common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	819117	application/xhtml+xml	67.205.3.89	0	0	14	0	0	0	0	0	0	0	0	text/html	27784	html-mf-xfn	1328767358000	14	http://www.chsglobe.com/tag/carolyn-blair/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	951789	application/xhtml+xml	184.172.171.170	0	0	0	0	0	0	0	0	74	0	0	text/html	52523	html-mf-xfn	1328767359000	74	http://robyngough.com/2009/03/17/its-no-blarney-sale/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	1107477	text/html	62.149.195.44	0	0	5	0	0	0	0	0	0	0	0	text/html	45967	html-mf-hcard	1328767360000	5	http://www.palermoanimali.it/ViewProfile-eugenia.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	1597022	application/xhtml+xml	64.14.74.38	0	0	9	0	0	0	0	0	0	0	0	text/html	23109	html-mf-hcard	1328767361000	9	http://cascadebicyclestudio.com/2006/08/seven-test-bikes-for-sale/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	1619856	application/xhtml+xml	184.172.252.137	0	0	6	0	0	0	0	0	0	0	0	text/html	29997	html-mf-hcard	1328767361000	6	http://thebestmusicblog.com/in-this-land/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	2508028	text/html	67.205.37.206	0	0	24	0	0	0	0	0	0	0	4	text/html	36334	html-mf-hcard	1328767387000	28	http://eoid.org/tag/kabab/page/2/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	2896187	application/xhtml+xml	69.195.97.151	0	0	0	0	0	0	0	0	4	0	0	text/html	27124	html-mf-xfn	1328767387000	4	http://www.noahhowell.com/2009/02/why-not-sober-up-in-the-y-not/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	2999134	application/xhtml+xml	208.84.154.17	0	0	0	0	0	0	0	0	0	0	4	text/html	12250	html-rdfa	1328767384000	4	http://www.newcircle.com.au/news/2010/05/marcus-reich-gravity-edit/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	3765008	application/xhtml+xml	77.232.92.12	0	0	0	0	0	0	0	0	174	0	0	text/html	32063	html-mf-xfn	1328767385000	174	http://spxl.tv/2008/09/03/mind-reggae-dubstep/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	4303841	text/html	50.22.90.97	0	0	70	0	0	0	0	0	0	0	0	text/html	34754	html-mf-xfn	1328767384000	70	http://www.thebiblequotes.com/page/16
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	4315637	application/xhtml+xml	63.108.88.105	0	0	0	0	0	0	0	0	0	4	0	text/html	132591	html-microdata	1328767384000	4	http://store.inkjetcarts.us/i-series-c165.aspx
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	4455032	application/xhtml+xml	50.22.66.127	0	0	14	0	0	0	0	0	0	0	0	text/html	49569	html-mf-xfn	1328767384000	14	http://jagonews.com/2010/08/mazhar-majeed-released-on-bail-how-a-reporter-becomes-bookie/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	4654890	application/xhtml+xml	64.87.13.220	0	0	0	0	0	0	0	0	0	0	2	text/html	62258	html-rdfa	1328767384000	2	http://www.ipsb.edu/about-ipsb/our-people/instructors/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	5630618	text/html	216.35.196.77	0	0	28	0	0	0	0	0	0	0	0	text/html	9163	html-mf-xfn	1328767383000	28	http://stephlewis.com/2004/10/man/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	5633563	text/html	66.147.242.173	0	0	0	0	0	0	0	0	0	0	13	text/html	45219	html-rdfa	1328767383000	13	http://jessicamullen.com/2010/06/04/learning-with-lifestreaming-17-lifestreaming-the-law-of-attraction/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	5744230	text/html	89.30.106.44	0	0	0	0	0	0	0	0	0	0	3	text/html	22345	html-rdfa	1328767381000	3	http://www.convention-collective-plasturgie.fr/convention-collective-plasturgie-c292/organisation-duree-temps-travail-t5682141/reduction-duree-travail-formation-s5726473/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	5766754	text/html	50.22.107.97	0	0	7	0	0	0	0	0	0	0	0	text/html	26456	html-mf-xfn	1328767381000	7	http://lowcarbdietplans.low-carb-diet-planner.com/tag/going-low-carb-and-loving-it/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	6557304	application/xhtml+xml	72.167.68.125	0	0	3	0	0	0	0	0	0	0	0	text/html	43279	html-mf-hcard	1328767381000	3	http://www.fireflygn.com/Gold-Luncheon-Napkin-50Ct-GLD50LCNP-PP.htm
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	6881862	application/xhtml+xml	50.23.110.233	0	0	6	0	0	0	0	0	0	0	0	text/html	34509	html-mf-hcard	1328767379000	6	http://www.topratedautoinsurancecompanies.com/tag/car-insurance-comparisons/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	8265636	application/xhtml+xml	202.172.26.8	0	0	0	0	0	0	0	0	4	0	0	text/html	32291	html-mf-xfn	1328767363000	4	http://www.ito-rhythm.com/iphone/448.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	8291802	application/xhtml+xml	174.132.89.99	0	0	6	0	0	0	0	0	0	0	0	text/html	33080	html-mf-hcard	1328767364000	6	http://www.thevirtualasst.com/stickybits-tag-your-world%e2%84%a2
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	8555340	application/xhtml+xml	208.84.154.17	0	0	0	0	0	0	0	0	0	0	3	text/html	38200	html-rdfa	1328767361000	3	http://www.newcircle.com.au/news/category/product-highlight/page/3/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	8598274	application/xhtml+xml	63.108.88.105	0	0	0	0	0	0	0	0	0	4	0	text/html	359000	html-microdata	1328767362000	4	http://store.inkjetcarts.us/pro-9600-c591.aspx
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	10593557	application/xhtml+xml	69.163.136.29	0	0	60	0	0	0	0	0	0	0	0	text/html	52985	html-mf-hcard	1328767361000	60	http://www.parkeoloji.com/catalhoyuklulerin-atalari/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	10668509	text/html	50.22.90.97	0	0	56	0	0	0	0	0	0	0	0	text/html	32477	html-mf-xfn	1328767361000	56	http://www.thebiblequotes.com/page/18
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	10863430	application/xhtml+xml	67.227.133.188	0	0	0	0	0	0	0	0	0	0	8	text/html	32932	html-rdfa	1328767361000	8	http://search.doctoralia.in/oncology/4
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	10891269	text/html	67.205.37.206	0	0	6	0	0	0	0	0	0	0	4	text/html	30365	html-mf-hcard	1328767360000	10	http://eoid.org/tag/lodhi-colony/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	11424817	application/xhtml+xml	64.87.13.220	0	0	0	0	0	0	0	0	0	0	2	text/html	29919	html-rdfa	1328767360000	2	http://www.ipsb.edu/admissions/admissions-eligibility/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	11554168	text/html	89.30.106.44	0	0	0	0	0	0	0	0	0	0	3	text/html	22444	html-rdfa	1328767360000	3	http://www.convention-collective-plasturgie.fr/convention-collective-plasturgie-c292/dispositions-particulieres-personnel-encadrement-t5682060/date-application-s5726306/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	11763799	application/xhtml+xml	173.236.136.14	0	0	0	0	0	0	0	0	0	0	11	text/html	6693	html-rdfa	1328767360000	11	http://www.stacieturnerphotography.com/blog/tag/newborn/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	11855300	text/html	69.163.230.119	0	0	0	0	0	0	0	0	26	0	0	text/html	25831	html-mf-xfn	1328767360000	26	http://seecreatures.com/tag/stella-mccartney/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12018409	application/xhtml+xml	72.167.68.125	0	0	3	0	0	0	0	0	0	0	0	text/html	44993	html-mf-hcard	1328767359000	3	http://www.fireflygn.com/I-Carly-Edible-Icing-Art-EDARICARLY-PP.htm
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12162109	application/xhtml+xml	217.64.195.223	0	0	0	0	0	0	0	0	60	0	0	text/html	27258	html-mf-xfn	1328767366000	60	http://www.sukkology.net/blog/2006/05/23/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12179833	text/html	98.129.229.53	0	0	64	0	0	0	0	0	0	0	0	text/html	67718	html-mf-xfn	1328767382000	64	http://epicbattleaxe.com/rant-gamestopitplease/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12223903	application/xhtml+xml	74.84.203.173	0	0	16	0	0	0	0	0	0	0	1	text/html	85797	html-mf-hcard	1328767373000	17	http://dailyiowegian.com/local/x546122586/Centerville-City-Council-to-meet-tonight
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12255878	text/html	199.204.137.111	0	0	0	0	0	0	0	0	22	0	0	text/html	66936	html-mf-xfn	1328767380000	22	http://www.gilsmethod.com/how-to-unload-unused-dlls-to-regain-memory-in-windows-xp
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12294089	application/xhtml+xml	62.233.114.118	0	0	0	0	0	0	0	0	0	0	6	text/html	62465	html-rdfa	1328767370000	6	http://www.stalbansreview.co.uk/news/2006.0/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12348880	application/xhtml+xml	66.147.242.83	0	0	0	0	0	0	0	0	0	0	1	text/html	37941	html-rdfa	1328767372000	1	http://realblogging.com/stefan-swanepoel/real-estate-industry-update-homeaway-acquires-escapehomes/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12437768	application/xhtml+xml	80.239.169.97	0	0	0	0	0	0	0	0	0	0	1	text/html	53991	html-rdfa	1328767369000	1	http://www.finanzablog.it/user/thesneezer
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	12993089	application/xhtml+xml	97.74.26.1	0	0	0	0	0	0	0	0	4	0	0	text/html	36433	html-mf-xfn	1328767378000	4	http://www.apoliticus.com/2009/04/queen-in-a-bad-mood-tells-berlusconi-to-pipe-down/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13061412	application/xhtml+xml	190.228.29.85	0	0	0	0	0	0	0	0	104	0	0	text/html	74144	html-mf-xfn	1328767359000	104	http://noticiasinformales.com/2008/08/la-lucha-del-acosta-la-lucha-de-todos.html/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13076551	application/xhtml+xml	95.174.24.131	0	0	14	0	0	0	0	0	0	0	0	text/html	38551	html-mf-hcard	1328767361000	14	http://www.casahelp.com/salute-e-benessere/con-il-guerrilla-gardening-il-giardinaggio-diventa-politico/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13158286	application/xhtml+xml	95.174.24.131	0	0	66	0	0	0	0	0	0	0	0	text/html	48097	html-mf-hcard	1328767386000	66	http://www.casahelp.com/gestione-manutenzione/alcuni-suggerimenti-per-togliere-le-macchie/comment-page-1/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13170156	application/xhtml+xml	190.228.29.85	0	0	0	0	0	0	0	0	104	0	0	text/html	89526	html-mf-xfn	1328767387000	104	http://noticiasinformales.com/2008/06/hoy-nos-despertamos-con-la-noticia-de.html/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13273385	application/xhtml+xml	81.169.145.150	0	0	7	0	0	0	0	0	0	0	0	text/html	26435	html-mf-xfn	1328767375000	7	http://www.inmeinerstrasse.de/blog/tag/marzahn/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13280920	application/xhtml+xml	50.56.22.177	0	0	0	0	0	0	0	0	0	0	3	text/html	47376	html-rdfa	1328767377000	3	http://www.bikes.com.au/c/256014/1/2010-radius.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13310853	application/xhtml+xml	194.9.95.116	0	0	37	0	0	0	0	0	0	0	0	text/html	93879	html-mf-hcard	1328767382000	37	http://elingrelsson.se/2009/03/28/man-kan-inte-valdtas/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13328447	text/html	68.233.241.127	0	0	14	0	0	0	0	0	0	0	0	text/html	40674	html-mf-xfn	1328767368000	14	http://ponselhandphone.com/tag/ponsel-chatting/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13374634	application/xhtml+xml	74.220.215.215	0	0	0	0	0	0	0	0	0	0	5	text/html	23896	html-rdfa	1328767380000	5	http://www.hopelesslyflawed.com/tag/mint-julep/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13506907	application/xhtml+xml	184.168.176.1	0	0	63	0	0	0	0	0	0	0	0	text/html	91292	html-mf-hcard	1328767365000	63	http://vremeigre.com/3d-cestitka-sa-srcima.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13960025	text/html	98.129.178.208	0	0	90	0	0	0	0	0	0	0	0	text/html	49551	html-mf-hcard	1328767377000	90	http://www.bignickel-sparkstribune.com/view/full_story/8850649/article-Former-Nev--Gov--Guinn-dead-in-Las-Vegas
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	13984443	application/xhtml+xml	69.89.27.238	0	0	30	0	0	0	0	0	0	0	0	text/html	90024	html-mf-hcard	1328767385000	30	http://monikamcgillicuddy.com/wordpress/tag/atkinson-nh-market-report/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	14555987	text/html	173.245.60.82	0	0	0	0	0	0	0	0	0	0	6	text/html	53034	html-rdfa	1328767374000	6	http://www.justofficechairs.com/commercial-buyer-program/32-gallon-square-receptacle
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	15108047	application/xhtml+xml	66.147.242.85	0	0	91	0	0	0	0	0	0	0	0	text/html	72920	html-mf-hcard	1328767375000	91	http://blog.muscle-build.com/45988/special-school-bodybuilding-material/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	15166896	text/html	97.74.141.1	0	0	7	0	0	0	0	0	0	0	6	text/html	30234	html-mf-xfn	1328767385000	13	http://poponandon.com/tag/andy-carr-show
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	15337058	application/xhtml+xml	199.204.248.106	0	0	0	0	0	0	0	0	0	0	7	text/html	51023	html-rdfa	1328767364000	7	http://www.nauinet.co.jp/blog2/archives/1998/05/post-2.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	15458596	text/html	184.172.213.138	0	0	0	0	0	0	0	0	0	0	67	text/html	208183	html-rdfa	1328767367000	67	http://www.aedrx.info/philips-onsite-aed-defibrillator-quick-order-package/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	15543860	text/html	69.89.31.181	0	0	0	0	0	0	0	0	14	0	0	text/html	46387	html-mf-xfn	1328767374000	14	http://donkeywest.com/2010/06/19/the-independence-of-love/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	15666160	application/xhtml+xml	199.204.248.106	0	0	0	0	0	0	0	0	0	0	7	text/html	28049	html-rdfa	1328767386000	7	http://www.nauinet.co.jp/blog2/archives/2007/09/2007-4.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16024219	text/html	94.124.197.56	0	0	0	0	0	0	0	0	0	0	10	text/html	107667	html-rdfa	1328767365000	10	http://www.themoscowtimes.com/news/article/soviet-political-cartoonist-yefimov-dead-at-108/371385.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16052154	application/xhtml+xml	97.74.180.128	0	0	175	0	0	0	0	0	0	0	0	text/html	55521	html-mf-hcard	1328767369000	175	http://www.mobilewirelessphone.com/2010/02/06/nokia-photo-browser-beta-labs/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16129270	application/xhtml+xml	94.228.36.2	0	0	10	0	0	0	0	0	0	0	0	text/html	53886	html-mf-hcard	1328767374000	10	http://www.touchliverpool.com/business/list/bid/4747361
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16238345	application/xhtml+xml	164.109.40.120	0	0	0	0	0	0	0	0	0	0	7	text/html	89117	html-rdfa	1328767366000	7	http://www.gomemphis.com/news/2009/nov/06/no-headline---2009-11-05-095820482508/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16282558	application/xhtml+xml	141.242.248.222	0	0	0	0	0	0	0	0	0	0	7	text/html	48341	html-rdfa	1328767372000	7	http://www.valleymorningstar.com/articles/donna-66380-funerals-january.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16356114	application/xhtml+xml	173.201.39.183	0	0	0	0	0	0	0	0	0	0	5	text/html	47970	html-mf-xfn	1328767373000	5	http://iamkoream.com/gotv/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16445967	application/xhtml+xml	205.139.40.93	0	0	10	0	0	0	0	0	0	0	0	text/html	54258	html-mf-hcard	1328767368000	10	http://www.vaildaily.com/article/20041230/NEWS/112300012
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16488161	application/xhtml+xml	63.240.213.244	0	0	16	0	0	0	0	0	0	0	7	text/html	64549	html-mf-hcard	1328767359000	23	http://www.kiowacountysignal.com/obituaries/x1517281790/Becklund-memorial-service-set-for-Friday-in-Pratt
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	16550109	application/xhtml+xml	84.45.105.136	0	0	11	0	0	0	0	0	0	0	0	text/html	52324	html-mf-hcard	1328767375000	11	http://www.touchhereford.com/business/list/bid/2269146
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17093818	text/html	208.82.16.68	0	0	30	0	0	0	0	0	0	0	0	text/html	76799	html-mf-hcard	1328767408000	30	http://www.thenetworkonline.org/profile/SusanYoung
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17145942	application/xhtml+xml	98.136.92.79	0	0	0	0	0	0	0	0	6	0	0	text/html	37758	html-mf-xfn	1328767390000	6	http://www.rashtrakut.com/blog/2009/11/08/spreading-creationism-abroad/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17157324	application/xhtml+xml	98.136.92.79	0	0	0	0	0	0	0	0	6	0	0	text/html	34243	html-mf-xfn	1328767415000	6	http://www.rashtrakut.com/blog/2009/12/04/literally-from-rags-to-riches/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17226378	text/html	76.74.255.123	0	0	0	0	0	0	0	0	138	0	0	text/html	73791	html-mf-xfn	1328767410000	138	http://banannery.com/tag/satire/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17244808	application/xhtml+xml	74.200.243.251	0	0	216	0	0	0	0	0	0	0	0	text/html	78503	html-mf-hcard	1328767401000	216	http://penguingeneration.com/2010/08/08/most-comments-in-a-week-award/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17262507	application/xhtml+xml	76.74.255.123	0	0	0	0	0	0	0	0	34	0	0	text/html	30781	html-mf-xfn	1328767390000	34	http://icanhazdot.net/tag/teched/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17272607	application/xhtml+xml	76.74.255.123	0	0	0	0	0	0	0	0	34	0	0	text/html	32352	html-mf-xfn	1328767413000	34	http://icanhazdot.net/2008/10/24/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17303221	application/xhtml+xml	12.228.94.216	0	0	0	0	0	0	0	0	0	62	1	text/html	36573	html-microdata	1328767399000	63	http://www.mobilealflorist.com/gift-baskets
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17400363	text/html	213.186.33.16	0	0	0	0	0	0	0	0	0	0	1	text/html	58814	html-rdfa	1328767408000	1	http://www.sinart.asso.fr/3-films-avec-bud-spencer-et-terence-hill-coffret-3-dvd-13215
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17881341	text/html	208.65.158.3	0	0	0	0	0	0	0	0	0	11	0	text/html	42060	html-microdata	1328767395000	11	http://www.condosatwilliamscentre.com/44/Condominium-at-Williams-Centre-Blog/New-Available-Unit-Unit-10305-has-become-available/New-Available-Unit-Unit-16306-has-become-available
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	17956468	text/html	64.42.222.57	0	0	0	0	0	0	0	0	0	20	0	text/html	55105	html-microdata	1328767415000	20	http://sdhomepro.com/mylistings.html/details-9586207
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	18125499	application/xhtml+xml	72.233.2.58	0	0	0	0	0	0	0	0	18	0	0	text/html	52288	html-mf-xfn	1328767396000	18	http://mundoepm.com.br/2009/11/20/videos-da-project-conference-2009/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	18138595	application/xhtml+xml	76.74.254.120	0	0	0	0	0	0	0	0	18	0	0	text/html	55622	html-mf-xfn	1328767416000	18	http://mundoepm.com.br/2009/09/24/fotos-da-project-conference-2009-2/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	20496683	application/xhtml+xml	202.181.99.36	0	0	7	0	0	0	0	0	0	0	0	text/html	28646	html-mf-hcard	1328767417000	7	http://www.hotstudio.net/serika/blog/2009/12/divinity-2-ego-draconis-part1.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	20503331	application/xhtml+xml	184.173.2.186	0	0	0	0	0	0	0	0	0	0	5	text/html	40724	html-rdfa	1328767418000	5	http://www.shreveportrealestateandhomes.com/pending-home-sales-rise-unexpectedly/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	20520723	application/xhtml+xml	65.254.248.134	0	0	56	0	0	0	0	0	4	0	0	text/html	167263	html-mf-xfn	1328767418000	60	http://thekingdomkey.net/forums/user/696-miss-ninja/page__tab__aboutme
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	20788054	application/xhtml+xml	66.228.131.228	0	0	6	0	0	0	0	0	0	0	0	text/html	24871	html-mf-hcard	1328767416000	6	http://www.gloriousfootball.com/tag/bocanegra/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	20813041	application/xhtml+xml	209.236.73.165	0	0	6	0	0	0	0	0	0	0	0	text/html	16792	html-mf-hcard	1328767416000	6	http://www.alexlcohen.com/tag/iphone-analytics/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	21291375	application/xhtml+xml	184.154.228.18	0	0	36	0	0	0	0	0	0	0	0	text/html	64204	html-mf-hcard	1328767417000	36	http://natasha.edcentric.org/2009/12/27/happy-holidays/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	21397202	application/xhtml+xml	67.192.126.212	0	0	0	0	0	0	0	0	8	0	0	text/html	26176	html-mf-xfn	1328767417000	8	http://blog.canvaspress.com/tag/canvas-art/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	21416035	text/html	69.163.243.254	0	0	7	0	0	0	0	0	0	0	0	text/html	12803	html-mf-xfn	1328767417000	7	http://www.darkmessiah.com/assassins-creed-iafricacom/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	21848252	application/xhtml+xml	74.50.0.35	0	0	21	0	0	0	0	0	0	0	0	text/html	26478	html-mf-hcard	1328767417000	21	http://www.asiahealthtourism.com/case-studies-following-on-from-truth-telling-question/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	21966175	application/xhtml+xml	50.18.59.48	0	0	0	0	0	0	0	0	0	0	6	text/html	23062	html-rdfa	1328767415000	6	http://www.philadelphiaflowers.net/p3/3447/Grand_Celebrations_Fruit_and_Wine_Basket-1.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	22751446	application/xhtml+xml	118.127.87.28	0	0	0	0	0	0	0	0	0	0	2	text/html	40962	html-rdfa	1328767415000	2	http://www.oasis.com/de/member/vakerox.htm
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	25162794	application/xhtml+xml	174.120.83.157	0	0	0	0	0	0	0	0	0	0	2	text/html	95698	html-mf-hreview	1328767412000	2	http://ipranayam.com/gasacidity-and-constipation/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	25312902	text/html	217.6.129.104	0	0	0	0	0	0	0	0	0	0	3	text/html	38038	html-rdfa	1328767412000	3	http://www.emsland-touristik.de/Ab_aufs_Rad-94-2579-1.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	25330674	text/html	193.203.205.226	0	0	5	0	0	0	0	0	0	0	0	text/html	42362	html-mf-hcard	1328767412000	5	http://fitclub.ro/antrenament-culturism-fitness/exercitii-culturism-fitness/fese/fandari-haltera
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	25389185	text/html	174.132.195.34	0	0	0	0	0	0	0	0	6	0	0	text/html	59673	html-mf-xfn	1328767412000	6	http://wsmarketingnews.com/tag/google-adwords/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	25479602	application/xhtml+xml	184.173.193.157	0	0	70	0	0	0	0	0	4	0	0	text/html	32107	html-mf-xfn	1328767410000	74	http://www.peterdorsi.com/category/general/page/10/
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	25571937	application/xhtml+xml	173.248.188.79	0	0	0	0	0	0	0	0	0	0	3	text/html	60112	html-rdfa	1328767410000	3	http://www.platinumlist.ae/gallery/item/273/DJ_Magazine_Party_feat_AMIN_GOLESTAN_AFROBOOGIE.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	25621473	application/xhtml+xml	212.36.82.32	0	0	0	0	0	0	0	0	40	0	0	text/html	27430	html-mf-xfn	1328767410000	40	http://www.netdancerplanet.info/2007/01/guapas-pixeladas.html
common-crawl/parse-output/segment/1346823845675/1346864466526_10.arc.gz	25656249	application/xhtml+xml	113.33.195.32	0	0	0	0	0	0	0	0	0	0	5	text/html	27807	html-rdfa	1328767411000	5	http://brushcutter.shop-niche.co.jp/2010/05/post-65d5.html