def is_valid_link(link):
'''Invalid links are to images. This works for both implicit and regular style links.'''
flags = ['.jpg', '.svg', '.png', '.gif', '.jpeg', '.bmp', '.tiff']
result = True
if link and 'page' in link:
result = result and (not any([_.has_substr(link['page'].lower(), flag) for flag in flags]))
else:
return False
if link and 'text' in link:
result = result and (not any([_.has_substr(link['text'].lower(), flag) for flag in flags]))
return result
def process_davivienda_message(message):
print('Davivienda: processing message')
amount = re.sub(r'[^\d.]', '', nth(lines(message.string), 6))
category_type = nth(lines(message.string), 7)
desc = trim(nth(split(nth(lines(message.string), 8), ':'), 1))
if has_substr(upper_case(desc), 'PSE'):
print('Davivienda: Ignored PSE payment')
return None, None, None
if has_substr(lower_case(category_type), 'deposito') or has_substr(
lower_case(category_type), 'abono'):
category_type = moneylover.CATEGORY_TYPE['income']
category_item = 'Salary' if has_substr(
upper_case(desc), 'ACH GNB SUDAMERIS') else 'Others'
else:
category_type = moneylover.CATEGORY_TYPE['expense']
category_item = categorize(desc)
return amount, {'type': category_type, 'item': category_item}, desc
def is_valid_page(page):
'''Invalid pages are images or disambiguation pages that were not
flagged at the parser level. Also check that the page has more than 5 characters.'''
flags = ['.jpg', '.svg', '.png', '.gif', '.jpeg', '.bmp', '.tiff', '(disambiguation)']
has_content = page and (len(page['plaintext'].strip()) > 5)
if page and has_content and 'title' in page:
return not any([_.has_substr(page['title'].lower(), flag) for flag in flags])
else:
return False
def predefined_category(text):
if has_substr(lower_case(text), 'une'): return 'Bills & Utilities'
if has_substr(lower_case(text), 'rappi'): return 'Food & Beverage'
if has_substr(lower_case(text), 'comcel'): return 'Bills & Utilities'
if has_substr(lower_case(text), 'nequi'): return 'Nequi'
if has_substr(lower_case(text), 'credito visa'): return 'Credit Card'
if has_substr(lower_case(text), 'fiducredicorp'): return 'Apartment'
if has_substr(lower_case(text), 'canon'): return 'Rentals'
def process_pse_message(message):
print('PSE(davivienda): processing message')
data = lines(last(message.table.table.find_all('span')))
desc = re.sub(r'<[^<>]*>', '', nth(data))
amount = re.sub(r'[^\d,]', '', nth(data, 1)).replace(',', '.')
is_visa = has_substr(lower_case(desc), 'credito visa')
if is_visa:
visa_category_type = moneylover.CATEGORY_TYPE['income']
visa_category_item = 'Payment'
category_type = moneylover.CATEGORY_TYPE['expense']
category_item = categorize(desc)
return amount, {
'type': category_type,
'item': category_item
}, desc, {
'type': visa_category_type,
'item': visa_category_item
} if is_visa else None
def test_has_substr(case, expected):
assert _.has_substr(*case) == expected