Advertisement
Guest User

% or & in host

a guest
Jan 13th, 2014
958
0
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 12.72 KB | None | 0 0
  1. data set: webdevdata.org-2013-09-01-201332
  2.  
  3. $ find ./ -name "*.html.txt" -print0 | xargs -0 -n1 -P8 grep -Eio "<[^>]+\s(href|src)\s*=\s*[\"']?https?://[^ \"'/?#]*[%&][^>]+>"
  4. <link rel="alternate" media="only screen and (max-width: 640px)" href="http://x.xzone.vn&lt;%= Request.RawUrl %>
  5. <link rel="alternate" media="handheld" href="http://m.snapdeal.com%2F"/>
  6. <a href='http://%/zzrglgc9googleab' rel='external nofollow' class='url'>
  7. <a href='http://%/zzrglgc9googleab' rel='external nofollow' class='url'>
  8. <script src=http://ad.&#111;x11.com/dj.asp?jiangxi|ganzhou>
  9. <a href="http://www.yujinrobot.xn--com%29%2027%20-gx73d2d/" target="_blank">
  10. <link rel="SHORTCUT ICON" href="http://&lt;%= ConfigurationManager.AppSettings[Resources.WebConfigItems.HomePath] %>
  11. <a href="http://www.apollointerior&nbsp;&nbsp;<img src='./images/new_star2.gif' border='0'>
  12. <a href="http://www.apollointerior&nbsp;&nbsp;<img src='./images/new_star2.gif' border='0'>
  13. <a href="http://www.fresherventure.net%20/">
  14. <a href=http://www.bdm.com.pl>Dom&nbsp;Maklerski&nbsp;BDM&nbsp;SA</a>
  15. <a href="http://www.ganaderianazarioiba&#241;ez.es/" target="_blanck">
  16. <a href="http://&#119;&#119;&#119;&#46;&#118;&#98;&#115;&#111;&#112;&#111;&#114;&#116;&#101;&#46;&#99;&#111;&#109;&#47;" target="_blank">
  17. <a href="http://&#119;&#119;&#119;&#46;&#118;&#98;&#115;&#111;&#112;&#111;&#114;&#116;&#101;&#46;&#99;&#111;&#109;&#47;&#102;&#111;&#114;&#111;&#115;&#47;" target="_blank">
  18. <a href="http://happyhours.<%= market.domain %>
  19. <a href="http://&#91;URL]https://www.facebook.com/thematsmith&#91;/URL]" target="_blank">
  20. <area shape="RECT" coords="1,1,61,51" href="http://www.aminparsian.com%20" target="_blank">
  21. <area shape="RECT" coords="69,1,148,50" href="http://www.pec.ir%20" target="_blank">
  22. <area shape="RECT" coords="163,1,213,50" href="http://www.parsianbroker.com%20" target="_blank">
  23. <area shape="RECT" coords="22,0,73,46" href="http://www.aminparsian.com%20" target="_blank">
  24. <area shape="RECT" coords="98,0,143,47" href="http://www.parsian-invest.com%20" target="_blank">
  25. <area shape="RECT" coords="180,1,254,46" href="http://www.pec.ir%20" target="_blank">
  26. <area shape="RECT" coords="376,2,421,47" href="http://www.parsian-lotus-hotels.com%20" target="_blank">
  27. <area shape="RECT" coords="457,2,503,47" href="http://www.parsianbroker.com%20" target="_parent">
  28. <a href="http://www.escort-girl-belgique.com%20" title="Escort Girl Belgique" target="_blank">
  29. <a href="http://www.camdirect.be%20" title="Cam Direct Belgique" target="_blank">
  30. <img src="http://www.spvisa-translati&#111;ns" width="50" height="50"/>
  31. <a href='http://Dr.Oz&#039;s' rel='external nofollow' class='url'>
  32. <a href="http://SimplePleasures~~Photography&#038;More">
  33. <a href="http://www.charlotteolympia.com%20" target="_blank">
  34. <a href="http://happyhours.<%= market.domain %>
  35. <a title="Free Email" name="om_hnav_sec8_link7" class="icid-cagnavbar_freeemail lnid-sec8_lnk7" href="http://mail.aol.ca&nbsp;&nbsp;&nbsp;">
  36. <a em="" frameborder="no" height="166" href="http://&lt;iframe width=" scrolling="no" src="https://w.soundcloud.com/player/?url=http%3A%2F%2Fapi.soundcloud.com%2Ftracks%2F107859978" target="_blank">
  37. <a class=" link" title="http://открыточка.рф" href="http://%D0%BE%D1%82%D0%BA%D1%80%D1%8B%D1%82%D0%BE%D1%87%D0%BA%D0%B0.%D1%80%D1%84" target="_blank">
  38. <a href="http://happyhours.<%= market.domain %>
  39. <a href="http://<%= utils.foreignLink( model.get('webSite')) %>
  40. <a class="btn btn-inverse btn-large" href="http://&#10;&#9;&#9;&#9;&#9;&#9;&#9;sobipro.sobitemplates.com/sobipro-templates/st-gallery-app">
  41. <a class="btn btn-inverse btn-large" href="http://&#10;&#9;&#9;&#9;&#9;&#9;&#9;sobipro.sobitemplates.com/st-resorts-template">
  42. <a class="btn btn-inverse btn-large" href="http://&#10;&#9;&#9;&#9;&#9;&#9;&#9;sobipro.sobitemplates.com/sp-biztabs-template">
  43. <a href="http://&lt;div&gt;">
  44. <img alt="Citibank" src="https://online.citibank.com&#x2f;GFC&#x2f;branding&#x2f;img&#x2f;citilogo_branding_60x35.png"/>
  45. <a class="article_title" href="http://<%=articles[i].article_host%><%=articles[i].article_url%>
  46. <a class="article_title" href="http://<%=articles[i].article_host%><%=articles[i].article_url%>
  47. <a class="article_title" href="http://<%=articles[i].article_host%><%=articles[i].article_url%>
  48. <a href="http://<%=articles[i].article_host%><%=articles[i].article_url%>
  49. <a class="article_title" href="http://<%=articles[i].article_host%><%=articles[i].article_url%>
  50. <a href="http://happyhours.<%= market.domain %>
  51. <a href="http://happyhours.<%= market.domain %>
  52. <a href="http://www.pe&ntilde;arol.org" target="_blank">
  53. <a href='http://kjg;t&#039;ur' rel='external nofollow' class='url'>
  54. <a class="headline-link" href="http://omniclimate.wordpress.com%20">
  55. <a href="http://www.mondocoolcast.com%3C/A%3EMondo%20Cool%20Cast%3C/A%3E%3Cbr%3E%3Ca%20href=">
  56. <img src="https://&#99;&#104;&#97;&#109;&#98;&#101;&#114;&#111;&#102;&#99;&#111;&#109;&#109;&#101;&#114;&#99;&#101;&#45;&#111;&#110;&#116;&#104;&#101;&#119;&#101;&#98;&#46;&#99;&#111;&#109;&#47;&#109;&#108;&#47;&#71;&#108;&#97;&#115;&#115;&#73;&#109;&#97;&#103;&#101;&#46;&#103;&#105;&#102;" alt="Chamber of Commerce - on the Web logo" title="Member: Chamber of Commerce - on the Web" width="100" height="100" border="0" />
  57. <a href="http://happyhours.<%= market.domain %>
  58. <a href="http://www.publicidadeimobiliaria.com%20">
  59. <a onclick="return nrgCount(event, 2502 , 'http://horoscopes.alternativli.co.il%2Fv%2F%D7%A7%D7%91%D7%9C%D7%94%2F4127-%D7%AA%D7%95%D7%A8%D7%AA-%D7%94%D7%A7%D7%91%D7%9C%D7%94-19-%D7%97%D7%95%D7%A9-%D7%94%D7%90%D7%95%D7%A8-2.html');return false;" href="http://horoscopes.alternativli.co.il%2Fv%2F%D7%A7%D7%91%D7%9C%D7%94%2F4127-%D7%AA%D7%95%D7%A8%D7%AA-%D7%94%D7%A7%D7%91%D7%9C%D7%94-19-%D7%97%D7%95%D7%A9-%D7%94%D7%90%D7%95%D7%A8-2.html" target="_self">
  60. <a onClick="_gaq.push(['gaAW._trackEvent', 'Header-Dropdown', 'Click-ViewProfile', 'View Profile']);" href="https://<%= ProfileUrl %>
  61. <a href="http://www.szmexpo.com%20" target="_blank">
  62. <a href=http://crazymovies.in>&copy; 2013 CrazyMovies.In </a>
  63. <img alt="Citibank" src="https://online.citibank.com&#x2f;GFC&#x2f;branding&#x2f;img&#x2f;citilogo_branding_60x35.png"/>
  64. <a title="www.lookingtoday.com​" href="http://www.lookingtoday.com%E2%80%8B">
  65. <a href="http://&#91;url=http://www.discounttiredirect.com/direct/findPromotions.do?pgid=809" target="_blank">
  66. <a href="http://&quot;http://forums.civfanatics.com/showthread.php?t=385009" target="_blank">
  67. <a href="http://&quot;http://forums.civfanatics.com/showpost.php?p=12663861&amp;postcount=12" target="_blank">
  68. <a href="http://the%20week in games,twig,new releases,dealzon,xbox 360,pc,ps3,psn,xbox live,wii u,3ds,ps vita,kotakucore" target="_blank">
  69. <a href="http://happyhours.<%= market.domain %>
  70. <a href="http://happyhours.<%= market.domain %>
  71. <a href="http://lalaloopsy%20workshop%20sailor%20pack%20playset/" rel="nofollow" target="_blank">
  72. <a href="http://&quot;http://www.youtube.com/user/iKryptic" target="_blank">
  73. <a href="http://www.lacari&ntilde;osa.com/" title="La Cari&ntilde;osa" target="_blank">
  74. <a href="http://&quot;http://www.autoguide.com/manufacturer/mercedes-benz/2013-mercedes-c350-4matic-coupe-review-2775.html" target="_blank">
  75. <script async src="http://pagead2.google&#115;yndication.com/pagead/js/ad&#115;bygoogle.js">
  76. <script async src="http://pagead2.google&#115;yndication.com/pagead/js/ad&#115;bygoogle.js">
  77. <a href="http://www.&[v_host];">
  78. <img src="https://&#99;&#104;&#97;&#109;&#98;&#101;&#114;&#111;&#102;&#99;&#111;&#109;&#109;&#101;&#114;&#99;&#101;&#45;&#111;&#110;&#116;&#104;&#101;&#119;&#101;&#98;&#46;&#99;&#111;&#109;&#47;&#109;&#108;&#47;&#71;&#108;&#97;&#115;&#115;&#73;&#109;&#97;&#103;&#101;&#46;&#103;&#105;&#102;" alt="Chamber of Commerce - on the Web logo" title="Member: Chamber of Commerce - on the Web" width="120" height="50" border="0" />
  79. <a href="http://http%3A//nasrnews.pgp.ir/%u062F%u0631%u0628%u0627%u0631%u0647-%u0645%u0627">
  80. <a href="http://www.&[v_host];">
  81. <a title="" href="http://%E6%96%B0%E9%93%BE%E6%8E%A5" target="_blank">
  82. <a class="temas" href="http://www.cajaespa&ntilde;a-duero-bienvenido.es/" target="_blank" title="Hazte Cliente">
  83. <a href='http://www.wehkamp.nl&#47;damesmode&#47;C21&#47;' >
  84. <a href='http://www.wehkamp.nl&#47;herenmode&#47;C22&#47;' >
  85. <a href='http://www.wehkamp.nl&#47;kinderen&#47;C23&#47;' >
  86. <a href='http://www.wehkamp.nl&#47;wonen-slapen&#47;C28&#47;' >
  87. <a href='http://www.wehkamp.nl&#47;tuin-klussen&#47;C30&#47;' >
  88. <a href='http://www.wehkamp.nl&#47;huishoudapparatuur&#47;C27&#47;' >
  89. <a href='http://www.wehkamp.nl&#47;beeld-geluid&#47;C26&#47;' >
  90. <a href='http://www.wehkamp.nl&#47;computer-telecom&#47;C31&#47;' >
  91. <a href='http://www.wehkamp.nl&#47;games-films-speelgoed&#47;C25&#47;' >
  92. <a href='http://www.wehkamp.nl&#47;sport-vrije-tijd&#47;C24&#47;' >
  93. <a href='http://www.wehkamp.nl&#47;mooi-gezond&#47;C29&#47;' >
  94. <a href="http://happyhours.<%= market.domain %>
  95. <a href="http://www.internet-prodaja-guma.com&utm_source=polovniautomobili.com&utm_medium=link_meni&utm_campaign=pa_link_meni_ipg_logo" target="_blank">
  96. <a href="http://www.game7&#46;de" rel="external">
  97. <a href="http://rder=&pricerange=&freetran=&change=&k=%2525E9%25259B%2525AA%2525E7%2525BA%2525BA&" target="_blank">
  98. <a href="http://cid=50008165&brand=&source=all&area=&order=s_d&pricerange=&freetran=&change=&k=&h=" target="_blank">
  99. <a href="http://www.lacari&ntilde;osa.com/" title="La Cari&ntilde;osa" target="_blank">
  100. <a href="http://www.&#x30B7;&#x30EB;&#x30D0;&#x30FC;&#x30A2;&#x30AF;&#x30BB;.jp/2013/08/bigblackmaria-&#x30B9;&#x30BF;&#x30C3;&#x30BA;-ring/" title="http://www.&#x30B7;&#x30EB;&#x30D0;&#x30FC;&#x30A2;&#x30AF;&#x30BB;.jp/2013/08/bigblackmaria-&#x30B9;&#x30BF;&#x30C3;&#x30BA;-ring/" rel="external">
  101. <a href="http://follow%20us on Twitter" target="_blank">
  102. <a href="http://happyhours.<%= market.domain %>
  103. <a href="http://&ETH;&frac12;&ETH;&deg;&Ntilde;†&ETH;&cedil;&ETH;&frac34;&ETH;&frac12;&ETH;&deg;&ETH;&raquo;&Ntilde;Œ&ETH;&frac12;&Ntilde;‹&ETH;&sup1;&ETH;&middot;&ETH;&deg;&ETH;&ordm;&ETH;&frac34;&ETH;&frac12;.&Ntilde;€&Ntilde;„/petit1.php" rel="nofollow">
  104. <a href="http://akpartiedirne.com%20%20/" target="_blank">
  105. <a href="http://k-%EC%8A%A4%ED%83%80%ED%8A%B8%EC%97%85.%ED%95%9C%EA%B5%AD" target="_blank" title="새창열림">
  106. <input name="ctl00$paypage" type="button" id="paypage" class="PayPageNew" href="http://&lt;%=domainUrl %>
  107. <input name="ctl00$video" type="button" id="video" class="Video" href="http://&lt;%=domainUrl %>
  108. <a href="http://www.unl&lt;/body&gt;&lt;/html&gt;">
  109. <a href="http://happyhours.<%= market.domain %>
  110. <a href="http://www.cio.co.ke%20" target="_blank">
  111. <a href="http://t&hellip" target=_blank >
  112. <a href="http://happyhours.<%= market.domain %>
  113. <a href="http://&lt;p&gt; &lt;a href=&quot;http://www.savorysavings.com/wp-content/uploads/2013/08/GMG-button.jpg&quot;&gt;&lt;img alt=&quot;GMG button&quot; class=&quot;alignleft size-full wp-image-4026&quot; height=&quot;242&quot; src=&quot;http://www.savorysavings.com/wp-content/uploads/2013/08/GMG-button.jpg&quot; width=&quot;232&quot; /&gt;&lt;/a&gt; &lt;/p&gt;" >
  114. <a href="http://www.nationalbookstore.com.ph%20/" rel="nofollow" target="_blank">
  115. <link rel="alternate" hreflang="ru" href="http://%D1%88%D0%B0%D1%85%D0%BC%D0%B0%D1%82%D1%8B.chess.com/" />
  116. <link rel="alternate" hreflang="fr" href="http://%C3%A9checs.chess.com/" />
  117. <a href="http://%D1%88%D0%B0%D1%85%D0%BC%D0%B0%D1%82%D1%8B.chess.com/">
  118. <a href="http://%C3%A9checs.chess.com/">
  119. <a href="http://www.zonanegativa.com&langpair=es%7Cen&hl=es&ie=UTF-8&oe=UTF-8">
  120. <A HREF=http://www&#46;hit-parade&#46;com/hp&#46;asp?site=a548259 TARGET=_top>
  121. <IMG SRC=http://loga&#46;hit-parade&#46;com/logohp1&#46;gif?site=a548259 TITLE="Hit-Parade" WIDTH=77 HEIGHT=15 BORDER=0>
  122. <a href="http://&#1580;&#1575;&#1605;&#1593;&#1577;.&#1602;&#1591;&#1585;/ar/">
  123. <a href="http://happyhours.<%= market.domain %>
  124. <area shape="RECT" coords="1,1,61,51" href="http://www.aminparsian.com%20" target="_blank">
  125. <area shape="RECT" coords="69,1,148,50" href="http://www.pec.ir%20" target="_blank">
  126. <area shape="RECT" coords="163,1,213,50" href="http://www.parsianbroker.com%20" target="_blank">
  127. <area shape="RECT" coords="22,0,73,46" href="http://www.aminparsian.com%20" target="_blank">
  128. <area shape="RECT" coords="98,0,143,47" href="http://www.parsian-invest.com%20" target="_blank">
  129. <area shape="RECT" coords="180,1,254,46" href="http://www.pec.ir%20" target="_blank">
  130. <area shape="RECT" coords="376,2,421,47" href="http://www.parsian-lotus-hotels.com%20" target="_blank">
  131. <area shape="RECT" coords="457,2,503,47" href="http://www.parsianbroker.com%20" target="_parent">
  132. <a href=http://www.bdm.com.pl>Dom&nbsp;Maklerski&nbsp;BDM&nbsp;SA</a>
  133. <a href="http://www.lacari&ntilde;osa.com/" title="La Cari&ntilde;osa" target="_blank">
  134. <a href="http://www.actricesdelpornoespa&ntilde;ol.com" style="text-decoration:none" target="_blank">
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement