Created
November 12, 2014 14:41
-
-
Save chrishokamp/fe6d4fb3224b680ea1e9 to your computer and use it in GitHub Desktop.
grab the images at a url
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
#!/usr/bin/python | |
#Author: Chris Hokamp | |
#Spring 2013 | |
import sys | |
import requests | |
from BeautifulSoup import BeautifulSoup | |
import re | |
if len(sys.argv) != 4: | |
sys.exit("Usage: grabImages.py <url> <fiterString> <path-to-save>") | |
url = sys.argv[1].strip() | |
filterStr = sys.argv[2].strip() | |
savePath = sys.argv[3].strip() | |
req = requests.get(url) | |
bs = BeautifulSoup(req.text) | |
#print bs | |
imgUrls = [x['src'] for x in bs('img')] | |
for x in bs('img'): | |
print x | |
r = re.compile(filterStr, re.IGNORECASE) | |
goodOnes = filter(lambda x: r.search(x) is not None, imgUrls) | |
for img in goodOnes: | |
print img | |
imgData = requests.get(img) | |
imgFileName = "%s/%s" % (savePath, img.split('/')[-1]) | |
#print "File Name %s" % imgFileName | |
imgFile = open(imgFileName, 'wb') | |
imgFile.write(imgData.content) | |
imgFile.close() | |
print "Saved %s" % imgFileName | |
#This line didn't work??: python grabImages.py "http://www.buzzfeed.com/mjs538/things-youll-see-only-in-china" .jpg ~/Pictures/only_in_china |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment