Created
November 2, 2014 10:32
-
-
Save Meneth32/bb0f61efa06c484cb4d0 to your computer and use it in GitHub Desktop.
get-imgur-album.py
This file contains 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
# requirements: | |
# pip install praw | |
# pip install beautifulsoup4 | |
# usage: python get-imgur-album.py <albumUrl> | |
# example: python get-imgur-album.py http://imgur.com/a/hCPIW | |
import re, praw, requests, os, glob, sys | |
from bs4 import BeautifulSoup | |
def downloadImage(imageUrl, localFileName): | |
response = requests.get(imageUrl) | |
if response.status_code == 200: | |
print('Downloading %s...' % (localFileName)) | |
with open(localFileName, 'wb') as fo: | |
for chunk in response.iter_content(4096): | |
fo.write(chunk) | |
response.connection.close() | |
submissionUrl = sys.argv[1] | |
albumId = submissionUrl[len('http://imgur.com/a/'):] | |
htmlSource = requests.get(submissionUrl).text | |
with open('album_%s.html' % (albumId), 'wb') as fo: | |
fo.write(bytes(htmlSource, 'UTF-8')) | |
soup = BeautifulSoup(htmlSource) | |
matches = soup.select('.jcarousel img') | |
for match in matches: | |
imageUrl = match['data-src'].replace('s.', '.') | |
index = match['data-index'] | |
if '?' in imageUrl: | |
imageFile = imageUrl[imageUrl.rfind('/') + 1:imageUrl.rfind('?')] | |
else: | |
imageFile = imageUrl[imageUrl.rfind('/') + 1:] | |
localFileName = 'album_%s_index_%s_imgur_%s' % (albumId, index, imageFile) | |
downloadImage('http:' + imageUrl, localFileName) | |
#print(localFileName) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment