museum crawling

#!/usr/bin/python
#-*- coding: utf-8 -*-
import urllib2
import urllib
from BeautifulSoup import BeautifulSoup
import re

#대충대충 갑시다.
def crawlMuseum(): #국립
	museumList = []
	result = []
	baseUrl="http://www.museum.or.kr/organ/"
	kind = ['국립','공립','사립','대학']
	print '목록 긁기'
	for i in range(len(kind)) :	# 1. 국립 2. 공립 3. 사립 4. 대학
		lst = [3,14,35,12] # 각 운영주체별 리스트 페이지 개수. 일단 대충 하드코딩.
		print kind[i]
		for j in range(lst[i]):
			print '페이지 %d'%j
			url = baseUrl+"museums01.php?cmdProc=listform&page=%d&orderByField=MuseumIntroduce_idx&orderBySort=DESC&MuseumIntroduce_kind=%d&sub_menu=%d"%(j+1,i+1,i+1)		
			#print url
		
			req = urllib2.Request(url)
			response = urllib2.urlopen(req,timeout=5)		
			# 파싱.
			html = unicode(response.read(),'cp949').encode('utf-8')
			#lst = re.findall('\\goList',html)
			#next = len(lst)-2				
			bs = BeautifulSoup(html)
			m = bs('td',{'class':'CommuniPd02'})
			for mm in m :
				href = mm('a')[0]['href']
				museumList.append(href)
	print '정보 긁기'
	for cnt,url in enumerate(museumList) :
		req = urllib2.Request(baseUrl+url)
		response = urllib2.urlopen(req,timeout=5)		
		# 파싱.
		html = unicode(response.read(),'cp949').encode('utf-8')
		bs = BeautifulSoup(html)
		name = bs('td',{'class':'DataFont01'})[0].string.strip()
		etc = bs('td',{'class':'PdTop5'})
		addr = etc[4].string.strip()
		print '%5d/%-5d\t%s,%s'%(cnt+1,len(museumList),name,addr)
		result.append([name,addr])
	print '파일 쓰기'
	with open('museum.csv','w') as f :
		#f.write('name|addr\n')
		for m in result :
			f.write(('M|%s|%s\n'%(m[0],m[1])).encode('utf-8'))

crawlMuseum()