def picture(ingredients):
ua = 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:32.0) Gecko/20100101 Firefox/32.0'
headers = {'User-Agent': ua, 'Accept': '*/*'}
all_imgs = {}
extra_stuff = '&tbm=isch'
for ingredient in ingredients.split(','):
sanitized_ingr = sanitize_ingredients.sanitize(ingredient)
query = 'https://www.google.ca/search?q=' + sanitized_ingr + extra_stuff
try:
page = requests.get(query, headers=headers, timeout=2)
tree = html.fromstring(page.text)
path = '/html/body/div[5]/div[4]/div[2]/div[3]/div/div[2]/div[2]/div/div/div/div/div[1]/div[1]/div[1]/div[1]/a/@href'
img = tree.xpath(path)
if len(img) > 0:
img = img[0]
img_url = img[img.find("imgurl=")+7:img.find("&")]
all_imgs[ingredient] = img_url
else:
all_imgs[ingredient] = []
except requests.exceptions.Timeout:
logging.warning("TIMEOUT GETTING PICTURE")
except requests.exceptions.ConnectionError:
logging.warning("CONNECTIONERROR GETTING PICTURE")
return all_imgs
def test_sanitize_ingredients(self):
urls = mock_yummly.search('turkeysandwich')[0]
ingredients = urls[2]
self.assertEqual('cooked turkey', sanitize_ingredients.sanitize(ingredients[0]))
self.assertEqual('celery ribs,', sanitize_ingredients.sanitize(ingredients[1]))
self.assertEqual('small onion,', sanitize_ingredients.sanitize(ingredients[2]))
self.assertEqual('hard-cooked eggs,', sanitize_ingredients.sanitize(ingredients[3]))
self.assertEqual('mayonnaise', sanitize_ingredients.sanitize(ingredients[4]))
self.assertEqual('salt', sanitize_ingredients.sanitize(ingredients[5]))
self.assertEqual('pepper', sanitize_ingredients.sanitize(ingredients[6]))
self.assertEqual('hamburger buns,', sanitize_ingredients.sanitize(ingredients[7]))
