ATBS Chapter 11 xkcd Downloader

xkcd_download.py

#!/usr/bin/python

# ATBS Chapter 11
# XKCD Downloader

# import modules
import requests, os, bs4

url = 'http://xkcd.com'     # starting URL
os.makedirs('xkcd', exist_ok=True) # store comics in ./xkcd
# exist_ok=True keyword argument prevents the function from throwing an
# exception if this folder already exists.
while not url.endswith('#'): # '#' indicates either first or last comic
    # Download the page
    print('Downloading page %s...' % url)
    res = requests.get(url)
    res.raise_for_status()
    soup = bs4.BeautifulSoup(res.text)

    # Find the URL of the comic image
    comicElem = soup.select('#comic img')
    if comicElem == []:
        print('Could not find comic image.')
        # comicElem would be a list value, so if list is blank, there was no
        # comic to be found on that page
    else:
        try:
            comicURL = 'http:' + comicElem[0].get('src')
            # Download the image
            print('Downloading image %s...' % (comicURL))
            res = requests.get(comicURL)
            res.raise_for_status()
        except requests.exceptions.MissingSchema:
            # skip this comic
            prevLink = soup.select('a[rel="prev"]')[0]
            url = 'http://xkcd.com' + prevLink.get('href')
            continue

        # Save the image to ./xkcd
    imageFile = open(os.path.join('xkcd', os.path.basename(comicURL, 'wb')
    for chunk in res.iter_content(100000):
        imageFile.write(chunk)
    imageFile.close()

    # Get the Prev button's URL
    prevLink = soup.select('a[rel="prev"]')[0]
    url = 'http://xkcd.com' + prevLink.get('href')

print('Done.')