import time
import logging
import concurrent.futures
import urllib.request
from bs4 import BeautifulSoup
from tqdm import tqdm

userid=576203327 #id vk
docid=574850052 #start doc number
num_page=1000 #number scan
URLS = [f"https://vk.com/doc{userid}_{doc_number}" for doc_number in range(docid,docid+num_page)]
logging.basicConfig(filename='app.log', filemode='w',
 format='%(message)s', level=logging.INFO)

def load_url(url, timeout):
    with urllib.request.urlopen(url, timeout=timeout) as conn:
        url= ''
        bs = BeautifulSoup(conn, 'html.parser')
        images = bs.find_all('img', class_="can_zoom")
        if images:
            url=images[0].get('src')
            logging.info(url)
        return url


start=time.time()
with tqdm(total=num_page) as pbar:
    with concurrent.futures.ThreadPoolExecutor(max_workers=16) as executor:
            future_to_url = {executor.submit(load_url, url, 60): url for url in URLS}
            for future in concurrent.futures.as_completed(future_to_url):
                pbar.update(1)
                url = future_to_url[future]
                try:
                    data = future.result()
                except Exception as exc:
                    print('%r generated an exception: %s' % (url, exc))
                else:
                    if data!='':
                        print(f'{data}')
end=time.time()
print(end-start)
input()