import os import requests from time import sleep from bs4 import BeautifulSoup as bs current_directory = os.getcwd() files_in_directory = os.listdir(current_directory) if("4chan_wallpapers" in files_in_directory): current_directory = current_directory + "/4chan_wallpapers" else: print("Creating wallpaper directory...") os.system("mkdir 4chan_wallpapers") sleep(3) current_directory = current_directory + "/4chan_wallpapers" os.chdir(current_directory) print("Changing directory...") sleep(3) files_in_directory = os.listdir(current_directory) address = "https://boards.4chan.org/wg/" response = requests.get(address) main = bs(response.content, 'html.parser') threads = main.find_all("a") for thread in threads: #print(thread["href"]) if("thread/" in thread["href"]): if("#" not in thread["href"]): if(len(thread["href"].split("/")) == 2): thread_link = "https://boards.4chan.org/wg/" + thread["href"] print(thread_link) response_thread = requests.get(thread_link) website = bs(response_thread.content, 'html.parser') links = website.find_all("a") for link in links: if("4cdn.org" in link["href"]): image_link = "https://"+link["href"][2:] image_file = image_link.split("/")[-1] if(image_file not in files_in_directory): files_in_directory.append(image_file) # Trusting the download won't fail print("Fetching: "+image_link) os.system("wget -q "+image_link+" &") # Becauses we add "&" for speeeed' # In the future, do wget -nc to skip already downloaded files