Created
June 16, 2020 02:12
-
-
Save pyrofolium/b34ebd4ccd173edb3e11fccf2e7f7bd8 to your computer and use it in GitHub Desktop.
This file contains 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
# 3003792 | |
# http://i.imgur.com/cz0yhtx.jpg | |
# http://i.imgur.com/KxyEGOn.jpg | |
# http://i.imgur.com/vPae8qL.jpg | |
# http://i.imgur.com/cz0yhtx.jpg | |
# bad_input | |
# http://www.google.com/isadsada | |
import sys | |
import urllib.request | |
from typing import Dict, Tuple | |
import hashlib | |
from collections import OrderedDict | |
# MUST USE LATEST VERSION OF PYTHON. LATEST VERSION OF PYTHON DICTS HAVE ORDER, EARLIER THEY DO NOT!!!!!!. (3.7++) | |
def process_picture(url_string: str, input_capacity: int, input_current_size: int = 0, | |
input_stored: Dict[str, int] = None) -> Tuple[int, str]: | |
input_stored = OrderedDict() if input_stored is None else input_stored | |
if url_string in input_stored: | |
value = input_stored[url_string] | |
del input_stored[url_string] # updating dict does not change order must delete and insert new value. | |
input_stored[url_string] = value | |
return input_current_size, f"{url_string.strip()} CACHE {len(input_stored[url_string])} {hashlib.sha256(input_stored[url_string]).hexdigest()}" | |
else: | |
with urllib.request.urlopen(url_string) as response: | |
picture = response.read() | |
size = len(picture) | |
if size <= input_capacity - input_current_size: | |
input_stored[url_string] = picture | |
input_current_size += len(picture) | |
return input_current_size, f"{url_string.strip()} DOWNLOADED {len(input_stored[url_string])} {hashlib.sha256(input_stored[url_string]).hexdigest()}" | |
elif size > input_capacity: | |
return input_current_size, f"{url_string.strip()} DOWNLOADED {len(picture)} {hashlib.sha256(picture).hexdigest()}" | |
else: | |
for key, value in [i for i in input_stored.items()]: | |
if size > input_capacity - input_current_size: | |
input_current_size -= len(value) | |
del input_stored[key] | |
else: | |
break | |
input_stored[url_string] = picture | |
input_current_size += len(picture) | |
return input_current_size, f"{url_string.strip()} DOWNLOADED {len(input_stored[url_string])} {hashlib.sha256(input_stored[url_string]).hexdigest()}" | |
input_file_name = sys.argv[-2] | |
output_file_name = sys.argv[-1] | |
input_file = open(input_file_name, 'r') | |
capacity = None | |
current_size = 0 | |
stored = OrderedDict() | |
output_file = open(output_file_name, 'w') | |
for index, line in enumerate(input_file.readlines()): | |
if index == 0: | |
capacity = int(line.strip()) | |
print(capacity) | |
else: | |
url = line | |
try: | |
current_size, output_string = process_picture(url, capacity, current_size, stored) | |
output_file.write(output_string + "\n") | |
except Exception as _: | |
continue | |
output_file.close() | |
input_file.close() | |
# print(input_file_name) | |
# print(output_file_name) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment