moc['materia'] = tr.text.replace('Materia:','').strip()
elif 'Iniciativa:' in tr.text:
moc['iniciativa'] = tr.text.replace('Iniciativa:','').strip()
elif 'Cámara de origen:' in tr.text:
moc['origen'] = tr.text.replace('Cámara de origen:','').strip()
# Hitos
for tr in browser.find_elements_by_css_selector('table#ctl00_mainPlaceHolder_grvtramitacion tbody tr'):
cols = tr.find_elements_by_tag_name('td')
if len(cols) > 4:
hito = {
"fecha": cols[0].text,
"sesion": cols[1].text,
"etapa": cols[2].text,
"sub_etapa": cols[3].text,
"documento_link": scraperhelper.getQueryParametersElementChild(cols[4])[0]
}
moc['hitos'].append(hito)
# Informes
browser.execute_script("__doPostBack('ctl00$mainPlaceHolder$btnInformes','')")
WebDriverWait(browser, 10).until(EC.presence_of_element_located((By.ID, 'ctl00_mainPlaceHolder_pnlInformes')))
for tr in browser.find_elements_by_css_selector('table#ctl00_mainPlaceHolder_grvinformes tbody tr'):
cols = tr.find_elements_by_tag_name('td')
if len(cols) > 3:
informe = {
"fecha": cols[0].text,
"etapa": cols[1].text,
"informe": cols[2].text,
"documento_link": scraperhelper.getQueryParametersElementChild(cols[3])[0]
}
# Go to 'Ordenes del día'
browser.get(
'https://www.camara.cl/trabajamos/sesion_ordendia.aspx?prmid=' +
session['prmid'])
for el in browser.find_elements_by_css_selector('#detail .stress'):
table = el.find_elements_by_tag_name('td')
if (len(table) > 0):
boletin = {
"boletin":
el.find_element_by_tag_name('h2').text.replace(
'Boletín ', ''),
"proyecto":
table[0].text.replace('ver detalle', ''),
"pley_prmid":
scraperhelper.getQueryParametersElementChild(table[0])[0],
"origen":
table[1].text,
"reglamentaria":
table[2].text,
"informantes":
table[3].text,
"informes": []
}
infs = table[4].find_elements_by_css_selector('tbody tr')
for tr in infs:
cols = tr.find_elements_by_tag_name('td')
if (len(cols) > 0):
inf = {
"fecha":
'#main table.tabla tbody tr'):
cols = tr.find_elements_by_tag_name('td')
if len(cols) > 5:
res = {
"ingreso":
cols[0].text,
"numero":
cols[1].text,
"titulo":
cols[2].text,
"estado":
cols[3].text,
"documento_link":
scraperhelper.getLinkFromElementChild(cols[4]),
"prmid":
scraperhelper.getQueryParametersElementChild(cols[5])[0]
}
data.append(res)
next_buttons = browser.find_elements_by_css_selector(
'.pages ul li.next a')
if len(next_buttons) > 0:
page = page + 1
browser.execute_script(
next_buttons[0].get_attribute('href').replace(
'javascript:', ''))
page_number = scraperhelper.waitForChangesInAttribute(
browser, '.pages ul li.current', page_number, text=True)
scraperhelper.pt('Loading Page ' + str(page))
else:
break