Last active
December 21, 2015 01:38
-
-
Save HeartSaVioR/6228652 to your computer and use it in GitHub Desktop.
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
import urllib | |
from time import sleep | |
url_template = "https://m.mypeople.daum.net/img/i1.daumcdn.net/air21.sticker/pc/still_img/sticker_%03d.png" | |
start_range=0 | |
end_range=1500 # 2013/08/14 last id : 1457 | |
sleep_for_crawl_success = 1 | |
sleep_for_crawl_fail = 2 | |
for sticker_id in range(start_range, end_range+1): | |
url = url_template % sticker_id | |
filename = url.split('/')[-1] | |
success = False | |
print "about to download %s -> %s" % (url, filename) | |
try: | |
http = urllib.urlopen(url) | |
if http.getcode() != 200: | |
print "status code is not 200" | |
elif not http.headers.has_key('content-type') or http.headers.get('content-type') != "image/png": | |
print "content-type not found or not image/png" | |
else: | |
with open(filename, 'w') as fw: | |
fw.write(http.read()) | |
success = True | |
except: | |
print "cannot download %s" % url | |
finally: | |
if success: | |
sleep(sleep_for_crawl_success) | |
else: | |
sleep(sleep_for_crawl_fail) | |
print "end process..." |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment