aboutsummaryrefslogtreecommitdiffstats
path: root/bin/extractor
diff options
context:
space:
mode:
authorterminaldweller <thabogre@gmail.com>2021-05-14 18:14:50 +0000
committerterminaldweller <thabogre@gmail.com>2021-05-14 18:14:50 +0000
commit6e528248414e330c9e25e81596ab47b8b8a5b701 (patch)
treee1aa41a7f3198eeac187e6177ec7d4a33db229d3 /bin/extractor
downloadscripts-master.tar.gz
scripts-master.zip
first commitmaster
Diffstat (limited to 'bin/extractor')
-rwxr-xr-xbin/extractor67
1 files changed, 67 insertions, 0 deletions
diff --git a/bin/extractor b/bin/extractor
new file mode 100755
index 0000000..c6dc4e7
--- /dev/null
+++ b/bin/extractor
@@ -0,0 +1,67 @@
+#!/usr/bin/env lua
+
+--by Egor Skriptunoff here:https://stackoverflow.com/questions/23590304/finding-a-url-in-a-string-lua-pattern
+local extractor = {}
+function extractor.getURLS(text_with_URLs)
+ local domains = [[.ac.ad.ae.aero.af.ag.ai.al.am.an.ao.aq.ar.arpa.as.asia.at.au
+ .aw.ax.az.ba.bb.bd.be.bf.bg.bh.bi.biz.bj.bm.bn.bo.br.bs.bt.bv.bw.by.bz.ca
+ .cat.cc.cd.cf.cg.ch.ci.ck.cl.cm.cn.co.com.coop.cr.cs.cu.cv.cx.cy.cz.dd.de
+ .dj.dk.dm.do.dz.ec.edu.ee.eg.eh.er.es.et.eu.fi.firm.fj.fk.fm.fo.fr.fx.ga
+ .gb.gd.ge.gf.gh.gi.gl.gm.gn.gov.gp.gq.gr.gs.gt.gu.gw.gy.hk.hm.hn.hr.ht.hu
+ .id.ie.il.im.in.info.int.io.iq.ir.is.it.je.jm.jo.jobs.jp.ke.kg.kh.ki.km.kn
+ .kp.kr.kw.ky.kz.la.lb.lc.li.lk.lr.ls.lt.lu.lv.ly.ma.mc.md.me.mg.mh.mil.mk
+ .ml.mm.mn.mo.mobi.mp.mq.mr.ms.mt.mu.museum.mv.mw.mx.my.mz.na.name.nato.nc
+ .ne.net.nf.ng.ni.nl.no.nom.np.nr.nt.nu.nz.om.org.pa.pe.pf.pg.ph.pk.pl.pm
+ .pn.post.pr.pro.ps.pt.pw.py.qa.re.ro.ru.rw.sa.sb.sc.sd.se.sg.sh.si.sj.sk
+ .sl.sm.sn.so.sr.ss.st.store.su.sv.sy.sz.tc.td.tel.tf.tg.th.tj.tk.tl.tm.tn
+ .to.tp.tr.travel.tt.tv.tw.tz.ua.ug.uk.um.us.uy.va.vc.ve.vg.vi.vn.vu.web.wf
+ .ws.xxx.ye.yt.yu.za.zm.zr.zw]]
+
+ local tlds = {}
+
+ for tld in domains:gmatch'%w+' do
+ tlds[tld] = true
+ end
+ local function max4(a,b,c,d) return math.max(a+0, b+0, c+0, d+0) end
+ local protocols = {[''] = 0, ['http://'] = 0, ['https://'] = 0, ['ftp://'] = 0}
+ local finished = {}
+
+ for pos_start, url, prot, subd, tld, colon, port, slash, path in
+ text_with_URLs:gmatch'()(([%w_.~!*:@&+$/?%%#-]-)(%w[-.%w]*%.)(%w+)(:?)(%d*)(/?)([%w_.~!*:@&+$/?%%#=-]*))'
+ do
+ if protocols[prot:lower()] == (1 - #slash) * #path and not subd:find'%W%W'
+ and (colon == '' or port ~= '' and port + 0 < 65536)
+ and (tlds[tld:lower()] or tld:find'^%d+$' and subd:find'^%d+%.%d+%.%d+%.$'
+ and max4(tld, subd:match'^(%d+)%.(%d+)%.(%d+)%.$') < 256)
+ then
+ finished[pos_start] = true
+ print(pos_start, url)
+ end
+ end
+
+ for pos_start, url, prot, dom, colon, port, slash, path in
+ text_with_URLs:gmatch'()((%f[%w]%a+://)(%w[-.%w]*)(:?)(%d*)(/?)([%w_.~!*:@&+$/?%%#=-]*))'
+ do
+ if not finished[pos_start] and not (dom..'.'):find'%W%W'
+ and protocols[prot:lower()] == (1 - #slash) * #path
+ and (colon == '' or port ~= '' and port + 0 < 65536)
+ then
+ print(pos_start, url)
+ end
+ end
+end
+
+function main()
+ local input = io.read("*a")
+ for k,v in pairs(arg) do
+ if v == "--url" then
+ extractor.getURLS(input)
+ else
+ print("invalid args...")
+ os.exit(1)
+ end
+ end
+end
+
+main()
+return extractor