def scrape_civil_escrito(self, causa_id, causa_obj, soup):
"""Searches for escritos pendientes in civil causa"""
rows = soup.find(id='titTablaCivEsc').parent.parent.find_all(
'tr'
) # double parent because this one has header tr inside <thead>
header = True
for row in rows:
if not header: # skip the header row
tds = row.find_all('td')
input_el = row.find('input', attrs={'name': 'id_documento'})
id_documento = input_el.attrs['value']
if id_documento:
doc_id = '{}__{}'.format(
causa_id, id_documento) # id = causa_id__id_documento
created = False
try:
doc_obj = EscritoCivilPorResolver.objects.get(
id=doc_id)
except:
doc_obj = EscritoCivilPorResolver(
id=doc_id,
causa=causa_obj,
fecha=simplify_string(tds[2].contents[0]),
tipo=simplify_string(tds[3].contents[0]),
solicitante=simplify_string(tds[4].contents[0]),
)
doc_obj.save()
created = True
if created:
if self.profile.initial_migration_done:
print('Sending notification: {}'.format(doc_obj))
send_new_doc_notification(doc_obj)
else:
header = False
def scrape_familia_document(self, causa):
"""Opens the detail of a causa. `causa` is the soup form element"""
session = self.session
url = Scraper.CAUSA_TYPES['familia']['detail']
data = {}
for input_elm in causa.find_all('input'):
if 'name' in input_elm.attrs.keys(
) and 'value' in input_elm.attrs.keys():
data[input_elm.attrs['name']] = input_elm.attrs['value']
causa_id = 'FAM_{}_{}_{}'.format(data['tipo_causa'], data['rol_causa'],
data['era_causa'])
tr = causa.parent.parent
tds = tr.find_all('td')
caratulado = simplify_string(tds[3].contents[0])
try:
causa_obj = Causa.objects.get(id=causa_id)
except Exception as ex:
causa_obj = Causa(id=causa_id,
user=self.profile,
type=Causa.TYPE_CHOICES_FAMILIA,
archived=False,
rol='{}-{}-{}'.format(data['tipo_causa'],
data['rol_causa'],
data['era_causa']),
caratulado=caratulado)
causa_obj.save()
if self.profile.initial_migration_done:
send_new_causa_notification(causa_obj)
if causa_obj and causa_id:
# print(causa_obj)
# Open causa details:
resp = session.post(url,
data=data,
headers=Scraper.SCRAPER_HEADERS)
if 'Causa Familia' in resp.text:
resp_text = resp.content.decode('ISO-8859-1').replace(
'\r', ' ').replace('\n', '')
html = '<html><body>{}</body></html>'.format(resp_text)
soup = BeautifulSoup(html, 'html.parser')
rows = soup.find(id='titTablaFam').parent.find_all('tr')
header = True
for row in rows:
if not header: # skip the header row
link = row.find('a')
if link and 'onclick' in link.attrs:
onclick = link.attrs[
'onclick'] # E.g "vvbbFF('Resolución',3,59987979,0);"
doc_id = onclick.replace('vvbbFF(', '').replace(
');', '').replace(',', '-').replace("'", '')
tds = row.find_all('td')
if doc_id:
created = False
try:
doc_obj = DocFamilia.objects.get(id=doc_id)
except:
doc_obj = DocFamilia(
id=doc_id,
causa=causa_obj,
etapa=simplify_string(
tds[2].contents[0]),
tramite=simplify_string(
tds[3].contents[0]),
desc_tramite=simplify_string(
tds[4].contents[0]),
referencia=simplify_string(
tds[5].contents[0]),
fecha=simplify_string(
tds[6].contents[0]),
)
doc_obj.save()
created = True
if created:
if self.profile.initial_migration_done:
print(
'Sending notification: {}'.format(
doc_obj))
send_new_doc_notification(doc_obj)
# print(doc_obj)
else:
header = False
def scrape_cobranza_document(self, causa):
"""Opens the detail of a causa. `causa` is the soup form element"""
session = self.session
url = Scraper.CAUSA_TYPES['cobranza']['detail']
data = {}
for input_elm in causa.find_all('input'):
if 'name' in input_elm.attrs.keys(
) and 'value' in input_elm.attrs.keys():
data[input_elm.attrs['name']] = input_elm.attrs['value']
causa_id = 'COB_{}_{}_{}'.format(data['tipo_causa'], data['rol_causa'],
data['era_causa'])
tr = causa.parent.parent
tds = tr.find_all('td')
caratulado = simplify_string(tds[3].contents[0])
try:
causa_obj = Causa.objects.get(id=causa_id)
except Exception as ex:
causa_obj = Causa(id=causa_id,
user=self.profile,
type=Causa.TYPE_CHOICES_COBRANZA,
archived=False,
rol='{}-{}-{}'.format(data['tipo_causa'],
data['rol_causa'],
data['era_causa']),
caratulado=caratulado)
causa_obj.save()
if self.profile.initial_migration_done:
send_new_causa_notification(causa_obj)
if causa_obj and causa_id:
# print(causa_obj)
# Open causa details:
resp = session.post(url,
data=data,
headers=Scraper.SCRAPER_HEADERS)
if 'Causa Cobranza' in resp.text:
resp_text = resp.content.decode('ISO-8859-1').replace(
'\r', ' ').replace('\n', '')
html = '<html><body>{}</body></html>'.format(resp_text)
soup = BeautifulSoup(html, 'html.parser')
rows = soup.find(id='titTablaCob').parent.find_all('tr')
header = True
for row in rows:
if not header: # skip the header row
doc_data = {}
for doc_input in row.find_all('input'):
try:
doc_data[doc_input.attrs[
'name']] = doc_input.attrs['value']
except:
pass
doc_keys = doc_data.keys()
doc_id = None
if 'cod_tribunal' in doc_keys and 'crr_iddocumento' in doc_keys:
doc_id = 'COB-{}-{}'.format(
doc_data['cod_tribunal'],
doc_data['crr_iddocumento'])
tds = row.find_all('td')
if doc_id:
created = False
try:
doc_obj = DocCobranza.objects.get(id=doc_id)
except:
doc_obj = DocCobranza(
id=doc_id,
causa=causa_obj,
etapa=simplify_string(tds[1].contents[0]),
tramite=simplify_string(
tds[2].contents[0]),
desc_tramite=simplify_string(
tds[3].contents[0]),
fecha=simplify_string(tds[4].contents[0]),
)
doc_obj.save()
created = True
if created:
if self.profile.initial_migration_done:
print('Sending notification: {}'.format(
doc_obj))
send_new_doc_notification(doc_obj)
# print(doc_obj)
else:
header = False
def scrape_civil_document(self, causa):
"""Opens the detail of a causa. `causa` is the soup form element"""
session = self.session
url = Scraper.CAUSA_TYPES['civil']['detail']
data = {}
for input_elm in causa.find_all('input'):
if 'name' in input_elm.attrs.keys(
) and 'value' in input_elm.attrs.keys():
data[input_elm.attrs['name']] = input_elm.attrs['value']
causa_id = 'CIV_{}_{}_{}'.format(data['tipo'], data['rol'],
data['ano'])
tr = causa.parent.parent
tds = tr.find_all('td')
caratulado = simplify_string(tds[3].contents[0])
try:
causa_obj = Causa.objects.get(id=causa_id)
except Exception as ex:
causa_obj = Causa(id=causa_id,
user=self.profile,
type=Causa.TYPE_CHOICES_CIVIL,
archived=False,
rol='{}-{}-{}'.format(data['tipo'], data['rol'],
data['ano']),
caratulado=caratulado)
causa_obj.save()
if self.profile.initial_migration_done:
send_new_causa_notification(causa_obj)
if causa_obj and causa_id:
# print(causa_obj)
# Open causa details:
resp = session.post(url,
data=data,
headers=Scraper.SCRAPER_HEADERS)
if 'Causa Civil' in resp.text:
resp_text = resp.content.decode('ISO-8859-1').replace(
'\r', ' ').replace('\n', '')
html = '<html><body>{}</body></html>'.format(resp_text)
soup = BeautifulSoup(html, 'html.parser')
self.scrape_civil_escrito(causa_id, causa_obj, soup)
rows = soup.find(id='titTablaCiv').parent.parent.find_all(
'tr'
) # double parent becaouse this one has header tr inside <thead>
header = True
for row in rows:
if not header: # skip the header row
tds = row.find_all('td')
if tds[0].contents[0] and tds[0].contents[0].strip(
) != '':
doc_id = '{}__{}'.format(causa_id,
tds[0].contents[0].strip(
)) # id = causa_id__folio
created = False
try:
doc_obj = DocCivil.objects.get(id=doc_id)
except:
tribunal = ''
try:
strongs = soup.find_all('strong')
if len(strongs) >= 8:
tribunal = simplify_string(
strongs[7].parent.contents[1])
except:
pass
doc_obj = DocCivil(
id=doc_id,
causa=causa_obj,
etapa=simplify_string(tds[3].contents[0]),
tramite=simplify_string(
tds[4].contents[0]),
descripcion=simplify_string(
tds[5].contents[0]),
fecha=simplify_string(tds[6].contents[0]),
foja=simplify_string(tds[7].contents[0]),
tribunal=tribunal)
doc_obj.save()
created = True
if created:
if self.profile.initial_migration_done:
print('Sending notification: {}'.format(
doc_obj))
send_new_doc_notification(doc_obj)
# print(doc_obj)
else:
header = False
def scrape_apelaciones_document(self, causa):
"""Opens the detail of a causa. `causa` is the soup form element"""
session = self.session
url = Scraper.CAUSA_TYPES['apelaciones']['detail']
data = {}
for input_elm in causa.find_all('input'):
if 'name' in input_elm.attrs.keys(
) and 'value' in input_elm.attrs.keys():
data[input_elm.attrs['name']] = input_elm.attrs['value']
causa_id = 'APE_{}_{}'.format(data['rol_causa'], data['era_causa'])
tr = causa.parent.parent
tds = tr.find_all('td')
caratulado = simplify_string(tds[3].contents[0])
try:
causa_obj = Causa.objects.get(id=causa_id)
except Exception as ex:
causa_obj = Causa(id=causa_id,
user=self.profile,
type=Causa.TYPE_CHOICES_APELACIONES,
archived=False,
rol='{}-{}'.format(data['rol_causa'],
data['era_causa']),
caratulado=caratulado)
causa_obj.save()
if self.profile.initial_migration_done:
send_new_causa_notification(causa_obj)
if causa_obj and causa_id:
# print(causa_obj)
# Open causa details:
resp = session.post(url,
data=data,
headers=Scraper.SCRAPER_HEADERS)
if 'Recurso Corte de Apelaciones' in resp.text:
resp_text = resp.content.decode('ISO-8859-1').replace(
'\r', ' ').replace('\n', '')
html = '<html><body>{}</body></html>'.format(resp_text)
soup = BeautifulSoup(html, 'html.parser')
rows = soup.find(id='titTablaApeGrid').parent.find_all('tr')
header = True
for row in rows:
if not header: # skip the header row
tds = row.find_all('td')
if tds[2].contents[0] and tds[2].contents[0].strip(
) != '':
doc_id = '{}__{}'.format(
causa_id, tds[2].contents[0].strip())
created = False
try:
doc_obj = DocApelaciones.objects.get(id=doc_id)
except:
libro = ''
nro_ingreso = ''
try:
descPopUps = soup.find_all(
'tr', attrs={'class': 'descPopUp'})
if len(descPopUps) >= 2:
descPopUpData = descPopUps[1].find_all(
'td')
libro = simplify_string(
descPopUpData[0].contents[0])
nro_ingreso = simplify_string(
descPopUpData[1].contents[0])
except:
pass
doc_obj = DocApelaciones(
id=doc_id,
causa=causa_obj,
tipo=simplify_string(tds[1].contents[0]),
descripcion=simplify_string(
tds[3].contents[0]),
fecha=simplify_string(tds[4].contents[0]),
salas=simplify_string(tds[5].contents[0]),
foja_inicial=simplify_string(
tds[6].contents[0]),
libro=libro,
nro_ingreso=nro_ingreso)
doc_obj.save()
created = True
if created:
if self.profile.initial_migration_done:
print('Sending notification: {}'.format(
doc_obj))
send_new_doc_notification(doc_obj)
# print(doc_obj)
else:
header = False
def scrape_suprema_document(self, causa):
"""Opens the detail of a causa"""
session = self.session
url = Scraper.CAUSA_TYPES['suprema']['detail']
data = {}
for input_elm in causa.find_all('input'):
if 'name' in input_elm.attrs.keys(
) and 'value' in input_elm.attrs.keys():
data[input_elm.attrs['name']] = input_elm.attrs['value']
causa_id = 'SUP_{}_{}'.format(data['rol_causa'], data['era_causa'])
try:
causa_obj = Causa.objects.get(id=causa_id)
except Exception as ex:
causa_obj = Causa(id=causa_id,
user=self.profile,
type=Causa.TYPE_CHOICES_SUPREMA,
archived=False,
rol='{}-{}'.format(data['rol_causa'],
data['era_causa']),
caratulado=data['caratulado'])
causa_obj.save()
if self.profile.initial_migration_done:
send_new_causa_notification(causa_obj)
if causa_obj and causa_id:
# print(causa_obj)
# Open causa details:
resp = session.post(url,
data=data,
headers=Scraper.SCRAPER_HEADERS)
if 'Recurso Corte Suprema' in resp.text:
resp_text = resp.content.decode('ISO-8859-1').replace(
'\r', ' ').replace('\n', '')
html = '<html><body>{}</body></html>'.format(resp_text)
soup = BeautifulSoup(html, 'html.parser')
rows = soup.find(id='titTablaSup').parent.find_all('tr')
header = True
for row in rows:
if not header: # skip the header row
tds = row.find_all('td')
iddoc_input = row.find('input',
attrs={'name': 'iddoc'})
if iddoc_input:
doc_id = '{}__{}'.format(
causa_id, iddoc_input.attrs['value'])
created = False
try:
doc_obj = DocSuprema.objects.get(id=doc_id)
except:
doc_obj = DocSuprema(
id=doc_id,
causa=causa_obj,
anio=simplify_string(tds[2].contents[0]),
fecha=simplify_string(tds[3].contents[0]),
tipo=simplify_string(tds[4].contents[0]),
nomenclatura=simplify_string(
tds[5].contents[0]),
descripcion=simplify_string(
tds[6].contents[0]),
salas=simplify_string(tds[7].contents[0]))
doc_obj.save()
created = True
if created:
if self.profile.initial_migration_done:
print('Sending notification: {}'.format(
doc_obj))
send_new_doc_notification(doc_obj)
# print(doc_obj)
else:
header = False