def get_sale_items():
base_url = "https://espressocanada.com/collections/saeco-philips-and-jura-superautomatic-coffee-machines"
soup = scanutil.get_soup(base_url)
website = 'espressocanada.com'
sale_spans = soup.select('span.sale')
sale_items = []
for sale_span in sale_spans:
if sale_span.select('span.sold_out'):
continue
sale_item = {
'type':
'superauto',
'name':
sale_span.parent.select('span.title')[0].text.strip(),
'image':
f"https:{sale_span.parent.parent.parent.select('img.noscript')[0]['src'].strip()}",
'url':
f"https://espressocanada.com{sale_span.parent.parent.parent.select('a')[0]['href'].strip()}",
'regular_price':
scanutil.get_money(sale_span.select('span.was_price')[0].text),
'sale_price':
scanutil.get_money(sale_span.select('span.money')[0].text),
'website':
website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type):
base_url = f"https://www.consiglioskitchenware.com/collections/{page_type}?view=view-48"
soup = scanutil.get_soup(base_url)
website = 'consiglioskitchenware.com'
page_links = soup.select('a.pagination--item')
if page_links:
num_pages = len(page_links)
else:
num_pages = 1
sale_items = []
for page_num in range(1,num_pages+1):
if page_num > 1:
soup = scanutil.get_soup(f"{base_url}&page={page_num}")
orig_prices = soup.select('div.price--compare-at')
for orig_price in orig_prices:
if orig_price.text.strip() == "" or orig_price.parent.parent.parent.select('a') == []:
continue
sale_item = {
'name' : orig_price.parent.parent.select('h2')[0].text.strip(),
'image' : f"https:{orig_price.parent.parent.parent.select('img')[0]['src'].strip()}",
'url' : f"https://consiglioskitchenware.com{orig_price.parent.parent.select('a')[0]['href'].strip()}",
'regular_price' : scanutil.get_money(orig_price.text),
'sale_price' : scanutil.get_money(orig_price.parent.parent.select('div.price--main')[0].text),
'website' : website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type):
base_url = f"https://www.espressotec.com/{page_type}?sort=pricedesc&limit=100&mode=4"
soup = scanutil.get_soup(base_url)
website = 'espressotec.com'
sale_items = []
sale_tags = soup.select('span.sale-text')
for sale_tag in sale_tags:
sale_item = {
'name':
sale_tag.parent.parent.parent.select('h4')[0].text.strip(),
'image':
sale_tag.parent.parent.select('img')[0]['src'].strip(),
'url':
sale_tag.parent.parent.select('a')[0]['href'].strip(),
'regular_price':
scanutil.get_money(
sale_tag.parent.parent.parent.select('span.price--non-sale')
[0].text),
'sale_price':
scanutil.get_money(
sale_tag.parent.parent.parent.select('span.price--withoutTax')
[0].text),
'website':
website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type):
base_url = f"https://greenbeanery.ca/collections/{page_type}"
soup = scanutil.get_soup(base_url)
website = 'greenbeanery.ca'
sale_items = []
sale_spans = soup.select('span.sale')
for sale_span in sale_spans:
if sale_span.parent.select('span.sold_out'):
continue
sale_item = {
'name':
sale_span.parent.select('span.title')[0].text.strip(),
'image':
f"https:{sale_span.parent.parent.parent.select('img')[0]['data-src'].strip()}",
'url':
f"https://greenbeanery.ca{sale_span.parent.parent.parent.select('a')[0]['href'].strip()}",
'regular_price':
scanutil.get_money(sale_span.select('span.money')[1].text),
'sale_price':
scanutil.get_money(sale_span.select('span.money')[0].text),
'website':
website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type):
base_url = f"https://www.homecoffeesolutions.com/collections/{page_type}"
page = requests.get(base_url)
soup = BeautifulSoup(page.content, 'html.parser')
website = 'homecoffeesolutions.com'
pages = soup.select('div.pagination__nav a')
if pages:
num_pages = int(int(pages[-1].text) / 2)
# Why is it double???
else:
num_pages = 1
sale_items = []
for page_num in range(1, num_pages + 1):
if page_num > 1:
page = requests.get(f"{base_url}?page={page_num}")
soup = BeautifulSoup(page.content, 'html.parser')
sale_prices = soup.select('span.price--highlight')
for sale_price in sale_prices:
sale_item = {
'name':
sale_price.parent.parent.select('a')[0].text.strip(),
'image':
f"https{sale_price.parent.parent.parent.parent.select('img')[0]['src'].strip()}",
'url':
f"https://homecoffeesolutions.com{sale_price.parent.parent.select('a')[0]['href'].strip()}",
'regular_price':
scanutil.get_money(
sale_price.parent.parent.select('span.price--compare')
[0].text),
'sale_price':
scanutil.get_money(sale_price.text),
'website':
website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type):
base_url = f"https://www.espressoplanet.com/coffee-espresso/{page_type}/?sort=orderby&sort_direction=0&objects_per_page=1000"
soup = scanutil.get_soup(base_url)
website = 'espressoplanet.com'
market_price_values = soup.select('span.market-price-value')
sale_items = []
for market_price_value in market_price_values:
sale_item = {
'name' : market_price_value.parent.parent.parent.select('a')[0].text.strip(),
'image' : market_price_value.parent.parent.parent.parent.select('img')[0]['data-src'].strip(),
'url' : f"https://www.espressoplanet.com/{market_price_value.parent.parent.parent.select('a')[0]['href'].strip()}",
'regular_price' : scanutil.get_money(market_price_value.text.strip()),
'sale_price' : scanutil.get_money(market_price_value.parent.parent.select('span.currency')[0].text.strip()),
'website' : website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type, url_fragment):
base_url = f"https://www.faema.ca/{url_fragment}?searching=Y&sort=13&cat=1915&show=1000&page=1"
soup = scanutil.get_soup(base_url)
website = 'faema.ca'
sale_items = []
sale_prices = soup.select('div.product_saleprice')
for sale_price in sale_prices:
sale_item = {
'name' : sale_price.parent.parent.parent.parent.parent.select('a')[0]['title'].strip(),
'image' : f"https://faema.ca{sale_price.parent.parent.parent.parent.parent.select('img')[0]['src'].strip()}",
'url' : sale_price.parent.parent.parent.parent.parent.select('a')[0]['href'].strip(),
'regular_price' : scanutil.get_money(sale_price.parent.parent.parent.select('div.product_productprice')[0].text),
'sale_price' : scanutil.get_money(sale_price.text),
'website' : website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items():
base_url = "https://wholelattelove.ca/collections/all-coffee-makers?_=pf"
soup = scanutil.get_soup(base_url)
website = 'wholelattelove.ca'
sale_items = []
page_num = 1
while True:
if page_num > 1:
soup = scanutil.get_soup(f"{base_url}&page={page_num}")
if len(soup.select('div.product-wrap')) == 0:
break
sale_spans = soup.select('span.sale')
for sale_span in sale_spans:
if sale_span.parent.select('span.sold_out'):
continue
sale_item = {
'name':
sale_span.parent.select('h2')[0].text.strip(),
'image':
f"https:{sale_span.parent.parent.parent.select('img')[0]['data-src'].strip()}",
'url':
f"https://wholelattelove.ca{sale_span.parent.parent.parent.select('a')[0]['href'].strip()}",
'regular_price':
scanutil.get_money(sale_span.select('span.money')[1].text),
'sale_price':
scanutil.get_money(sale_span.select('span.money')[0].text),
'website':
website
}
sale_items.append(sale_item)
page_num += 1
return sale_items
def get_sale_items_for(page_type):
base_url = f"https://caffetech.com/collections/{page_type}"
soup = scanutil.get_soup(base_url)
website = 'caffetech.com'
pages = soup.select('ul.pagination__nav a')
if pages:
num_pages = int(pages[-1].text)
else:
num_pages = 1
sale_items = []
for page_num in range(1, num_pages + 1):
if page_num > 1:
soup = scanutil.get_soup(f"{base_url}?page={page_num}")
sale_prices = soup.select('span.product-item__price--new')
for sale_price in sale_prices:
sale_item = {
'name':
f"{sale_price.parent.select('h4')[0].text.strip()} - {sale_price.parent.select('a')[0].text.strip()}",
'image':
f"https:{sale_price.parent.parent.select('img')[1]['src'].strip()}",
'url':
f"http://caffetech.com{sale_price.parent.select('a')[0]['href'].strip()}",
'regular_price':
scanutil.get_money(
sale_price.parent.select('span.product-item__price--old')
[0].text),
'sale_price':
scanutil.get_money(sale_price.text),
'website':
website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type):
base_url = f"https://espressodolce.ca/product-category/espresso-machines/{page_type}/"
soup = scanutil.get_soup(base_url)
website = 'espressodolce.ca'
pages = soup.select('ul.page-numbers a')
if pages:
num_pages = len(pages)
else:
num_pages = 1
sale_items = []
for page_num in range(1, num_pages + 1):
if page_num > 1:
soup = scanutil.get_soup(f"{base_url}/page/{page_num}")
orig_prices = soup.select('del')
for orig_price in orig_prices:
sale_item = {
'name':
orig_price.parent.parent.select('p.name')[0].text.strip(),
'image':
orig_price.parent.parent.parent.parent.select('img')[0]
['src'].strip(),
'url':
orig_price.parent.parent.select('a')[1]['href'].strip(),
'regular_price':
scanutil.get_money(orig_price.text),
'sale_price':
scanutil.get_money(orig_price.parent.select('ins')[0].text),
'website':
website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type):
if page_type != "open-box-returns":
page_type = f"consumer/{page_type}"
base_url = f"https://idrinkcoffee.com/collections/{page_type}"
soup = scanutil.get_soup(base_url)
website = 'idrinkcoffee.com'
pages = soup.select('div.articlePreviewPagination a')
if pages:
num_pages = int(pages[-1].text)
else:
num_pages = 1
sale_items = []
for page_num in range(1, num_pages + 1):
if page_num > 1:
soup = scanutil.get_soup(f"{base_url}?page={page_num}")
orig_prices = soup.select('s')
for orig_price in orig_prices:
sale_item = {
'name':
orig_price.parent.parent.select('h2')[0].text.strip(),
'image':
f"https:{orig_price.parent.parent.select('img')[0]['data-src'].strip()}",
'url':
f"https://www.idrinkcoffee.com/{orig_price.parent.parent['href'].strip()}",
'regular_price':
scanutil.get_money(orig_price.text),
'sale_price':
scanutil.get_money(orig_price.parent.select('span')[0].text),
'website':
website
}
sale_items.append(sale_item)
return sale_items
def get_sale_items_for(page_type, url_fragment):
base_url = f"https://www.zcafe.ca/site/{url_fragment}"
soup = scanutil.get_soup(base_url)
website = 'zcafe.ca'
sale_items = []
images = soup.select('img[style]')
for image in images:
url = image.parent.parent.select('a')[0]['href'].strip()
img_src = re.search('.*\((.*)\).*',image['style']).group(1)
sale_item = {
'name' : image.parent.parent.parent.parent.select('a.producttitle')[0].text.strip(),
'image' : f"https://zcafe.ca{img_src}",
'url' : url,
'regular_price' : get_regular_price(url),
'sale_price' : scanutil.get_money(image.parent.parent.parent.parent.parent.select('div')[0].text),
'website' : website
}
sale_items.append(sale_item)
return sale_items
def get_regular_price(url):
soup = scanutil.get_soup(url)
price = scanutil.get_money(soup.select('#ProductInfo_Lbl_product_price_strike')[0].text)
return price