├── README.md
└── scraper.py


/README.md:
--------------------------------------------------------------------------------
1 | # 500px-scraper
2 | A python web scraper to download full size 500px.com images.
3 | 
4 | Just specify the URL and Save File name.
5 | 
6 | Usage : 
7 | python scraper.py -i 'URL' -s 'SaveFileName'
8 | 


--------------------------------------------------------------------------------
/scraper.py:
--------------------------------------------------------------------------------
 1 | from bs4 import BeautifulSoup
 2 | import urllib
 3 | import sys, getopt
 4 | 
 5 | def main(argv):
 6 | 	url = ''
 7 | 	save = ''
 8 | 	try:
 9 | 		opts, args = getopt.getopt(argv,"hi:s:",["url=","save="])
10 | 	except getopt.GetoptError:
11 | 		print 'scraper.py -i <imageurl> -s <savefilename>'
12 | 		sys.exit(2)
13 | 	for opt, arg in opts:
14 | 		if opt == '-h':
15 | 			print 'scraper.py -i <imageurl> -s <savefilename>'
16 | 			sys.exit()
17 | 		elif opt in ("-i", "--url"):
18 | 			url = arg
19 | 		elif opt in ("-s", "--save"):
20 | 			save = arg
21 | 	print 'URL : "', url
22 | 	print 'Save File Name : ', save
23 | 	r=urllib.urlopen(url).read()
24 | 	soup=BeautifulSoup(r)
25 | 	img=soup.find_all("meta",property="og:image")
26 | 	imgurl=img[0]["content"]
27 | 	urllib.urlretrieve(imgurl, save)
28 | 
29 | if __name__ == "__main__":
30 | 	main(sys.argv[1:])


--------------------------------------------------------------------------------