#!/usr/bin/python3
#import myurllib2 as urllib2
import urllib.request
import ssl
from lxml.html import document_fromstring
 
https_sslv3_handler=urllib.request.HTTPSHandler(context=ssl.SSLContext(ssl.PROTOCOL_SSLv3))
opener=urllib.request.build_opener(https_sslv3_handler)
urllib.request.install_opener(opener)
def fetch_url(url):
  for tries in range(3):
    try:
      handle=urllib.request.urlopen(url)
      break
    except IOError as e:
      if hasattr(e, 'code'): # HTTPError
        print( 'http error code: ', e.code )
      elif hasattr(e, 'reason'): # URLError
        print( "can't connect, reason: ", e.reason )
      else:
        raise
  return handle
 
 
def fetch_utilisateurs(unite):
  liste=[]
  page=0
  while True:
    html=fetch_url("https://web-ast.dsi.cnrs.fr/l3c/owa/personnel.liste?nom=&prenom=&code_labo=%s&p_dep=&sec=&bap=&emptype=&nat_pers=&typ_pers=&organisme=&delegation=&ville=&p_i=%s&p_nb_res=0"%(unite,page))
    string=html.read()
    content=document_fromstring(string)
    struct=content.xpath('/html/body/table[3]/tr')
    for i in struct:
      children=i.getchildren()
      if children[0].tag=="td":
         liste.append("%s %s"%(children[0].text_content(),children[1].text_content()))
    struct=content.xpath("//input[@alt='les 10 personnes suivantes']")
    if struct:
      #"une page suivante"
      page+=10
    else:
      #"c'est fini"
      break
  return liste
 
if __name__=="__main__":
  unite="UMR7640"
  liste_utilisateurs=fetch_utilisateurs(unite)
  for i in liste_utilisateurs:
    print( i)