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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
import xml.etree.ElementTree as ET
import datetime
import html
import re
from ofxstatement.plugin import Plugin
from ofxstatement.statement import Statement, StatementLine
CD_CREDIT = 'CRDT'
CD_DEBIT = 'DBIT'
class OtpPlugin(Plugin):
"""OTP (XML)
"""
def get_parser(self, filename):
return OtpParser(filename)
class OtpParser(object):
def __init__(self, filename):
self.filename = filename
def parse(self):
"""Main entry point for parsers
"""
self.statement = Statement()
tree = ET.parse(self.filename)
self._parse_statement_properties(tree)
self._parse_lines(tree)
return self.statement
def _parse_statement_properties(self, tree):
stmt = tree.find('./Rpt')
bnk = stmt.find('./Acct/Svcr/FinInstnId/Nm')
iban = stmt.find('./Acct/Id/Othr/Id')
bals = stmt.findall('./Bal')
bal_amts = {}
bal_dates = {}
for bal in bals:
cd = bal.find('./Tp/CdOrPrtry/Cd')
amt = bal.find('./Amt')
dt = bal.find('./Dt')
# Amount currency should match with statement currency
bal_amts[cd.text] = self._parse_amount(amt)
bal_dates[cd.text] = self._parse_date(dt)
self.statement.bank_id = bnk.text
self.statement.account_id = iban.text
self.statement.start_balance = bal_amts['OPBD']
self.statement.start_date = bal_dates['OPBD']
self.statement.end_balance = bal_amts.get('CLBD', None)
self.statement.end_date = bal_dates.get('CLBD', None)
def _parse_lines(self, tree):
for ntry in _findall(tree, 'Rpt/Ntry'):
sline = self._parse_line(ntry)
self.statement.lines.append(sline)
def _parse_line(self, ntry):
sline = StatementLine()
crdeb = _find(ntry, 'CdtDbtInd').text
amtnode = _find(ntry, 'Amt')
amt = self._parse_amount(amtnode)
if crdeb == CD_DEBIT:
amt = -amt
payee = _find(ntry, 'NtryDtls/TxDtls/RltdPties/Cdtr/Nm')
else:
payee = _find(ntry, 'NtryDtls/TxDtls/RltdPties/Dbtr/Nm')
if payee is not None:
payee = payee.text
sline.payee = payee
sline.amount = amt
dt = _find(ntry, 'ValDt')
sline.date = self._parse_date(dt)
bookdt = _find(ntry, 'BookgDt')
sline.date_user = self._parse_date(bookdt)
svcref = _find(ntry, 'NtryDtls/TxDtls/Refs/AcctSvcrRef')
sline.refnum = getattr(svcref, 'text', None)
rmtinf = _find(ntry, 'NtryDtls/TxDtls/RmtInf/Ustrd')
sline.memo = rmtinf.text if rmtinf.text else ''
addtlinf_node = _find(ntry, 'NtryDtls/TxDtls/AddtlTxInf')
addtlinf = self._parse_addtlinf(addtlinf_node)
if 'VÁSÁRLÁS KÁRTYÁVAL' == addtlinf and not sline.payee:
sline.payee = _trim_payee(sline.memo)
sline.memo += ' ' + addtlinf
return sline
def _parse_date(self, dtnode):
if dtnode is None:
return None
dt = _find(dtnode, 'Dt')
dttm = _find(dtnode, 'DtTm')
if dt is not None:
return datetime.datetime.strptime(dt.text, "%Y-%m-%d")
else:
assert dttm is not None
return datetime.datetime.strptime(dttm.text, "%Y-%m-%dT%H:%M:%S")
def _parse_amount(self, amtnode):
return float(amtnode.text)
def _parse_addtlinf(self, addtlinf):
string = '<root>' + html.unescape(addtlinf.text) + '</root>'
return ET.fromstring(string).find('narr').text
def _toxpath(spath):
tags = spath.split('/')
path = ['%s' % t for t in tags]
xpath = './%s' % '/'.join(path)
return xpath
def _find(tree, spath):
return tree.find(_toxpath(spath))
def _findall(tree, spath):
return tree.findall(_toxpath(spath))
_trim_payee_regexes = [
re.compile(' .*'),
re.compile('\d+\.\d+\.\d+ \d+'),
re.compile('[\d,]+EUR.*')
]
def _trim_payee(payee):
for r in _trim_payee_regexes:
payee = r.sub('', payee)
return payee
|
