Download all from imgur embed URL

dl.py

import os
import sys
from os.path import basename, splitext
from urlparse import urlparse

import requests
from bs4 import BeautifulSoup


def extract_full_size_url_from_tag(image_tag):
    thumbnail_src = image_tag['data-src']
    parsed = urlparse(thumbnail_src)
    file_name, file_ext = splitext(basename(parsed.path))
    file_name = file_name[:-1]
    return 'http://{}/{}{}'.format(parsed.hostname, file_name, file_ext)


def extract_file_name_from_url(image_url):
    parsed = urlparse(image_url)
    return basename(parsed.path)


def download_image(image_url, path):
    print 'DOWNLOADING: %s @ %s' % (image_url, path)
    r = requests.get(image_url, stream=True)
    if r.status_code == 200:
        with open(path, 'wb') as f:
            for chunk in r.iter_content():
                f.write(chunk)
        print 'SAVED: %s' % path


def download_all_from_embed(embed_url, download_path):

    embed_response = requests.get(embed_url)
    if not embed_response.ok:
        print "ERROR in response on %" % embed_url
        sys.exit(1)

    soup = BeautifulSoup(embed_response.content)
    images = soup.find_all('img', class_="thumb-title-embed")
    for image_tag in images:
        image_url = extract_full_size_url_from_tag(image_tag)
        file_name = extract_file_name_from_url(image_url)
        path = os.path.join(download_path, file_name)
        if not os.path.exists(path):
            download_image(image_url, path)
        else:
            print 'SKIPPING: %s' % image_url


if __name__ == "__main__":
    embed, path = sys.argv[1:]

    if not os.path.exists(path):
        os.mkdir(path)

    download_all_from_embed(embed, path)

requirements.txt

requests==2.3.0
beautifulsoup4==4.3.2

Usage:

python dl.py <url-of-embed-page>