8ch.py

import requests, json, time, os

subject = 'trains'

r = requests.get('http://8ch.net/b/catalog.json')
j = json.loads(r.text)

def download(url, name, thread):
    filepath = './' + str(thread) + '/' + name
    if not os.path.exists(filepath):
        print('Get got: ' + name)
        r = requests.get(url, stream=True)
        with open(filepath, 'wb') as f:
            for chunk in r.iter_content(chunk_size=1024): 
                if chunk:
                    f.write(chunk)
                    f.flush()

def get_got():
    for t in j:
        threads = t['threads']

        for thread in threads:
            sub = thread['sub']
            if sub == subject:
                num = thread['no']

    dirr = './' + str(num)

    if sub:
        if not os.path.exists(dirr):
            os.makedirs(dirr)

    if sub:
        r2 = requests.get('http://8ch.net/b/res/' + str(num) + '.json')
        j2 = json.loads(r2.text)
        posts = j2['posts']

        def gk(key, value):
            return value.get(key, '') 

        for post in posts:
            if gk('filename', post):
                or_filename = gk('filename', post)
                filename = gk('tim', post) + gk('ext', post)
                download('http://8ch.net/b/src/' + filename, or_filename + gk('ext', post), num)
            if gk('extra_files', post):
                for extra_file in gk('extra_files', post):
                    orf = gk('filename', extra_file)
                    fin = gk('tim', extra_file) + gk('ext', extra_file)
                    download('http://8ch.net/b/src/' + fin, orf + gk('ext', extra_file), num)
    print('Dormindo...')
    time.sleep(5 * 60)

while True:
    get_got()