Last active
August 3, 2024 03:56
-
-
Save Pobega/2948c97d58c79e741df787081f97126c to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python3 | |
import argparse | |
import requests | |
from bs4 import BeautifulSoup, SoupStrainer | |
def main(): | |
parser = argparse.ArgumentParser( | |
prog='TIC Scraper', | |
description='Scrape the top games from tic80.com') | |
parser.add_argument('-p', '--pages', default=30, type=int, dest='pages', help='The number of pages to scrape.') | |
parser.add_argument('-c', '--category', default=0, type=int, dest='category', help='The category in the URL bar at tic80.com (defaults to games)') | |
args = parser.parse_args() | |
pages = [] | |
game_urls = [] | |
scraped_carts = [] | |
for i in range(0, args.pages): | |
pages.append(f'https://tic80.com/play?cat={args.category}&sort=2&page={i}') | |
print("Scraping game list...") | |
for page in pages: | |
print(f' Scraping {page}') | |
try: | |
r = requests.get(page) | |
except: | |
r = requests.get(page) | |
soup = BeautifulSoup(r.content, 'html5lib') | |
game_pages = soup.find_all('div', attrs = {'class':'thumbnail'}) | |
for game_page in game_pages: | |
game_url_ending = game_page.a['href'] | |
game_urls.append(f'https://tic80.com{game_url_ending}') | |
print("Scraping game data...") | |
for idx, game_url in enumerate(game_urls, start=1): | |
print(f' Scraping {game_url} ({idx}/{len(game_urls)})...') | |
cart = {} | |
try: | |
r = requests.get(game_url) | |
except: | |
r = requests.get(game_url) | |
soup = BeautifulSoup(r.content, 'html.parser') | |
# Scrape game carts | |
for link in soup.find_all('a'): | |
if link.has_attr('href'): | |
if link['href'].endswith('.tic'): | |
if link['href'].startswith('http'): | |
cart['url'] = link["href"] | |
else: | |
cart['url'] = f'https://tic80.com{link["href"]}' | |
# Scrape game covers | |
cart_img = soup.find('meta', attrs={'property':'og:image'}) | |
cart['cover'] = cart_img['content'] | |
# Add to total list | |
scraped_carts.append(cart) | |
print(scraped_carts) | |
for idx, cart in enumerate(scraped_carts, start=1): | |
game_name = cart['url'].split('/')[-1].split('.')[0] | |
print(f'Downloading {game_name} ({idx}/{len(scraped_carts)})...') | |
try: | |
response = requests.get(cart['url']) | |
except: | |
response = requests.get(cart['url']) | |
with open(f'Carts/{game_name}.tic', mode='wb') as file: | |
file.write(response.content) | |
try: | |
response = requests.get(cart['cover']) | |
except: | |
response = requests.get(cart['cover']) | |
with open(f'Imgs/{game_name}.gif', mode='wb') as file: | |
file.write(response.content) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment