# ==[ 4chan Image Scraper Tool ]==
# Tool used for mass downloading images from 4chan threads

# Author: Justus Fee
# Created: 3 November 2019
# Last edited: 20 April 2020

# Req. packages: beautifulsoup4, requests, lxml

import bs4
import requests
import os
import time

url = input("What's the thread you need, chief?\n>")

res = requests.get(url)
res.raise_for_status()

folder = input("What do you want the folder called, chief?\n>")
os.makedirs("chan/" + folder, exist_ok=True)

thread = bs4.BeautifulSoup(res.text, features="lxml")

pics = thread.select("div.fileText a")
pics_len = len(pics)
print("\n{0} pictures found.\n".format(pics_len))

start_time = time.time()
for n in range(pics_len):
    page_url = "https:" + pics[n]["href"]
    page = requests.get(page_url)
    
    extension = os.path.splitext(os.path.basename(page_url))[1]

    image = open(os.path.join("chan/" + folder, str(n+1) + extension), "wb")
    for chunk in page.iter_content(100000):
        image.write(chunk)
    image.close()
    print("[{0:.2%}] Downloading picture {1} / {2}".format((n+1)/(pics_len), n+1, pics_len), end="\r")
end_time = time.time()

print("\nJob's done!")
elapsed = round(end_time - start_time)
print("Took {0:.2} minutes ({1} seconds).".format((elapsed/60), elapsed))