azdelivery-document-lists

# I required a pdf from azdelivery, but I could not find a search function
# so I scrape all pages

from collections.abc import Generator
from itertools import count

import requests
from bs4 import BeautifulSoup

BASE_URL = "https://www.az-delivery.de/en/collections/kostenlose-e-books?page={page}"


def get(page: int) -> tuple[str, list[str]]:
    resp = requests.get(url := BASE_URL.format(page=page))
    elements = BeautifulSoup(resp.content, "html.parser").select(
        "a.product-item__title"
    )
    return url, [e.text for e in elements]


def walk(start=1) -> Generator[tuple[str, list[str]], None, None]:
    for page in count(1):
        url, elements = get(page)
        if not elements:
            return
        yield url, elements


results = {}
for url, elements in walk():
    results[url] = elements
    print(url)