Scrape some website for the avatar comics

scrape_avatar_comics.py

#!/usr/bin/python3

import os
import sys
import itertools
import requests
from bs4 import BeautifulSoup

url_fmt  = "https://www.omgbeaupeep.com/comics/Avatar_The_Last_Airbender/{:03}/{}/"
dir_name = "avatar_comics"

try:
    os.mkdir(dir_name)
except FileExistsError:
    pass

if len(sys.argv) != 3:
    print(f"Usage: {sys.argv[0]} from to")
    sys.exit(1)

comic_from = int(sys.argv[1])
comic_to   = int(sys.argv[2])

for comic_id in range(comic_from, comic_to + 1):
    print(f"Downloading comic {comic_id:03}")
    comic_dir = os.path.join(dir_name, f"comic-{comic_id:03}")
    try:
        os.mkdir(comic_dir)
    except FileExistsError:
        pass

    for page_id in itertools.count(1):
        respond = requests.get(
            f"https://www.omgbeaupeep.com/comics/Avatar_The_Last_Airbender/{comic_id:03}/{page_id}/")
        if respond.status_code != 200:
            print(f"Couldn't download page {page_id}")
            raise IOError

        soup = BeautifulSoup(respond.content, "html.parser")
        try:
            img = [s for s in soup.find_all("img") if s.get("class") is not None][0]
        except IndexError:
            break

        img_src = img.get("src")
        b = os.path.basename(img_src)
        page_path = os.path.join(comic_dir, b[b.rfind("-") + 1:])
        print(f"Downloading page {page_id} to {page_path}")
        respond = requests.get(
            f"https://www.omgbeaupeep.com/comics/{img_src}")

        if respond.status_code != 200:
            print(f"Couldn't download page src {page_id}")
            raise IOError

        with open(page_path, "wb") as f:
            f.write(respond.content)