"asistencia": tds[2].text,
"observacion": tds[3].text,
"ingreso": tds[4].text
}
sesion['asistencia'].append(asistencia)
# scraperhelper.pt('Assistance Scraped')
"""
browser.get(
'https://www.camara.cl/trabajamos/sesion_asistencia.aspx?prmid=' +
session['prmid'])
js_script = "return_scrap_array = []; $('#detail .col.detalle table.tabla tbody tr').each(function(index) { return_scrap_array.push($(this).find('td').get().map( (td) => [td.textContent, td.getElementsByTagName('a')[0] ? td.getElementsByTagName('a')[0].href : ''] ) )}); return JSON.stringify(return_scrap_array);"
asist_array = json.loads(browser.execute_script(js_script))
for asist in asist_array:
asistencia = {
"diputado_prmid":
scraperhelper.getQueryParametersFromUrl(asist[0][1])[0],
"partido_prmid":
asist[1][0],
"asistencia":
asist[2][0],
"observacion":
asist[3][0],
"ingreso":
asist[4][0]
}
sesion['asistencia'].append(asistencia)
# Go to 'Intervenciones'
browser.get(
'https://www.camara.cl/trabajamos/sesion_intervenciones.aspx?prmid='
+ session['prmid'])
scraperhelper.pt('Get Handy Elements')
while int(option_selected) > 45:
scraperhelper.pt('Get year id: ' + str(option_selected) + ' ----------')
page_number = browser.find_element_by_css_selector('#detail .pages ul li.current').text
subcount = 1
while True:
scraperhelper.pt('Get Sessions: Page ' + str(subcount))
subcount = subcount + 1
rows = browser.find_elements_by_css_selector('#detail table.tabla tbody tr')
for row in rows:
try:
columns = row.find_elements_by_css_selector('td')
prmid = scraperhelper.getQueryParametersFromUrl(columns[1].find_element_by_tag_name('a').get_attribute('href'))
sesion = {
"fecha":columns[0].text,
"sesion":columns[1].text,
"estado":columns[2].text,
"prmid":prmid[0]
}
data.append(sesion)
except StaleElementReferenceException:
print('ERROR!! -----')
next_buttons = browser.find_elements_by_css_selector('#detail .pages ul li.next a')
if len(next_buttons) > 0:
browser.execute_script(next_buttons[0].get_attribute('href').replace('javascript:',''))
page_number = scraperhelper.waitForChangesInAttribute(browser, '#detail .pages ul li.current', page_number, text = True)
else:
"abstencion": [],
"articulo_quinto": [],
"pareos": []
}
for el in browser.find_elements_by_css_selector('#detail .stress'):
try:
h2 = el.find_element_by_tag_name('h2').text
except NoSuchElementException as ex:
h2 = 'SIN TITULO'
if 'A favor' in h2:
for a in el.find_elements_by_css_selector('#ctl00_mainPlaceHolder_dtlAFavor td a'):
vote['favor'].append(scraperhelper.getQueryParametersFromUrl(a.get_attribute('href'))[0])
elif 'En contra' in h2:
for a in el.find_elements_by_css_selector('#ctl00_mainPlaceHolder_dtlEncontra td a'):
vote['contra'].append(scraperhelper.getQueryParametersFromUrl(a.get_attribute('href'))[0])
elif 'Abstención' in h2:
for a in el.find_elements_by_css_selector('#ctl00_mainPlaceHolder_dtlAbstencion td a'):
vote['abstencion'].append(scraperhelper.getQueryParametersFromUrl(a.get_attribute('href'))[0])
elif 'Artículo 5°' in h2:
for a in el.find_elements_by_css_selector('table td a'):
vote['articulo_quinto'].append(scraperhelper.getQueryParametersFromUrl(a.get_attribute('href'))[0])
elif 'Pareos' in h2:
for a in el.find_elements_by_css_selector('#ctl00_mainPlaceHolder_dtlPareos td a'):
vote['pareos'].append(scraperhelper.getQueryParametersFromUrl(a.get_attribute('href'))[0])
else:
vote['boletin'] = h2.replace('Boletín ','')
vote['fecha'] = scraperhelper.getRestOfTheTextForElementWith(el, './p', 'Fecha:').strip()
browser = scraperhelper.initBrowser()
# output lists
data = []
errors = []
# main script GO!
try:
browser.get('https://www.camara.cl/camara/diputados.aspx')
scraperhelper.pt('Get Current Reps Site')
content = browser.find_elements_by_css_selector('li.alturaDiputado h4 a')
for el in content:
data.append({
"prmid":
scraperhelper.getQueryParametersFromUrl(
el.get_attribute('href'))[0],
"nombre":
str(el.text.replace('SR. ', '').replace('SRA. ', '')),
"periodo":
"2014-2018"
})
except TimeoutException as ex:
scraperhelper.pt('PAGE TimeoutException ERROR')
except NoSuchElementException as ex:
scraperhelper.pt('PAGE NoSuchElementException ERROR')
except StaleElementReferenceException as ex:
scraperhelper.pt('PAGE StaleElementReferenceException ERROR')
except WebDriverException as ex:
scraperhelper.pt('PAGE WebDriverException ERROR')