get webtoon

output.txt

일곱개의 대죄 1권

001
http://i.imgur.com/zv7imF5.jpg
001
http://i.imgur.com/9HWsHyH.jpg
002
http://i.imgur.com/NJhen9i.jpg
003
http://i.imgur.com/b8GoFt6.jpg
004
http://i.imgur.com/FPKSYUf.jpg
005
http://i.imgur.com/uDFdnCS.jpg
006
http://i.imgur.com/QCvZQ7i.jpg
007
http://i.imgur.com/Ts7rVGd.jpg
008
http://i.imgur.com/GI5Yf46.jpg
009
http://i.imgur.com/IeSbDYY.jpg
010
http://i.imgur.com/5hAZ0X3.jpg
011
http://i.imgur.com/HUMQKH1.jpg
012
http://i.imgur.com/2fSKbSx.jpg
013
http://i.imgur.com/NJ36Bz4.jpg
014
http://i.imgur.com/7XrWdQa.jpg
015
http://i.imgur.com/m5QdQwt.jpg
016
http://i.imgur.com/eA9DtPU.jpg
017
http://i.imgur.com/GuvWiNp.jpg
018
http://i.imgur.com/iBlwv3d.jpg
019
http://i.imgur.com/XDmkTPv.jpg
020
http://i.imgur.com/mR6cbP8.jpg
021
http://i.imgur.com/kaS09eA.jpg
022
http://i.imgur.com/aaVzYVe.jpg
023
http://i.imgur.com/tE3MAAU.jpg
024
http://i.imgur.com/V1ER0np.jpg
025
http://i.imgur.com/Qq32pRq.jpg
026
http://i.imgur.com/wgPvMpM.jpg
027
http://i.imgur.com/7Dkmlay.jpg
028
http://i.imgur.com/QPpksWG.jpg
029
http://i.imgur.com/qcmFRwC.jpg
030
http://i.imgur.com/v5bbYg2.jpg
031
http://i.imgur.com/uYUa7IT.jpg
032
http://i.imgur.com/dvHgWsa.jpg
033
http://i.imgur.com/qkjcyJh.jpg
034
http://i.imgur.com/11i1pfL.jpg
035
http://i.imgur.com/lnqsOnv.jpg
036
http://i.imgur.com/tL8W8sW.jpg
037
http://i.imgur.com/LqBaC6o.jpg
038
http://i.imgur.com/7tXPouz.jpg
039
http://i.imgur.com/7pueWuQ.jpg
040
http://i.imgur.com/5zDobzX.jpg
041
http://i.imgur.com/3COQQFv.jpg
042
http://i.imgur.com/IwnIniW.jpg
043
http://i.imgur.com/CHk71vv.jpg
044
http://i.imgur.com/Ee9Phjh.jpg
045
http://i.imgur.com/uL5l93T.jpg
046
Traceback (most recent call last):
  File "webtoon_test.py", line 44, in <module>
    image.retrieve(d_link['href'], download_file)
  File "/usr/lib/python2.7/urllib.py", line 240, in retrieve
    fp = self.open(url, data)
  File "/usr/lib/python2.7/urllib.py", line 208, in open
    return getattr(self, name)(url)
  File "/usr/lib/python2.7/urllib.py", line 345, in open_http
    h.endheaders(data)
  File "/usr/lib/python2.7/httplib.py", line 969, in endheaders
    self._send_output(message_body)
  File "/usr/lib/python2.7/httplib.py", line 829, in _send_output
    self.send(msg)
  File "/usr/lib/python2.7/httplib.py", line 791, in send
    self.connect()
  File "/usr/lib/python2.7/httplib.py", line 772, in connect
    self.timeout, self.source_address)
  File "/usr/lib/python2.7/socket.py", line 571, in create_connection
    raise err
IOError: [Errno socket error] [Errno 111] Connection refused

webtoon_test.py

# coding: utf8
import urllib
from bs4 import BeautifulSoup
import os

HOST = 'http://zangsisi.tumblr.com/post/100002577940'
html = urllib.urlopen(HOST)
soup = BeautifulSoup(html)

book = 0
for link in soup.select('div.PostBody p a'):
	print
	print
	print link.get_text()
	print
	page_url = link['href']
	page = urllib.urlopen(page_url)
	soup2 = BeautifulSoup(page)

	book += 1
	str_book = '%0*d' % (3, book)
	print str_book
	print

	chapter = 0

	for d_link in soup2.select('div.PostBody div.wrapper div.image a.zoom'):
		
		print d_link['href']

		image = urllib.URLopener()

		download_path = '/tmp/webtoon/SevenSins/'+str_book
		try:
			os.stat(download_path)
		except:
			os.mkdir(download_path)

		chapter += 1
		str_chapter = '%0*d' % (3, chapter)
		print str_chapter

		download_file = download_path+'/'+str_chapter+'.jpg'
		image.retrieve(d_link['href'], download_file)