Last active
August 29, 2015 14:02
-
-
Save ialhashim/f04f3afd78edfede3a1c to your computer and use it in GitHub Desktop.
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
from random import sample | |
from string import digits, ascii_uppercase, ascii_lowercase | |
from tempfile import gettempdir | |
from os import path | |
def rand_fname(suffix='', length=8): | |
chars = ascii_lowercase + ascii_uppercase + digits | |
#fname = path.join(gettempdir(), 'tmp-' + ''.join(sample(chars, length)) + suffix) | |
fname = 'tmp-' + ''.join(sample(chars, length)) + suffix | |
return fname if not path.exists(fname) \ | |
else rand_fname(suffix, length) | |
import os | |
import re | |
import urllib | |
import urllib.request | |
def getimages(html_file): | |
linestring = open(html_file, encoding="utf8").read() | |
for match in re.findall(r'imgurl=(.*?(?:&|\.(?:jpg|gif|png|jpeg)))', linestring, re.I): | |
#print (match) | |
file_save_dir = 'images' | |
filename_length = 20 | |
filename = rand_fname() | |
try: | |
dest = os.path.join(file_save_dir, filename + '.png') | |
print ("OK, saving to:" + dest) | |
urllib.request.urlretrieve (match, dest) | |
except Exception as e: | |
print ("Error: %s" % e) | |
import sys | |
if len(sys.argv) > 1: | |
getimages( sys.argv[1] ) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment