feat: parse scraped ingredients (#26)

CONTRIBUTING.md

@@ -34,7 +34,8 @@ The `description` is a descriptive summary of the change the PR will make.
 - Create a python environment `python3 -m venv venv`
 - Activate your python environment `source venv/bin/activate` (environment can be deactivated with `deactivate`)
 - Install dependencies `pip3 install -r requirements.txt`
-- Initialize/Upgrade the sqlite database with `flask db upgrade`
+- Initialize/Upgrade the SQLite database with `flask db upgrade`
+- Initialize/Upgrade requirements for the recipe scraper `python -c "import nltk; nltk.download('averaged_perceptron_tagger')"`
 - Run debug server with `python3 wsgi.py` or without debugging `flask run`
 - The backend should be reachable at `localhost:5000`
 

Dockerfile

@@ -38,6 +38,8 @@ COPY migrations /usr/src/kitchenowl/migrations
 WORKDIR /usr/src/kitchenowl
 VOLUME ["/data"]
 
+RUN python -c "import nltk; nltk.download('averaged_perceptron_tagger')"
+
 ENV STORAGE_PATH='/data'
 ENV JWT_SECRET_KEY='PLEASE_CHANGE_ME'
 ENV DEBUG='False'

app/controller/recipe/recipe_controller.py

@@ -13,6 +13,7 @@
 from app.models import Recipe, Item, Tag
 from recipe_scrapers import scrape_me
 from recipe_scrapers._exceptions import SchemaOrgException
+from ingredient_parser import parse_ingredient
 from werkzeug.utils import secure_filename
 from .schemas import SearchByNameRequest, AddRecipe, UpdateRecipe, GetAllFilterRequest, ScrapeRecipe
 
@@ -218,7 +219,16 @@ def scrapeRecipe(args):
  recipe.source = args['url']
  items = {}
  for ingredient in scraper.ingredients():
- items[ingredient] = None
+ parsed = parse_ingredient(ingredient)
+ item = Item.find_by_name(1, parsed['name'])
+ if not item:
+ item = Item(name=parsed['name'])
+
+ items[ingredient] = item.obj_to_dict() | {
+ "description": ' '.join(
+ filter(None, [parsed['quantity'] + parsed['unit'], parsed['comment']])),
+ "optional": False,
+ }
  return jsonify({
  'recipe': recipe.obj_to_dict(),
  'items': items,

requirements.txt

@@ -26,6 +26,7 @@ greenlet==2.0.2
 html-text==0.5.2
 html5lib==1.1
 idna==3.4
+ingredient-parser-nlp==0.1.0b1
 iniconfig==2.0.0
 isodate==0.6.1
 itsdangerous==2.1.2
@@ -43,6 +44,7 @@ mccabe==0.7.0
 mf2py==1.1.2
 mlxtend==0.22.0
 mypy-extensions==1.0.0
+nltk==3.8.1
 numpy==1.24.2
 packaging==23.0
 pandas==2.0.0
@@ -58,6 +60,7 @@ PyJWT==2.6.0
 pyparsing==3.0.9
 pyRdfa3==3.5.3
 pytest==7.2.2
+python-crfsuite==0.9.9
 python-dateutil==2.8.2
 python-editor==1.0.4
 pytz==2023.3
@@ -76,8 +79,10 @@ SQLAlchemy==2.0.8
 threadpoolctl==3.1.0
 toml==0.10.2
 tomli==2.0.1
+tqdm==4.65.0
 typed-ast==1.5.4
 types-beautifulsoup4==4.12.0.1
+types-html5lib==1.1.11.10
 types-requests==2.28.11.17
 types-urllib3==1.26.25.10
 typing_extensions==4.5.0