Last active
July 27, 2016 18:31
-
-
Save sebastialonso/38871f61e8f3961fdcc5ddd535612691 to your computer and use it in GitHub Desktop.
YGYL automatic downloader (py2)
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
import requests, json | |
CATALOG_URL = 'http://a.4cdn.org/gif/catalog.json' | |
THREAD_URL = 'http://a.4cdn.org/gif/thread/' | |
CDN_URL = 'http://i.4cdn.org/gif/' | |
CRITERIA = 'YGYL' | |
files_saved = 0 | |
def parse_thread(number): | |
global files_saved | |
url = get_thread_url(number) | |
thread = get_dict_from_url(url) | |
posts = thread['posts'] | |
for post in posts: | |
if post.get('filename') != None: | |
filename = str(post['filename']) + post['ext'] | |
with open(filename, "wb") as handle: | |
webm = get_resource_from_post(post) | |
print "{filename} OK: {ok}".format(ok=webm.ok, filename=filename) | |
files_saved += 1 | |
handle.write(webm.content) | |
def get_dict_from_url(url): | |
req = requests.get(url) | |
return json.JSONDecoder().decode(req.text) | |
def get_thread_url(number): | |
return THREAD_URL + str(number) + ".json" | |
def get_resource_from_post(post): | |
url = CDN_URL + str(post['tim']) + post['ext'] | |
return requests.get(url) | |
board = get_dict_from_url(CATALOG_URL) | |
print "You Groove You Lose Downloader" | |
for page in board: | |
threads = page['threads'] | |
print "Scanning page {page}".format(page=page['page']) | |
for thread in threads: | |
if thread.get('sub') != None and (CRITERIA in thread['sub'] or CRITERIA.swapcase() in thread['sub']): | |
print "Found {crit} thread".format(crit=CRITERIA) | |
parse_thread(thread['no']) | |
print "{num} files saved!".format(num=files_saved) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment