Leaderboard

Ca sa functioneze, ii trebuie un fisier cu domenii, cu sau fara prefixul http:// la inceput. Usage: python emailscrapper.py Threads File Exemplu: python emalscrapper.py 50 domenii.txt Mailurile se salveaza in emails.txt UPDATE 1.3: - izolare completa la proceselor - renuntat la threading, acum functioneaza cu multiprocese total paralele - preluare rezultate mai corect - 2-3x mai rapid fata de precedenta versiune Versiune minima pentru functionare este Python 2.6 Pentru variante customizate, aveti jabberul meu in cod. """ RST eMail Crawler Version: 1.3 Author: Elohim Contact Jabber: viktor@rows.io """ import urllib2 import re import sys import cookielib from threading import Timer from multiprocessing import Process, Queue class GetResults(Process): def __init__(self, rezqueue): Process.__init__(self) self.rezqueue = rezqueue def run(self): while True: email = self.rezqueue.get() if email is None: return False with open("emails.txt","a") as EmailFile: EmailFile.write(email.rstrip()+"\n") print email class Crawler(Process): def __init__(self, queue, rezqueue): Process.__init__(self) self.queue = queue self.rezqueue = rezqueue def run(self): while True: site = self.queue.get() if site is None: return False self.crawl(site) def crawl(self,site): try: WatchIt = Timer(15.0, self.WatchDog) WatchIt.start() cj = cookielib.CookieJar() opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj)) opener.addheaders = [('Accept:','*'),("User-Agent", "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:31.0) Gecko/20100101 Firefox/31.0")] opener.addheaders = [('Content-Type', 'text/html; charset=utf-8'),("Accept-Encoding", "")] resp = opener.open(site,timeout=10) WatchIt.cancel() self.getem(resp.read()) except Exception, e: #print e f = 1 def getem(self,resp): try: emails = re.findall(r"[A-Za-z0-9%&*+?^_`{|}~-]+(?:\.[A-Za-z0-9!#$%&*+?^_`{|}~-]+)*@(?:[A-Za-z0-9](?:[a-z0-9-]*[A-Za-z0-9])?\.)+(?:[A-Za-z]{2}|com|org|net|edu|gov|mil|biz|info|mobi|name|aer o|asia|jobs|museum)\b", str(resp)) CleanEmails = set(emails) for em in CleanEmails: self.rezqueue.put(em.lower()) except Exception, e: return False def WatchDog(self): return False if __name__ == "__main__": if len(sys.argv) < 3: print "Usage:",sys.argv[0],"Threads DomainFile.txt" print "\tExample: ",sys.argv[0],"30 domains.txt" sys.exit() queue = Queue(maxsize=30000) rezqueue = Queue() ThreadNumber = int(sys.argv[1]) ThreadList = [] for i in range(ThreadNumber): t = Crawler(queue,rezqueue) t.daemon = True t.start() ThreadList.append(t) GR = GetResults(rezqueue) GR.daemon = True GR.start() with open(sys.argv[2],"rU") as urls: for url in urls: try: if url.startswith('http://'): queue.put(url.rstrip()) else: url = 'http://'+url.rstrip() queue.put(url.rstrip()) except Exception, e: print e for i in range(ThreadNumber): queue.put(None) for Worker in ThreadList: Worker.join() print "All done!" rezqueue.put(None) GR.join()

Pune te rog la categoria non it. ti-am mutat ambele threaduri (si cel cu pr0n keywords si asta). De asemenea, nu mai da paste pe rst la 3000 porn keywords, le pui pe pastebin mai bine. Atrag vizite aiurea si dau rau in google pentru ca se face asocierea intre domeniu/site si cuvintele acelea. merci

Cum zice si colegul mai sus.... Da pun pariu ca illuminati fac asta. Illuminati incearca sa uneasca toata Europa.... (parere proprie) apoi celalalte tari... iar cand se ajunge la New World Order o sa apara anticristu, el o sa conduca de la Templu din Ierusalim (parca), o sa fie 3 ani jumate de prosperitate, ++++ free, etc apoi 3 ani juma de chin.... Hmm interesant unde s-a ajuns, citisem undeva ca anticrist e incarnat , hmm true? Nu mai retin de unde mi-a ramas intiparita chestia cu: "al 3-lea razboi mondial o sa apara cand vor murii toti veterani celui de-al doilea razboi.... " sau ceva de genu.... si era explicat cu Schita cei ce sau nascut pe 1945 au acum 69 de ani... deci pot sa traiasca si 100....