def start():
try:
global start_url, current_page, resultPath
init()
printDH('Iniciando la app...')
driver.get(start_url)
name = driver.find_element_by_css_selector('#HEADING').text.encode('UTF-8')
image = None
try:
image = driver.find_element_by_css_selector('#HERO_PHOTO')
image = image.get_attribute('src')
except:
try:
image = driver.find_element_by_css_selector('#BIG_PHOTO_CAROUSEL img')
image = image.get_attribute('src')
except:
image = "https://watermarkherveybay.files.wordpress.com/2015/08/tripadvisor-logo-nw1.jpg?w=620&h=350"
printDH('Extrayendo las opiniones de %s' % name)
printDH('Leyendo la página %d de %d' % (current_page, max_page))
reviews = parse_reviews_list()
while(if_next_page_exists_go()):
current_page+=1
printDH('Leyendo la página %d de %d' % (current_page, max_page) )
reviews = reviews + parse_reviews_list()
result = {'@context':'http://schema.org', 'name':name, 'image':image, 'reviews':reviews}
saveText(json.dumps(result), resultPath)
#print json.dumps(result)
except Exception as e:
print str(e)
returnError()
def returnError(error=None):
global resultPath
item = {'error':'Crawler has failed to fetch the comments', 'loading':False}
saveText(json.dumps(item), resultPath)
