def parseRecipes(urls):
recipeList = []
for url in urls:
print("Getting Recipe for " + str(url))
#web-scrape
data = scrap_me(url)
recipeName = data.title()
recipeTime = int(data.prepTime())
recipeDescription = data.description()
recipeIngredients = data.ingredients()
recipeInstructions = data.instructions()
#clean-up
recipeInstructions = removeAds(recipeInstructions)
recipeIngredients = [
parseIngredient(removeAds(i)) for i in recipeIngredients
]
recipeIngredients = [x for x in recipeIngredients if x is not None]
#storage
recipeList.append(
Recipe(recipeName, recipeDescription, recipeInstructions,
recipeTime, recipeIngredients))
#to store into DB
ingredientList = findUniqueIngredients(recipeList)
return ingredientList, recipeList
def get_recipe(url):
try:
scrap = scrap_me(url)
except:
print('Could not scrape URL {}'.format(url))
return {}
try:
title = scrap.title()
except AttributeError:
title = None
try:
ingredients = scrap.ingredients()
except AttributeError:
ingredients = None
try:
instructions = scrap.instructions()
except AttributeError:
instructions = None
try:
picture_link = scrap.picture()
except AttributeError:
picture_link = None
return {
'title': title,
'ingredients': ingredients,
'instructions': instructions,
'picture_link': picture_link,
}
def post(self, request, *args, **kwargs):
url = request.data.get('url')
if url:
try:
data = scrap_me(url)
response = {}
response['title'] = self.mine_data(data, 'title')
response['servings'] = self.mine_data(data, 'servings')
response['ingredients'] = self.mine_data(data, 'ingredients')
response['info'] = self.mine_data(data, 'description')
response['image'] = self.mine_data(data, 'image')
response['source'] = url
# Get the directions and add a step key to it.
response['directions'] = [{
'step': i + 1,
'title': instruction
} for i, instruction in enumerate(data.instructions())]
# Break the total time into two groups.
# Prep Time and Cook Time.
total_time = self.mine_data(data, 'total_time')
if 'prep-time' in total_time:
response['prep_time'] = total_time.get('prep-time', '')
if 'cook-time' in total_time:
response['cook_time'] = total_time.get('cook-time', '')
return Response(response)
except:
return Response({
'error': '2',
'response': 'Bad URL or URL not supported'
})
return Response({'error': '3', 'response': 'No URL given.'})
def __init__(self, recipe_link="", image_link=""):
recipe_count = 0
from recipe_scrapers import scrap_me
scraped_recipe = scrap_me(recipe_link)
self.title = scraped_recipe.title()
self.number = "Recipe_" + str(len(Recipe.recipe_list)).zfill(2)
self.time = scraped_recipe.total_time()
self.ingredient_list = scraped_recipe.ingredients()
self.instructions = scraped_recipe.instructions()
self.image_link = image_link
Recipe.recipe_dict[self] = [self.number, self.title]
Recipe.recipe_list.append([self, self.number, self.title])
Recipe.all_ingredient_list.append(self.ingredient_list)
from recipe_scrapers import scrap_me
scrap = scrap_me("https://www.epicurious.com/recipes/food/views/creamy-pasta-with-crispy-mushrooms")
print(scrap.tags())
print(scrap.servings())
scrap = scrap_me("https://www.foodnetwork.com/recipes/trisha-yearwood/slow-cooker-georgia-pulled-pork-barbeque-recipe-2078315")
print(scrap.tags())
scrap = scrap_me("https://www.allrecipes.com/recipe/17991/stuffed-green-peppers-i/?internalSource=previously%20viewed&referringContentType=Homepage")
print(scrap.servings())
#!/usr/bin/python3
from recipe_scrapers import scrap_me
s = scrap_me(
"http://allrecipes.com/recipe/221093/good-frickin-paprika-chicken/")
try:
print("~~~~~~~~~~~TITLE~~~~~~~~~~~~~")
print(s.title())
except Exception:
print("no title")
try:
print("~~~~~~~~~~~TIME~~~~~~~~~~~~~")
print(s.total_time())
except Exception:
print("no time")
try:
print("~~~~~~~~~~~INGREDIENTS~~~~~~~~~~~~~")
print(s.ingredients())
except Exception:
print("no ingredients")
try:
print("~~~~~~~~~~~INSTRUCTIONS~~~~~~~~~~~~~")
print(s.instructions())
except Exception:
print("no instructions")
try:
print("~~~~~~~~~~~IMAGE~~~~~~~~~~~~~")
print(s.image())
except Exception:
lower - upper
150000 - 152000 - niha
152000 - 154000 - farhan
154000 - 156000 - jay
156000 - 158000 - sid
'''
#Change these
lower = 158000
upper = 160000
cols = ['title', 'time', 'ingredients', 'instructions']
list = pd.DataFrame(columns=cols)
recipeNames = []
for i in range(lower, upper, 1):
try:
s = scrap_me('http://allrecipes.com/recipe/' + str(i))
print(i)
if (s.title() not in recipeNames):
time.sleep(1)
recipeNames.append(s.title())
list.loc[len(list)] = [
s.title(),
s.total_time(),
s.ingredients(),
s.instructions()
]
print(s.title())
if len(list) >= 5000:
break
except Exception:
print("not found recipe: {}".format(i))
def get_recipe(url):
try:
scrap = scrap_me(url)
except:
print('Could not scrape URL {}'.format(url))
return {}
try:
title = scrap.title()
except AttributeError:
title = None
try:
ingredients = scrap.ingredients()
except AttributeError:
ingredients = None
try:
instructions = scrap.instructions()
except AttributeError:
instructions = None
try:
picture_link = scrap.picture()
except AttributeError:
picture_link = None
try:
fat_content = scrap.fatContent()
except AttributeError:
fat_content = None
try:
satfat_content = scrap.satfatContent()
except AttributeError:
satfat_content = None
# try:
# pufa_content = scrap.pufaContent()
# except AttributeError:
# pufa_content = None
#
# try:
# mufa_content = scrap.mufaContent()
# except AttributeError:
# mufa_content = None
try:
sodium_content = scrap.sodiumContent()
except AttributeError:
sodium_content = None
try:
carb_content = scrap.carbContent()
except AttributeError:
carb_content = None
try:
protein_content = scrap.proteinContent()
except AttributeError:
protein_content = None
try:
fiber_content = scrap.fiberContent()
except AttributeError:
fiber_content = None
try:
calories = scrap.calories()
except AttributeError:
calories = None
try:
tag_cuisine = scrap.tagCuisine()
except AttributeError:
tag_cuisine = None
try:
tag_special = scrap.tagSpecial()
except AttributeError:
tag_special = None
try:
tag_meal = scrap.tagMeal()
except AttributeError:
tag_meal = None
try:
tag_tag = scrap.tagTag()
except AttributeError:
tag_tag = None
try:
tag_ingre = scrap.tagIngre()
except AttributeError:
tag_ingre = None
try:
tag_type = scrap.tagType()
except AttributeError:
tag_type = None
try:
tag_occasion = scrap.tagOccasion()
except AttributeError:
tag_occasion = None
try:
tag_tech = scrap.tagTech()
except AttributeError:
tag_tech = None
try:
tag_equip = scrap.tagEquip()
except AttributeError:
tag_equip = None
try:
tag_source = scrap.tagSource()
except AttributeError:
tag_source = None
try:
total_time = scrap.totalTime()
except AttributeError:
total_time = None
return {
'title': title,
'ingredients': ingredients,
'instructions': instructions,
'picture_link': picture_link,
'fat_content': fat_content,
'satfat_content': satfat_content,
# 'pufa_content' : pufa_content,
# 'mufa_content' : mufa_content,
'sodium_content': sodium_content,
'carb_content': carb_content,
'protein_content': protein_content,
'fiber_content': fiber_content,
'calories': calories,
'tag_cuisine': tag_cuisine,
'tag_special': tag_special,
'tag_meal': tag_meal,
'tag_tag': tag_tag,
'tag_ingredient': tag_ingre,
'tag_type': tag_type,
'tag_occasion': tag_occasion,
'tag_tech': tag_tech,
'tag_equipment': tag_equip,
'tag_source': tag_source,
'total_time': total_time
}