def get_product_data(product):
product_html = utils.get_html_as_string(product_base_url + product)
parser = BeautifulSoup(product_html, 'html.parser')
brand = 'ERR BRAND NOT FOUND'
num_ratings = 'ERR NUM RATINGS NOT FOUND'
rating = 'ERR RATING NOT FOUND'
#find brand and num_ratings
for span in parser.find_all('span'):
if span.get('itemprop') != None and span.get('itemprop') == 'brand':
brand = span.string
if span.get('itemprop') != None and span.get('itemprop') == 'ratingCount':
num_ratings = span.string
#case of 0 ratings detected when ratingCount not present on page
if num_ratings == 'ERR NUM RATINGS NOT FOUND':
num_ratings = '0'
rating = 'n/a'
else:
#find rating if present
for p in parser.find_all('p'):
if p.get('class') != None and p.get('class')[0] == 'heading-e':
if p.string != 'Age' and p.string != 'Gender':
rating = p.string.split(' ')[3]
data = [product_base_url + product, brand, num_ratings, rating]
return data
def parse_search(query):
search_html = utils.get_html_as_string(search_base_url + query)
product_links = get_product_pages(search_html)
filename = '../parsed_data/' +time.strftime("%m-%d-%Y") +'_' +time.strftime("%H-%M-%S") +'_' +query +'.csv'
with open(filename, 'w', newline='') as csvfile:
writer = csv.writer(csvfile, delimiter=',')
for product in product_links:
writer.writerow(get_product_data(product))
