getimg.py

import sys, re, csv, requests
from bs4 import BeautifulSoup

if sys.version_info[0] == 3:
    from urllib.request import urlopen
else:
    # Not Python 3 - today, it is most likely to be Python 2
    # But note that this might need an update when Python 4
    # might be around one day
    from urllib import urlopen

#filename = '/Users/Jacobo/pr/upmatch/a.jpg'
#with open(filename, 'wb') as file:
 #   file.write(urlopen('https://etu.math.upmc.fr/math/photos/3520121.jpg').read())

def get_infos(r):
    soup = BeautifulSoup(r.text, 'html.parser')
    info = dict()
    for o in soup.findAll("td",{'class':'result'}):
        info['name'] =o.text.strip() #prenom NOM
        info['etu']=str(o)[78:85] #numETU
        adresse='https://www.annuaire.upmc.fr/upmc/list.upmc?method=list&dn=uidInterne='+str(o)[re.search(r'Interne=', str(o)).span()[1]:re.search(r',ou=', str(o)).span()[0]]+',ou=People&mode=display'
        with urlopen(adresse) as url:
            s = url.read()
        full = BeautifulSoup(s, 'html.parser')
        mail=full.findAll("td",{'class':'attributeDisplayer_value'})
        mail=str(mail[5])
        info['mail']=mail[re.search(r'@etu.upmc.fr">',mail).span()[1]:re.search(r'</a>',mail).span()[0]]

        ##ajout des photos:
        try:
            pic = '/Users/Jacobo/pr/upmatch/photos/'+info['etu']+'.jpg'
            with open(filename, 'wb') as file:
                file.write(urlopen('https://etu.math.upmc.fr/math/photos/'+info['etu']+'.jpg').read())
                info['pic']=1
        except:
            info['pic']=0
    return info

def make_csv(infos, filename):
    with open(filename, 'w') as csvfile:
        fieldnames = list({key for info in infos for key in info.keys()})
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
        writer.writeheader()
        for info in infos:
            writer.writerow(info)


url = "https://www.annuaire.upmc.fr/upmc/simpleSearch.upmc"
infos=list()
filename="/Users/Jacobo/pr/upmatch/data.csv"
for i in range(97,123):
    for j in range(97,123):
        for k in range(97,123):
            name=chr(i)+chr(j)+chr(k)
            payload = {
                'name': name,
                'name_query_type': 'NAME*',
                'surname': '',
                'surname_query_type': 'SURNAME*',
                'filter': 'objectClass=etudiant',
                'number': '2500',
                'bouton.x': '38',
                'bouton.y': '15',
                'inputPage': 'inputBadSearchWithoutFilters',
            }
            session = requests.session()
            r = requests.post(url, data=payload)

            #call get info with r

            infos.append(get_infos(r))
            make_csv(infos,filename)