Scraper para cinecenter.com.bo

cinecenter.py

import re
from urllib2 import Request, urlopen
from bs4 import BeautifulSoup as Soup

class Scraper(object):
	regions = dict(
		lapaz = 'La Paz',
		cochabamba = 'Cochabamba',
		santacruz = 'Santa Cruz'
	)

	base_url = 'http://cinecenter.com.bo'
	
	def __init__(self, region):
		if region not in self.regions:
			raise ValueError('region does not exist')
		
		self.region = region
		self.session = None
	
	def init_session(self):
		response = urlopen('%s/%s.html' % (self.base_url, self.region))
		
		headers = dict(response.info())
		
		assert 'set-cookie' in headers, 'no cookie header'
		
		header = headers['set-cookie']
		
		cname, cvalue = header.split(';')[0].strip().split('=')
		
		assert cname.strip().upper() == 'PHPSESSID', 'nope?'
		
		self.session = cvalue
		
		assert self.session is not None, 'session cookie could not be fetched'
	
	def session_request(self, *args, **kwargs):
		if self.session is None:
			self.init_session()
		
		request = Request(*args, **kwargs)
		
		cookie = 'PHPSESSID=' + self.session
		
		if 'Cookie' in request.headers:
			cookie = '%s; %s' % (request.headers['Cookie'], cookie)
		
		request.add_header('Cookie', cookie)
		
		return request
	
	def scrape(self):
		request = self.session_request(self.base_url + '/index.php?accion=getCartelera')
		
		response = urlopen(request)
		
		dom = Soup(response.read())
		
		title_re = re.compile('^PELICULA')
		
		for movie in dom('td', class_ = 'over_modul'):
			img = movie.find('img', title = title_re)
			
			title = img['title'].split('PELICULA:', 1)[-1].strip()
			
			horarios = movie.find('div', class_ = 'div_hint').get_text().strip().split('\n')
			
			normal = horarios[1]
			tresd = horarios[3]
			vip = horarios[5]
			
			print title.encode('utf-8')
			print 'Normal', normal
			print '3D', tresd
			
			print

if __name__ == '__main__':
	Scraper('santacruz').scrape()