census/core.py at master · joanfont/census · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
from copy import copy
from bs4 import BeautifulSoup
import requests
from re import compile


class BaseError(Exception):
    def __init__(self, error_code, error_desc, status_code):
        self.error_code = error_code
        self.error_desc = error_desc
        self.status_code = status_code

    def to_dict(self):
        return {
            'error_code': self.error_code,
            'error_desc': self.error_desc,
        }


class NifRequiredError(BaseError):
    pass


class InvalidNifError(BaseError):
    pass


class Voter:
    def __init__(self, nif, district, section, table, school, address):
        self.nif = nif
        self.district = district
        self.section = section
        self.table = table
        self.school = school
        self.address = address

    def to_dict(self):
        return {
            'nif': self.nif,
            'district': self.district,
            'section': self.section,
            'table': self.table,
            'school': self.school,
            'address': self.address,
        }

    @classmethod
    def from_li_items(cls, nif, li_items):
        def _extract_number(li):
            regex = compile('(\d+)')
            text = li.text
            res = regex.search(text)
            return int(res.group(1).strip()) if res else None

        def _extract_string(li):
            regex = compile('(.*):(.*)')
            text = li.text
            res = regex.search(text)
            return res.group(2).strip() if res else None

        li_district, li_section, li_table, li_school, li_address = li_items

        district = _extract_number(li_district)
        section = _extract_number(li_section)
        table = _extract_string(li_table)
        school = _extract_string(li_school)
        address = _extract_string(li_address)

        return cls(nif, district, section, table, school, address)


class ElectoralCensus:

    BASE_URL = 'https://cens.palma.cat'
    URL = '{base}/portal/PALMA/cens/cens_principal1.jsp?codResi=1'.format(base=BASE_URL)

    DEFAULT_PARAMS = {
        'form_name': 'formcenso',
        'seccion': 'Consulta.jsp',
    }

    DEFAULT_HEADERS = {
        'Origin': BASE_URL,
        'Referer': URL,
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.95 Safari/537.36',
        'Accept-Language': 'es-ES,es;q=0.8',

    }

    @classmethod
    def find_by_nif(cls, nif):

        if not nif:
            raise NifRequiredError('bad_request', 'El camp NIF és obligatori', 400)

        soup = cls.get_soup(nif)

        if soup.find('table', {'id': 'formcenso-errors'}):
            error_desc = 'El NIF {} és invàlid'.format(nif)
            raise InvalidNifError('not_found', error_desc, 404)

        ul = soup.find('div', {'id': 'mesaInfo'})
        li_items = ul.find_all('li')

        voter = Voter.from_li_items(nif, li_items)

        return voter

    @classmethod
    def get_soup(cls, nif):
        url_params = copy(cls.DEFAULT_PARAMS)
        url_params.update({
            'nifPersona': nif,
        })

        response = requests.get(cls.URL, params=url_params, headers=cls.DEFAULT_HEADERS)
        html = response.text
        soup = BeautifulSoup(html, 'html.parser')

        return soup