mirrors/recipes
1
0
Fork 0
mirror of https://github.com/TandoorRecipes/recipes.git synced 2026-01-01 12:18:45 -05:00
Code Issues Packages Projects Releases Wiki Activity

helper/recipe_url_import

Browse Source
This commit is contained in:
Tobias Lindenberg
2021-01-10 13:57:06 +01:00
parent 986bda0c81
commit 1ad468e652
1 changed files with 78 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

103
cookbook/helper/recipe_url_import.py
View File

@@ -1,18 +1,16 @@
import json
import random
import re
import unicodedata
from json import JSONDecodeError
import microdata
from bs4 import BeautifulSoup
from cookbook.helper.ingredient_parser import parse as parse_ingredient
from cookbook.models import Keyword
from django.http import JsonResponse
from django.utils.dateparse import parse_duration
from django.utils.translation import gettext as _
from cookbook.models import Keyword
from cookbook.helper.ingredient_parser import parse as parse_ingredient
def get_from_html(html_text, url):
soup = BeautifulSoup(html_text, "html.parser")
@@ -31,10 +29,16 @@ def get_from_html(html_text, url):
if '@type' in x and x['@type'] == 'Recipe':
ld_json_item = x
if '@type' in ld_json_item and ld_json_item['@type'] == 'Recipe':
if ('@type' in ld_json_item
and ld_json_item['@type'] == 'Recipe'):
return find_recipe_json(ld_json_item, url)
except JSONDecodeError as e:
return JsonResponse({'error': True, 'msg': _('The requested site provided malformed data and cannot be read.')}, status=400)
except JSONDecodeError:
return JsonResponse(
{
'error': True,
'msg': _('The requested site provided malformed data and cannot be read.') # noqa: E501
},
status=400)
# now try to find microdata
items = microdata.get_items(html_text)
@@ -43,14 +47,19 @@ def get_from_html(html_text, url):
if 'schema.org/Recipe' in str(md_json['type']):
return find_recipe_json(md_json['properties'], url)
return JsonResponse({'error': True, 'msg': _('The requested site does not provide any recognized data format to import the recipe from.')}, status=400)
return JsonResponse(
{
'error': True,
'msg': _('The requested site does not provide any recognized data format to import the recipe from.') # noqa: E501
},
status=400)
def find_recipe_json(ld_json, url):
if type(ld_json['name']) == list:
try:
ld_json['name'] = ld_json['name'][0]
except:
except Exception:
ld_json['name'] = 'ERROR'
# some sites use ingredients instead of recipeIngredients
@@ -59,8 +68,9 @@ def find_recipe_json(ld_json, url):
if 'recipeIngredient' in ld_json:
# some pages have comma separated ingredients in a single array entry
if len(ld_json['recipeIngredient']) == 1 and len(ld_json['recipeIngredient'][0]) > 30:
ld_json['recipeIngredient'] = ld_json['recipeIngredient'][0].split(',')
if (len(ld_json['recipeIngredient']) == 1
and len(ld_json['recipeIngredient'][0]) > 30):
ld_json['recipeIngredient'] = ld_json['recipeIngredient'][0].split(',') # noqa: E501
for x in ld_json['recipeIngredient']:
if '\n' in x:
@@ -71,13 +81,41 @@ def find_recipe_json(ld_json, url):
ingredients = []
for x in ld_json['recipeIngredient']:
if x.replace(' ','') != '':
if x.replace(' ', '') != '':
try:
amount, unit, ingredient, note = parse_ingredient(x)
if ingredient:
ingredients.append({'amount': amount, 'unit': {'text': unit, 'id': random.randrange(10000, 99999)}, 'ingredient': {'text': ingredient, 'id': random.randrange(10000, 99999)}, "note": note, 'original': x})
except:
ingredients.append({'amount': 0, 'unit': {'text': "", 'id': random.randrange(10000, 99999)}, 'ingredient': {'text': x, 'id': random.randrange(10000, 99999)}, "note": "", 'original': x})
ingredients.append(
{
'amount': amount,
'unit': {
'text': unit,
'id': random.randrange(10000, 99999)
},
'ingredient': {
'text': ingredient,
'id': random.randrange(10000, 99999)
},
'note': note,
'original': x
}
)
except Exception:
ingredients.append(
{
'amount': 0,
'unit': {
'text': '',
'id': random.randrange(10000, 99999)
},
'ingredient': {
'text': x,
'id': random.randrange(10000, 99999)
},
'note': '',
'original': x
}
)
ld_json['recipeIngredient'] = ingredients
else:
@@ -91,7 +129,9 @@ def find_recipe_json(ld_json, url):
ld_json['keywords'] = ld_json['keywords'].split(',')
# keywords as string in list
if type(ld_json['keywords']) == list and len(ld_json['keywords']) == 1 and ',' in ld_json['keywords'][0]:
if (type(ld_json['keywords']) == list
and len(ld_json['keywords']) == 1
and ',' in ld_json['keywords'][0]):
ld_json['keywords'] = ld_json['keywords'][0].split(',')
# keywords as list
@@ -126,10 +166,10 @@ def find_recipe_json(ld_json, url):
instructions += str(i)
ld_json['recipeInstructions'] = instructions
ld_json['recipeInstructions'] = re.sub(r'\n\s*\n', '\n\n', ld_json['recipeInstructions'])
ld_json['recipeInstructions'] = re.sub(' +', ' ', ld_json['recipeInstructions'])
ld_json['recipeInstructions'] = ld_json['recipeInstructions'].replace('<p>', '')
ld_json['recipeInstructions'] = ld_json['recipeInstructions'].replace('</p>', '')
ld_json['recipeInstructions'] = re.sub(r'\n\s*\n', '\n\n', ld_json['recipeInstructions']) # noqa: E501
ld_json['recipeInstructions'] = re.sub(' +', ' ', ld_json['recipeInstructions']) # noqa: E501
ld_json['recipeInstructions'] = ld_json['recipeInstructions'].replace('<p>', '') # noqa: E501
ld_json['recipeInstructions'] = ld_json['recipeInstructions'].replace('</p>', '') # noqa: E501
else:
ld_json['recipeInstructions'] = ''
@@ -149,9 +189,14 @@ def find_recipe_json(ld_json, url):
if 'cookTime' in ld_json:
try:
if type(ld_json['cookTime']) == list and len(ld_json['cookTime']) > 0:
if (type(ld_json['cookTime']) == list
and len(ld_json['cookTime']) > 0):
ld_json['cookTime'] = ld_json['cookTime'][0]
ld_json['cookTime'] = round(parse_duration(ld_json['cookTime']).seconds / 60)
ld_json['cookTime'] = round(
parse_duration(
ld_json['cookTime']
).seconds / 60
)
except TypeError:
ld_json['cookTime'] = 0
else:
@@ -159,16 +204,24 @@ def find_recipe_json(ld_json, url):
if 'prepTime' in ld_json:
try:
if type(ld_json['prepTime']) == list and len(ld_json['prepTime']) > 0:
if (type(ld_json['prepTime']) == list
and len(ld_json['prepTime']) > 0):
ld_json['prepTime'] = ld_json['prepTime'][0]
ld_json['prepTime'] = round(parse_duration(ld_json['prepTime']).seconds / 60)
ld_json['prepTime'] = round(
parse_duration(
ld_json['prepTime']
).seconds / 60
)
except TypeError:
ld_json['prepTime'] = 0
else:
ld_json['prepTime'] = 0
for key in list(ld_json):
if key not in ['prepTime', 'cookTime', 'image', 'recipeInstructions', 'keywords', 'name', 'recipeIngredient']:
if key not in [
'prepTime', 'cookTime', 'image', 'recipeInstructions',
'keywords', 'name', 'recipeIngredient'
]:
ld_json.pop(key, None)
return JsonResponse(ld_json)