mirror of https://github.com/WikiTeam/wikiteam
add more wikis to referata list; uploading basic referata-spider.py
parent
d97c46afd1
commit
7a6ef18339
@ -0,0 +1,29 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import random
|
||||
import re
|
||||
import requests
|
||||
import time
|
||||
|
||||
def main():
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (X11; Linux i686; rv:24.0) Gecko/20100101 Firefox/24.0',
|
||||
}
|
||||
|
||||
keyword = 'site:referata.com'
|
||||
for start in range(0, 1000, 10):
|
||||
url = 'https://www.google.es/search?q=%s&start=%d' % (re.sub(' ', '%20', keyword), start)
|
||||
r = requests.get(url, headers=headers)
|
||||
raw = r.text
|
||||
|
||||
m = re.findall(ur'(?im)<h3 class="r"><a href=\"([^ ]+?)" onmouse', raw)
|
||||
for i in m:
|
||||
print i
|
||||
|
||||
if re.search(ur'id="ofr"', raw): #resultados omitidos, final
|
||||
break
|
||||
|
||||
time.sleep(random.randint(3,10))
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
@ -1,57 +1,156 @@
|
||||
http://100dukes.referata.com
|
||||
http://100rogues.referata.com
|
||||
http://100wars.referata.com
|
||||
http://aadb.referata.com
|
||||
http://acqua.referata.com
|
||||
http://actoer.referata.com
|
||||
http://a.referata.com
|
||||
http://bdsmarena.referata.com
|
||||
http://biblioclub.referata.com
|
||||
http://biblioclub-wiki.referata.com
|
||||
http://bibliowiki.referata.com
|
||||
http://booksnetwork.referata.com
|
||||
http://books.referata.com
|
||||
http://botmg.referata.com
|
||||
http://bzpc.referata.com
|
||||
http://canaries.referata.com
|
||||
http://ccwiki.referata.com
|
||||
http://cdolist.referata.com
|
||||
http://challengertennis.referata.com
|
||||
http://climb.referata.com
|
||||
http://clinica-spa-lagoas-do-maceio.referata.com
|
||||
http://cometanet.referata.com
|
||||
http://communityrightsvscorporaterights.referata.com
|
||||
http://comparateurmutuelle.referata.com
|
||||
http://compose.referata.com
|
||||
http://culdcept.referata.com
|
||||
http://das.referata.com
|
||||
http://df-test.referata.com
|
||||
http://dixwell.referata.com
|
||||
http://dreamlords.referata.com
|
||||
http://efelaste.referata.com
|
||||
http://emergencyfoodsupply.referata.com
|
||||
http://emto-nanopub.referata.com
|
||||
http://enminipedia.referata.com
|
||||
http://essaiconstitution.referata.com
|
||||
http://everythingfanon.referata.com
|
||||
http://ewiki.referata.com
|
||||
http://exhilaration.referata.com
|
||||
http://exmisa.referata.com
|
||||
http://fad.referata.com
|
||||
http://fanstuff2.referata.com
|
||||
http://foodfinds.referata.com
|
||||
http://funnywiki.referata.com
|
||||
http://galacticheroes.referata.com
|
||||
http://geospatial.referata.com
|
||||
http://goldenpages.referata.com
|
||||
http://gsf.referata.com
|
||||
http://guitars.referata.com
|
||||
http://gymnasioker4.referata.com
|
||||
http://hacklabs-fi.referata.com
|
||||
http://hafenpedia.referata.com
|
||||
http://haskala.referata.com
|
||||
http://histdocs.referata.com
|
||||
http://hswi13.referata.com
|
||||
http://hswi.referata.com
|
||||
http://humanitariancomp.referata.com
|
||||
http://i-i.referata.com
|
||||
http://interkom.referata.com
|
||||
http://irkutsk.referata.com
|
||||
http://jimshole.referata.com
|
||||
http://jobasha.referata.com
|
||||
http://julian.referata.com
|
||||
http://juvenal.referata.com
|
||||
http://lagoasdomaceio.referata.com
|
||||
http://latinopedia.referata.com
|
||||
http://legendary-realms.referata.com
|
||||
http://lettrures.referata.com
|
||||
http://listadedesejos.referata.com
|
||||
http://loopa23.referata.com
|
||||
http://lost.referata.com
|
||||
http://ltfandom.referata.com
|
||||
http://lumeniki.referata.com
|
||||
http://mabiwiki.referata.com
|
||||
http://macdatarecovery.referata.com
|
||||
http://maiq.referata.com
|
||||
http://manifesto4now.referata.com
|
||||
http://mapping.referata.com
|
||||
http://mdac.referata.com
|
||||
http://mdgf.referata.com
|
||||
http://melodeon.referata.com
|
||||
http://menofwarwiki.referata.com
|
||||
http://micronations.referata.com
|
||||
http://minionsofthebraindatabase.referata.com
|
||||
http://moldovanwiki.referata.com
|
||||
http://mywiki.referata.com
|
||||
http://nb.referata.com
|
||||
http://northantscamra.referata.com
|
||||
http://opensciinfo.referata.com
|
||||
http://otp22.referata.com
|
||||
http://overlord.referata.com
|
||||
http://pex.referata.com
|
||||
http://pixelnations.referata.com
|
||||
http://poerup.referata.com
|
||||
http://pokemon.referata.com
|
||||
http://pokeset.referata.com
|
||||
http://prados.referata.com
|
||||
http://prodstat.referata.com
|
||||
http://quantlib.referata.com
|
||||
http://ragnaroktrans.referata.com
|
||||
http://recedis.referata.com
|
||||
http://referata.com
|
||||
http://reversespace.referata.com
|
||||
http://rita.referata.com
|
||||
http://rodokmeny.referata.com
|
||||
http://rogatiapedia.referata.com
|
||||
http://rootsup.referata.com
|
||||
http://saga3.referata.com
|
||||
http://sandbox.referata.com
|
||||
http://scratchpad.referata.com
|
||||
http://scumbags.referata.com
|
||||
http://sdrawxf.referata.com
|
||||
http://semanticguildwiki.referata.com
|
||||
http://semantika.referata.com
|
||||
http://servicebox.referata.com
|
||||
http://shadowmax.referata.com
|
||||
http://silver-eevee.referata.com
|
||||
http://smw.referata.com
|
||||
http://socialecologicalsystems.referata.com
|
||||
http://sockbook.referata.com
|
||||
http://spongefan.referata.com
|
||||
http://stargate.referata.com
|
||||
http://stlukesra.referata.com
|
||||
http://symphoelectronic.referata.com
|
||||
http://taichangpedia.referata.com
|
||||
http://tennisonline1.referata.com
|
||||
http://tennisonline.referata.com
|
||||
http://thelearningbank.referata.com
|
||||
http://tism.referata.com
|
||||
http://totalwwe.referata.com
|
||||
http://twisty.referata.com
|
||||
http://twnews.referata.com
|
||||
http://ulm.referata.com
|
||||
http://ultratool.referata.com
|
||||
http://unreliable-source.referata.com
|
||||
http://userpedia.referata.com
|
||||
http://valuenetwork.referata.com
|
||||
http://visced.referata.com
|
||||
http://whocomments.referata.com
|
||||
http://wiggonskiln.referata.com
|
||||
http://wijipedia.referata.com
|
||||
http://wikidata.referata.com
|
||||
http://wikidb.referata.com
|
||||
http://wikidraft.referata.com
|
||||
http://wikilit.referata.com
|
||||
http://wikimovie.referata.com
|
||||
http://wikipapers.referata.com
|
||||
http://wikipascom.referata.com
|
||||
http://wiki.referata.com
|
||||
http://wikisrb2upper.referata.com
|
||||
http://wiki-yamaha-rd.referata.com
|
||||
http://www.referata.com
|
||||
http://xop.referata.com
|
||||
http://xstream-brasil.referata.com
|
||||
http://xstream-brazil.referata.com
|
||||
http://yoshiwiki.referata.com
|
||||
http://yt-tycoon.referata.com
|
||||
|
Loading…
Reference in New Issue