def extract_seance(element):
return {
'url':
urljoin(AN_BASE_URL, element.a['href']) if element.a else None,
'date': extract_datetime(element.text.split('séance du ')[1]),
'type': LegislativeActType.DISCUSSION_SEANCE_PUBLIQUE
}
def extract_data(self):
if not self.elements:
return
matched_dates = re.findall(r' le (\d+\s?\w* \w+ \d{4})',
self.elements[0].text, re.I | re.UNICODE)
return [{
'type':
LegislativeActType.PROCEDURE_ACCELEREE,
'date':
extract_datetime(matched_dates[0]) if matched_dates else None
}]
def extract_data(self):
status = None
if 'adopté' in self.elements[0].text:
status = DecisionStatus.ADOPTE
elif 'modifié' in self.elements[0].text:
status = DecisionStatus.MODIFIE
elif 'rejeté' in self.elements[0].text:
status = DecisionStatus.REJETE
matched_dates = re.findall(r' le (\d+\s?\w* \w+ \d{4})',
self.elements[0].text, re.I | re.UNICODE)
return [{
'type':
LegislativeActType.DECISION,
'status':
status,
'date':
extract_datetime(matched_dates[0]) if matched_dates else None,
'url':
urljoin(AN_BASE_URL, self.elements[0].a['href'])
if self.elements[0].a else None
}]
def extract_date(self):
matched_dates = re.findall(r' déposée? le (\d+ \w+ \d{4})',
self.elements[0].text, re.UNICODE)
return extract_datetime(matched_dates[0]) if matched_dates else None
def test_extract_date():
assert extract_datetime('15 mai 2013 à 14 heures 30') == datetime(2013, 5, 15, 14, 30)
assert extract_datetime('lundi 17 juin 2013') == datetime(2013, 6, 17)
assert extract_datetime('mercredi 11 septembre 2013') == datetime(2013, 9, 11)
assert extract_datetime('24 mars 2015 à 17 heures') == datetime(2015, 3, 24, 17, 0)