def test_should_retrieve_products_from_query(self, store, query):
ProductDatabase.clear_database()
extractor = PageExtractor(store)
products_list = extractor.retrieve_products_from_query(query)
assert type(products_list) == list
# Cannot check for equal because there might be items repited which were not inserted in the database
assert len(products_list) >= ProductDatabase.get_products_total()
def test_should_get_info_list_about_products(self, store, query):
# previous_product_total = ProductDatabase.get_products_total()
extractor = PageExtractor(store)
parsed_html = extractor.retrieve_html_parsed_from_query(query)
items_list = extractor.get_info_list_about_products(parsed_html)
assert type(items_list) == list
assert type(items_list[0]) == dict
def test_should_get_info_dict_for_product(self, store, query):
extractor = PageExtractor(store)
parsed_html = extractor.retrieve_html_parsed_from_query(query)
parsed_list = extractor.get_items_list_from_parsed_html(parsed_html)
item = extractor.get_info_dict_for_product(parsed_list[0])
# import pdb; pdb.set_trace()
assert type(parsed_list) == element.ResultSet
assert type(item) == dict
assert item['name'] is not None
assert item['link'] is not None
def test_should_store_products_on_json(self, store, query):
import os
ProductDatabase.clear_database()
filename = 'test.json'
extractor = PageExtractor(store)
products_list = extractor.retrieve_products_from_query(query)
extractor.store_products_on_json(products_list, filename)
# import pdb; pdb.set_trace()
assert os.path.exists(filename) == True
# Cannot check for equal because there might be items repited which were not inserted in the database
assert len(products_list) >= ProductDatabase.get_products_total()
def test_should_query_webdriver(self):
import os
# import pandas as pd
from products import Product
ProductDatabase.clear_database()
filename = 'test.json'
extractor = PageExtractor('submarino')
products_list = extractor.query_webdriver("goblet of fire")
products = [Product(item_attrs) for item_attrs in products_list]
extractor.store_products_on_json(products, filename)
# import pdb; pdb.set_trace()
filtered_products = ProductDatabase.filter(price__gte=700,
price__lt=1000)
extractor.store_products_on_json(filtered_products,
'test_filtered.json')
# df = pd.DataFrame({
# 'name': [prod.name for prod in filtered_products],
# 'price': [prod.price for prod in filtered_products]
# })
assert os.path.exists(filename) == True
# We cant check it like this since the add_product on ProductDatabase checks whether the product was already inserted
# assert len(products_list) == ProductDatabase.get_products_total()
assert ProductDatabase.get_products_total() != 0
def test_should_get_items_list_from_parsed_html(self, store, query):
extractor = PageExtractor(store)
parsed_html = extractor.retrieve_html_parsed_from_query(query)
parsed_list = extractor.get_items_list_from_parsed_html(parsed_html)
assert type(parsed_list) == element.ResultSet
assert type(parsed_list[0]) == element.Tag
def test_should_retrieve_html_parsed_from_query(self, store, query):
extractor = PageExtractor(store)
parsed_html = extractor.retrieve_html_parsed_from_query(query)
assert type(parsed_html) == BeautifulSoup
assert extractor.parsed_html == parsed_html
def test_should_get_search_url(self, store, query, expected_url):
extractor = PageExtractor(store)
assert extractor.get_search_url(query) == expected_url
def test_should_get_tag_and_class_for_info(self, store, item,
expected_tuple):
extractor = PageExtractor(store)
tag_and_class = extractor.get_tag_and_class_for_info(item)
assert tag_and_class == expected_tuple
def test_should_init(self):
extractor = PageExtractor('magazineluiza')
assert extractor.store_id == 'magazineluiza'
def test_should_convert_BRL_currency_to_float(self, currency_str,
expected_float):
value = PageExtractor.convert_BRL_currency_to_float(currency_str)
assert value == expected_float