munch-ease-backend/products/scraping.py

55 lines
1.8 KiB
Python
Raw Normal View History

2024-01-13 01:54:04 +00:00
import re, httpx
HEADERS = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:121.0) Gecko/20100101 Firefox/121.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
'Accept-Language': 'en-US,en;q=0.5',
'Accept-Encoding': 'gzip, deflate, br',
'DNT': '1',
'Sec-GPC': '1',
'Connection': 'keep-alive',
'Upgrade-Insecure-Requests': '1',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'none',
'Sec-Fetch-User': '?1',
'Pragma': 'no-cache',
'Cache-Control': 'no-cache',
}
async def _get_cookies(client):
# Make a request to https://www.woolworths.com.au/ as if we were a normal browser, then return the cookies
response = await client.get('https://www.woolworths.com.au/', headers=HEADERS, follow_redirects=True)
return dict(response.cookies)
last_cookies = None
async def scrape_woolies_data(url: str) -> dict:
global last_cookies
async with httpx.AsyncClient() as client:
if last_cookies:
cookies = last_cookies
else:
cookies = await _get_cookies(client)
last_cookies = cookies
try:
response = await client.get(url, headers=HEADERS, follow_redirects=True, cookies=cookies)
response.raise_for_status()
return response.json()
except httpx.NetworkError as ne:
print(ne)
last_cookies = None
return None
def get_product_id(url: str) -> str:
woolies_regex = r'https://www.woolworths.com.au/shop/productdetails/(\d+)/?.*'
match = re.match(woolies_regex, url)
if match:
return match.group(1)
return None
def get_product_details_url(product_id) -> str:
return f'https://www.woolworths.com.au/apis/ui/product/detail/{product_id}'