Mfcttrf

This came out on the spur of the moment, as a quick and dirty tool to have the job done.

This is a simple image scraper for immensely popular and legendary comic website inspired by a Python Easter Egg.

For those who don't know it, run your Python interpreter and type import antigravity and hit Enter. :)

As for the code below, I'd appreciate any feedback, particularly in regards to threading, as I'm new to this.

#!/usr/bin/python3

import os
import sys
import time
import threading
from pathlib import Path
from shutil import copyfileobj


import requests
from lxml import html


BASE_URL = "https://www.xkcd.com/"
ARCHIVE = "https://www.xkcd.com/archive"
SAVE_DIRECTORY = Path('xkcd_comics')
LOGO = """
 _ _ 
 tiny | | image | | downloader for
 __ _| | _____ __| | ___ ___ _ __ ___ 
 / / |/ / __/ _` | / __/ _ | '_ ` _ 
 > <| < (_| (_| || (_| (_) | | | | | |
 /_/__|______,_(_)______/|_| |_| |_|
 version 0.1
"""


def show_logo():
 print(LOGO)


def fetch_url(url: str) -> requests.Response:
 return requests.get(url)


def head_option(values: list) -> str:
 return next(iter(values), None)


def get_penultimate(url: str) -> int:
 page = fetch_url(url)
 tree = html.fromstring(page.content)
 newest_comic = head_option(
 tree.xpath('//*[@id="middleContainer"]/a[1]/@href'))
 return int(newest_comic.replace("/", ""))


def get_images_from_page(url: str) -> str:
 page = fetch_url(url)
 tree = html.fromstring(page.content)
 return head_option(tree.xpath('//*[@id="comic"]//img/@src'))


def get_number_of_pages(latest_comic: int) -> int:
 print(f"There are latest_comic comics.")
 print(f"How many do you want to download? Type 0 to exit.")
 while True:
 try:
 number_of_comics = int(input(">> "))
 except ValueError:
 print("Error: Expected a number. Try again.")
 continue
 if number_of_comics > latest_comic or number_of_comics < 0:
 print("Error: Incorrect number of comics. Try again.")
 continue
 elif number_of_comics == 0:
 sys.exit()
 return number_of_comics


def clip_url(img: str) -> str:
 return img.rpartition("/")[-1]


def make_dir():
 return os.makedirs(SAVE_DIRECTORY, exist_ok=True)


def save_image(img: str):
 comic_name = clip_url(img)
 print(f"Downloading: comic_name")
 f_name = SAVE_DIRECTORY / comic_name
 with requests.get("https:" + img, stream=True) as img, open(f_name, "wb") 
 as output:
 copyfileobj(img.raw, output)


def show_time(seconds: int) -> int:
 minutes, seconds = divmod(seconds, 60)
 hours, minutes = divmod(minutes, 60)
 time_elapsed = f"hours:02d:minutes:02d:seconds:02d" 
 return time_elapsed


def get_xkcd():
 show_logo()
 make_dir()

 collect_garbage = []
 latest_comic = get_penultimate(ARCHIVE)
 pages = get_number_of_pages(latest_comic)

 start = time.time()
 for page in reversed(range(latest_comic - pages + 1, latest_comic + 1)):
 print(f"Fetching page page out of latest_comic")
 try:
 url = get_images_from_page(f"BASE_URLpage/")
 thread = threading.Thread(target=save_image, args=(url, ))
 thread.start()
 except (ValueError, AttributeError, requests.exceptions.MissingSchema):
 print(f"WARNING: Invalid comic image source url.")
 collect_garbage.append(f"BASE_URLpage")
 continue
 thread.join()
 end = time.time()

 print(f"Downloaded pages comic(s) in show_time(int(end - start)).")

 if len(collect_garbage) > 0:
 print("However, was unable to download images for these pages:")
 print("n".join(page for page in collect_garbage))


def main():
 get_xkcd()


if __name__ == '__main__':
 main()

Globals

As it is, there's no point to LOGO being a global. It's only used by show_logo, so move it there.

Base URLs

You correctly saved a base URL, but then didn't use it in the correct contexts. Particularly problematic:

ARCHIVE = "https://www.xkcd.com/archive"

This ignores the BASE_URL entirely, when it shouldn't.

fetch_url is currently useless - it doesn't add anything to requests.get. You could make it useful by making the argument a path relative to the base path.

with requests.get("https:" + img
# ...
url = get_images_from_page(f"BASE_URLpage/")

Naive string concatenation is not the right thing to do, here. Python has a full-featured urllib to deal with URL parsing and construction.

show_time

divmod on a numeric time interval is not the right thing to do. Use datetime.timedelta.