[PL] Pobieranie tytulow filmów z Filmweb.pl

filmweb.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import urllib
import sys
import os
import re

import unicodecsv as csv
from BeautifulSoup import BeautifulSoup

try:
	from cStringIO import StringIO
except:
	from StringIO import StringIO


class FilmwebTitile(object):

	def __init__(self, start=1):
		self.url   = "http://www.filmweb.pl/Film?id=%s"
		self.start = start
		self.stop  = 700000


	def get_info(self, id):
		try:
			soup   = BeautifulSoup(urllib.urlopen(self.url % id).read())
			titles = soup.find('div', attrs = {'class': 'filmTitle'})

			# Title
			try:
				title = titles.h1.text
			except Exception:
				title = None

			# Original Title
			try:
				original_title = titles.h2.text
			except Exception:
				original_title = None

			# Year
			try:
				year = titles.span.text.strip()[1:-1]
			except Exception:
				year = ''

			# Country
			try:
				countries = soup.findAll('a', href = re.compile(r'.*countryIds*'))
				countries = '|'.join([e.text for e in countries])
			except Exception:
				country = None

			if title and original_title and year and countries:
				return (title, original_title, year, countries,)
			return None

		except Exception, e:
			print("[ERROR]: %s" % e)
			return None


	def go(self, db_file):
		with open(db_file, "a") as myfile:
			for id in range(self.start, self.stop+1):
				csv_list = self.get_info(id)
				if csv_list:
					print "[%s] %s" %  (id, csv_list[0])
					myfile.write(self.csv_row(csv_list))


	def csv_row(self, row):
		csvfile   = StringIO()
		csvwriter = csv.writer(csvfile)
		csvwriter.writerow(row)
		return csvfile.getvalue()

if __name__ == '__main__':
	filmweb = FilmwebTitile()
	filmweb.go('filmweb.txt')