arcadeartwork.org box art scraper

scrape.py

#! arcadeartwork.org box art scraper
#!/env/Python3.10.4
#/MobCat (2023)

import requests #pip install requests
import re
import os

# Not all consoles on site are here. Too many categories and sub categories.
# To make new one. Open The Album you want to download `https://www.arcadeartwork.org/index.php?/category/547`
# then open the first image in a new tab, scroll allll the way to the bottom and open the last image in a new tab
# we should now have 2 URLs like
# https://www.arcadeartwork.org/picture.php?/83435/category/547
# https://www.arcadeartwork.org/picture.php?/83994/category/547
# We want the first number after the ?/
# This will say where to start scraping and where to end scraping.
# 3: (83435, 83994, "NES", "Nintendo Entertainment System")
# Select index: (start range, end range, "FolderName", "Menu Name")
consoles = {
	1:  (145820, 146377, "3DO",   "3DO"),
	2:  (56317,  56354,  "Bally", "Bally Astrocade"),
	3:  (83435,  83994,  "NES",   "Nintendo Entertainment System"),
	4:  (27793,  28353,  "SNES",  "Super Nintendo Entertainment System"),
	5:  (82229,  82527,  "N64",   "Nintendo 64"),
	6:  (32285,  36354,  "NDS",   "Nintendo DS"),
	7:  (101717, 101738, "VB",    "Nintendo Virtual Boy"),
	8:  (43108,  43675,  "GB",    "Nintendo Game Boy"),
	9:  (80976,  81548,  "GBC",   "Nintendo Game Boy Color"),
	10: (56393,  58719,  "GBA",   "Nintendo Game Boy Advance"),
	11: (55740,  56316,  "GBA",   "Nintendo Game GameCube"),
}

# Menu builder
print(f"""
arcadeartwork.org box art scraper
By MobCat
20231113

Please select a console
""")
for i in consoles:
	print(f"{i}: {consoles[i][3]} ({(consoles[i][1] - consoles[i][0]) + 1} Boxes)") # +1 for 0th index? lol idk.

try:
	select = int(input("\nSelection: "))
except KeyboardInterrupt:
	print("Terminate the script.")
	exit()

# Sainaty checks
if select not in consoles:
	print(f'{select} Is not a vaild type\nPlease try again')
	exit()

if not os.path.exists(consoles[select][2]):
	print(f'"{consoles[select][2]}" directory not found, makeing a new one now.')
	os.makedirs(consoles[select][2])


# Set our download range to our selected console
try:
	cnt = consoles[select][0]
	while cnt <= consoles[select][1]:

		# Go rip image based on id in range
		response = requests.get(f'https://www.arcadeartwork.org/action.php?id={cnt}&part=e&download')
		
		# Check if the request was successful (status code 200)
		if response.status_code == 200:
			# Try to get the filename from the "Content-Disposition" header
			content_disposition = response.headers.get('Content-Disposition')
		
			# Extract the filename using a regular expression
			filename_match = re.search(r'filename="(.+)"', content_disposition)
	
			# Regex for replacing - to space and truncating unnecessary amount of spaces
			filename = filename_match.group(1)
			cleaned_filename = re.sub('-+', ' ', filename)
			cleaned_filename = cleaned_filename.strip()
		
			# Save the image with the extracted filename
			with open(f'{consoles[select][2]}/{cleaned_filename}', 'wb') as f:
				f.write(response.content)
			print(f"Downloaded {consoles[select][2]}\\{cleaned_filename}")
		else:
			print(f"Failed to download image. Status code: {response.status_code}")
	
		cnt += 1
	
	print("Done ^__^")

except KeyboardInterrupt:
	print("Script terminated.")
	exit()