+375(25)693-30-85
abrannik25@gmail.com
@de4lt_dd
Bachelor, Belarusian State University, Minsk
import requests
from bs4 import BeautifulSoup
import csv
CSV = 'cards.csv'
HOST = 'https://mcdonalds.by/ru/'
URL = 'https://mcdonalds.by/ru/news.html'
HEADERS = {'accept': 'text/html,application/xhtml+xml,application/xml',
'user-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)'}
def get_html(url, params=''):
r = requests.get(url, headers=HEADERS, params=params)
return r
def get_content(html):
soup = BeautifulSoup(html, 'html.parser')
items = soup.find_all('div', class_='row mc-news-all-blocks-holder')
cards = []
# print(items)
for item in items:
cards.append(
{
'title': item.find('div', class_='col-lg-12 col-md-12 col-sm-12 col-xs-12').get_text(strip=True),
'link_product': item.find('div', class_='mc-news-all-img-holder').find('a').get('href')
}
)
return cards
def save_doc(items, path):
with open(path, 'w', newline='') as file:
writer = csv.writer(file, delimiter=';')
writer.writerow(['Название продукта: ', 'Ссылка: '])
for item in items:
writer.writerow([item['title'], item['link_product']])
def parser():
PAGE = input('Количество страниц: ')
PAGE = int(PAGE.strip())
html = get_html(URL)
if html.status_code == 200:
cards = []
for page in range(1, PAGE):
print(f'Парсим страницу: {page}')
html = get_html(URL, params={'page': page})
cards.extend(get_content(html.text))
save_doc(cards, CSV)
else:
print('Error')
parser()