#!/usr/bin/python3 from bs4 import BeautifulSoup from requests import get from sys import argv if len(argv) != 3: raise Exception("prvi arg je url do threada, drugi arg je končnica, recimo .webm") s = BeautifulSoup(get(argv[1]).content, "html.parser") for a in s.find_all("a"): if a.attrs["href"].endswith(argv[2]): fn = None if "title" in a.attrs and "/" not in a.attrs["title"]: fn = a.attrs["title"] elif "/" not in a.getText() and ("class" not in a.attrs or "fileThumb" not in a.attrs["class"]): fn = a.getText() if fn is not None: print(fn) open(fn, "wb").write(get("http:" + a.attrs["href"]).content)