2022-10-15 14:40:42 -04:00
|
|
|
from recipe_graph import scrape
|
2023-05-17 22:01:19 -04:00
|
|
|
from bs4 import BeautifulSoup
|
2022-10-15 14:40:42 -04:00
|
|
|
|
2023-05-17 22:01:19 -04:00
|
|
|
import pytest
|
|
|
|
|
|
|
|
|
|
|
2023-05-18 08:57:33 -04:00
|
|
|
def test_load_page():
|
|
|
|
|
page = scrape.load_page("https://hs.andreistoica.ca:4943")
|
2023-05-17 22:01:19 -04:00
|
|
|
assert type(page) == BeautifulSoup
|
|
|
|
|
|
2023-05-18 08:57:33 -04:00
|
|
|
page = scrape.load_page("https://hs.andreistoica.ca:4943/some-nonesense")
|
2023-05-18 16:02:14 -04:00
|
|
|
assert page == None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def test_ingredient_regex():
|
|
|
|
|
regex = scrape.ingredient_regex(["cup"], ["crushed"])
|
|
|
|
|
assert (
|
|
|
|
|
regex.pattern
|
|
|
|
|
== "((?:[\\d\\./\\u00BC-\\u00BE\\u2150-\\u215E]*\\s?(?:\\(.+\\))?)*)((?:(?:[cC]up)e?s?)?)((?:(?:(?:[cC]rushed)(?:ly)?)| )*)([a-zA-Z '\\-]+),?(.*)"
|
|
|
|
|
)
|
|
|
|
|
regex = scrape.ingredient_regex(["cup", "ounce"], ["crushed", "ground"])
|
|
|
|
|
assert (
|
|
|
|
|
regex.pattern
|
|
|
|
|
== "((?:[\\d\\./\\u00BC-\\u00BE\\u2150-\\u215E]*\\s?(?:\\(.+\\))?)*)((?:(?:[cC]up|[oO]unce)e?s?)?)((?:(?:(?:[cC]rushed|[gG]round)(?:ly)?)| )*)([a-zA-Z '\\-]+),?(.*)"
|
|
|
|
|
)
|
