Last active
October 11, 2015 04:37
-
-
Save scturtle/3803651 to your computer and use it in GitHub Desktop.
bengou comics downloader (gevent, timeout)
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
# coding: utf-8 | |
import requests | |
import sys, os, re | |
from gevent import monkey, pool, Timeout | |
monkey.patch_all(dns=False) | |
p = pool.Pool(20) | |
TIMEOUT = 10 | |
title_p = re.compile(r'title>([^\]]*)</title') | |
base_p = re.compile(r"pic_base\s=\s'([^']*)'") | |
pics_p = re.compile(r"picTree\s=\s\[([^\]]*)\]") | |
cnt = None | |
sam = None | |
def download(url): | |
global cnt, sam | |
while True: | |
try: | |
r = requests.get(url) | |
break | |
except Exception as e: | |
print e.message | |
r.encoding = 'utf8' | |
html = r.text | |
title = title_p.findall(html)[0] | |
if not os.path.exists(title): | |
os.mkdir(title) | |
base = base_p.findall(html)[0] | |
if base[-1] != '/': | |
base += '/' | |
pics = pics_p.findall(html)[0].split(',') | |
pics = map(lambda x: x.strip('"'), pics) | |
cnt, sam = 0, len(pics) | |
origin = os.path.abspath('.') | |
os.chdir(title) | |
print cnt, '/', sam | |
for i, pic in enumerate(pics): | |
#dl(i, base+pic) | |
p.spawn(dl, i, base+pic) | |
p.join() | |
os.chdir(origin) | |
def dl(i, pic_url): | |
global cnt | |
filename = str(i) + pic_url[pic_url.rindex('.'):] | |
if not os.path.exists(filename): | |
while True: | |
try: | |
with Timeout(TIMEOUT) as timeout: | |
img = requests.get(pic_url).content | |
open(filename, 'wb').write(img) | |
break | |
except (Exception, Timeout) as e: | |
print e.message or 'timeout' | |
cnt += 1 | |
print cnt, '/', sam | |
if __name__ == '__main__': | |
if len(sys.argv) < 2: | |
print 'Useage:' | |
print __file__, '[url]' | |
exit() | |
url = sys.argv[1] | |
download(url) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment