#!/usr/bin/env python # -*- coding: cp1252 -*- import sys import string import httplib import time import getopt def elaborate(pattern, query, page): temp=pattern temp=temp.replace('###QUERY###',query) temp=temp.replace('###PAGE###',page) return temp def searchMe(pages,url): result=[] z=0 for i in pages: print 'Analizzo pagina ',z,'...' temp=i.split('

= 0: result.append('Pagina:'+str(z)+', posizione:'+str(x)) x=x+1 return result def output(res,fout): fout.write("Risultati ricerca

Risultati ricerca su "+engine+"
del sito "+url+" con chiave "+query+" in "+str(numPage)+" pagine





") fout.write('
    ') for i in res: fout.write('
  1. '+i+'
    2. ') print 'Record '+url+' trovato -> '+i fout.write('
') fout.write('
Dati prodotti da whereIs.py; Copyright Antonello Cicchese
') print 'Analisi conclusa' def main(): pattern="/search?q=###QUERY###&start=###PAGE###&sa=N" htmlSrc=[] temp=[] fname='data.txt' fin=open(fname,'r') fout=open('risultato.htm','w+') line=fin.readlines() fin.close() data=[] for ele in range(4): data.append(str(line[ele].split('=')[1])) global engine global url global query global numPage engine=data[0].strip() url=data[1].strip() query=data[2].strip() numPage=int(data[3].strip()) if numPage>100: print "Una ricerca su piu' di 100 pagine non produce risultati attendibili" print "numero di pagine ridotto a 100" numPage=100 for i in range(numPage): ricerca=elaborate(pattern,query,str(i*10)) print 'Connessione n°',i,' URL: http://'+engine+''+ricerca try: conn = httplib.HTTPConnection(engine) conn.request ("GET",ricerca) r = conn.getresponse() except: print('Impossibile connettersi') break if r.reason == 'OK': data = r.read() print 'Pagina ',i,' scaricata' htmlSrc.append(data) else: print("Errore download pagina") break conn.close() time.sleep(2) #Numero di secondi di pausa tra una query e l'altra temp=searchMe(htmlSrc,url) output(temp,fout) fout.close() if __name__=="__main__": main()