serverpartdeals.com $/TiB

serverpartdeals.py

import re
import niquests
import sys
from bs4 import BeautifulSoup


def parse_page(soup):
    drives = soup.find_all(class_="boost-pfs-filter-product-bottom")

    for drive in drives:
        product_title = drive.find(class_="boost-pfs-filter-product-item-title").text
        try:
            drive_size = float(re.search(r"[0-9.]+(?=TB)", product_title).group(0))
        except AttributeError:
            print("xxx xxx", product_title, file=sys.stderr)
            continue

        try:
            drive_price = float(
                drive.find(
                    class_="boost-pfs-filter-product-item-regular-price"
                ).text.replace("$", "")
            )
        except AttributeError:
            drive_price = float(
                drive.find(
                    class_="boost-pfs-filter-product-item-sale-price"
                ).text.replace("$", "")
            )

        print(round(drive_price/drive_size, 2), drive_size, drive_price, product_title)


def crawl():
    page = 1
    url = "https://serverpartdeals.com/collections/hard-drives"
    while True:
        print("Getting page", page, file=sys.stderr)
        content = niquests.get(
            url,
            params={
                "display": "list",
                "page": page,
            },
            headers={
                "User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:135.0) Gecko/20100101 Firefox/135.0",
                "Accept-Language": "en-US,en;q=0.5",
            },
        ).content
        soup = BeautifulSoup(content, features="html.parser")
        parse_page(soup)
        if soup.find("a", string="→"):
            page += 1
        else:
            break


if __name__ == "__main__":
    crawl()