Paddy/Betterzon
1
0
Fork 0
mirror of https://github.com/Mueller-Patrick/Betterzon.git synced 2024-12-23 12:15:11 +00:00
Code Issues Projects Releases Wiki Activity

Added another selector for price on amazon (does not work for books)

Browse Source
This commit is contained in:
henningxtro 2021-05-18 23:18:15 +02:00
parent 63cbac5490
commit 91a9a47f00
1 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
Crawler/crawler.py
View File

@ -62,6 +62,7 @@ def crawl(product_ids: [int]) -> dict:
'products_with_problems': products_with_problems 'products_with_problems': products_with_problems
} }
def __crawl_amazon__(product_info: dict) -> tuple: def __crawl_amazon__(product_info: dict) -> tuple:
""" """
Crawls the price for the given product from amazon Crawls the price for the given product from amazon
@ -71,7 +72,11 @@ def __crawl_amazon__(product_info: dict) -> tuple:
page = requests.get(product_info['url'], headers=HEADERS) page = requests.get(product_info['url'], headers=HEADERS)
soup = BeautifulSoup(page.content, features="lxml") soup = BeautifulSoup(page.content, features="lxml")
try: try:
price = int(soup.find(id='priceblock_ourprice').get_text().replace(".", "").replace(",", "").replace("€", "").strip()) price = int(
soup.find(id='priceblock_ourprice').get_text().replace(".", "").replace(",", "").replace("€", "").strip())
if not price:
price = int(soup.find(id='price_inside_buybox').get_text().replace(".", "").replace(",", "").replace("€", "").strip())
except RuntimeError: except RuntimeError:
price = -1 price = -1
except AttributeError: except AttributeError: