Short script for scraping literaturbanken book images

litteraturbanken_scrape.py

#!/usr/bin/python
# -*- coding: utf-8 -*-
# short script for scraping literaturbanken book images
import requests
from tqdm import tqdm

def download_single(num, prefix, url):
    num_s = '{0:04}'.format(num)
    full_url = url.format(num_s)
    output_file = '{1}_{0}.jpg'.format(num_s, prefix)
    r = requests.get(full_url, stream=True)
    chunk_size = 1024
    label = 'page_{}'.format(num_s)
    with open(output_file, 'wb') as handle:
        pbar = tqdm(desc=label, unit_scale=True, unit='B')
        for data in r.iter_content(chunk_size=chunk_size):
            if data:  # filter out keep-alive new chunks
                pbar.update(len(data))
                handle.write(data)

def download_all(book_id, prefix, pages, zoom_level=5):
    url = 'https://litteraturbanken.se/txt/{0}/{0}_{1}/{0}_{1}_{{}}.jpeg'.format(book_id, zoom_level)
    for num in range(1, pages+1):
        download_single(num, prefix, url)

def example():
    download_all('lb3040872', 'Prinsarnes_blomsteralfabet', 70, 5)