Created
April 2, 2017 15:20
-
-
Save craigmbooth/d70924d4f1875c1a319b5f40e2851cd7 to your computer and use it in GitHub Desktop.
This script downloads all of the images from the billboard gallery on the website of Robert Montgomery.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """I wanted a screensaver of Robert Montgomery poems. This script pulls | |
| them from the gallery on his website | |
| """ | |
| import os | |
| import sys | |
| from bs4 import BeautifulSoup | |
| import requests | |
| if __name__ == "__main__": | |
| res = requests.get("http://www.robertmontgomery.org/new-gallery/") | |
| if not res.ok: | |
| sys.exit("Failed to fetch website") | |
| # The page has a div with class=slide for each image, which contains | |
| # an img tag for the image itself | |
| soup = BeautifulSoup(res.text, 'html.parser') | |
| for slide in soup.findAll('div', attrs={'class':'slide'}): | |
| img = slide.find('img') | |
| if img is None: | |
| continue | |
| data = requests.get(img["src"]) | |
| with open(os.path.join("images", img["src"].split("/")[-1]), "wb") as f: | |
| for chunk in data: | |
| f.write(chunk) | |
| print "Saved: {}".format(img["src"].split("/")[-1]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment