def getDecisoes(cls):
try:
return cls.collection.find()
except Exception as e:
createLog('error', e)
return None
def getNews(cls):
try:
result = cls.db.news.find()
return result
except Exception as e:
createLog('error', e)
return None
def createCSV(file, headers, data):
try:
output = csv.writer(open(file,'w'))
except Exception as e:
createLog('error', e)
return False
output.writerow(headers)
for i in data:
output.writerow(i)
def setNewsBody(cls, link, body):
try:
result = cls.db.news.update({"link": link},
{'$set': {
'body': body
}})
return result
except Exception as e:
createLog('error', e)
return False
def saveAtoProcurador(cls, data):
if not isinstance(data, DTODorjAtosProcurador):
createLog(
'error', "saveAtoProcurador recebeu objeto do tipo {}".format(
type(data)))
return False
try:
result = cls.collection.insert_one(data.__dict__)
return result
except Exception as e:
createLog('error', e)
return False
def saveDecisoes(cls, data):
if not isinstance(data, DTODorjDecisoesConselho):
createLog(
'error',
"saveDecisoes recebeu objeto do tipo {}".format(type(data)))
return False
try:
result = cls.collection.insert_one(data.__dict__)
return result
except Exception as e:
createLog('error', e)
return False
def saveNewsHeaders(cls, data):
if not isinstance(data, DTOJornalJuridHeaders):
createLog(
'error',
"saveNewsHeaders recebeu objeto do tipo {}".format(type(data)))
return False
try:
result = cls.db.news.insert_one(data.__dict__)
return result
except Exception as e:
createLog('error', e)
return False
def __init__(self, category, subcategory = None):
try:
url = "{}/{}/{}".format(
JornalJurid.baseUrl,
category,
subcategory if subcategory else ""
)
r = requests.get(url)
if r.status_code == 404 or r.status_code == 500:
createLog('error', 'O endereço {} não foi encontrado'.format(url))
return None
except Exception as e:
createLog('error', e)
return None
self.soup = BeautifulSoup(r.text, 'html.parser', from_encoding="ISO-8859-1")
def getDecisoes(self):
"""
Retorna lista com decisões tomadas pelo Conselho.
"""
anchor = self.soup.find_all(attrs={"class": "ft19"})[-1]
if(len(anchor.get_text()) != 39):
print("Não foi possível encontrar a ancora")
return False
lineBreakIndicators = [['ft119'],['ft120'], ['ft121'],['ft219'],['ft220'], ['ft221'], ['ft222'], ['ft319'] ,['ft320'], ['ft321'],['ft322']]
currentEl = anchor.next_sibling.next_sibling
currentPage = 1
DecisoesList = []
while currentEl:
if "Processo" in currentEl.get_text() and "nº" in currentEl.get_text():
numberPos = currentEl.get_text().find('nº')
number = currentEl.get_text()[numberPos+2:numberPos+16]
DecisoesList.append(DTODorjDecisoesConselho(number, currentEl.get_text()[numberPos+17:]))
createLog('debug', "Novo Processo || {}".format(currentEl.get_text()))
elif currentEl['class'] in lineBreakIndicators:
DecisoesList[-1].content += currentEl.get_text()
createLog('debug', "Continuação || {}".format(currentEl.get_text()))
currentEl = currentEl.next_sibling.next_sibling
if currentEl == None:
print("Final da página")
currentPage += 1
page = self.soup.find(id="page{}-div".format(str(currentPage)))
if page == None:
print("Final do documento")
return DecisoesList
currentEl = page.find('p')
def getNewsBody(cls, link):
""""
Retornar o artigo completo a partir do link
"""
url = cls.baseUrl + link
try:
r = requests.get(url)
if r.status_code == 404 or r.status_code == 500:
createLog('error', 'O endereço {} não foi encontrado'.format(url))
return None
except Exception as e:
createLog('error', e)
return None
soup = BeautifulSoup(r.text, 'html.parser', from_encoding="ISO-8859-1")
if soup.find(class_="text-article") != None:
body = soup.find(class_="text-article").text
return body
elif soup.find(class_="header-view") != None:
body = soup.find(class_="header-view").find('p').text
return body
def getAtosProcurador(self):
"""
Retorna uma lista com os DTOs referentes aos Atos do Procurador-Geral.
"""
anchors = self.soup.find_all(attrs={"class": "ft110"})
for item in anchors:
if "PROCURADOR-GERAL" in item.get_text() and len(item.get_text()) == 24:
anchor = item
print("Ancore found: " + item.get_text())
if anchor == None:
raise(Exception("Atos do Procurador-Geral não encontrados"))
currentEl = anchor.next_sibling.next_sibling
currentData = None
shouldContinue = True
AtosList = []
lineBreakIndicators = [['ft116'], ['ft117'], ['ft118'],['ft119'] ,['ft120']]
while shouldContinue:
if(currentEl['class'] == ['ft110'] and len(currentEl.get_text()) == 13):
currentType = "data"
createLog('debug', currentType + '||' + currentEl.get_text())
currentData = datetime.strptime(currentEl.get_text()[-10:], "%d.%m.%Y")
currentEl = currentEl.next_sibling.next_sibling
elif(currentEl['class'] in lineBreakIndicators):
currentType = "text"
createLog('debug', currentType + '||' + currentEl.get_text())
AtosList[-1].content += currentEl.get_text()
currentEl = currentEl.next_sibling.next_sibling
elif(currentEl['class'] == ['ft13']):
currentType = "newLine"
createLog('debug', currentType + '||' + currentEl.get_text())
dto_rj = DTODorjAtosProcurador(currentData, currentEl.get_text())
AtosList.append(dto_rj)
currentEl = currentEl.next_sibling.next_sibling
else:
# print("Elemento não se encaixa nas definições:" + str(currentEl))
shouldContinue = False
return AtosList
def getAtosProcurador(cls):
try:
return cls.collection.find()
except Exception as e:
createLog('error', e)
return None