ØÍ~âW«rEñw‹eùMMHß²`¬Öó½íf³:‹k˜¯÷}Z!ã¿<¥,\#öµÀ¯aÒNÆIé,Ћ–lŽ#Àæ9ÀÒS·I’½-Ïp Äz¤Š Â* ­íÄ9­< h>׍3ZkËU¹§˜ŒŠ±f­’¤º³Q ÏB?‹#µíÃ¥®@(Gs«†vI¥Mµ‹Á©e~2ú³ÁP4ìÕi‚²Ê^ö@-DþÓàlÜOÍ]n"µã:žpsŽ¢:! Aõ.ç~ÓBûH÷JCÌ]õVƒd «ú´QÙEA–¯¯Œ!.ˆˆëQ±ù œ·Ì!Õâ )ùL„ÅÀlÚè5@B…o´Æ¸XÓ&Û…O«˜”_#‡ƒ„ûÈt!¤ÁÏ›ÎÝŠ?c9 â\>lÓÁVÄÑ™£eØY]:fÝ–—ù+p{™ðè û³”g±OƒÚSù£áÁÊ„ä,ï7š²G ÕÌBk)~ÑiCµ|h#u¤¶îK¨² #²vݯGãeÖ϶ú…¾múÀ¶þÔñ‚Š9'^($¤§ò “š½{éúp÷J›ušS¹áªCÂubÃH9™D™/ZöØÁ‡¦ÝÙŸ·kð*_”.C‹{áXó€‡c¡c€§/šò/&éš÷,àéJþ‰X›fµ“C¨œ®r¬"kL‰Â_q…Z–.ÉL~O µ›zn‚¹À¦Öª7\àHµšÖ %»ÇníV[¥*Õ;ƒ#½¾HK-ÖIÊdÏEÚ#=o÷Óò³´Š: Ç?{¾+9›–‘OEáU·S€˜j"ÄaÜ ŒÛWt› á–c#a»pÔZÞdŽtWê=9éöÊ¢µ~ ë ;Öe‡Œ®:bî3±ýê¢wà¼îpêñ¹¾4 zc¾ðÖÿzdêŒÑÒŝÀ‰s6¤í³ÎÙB¿OZ”+F¤á‡3@Ñëäg©·Ž ˆèª<ù@É{&S„œÕúÀA)‰h:YÀ5^ÂÓŒ°õäU\ ùËÍû#²?Xe¬tu‰^zÒÔãë¼ÛWtEtû …‚g¶Úüâî*moGè¨7%u!]PhÏd™Ý%Îx: VÒ¦ôÊD3ÀŽKÛËãvÆî…N¯ä>Eró–ð`5 Œ%u5XkñÌ*NU%¶áœÊ:Qÿú»“úzyÏ6å-၇¾ ´ ÒÊ]y žO‘w2Äøæ…H’²f±ÎÇ.ª|¥'gîV•Ü .̘¯€šòü¤U~Ù†*¢!?ò wý,}´°ÔÞnïoKq5µb!áÓ3"vAßH¡³¡·G(ÐÎ0Îò¼MG!/ài®@—¬04*`…«é8ªøøló“ˆÊ”èù¤…ßÊoÿé'ËuÌÖ5×È¡§ˆˆfŽë9}hìâ_!!¯  B&Ëö¶‰ÀAÙNVŸ Wh›¸®XÑJì¨ú“¿÷3uj²˜¨ÍÎìë±aúŠÝå¯ð*Ó¨ôJ“yºØ)m°WýOè68†ŸÏ2—‰Ïüꪫٚ¥‹l1 ø ÏÄFjêµvÌbü¦èÝx:X±¢H=MÐß—,ˆÉÇ´(9ú¾^ÅÚ4¿m‡$âX‘å%(AlZo@½¨UOÌÕ”1ø¸jÎÀÃÃ_ µ‘Ü.œº¦Ut: Æï’!=¯uwû#,“pþÇúŒø(é@?³ü¥‘Mo §—s@Œ#)§ŒùkL}NOÆêA›¸~r½¼ÙA—HJ«eˆÖ´*¡ÓpÌŸö.m<-"³ûÈ$¬_6­åf£ïÚâj1y§ÕJ½@dÞÁr&Í\Z%D£Íñ·AZ Û³øüd/ªAi†/Й~  ‡âĮҮÏh§°b—›Û«mJžòG'[ÈYýŒ¦9psl ýÁ ®±f¦x,‰½tN ‚Xª9 ÙÖH.«Lo0×?͹m¡å†Ѽ+›2ƒF ±Ê8 7Hցϓ²Æ–m9…òŸï]Â1äN†VLâCˆU .ÿ‰Ts +ÅÎx(%¦u]6AF Š ØF鈄‘ |¢¶c±soŒ/t[a¾–û:s·`i햍ê›ËchÈ…8ßÀUÜewŒðNOƒõD%q#éû\9¤x¹&UE×G¥ Í—™$ð E6-‡¼!ýpãÔM˜ Âsìe¯ñµK¢Ç¡ùôléœ4Ö£”À Š®Ðc ^¨À}ÙËŸ§›ºê{ÊuÉC ×Sr€¤’fÉ*j!úÓ’Gsùìoîßîn%ò· àc Wp÷$¨˜)û»H ×8ŽÒ€Zj¤3ÀÙºY'Ql¦py{-6íÔCeiØp‘‡XÊîÆUߢ܂ž£Xé¼Y8þ©ëgñß}é.ÎógÒ„ÃØËø¯»™§Xýy M%@NŠ À(~áÐvu7&•,Ù˜ó€uP‡^^®=_E„jt’ 403WebShell
403Webshell
Server IP : 198.54.126.4  /  Your IP : 216.73.216.153
Web Server : Apache
System : Linux host55.registrar-servers.com 4.18.0-513.18.1.lve.2.el8.x86_64 #1 SMP Sat Mar 30 15:36:11 UTC 2024 x86_64
User : aeaw ( 7508)
PHP Version : 8.1.33
Disable Function : NONE
MySQL : OFF  |  cURL : ON  |  WGET : ON  |  Perl : ON  |  Python : ON  |  Sudo : OFF  |  Pkexec : OFF
Directory :  /opt/hc_python/lib64/python3.12/site-packages/lxml/html/

Upload File :
current_dir [ Writeable ] document_root [ Writeable ]

 

Command :

[ Back ]     

Current File : /opt/hc_python/lib64/python3.12/site-packages/lxml/html/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()

Youez - 2016 - github.com/yon3zu
LinuXploit