import sys
from pathlib import Path

import xlrd
import requests
from bs4 import BeautifulSoup


URLS = {
    "Free Emergency Nursing titles (German)": "https://resource-cms.springernature.com/springer-cms/rest/v1/content/17856246/data/v3",
    "Free English textbook titles (all disciplines)": "https://resource-cms.springernature.com/springer-cms/rest/v1/content/17858272/data/v4",
    "Free German textbook titles (all disciplines)": "https://resource-cms.springernature.com/springer-cms/rest/v1/content/17863240/data/v2",
}
DOWNLOAD_PATH = Path("Download")
DOWNLOAD_PATH.mkdir(exist_ok=True)


def get_urls():
    sheets = []
    for kind, url in URLS.items():
        print("Downloading", kind)
        rep = requests.get(url)
        sheets.append(xlrd.open_workbook(file_contents=rep.content).sheet_by_index(0))

    result = []
    for sheet in sheets:
        iterator = zip(sheet.col_slice(0), sheet.col_slice(18))
        next(iterator)
        for title, url in iterator:
            result.append((title.value, url.value))
    return result


def get_downloads(pages):
    base = "https://link.springer.com"
    for title, url in pages:
        bs = BeautifulSoup(requests.get(url).content, "html.parser")
        if result := bs.find("a", href=True, attrs={"class": "c-button"}):
            yield title, base + result.get("href")


def downloader(title, url):
    _, _, suffix = url.rpartition(".")
    target = (DOWNLOAD_PATH / title).with_suffix("." + suffix)
    if not target.exists():
        print(f"Downloading `{title}`")
        with target.open("wb") as fd:
            rep = requests.get(url, stream=True)
            for chunk in rep.iter_content(8196):
                fd.write(chunk)


def download():
    links_to_books = get_urls()
    print(f"Downloading {len(links_to_books)} eBooks")
    for title, url in get_downloads(links_to_books):
        try:
            downloader(title, url)
        except Exception as e:
            print(e, file=sys.stderr)


if __name__ == "__main__":
    download()